BarTrace

Application to track the path and speed of a barbell when weightlifting.
84 Downloads
Updated 16 Jul 2020

Started by Dave Bergstein (dbergstein@gmail.com)

I'm learning to weightlift and find it helpful to see the path and speed of the barbell of my lifts. I also like playing with deep learning. The code is on GitHub. Pull Requests welcomed. Feel free to fork and use.

I use imfindcircle to label the data (though my use of it is slow and sometimes inaccurate). I then use this labeled data (inaccuracies and all) to train a CNN where I replace the final layers with a YOLOv2 network. The resulting neural network is more accurate and much faster. My network training code is included, but I only include a sample of the data given it's size. The videos were all taken at Grit City, Bronx, NY with either Randy Triunfel (my coach) or me, so the model wasn't trained with much variety.

See StartHere.mlx for details and getting started

Cite As

David Bergstein (2024). BarTrace (https://github.com/DaveBergstein/BarTrace/releases/tag/1.0.0), GitHub. Retrieved .

MATLAB Release Compatibility
Created with R2020a
Compatible with any release
Platform Compatibility
Windows macOS Linux

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!
Version Published Release Notes
1.0.0

See release notes for this release on GitHub: https://github.com/DaveBergstein/BarTrace/releases/tag/1.0.0

0.25

See release notes for this release on GitHub: https://github.com/DaveBergstein/BarTrace/releases/tag/v0.25

0.2

See release notes for this release on GitHub: https://github.com/DaveBergstein/BarTrace/releases/tag/v0.2
See release notes for this release on GitHub: https://github.com/DaveBergstein/BarTrace/releases/tag/v0.2

0.1

To view or report issues in this GitHub add-on, visit the GitHub Repository.
To view or report issues in this GitHub add-on, visit the GitHub Repository.