Skip to content
AI-powered yoga pose correction web application
Python HTML CSS Shell
Branch: master
Clone or download
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
code
docs
misc
samples
venv
.gitattributes
.gitignore
Aligned_VC_Presentation_Deck.pdf
README.md

README.md

Project Description

Aligned is a yoga pose correction web app that processes video of a user’s yoga pose and provides feedback on how to improve the pose. The app was built using Flask and runs on an Amazon EC2 instance with GPU for deep learning.

Aligned was selected by USF faculty as one of the top apps of 2019 and, as a result, our team had the opportunity to present the app to a panel of VCs. We plan to continue developing Aligned as a side project in the near future. Please note that the app's website is not currently operational due to the high cost of continuously running the EC2.

How does it work?

Watch Demo Video

  • User logs in and selects which pose to evaluate
  • App provides instructions on how to execute the pose
  • Once ready, the user records a video of themselves doing the pose within the app (using webcam)
  • Video is automatically processed using OpenPose, an open-source, deep learning-based library for keypoint detection.
  • The app uses the keypoints from OpenPose to classify different pose faults using a rule-based system.
  • Feedback is provided to the user on how they can safely improve their pose.

Important Links

Contributors

Katja Wittfoth, Brian Dorsey, Quinn Keck, Evan Calkins, Sankeerti Haniyur, Connor Swanson, Maria Vasilenko

You can’t perform that action at this time.