DevMesh

FitStream for yoga, personal trainer, physical therapy, dance teacher

Peter Ma

Peter Ma

San Francisco

2 0
  • 0 Collaborators

Using AI Streaming platform for fitness professionals, yoga teachers, dance instructors so they can host live class with live feedbacks. We use tensorflow PoseNet to plot user's poses and compare with the streamer instructors to get a feedback system for the instructors themselves. ...learn more

Project status: Under Development

Mobile, RealSense™, Internet of Things, Artificial Intelligence

Groups
Movidius™ Neural Compute Group

Intel Technologies
DevCloud, Intel Opt ML/DL Framework, Movidius NCS

Code Samples [1]Links [2]

Overview / Usage

Twitch and other live stream platform has made it for gamers who has high latency and high bandwidth, but for fitness professionals, yoga teachers and dance instructors that's still a high barrier of entry. With rise of 5G and AI on the edge, we can make that happen on our mobile phone everywhere.

The fitness professional and yoga instructors now can stream their class live, the current platforms are not interactive and lacks feedback loop, the effect makes no difference than simple video recording. With help of AI on the edge we can provide feedback loop to the streamers so they can be more aware of their class.

Methodology / Approach

We use tensorflow to get the pose and stream that through webRTC, and correctly getting the poses done

Technologies Used

Tensorflow, Movidius, RealSense, 5G

Repository

https://github.com/coolioxlr/fitstream

Comments (0)