-
-
Good form example
-
Bad form example
Inspiration
Have you ever gone to the gym, and wondered if you were doing your exercises correctly? I know I have- I once blew out my back trying to deadlift 300 pounds. At that moment, I wished I had something to tell me if my form was right. Well, that’s exactly what we set out to do with our project.
What it does
Our solution involves using computer vision and machine learning to give the user visual cues indicating how good their form is for a particular exercise.
How we built it
The technologies we used to tackle this endeavor include OpenCV, Posenet, Tensorflow, and Python!
Challenges we ran into
The biggest challenge we had was finding the right libraries for our project! We had to go through a LOT of different libraries before we settled on one that was just right for us. Some other libraries we looked through included OpenPose, BlazePose, Tensorflow.js, and many more!
Accomplishments that we're proud of
We're proud to say that we managed to get the program to work :D
What we learned
This was the first time we really got exposure to computer vision libraries like OpenCV, so we took a lot of time trying to understand how it works and how we can connect it back to implementing the form tracking ideas we had! We also used Figma for the first time to mockup what our project would look like as an app on a mobile screen. Lastly, we worked well as a team :)!
What's next for True to Form
Improve the algorithm to include more analysis for different exercises Integrate the python program into a web/mobile app
Log in or sign up for Devpost to join the conversation.