Pose landmarks detection task MediaPipe
The MediaPipe Pose Landmarker task lets you detect the landmarks of human bodies in an image. You can use this task to identify key body locations and render visual effects on them. This task uses machine learning (ML) models that can work with single images or a continuous stream of images. The task outputs body pose landmarks in image coordinates and in 3-dimensional (x,y,z) world coordinates.
- [Intro Key Points] https://github.com/pilarcode/human_pose_estimation/blob/main/notebooks/IntroMediaPipe.ipynb
- [Pose estimation in images] https://github.com/pilarcode/human_pose_estimation/blob/main/notebooks/PoseEstimation_Image.ipynb
- [Pose estimation in videos] https://github.com/pilarcode/human_pose_estimation/blob/main/notebooks/PoseEstimation_Video.ipynb