Multi-Person Pose Estimation with Local Joint-to-Person Associations
This addresses the limitation of existing methods that only handle single-person pose estimation, enabling pose estimation in groups or crowds for applications like surveillance or sports analysis, though it is incremental as it builds on prior work.
The paper tackles the problem of multi-person pose estimation in images with occlusions or truncations by framing it as a joint-to-person association problem, achieving state-of-the-art accuracy on the MPII Human Pose Dataset while being 6,000 to 19,000 times faster.
Despite of the recent success of neural networks for human pose estimation, current approaches are limited to pose estimation of a single person and cannot handle humans in groups or crowds. In this work, we propose a method that estimates the poses of multiple persons in an image in which a person can be occluded by another person or might be truncated. To this end, we consider multi-person pose estimation as a joint-to-person association problem. We construct a fully connected graph from a set of detected joint candidates in an image and resolve the joint-to-person association and outlier detection using integer linear programming. Since solving joint-to-person association jointly for all persons in an image is an NP-hard problem and even approximations are expensive, we solve the problem locally for each person. On the challenging MPII Human Pose Dataset for multiple persons, our approach achieves the accuracy of a state-of-the-art method, but it is 6,000 to 19,000 times faster.