diff --git a/static/data/datasets.json b/static/data/datasets.json index 4e4f042..e208a53 100644 --- a/static/data/datasets.json +++ b/static/data/datasets.json @@ -1,67 +1,4 @@ [ - - { - "name": "apple_flower_segmentation", - "machine_learning_task": "semantic_segmentation", - "agricultural_task": "flower_segmentation", - "location": "United States, North America", - "sensor_modality": "RGB", - "real_or_synthetic": "real", - "platform": "ground", - "input_data_format": "JPG", - "annotation_format": "image", - "num_images": 148, - "documentation": "https://data.nal.usda.gov/dataset/data-multi-species-fruit-flower-detection-using-refined-semantic-segmentation-network", - "classes": "apple", - "stats_mean": [ - 0.458, - 0.479, - 0.405 - ], - "stats_std": [ - 0.204, - 0.193, - 0.216 - ], - "examples_image_url": "/img/agml/sample_images/apple_flower_segmentation_examples.webp", - "source": "agml", - "license": "US Public Domain", - "citation": "@ARTICLE{8392727,\n author={Dias, Philipe A. and Tabb, Amy and Medeiros, Henry},\n journal={IEEE Robotics and Automation Letters}, \n title={Multispecies Fruit Flower Detection Using a Refined Semantic Segmentation Network}, \n year={2018},\n volume={3},\n number={4},\n pages={3003-3010},\n doi={10.1109/LRA.2018.2849498}}", - "crop_types": [ - "apple" - ] - }, - { - "name": "apple_segmentation_minnesota", - "machine_learning_task": "semantic_segmentation", - "agricultural_task": "fruit_segmentation", - "location": "United States, North America", - "sensor_modality": "RGB", - "real_or_synthetic": "real", - "platform": "ground", - "input_data_format": "PNG", - "annotation_format": "image", - "num_images": 670, - "documentation": "https://rsn.umn.edu/projects/orchard-monitoring/minneapple", - "classes": "apple", - "stats_mean": [ - 0.374, - 0.437, - 0.338 - ], - "stats_std": [ - 0.263, - 0.288, - 0.331 - ], - "examples_image_url": "/img/agml/sample_images/apple_segmentation_minnesota_examples.webp", - "source": "agml", - "license": "MIT", - "citation": "@misc{hani2019minneapple,\n title={MinneApple: A Benchmark Dataset for Apple Detection and Segmentation},\n author={Nicolai Häni and Pravakar Roy and Volkan Isler}\n year={2019},\n eprint={1909.06441},\n archivePrefix={arXiv},\n primaryClass={cs.CV}\n}", - "crop_types": [ - "apple" - ] - }, { "name": "autonomous_greenhouse_regression", "machine_learning_task": null, @@ -85,270 +22,6 @@ "lettuce" ] }, - { - "name": "bean_synthetic_earlygrowth_aerial", - "machine_learning_task": "semantic_segmentation", - "agricultural_task": "plant_segmentation", - "location": "Digital, Digital", - "sensor_modality": "RGB", - "real_or_synthetic": "synthetic", - "platform": "aerial", - "input_data_format": "JPG", - "annotation_format": "image", - "num_images": 2500, - "documentation": "https://github.com/Project-AgML/AgML/blob/main/docs/datasets/bean_synthetic_earlygrowth_aerial.md", - "classes": "leaves, branches", - "stats_mean": null, - "stats_std": null, - "examples_image_url": "/img/agml/sample_images/bean_synthetic_earlygrowth_aerial_examples.webp", - "source": "agml", - "license": "MIT", - "citation": "@ARTICLE{10.3389/fpls.2019.01185,\n \nAUTHOR={Bailey, Brian N.}, \n\t \nTITLE={Helios: A Scalable 3D Plant and Environmental Biophysical Modeling Framework}, \n\t\nJOURNAL={Frontiers in Plant Science}, \n\t\nVOLUME={10}, \n\t\nYEAR={2019}, \n\t \nURL={https://www.frontiersin.org/article/10.3389/fpls.2019.01185}, \n\t\nDOI={10.3389/fpls.2019.01185}, \n\t\nISSN={1664-462X}, \n \nABSTRACT={This article presents an overview of Helios, a new three-dimensional (3D) plant and environmental modeling framework. Helios is a model coupling framework designed to provide maximum flexibility in integrating and running arbitrary 3D environmental system models. Users interact with Helios through a well-documented open-source C++ API. Version 1.0 comes with model plug-ins for radiation transport, the surface energy balance, stomatal conductance, photosynthesis, solar position, and procedural tree generation. Additional plug-ins are also available for visualizing model geometry and data and for processing and integrating LiDAR scanning data. Many of the plug-ins perform calculations on the graphics processing unit, which allows for efficient simulation of very large domains with high detail. An example modeling study is presented in which leaf-level heterogeneity in water usage and photosynthesis of an orchard is examined to understand how this leaf-scale variability contributes to whole-tree and -canopy fluxes.}\n}", - "crop_types": [ - "bean" - ] - }, - { - "name": "betel_leaf_disease_classification", - "machine_learning_task": "image_classification", - "agricultural_task": "betel_leaf_disease_classification", - "location": "Bangladesh, Asia", - "sensor_modality": "RGB", - "real_or_synthetic": "real", - "platform": "uav", - "input_data_format": "JPG", - "annotation_format": "directory_names", - "num_images": 3589, - "documentation": "https://www.semanticscholar.org/paper/Betel-Leaf-Diseases-Classification-using-Machine-A-David-Mukunthan/38208c9d2306444e3b9f8593715a46e2dcf26f44#paper-topics", - "classes": "Bacterial_Leaf_Disease, Dried_Leaf, Fungal_Brown_Spot_Disease, Healthy_Leaf", - "stats_mean": [ - 0.443, - 0.52, - 0.324 - ], - "stats_std": [ - 0.186, - 0.197, - 0.218 - ], - "examples_image_url": "/img/agml/sample_images/betel_leaf_disease_classification_examples.webp", - "source": "agml", - "license": "CC BY 4.0", - "citation": "Rashid, Mohammad Rifat Ahmmad; Hossain, Md. Miskat ; Biswas, Joy ; Majumder, Hredoy (2024), “Betel Leaf Image Dataset from Bangladesh”, Mendeley Data, V2, doi: 10.17632/g7fpgj57wc.2", - "crop_types": [ - "betel" - ] - }, - { - "name": "carrot_weeds_germany", - "machine_learning_task": "semantic_segmentation", - "agricultural_task": "weed_segmentation", - "location": "Germany, Europe", - "sensor_modality": "RGB", - "real_or_synthetic": "real", - "platform": "ground_mobile", - "input_data_format": "PNG", - "annotation_format": "image", - "num_images": 60, - "documentation": "https://github.com/cwfid/dataset", - "classes": "carrot, weeds", - "stats_mean": [ - 0.274, - 0.311, - 0.274 - ], - "stats_std": [ - 0.086, - 0.1, - 0.086 - ], - "examples_image_url": "/img/agml/sample_images/carrot_weeds_germany_examples.webp", - "source": "agml", - "license": "", - "citation": "@inproceedings{haug15,\n author={Haug, Sebastian and Ostermann, J{\\\"o}rn},\n title={A Crop/Weed Field Image Dataset for the Evaluation of Computer Vision Based Precision Agriculture Tasks},\n year={2015},\n booktitle={Computer Vision - ECCV 2014 Workshops},\n doi={10.1007/978-3-319-16220-1_8},\n url={http://dx.doi.org/10.1007/978-3-319-16220-1_8},\n pages={105--116}\n}", - "crop_types": [ - "carrot" - ] - }, - { - "name": "crop_weeds_greece", - "machine_learning_task": "image_classification", - "agricultural_task": "weed_classification", - "location": "Greece, Europe", - "sensor_modality": "RGB", - "real_or_synthetic": null, - "platform": "handheld", - "input_data_format": "JPG", - "annotation_format": "directory_names", - "num_images": 508, - "documentation": "https://github.com/AUAgroup/early-crop-weed", - "classes": "black_nightshade, velvet_leaf, cotton, tomato", - "stats_mean": [ - 0.725, - 0.669, - 0.544 - ], - "stats_std": [ - 0.164, - 0.153, - 0.138 - ], - "examples_image_url": "/img/agml/sample_images/crop_weeds_greece_examples.webp", - "source": "agml", - "license": "MIT", - "citation": "@article{ESPEJOGARCIA2020105306,\n title = {Towards weeds identification assistance through transfer learning},\n journal = {Computers and Electronics in Agriculture},\n volume = {171},\n pages = {105306},\n year = {2020},\n issn = {0168-1699},\n doi = {https://doi.org/10.1016/j.compag.2020.105306},\n url = {https://www.sciencedirect.com/science/article/pii/S0168169919319854},\n author = {Borja Espejo-Garcia and Nikos Mylonas and Loukas Athanasakos and Spyros Fountas and Ioannis Vasilakoglou},\n keywords = {Weed identification, Deep learning, Transfer learning, Open data, Precision agriculture},\n abstract = {Reducing the use of pesticides through selective spraying is an important component towards a more sustainable computer-assisted agriculture. Weed identification at early growth stage contributes to reduced herbicide rates. However, while computer vision alongside deep learning have overcome the performance of approaches that use hand-crafted features, there are still some open challenges in the development of a reliable automatic plant identification system. These type of systems have to take into account different sources of variability, such as growth stages and soil conditions, with the added constraint of the limited size of usual datasets. This study proposes a novel crop/weed identification system that relies on a combination of fine-tuning pre-trained convolutional networks (Xception, Inception-Resnet, VGNets, Mobilenet and Densenet) with the “traditional” machine learning classifiers (Support Vector Machines, XGBoost and Logistic Regression) trained with the previously deep extracted features. The aim of this approach was to avoid overfitting and to obtain a robust and consistent performance. To evaluate this approach, an open access dataset of two crop [tomato (Solanum lycopersicum L.) and cotton (Gossypium hirsutum L.)] and two weed species [black nightshade (Solanum nigrum L.) and velvetleaf (Abutilon theophrasti Medik.)] was generated. The pictures were taken by different production sites across Greece under natural variable light conditions from RGB cameras. The results revealed that a combination of fine-tuned Densenet and Support Vector Machine achieved a micro F1 score of 99.29% with a very low performance difference between train and test sets. Other evaluated approaches also obtained repeatedly more than 95% F1 score. Additionally, our results analysis provides some heuristics for designing transfer-learning based systems to avoid overfitting without decreasing performance.}\n}", - "crop_types": [ - "cotton", - "tomato" - ] - }, - { - "name": "grape_detection_californiaday", - "machine_learning_task": "object_detection", - "agricultural_task": "fruit_detection", - "location": "United States, North America", - "sensor_modality": "RGB", - "real_or_synthetic": "real", - "platform": "ground", - "input_data_format": "JPG", - "annotation_format": "image", - "num_images": 126, - "documentation": null, - "classes": "grape", - "stats_mean": [ - 0.446, - 0.464, - 0.275 - ], - "stats_std": [ - 0.268, - 0.259, - 0.263 - ], - "examples_image_url": "/img/agml/sample_images/grape_detection_californiaday_examples.webp", - "source": "agml", - "license": "", - "citation": "@misc{GrapeDay,\n author = {Plant AI and Biophysics Lab},\n title = {Grape Detection 2019 Day},\n year = {2019},\n url = {https://github.com/plant-ai-biophysics-lab/AgML} \n ", - "crop_types": [ - "grape" - ] - }, - { - "name": "grape_detection_californianight", - "machine_learning_task": "object_detection", - "agricultural_task": "fruit_detection", - "location": "United States, North America", - "sensor_modality": "RGB", - "real_or_synthetic": "real", - "platform": "ground", - "input_data_format": "JPG", - "annotation_format": "image", - "num_images": 150, - "documentation": null, - "classes": "grape", - "stats_mean": [ - 0.222, - 0.213, - 0.225 - ], - "stats_std": [ - 0.205, - 0.201, - 0.206 - ], - "examples_image_url": "/img/agml/sample_images/grape_detection_californianight_examples.webp", - "source": "agml", - "license": "", - "citation": "@misc{GrapeNight,\n author = {Plant AI and Biophysics Lab},\n title = {Grape Detection 2020 Night},\n year = {2020},\n url = {https://github.com/plant-ai-biophysics-lab/AgML} \n ", - "crop_types": [ - "grape" - ] - }, - { - "name": "grape_detection_syntheticday", - "machine_learning_task": "object_detection", - "agricultural_task": "fruit_detection", - "location": "United States, North America", - "sensor_modality": "RGB", - "real_or_synthetic": "synthetic", - "platform": "ground", - "input_data_format": "JPG", - "annotation_format": "coco_json", - "num_images": 448, - "documentation": "N/A", - "classes": "grape", - "stats_mean": [ - 0.25, - 0.276, - 0.207 - ], - "stats_std": [ - 0.151, - 0.186, - 0.224 - ], - "examples_image_url": "/img/agml/sample_images/grape_detection_syntheticday_examples.webp", - "source": "agml", - "license": "", - "citation": "@ARTICLE{10.3389/fpls.2019.01185,\n \nAUTHOR={Bailey, Brian N.}, \n\t \nTITLE={Helios: A Scalable 3D Plant and Environmental Biophysical Modeling Framework}, \n\t\nJOURNAL={Frontiers in Plant Science}, \n\t\nVOLUME={10}, \n\t\nYEAR={2019}, \n\t \nURL={https://www.frontiersin.org/article/10.3389/fpls.2019.01185}, \n\t\nDOI={10.3389/fpls.2019.01185}, \n\t\nISSN={1664-462X}, \n \nABSTRACT={This article presents an overview of Helios, a new three-dimensional (3D) plant and environmental modeling framework. Helios is a model coupling framework designed to provide maximum flexibility in integrating and running arbitrary 3D environmental system models. Users interact with Helios through a well-documented open-source C++ API. Version 1.0 comes with model plug-ins for radiation transport, the surface energy balance, stomatal conductance, photosynthesis, solar position, and procedural tree generation. Additional plug-ins are also available for visualizing model geometry and data and for processing and integrating LiDAR scanning data. Many of the plug-ins perform calculations on the graphics processing unit, which allows for efficient simulation of very large domains with high detail. An example modeling study is presented in which leaf-level heterogeneity in water usage and photosynthesis of an orchard is examined to understand how this leaf-scale variability contributes to whole-tree and -canopy fluxes.}\n}", - "crop_types": [ - "grape" - ] - }, - { - "name": "growliflower_cauliflower_segmentation", - "machine_learning_task": "semantic_segmentation", - "agricultural_task": "crop_segmentation", - "location": "Worldwide", - "sensor_modality": "RGB", - "real_or_synthetic": "real", - "platform": "handheld/ground", - "input_data_format": "JPG", - "annotation_format": "image", - "num_images": 1542, - "documentation": "https://phenoroam.phenorob.de/geonetwork/srv/eng/catalog.search#/metadata/cb328232-31f5-4b84-a929-8e1ee551d66a", - "classes": "maskLeaves, maskPlants, maskStems, maskVoid", - "stats_mean": null, - "stats_std": null, - "examples_image_url": "/img/agml/sample_images/growliflower_cauliflower_segmentation_examples.webp", - "source": "agml", - "license": "", - "citation": "Kierdorf, Jana & Junker-Frohn, Laura & Delaney, Mike & Olave, Mariele & Burkart, Andreas & Jaenicke, Hannah & Muller, Onno & Roscher, Ribana. (2022). GrowliFlower: An image time‐series dataset for GROWth analysis of cauLIFLOWER. Journal of Field Robotics. 