Realtime Multi-person 2D Pose Estimation Using Part Affinity Fields
Top Cited Papers
- 1 July 2017
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 10636919,p. 1302-1310
- https://doi.org/10.1109/cvpr.2017.143
Abstract
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.Keywords
This publication has 22 references indexed in Scilit:
- Towards Accurate Multi-person Pose Estimation in the WildPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2017
- Multi-person Pose Estimation with Local Joint-to-Person AssociationsLecture Notes in Computer Science, 2016
- Deep Residual Learning for Image RecognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2016
- Convolutional Pose MachinesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2016
- Efficient object localization using Convolutional NetworksPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2015
- Multi-source Deep Learning for Human Pose EstimationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2014
- DeepPose: Human Pose Estimation via Deep Neural NetworksPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2014
- Articulated Human Detection with Flexible Mixtures of PartsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2012
- Clustered Pose and Nonlinear Appearance Models for Human Pose EstimationPublished by British Machine Vision Association and Society for Pattern Recognition ,2010
- The Hungarian method for the assignment problemNaval Research Logistics Quarterly, 1955