AlphaPose: Whole-Body Regional Multi-Person Pose Estimation and Tracking in Real-Time
IEEE Transactions on Pattern Analysis and Machine Intelligence · 01.06.2023 · 45 (6) · 7157-7173
DOI: 10.1109/tpami.2022.3222784 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, erschienen am 01.06.2023. Verfasst von Hao-Shu Fang und 7 weiteren Autor:innen. Hauptthemen laut MEDLINE: Algorithms, Posture. Die Arbeit wurde bisher 695-mal zitiert (Crossref) und nennt 89 Literaturangaben. Gefördert von: National Key R&D Program of China, Shanghai Municipal Science and Technology, Shanghai Qi Zhi Institute.
Abstract (Originalsprache)
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.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Förderung
- National Key R&D Program of China
- Shanghai Municipal Science and Technology
- Shanghai Qi Zhi Institute
- Shanghai Municipal Commission of Economy and Informatization
Zitieren
APA
Fang, H. S., Li, J., Tang, H., Xu, C., Zhu, H., Xiu, Y., Li, Y. L., & Lu, C. (2023). AlphaPose: Whole-Body Regional Multi-Person Pose Estimation and Tracking in Real-Time. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(6), 7157-7173. https://doi.org/10.1109/tpami.2022.3222784
Vancouver
Fang HS, Li J, Tang H, Xu C, Zhu H, Xiu Y, et al. AlphaPose: Whole-Body Regional Multi-Person Pose Estimation and Tracking in Real-Time. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2023;45(6):7157-7173. doi:10.1109/tpami.2022.3222784
BibTeX
@article{Fang2023,
author = {Fang, Hao-Shu and Li, Jiefeng and Tang, Hongyang and Xu, Chao and Zhu, Haoyi and Xiu, Yuliang and Li, Yong-Lu and Lu, Cewu},
title = {AlphaPose: Whole-Body Regional Multi-Person Pose Estimation and Tracking in Real-Time},
journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
year = {2023},
volume = {45},
number = {6},
pages = {7157--7173},
doi = {10.1109/tpami.2022.3222784}
}
EUVIMED