Deadlift-o-Meter is a project that utilizes a Scikit-Learn model, Mediapipe, and Tkinter to count correct deadlift reps using a live webcam feed. The application analyzes the user's body movements and provides real-time feedback on their performance.
- Live webcam feed for real-time analysis
- Scikit-Learn model for body movement classification
- Mediapipe for pose estimation and landmark detection
- Tkinter for building the graphical user interface
- Rep counter for tracking the number of correct deadlift reps
- Stage detection for identifying the up and down phases of the deadlift
- Probability estimation for evaluating the quality of the performed reps
To use the Deadlift-o-Meter project, follow these steps:
- Clone the repository:
git clone https://github.com/mostafa-ghaith/Deadlift-o-Meter.git - Run the
main.pyfile to launch the Deadlift-o-Meter application. - Ensure that the required dependencies are installed.
- Perform deadlifts in front of the webcam. The application will provide real-time feedback on the number of correct reps, the current stage (up or down), and the probability estimation for each rep.
Feel free to explore the code, contribute to the project, and customize it according to your needs.
Credits: This project is based on the work of Nicholas Renotte. I would like to thank Nicholas Renotte for his contributions and inspiration.