Minimal Case Relative Pose Computation Using Ray-Point-Ray Features

doi:10.1109/TPAMI.2019.2892372

CORC > 自动化研究所 > 中国科学院自动化研究所 > 智能制造技术与系统研究中心 > 智能机器人团队

	Minimal Case Relative Pose Computation Using Ray-Point-Ray Features
	Zhao, Ji 1; Kneip, Laurent 3; He, Yijia 2; Ma, Jiayi 4
刊名	IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
	2020-05-01
卷号	42 期号:5 页码:1176-1190
关键词	Three-dimensional displays Transmission line matrix methods Cameras Pose estimation Feature extraction Geometry Computer vision Structure-from-motion visual odometry minimal relative pose automatic solver generation Grobner bases ray-point-ray structures
ISSN号	0162-8828
DOI	10.1109/TPAMI.2019.2892372
通讯作者	Kneip, Laurent(lkneip@shanghaitech.edu.cn)
英文摘要	Corners are popular features for relative pose computation with 2D-2D point correspondences. Stable corners may be formed by two 3D rays sharing a common starting point. We call such elements ray-point-ray (RPR) structures. Besides a local invariant keypoint given by the lines' intersection, their reprojection also defines a corner orientation and an inscribed angle in the image plane. The present paper investigates such RPR features, and aims at answering the fundamental question of what additional constraints can be formed from correspondences between RPR features in two views. In particular, we show that knowing the value of the inscribed angle between the two 3D rays poses additional constraints on the relative orientation. Using the latter enables the solution of the relative pose problem with as few as 3 correspondences across the two images. We provide a detailed analysis of all minimal cases distinguishing between 90-degree RPR-structures and structures with an arbitrary, known inscribed angle. We furthermore investigate the special cases of a known directional correspondence and planar motion, the latter being solvable with only a single RPR correspondence. We complete the exposition by outlining an image processing technique for robust RPR-feature extraction. Our results suggest high practicality in man-made environments, where 90-degree RPR-structures naturally occur.
资助项目	National Natural Science Foundation of China[61773295] ; ShanghaiTech University
WOS关键词	CLOSED-FORM SOLUTION ; EGOMOTION ESTIMATION ; MOTION
WOS研究方向	Computer Science ; Engineering
语种	英语
出版者	IEEE COMPUTER SOC
WOS记录号	WOS:000523685800012
资助机构	National Natural Science Foundation of China ; ShanghaiTech University
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/38767]
专题	自动化研究所_智能制造技术与系统研究中心_智能机器人团队
通讯作者	Kneip, Laurent
作者单位	1.TuSimple, Beijing 100020, Peoples R China 2.Chinese Acad Sci, Inst Automat, Beijing 100190, Peoples R China 3.ShanghaiTech Univ, Shanghai 201210, Peoples R China 4.Wuhan Univ, Elect Informat Sch, Wuhan 430072, Peoples R China
推荐引用方式 GB/T 7714	Zhao, Ji,Kneip, Laurent,He, Yijia,et al. Minimal Case Relative Pose Computation Using Ray-Point-Ray Features[J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,2020,42(5):1176-1190.
APA	Zhao, Ji,Kneip, Laurent,He, Yijia,&Ma, Jiayi.(2020).Minimal Case Relative Pose Computation Using Ray-Point-Ray Features.IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,42(5),1176-1190.
MLA	Zhao, Ji,et al."Minimal Case Relative Pose Computation Using Ray-Point-Ray Features".IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 42.5(2020):1176-1190.