Improving Occluded Human Pose Estimation via Linked Joints

Keypoint heatmaps,which produce peak values of Gaussian distributions for individual human joints,are crucial components in 2D human pose estimation.However,existing merits using keypoint heatmaps are usually defeated in body occlusion,resulting in inaccurate joint predictions.We consider that the failure is mainly due to keypoint heatmaps' insufficiency for distinguishing the joints from two occluded bodies.In this paper,we propose a novel method termed SkeletonMap(SMap),which introduces the prior knowledge of body structure to constrain relative connection of joints.As an extension of keypoint heatmaps,SMap can be efficiently plugged into existing 2D human pose estimation models and boost performance with negligible increase in computational cost,without bells and whistles.Extensive experiments are conducted to show the effectiveness and generalization of SMap. We hope our simple and efficient approach will serve as a solid component for future research in 2D human pose estimation.