Inspiration
We wanted to design a program that would help people doing physical therapy. We realize that physical therapists often assign workouts for their patients to do at home. While the patients are usually given a video of their assigned workout, the patient still may not know if they are doing the exercises properly.
What it does
The program uses a camera to detect body movement and gives audio feedback based on whether or not the patient is performing the exercise correctly,
How we built it
We created the program using openpose API.
Challenges we ran into
We ran into problems that were incorrectly detecting the body movements. We had to make calculations to accept a certain variations in angles of the body.
Accomplishments that we're proud of
We are proud of being able to use a new API that we never used before and using machine learning.
What we learned
We learned that using machine learning, we can improve the lives of patients trying to recover.
What's next for Virtual Physical Therapists
We plan to extend the project to include mobile devices for further convenience for patients.
Log in or sign up for Devpost to join the conversation.