Smart Gym System is a real-time model, that aims to help trainees to train in their home as a solution that saves time, effort, and money to go to Gym and follow up with a Couch to train them.
We aim in our system to get best performance and to be used by multi-person in real-time.
The project provides a solution to count repetitions of a Gym exercise in real time. The method uses pose estimation to track athletes, recognize their performed exercises, count the repetitions, and analyze the performance of the repetitions by providing early real-time feedback. YOLOv7 Pose is a real-time network that detects human poses and extracts their 3D skeleton keypoints from an input video or an external camera. YOLOv7 Pose is trained on the COCO dataset which has 17 landmark topologies. It is implemented in PyTorch making the code super easy to customize as per your need. The pre-trained keypoint detection model is yolov7-w6-pose.pth. In order to an effective counting and analyzing repetitions, each exercise has different pre-selected parameters, upper and lower range of motion, major joint, and type of Exercise. The method measures, filters, and smooths the angles of the major joint for the performed exercise. Then, it counts the repetitions of the exercise, finally it provides feedback.
I went to the gym today, but how well did I do? And where should I improve? ... Ah, my back hurts slightly! Artificial intelligence technology has made its way absolutely necessary in a variety of industries including the fitness industry. Human pose estimation is one of the important researches in the field of Computer Vision for the last few years. In this project, pose estimation and deep machine learning techniques are combined to analyze the performance and report feedback on the repetitions of performed exercises in real time. Involving machine learning technology in the fitness industry could help the judges to count repetitions of any exercise during Weightlifting or CrossFit competitions. The trainee cannot perform the exercises alone without the guidance and follow-up of the trainer so that he does not injure himself by mistake while doing exercises. User engagement can be sustained, and injuries avoided by being able to reconstruct 3d human pose Estimation, relate it to good training practices, identify errors, and provide early real-time feedback. The system can be used at home, outdoors, or at the gym.
- Muhammad El-Qappaney
Data scientist - Alaa Elmohamadey
Data scientist - Muhammad Hussien
Software engineer - Ahmed Alaa
Software engineer - Muhammad Arbi
Software engineer