Pose Detection
Strike a pose! In this video, I explore the BodyPose model in ml5.js with MoveNet and BlazePose, showing how to track body keypoints and visualize 'skeleton' connections using live video.
ml5 page with documentation and supporting material.
Syllabus for ITP IMA course on Machine Learning.
COCO is a large-scale object detection, segmentation, and captioning dataset.
Humans of AI by artist Phillip Schmitt seeks to bring attention to the images used to train AI models.
Blog post by Ronny Votel and Na Li introducing MoveNet.
Academic paper introducing the BlazePose model.
PoseNet Sketchbook is a collection of open source, interactive web experiments by Maya Man
Letters made out of Olympians during the Paris 2024 Olympics
My tutorial on the lerp function.
- Editing
by Mathieu Blanchette
- Animations
by Jason Heglund