40. 10.1002/rob.22122. ", - "crop_types": [ - "cauliflower" - ] - }, - { - "name": "guava_disease_pakistan", - "machine_learning_task": "image_classification", - "agricultural_task": "disease_classification", - "location": "Pakistan, Asia", - "sensor_modality": "RGB", - "real_or_synthetic": null, - "platform": "ground", - "input_data_format": "JPG", - "annotation_format": "directory_names", - "num_images": 306, - "documentation": "https://data.mendeley.com/datasets/s8x6jn5cvr/1", - "classes": "Canker, Dot, Mummification, Rust", - "stats_mean": [ - 0.446, - 0.451, - 0.323 - ], - "stats_std": [ - 0.187, - 0.184, - 0.187 - ], - "examples_image_url": "/img/agml/sample_images/guava_disease_pakistan_examples.webp", - "source": "agml", - "license": "", - "citation": "@article{Rauf_Lali_2021, \n title={A Guava Fruits and Leaves Dataset for Detection and Classification of Guava Diseases through Machine Learning}, \n volume={1}, \n url={https://data.mendeley.com/datasets/s8x6jn5cvr/1}, \n DOI={10.17632/s8x6jn5cvr.1}, \n abstractNote={(1) Plant diseases are the primary cause of reduced productivity in agriculture, which results in economic losses. Guava is a big source of nutrients for humans all over the world. Guava diseases, on the other hand, harm the yield and quality of the crop. (2) For the identification and classification of plant diseases, computer vision and image processing methods have been commonly used. (3) The dataset includes an image gallery of healthy and unhealthy Guava fruits and leaves that could be used by researchers to adopt advanced computer vision techniques to protect plants from disease. Dot, Canker, Mummification, and Rust are the diseases targeted in the data sets. (4) The dataset contains 306 images of healthy and unhealthy images for both Guava fruits and leaves collectively. Each image contains 6000 * 4000 dimensions with 300 dpi resolution. (5) All images were acquired from the tropical areas of Pakistan under the supervision of Prof. Dr. Ikramullah Lali. (6) All images were annotated manually by the domain expert such as For Guava fruits and leaves; Dot (76), Canker (77), Mummification (83), and Rust (70) Note: The data labeling was manual and can be updated by automatic labeling through machine learning. In the meantime, the authors can also use the data set for the clustering problem.}, \n author={Rauf, Hafiz Tayyab and Lali, Muhammad Ikram Ullah}, \n year={2021}, month={Apr} \n}\n", - "crop_types": [ - "guava" - ] - }, { "name": "iNatAg", "machine_learning_task": "image_classification", @@ -124656,37 +124329,6 @@ "citation": "@Article{s18051580,\n author = {Teimouri, Nima and Dyrmann, Mads and Nielsen, Per Rydahl and Mathiassen, Solvejg Kopp and Somerville, Gayle J. and Jørgensen, Rasmus Nyholm},\n title = {Weed Growth Stage Estimator Using Deep Convolutional Neural Networks},\n journal = {Sensors},\n volume = {18},\n year = {2018},\n number = {5},\n url = {http://www.mdpi.com/1424-8220/18/5/1580},\n issn = {1424-8220}\n}", "crop_types": null }, - { - "name": "mango_detection_australia", - "machine_learning_task": "object_detection", - "agricultural_task": "fruit_detection", - "location": "Australia, Oceania", - "sensor_modality": "RGB", - "real_or_synthetic": "real", - "platform": "handheld", - "input_data_format": "JPG", - "annotation_format": "coco_json", - "num_images": 1730, - "documentation": "https://researchdata.edu.au/mangoyolo-set/1697505", - "classes": "mango", - "stats_mean": [ - 0.073, - 0.119, - 0.05 - ], - "stats_std": [ - 0.059, - 0.079, - 0.043 - ], - "examples_image_url": "/img/agml/sample_images/mango_detection_australia_examples.webp", - "source": "agml", - "license": "", - "citation": "@Misc{Koirala2019,\n author={Koirala, Anand and Walsh, Kerry and Wang, Z. and McCarthy, C.},\n title={MangoYOLO data set},\n year={2019},\n month={2021},\n day={10-19},\n publisher={Central Queensland University},\n keywords={Mango images; Fruit detection; Yield estimation; Mango; Agricultural Land Management; Horticultural Crop Growth and Development},\n abstract={Datasets and directories are structured similar to the PASCAL VOC dataset, avoiding the need to change scripts already available, with the detection frameworks ready to parse PASCAL VOC annotations into their format. The sub-directory JPEGImages consist of 1730 images (612x512 pixels) used for train, test and validation. Each image has at least one annotated fruit. The sub-directory Annotations consists of all the annotation files (record of bounding box coordinates for each image) in xml format and have the same name as the image name. The sub-directory Main consists of the text file that contains image names (without extension) used for train, test and validation. Training set (train.txt) lists 1300 train images Validation set (val.txt) lists 130 validation images Test set (test.txt) lists 300 test images Each image has an XML annotation file (filename = image name) and each image set (training validation and test set) has associated text files (train.txt, val.txt and test.txt) containing the list of image names to be used for training and testing. The XML annotation file contains the image attributes (name, width, height), the object attributes (class name, object bounding box co-ordinates (xmin, ymin, xmax, ymax)). (xmin, ymin) and (xmax, ymax) are the pixel co-ordinates of the bounding box's top-left corner and bottom-right corner respectively.},\n note={CC-BY-4.0},\n url={https://figshare.com/articles/dataset/MangoYOLO_data_set/13450661, https://researchdata.edu.au/mangoyolo-set},\n language={English}\n}", - "crop_types": [ - "mango" - ] - }, { "name": "papaya_leaf_disease_classification", "machine_learning_task": "image_classification", @@ -124710,524 +124352,6 @@ "papaya" ] }, - { - "name": "peachpear_flower_segmentation", - "machine_learning_task": "semantic_segmentation", - "agricultural_task": "flower_segmentation", - "location": "Worldwide", - "sensor_modality": null, - "real_or_synthetic": null, - "platform": null, - "input_data_format": null, - "annotation_format": null, - "num_images": 42, - "documentation": "https://data.nal.usda.gov/dataset/data-multi-species-fruit-flower-detection-using-refined-semantic-segmentation-network", - "classes": "Flower", - "stats_mean": [ - 0.438, - 0.435, - 0.415 - ], - "stats_std": [ - 0.208, - 0.214, - 0.244 - ], - "examples_image_url": "/img/agml/sample_images/peachpear_flower_segmentation_examples.webp", - "source": "agml", - "license": "US Public Domain", - "citation": "@ARTICLE{8392727,\n author={Dias, Philipe A. and Tabb, Amy and Medeiros, Henry},\n journal={IEEE Robotics and Automation Letters}, \n title={Multispecies Fruit Flower Detection Using a Refined Semantic Segmentation Network}, \n year={2018},\n volume={3},\n number={4},\n pages={3003-3010},\n doi={10.1109/LRA.2018.2849498}}", - "crop_types": [ - "peach", - "pear" - ] - }, - { - "name": "plant_doc_classification", - "machine_learning_task": "image_classification", - "agricultural_task": "disease_classification", - "location": "Worldwide", - "sensor_modality": "RGB", - "real_or_synthetic": "real", - "platform": "ground", - "input_data_format": "JPG", - "annotation_format": "directory_names", - "num_images": 2598, - "documentation": "https://github.com/pratikkayal/PlantDoc-Dataset", - "classes": "Corn leaf blight, Tomato Early blight leaf, Potato leaf early blight, Potato leaf late blight, Blueberry leaf, grape leaf black rot, Bell_pepper leaf spot, Cherry leaf, Peach leaf, Soyabean leaf, Strawberry leaf, Apple Scab Leaf, Corn rust leaf, Apple leaf, Corn Gray leaf spot, Tomato leaf mosaic virus, Tomato mold leaf, Tomato leaf yellow virus, Tomato leaf bacterial spot, Tomato leaf late blight, Squash Powdery mildew leaf, Bell_pepper leaf, grape leaf, Apple rust leaf, Tomato Septoria leaf spot, Tomato leaf, Raspberry leaf, Tomato two spotted spider mites leaf", - "stats_mean": [ - 0.482, - 0.55, - 0.383 - ], - "stats_std": [ - 0.212, - 0.204, - 0.221 - ], - "examples_image_url": "/img/agml/sample_images/plant_doc_classification_examples.webp", - "source": "agml", - "license": "CC BY-SA 4.0", - "citation": "@inproceedings{10.1145/3371158.3371196,\n author = {Singh, Davinder and Jain, Naman and Jain, Pranjali and Kayal, Pratik and Kumawat, Sudhakar and Batra, Nipun},\n title = {PlantDoc: A Dataset for Visual Plant Disease Detection},\n year = {2020},\n isbn = {9781450377386},\n publisher = {Association for Computing Machinery},\n address = {New York, NY, USA},\n url = {https://doi.org/10.1145/3371158.3371196},\n doi = {10.1145/3371158.3371196},\n booktitle = {Proceedings of the 7th ACM IKDD CoDS and 25th COMAD},\n pages = {249–253},\n numpages = {5},\n keywords = {Deep Learning, Object Detection, Image Classification},\n location = {Hyderabad, India},\n series = {CoDS COMAD 2020}\n }", - "crop_types": null - }, - { - "name": "plant_doc_detection", - "machine_learning_task": "object_detection", - "agricultural_task": "disease_classification", - "location": "Worldwide", - "sensor_modality": "RGB", - "real_or_synthetic": "real", - "platform": "ground", - "input_data_format": "JPG", - "annotation_format": "coco_json", - "num_images": 2346, - "documentation": "https://github.com/pratikkayal/PlantDoc-Object-Detection-Dataset", - "classes": "Corn leaf blight, Tomato Early blight leaf, Potato leaf early blight, Potato leaf late blight, Blueberry leaf, grape leaf black rot, Bell_pepper leaf spot, Cherry leaf, Peach leaf, Soyabean leaf, Strawberry leaf, Apple Scab Leaf, Corn rust leaf, Apple leaf, Corn Gray leaf spot, Tomato leaf mosaic virus, Tomato mold leaf, Tomato leaf yellow virus, Tomato leaf bacterial spot, Tomato leaf late blight, Squash Powdery mildew leaf, Bell_pepper leaf, grape leaf, Apple rust leaf, Tomato Septoria leaf spot, Tomato leaf, Raspberry leaf, Potato leaf, Tomato two spotted spider mites leaf", - "stats_mean": [ - 0.477, - 0.544, - 0.378 - ], - "stats_std": [ - 0.211, - 0.204, - 0.218 - ], - "examples_image_url": "/img/agml/sample_images/plant_doc_detection_examples.webp", - "source": "agml", - "license": "CC BY-SA 4.0", - "citation": "@inproceedings{10.1145/3371158.3371196,\n author = {Singh, Davinder and Jain, Naman and Jain, Pranjali and Kayal, Pratik and Kumawat, Sudhakar and Batra, Nipun},\n title = {PlantDoc: A Dataset for Visual Plant Disease Detection},\n year = {2020},\n isbn = {9781450377386},\n publisher = {Association for Computing Machinery},\n address = {New York, NY, USA},\n url = {https://doi.org/10.1145/3371158.3371196},\n doi = {10.1145/3371158.3371196},\n booktitle = {Proceedings of the 7th ACM IKDD CoDS and 25th COMAD},\n pages = {249–253},\n numpages = {5},\n keywords = {Deep Learning, Object Detection, Image Classification},\n location = {Hyderabad, India},\n series = {CoDS COMAD 2020}\n }", - "crop_types": null - }, - { - "name": "plant_seedlings_aarhus", - "machine_learning_task": "image_classification", - "agricultural_task": "weed_classification", - "location": "Denmark, Europe", - "sensor_modality": "RGB", - "real_or_synthetic": "real", - "platform": "ground_fixed", - "input_data_format": "PNG", - "annotation_format": "directory_names", - "num_images": 5539, - "documentation": "https://vision.eng.au.dk/plant-seedlings-dataset/", - "classes": "maize, common_wheat, sugar_beet, scentless_mayweed, common_chickweed, shepherds_purse, cleavers, charlock, fat_hen, smallflowered_cranesbill, black_grass, loose_silkybent", - "stats_mean": [ - 0.329, - 0.289, - 0.207 - ], - "stats_std": [ - 0.093, - 0.096, - 0.106 - ], - "examples_image_url": "/img/agml/sample_images/plant_seedlings_aarhus_examples.webp", - "source": "agml", - "license": "CC BY-SA 4.0", - "citation": "@article{Giselsson2017,\n author = {Giselsson, Thomas Mosgaard and Dyrmann, Mads and J{\\o}rgensen, Rasmus Nyholm and Jensen, Peter Kryger and Midtiby, Henrik Skov},\n journal = {arXiv preprint},\n keywords = {benchmark,database,plant seedlings,segmentation,site-specific weed control},\n title = {{A Public Image Database for Benchmark of Plant Seedling Classification Algorithms}},\n year = {2017}\n}", - "crop_types": null - }, - { - "name": "plant_village_classification", - "machine_learning_task": "image_classification", - "agricultural_task": "disease_classification", - "location": "United States, North America", - "sensor_modality": "RGB", - "real_or_synthetic": "real", - "platform": "ground", - "input_data_format": "JPG", - "annotation_format": "directory_names", - "num_images": 55448, - "documentation": "https://github.com/spMohanty/PlantVillage-Dataset", - "classes": "Apple___Apple_scab, Apple___Black_rot, Apple___Cedar_apple_rust, Apple___healthy, Background_without_leaves, Blueberry___healthy, Cherry___Powdery_mildew, Cherry___healthy, Corn___Cercospora_leaf_spot Gray_leaf_spot, Corn___Common_rust, Corn___Northern_Leaf_Blight, Corn___healthy, Grape___Black_rot, Grape___Esca_(Black_Measles), Grape___Leaf_blight_(Isariopsis_Leaf_Spot), Grape___healthy, Orange___Haunglongbing_(Citrus_greening), Peach___Bacterial_spot, Peach___healthy, Pepper,_bell___Bacterial_spot, Pepper,_bell___healthy, Potato___Early_blight, Potato___Late_blight, Potato___healthy, Raspberry___healthy, Soybean___healthy, Squash___Powdery_mildew, Strawberry___Leaf_scorch, Strawberry___healthy, Tomato___Bacterial_spot, Tomato___Early_blight, Tomato___Late_blight, Tomato___Leaf_Mold, Tomato___Septoria_leaf_spot, Tomato___Spider_mites Two-spotted_spider_mite, Tomato___Target_Spot, Tomato___Tomato_Yellow_Leaf_Curl_Virus, Tomato___Tomato_mosaic_virus, Tomato___healthy", - "stats_mean": [ - 0.467, - 0.489, - 0.412 - ], - "stats_std": [ - 0.177, - 0.152, - 0.194 - ], - "examples_image_url": "/img/agml/sample_images/plant_village_classification_examples.webp", - "source": "agml", - "license": "", - "citation": "@article{DBLP:journals/corr/HughesS15,\n author = {David P. Hughes and\n Marcel Salath{'{e} } },\n title = {An open access repository of images on plant health to enable the\n development of mobile disease diagnostics through machine\n learning and crowdsourcing},\n journal = {CoRR},\n volume = {abs/1511.08060},\n year = {2015},\n url = {http://arxiv.org/abs/1511.08060},\n archivePrefix = {arXiv},\n eprint = {1511.08060},\n timestamp = {Mon, 13 Aug 2018 16:48:21 +0200},\n biburl = {https://dblp.org/rec/bib/journals/corr/HughesS15},\n bibsource = {dblp computer science bibliography, https://dblp.org}\n}", - "crop_types": null - }, - { - "name": "rangeland_weeds_australia", - "machine_learning_task": "image_classification", - "agricultural_task": "weed_classification", - "location": "Australia, Oceania", - "sensor_modality": "RGB", - "real_or_synthetic": "real", - "platform": "ground", - "input_data_format": "JPG", - "annotation_format": "directory_names", - "num_images": 17509, - "documentation": "https://github.com/AlexOlsen/DeepWeeds", - "classes": "chinee_apple, lantana, negative, parkinsonia, parthenium, prickly_acacia, rubber_vine, siam_weed, snake_weed", - "stats_mean": [ - 0.379, - 0.39, - 0.38 - ], - "stats_std": [ - 0.224, - 0.225, - 0.223 - ], - "examples_image_url": "/img/agml/sample_images/rangeland_weeds_australia_examples.webp", - "source": "agml", - "license": "CC BY-SA 4.0", - "citation": "@Article{Olsen2019,\n author={Olsen, Alex and Konovalov, Dmitry A. and Philippa, Bronson and Ridd, Peter and Wood, Jake C. and Johns, Jamie and Banks, Wesley and Girgenti, Benjamin and Kenny, Owen and Whinney, James and Calvert, Brendan and Azghadi, Mostafa Rahimi and White, Ronald D.},\n title={DeepWeeds: A Multiclass Weed Species Image Dataset for Deep Learning},\n journal={Scientific Reports},\n year={2019},\n month={Feb},\n day={14},\n volume={9},\n number={1},\n pages={2058},\n abstract={Robotic weed control has seen increased research of late with its potential for boosting productivity in agriculture. Majority of works focus on developing robotics for croplands, ignoring the weed management problems facing rangeland stock farmers. Perhaps the greatest obstacle to widespread uptake of robotic weed control is the robust classification of weed species in their natural environment. The unparalleled successes of deep learning make it an ideal candidate for recognising various weed species in the complex rangeland environment. This work contributes the first large, public, multiclass image dataset of weed species from the Australian rangelands; allowing for the development of robust classification methods to make robotic weed control viable. The DeepWeeds dataset consists of 17,509 labelled images of eight nationally significant weed species native to eight locations across northern Australia. This paper presents a baseline for classification performance on the dataset using the benchmark deep learning models, Inception-v3 and ResNet-50. These models achieved an average classification accuracy of 95.1{\\%} and 95.7{\\%}, respectively. We also demonstrate real time performance of the ResNet-50 architecture, with an average inference time of 53.4 ms per image. These strong results bode well for future field implementation of robotic weed control methods in the Australian rangelands.},\n issn={2045-2322},\n doi={10.1038/s41598-018-38343-3},\n url={https://doi.org/10.1038/s41598-018-38343-3}\n}", - "crop_types": null - }, - { - "name": "red_grapes_and_leaves_segmentation", - "machine_learning_task": "semantic_segmentation", - "agricultural_task": "vineyard_scene_segmentation", - "location": "Greece, Europe", - "sensor_modality": "RGB", - "real_or_synthetic": "real", - "platform": "handheld/ground", - "input_data_format": "JPG", - "annotation_format": "image", - "num_images": 258, - "documentation": "https://link.springer.com/chapter/10.1007/978-3-030-48791-1_22", - "classes": "Leaf, Grape", - "stats_mean": [ - 0.392, - 0.493, - 0.525 - ], - "stats_std": [ - 0.272, - 0.287, - 0.283 - ], - "examples_image_url": "/img/agml/sample_images/red_grapes_and_leaves_segmentation_examples.webp", - "source": "agml", - "license": "", - "citation": "@inproceedings{kalampokas2020semantic,\n title={Semantic segmentation of vineyard images using convolutional neural networks},\n author={Kalampokas, Theofanis and Tziridis, Konstantinos and Nikolaou, Alexandros and Vrochidou, Eleni and Papakostas, George A and Pachidis, Theodore and Kaburlasos, Vassilis G},\n booktitle={International Conference on Engineering Applications of Neural Networks},\n pages={292--303},\n year={2020},\n organization={Springer}}", - "crop_types": [ - "grape" - ] - }, - { - "name": "rice_leaf_disease_classification", - "machine_learning_task": "image_classification", - "agricultural_task": "rice_leaf_disease_classification", - "location": "Worldwide", - "sensor_modality": "RGB", - "real_or_synthetic": "real", - "platform": "uav", - "input_data_format": "JPG", - "annotation_format": "directory_names", - "num_images": 3829, - "documentation": "https://www.kaggle.com/datasets/anshulm257/rice-disease-dataset/data", - "classes": "Bacterial_Leaf_Blight, Brown_Spot, Healthy_Rice_Leaf, Leaf_Blast, Leaf_Scald, Sheath_Blight", - "stats_mean": [ - 0.38, - 0.511, - 0.245 - ], - "stats_std": [ - 0.186, - 0.175, - 0.135 - ], - "examples_image_url": "/img/agml/sample_images/rice_leaf_disease_classification_examples.webp", - "source": "agml", - "license": "", - "citation": "", - "crop_types": [ - "rice" - ] - }, - { - "name": "rice_seedling_segmentation", - "machine_learning_task": "semantic_segmentation", - "agricultural_task": "weed_segmentation", - "location": "China, Asia", - "sensor_modality": "RGB", - "real_or_synthetic": "real", - "platform": "handheld", - "input_data_format": "JPG", - "annotation_format": "image", - "num_images": 224, - "documentation": "https://github.com/kabbas570/CED-Net-Crops-and-Weeds-Segmentation-for-Smart-Farming-Using-a-Small-Cascaded-Encoder-Decoder-Archi", - "classes": "Rice, Weed", - "stats_mean": [ - 0.655, - 0.701, - 0.635 - ], - "stats_std": [ - 0.085, - 0.108, - 0.111 - ], - "examples_image_url": "/img/agml/sample_images/rice_seedling_segmentation_examples.webp", - "source": "agml", - "license": "", - "citation": "@Article{electronics9101602,\n AUTHOR = {Khan, Abbas and Ilyas, Talha and Umraiz, Muhammad and Mannan, Zubaer Ibna and Kim, Hyongsuk},\n TITLE = {CED-Net: Crops and Weeds Segmentation for Smart Farming Using a Small Cascaded Encoder-Decoder Architecture},\n JOURNAL = {Electronics},\n VOLUME = {9},\n YEAR = {2020},\n NUMBER = {10},\n ARTICLE-NUMBER = {1602},\n URL = {https://www.mdpi.com/2079-9292/9/10/1602},\n ISSN = {2079-9292},\n ABSTRACT = {Convolutional neural networks (CNNs) have achieved state-of-the-art performance in numerous aspects of human life and the agricultural sector is no exception. One of the main objectives of deep learning for smart farming is to identify the precise location of weeds and crops on farmland. In this paper, we propose a semantic segmentation method based on a cascaded encoder-decoder network, namely CED-Net, to differentiate weeds from crops. The existing architectures for weeds and crops segmentation are quite deep, with millions of parameters that require longer training time. To overcome such limitations, we propose an idea of training small networks in cascade to obtain coarse-to-fine predictions, which are then combined to produce the final results. Evaluation of the proposed network and comparison with other state-of-the-art networks are conducted using four publicly available datasets: rice seeding and weed dataset, BoniRob dataset, carrot crop vs. weed dataset, and a paddy–millet dataset. The experimental results and their comparisons proclaim that the proposed network outperforms state-of-the-art architectures, such as U-Net, SegNet, FCN-8s, and DeepLabv3, over intersection over union (IoU), F1-score, sensitivity, true detection rate, and average precision comparison metrics by utilizing only (1/5.74 × U-Net), (1/5.77 × SegNet), (1/3.04 × FCN-8s), and (1/3.24 × DeepLabv3) fractions of total parameters.},\n DOI = {10.3390/electronics9101602}\n}", - "crop_types": [ - "rice" - ] - }, - { - "name": "riseholme_strawberry_classification_2021", - "machine_learning_task": "image_classification", - "agricultural_task": "disease_classification", - "location": null, - "sensor_modality": "RGB", - "real_or_synthetic": "real", - "platform": "ground", - "input_data_format": "PNG", - "annotation_format": "directory_names", - "num_images": 3520, - "documentation": "https://github.com/ctyeong/Riseholme-2021", - "classes": "anomalous, occluded, ripe, unripe", - "stats_mean": [ - 0.575, - 0.464, - 0.364 - ], - "stats_std": [ - 0.198, - 0.192, - 0.177 - ], - "examples_image_url": "/img/agml/sample_images/riseholme_strawberry_classification_2021_examples.webp", - "source": "agml", - "license": "", - "citation": "@inproceedings{CWSC21,\n title={Self-supervised Representation Learning for Reliable Robotic Monitoring of Fruit Anomalies},\n author={Choi, Taeyeong and Would, Owen and Salazar-Gomez, Adrian and Cielniak, Grzegorz},\n booktitle={2022 International Conference on Robotics and Automation (ICRA)},\n pages={2266--2272},\n year={2022},\n organization={IEEE}\n}", - "crop_types": [ - "strawberry" - ] - }, - { - "name": "soybean_insect_classification", - "machine_learning_task": "image_classification", - "agricultural_task": "pest_classification", - "location": "Brazil, South America", - "sensor_modality": "RGB", - "real_or_synthetic": "real", - "platform": "uav", - "input_data_format": "JPG", - "annotation_format": "directory_names", - "num_images": 6410, - "documentation": "https://data.mendeley.com/datasets/bycbh73438/1", - "classes": "Caterpillar, Diabrotica_speciosa, Healthy", - "stats_mean": [ - 0.413, - 0.516, - 0.335 - ], - "stats_std": [ - 0.22, - 0.23, - 0.203 - ], - "examples_image_url": "/img/agml/sample_images/soybean_insect_classification_examples.webp", - "source": "agml", - "license": "CC BY 4.0", - "citation": "Mignoni, Maria Eloisa (2021), “Images of Soybean Leaves”, Mendeley Data, V1, doi: 10.17632/bycbh73438.1", - "crop_types": [ - "soybean" - ] - }, - { - "name": "soybean_weed_uav_brazil", - "machine_learning_task": "image_classification", - "agricultural_task": "weed_classification", - "location": "Brazil, South America", - "sensor_modality": "RGB", - "real_or_synthetic": "real", - "platform": "uav", - "input_data_format": "tif", - "annotation_format": "directory_names", - "num_images": 15336, - "documentation": "https://data.mendeley.com/datasets/3fmjm7ncc6/2", - "classes": "broadleaf, grass, soil, soybean", - "stats_mean": [ - 0.329, - 0.334, - 0.187 - ], - "stats_std": [ - 0.245, - 0.249, - 0.157 - ], - "examples_image_url": "/img/agml/sample_images/soybean_weed_uav_brazil_examples.webp", - "source": "agml", - "license": "CC BY-NC 3.0", - "citation": "dos Santos Ferreira, Alessandro; Pistori, Hemerson; Matte Freitas, Daniel; Gonçalves da Silva, Gercina (2017), “Data for: Weed Detection in Soybean Crops Using ConvNets”, Mendeley Data, V2, doi: 10.17632/3fmjm7ncc6.2", - "crop_types": [ - "soybean" - ] - }, - { - "name": "strawberry_detection_2022", - "machine_learning_task": "object_detection", - "agricultural_task": "strawberry_detection", - "location": "Worldwide", - "sensor_modality": "RGB", - "real_or_synthetic": "real", - "platform": "handheld/ground", - "input_data_format": "JPG", - "annotation_format": "coco_json", - "num_images": 175, - "documentation": null, - "classes": "strawberry, flower, green, large_white, pink, red, small_white", - "stats_mean": [ - 0.288, - 0.306, - 0.299 - ], - "stats_std": [ - 0.21, - 0.199, - 0.205 - ], - "examples_image_url": "/img/agml/sample_images/strawberry_detection_2022_examples.webp", - "source": "agml", - "license": "CC BY 4.0", - "citation": "", - "crop_types": [ - "strawberry" - ] - }, - { - "name": "strawberry_detection_2023", - "machine_learning_task": "object_detection", - "agricultural_task": "strawberry_detection", - "location": "Worldwide", - "sensor_modality": "RGB", - "real_or_synthetic": "real", - "platform": "handheld/ground", - "input_data_format": "JPG", - "annotation_format": "coco_json", - "num_images": 204, - "documentation": null, - "classes": "strawberry, flower, green, large_white, pink, red, small_white", - "stats_mean": [ - 0.272, - 0.276, - 0.2 - ], - "stats_std": [ - 0.148, - 0.148, - 0.148 - ], - "examples_image_url": "/img/agml/sample_images/strawberry_detection_2023_examples.webp", - "source": "agml", - "license": "CC BY 4.0", - "citation": "", - "crop_types": [ - "strawberry" - ] - }, - { - "name": "sugarbeet_weed_segmentation", - "machine_learning_task": "semantic_segmentation", - "agricultural_task": "weed_segmentation", - "location": "None, None", - "sensor_modality": "RGB", - "real_or_synthetic": "real", - "platform": "ground", - "input_data_format": "PNG", - "annotation_format": "image", - "num_images": 1931, - "documentation": "https://github.com/inkyusa/weedNet", - "classes": "sugar_beet, random_weeds", - "stats_mean": [ - 0.374, - 0.374, - 0.374 - ], - "stats_std": [ - 0.17, - 0.17, - 0.17 - ], - "examples_image_url": "/img/agml/sample_images/sugarbeet_weed_segmentation_examples.webp", - "source": "agml", - "license": "GPL-3.0", - "citation": "@ARTICLE{8115245,\n author={I. Sa and Z. Chen and M. Popović and R. Khanna and F. Liebisch and J. Nieto and R. Siegwart},\n journal={IEEE Robotics and Automation Letters},\n title={weedNet: Dense Semantic Weed Classification Using Multispectral Images and MAV for Smart Farming},\n year={2018},\n volume={3},\n number={1},\n pages={588-595},\n keywords={agriculture;agrochemicals;autonomous aerial vehicles;control engineering computing;convolution;crops;feature extraction;image classification;learning (artificial intelligence);neural nets;vegetation;MAV;SegNet;convolutional neural network;crop health;crop management;curve classification metrics;dense semantic classes;dense semantic weed classification;encoder-decoder;input image channels;multispectral images;selective weed treatment;vegetation index;weed detection;Agriculture;Cameras;Image segmentation;Robots;Semantics;Training;Vegetation mapping;Aerial systems;agricultural automation;applications;robotics in agriculture and forestry},\n doi={10.1109/LRA.2017.2774979},\n ISSN={},\n month={Jan}\n}", - "crop_types": [ - "sugarbeet" - ] - }, - { - "name": "sugarcane_damage_usa", - "machine_learning_task": "image_classification", - "agricultural_task": "damage_classification", - "location": "United States, North America", - "sensor_modality": "RGB", - "real_or_synthetic": null, - "platform": "ground_fixed", - "input_data_format": "bmp", - "annotation_format": "directory_names", - "num_images": 153, - "documentation": "https://github.com/The77Lab/SugarcaneBilletsDataset", - "classes": "cracked, crushed, no_buds, two_buds, single_damaged_buds, no_damage", - "stats_mean": [ - 0.244, - 0.247, - 0.262 - ], - "stats_std": [ - 0.224, - 0.217, - 0.192 - ], - "examples_image_url": "/img/agml/sample_images/sugarcane_damage_usa_examples.webp", - "source": "agml", - "license": "", - "citation": "@ARTICLE{8412587,\n author={Alencastre-Miranda, Moises and Davidson, Joseph R. and Johnson, Richard M. and Waguespack, Herman and Krebs, Hermano Igo},\n journal={IEEE Robotics and Automation Letters}, \n title={Robotics for Sugarcane Cultivation: Analysis of Billet Quality using Computer Vision}, \n year={2018},\n volume={3},\n number={4},\n pages={3828-3835},\n doi={10.1109/LRA.2018.2856999}}", - "crop_types": [ - "sugarcane" - ] - }, - { - "name": "sunflower_disease_classification", - "machine_learning_task": "image_classification", - "agricultural_task": "sunflower_disease_classification", - "location": "Bangladesh, Asia", - "sensor_modality": "RGB", - "real_or_synthetic": "real", - "platform": "uav", - "input_data_format": "JPG", - "annotation_format": "directory_names", - "num_images": 2358, - "documentation": "https://www.sciencedirect.com/science/article/pii/S2352340922002542", - "classes": "Downy_mildew, Fresh_leaf, Gray_mold, Leaf_scars", - "stats_mean": [ - 0.456, - 0.454, - 0.244 - ], - "stats_std": [ - 0.225, - 0.214, - 0.18 - ], - "examples_image_url": "/img/agml/sample_images/sunflower_disease_classification_examples.webp", - "source": "agml", - "license": "CC BY 4.0", - "citation": "Rajbongshi, Aditya; Sara, Umme ; Akter, Bonna ; Shakil, Rashiduzzaman ; Sazzad, Sadia (2022), “Sun Flower Fruits and Leaves dataset for Sunflower Disease Classification through Machine Learning and Deep Learning”, Mendeley Data, V1, doi: 10.17632/b83hmrzth8.1", - "crop_types": [ - "sunflower" - ] - }, { "name": "susnato_plant_disease_detection_processed", "machine_learning_task": "object_detection", @@ -125248,220 +124372,5 @@ "license": "cc-by-4.0", "citation": "@inproceedings{10.1145/3371158.3371196,\nauthor = {Singh, Davinder and Jain, Naman and Jain, Pranjali and Kayal, Pratik and Kumawat, Sudhakar and Batra, Nipun},\ntitle = {PlantDoc: A Dataset for Visual Plant Disease Detection},\nyear = {2020},\npublisher = {Association for Computing Machinery},\nurl = {https://doi.org/10.1145/3371158.3371196}}", "crop_types": null - }, - { - "name": "tea_leaf_disease_classification", - "machine_learning_task": "image_classification", - "agricultural_task": "tea_leaf_disease_classification", - "location": "India, Asia", - "sensor_modality": "RGB", - "real_or_synthetic": "real", - "platform": "uav", - "input_data_format": "JPG", - "annotation_format": "directory_names", - "num_images": 5867, - "documentation": "https://www.kaggle.com/datasets/saikatdatta1994/tea-leaf-disease", - "classes": "algal_spot, brown_blight, gray_blight, healthy, helopeltis, red_spot", - "stats_mean": [ - 0.72, - 0.715, - 0.721 - ], - "stats_std": [ - 0.264, - 0.243, - 0.325 - ], - "examples_image_url": "/img/agml/sample_images/tea_leaf_disease_classification_examples.webp", - "source": "agml", - "license": "CC BY-NC 4.0", - "citation": "@article{BALASUNDARAM2025103784, title = {Tea leaf disease detection using segment anything model and deep convolutional neural networks}, journal = {Results in Engineering}, volume = {25}, pages = {103784}, year = {2025}, issn = {2590-1230}, doi = {https://doi.org/10.1016/j.rineng.2024.103784}, url = {https://www.sciencedirect.com/science/article/pii/S2590123024020279}, author = {Ananthakrishnan Balasundaram and Prem Sundaresan and Aryan Bhavsar and Mishti Mattu and Muthu Subash Kavitha and Ayesha Shaik}}", - "crop_types": [ - "tea" - ] - }, - { - "name": "tomato_leaf_disease", - "machine_learning_task": "image_classification", - "agricultural_task": "disease_classification", - "location": "Worldwide", - "sensor_modality": "RGB", - "real_or_synthetic": "real", - "platform": "handheld", - "input_data_format": "JPEG", - "annotation_format": "directory_names", - "num_images": 11000, - "documentation": "https://www.kaggle.com/datasets/kaustubhb999/tomatoleaf?resource=download", - "classes": "Bacterial Spot, Early Blight, Healthy, Late Blight, Leaf Mold, Septoria Leaf Spot, Spider Mites Two-spotted Spider Mite, Target Spot, Tomato Mosaic Virus, Tomato Yellow Leaf Curl Virus", - "stats_mean": [ - 0.453, - 0.463, - 0.419 - ], - "stats_std": [ - 0.169, - 0.148, - 0.185 - ], - "examples_image_url": "/img/agml/sample_images/tomato_leaf_disease_examples.webp", - "source": "agml", - "license": "CC0: Public Domain", - "citation": "", - "crop_types": [ - "tomato" - ] - }, - { - "name": "tomato_ripeness_detection", - "machine_learning_task": "object_detection", - "agricultural_task": "fruit_ripeness_detection", - "location": "Worldwide", - "sensor_modality": "RGB", - "real_or_synthetic": "real", - "platform": "ground", - "input_data_format": "JPG", - "annotation_format": "coco_json", - "num_images": 804, - "documentation": "https://www.kaggle.com/datasets/nexuswho/laboro-tomato", - "classes": "b_fully_ripened, b_half_ripened, b_green, l_fully_ripened, l_half_ripened, l_green", - "stats_mean": [ - 0.468, - 0.505, - 0.318 - ], - "stats_std": [ - 0.21, - 0.193, - 0.224 - ], - "examples_image_url": "/img/agml/sample_images/tomato_ripeness_detection_examples.webp", - "source": "agml", - "license": "CC BY-NC-SA 4.0", - "citation": "", - "crop_types": [ - "tomato" - ] - }, - { - "name": "vegann_multicrop_presence_segmentation", - "machine_learning_task": "semantic_segmentation", - "agricultural_task": "vegetation_segmentation", - "location": "Worldwide", - "sensor_modality": "RGB", - "real_or_synthetic": "real", - "platform": "aerial", - "input_data_format": "PNG", - "annotation_format": "image", - "num_images": 3775, - "documentation": "https://zenodo.org/records/7636408", - "classes": "plant", - "stats_mean": [ - 16.392, - 18.685, - 14.235 - ], - "stats_std": [ - 4.59, - 5.818, - 4.19 - ], - "examples_image_url": "/img/agml/sample_images/vegann_multicrop_presence_segmentation_examples.webp", - "source": "agml", - "license": "CC BY-SA 4.0", - "citation": " @article{Madec_Irfan_Velumani_Baret_David_Daubige_Samatan_Serouart_Smith_James_et al._2023, title={VegAnn, Vegetation Annotation of multi-crop RGB images acquired under diverse conditions for segmentation}, volume={10}, ISSN={2052-4463}, url={https://www.nature.com/articles/s41597-023-02098-y}, DOI={10.1038/s41597-023-02098-y}, abstractNote={Abstract\n \n Applying deep learning to images of cropping systems provides new knowledge and insights in research and commercial applications. Semantic segmentation or pixel-wise classification, of RGB images acquired at the ground level, into vegetation and background is a critical step in the estimation of several canopy traits. Current state of the art methodologies based on convolutional neural networks (CNNs) are trained on datasets acquired under controlled or indoor environments. These models are unable to generalize to real-world images and hence need to be fine-tuned using new labelled datasets. This motivated the creation of the VegAnn -\n Veg\n etation\n Ann\n otation - dataset, a collection of 3775 multi-crop RGB images acquired for different phenological stages using different systems and platforms in diverse illumination conditions. We anticipate that VegAnn will help improving segmentation algorithm performances, facilitate benchmarking and promote large-scale crop vegetation segmentation research.}, number={1}, journal={Scientific Data}, author={Madec, Simon and Irfan, Kamran and Velumani, Kaaviya and Baret, Frederic and David, Etienne and Daubige, Gaetan and Samatan, Lucas Bernigaud and Serouart, Mario and Smith, Daniel and James, Chrisbin and Camacho, Fernando and Guo, Wei and De Solan, Benoit and Chapman, Scott C. and Weiss, Marie}, year={2023}, month=may, pages={302}, language={en} }\n", - "crop_types": null - }, - { - "name": "vine_virus_photo_dataset", - "machine_learning_task": "image_classification", - "agricultural_task": "vine_virus_photo", - "location": "Worldwide", - "sensor_modality": "RGB", - "real_or_synthetic": "real", - "platform": "handheld/ground", - "input_data_format": "jpg, png, jpeg, JPG", - "annotation_format": "directory_names", - "num_images": 3866, - "documentation": null, - "classes": "Leafroll 3, No Virus, Other Red, Red Blotch", - "stats_mean": [ - 0.45, - 0.449, - 0.295 - ], - "stats_std": [ - 0.231, - 0.228, - 0.23 - ], - "examples_image_url": "/img/agml/sample_images/vine_virus_photo_dataset_examples.webp", - "source": "agml", - "license": "Apache 2.0", - "citation": "", - "crop_types": [ - "vine" - ] - }, - { - "name": "wheat_head_counting", - "machine_learning_task": "object_detection", - "agricultural_task": "wheat_head_counting", - "location": "Worldwide", - "sensor_modality": "RGB", - "real_or_synthetic": "real", - "platform": "ground", - "input_data_format": "JPG", - "annotation_format": "coco_json", - "num_images": 6512, - "documentation": "https://zenodo.org/record/5092309", - "classes": "Wheat Head", - "stats_mean": [ - 0.371, - 0.361, - 0.23 - ], - "stats_std": [ - 0.219, - 0.217, - 0.177 - ], - "examples_image_url": "/img/agml/sample_images/wheat_head_counting_examples.webp", - "source": "agml", - "license": "CC BY-SA 4.0", - "citation": "@article{david2020global,\n title={Global Wheat Head Detection (GWHD) dataset: a large and diverse dataset of high-resolution RGB-labelled images to develop and benchmark wheat head detection methods},\n author={David, Etienne and Madec, Simon and Sadeghi-Tehran, Pouria and Aasen, Helge and Zheng, Bangyou and Liu, Shouyang and Kirchgessner, Norbert and Ishikawa, Goro and Nagasawa, Koichi and Badhon, Minhajul A and others},\n journal={Plant Phenomics},\n volume={2020},\n year={2020},\n publisher={Science Partner Journal}\n }", - "crop_types": [ - "wheat" - ] - }, - { - "name": "white_grapes_and_leaves_segmentation", - "machine_learning_task": "semantic_segmentation", - "agricultural_task": "vineyard_scene_segmentation", - "location": "Greece, Europe", - "sensor_modality": "RGB", - "real_or_synthetic": "real", - "platform": "handheld/ground", - "input_data_format": "JPG", - "annotation_format": "image", - "num_images": 273, - "documentation": "https://link.springer.com/chapter/10.1007/978-3-030-48791-1_22", - "classes": "Leaf, Grape", - "stats_mean": [ - 0.309, - 0.473, - 0.524 - ], - "stats_std": [ - 0.233, - 0.246, - 0.253 - ], - "examples_image_url": "/img/agml/sample_images/white_grapes_and_leaves_segmentation_examples.webp", - "source": "agml", - "license": "", - "citation": "@inproceedings{kalampokas2020semantic,\n title={Semantic segmentation of vineyard images using convolutional neural networks},\n author={Kalampokas, Theofanis and Tziridis, Konstantinos and Nikolaou, Alexandros and Vrochidou, Eleni and Papakostas, George A and Pachidis, Theodore and Kaburlasos, Vassilis G},\n booktitle={International Conference on Engineering Applications of Neural Networks},\n pages={292--303},\n year={2020},\n organization={Springer}}", - "crop_types": [ - "grape" - ] } ] \ No newline at end of file diff --git a/static/data/hf_datasets.json b/static/data/hf_datasets.json index b7db426..ad40c47 100644 --- a/static/data/hf_datasets.json +++ b/static/data/hf_datasets.json @@ -3638,5 +3638,1225 @@ "source": "huggingface", "hf_link": "https://huggingface.co/datasets/Project-AgML/ghai_strawberry_fruit_detection", "examples_image_url": "/img/agml/sample_images/ghai_strawberry_fruit_detection_sample.webp" + }, + { + "name": "grape_detection_californiaday", + "machine_learning_task": "object_detection", + "agricultural_task": "fruit_detection", + "location": "United States, North America", + "sensor_modality": "RGB", + "real_or_synthetic": "real", + "environment": "Field", + "platform": "ground", + "input_data_format": "JPG", + "annotation_format": "image", + "num_images": 126, + "documentation": null, + "classes": "grape", + "stats_mean": [ + 0.446, + 0.464, + 0.275 + ], + "stats_std": [ + 0.268, + 0.259, + 0.263 + ], + "examples_image_url": "/img/agml/sample_images/grape_detection_californiaday_examples.webp", + "source": "huggingface", + "hf_link": "https://huggingface.co/datasets/Project-AgML/grape_detection_californiaday", + "license": "", + "citation": "@misc{GrapeDay,\n author = {Plant AI and Biophysics Lab},\n title = {Grape Detection 2019 Day},\n year = {2019},\n url = {https://github.com/plant-ai-biophysics-lab/AgML} \n ", + "crop_types": [ + "grape" + ] + }, + { + "name": "grape_detection_californianight", + "machine_learning_task": "object_detection", + "agricultural_task": "fruit_detection", + "location": "United States, North America", + "sensor_modality": "RGB", + "real_or_synthetic": "real", + "environment": "Field", + "platform": "ground", + "input_data_format": "JPG", + "annotation_format": "image", + "num_images": 150, + "documentation": null, + "classes": "grape", + "stats_mean": [ + 0.222, + 0.213, + 0.225 + ], + "stats_std": [ + 0.205, + 0.201, + 0.206 + ], + "examples_image_url": "/img/agml/sample_images/grape_detection_californianight_examples.webp", + "source": "huggingface", + "hf_link": "https://huggingface.co/datasets/Project-AgML/grape_detection_californianight", + "license": "", + "citation": "@misc{GrapeNight,\n author = {Plant AI and Biophysics Lab},\n title = {Grape Detection 2020 Night},\n year = {2020},\n url = {https://github.com/plant-ai-biophysics-lab/AgML} \n ", + "crop_types": [ + "grape" + ] + }, + { + "name": "grape_detection_syntheticday", + "machine_learning_task": "object_detection", + "agricultural_task": "fruit_detection", + "location": "United States, North America", + "sensor_modality": "RGB", + "real_or_synthetic": "synthetic", + "environment": "field", + "platform": "ground", + "input_data_format": "JPG", + "annotation_format": "coco_json", + "num_images": 448, + "documentation": "N/A", + "classes": "grape", + "stats_mean": [ + 0.25, + 0.276, + 0.207 + ], + "stats_std": [ + 0.151, + 0.186, + 0.224 + ], + "examples_image_url": "/img/agml/sample_images/grape_detection_syntheticday_examples.webp", + "source": "huggingface", + "hf_link": "https://huggingface.co/datasets/Project-AgML/grape_detection_syntheticday", + "license": "", + "citation": "@ARTICLE{10.3389/fpls.2019.01185,\n \nAUTHOR={Bailey, Brian N.}, \n\t \nTITLE={Helios: A Scalable 3D Plant and Environmental Biophysical Modeling Framework}, \n\t\nJOURNAL={Frontiers in Plant Science}, \n\t\nVOLUME={10}, \n\t\nYEAR={2019}, \n\t \nURL={https://www.frontiersin.org/article/10.3389/fpls.2019.01185}, \n\t\nDOI={10.3389/fpls.2019.01185}, \n\t\nISSN={1664-462X}, \n \nABSTRACT={This article presents an overview of Helios, a new three-dimensional (3D) plant and environmental modeling framework. Helios is a model coupling framework designed to provide maximum flexibility in integrating and running arbitrary 3D environmental system models. Users interact with Helios through a well-documented open-source C++ API. Version 1.0 comes with model plug-ins for radiation transport, the surface energy balance, stomatal conductance, photosynthesis, solar position, and procedural tree generation. Additional plug-ins are also available for visualizing model geometry and data and for processing and integrating LiDAR scanning data. Many of the plug-ins perform calculations on the graphics processing unit, which allows for efficient simulation of very large domains with high detail. An example modeling study is presented in which leaf-level heterogeneity in water usage and photosynthesis of an orchard is examined to understand how this leaf-scale variability contributes to whole-tree and -canopy fluxes.}\n}", + "crop_types": [ + "grape" + ] + }, + { + "name": "mango_detection_australia", + "machine_learning_task": "object_detection", + "agricultural_task": "fruit_detection", + "location": "Australia, Oceania", + "sensor_modality": "RGB", + "real_or_synthetic": "real", + "environment": "Field", + "platform": "handheld", + "input_data_format": "JPG", + "annotation_format": "coco_json", + "num_images": 1242, + "documentation": "https://researchdata.edu.au/mangoyolo-set/1697505", + "classes": "mango", + "stats_mean": [ + 0.073, + 0.119, + 0.05 + ], + "stats_std": [ + 0.059, + 0.079, + 0.043 + ], + "examples_image_url": "/img/agml/sample_images/mango_detection_australia_examples.webp", + "source": "huggingface", + "hf_link": "https://huggingface.co/datasets/Project-AgML/mango_detection_australia", + "license": "", + "citation": "@Misc{Koirala2019,\n author={Koirala, Anand and Walsh, Kerry and Wang, Z. and McCarthy, C.},\n title={MangoYOLO data set},\n year={2019},\n month={2021},\n day={10-19},\n publisher={Central Queensland University},\n keywords={Mango images; Fruit detection; Yield estimation; Mango; Agricultural Land Management; Horticultural Crop Growth and Development},\n abstract={Datasets and directories are structured similar to the PASCAL VOC dataset, avoiding the need to change scripts already available, with the detection frameworks ready to parse PASCAL VOC annotations into their format. The sub-directory JPEGImages consist of 1730 images (612x512 pixels) used for train, test and validation. Each image has at least one annotated fruit. The sub-directory Annotations consists of all the annotation files (record of bounding box coordinates for each image) in xml format and have the same name as the image name. The sub-directory Main consists of the text file that contains image names (without extension) used for train, test and validation. Training set (train.txt) lists 1300 train images Validation set (val.txt) lists 130 validation images Test set (test.txt) lists 300 test images Each image has an XML annotation file (filename = image name) and each image set (training validation and test set) has associated text files (train.txt, val.txt and test.txt) containing the list of image names to be used for training and testing. The XML annotation file contains the image attributes (name, width, height), the object attributes (class name, object bounding box co-ordinates (xmin, ymin, xmax, ymax)). (xmin, ymin) and (xmax, ymax) are the pixel co-ordinates of the bounding box's top-left corner and bottom-right corner respectively.},\n note={CC-BY-4.0},\n url={https://figshare.com/articles/dataset/MangoYOLO_data_set/13450661, https://researchdata.edu.au/mangoyolo-set},\n language={English}\n}", + "crop_types": [ + "mango" + ] + }, + { + "name": "plant_doc_detection", + "machine_learning_task": "object_detection", + "agricultural_task": "disease_classification", + "location": "Worldwide", + "sensor_modality": "RGB", + "real_or_synthetic": "real", + "environment": "Field", + "platform": "ground", + "input_data_format": "JPG", + "annotation_format": "coco_json", + "num_images": 2346, + "documentation": "https://github.com/pratikkayal/PlantDoc-Object-Detection-Dataset", + "classes": "Corn leaf blight, Tomato Early blight leaf, Potato leaf early blight, Potato leaf late blight, Blueberry leaf, grape leaf black rot, Bell_pepper leaf spot, Cherry leaf, Peach leaf, Soyabean leaf, Strawberry leaf, Apple Scab Leaf, Corn rust leaf, Apple leaf, Corn Gray leaf spot, Tomato leaf mosaic virus, Tomato mold leaf, Tomato leaf yellow virus, Tomato leaf bacterial spot, Tomato leaf late blight, Squash Powdery mildew leaf, Bell_pepper leaf, grape leaf, Apple rust leaf, Tomato Septoria leaf spot, Tomato leaf, Raspberry leaf, Potato leaf, Tomato two spotted spider mites leaf", + "stats_mean": [ + 0.477, + 0.544, + 0.378 + ], + "stats_std": [ + 0.211, + 0.204, + 0.218 + ], + "examples_image_url": "/img/agml/sample_images/plant_doc_detection_examples.webp", + "source": "huggingface", + "hf_link": "https://huggingface.co/datasets/Project-AgML/plant_doc_detection", + "license": "CC BY-SA 4.0", + "citation": "@inproceedings{10.1145/3371158.3371196,\n author = {Singh, Davinder and Jain, Naman and Jain, Pranjali and Kayal, Pratik and Kumawat, Sudhakar and Batra, Nipun},\n title = {PlantDoc: A Dataset for Visual Plant Disease Detection},\n year = {2020},\n isbn = {9781450377386},\n publisher = {Association for Computing Machinery},\n address = {New York, NY, USA},\n url = {https://doi.org/10.1145/3371158.3371196},\n doi = {10.1145/3371158.3371196},\n booktitle = {Proceedings of the 7th ACM IKDD CoDS and 25th COMAD},\n pages = {249–253},\n numpages = {5},\n keywords = {Deep Learning, Object Detection, Image Classification},\n location = {Hyderabad, India},\n series = {CoDS COMAD 2020}\n }", + "crop_types": null + }, + { + "name": "strawberry_detection_2022", + "machine_learning_task": "object_detection", + "agricultural_task": "crop_detection", + "location": "Worldwide", + "sensor_modality": "RGB", + "real_or_synthetic": "real", + "environment": "Field", + "platform": "handheld/ground", + "input_data_format": "JPG", + "annotation_format": "coco_json", + "num_images": 175, + "documentation": null, + "classes": "strawberry, flower, green, large_white, pink, red, small_white", + "stats_mean": [ + 0.288, + 0.306, + 0.299 + ], + "stats_std": [ + 0.21, + 0.199, + 0.205 + ], + "examples_image_url": "/img/agml/sample_images/strawberry_detection_2022_examples.webp", + "source": "huggingface", + "hf_link": "https://huggingface.co/datasets/Project-AgML/strawberry_detection_2022", + "license": "CC BY 4.0", + "citation": "", + "crop_types": [ + "strawberry" + ] + }, + { + "name": "strawberry_detection_2023", + "machine_learning_task": "object_detection", + "agricultural_task": "crop_detection", + "location": "Worldwide", + "sensor_modality": "RGB", + "real_or_synthetic": "real", + "environment": "Field", + "platform": "handheld/ground", + "input_data_format": "JPG", + "annotation_format": "coco_json", + "num_images": 204, + "documentation": null, + "classes": "strawberry, flower, green, large_white, pink, red, small_white", + "stats_mean": [ + 0.272, + 0.276, + 0.2 + ], + "stats_std": [ + 0.148, + 0.148, + 0.148 + ], + "examples_image_url": "/img/agml/sample_images/strawberry_detection_2023_examples.webp", + "source": "huggingface", + "hf_link": "https://huggingface.co/datasets/Project-AgML/strawberry_detection_2023", + "license": "CC BY 4.0", + "citation": "", + "crop_types": [ + "strawberry" + ] + }, + { + "name": "tomato_ripeness_detection", + "machine_learning_task": "object_detection", + "agricultural_task": "fruit_ripeness_detection", + "location": "Worldwide", + "sensor_modality": "RGB", + "real_or_synthetic": "real", + "environment": "Field", + "platform": "ground", + "input_data_format": "JPG", + "annotation_format": "coco_json", + "num_images": 804, + "documentation": "https://www.kaggle.com/datasets/nexuswho/laboro-tomato", + "classes": "b_fully_ripened, b_half_ripened, b_green, l_fully_ripened, l_half_ripened, l_green", + "stats_mean": [ + 0.468, + 0.505, + 0.318 + ], + "stats_std": [ + 0.21, + 0.193, + 0.224 + ], + "examples_image_url": "/img/agml/sample_images/tomato_ripeness_detection_examples.webp", + "source": "huggingface", + "hf_link": "https://huggingface.co/datasets/Project-AgML/strawberry_detection_2023", + "license": "CC BY-NC-SA 4.0", + "citation": "", + "crop_types": [ + "tomato" + ] + }, + { + "name": "wheat_head_counting", + "machine_learning_task": "object_detection", + "agricultural_task": "crop_detection", + "location": "Worldwide", + "sensor_modality": "RGB", + "real_or_synthetic": "real", + "environment": "Field", + "platform": "ground", + "input_data_format": "JPG", + "annotation_format": "coco_json", + "num_images": 6512, + "documentation": "https://zenodo.org/record/5092309", + "classes": "Wheat Head", + "stats_mean": [ + 0.371, + 0.361, + 0.23 + ], + "stats_std": [ + 0.219, + 0.217, + 0.177 + ], + "examples_image_url": "/img/agml/sample_images/wheat_head_counting_examples.webp", + "source": "huggingface", + "hf_link": "https://huggingface.co/datasets/Project-AgML/wheat_head_counting", + "license": "CC BY-SA 4.0", + "citation": "@article{david2020global,\n title={Global Wheat Head Detection (GWHD) dataset: a large and diverse dataset of high-resolution RGB-labelled images to develop and benchmark wheat head detection methods},\n author={David, Etienne and Madec, Simon and Sadeghi-Tehran, Pouria and Aasen, Helge and Zheng, Bangyou and Liu, Shouyang and Kirchgessner, Norbert and Ishikawa, Goro and Nagasawa, Koichi and Badhon, Minhajul A and others},\n journal={Plant Phenomics},\n volume={2020},\n year={2020},\n publisher={Science Partner Journal}\n }", + "crop_types": [ + "wheat" + ] + }, + { + "name": "crop_weeds_greece", + "machine_learning_task": "image_classification", + "agricultural_task": "weed_classification", + "location": "Greece, Europe", + "sensor_modality": "RGB", + "real_or_synthetic": "real", + "environment": "Field", + "platform": "handheld", + "input_data_format": "JPG", + "annotation_format": "directory_names", + "num_images": 508, + "documentation": "https://github.com/AUAgroup/early-crop-weed", + "classes": "black_nightshade, velvet_leaf, cotton, tomato", + "stats_mean": [ + 0.725, + 0.669, + 0.544 + ], + "stats_std": [ + 0.164, + 0.153, + 0.138 + ], + "examples_image_url": "/img/agml/sample_images/crop_weeds_greece_sample.webp", + "source": "huggingface", + "hf_link": "https://huggingface.co/datasets/Project-AgML/crop_weeds_greece", + "license": "MIT", + "citation": "@article{ESPEJOGARCIA2020105306,\n title = {Towards weeds identification assistance through transfer learning},\n journal = {Computers and Electronics in Agriculture},\n volume = {171},\n pages = {105306},\n year = {2020},\n issn = {0168-1699},\n doi = {https://doi.org/10.1016/j.compag.2020.105306},\n url = {https://www.sciencedirect.com/science/article/pii/S0168169919319854},\n author = {Borja Espejo-Garcia and Nikos Mylonas and Loukas Athanasakos and Spyros Fountas and Ioannis Vasilakoglou},\n keywords = {Weed identification, Deep learning, Transfer learning, Open data, Precision agriculture},\n abstract = {Reducing the use of pesticides through selective spraying is an important component towards a more sustainable computer-assisted agriculture. Weed identification at early growth stage contributes to reduced herbicide rates. However, while computer vision alongside deep learning have overcome the performance of approaches that use hand-crafted features, there are still some open challenges in the development of a reliable automatic plant identification system. These type of systems have to take into account different sources of variability, such as growth stages and soil conditions, with the added constraint of the limited size of usual datasets. This study proposes a novel crop/weed identification system that relies on a combination of fine-tuning pre-trained convolutional networks (Xception, Inception-Resnet, VGNets, Mobilenet and Densenet) with the “traditional” machine learning classifiers (Support Vector Machines, XGBoost and Logistic Regression) trained with the previously deep extracted features. The aim of this approach was to avoid overfitting and to obtain a robust and consistent performance. To evaluate this approach, an open access dataset of two crop [tomato (Solanum lycopersicum L.) and cotton (Gossypium hirsutum L.)] and two weed species [black nightshade (Solanum nigrum L.) and velvetleaf (Abutilon theophrasti Medik.)] was generated. The pictures were taken by different production sites across Greece under natural variable light conditions from RGB cameras. The results revealed that a combination of fine-tuned Densenet and Support Vector Machine achieved a micro F1 score of 99.29% with a very low performance difference between train and test sets. Other evaluated approaches also obtained repeatedly more than 95% F1 score. Additionally, our results analysis provides some heuristics for designing transfer-learning based systems to avoid overfitting without decreasing performance.