You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
fhw 0392d8f888 测试脚本及数据 12 months ago
..
associative_embedding register vitpose-b/l/h for coco 3 years ago
deeppose register vitpose-b/l/h for coco 3 years ago
topdown_heatmap 测试脚本及数据 12 months ago
README.md register vitpose-b/l/h for coco 3 years ago

README.md

Image-based 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. AE) 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.