RGB-D Point Cloud Registration Based on Salient Object Detection

doi:10.1109/TNNLS.2021.3053274

	RGB-D Point Cloud Registration Based on Salient Object Detection
	Wan, Teng 1; Du, Shaoyi 1; Cui, Wenting 1; Yao, Runzhao 1; Ge, Yuyan 1; Li, Ce 3; Gao, Yue 2; Zheng, Nanning 1
刊名	IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
	2022
关键词	Image color analysis Three-dimensional displays Colored noise Object detection Standards Robustness Registers Bidirectional color distance (BCD) maximum correntropy criterion (MCC) red green blue-depth (RGB-D) point-set registration salient object detection (SOD)
ISSN号	2162-237X
DOI	10.1109/TNNLS.2021.3053274
英文摘要	We propose a robust algorithm for aligning rigid, noisy, and partially overlapping red green blue-depth (RGB-D) point clouds. To address the problems of data degradation and uneven distribution, we offer three strategies to increase the robustness of the iterative closest point (ICP) algorithm. First, we introduce a salient object detection (SOD) method to extract a set of points with significant structural variation in the foreground, which can avoid the unbalanced proportion of foreground and background point sets leading to the local registration. Second, registration algorithms that rely only on structural information for alignment cannot establish the correct correspondences when faced with the point set with no significant change in structure. Therefore, a bidirectional color distance (BCD) is designed to build precise correspondence with bidirectional search and color guidance. Third, the maximum correntropy criterion (MCC) and trimmed strategy are introduced into our algorithm to handle with noise and outliers. We experimentally validate that our algorithm is more robust than previous algorithms on simulated and real-world scene data in most scenarios and achieve a satisfying 3-D reconstruction of indoor scenes.
WOS研究方向	Computer Science ; Engineering
语种	英语
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
WOS记录号	WOS:000733542800001
内容类型	期刊论文
源URL	[http://ir.lut.edu.cn/handle/2XXMBERH/155021]
专题	电气工程与信息工程学院
作者单位	1.Xi An Jiao Tong Univ, Inst Artificial Intelligence & Robot, Coll Artificial Intelligence, Xian 710049, Peoples R China; 2.Tsinghua Univ, Sch Software, Beijing 100084, Peoples R China 3.Lanzhou Univ Technol, Coll Elect & Informat Engn, