An extension of the previous 'Fitness-AI-Coach': a complete web application with real-time exercise recognition and counting. The exercise recognition model achieves 99% accuracy on the test set and 95% and 90% on two additional external datasets. || Give a star ⭐ to the repository if it was useful. Thank you! 😊

Learning to learn for Personalised Human Activity Recognition

A lightweight, privacy-first, real-time rep counter for common bodyweight exercises. GC_Fit uses MediaPipe's Pose model and OpenCV to detect joint landmarks from a webcam feed and count repetitions of exercises (push-ups, sit-ups, squats) based on simple geometric rules.

A real-time fitness pose detection system for recognizing push-ups, squats, and sit-ups using MediaPipe and LSTM

基于计算机视觉（姿态估计）的运动动作识别、规范性评估与实时反馈系统 核心对比：MediaPipe+1D-CNN+GRU vs 传统DTW模板匹配 / 规则驱动方法 应用场景：大众健身、居家体能训练、青少年体测辅导 (桌面端/移动端)

A real-time pose-based exercise recognition project. It classifies exercise motion from short temporal windows, estimates repetition counts with a deterministic finite-state method, and reports similarity against class-level motion centroids.

A smart, wearable glove that recognizes and tracks exercise movements using AI, real-time feedback, and an interactive button interface.

Deep learning model implementation and research projects including AlexNet, InceptionV3, VGG16, ZFNet, Bangla digit recognition, flower classification, rice classification, and exercise detection using TensorFlow and Keras.

End-to-end Human Pose Estimation system for real-time exercise analysis with CNN-based age-gender prediction and Flask API deployment.