DJW cdece0b32a 第一次提交 | hai 9 meses | |
---|---|---|
.. | ||
associative_embedding | hai 9 meses | |
cid | hai 9 meses | |
dekr | hai 9 meses | |
integral_regression | hai 9 meses | |
rtmpose | hai 9 meses | |
simcc | hai 9 meses | |
topdown_heatmap | hai 9 meses | |
topdown_regression | hai 9 meses | |
README.md | hai 9 meses |
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.
Please follow DATA Preparation to prepare data.
Please follow Demo to run demos.