Distributed Human 3D Pose Estimation and Action Recognition*

Abstract

In this paper, we propose a distributed solution for 3D human pose estimation using a RGBD camera network. The key feature of our method is a dynamic hybrid consensus filter (DHCF) is introduced to fuse the multiple view information of cameras. In contrast to the centralized fusion solution, the DHCF algorithm can be used in a distributed network, which requires no central information fusion center. Therefore, the DHCF based fusion algorithm can benefit from many advantages of distributed network. We also show that the proposed fusion algorithm can handle the occlusion problems effectively, and achieve higher action recognition rate compared to the ones using only single view information.