}\n}", + "crop_types": [ + "cotton", + "tomato" + ] + }, + { + "name": "plant_seedlings_aarhus", + "machine_learning_task": "image_classification", + "agricultural_task": "weed_classification", + "location": "Denmark, Europe", + "sensor_modality": "RGB", + "real_or_synthetic": "real", + "environment": "Field", + "platform": "ground_fixed", + "input_data_format": "PNG", + "annotation_format": "directory_names", + "num_images": 5539, + "documentation": "https://vision.eng.au.dk/plant-seedlings-dataset/", + "classes": "maize, common_wheat, sugar_beet, scentless_mayweed, common_chickweed, shepherds_purse, cleavers, charlock, fat_hen, smallflowered_cranesbill, black_grass, loose_silkybent", + "stats_mean": [ + 0.329, + 0.289, + 0.207 + ], + "stats_std": [ + 0.093, + 0.096, + 0.106 + ], + "examples_image_url": "/img/agml/sample_images/plant_seedlings_aarhus_sample.webp", + "source": "huggingface", + "hf_link": "https://huggingface.co/datasets/Project-AgML/plant_seedlings_aarhus", + "license": "CC BY-SA 4.0", + "citation": "@article{Giselsson2017,\n author = {Giselsson, Thomas Mosgaard and Dyrmann, Mads and J{\\o}rgensen, Rasmus Nyholm and Jensen, Peter Kryger and Midtiby, Henrik Skov},\n journal = {arXiv preprint},\n keywords = {benchmark,database,plant seedlings,segmentation,site-specific weed control},\n title = {{A Public Image Database for Benchmark of Plant Seedling Classification Algorithms}},\n year = {2017}\n}", + "crop_types": [ + "maize", + "wheat" + ] + }, + { + "name": "soybean_weed_uav_brazil", + "machine_learning_task": "image_classification", + "agricultural_task": "weed_classification", + "location": "Brazil, South America", + "sensor_modality": "RGB", + "real_or_synthetic": "real", + "environment": "Lab", + "platform": "uav", + "input_data_format": "tif", + "annotation_format": "directory_names", + "num_images": 15336, + "documentation": "https://data.mendeley.com/datasets/3fmjm7ncc6/2", + "classes": "broadleaf, grass, soil, soybean", + "stats_mean": [ + 0.329, + 0.334, + 0.187 + ], + "stats_std": [ + 0.245, + 0.249, + 0.157 + ], + "examples_image_url": "/img/agml/sample_images/soybean_weed_uav_brazil_sample.webp", + "source": "huggingface", + "hf_link": "https://huggingface.co/datasets/Project-AgML/soybean_weed_uav_brazil", + "license": "CC BY-NC 3.0", + "citation": "dos Santos Ferreira, Alessandro; Pistori, Hemerson; Matte Freitas, Daniel; Gonçalves da Silva, Gercina (2017), “Data for: Weed Detection in Soybean Crops Using ConvNets”, Mendeley Data, V2, doi: 10.17632/3fmjm7ncc6.2", + "crop_types": [ + "soybean" + ] + }, + { + "name": "sugarcane_damage_usa", + "machine_learning_task": "image_classification", + "agricultural_task": "damage_classification", + "location": "United States, North America", + "sensor_modality": "RGB", + "real_or_synthetic": "real", + "environment": "Lab", + "platform": "ground_fixed", + "input_data_format": "bmp", + "annotation_format": "directory_names", + "num_images": 153, + "documentation": "https://github.com/The77Lab/SugarcaneBilletsDataset", + "classes": "cracked, crushed, no_buds, two_buds, single_damaged_buds, no_damage", + "stats_mean": [ + 0.244, + 0.247, + 0.262 + ], + "stats_std": [ + 0.224, + 0.217, + 0.192 + ], + "examples_image_url": "/img/agml/sample_images/sugarcane_damage_usa_sample.webp", + "source": "huggingface", + "hf_link": "https://huggingface.co/datasets/Project-AgML/sugarcane_damage_usa", + "license": "", + "citation": "@ARTICLE{8412587,\n author={Alencastre-Miranda, Moises and Davidson, Joseph R. and Johnson, Richard M. and Waguespack, Herman and Krebs, Hermano Igo},\n journal={IEEE Robotics and Automation Letters}, \n title={Robotics for Sugarcane Cultivation: Analysis of Billet Quality using Computer Vision}, \n year={2018},\n volume={3},\n number={4},\n pages={3828-3835},\n doi={10.1109/LRA.2018.2856999}}", + "crop_types": [ + "sugarcane" + ] + }, + { + "name": "guava_disease_pakistan", + "machine_learning_task": "image_classification", + "agricultural_task": "disease_classification", + "location": "Pakistan, Asia", + "sensor_modality": "RGB", + "real_or_synthetic": "real", + "environment": "Field", + "platform": "ground", + "input_data_format": "JPG", + "annotation_format": "directory_names", + "num_images": 306, + "documentation": "https://data.mendeley.com/datasets/s8x6jn5cvr/1", + "classes": "Canker, Dot, Mummification, Rust", + "stats_mean": [ + 0.446, + 0.451, + 0.323 + ], + "stats_std": [ + 0.187, + 0.184, + 0.187 + ], + "examples_image_url": "/img/agml/sample_images/guava_disease_pakistan_sample.webp", + "source": "huggingface", + "hf_link": "https://huggingface.co/datasets/Project-AgML/guava_disease_pakistan", + "license": "", + "citation": "@article{Rauf_Lali_2021, \n title={A Guava Fruits and Leaves Dataset for Detection and Classification of Guava Diseases through Machine Learning}, \n volume={1}, \n url={https://data.mendeley.com/datasets/s8x6jn5cvr/1}, \n DOI={10.17632/s8x6jn5cvr.1}, \n abstractNote={(1) Plant diseases are the primary cause of reduced productivity in agriculture, which results in economic losses. Guava is a big source of nutrients for humans all over the world. Guava diseases, on the other hand, harm the yield and quality of the crop. (2) For the identification and classification of plant diseases, computer vision and image processing methods have been commonly used. (3) The dataset includes an image gallery of healthy and unhealthy Guava fruits and leaves that could be used by researchers to adopt advanced computer vision techniques to protect plants from disease. Dot, Canker, Mummification, and Rust are the diseases targeted in the data sets. (4) The dataset contains 306 images of healthy and unhealthy images for both Guava fruits and leaves collectively. Each image contains 6000 * 4000 dimensions with 300 dpi resolution. (5) All images were acquired from the tropical areas of Pakistan under the supervision of Prof. Dr. Ikramullah Lali. (6) All images were annotated manually by the domain expert such as For Guava fruits and leaves; Dot (76), Canker (77), Mummification (83), and Rust (70) Note: The data labeling was manual and can be updated by automatic labeling through machine learning. In the meantime, the authors can also use the data set for the clustering problem.}, \n author={Rauf, Hafiz Tayyab and Lali, Muhammad Ikram Ullah}, \n year={2021}, month={Apr} \n}\n", + "crop_types": [ + "guava" + ] + }, + { + "name": "plant_doc_classification", + "machine_learning_task": "image_classification", + "agricultural_task": "disease_classification", + "location": "Worldwide", + "sensor_modality": "RGB", + "real_or_synthetic": "real", + "environment": "Field", + "platform": "ground", + "input_data_format": "JPG", + "annotation_format": "directory_names", + "num_images": 2598, + "documentation": "https://github.com/pratikkayal/PlantDoc-Dataset", + "classes": "Corn leaf blight, Tomato Early blight leaf, Potato leaf early blight, Potato leaf late blight, Blueberry leaf, grape leaf black rot, Bell_pepper leaf spot, Cherry leaf, Peach leaf, Soyabean leaf, Strawberry leaf, Apple Scab Leaf, Corn rust leaf, Apple leaf, Corn Gray leaf spot, Tomato leaf mosaic virus, Tomato mold leaf, Tomato leaf yellow virus, Tomato leaf bacterial spot, Tomato leaf late blight, Squash Powdery mildew leaf, Bell_pepper leaf, grape leaf, Apple rust leaf, Tomato Septoria leaf spot, Tomato leaf, Raspberry leaf, Tomato two spotted spider mites leaf", + "stats_mean": [ + 0.482, + 0.55, + 0.383 + ], + "stats_std": [ + 0.212, + 0.204, + 0.221 + ], + "examples_image_url": "/img/agml/sample_images/plant_doc_classification_sample.webp", + "source": "huggingface", + "hf_link": "https://huggingface.co/datasets/Project-AgML/plant_doc_classification", + "license": "CC BY-SA 4.0", + "citation": "@inproceedings{10.1145/3371158.3371196,\n author = {Singh, Davinder and Jain, Naman and Jain, Pranjali and Kayal, Pratik and Kumawat, Sudhakar and Batra, Nipun},\n title = {PlantDoc: A Dataset for Visual Plant Disease Detection},\n year = {2020},\n isbn = {9781450377386},\n publisher = {Association for Computing Machinery},\n address = {New York, NY, USA},\n url = {https://doi.org/10.1145/3371158.3371196},\n doi = {10.1145/3371158.3371196},\n booktitle = {Proceedings of the 7th ACM IKDD CoDS and 25th COMAD},\n pages = {249–253},\n numpages = {5},\n keywords = {Deep Learning, Object Detection, Image Classification},\n location = {Hyderabad, India},\n series = {CoDS COMAD 2020}\n }", + "crop_types": [ + "apple", + "Bell Pepper", + "Blueberry", + "Cherry", + "corn", + "grape", + "Potato", + "Rasperry", + "Soybean", + "Squash", + "strawberry", + "Tomato" + ] + }, + { + "name": "plant_village_classification", + "machine_learning_task": "image_classification", + "agricultural_task": "disease_classification", + "location": "United States, North America", + "sensor_modality": "RGB", + "real_or_synthetic": "real", + "environment": "Lab", + "platform": "ground", + "input_data_format": "JPG", + "annotation_format": "directory_names", + "num_images": 55448, + "documentation": "https://github.com/spMohanty/PlantVillage-Dataset", + "classes": "Apple___Apple_scab, Apple___Black_rot, Apple___Cedar_apple_rust, Apple___healthy, Background_without_leaves, Blueberry___healthy, Cherry___Powdery_mildew, Cherry___healthy, Corn___Cercospora_leaf_spot Gray_leaf_spot, Corn___Common_rust, Corn___Northern_Leaf_Blight, Corn___healthy, Grape___Black_rot, Grape___Esca_(Black_Measles), Grape___Leaf_blight_(Isariopsis_Leaf_Spot), Grape___healthy, Orange___Haunglongbing_(Citrus_greening), Peach___Bacterial_spot, Peach___healthy, Pepper,_bell___Bacterial_spot, Pepper,_bell___healthy, Potato___Early_blight, Potato___Late_blight, Potato___healthy, Raspberry___healthy, Soybean___healthy, Squash___Powdery_mildew, Strawberry___Leaf_scorch, Strawberry___healthy, Tomato___Bacterial_spot, Tomato___Early_blight, Tomato___Late_blight, Tomato___Leaf_Mold, Tomato___Septoria_leaf_spot, Tomato___Spider_mites Two-spotted_spider_mite, Tomato___Target_Spot, Tomato___Tomato_Yellow_Leaf_Curl_Virus, Tomato___Tomato_mosaic_virus, Tomato___healthy", + "stats_mean": [ + 0.467, + 0.489, + 0.412 + ], + "stats_std": [ + 0.177, + 0.152, + 0.194 + ], + "examples_image_url": "/img/agml/sample_images/plant_village_classification_sample.webp", + "source": "huggingface", + "hf_link": "https://huggingface.co/datasets/Project-AgML/plant_village_classification", + "license": "", + "citation": "@article{DBLP:journals/corr/HughesS15,\n author = {David P. Hughes and\n Marcel Salath{'{e} } },\n title = {An open access repository of images on plant health to enable the\n development of mobile disease diagnostics through machine\n learning and crowdsourcing},\n journal = {CoRR},\n volume = {abs/1511.08060},\n year = {2015},\n url = {http://arxiv.org/abs/1511.08060},\n archivePrefix = {arXiv},\n eprint = {1511.08060},\n timestamp = {Mon, 13 Aug 2018 16:48:21 +0200},\n biburl = {https://dblp.org/rec/bib/journals/corr/HughesS15},\n bibsource = {dblp computer science bibliography, https://dblp.org}\n}", + "crop_types": [ + "Apple", + "Blueberry", + "Cherry", + "Corn", + "Grape", + "Orange", + "Peach", + "Bell Pepper", + "Potato", + "Rasperry", + "Soybean", + "Squash", + "strawberry", + "tomato" + ] + }, + { + "name": "rangeland_weeds_australia", + "machine_learning_task": "image_classification", + "agricultural_task": "weed_classification", + "location": "Australia, Oceania", + "sensor_modality": "RGB", + "real_or_synthetic": "real", + "environment": "Field", + "platform": "ground", + "input_data_format": "JPG", + "annotation_format": "directory_names", + "num_images": 17509, + "documentation": "https://github.com/AlexOlsen/DeepWeeds", + "classes": "chinee_apple, lantana, negative, parkinsonia, parthenium, prickly_acacia, rubber_vine, siam_weed, snake_weed", + "stats_mean": [ + 0.379, + 0.39, + 0.38 + ], + "stats_std": [ + 0.224, + 0.225, + 0.223 + ], + "examples_image_url": "/img/agml/sample_images/rangeland_weeds_australia_sample.webp", + "source": "huggingface", + "hf_link": "https://huggingface.co/datasets/Project-AgML/rangeland_weeds_australia", + "license": "CC BY-SA 4.0", + "citation": "@Article{Olsen2019,\n author={Olsen, Alex and Konovalov, Dmitry A. and Philippa, Bronson and Ridd, Peter and Wood, Jake C. and Johns, Jamie and Banks, Wesley and Girgenti, Benjamin and Kenny, Owen and Whinney, James and Calvert, Brendan and Azghadi, Mostafa Rahimi and White, Ronald D.},\n title={DeepWeeds: A Multiclass Weed Species Image Dataset for Deep Learning},\n journal={Scientific Reports},\n year={2019},\n month={Feb},\n day={14},\n volume={9},\n number={1},\n pages={2058},\n abstract={Robotic weed control has seen increased research of late with its potential for boosting productivity in agriculture. Majority of works focus on developing robotics for croplands, ignoring the weed management problems facing rangeland stock farmers. Perhaps the greatest obstacle to widespread uptake of robotic weed control is the robust classification of weed species in their natural environment. The unparalleled successes of deep learning make it an ideal candidate for recognising various weed species in the complex rangeland environment. This work contributes the first large, public, multiclass image dataset of weed species from the Australian rangelands; allowing for the development of robust classification methods to make robotic weed control viable. The DeepWeeds dataset consists of 17,509 labelled images of eight nationally significant weed species native to eight locations across northern Australia. This paper presents a baseline for classification performance on the dataset using the benchmark deep learning models, Inception-v3 and ResNet-50. These models achieved an average classification accuracy of 95.1{\\%} and 95.7{\\%}, respectively. We also demonstrate real time performance of the ResNet-50 architecture, with an average inference time of 53.4 ms per image. These strong results bode well for future field implementation of robotic weed control methods in the Australian rangelands.},\n issn={2045-2322},\n doi={10.1038/s41598-018-38343-3},\n url={https://doi.org/10.1038/s41598-018-38343-3}\n}", + "crop_types": null + }, + { + "name": "rice_leaf_disease_classification", + "machine_learning_task": "image_classification", + "agricultural_task": "disease_classification", + "location": "Worldwide", + "sensor_modality": "RGB", + "real_or_synthetic": "real", + "environment": "Field", + "platform": "uav", + "input_data_format": "JPG", + "annotation_format": "directory_names", + "num_images": 3829, + "documentation": "https://www.kaggle.com/datasets/anshulm257/rice-disease-dataset/data", + "classes": "Bacterial_Leaf_Blight, Brown_Spot, Healthy_Rice_Leaf, Leaf_Blast, Leaf_Scald, Sheath_Blight", + "stats_mean": [ + 0.38, + 0.511, + 0.245 + ], + "stats_std": [ + 0.186, + 0.175, + 0.135 + ], + "examples_image_url": "/img/agml/sample_images/rice_leaf_disease_classification_sample.webp", + "source": "huggingface", + "hf_link": "https://huggingface.co/datasets/Project-AgML/rice_leaf_disease_classification", + "license": "", + "citation": "", + "crop_types": [ + "rice" + ] + }, + { + "name": "riseholme_strawberry_classification_2021", + "machine_learning_task": "image_classification", + "agricultural_task": "disease_classification", + "location": null, + "sensor_modality": "RGB", + "real_or_synthetic": "real", + "environment": "Field", + "platform": "ground", + "input_data_format": "PNG", + "annotation_format": "directory_names", + "num_images": 3520, + "documentation": "https://github.com/ctyeong/Riseholme-2021", + "classes": "anomalous, occluded, ripe, unripe", + "stats_mean": [ + 0.575, + 0.464, + 0.364 + ], + "stats_std": [ + 0.198, + 0.192, + 0.177 + ], + "examples_image_url": "/img/agml/sample_images/riseholme_strawberry_classification_2021_examples.webp", + "source": "huggingface", + "hf_link": "https://huggingface.co/datasets/Project-AgML/riseholme_strawberry_classification_2021", + "license": "", + "citation": "@inproceedings{CWSC21,\n title={Self-supervised Representation Learning for Reliable Robotic Monitoring of Fruit Anomalies},\n author={Choi, Taeyeong and Would, Owen and Salazar-Gomez, Adrian and Cielniak, Grzegorz},\n booktitle={2022 International Conference on Robotics and Automation (ICRA)},\n pages={2266--2272},\n year={2022},\n organization={IEEE}\n}", + "crop_types": [ + "strawberry" + ] + }, + { + "name": "tomato_leaf_disease", + "machine_learning_task": "image_classification", + "agricultural_task": "disease_classification", + "location": "Worldwide", + "sensor_modality": "RGB", + "real_or_synthetic": "real", + "environment": "Lab", + "platform": "handheld", + "input_data_format": "JPEG", + "annotation_format": "directory_names", + "num_images": 