AlphaPose: Whole-Body Regional Multi-Person Pose Estimation and Tracking in Real-Time
By Haoshu Fang, Jiefeng Li, Hongyang Tang, Chaoshun Xu, Haoyi Zhu, Yuliang Xiu, Yong-Lu Li, Cewu Lu. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2022
732 citations recorded by the source corpus.
Accurate whole-body multi-person pose estimation and tracking is an important yet challenging topic in computer vision. To capture the subtle actions of humans for complex behavior analysis, whole-body pose estimation including the face, body, hand and foot is essential over conventional body-only pose estimation. In this article, we present AlphaPose, a system that can perform accurate whole-body pose estimation and tracking jointly while running in realtime. To this end, we propose several new techniques: Symmetric Integral Keypoint Regression (SIKR) for fast and fine localization, Parametric Pose Non-Maximum-Suppression (P-NMS) for eliminating redundant human detections and Pose Aware Identity Embedding for jointly pose estimation and tracking. During training, we resort to Part-Guided Proposal Generator (PGPG) and multi-domain knowledge distillation to further improve the accuracy. Our method is able to localize whole-body keypoints accurately and tracks humans simultaneously given inaccurate bounding boxes and redundant detections. We show a significant improvement over current state-of-the-art methods in both speed and accuracy on COCO-wholebody, COCO, PoseTrack, and our proposed Halpe-FullBody pose estimation dataset. Our model, source codes and dataset are made publicly available at https://github.com/MVIG-SJTU/AlphaPose.
Subfields: Artificial Intelligence, Biomedical Engineering, Computer Vision and Pattern Recognition
View Paper: https://www.semanticscholar.org/paper/dc42daac244e93275fb44a269a68cace144d32ea
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Ilija Radosavovic
- Jitendra Malik
- Angjoo Kanazawa
- David F. Fouhey
- Dandan Shan
- Georgios Pavlakos
- Tao Jiang
- Chengqi Lyu
In Biomedical Engineering
- Georgios Pavlakos
- Angjoo Kanazawa
- David F. Fouhey
- Jitendra Malik
- Tao Jiang
- Li Fei-Fei
- Andrew Zisserman
- Deva Ramanan
In Computer Vision and Pattern Recognition
- Jitendra Malik
- Luc Van Gool
- Trevor Darrell
- Cordelia Schmid
- Abhinav Kumar Gupta
- Andrea Vedaldi
- Andrew Zisserman
- Dacheng Tao
Citations in the corpus
- RTMPose: Real-Time Multi-Person Pose Estimation based on MMPose (2023, methodology): “4 Top- FastPose50-dcn-si [18] 256×192 6.”
- Reconstructing Hands in 3D with Transformers (2023, methodology): “Among the larger scale efforts, COCO-WholeBody [25] provides hand annotations for the people in the COCO dataset [35] and Halpe [15] annotates hands in the HICO-DET dataset [4, 5].”
- Effective Whole-body Pose Estimation with Two-stages Distillation (2023, unknown): “With the emergence of whole-body data [9, 19], the models for whole-body pose estimation make great progress [13, 18, 48].”