3D hypothesis clustering for cross-view matching in multiperson motion capture

作     者：Miaopeng Li Zimeng Zhou Xinguo Liu Miaopeng Li;Zimeng Zhou;Xinguo Liu

作者机构：State Key Lab of CAD&CGZhejiang UniversityHangzhou310058China 

出 版 物：《Computational Visual Media》 (计算可视媒体（英文版）)

年 卷 期：2020年第6卷第2期

页      面：147-156页

核心收录：

学科分类：08[工学] 080203[工学-机械设计及理论] 0802[工学-机械工程] 

基　　金：partially supported by National Natural Science Foundation of China(No.61872317) Face Unity Technology 

主　　题：multi-person motion capture cross-view matching clustering human pose estimation 

摘      要：We present a multiview method for markerless motion capture of multiple people. The main challenge in this problem is to determine crossview correspondences for the 2 D joints in the presence of noise. We propose a 3 D hypothesis clustering technique to solve this problem. The core idea is to transform joint matching in 2 D space into a clustering problem in a 3 D hypothesis space. In this way, evidence from photometric appearance, multiview geometry, and bone length can be integrated to solve the clustering problem efficiently and robustly. Each cluster encodes a set of matched 2 D joints for the same person across different views, from which the 3 D joints can be effectively inferred. We then assemble the inferred 3 D joints to form full-body skeletons for all persons in a bottom–up way. Our experiments demonstrate the robustness of our approach even in challenging cases with heavy occlusion,closely interacting people, and few cameras. We have evaluated our method on many datasets, and our results show that it has significantly lower estimation errors than many state-of-the-art methods.