Accurate and robust registration of low overlapping point clouds

doi:10.1016/j.cag.2023.12.003

	Accurate and robust registration of low overlapping point clouds
	Yang, Jieyin 1,2; Zhao, Mingyang 3,4; Wu, Yingrui2,4 ; Jia, Xiaohong 1,2
发表期刊	COMPUTERS & GRAPHICS-UK
ISSN	0097-8493
	2024-02-01
卷号	118 页码:146-160
通讯作者	Jia, Xiaohong(xhjia@amss.ac.cn)
摘要	Point cloud registration has various applications within the computer -aided design (CAD) community, such as model reconstruction, retrieving, and analysis. Previous approaches mainly deal with the registration with a high overlapping hypothesis, while few existing methods explore the registration between low overlapping point clouds. However, the latter registration task is both challenging and essential, since the weak correspondence in point clouds usually leads to an inappropriate initialization, making the algorithm get stuck in a local minimum. To improve the performance against low overlapping scenarios, in this work, we develop a novel algorithm for accurate and robust registration of low overlapping point clouds using optimal transformation. The core of our method is the effective integration of geometric features with the probabilistic model hidden Markov random field. First, we determine and remove the outliers of the point clouds by modeling a hidden Markov random field based on a high dimensional feature distribution. Then, we derive a necessary and sufficient condition when the symmetric function is minimized and present a new curvature -aware symmetric function to make the point correspondence more discriminative. Finally, we integrate our curvature -aware symmetric function into a geometrically stable sampling framework, which effectively constrains unstable transformations. We verify the accuracy and robustness of our method on a wide variety of datasets, particularly on low overlapping range scanned point clouds. Results demonstrate that our proposed method attains better performance with higher accuracy and robustness compared to representative state-of-the-art approaches.
关键词	Point cloud registration ICP HMRF Low overlapping Outliers
DOI	10.1016/j.cag.2023.12.003
关键词[WOS]	SAMPLE CONSENSUS ; PARAMETERS
收录类别	SCI
语种	英语
资助项目	National Key R&D Program of China[2021YFB1715900] ; National Natural Science Foundation of China[12022117] ; CAS Project for Young Scientists in Basic Research[YSBR-034]
项目资助者	National Key R&D Program of China ; National Natural Science Foundation of China ; CAS Project for Young Scientists in Basic Research
WOS研究方向	Computer Science
WOS类目	Computer Science, Software Engineering
WOS记录号	WOS:001152097000001
出版者	PERGAMON-ELSEVIER SCIENCE LTD
引用统计	被引频次：1[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/55411
专题	多模态人工智能系统全国重点实验室
通讯作者	Jia, Xiaohong
作者单位	1.Chinese Acad Sci, Acad Math & Syst Sci, KLMM, Beijing, Peoples R China 2.Univ Chinese Acad Sci, Beijing, Peoples R China 3.Chinese Acad Sci, CAIR Hong Kong Inst Sci & Innovat, Hong Kong, Peoples R China 4.Chinese Acad Sci, Inst Automat, State Key Lab Multimodal Artificial Intelligence S, Beijing, Peoples R China
推荐引用方式 GB/T 7714	Yang, Jieyin,Zhao, Mingyang,Wu, Yingrui,et al. Accurate and robust registration of low overlapping point clouds[J]. COMPUTERS & GRAPHICS-UK,2024,118:146-160.
APA	Yang, Jieyin,Zhao, Mingyang,Wu, Yingrui,&Jia, Xiaohong.(2024).Accurate and robust registration of low overlapping point clouds.COMPUTERS & GRAPHICS-UK,118,146-160.
MLA	Yang, Jieyin,et al."Accurate and robust registration of low overlapping point clouds".COMPUTERS & GRAPHICS-UK 118(2024):146-160.