PoseNet is a machine learning vision model that estimates the pose of a person in an image or video by estimating where key body joints are.
PoseNet runs in Python, JavaScript, and C++. In class, we will be using the JavaScript version.
p5.js
p5.js is a JavaScript library with the goal of making coding accessible to artists, designers, educators, and beginners.
p5.js is inspired by—and very similar to—Processing. If you know Processing, many of the concepts in p5.js will look familiar (and vice versa). Unlike Processing, p5.js uses JavaScript, and runs in a web browser (including on mobile devices).
ml5.js
ml5.js simplifies the creation and exploration of programs that use artificial intelligence (machine learning) algorithms in a web page.
In this assignment, we will employ ml5.js as a means to access PoseNet.
ml5.js is developed and maintained by NYU ITP.
https://storage.googleapis.com/tfjs-models/demos/posenet/camera.html
Stand back from the computer so it sees your whole body, and work with others in the class, asking them to move and pose.
Questions:
Q. Try out different poses. What is PoseNet good at? What breaks it?
Q. What frame rate (fps) does your computer report? (This is the number at the upper left corner.) Send this in Slack. Q. What effect does confidence levels have? Take notes to answer in the homework assignment.