ClusterSLAM:A SLAM backend for simultaneous rigid body clustering and motion estimation

作     者：Jiahui Huang Sheng Yang Zishuo Zhao Yu-Kun Lai Shi-Min Hu Jiahui Huang;Sheng Yang;Zishuo Zhao;Yu-Kun Lai;Shi-Min Hu

作者机构：BNRistDepartment of Computer Science and TechnologyTsinghua UniversityBeijing 100084China Alibaba A.I.LabsHangzhou 311121China School of Computer Science and InformaticsCardiff UniversityCardiffCF243AAUK 

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

年 卷 期：2021年第7卷第1期

页      面：87-101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：supported by the National Key Technology R&D Program(Project No.2017YFB1002604) the Joint NSFC-DFG Research Program(Project No.61761136018) the National Natural Science Foundation of China(Project No.61521002) 

主　　题：dynamic SLAM motion segmentation scene perception 

摘      要：We present a practical backend for stereo visual SLAM which can simultaneously discover individual rigid bodies and compute their motions in dynamic *** recent factor graph based state optimization algorithms have shown their ability to robustly solve SLAM problems by treating dynamic objects as outliers,their dynamic motions are rarely *** this paper,we exploit the consensus of 3 D motions for landmarks extracted from the same rigid body for clustering,and to identify static and dynamic objects in a unified ***,our algorithm builds a noise-aware motion affinity matrix from landmarks,and uses agglomerative clustering to distinguish rigid *** decoupled factor graph optimization to revise their shapes and trajectories,we obtain an iterative scheme to update both cluster assignments and motion estimation *** on both synthetic scenes and KITTI demonstrate the capability of our approach,and further experiments considering online efficiency also show the effectiveness of our method for simultaneously tracking ego-motion and multiple objects.