Faster multi-person pose estimation by using object modeling
Faster multi-person pose estimation by using object modeling
Rethinking Keypoint Representations: Modeling Keypoints and Poses as Objects for Multi-Person Human Pose Estimation
arXiv paper abstract https://arxiv.org/abs/2111.08557
arXiv PDF paper https://arxiv.org/pdf/2111.08557.pdf
In ... human pose estimation, heatmap-based regression is the dominant approach despite ... drawbacks: ... suffer from quantization error and require excessive computation
... propose a new ... method in which individual keypoints and ... poses) are modeled as objects within a dense single-stage anchor-based detection framework.
... apply KAPAO to the problem of single-stage multi-person human pose estimation by simultaneously detecting human pose objects and keypoint objects and fusing the detections
... KAPAO is significantly faster and more accurate than previous methods, which suffer greatly from heatmap post-processing.
... Our large model, KAPAO-L, achieves an AP of 70.6 on the Microsoft COCO Keypoints validation set without test-time augmentation, which is 2.5x faster and 4.0 AP more accurate than the next best single-stage model.
Furthermore, KAPAO excels in the presence of heavy occlusion. ...
Please like and share this post if you enjoyed it using the buttons at the bottom!
Stay up to date. Subscribe to my posts https://morrislee1234.wixsite.com/website/contact
Web site with my other posts by category https://morrislee1234.wixsite.com/website
Comments