PoseNet is a machine learning model that allows for Real-time Human Pose Estimation.
PoseNet can be used to estimate either a single pose or multiple poses, meaning there is a version of the algorithm that can detect only one person in an image/video and one version that can detect multiple persons in an image/video.
How Can You Use Posenet in Your Projects #
Runway ML #
Runway ML is a very nice tool for experimenting with various Machine Learning models. You can even easily connect the output of one model to the input of another.
Unfortunately, unless you have a Linux computer with a very powerful GPU, Runway ML is going to run very slowly.
ml5.js - Friendly Machine Learning for The Web #
ml5.js is a library that implements various machine learning models in a very friendly way. ml5.js works nicely together with p5.js so the easiest way to get started with it is using the p5.js web editor. See the instructions here: https://learn.ml5js.org/docs/#/
See below for an example application I made using this library.
PoseNet for Installations #
I haven’t tried this, but seems pretty nice https://github.com/oveddan/posenet-for-installations
It seems that there was some bug that made it crash, Oskar has a fix: https://github.com/Havdon/posenet-for-installations