This illustrates the use of a deep learning model called PoseNet. It defines blocks for obtaining up to 17 locations on one or more people (nose, elbow, knee, etc.)data:image/png;base64,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This illustrates the use of a deep learning model called PoseNet. It defines blocks for obtaining up to 17 locations on one or more people (nose, elbow, knee, etc.)

Reports the value of the 'key' in a table that is a list of pairs of keys and values.

Reports the locations of 17 or 33 body parts for each body detected in the costume. Three models are available: MoveNet is an ultra fast and accurate model that detects 17 keypoints of a body. BlazePose can detect 33 keypoints, it provides additional keypoints for face, hands and feet. It reports both 2D and 3D locations. PoseNet can detect multiple poses, each pose contains 17 keypoints. For full documentation including options click the following help: https://github.com/tensorflow/tfjs-models/tree/master/pose-detection

MoveNet is an ultra fast and accurate model that detects 17 keypoints of a body. BlazePose can detect 33 keypoints, it provides additional keypoints for face, hands and feet. PoseNet can detect multiple poses, each pose contains 17 keypoints.stage costume percentagefalsebodyTurn the result into a form easier to see and use.

Converts costume coordinates to stage or percentage

x ystage costume percentage

This is the workhorse behind the reporters for the body and hand poses and face landmarks.

MoveNet PoseNet BlazePose MediaPipeFaceDetector MediaPipeFaceMesh MediaPipeHands ARPortraitDepth

poses_and_landmarksmodel name

data:image/png;base64,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There are 3 models for detecting parts of the body. 1. MoveNet is an ultra fast and accurate model that detects 17 keypoints of a body. 2.BlazePose can detect 33 keypoints, it provides additional keypoints for face, hands and feet. It reports both 2D and 3D locations. 3. PoseNet can detect multiple poses, each pose contains 17 keypoints. For full documentation including options visit: https://github.com/tensorflow/tfjs-models/tree/master/pose-detectionClick to see all the properies of a pose.