Realtime Multi-person 2D Pose Estimation Using Part Affinity Fields
Zhe Cao, Tomas Simon, Shih-En Wei et al. · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · 2017
We present an approach to efficiently detect the 2D pose of multiple people in an image. The approach uses a nonparametric representation, which we refer to as Part Affinity Fields (PAFs), to learn to associate body parts with individuals in the image. The architecture encodes global context, allowing a greedy bottom-up parsing step that maintains high accuracy while achieving realtime performance, irrespective of the number of people in the image. The architecture is designed to jointly learn part locations and their association via two branches of the same sequential prediction process. Our method placed first in the inaugural COCO 2016 keypoints challenge, and significantly exceeds the previous state-of-the-art result on the MPII Multi-Person benchmark, both in performance and efficiency.
Cited by 7,278 works. doi:10.1109/cvpr.2017.143
Authors
References
- Deep Residual Learning for Image Recognition
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Microsoft COCO: Common Objects in Context
- SSD: Single Shot MultiBox Detector
- The Hungarian method for the assignment problem
- DeepPose: Human Pose Estimation via Deep Neural Networks
- Pictorial Structures for Object Recognition
- Stacked Hourglass Networks for Human Pose Estimation
- Introduction to Graph Theory
- 2D Human Pose Estimation: New Benchmark and State of the Art Analysis