Dynamic Rigid Bodies Mining and Motion Estimation Based on Monocular Camera

doi:10.1109/TCYB.2022.3163545

CORC > 自动化研究所 > 中国科学院自动化研究所 > 复杂系统管理与控制国家重点实验室 > 先进机器人控制团队

	Dynamic Rigid Bodies Mining and Motion Estimation Based on Monocular Camera
	Gao, Xuanchang 1,3; Liu, Xilong 1; Cao, Zhiqiang 1; Tan, Min 1; Yu, Junzhi 1,2
刊名	IEEE TRANSACTIONS ON CYBERNETICS
	2022-04-13
页码	12
关键词	Dynamics Motion segmentation Cameras Manifolds Estimation Motion estimation Simultaneous localization and mapping Dynamic rigid bodies monocular camera motion estimation probabilistic field region confidence
ISSN号	2168-2267
DOI	10.1109/TCYB.2022.3163545
通讯作者	Liu, Xilong(xilong.liu@ia.ac.cn)
英文摘要	Dynamic object perception is an important yet challenging direction in the field of robot navigation. Without any prior knowledge about motion and objects, a novel dynamic rigid bodies mining and motion estimation method based on monocular camera is proposed in this article. Different from the existing works based on sampling that associate feature points to motion hypotheses according to the reprojection errors, our work endeavors to find the intrinsic relevance among motion hypotheses. To represent this relevance, the concept of the probabilistic field on the Lie group Sim(3) manifold is introduced, which is established using random sampling. It provides a computable way for the regions on the manifold where rigid bodies possibly appear. The probability of a motion hypothesis falling on a region is expressed by its confidence. The regions with large confidences in the probabilistic field are selected as potential rigid bodies, whose corresponding feature points are further sampled for pose calculation. As a result, the randomness of sampling is reduced and the inliers for possible rigid bodies are enhanced, which guarantees the accuracy of motion estimation. On this basis, the tracking of rigid bodies is achieved. The proposed method distinguishes the feature points of dynamic objects with 3-D motion from those in the static background, thus enabling simultaneous localization and mapping (SLAM) to be initialized in dynamic environments. The experimental results on the KITTI, Hopkins 155, and MTPV62 datasets demonstrate the effectiveness. Comparison experiments indicate that our method outperforms the other methods in sensitivity of dynamic objects perception.
资助项目	National Natural Science Foundation of China[61973302] ; National Natural Science Foundation of China[61633020] ; National Key Research and Development Program of China[2019YFB1311100]
WOS关键词	SEGMENTATION ; PERSPECTIVE
WOS研究方向	Automation & Control Systems ; Computer Science
语种	英语
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
WOS记录号	WOS:000782820900001
资助机构	National Natural Science Foundation of China ; National Key Research and Development Program of China
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/48350]
专题	自动化研究所_复杂系统管理与控制国家重点实验室_先进机器人控制团队
通讯作者	Liu, Xilong
作者单位	1.Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing 100190, Peoples R China 2.Peking Univ, Coll Engn, BIC ESAT, Dept Adv Mfg & Robot,State Key Lab Turbulence & C, Beijing 100871, Peoples R China 3.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China
推荐引用方式 GB/T 7714	Gao, Xuanchang,Liu, Xilong,Cao, Zhiqiang,et al. Dynamic Rigid Bodies Mining and Motion Estimation Based on Monocular Camera[J]. IEEE TRANSACTIONS ON CYBERNETICS,2022:12.
APA	Gao, Xuanchang,Liu, Xilong,Cao, Zhiqiang,Tan, Min,&Yu, Junzhi.(2022).Dynamic Rigid Bodies Mining and Motion Estimation Based on Monocular Camera.IEEE TRANSACTIONS ON CYBERNETICS,12.
MLA	Gao, Xuanchang,et al."Dynamic Rigid Bodies Mining and Motion Estimation Based on Monocular Camera".IEEE TRANSACTIONS ON CYBERNETICS (2022):12.