11000, + "documentation": "https://www.kaggle.com/datasets/kaustubhb999/tomatoleaf?resource=download", + "classes": "Bacterial Spot, Early Blight, Healthy, Late Blight, Leaf Mold, Septoria Leaf Spot, Spider Mites Two-spotted Spider Mite, Target Spot, Tomato Mosaic Virus, Tomato Yellow Leaf Curl Virus", + "stats_mean": [ + 0.453, + 0.463, + 0.419 + ], + "stats_std": [ + 0.169, + 0.148, + 0.185 + ], + "examples_image_url": "/img/agml/sample_images/tomato_leaf_disease_sample.webp", + "source": "huggingface", + "hf_link": "https://huggingface.co/datasets/Project-AgML/tomato_leaf_disease", + "license": "CC0: Public Domain", + "citation": "", + "crop_types": [ + "tomato" + ] + }, + { + "name": "vine_virus_photo_dataset", + "machine_learning_task": "image_classification", + "agricultural_task": "disease_classification", + "location": "Worldwide", + "sensor_modality": "RGB", + "real_or_synthetic": "real", + "environment": "Field", + "platform": "handheld/ground", + "input_data_format": "jpg, png, jpeg, JPG", + "annotation_format": "directory_names", + "num_images": 3866, + "documentation": null, + "classes": "Leafroll 3, No Virus, Other Red, Red Blotch", + "stats_mean": [ + 0.45, + 0.449, + 0.295 + ], + "stats_std": [ + 0.231, + 0.228, + 0.23 + ], + "examples_image_url": "/img/agml/sample_images/vine_virus_photo_dataset_sample.webp", + "source": "huggingface", + "hf_link": "https://huggingface.co/datasets/Project-AgML/vine_virus_photo_dataset", + "license": "Apache 2.0", + "citation": "", + "crop_types": [ + "vine" + ] + }, + { + "name": "durian_disease_classification", + "machine_learning_task": "image_classification", + "agricultural_task": "disease_classification", + "location": "Vietnam", + "environment": "field", + "real_or_synthetic": "real", + "crop_types": [ + "durian" + ], + "sensor_modality": "rgb", + "input_data_format": "image_folder", + "annotation_format": "classLabel", + "num_images": 5451, + "classes": [ + "anthracnose_disease", + "canker_disease", + "fruit_rot", + "mealybug_infestation", + "pink_disease", + "sooty_mold", + "stem_blight", + "stem_cracking_ gummosis", + "thrips_disease", + "yellow_leaf" + ], + "license": "cc-by-4.0", + "documentation": "https://doi.org/10.1016/j.dib.2025.112244", + "citation": "Nguyen, Tan (2025), “Image Dataset of Ten Durian Diseases Captured in Real-Field Conditions from a Family Orchard in Vinh Long, Vietnam”, Mendeley Data, V1, doi: 10.17632/mhjwyb5p48.1", + "source": "huggingface", + "hf_link": "https://huggingface.co/datasets/Project-AgML/durian_disease_classification" + }, + { + "name": "betel_leaf_disease_classification", + "machine_learning_task": "image_classification", + "agricultural_task": "disease_classification", + "location": "Bangladesh, Asia", + "sensor_modality": "RGB", + "real_or_synthetic": "real", + "environment": "field", + "platform": "uav", + "input_data_format": "JPG", + "annotation_format": "directory_names", + "num_images": 3589, + "documentation": "https://www.semanticscholar.org/paper/Betel-Leaf-Diseases-Classification-using-Machine-A-David-Mukunthan/38208c9d2306444e3b9f8593715a46e2dcf26f44#paper-topics", + "classes": "Bacterial_Leaf_Disease, Dried_Leaf, Fungal_Brown_Spot_Disease, Healthy_Leaf", + "stats_mean": [ + 0.443, + 0.52, + 0.324 + ], + "stats_std": [ + 0.186, + 0.197, + 0.218 + ], + "examples_image_url": "/img/agml/sample_images/betel_leaf_disease_classification_examples.webp", + "source": "huggingface", + "hf_link": "https://huggingface.co/datasets/Project-AgML/betel_leaf_disease_classification", + "license": "CC BY 4.0", + "citation": "Rashid, Mohammad Rifat Ahmmad; Hossain, Md. Miskat ; Biswas, Joy ; Majumder, Hredoy (2024), “Betel Leaf Image Dataset from Bangladesh”, Mendeley Data, V2, doi: 10.17632/g7fpgj57wc.2", + "crop_types": [ + "betel" + ] + }, + { + "name": "tea_leaf_disease_classification", + "machine_learning_task": "image_classification", + "agricultural_task": "disease_classification", + "location": "India, Asia", + "sensor_modality": "RGB", + "real_or_synthetic": "real", + "platform": "uav", + "input_data_format": "JPG", + "annotation_format": "directory_names", + "num_images": 5867, + "documentation": "https://www.kaggle.com/datasets/saikatdatta1994/tea-leaf-disease", + "classes": "algal_spot, brown_blight, gray_blight, healthy, helopeltis, red_spot", + "stats_mean": [ + 0.72, + 0.715, + 0.721 + ], + "stats_std": [ + 0.264, + 0.243, + 0.325 + ], + "examples_image_url": "/img/agml/sample_images/tea_leaf_disease_classification_examples.webp", + "source": "huggingface", + "hf_link": "https://huggingface.co/datasets/Project-AgML/tea_leaf_disease_classification", + "license": "CC BY-NC 4.0", + "citation": "@article{BALASUNDARAM2025103784, title = {Tea leaf disease detection using segment anything model and deep convolutional neural networks}, journal = {Results in Engineering}, volume = {25}, pages = {103784}, year = {2025}, issn = {2590-1230}, doi = {https://doi.org/10.1016/j.rineng.2024.103784}, url = {https://www.sciencedirect.com/science/article/pii/S2590123024020279}, author = {Ananthakrishnan Balasundaram and Prem Sundaresan and Aryan Bhavsar and Mishti Mattu and Muthu Subash Kavitha and Ayesha Shaik}}", + "crop_types": [ + "tea" + ] + }, + { + "name": "soybean_insect_classification", + "machine_learning_task": "image_classification", + "agricultural_task": "pest_classification", + "location": "Brazil, South America", + "sensor_modality": "RGB", + "real_or_synthetic": "real", + "platform": "uav", + "input_data_format": "JPG", + "annotation_format": "directory_names", + "num_images": 6410, + "documentation": "https://data.mendeley.com/datasets/bycbh73438/1", + "classes": "Caterpillar, Diabrotica_speciosa, Healthy", + "stats_mean": [ + 0.413, + 0.516, + 0.335 + ], + "stats_std": [ + 0.22, + 0.23, + 0.203 + ], + "examples_image_url": "/img/agml/sample_images/soybean_insect_classification_examples.webp", + "source": "huggingface", + "hf_link": "https://huggingface.co/datasets/Project-AgML/soybean_insect_classification", + "license": "CC BY 4.0", + "citation": "Mignoni, Maria Eloisa (2021), “Images of Soybean Leaves”, Mendeley Data, V1, doi: 10.17632/bycbh73438.1", + "crop_types": [ + "soybean" + ] + }, + { + "name": "sunflower_disease_classification", + "machine_learning_task": "image_classification", + "agricultural_task": "disease_classification", + "location": "Bangladesh, Asia", + "sensor_modality": "RGB", + "real_or_synthetic": "real", + "platform": "uav", + "input_data_format": "JPG", + "annotation_format": "directory_names", + "num_images": 2358, + "documentation": "https://doi.org/10.1016/j.dib.2022.108043", + "classes": "Downy_mildew, Fresh_leaf, Gray_mold, Leaf_scars", + "stats_mean": [ + 0.456, + 0.454, + 0.244 + ], + "stats_std": [ + 0.225, + 0.214, + 0.18 + ], + "examples_image_url": "/img/agml/sample_images/sunflower_disease_classification_examples.webp", + "source": "huggingface", + "hf_link": "https://huggingface.co/datasets/Project-AgML/sunflower_disease_classification", + "license": "CC BY 4.0", + "citation": "Rajbongshi, Aditya; Sara, Umme ; Akter, Bonna ; Shakil, Rashiduzzaman ; Sazzad, Sadia (2022), “Sun Flower Fruits and Leaves dataset for Sunflower Disease Classification through Machine Learning and Deep Learning”, Mendeley Data, V1, doi: 10.17632/b83hmrzth8.1", + "crop_types": [ + "sunflower" + ] + }, + { + "name": "carrot_weeds_germany", + "machine_learning_task": "semantic_segmentation", + "agricultural_task": "weed_segmentation", + "location": "Germany, Europe", + "sensor_modality": "RGB", + "real_or_synthetic": "real", + "environment": "Field", + "platform": "ground_mobile", + "input_data_format": "PNG", + "annotation_format": "image", + "num_images": 60, + "documentation": "https://github.com/cwfid/dataset", + "classes": "carrot, weeds", + "stats_mean": [ + 0.274, + 0.311, + 0.274 + ], + "stats_std": [ + 0.086, + 0.1, + 0.086 + ], + "examples_image_url": "/img/agml/sample_images/carrot_weeds_germany_examples.webp", + "source": "huggingface", + "hf_link": "https://huggingface.co/datasets/Project-AgML/sunflower_disease_classification", + "license": "", + "citation": "@inproceedings{haug15,\n author={Haug, Sebastian and Ostermann, J{\\\"o}rn},\n title={A Crop/Weed Field Image Dataset for the Evaluation of Computer Vision Based Precision Agriculture Tasks},\n year={2015},\n booktitle={Computer Vision - ECCV 2014 Workshops},\n doi={10.1007/978-3-319-16220-1_8},\n url={http://dx.doi.org/10.1007/978-3-319-16220-1_8},\n pages={105--116}\n}", + "crop_types": [ + "carrot" + ] + }, + { + "name": "apple_flower_segmentation", + "machine_learning_task": "semantic_segmentation", + "agricultural_task": "flower_segmentation", + "location": "United States, North America", + "sensor_modality": "RGB", + "real_or_synthetic": "real", + "environment": "Field", + "platform": "ground", + "input_data_format": "JPG", + "annotation_format": "image", + "num_images": 148, + "documentation": "https://data.nal.usda.gov/dataset/data-multi-species-fruit-flower-detection-using-refined-semantic-segmentation-network", + "classes": "apple", + "stats_mean": [ + 0.458, + 0.479, + 0.405 + ], + "stats_std": [ + 0.204, + 0.193, + 0.216 + ], + "examples_image_url": "/img/agml/sample_images/apple_flower_segmentation_examples.webp", + "source": "huggingface", + "hf_link": "https://huggingface.co/datasets/Project-AgML/apple_flower_segmentation", + "license": "US Public Domain", + "citation": "@ARTICLE{8392727,\n author={Dias, Philipe A. and Tabb, Amy and Medeiros, Henry},\n journal={IEEE Robotics and Automation Letters}, \n title={Multispecies Fruit Flower Detection Using a Refined Semantic Segmentation Network}, \n year={2018},\n volume={3},\n number={4},\n pages={3003-3010},\n doi={10.1109/LRA.2018.2849498}}", + "crop_types": [ + "apple" + ] + }, + { + "name": "apple_segmentation_minnesota", + "machine_learning_task": "semantic_segmentation", + "agricultural_task": "fruit_segmentation", + "location": "United States, North America", + "sensor_modality": "RGB", + "real_or_synthetic": "real", + "environment": "Field", + "platform": "ground", + "input_data_format": "PNG", + "annotation_format": "image", + "num_images": 670, + "documentation": "https://rsn.umn.edu/projects/orchard-monitoring/minneapple", + "classes": "apple", + "stats_mean": [ + 0.374, + 0.437, + 0.338 + ], + "stats_std": [ + 0.263, + 0.288, + 0.331 + ], + "examples_image_url": "/img/agml/sample_images/apple_segmentation_minnesota_examples.webp", + "source": "huggingface", + "hf_link": "https://huggingface.co/datasets/Project-AgML/apple_segmentation_minnesota", + "license": "MIT", + "citation": "@misc{hani2019minneapple,\n title={MinneApple: A Benchmark Dataset for Apple Detection and Segmentation},\n author={Nicolai Häni and Pravakar Roy and Volkan Isler}\n year={2019},\n eprint={1909.06441},\n archivePrefix={arXiv},\n primaryClass={cs.CV}\n}", + "crop_types": [ + "apple" + ] + }, + { + "name": "rice_seedling_segmentation", + "machine_learning_task": "semantic_segmentation", + "agricultural_task": "weed_segmentation", + "location": "China, Asia", + "sensor_modality": "RGB", + "real_or_synthetic": "real", + "environment": "Field", + "platform": "handheld", + "input_data_format": "JPG", + "annotation_format": "image", + "num_images": 224, + "documentation": "https://github.com/kabbas570/CED-Net-Crops-and-Weeds-Segmentation-for-Smart-Farming-Using-a-Small-Cascaded-Encoder-Decoder-Archi", + "classes": "Rice, Weed", + "stats_mean": [ + 0.655, + 0.701, + 0.635 + ], + "stats_std": [ + 0.085, + 0.108, + 0.111 + ], + "examples_image_url": "/img/agml/sample_images/rice_seedling_segmentation_examples.webp", + "source": "huggingface", + "hf_link": "https://huggingface.co/datasets/Project-AgML/apple_segmentation_minnesota", + "license": "", + "citation": "@Article{electronics9101602,\n AUTHOR = {Khan, Abbas and Ilyas, Talha and Umraiz, Muhammad and Mannan, Zubaer Ibna and Kim, Hyongsuk},\n TITLE = {CED-Net: Crops and Weeds Segmentation for Smart Farming Using a Small Cascaded Encoder-Decoder Architecture},\n JOURNAL = {Electronics},\n VOLUME = {9},\n YEAR = {2020},\n NUMBER = {10},\n ARTICLE-NUMBER = {1602},\n URL = {https://www.mdpi.com/2079-9292/9/10/1602},\n ISSN = {2079-9292},\n ABSTRACT = {Convolutional neural networks (CNNs) have achieved state-of-the-art performance in numerous aspects of human life and the agricultural sector is no exception. One of the main objectives of deep learning for smart farming is to identify the precise location of weeds and crops on farmland. In this paper, we propose a semantic segmentation method based on a cascaded encoder-decoder network, namely CED-Net, to differentiate weeds from crops. The existing architectures for weeds and crops segmentation are quite deep, with millions of parameters that require longer training time. To overcome such limitations, we propose an idea of training small networks in cascade to obtain coarse-to-fine predictions, which are then combined to produce the final results. Evaluation of the proposed network and comparison with other state-of-the-art networks are conducted using four publicly available datasets: rice seeding and weed dataset, BoniRob dataset, carrot crop vs. weed dataset, and a paddy–millet dataset. The experimental results and their comparisons proclaim that the proposed network outperforms state-of-the-art architectures, such as U-Net, SegNet, FCN-8s, and DeepLabv3, over intersection over union (IoU), F1-score, sensitivity, true detection rate, and average precision comparison metrics by utilizing only (1/5.74 × U-Net), (1/5.77 × SegNet), (1/3.04 × FCN-8s), and (1/3.24 × DeepLabv3) fractions of total parameters.},\n DOI = {10.3390/electronics9101602}\n}", + "crop_types": [ + "rice" + ] + }, + { + "name": "sugarbeet_weed_segmentation", + "machine_learning_task": "semantic_segmentation", + "agricultural_task": "weed_segmentation", + "location": "None, None", + "sensor_modality": "RGB", + "real_or_synthetic": "real", + "environment": "Field", + "platform": "ground", + "input_data_format": "PNG", + "annotation_format": "image", + "num_images": 1931, + "documentation": "https://github.com/inkyusa/weedNet", + "classes": "sugar_beet, random_weeds", + "stats_mean": [ + 0.374, + 0.374, + 0.374 + ], + "stats_std": [ + 0.17, + 0.17, + 0.17 + ], + "examples_image_url": "/img/agml/sample_images/sugarbeet_weed_segmentation_examples.webp", + "source": "huggingface", + "hf_link": "https://huggingface.co/datasets/Project-AgML/sugarbeet_weed_segmentation", + "license": "GPL-3.0", + "citation": "@ARTICLE{8115245,\n author={I. Sa and Z. Chen and M. Popović and R. Khanna and F. Liebisch and J. Nieto and R. Siegwart},\n journal={IEEE Robotics and Automation Letters},\n title={weedNet: Dense Semantic Weed Classification Using Multispectral Images and MAV for Smart Farming},\n year={2018},\n volume={3},\n number={1},\n pages={588-595},\n keywords={agriculture;agrochemicals;autonomous aerial vehicles;control engineering computing;convolution;crops;feature extraction;image classification;learning (artificial intelligence);neural nets;vegetation;MAV;SegNet;convolutional neural network;crop health;crop management;curve classification metrics;dense semantic classes;dense semantic weed classification;encoder-decoder;input image channels;multispectral images;selective weed treatment;vegetation index;weed detection;Agriculture;Cameras;Image segmentation;Robots;Semantics;Training;Vegetation mapping;Aerial systems;agricultural automation;applications;robotics in agriculture and forestry},\n doi={10.1109/LRA.2017.2774979},\n ISSN={},\n month={Jan}\n}", + "crop_types": [ + "sugarbeet" + ] + }, + { + "name": "bean_synthetic_earlygrowth_aerial", + "machine_learning_task": "semantic_segmentation", + "agricultural_task": "plant_segmentation", + "location": "Digital, Digital", + "sensor_modality": "RGB", + "real_or_synthetic": "synthetic", + "environment": "Field", + "platform": "aerial", + "input_data_format": "JPG", + "annotation_format": "image", + "num_images": 2500, + "documentation": "https://github.com/Project-AgML/AgML/blob/main/docs/datasets/bean_synthetic_earlygrowth_aerial.md", + "classes": "leaves, branches", + "stats_mean": null, + "stats_std": null, + "examples_image_url": "/img/agml/sample_images/bean_synthetic_earlygrowth_aerial_examples.webp", + "source": "huggingface", + "hf_link": "https://huggingface.co/datasets/Project-AgML/bean_synthetic_earlygrowth_aerial", + "license": "MIT", + "citation": "@ARTICLE{10.3389/fpls.2019.01185,\n \nAUTHOR={Bailey, Brian N.}, \n\t \nTITLE={Helios: A Scalable 3D Plant and Environmental Biophysical Modeling Framework}, \n\t\nJOURNAL={Frontiers in Plant Science}, \n\t\nVOLUME={10}, \n\t\nYEAR={2019}, \n\t \nURL={https://www.frontiersin.org/article/10.3389/fpls.2019.01185}, \n\t\nDOI={10.3389/fpls.2019.01185}, \n\t\nISSN={1664-462X}, \n \nABSTRACT={This article presents an overview of Helios, a new three-dimensional (3D) plant and environmental modeling framework. Helios is a model coupling framework designed to provide maximum flexibility in integrating and running arbitrary 3D environmental system models. Users interact with Helios through a well-documented open-source C++ API. Version 1.0 comes with model plug-ins for radiation transport, the surface energy balance, stomatal conductance, photosynthesis, solar position, and procedural tree generation. Additional plug-ins are also available for visualizing model geometry and data and for processing and integrating LiDAR scanning data. Many of the plug-ins perform calculations on the graphics processing unit, which allows for efficient simulation of very large domains with high detail. An example modeling study is presented in which leaf-level heterogeneity in water usage and photosynthesis of an orchard is examined to understand how this leaf-scale variability contributes to whole-tree and -canopy fluxes.}\n}", + "crop_types": [ + "bean" + ] + }, + { + "name": "growliflower_cauliflower_segmentation", + "machine_learning_task": "semantic_segmentation", + "agricultural_task": "crop_segmentation", + "location": "Worldwide", + "sensor_modality": "RGB", + "real_or_synthetic": "real", + "environment": "Field", + "platform": "handheld/ground", + "input_data_format": "JPG", + "annotation_format": "image", + "num_images": 1542, + "documentation": "https://phenoroam.phenorob.de/geonetwork/srv/eng/catalog.search#/metadata/cb328232-31f5-4b84-a929-8e1ee551d66a", + "classes": "maskLeaves, maskPlants, maskStems, maskVoid", + "stats_mean": null, + "stats_std": null, + "examples_image_url": "/img/agml/sample_images/growliflower_cauliflower_segmentation_examples.webp", + "source": "huggingface", + "hf_link": "https://huggingface.co/datasets/Project-AgML/growliflower_cauliflower_segmentation", + "license": "", + "citation": "Kierdorf, Jana & Junker-Frohn, Laura & Delaney, Mike & Olave, Mariele & Burkart, Andreas & Jaenicke, Hannah & Muller, Onno & Roscher, Ribana. (2022). GrowliFlower: An image time‐series dataset for GROWth analysis of cauLIFLOWER. Journal of Field Robotics. 40. 10.1002/rob.22122. ", + "crop_types": [ + "cauliflower" + ] + }, + { + "name": "peachpear_flower_segmentation", + "machine_learning_task": "semantic_segmentation", + "agricultural_task": "flower_segmentation", + "location": "Worldwide", + "sensor_modality": null, + "real_or_synthetic": "real", + "environment": "Field", + "platform": null, + "input_data_format": null, + "annotation_format": null, + "num_images": 42, + "documentation": "https://data.nal.usda.gov/dataset/data-multi-species-fruit-flower-detection-using-refined-semantic-segmentation-network", + "classes": "Flower", + "stats_mean": [ + 0.438, + 0.435, + 0.415 + ], + "stats_std": [ + 0.208, + 0.214, + 0.244 + ], + "examples_image_url": "/img/agml/sample_images/peachpear_flower_segmentation_examples.webp", + "source": "huggingface", + "hf_link": "https://huggingface.co/datasets/Project-AgML/peachpear_flower_segmentation", + "license": "US Public Domain", + "citation": "@ARTICLE{8392727,\n author={Dias, Philipe A. and Tabb, Amy and Medeiros, Henry},\n journal={IEEE Robotics and Automation Letters}, \n title={Multispecies Fruit Flower Detection Using a Refined Semantic Segmentation Network}, \n year={2018},\n volume={3},\n number={4},\n pages={3003-3010},\n doi={10.1109/LRA.2018.2849498}}", + "crop_types": [ + "peach", + "pear" + ] + }, + { + "name": "red_grapes_and_leaves_segmentation", + "machine_learning_task": "semantic_segmentation", + "agricultural_task": "vineyard_scene_segmentation", + "location": "Greece, Europe", + "sensor_modality": "RGB", + "real_or_synthetic": "real", + "environment": "Field", + "platform": "handheld/ground", + "input_data_format": "JPG", + "annotation_format": "image", + "num_images": 258, + "documentation": "https://link.springer.com/chapter/10.1007/978-3-030-48791-1_22", + "classes": "Leaf, Grape", + "stats_mean": [ + 0.392, + 0.493, + 0.525 + ], + "stats_std": [ + 0.272, + 0.287, + 0.283 + ], + "examples_image_url": "/img/agml/sample_images/red_grapes_and_leaves_segmentation_examples.webp", + "source": "huggingface", + "hf_link": "https://huggingface.co/datasets/Project-AgML/red_grapes_and_leaves_segmentation", + "license": "", + "citation": "@inproceedings{kalampokas2020semantic,\n title={Semantic segmentation of vineyard images using convolutional neural networks},\n author={Kalampokas, Theofanis and Tziridis, Konstantinos and Nikolaou, Alexandros and Vrochidou, Eleni and Papakostas, George A and Pachidis, Theodore and Kaburlasos, Vassilis G},\n booktitle={International Conference on Engineering Applications of Neural Networks},\n pages={292--303},\n year={2020},\n organization={Springer}}", + "crop_types": [ + "grape" + ] + }, + { + "name": "vegann_multicrop_presence_segmentation", + "machine_learning_task": "semantic_segmentation", + "agricultural_task": "vegetation_segmentation", + "location": "Worldwide", + "sensor_modality": "RGB", + "real_or_synthetic": "real", + "platform": "aerial", + "input_data_format": "PNG", + "annotation_format": "image", + "num_images": 3775, + "documentation": "https://zenodo.org/records/7636408", + "classes": "plant", + "stats_mean": [ + 16.392, + 18.685, + 14.235 + ], + "stats_std": [ + 4.59, + 5.818, + 4.19 + ], + "examples_image_url": "/img/agml/sample_images/vegann_multicrop_presence_segmentation_examples.webp", + "source": "huggingface", + "hf_link": "https://huggingface.co/datasets/Project-AgML/vegann_multicrop_presence_segmentation", + "license": "CC BY-SA 4.0", + "citation": " @article{Madec_Irfan_Velumani_Baret_David_Daubige_Samatan_Serouart_Smith_James_et al._2023, title={VegAnn, Vegetation Annotation of multi-crop RGB images acquired under diverse conditions for segmentation}, volume={10}, ISSN={2052-4463}, url={https://www.nature.com/articles/s41597-023-02098-y}, DOI={10.1038/s41597-023-02098-y}, abstractNote={Abstract\n \n Applying deep learning to images of cropping systems provides new knowledge and insights in research and commercial applications. Semantic segmentation or pixel-wise classification, of RGB images acquired at the ground level, into vegetation and background is a critical step in the estimation of several canopy traits. Current state of the art methodologies based on convolutional neural networks (CNNs) are trained on datasets acquired under controlled or indoor environments. These models are unable to generalize to real-world images and hence need to be fine-tuned using new labelled datasets. This motivated the creation of the VegAnn -\n Veg\n etation\n Ann\n otation - dataset, a collection of 3775 multi-crop RGB images acquired for different phenological stages using different systems and platforms in diverse illumination conditions. We anticipate that VegAnn will help improving segmentation algorithm performances, facilitate benchmarking and promote large-scale crop vegetation segmentation research.}, number={1}, journal={Scientific Data}, author={Madec, Simon and Irfan, Kamran and Velumani, Kaaviya and Baret, Frederic and David, Etienne and Daubige, Gaetan and Samatan, Lucas Bernigaud and Serouart, Mario and Smith, Daniel and James, Chrisbin and Camacho, Fernando and Guo, Wei and De Solan, Benoit and Chapman, Scott C. and Weiss, Marie}, year={2023}, month=may, pages={302}, language={en} }\n", + "crop_types": null + }, + { + "name": "white_grapes_and_leaves_segmentation", + "machine_learning_task": "semantic_segmentation", + "agricultural_task": "vineyard_scene_segmentation", + "location": "Greece, Europe", + "sensor_modality": "RGB", + "real_or_synthetic": "real", + "platform": "handheld/ground", + "input_data_format": "JPG", + "annotation_format": "image", + "num_images": 273, + "documentation": "https://link.springer.com/chapter/10.1007/978-3-030-48791-1_22", + "classes": "Leaf, Grape", + "stats_mean": [ + 0.309, + 0.473, + 0.524 + ], + "stats_std": [ + 0.233, + 0.246, + 0.253 + ], + "examples_image_url": "/img/agml/sample_images/white_grapes_and_leaves_segmentation_examples.webp", + "source": "huggingface", + "hf_link": "https://huggingface.co/datasets/Project-AgML/white_grapes_and_leaves_segmentation", + "license": "", + "citation": "@inproceedings{kalampokas2020semantic,\n title={Semantic segmentation of vineyard images using convolutional neural networks},\n author={Kalampokas, Theofanis and Tziridis, Konstantinos and Nikolaou, Alexandros and Vrochidou, Eleni and Papakostas, George A and Pachidis, Theodore and Kaburlasos, Vassilis G},\n booktitle={International Conference on Engineering Applications of Neural Networks},\n pages={292--303},\n year={2020},\n organization={Springer}}", + "crop_types": [ + "grape" + ] } ] diff --git a/static/img/agml/sample_images/crop_weeds_greece_sample.webp b/static/img/agml/sample_images/crop_weeds_greece_sample.webp new file mode 100644 index 0000000..1a0c7ca Binary files /dev/null and b/static/img/agml/sample_images/crop_weeds_greece_sample.webp differ diff --git a/static/img/agml/sample_images/durian_disease_classification_sample.webp b/static/img/agml/sample_images/durian_disease_classification_sample.webp new file mode 100644 index 0000000..ca3aec0 Binary files /dev/null and b/static/img/agml/sample_images/durian_disease_classification_sample.webp differ diff --git a/static/img/agml/sample_images/guava_disease_pakistan_sample.webp b/static/img/agml/sample_images/guava_disease_pakistan_sample.webp new file mode 100644 index 0000000..54b124b Binary files /dev/null and b/static/img/agml/sample_images/guava_disease_pakistan_sample.webp differ diff --git a/static/img/agml/sample_images/plant_doc_classification_sample.webp b/static/img/agml/sample_images/plant_doc_classification_sample.webp new file mode 100644 index 0000000..082e5f0 Binary files /dev/null and b/static/img/agml/sample_images/plant_doc_classification_sample.webp differ diff --git a/static/img/agml/sample_images/plant_seedlings_aarhus_sample.webp b/static/img/agml/sample_images/plant_seedlings_aarhus_sample.webp new file mode 100644 index 0000000..b85bf11 Binary files /dev/null and b/static/img/agml/sample_images/plant_seedlings_aarhus_sample.webp differ diff --git a/static/img/agml/sample_images/plant_village_classification_sample.webp b/static/img/agml/sample_images/plant_village_classification_sample.webp new file mode 100644 index 0000000..fe4a132 Binary files /dev/null and b/static/img/agml/sample_images/plant_village_classification_sample.webp differ diff --git a/static/img/agml/sample_images/rangeland_weeds_australia_sample.webp b/static/img/agml/sample_images/rangeland_weeds_australia_sample.webp new file mode 100644 index 0000000..6159981 Binary files /dev/null and b/static/img/agml/sample_images/rangeland_weeds_australia_sample.webp differ diff --git a/static/img/agml/sample_images/rice_leaf_disease_classification_sample.webp b/static/img/agml/sample_images/rice_leaf_disease_classification_sample.webp new file mode 100644 index 0000000..fb78c24 Binary files /dev/null and b/static/img/agml/sample_images/rice_leaf_disease_classification_sample.webp differ diff --git a/static/img/agml/sample_images/soybean_weed_uav_brazil_sample.webp b/static/img/agml/sample_images/soybean_weed_uav_brazil_sample.webp new file mode 100644 index 0000000..ac44a56 Binary files /dev/null and b/static/img/agml/sample_images/soybean_weed_uav_brazil_sample.webp differ diff --git a/static/img/agml/sample_images/sugarcane_damage_usa_sample.webp b/static/img/agml/sample_images/sugarcane_damage_usa_sample.webp new file mode 100644 index 0000000..4c0f6e5 Binary files /dev/null and b/static/img/agml/sample_images/sugarcane_damage_usa_sample.webp differ diff --git a/static/img/agml/sample_images/tomato_leaf_disease_sample.webp b/static/img/agml/sample_images/tomato_leaf_disease_sample.webp new file mode 100644 index 0000000..237ea8f Binary files /dev/null and b/static/img/agml/sample_images/tomato_leaf_disease_sample.webp differ diff --git a/static/img/agml/sample_images/vine_virus_photo_dataset_sample.webp b/static/img/agml/sample_images/vine_virus_photo_dataset_sample.webp new file mode 100644 index 0000000..786b337 Binary files /dev/null and b/static/img/agml/sample_images/vine_virus_photo_dataset_sample.webp differ