人体姿态识别

---

Build Type	Linux	MacOS	Windows
Build Status	[外链图片转存失败,源站可能有防盗链机制,建议将图片保存下来直接上传(img-3Tgzy56L-1617902411948)(https://github.com/CMU-Perceptual-Computing-Lab/openpose/workflows/CI/badge.svg)]	[外链图片转存失败,源站可能有防盗链机制,建议将图片保存下来直接上传(img-ceVrTQiG-1617902411951)(https://github.com/CMU-Perceptual-Computing-Lab/openpose/workflows/CI/badge.svg)]

OpenPose has represented the first real-time multi-person system to jointly detect human body, hand, facial, and foot keypoints (in total 135 keypoints) on single images.

It is authored by Ginés Hidalgo, Zhe Cao, Tomas Simon, Shih-En Wei, Yaadhav Raaj, Hanbyul Joo, and Yaser Sheikh. It is maintained by Ginés Hidalgo and Yaadhav Raaj. OpenPose would not be possible without the CMU Panoptic Studio dataset. We would also like to thank all the people who has helped OpenPose in any way.

^{Authors Ginés Hidalgo (left) and}