How to use tensorflowJS to detect key points of human body

How to use tensorflowJS to achieve human body key point detection, in view of this problem, this article introduces the corresponding analysis and solution in detail, hoping to help more partners who want to solve this problem to find a more simple and feasible method.

Recently, tensorflowJS updated a pre-training model to estimate the posture of the human body in real time, returning 17 key nodes, as shown below:

This model, called PoseNet, can estimate 17 key points such as nose, eyes, ears, arms and leg joints in the photo. The key can achieve real-time results, and we can easily experience this technology in web browsers. Using this model is also very easy, and here is the official sample code:

Var imageScaleFactor = 0.5

Var flipHorizontal = false

Var outputStride = 16

Var maxPoseDetections = 2

Var imageElement = document.getElementById ('cat'); posenet.load () .then (function (net) {

Return net.estimateMultiplePoses (imageElement, 0.5, flipHorizontal, outputStride, maxPoseDetections)}) .then (function (poses) {

Console.log (poses);})

This is the answer to the question on how to use tensorflowJS to achieve human body key point detection. I hope the above content can be of some help to you. If you still have a lot of doubts to be solved, you can follow the industry information channel to learn more about it.