Human Body 2D Pose Estimation

Multi-person human pose estimation is defined as the task of detecting the poses (or keypoints) of all people from an input image.

Existing approaches can be categorized into top-down and bottom-up approaches.

Top-down methods (e.g. DeepPose) divide the task into two stages: human detection and pose estimation. They perform human detection first, followed by single-person pose estimation given human bounding boxes.

Bottom-up approaches (e.g. Associative Embedding) first detect all the keypoints and then group/associate them into person instances.

Data preparation

Please follow DATA Preparation to prepare data.

Demo

Please follow Demo to run demos.