PoseNet in a machine learning model which allows for real-time human pose estimation with any webcam. In Collaboration with the Google Creation lab, I open-sourced a Tensorflow.js version, allowing for it to be tinkered with and used in the browser with just a few lines of code.
Content below is excerpt from the blog post:
In collaboration with the Google Creative Lab, I’m excited to announce the release of a TensorFlow.js version of PoseNet, a machine learning model which allows for real-time human pose estimation in the browser. Try a live demo here.
So what is pose estimation anyway? Pose estimation refers to computer vision techniques that detect human figures in images and video, so that one could determine, for example, where someone’s elbow shows up in an image. To be clear, this technology is not recognizing who is in an image — there is no personal identifiable information associated to pose detection. The algorithm is simply estimating where key body joints are.
…read the rest in the blog post.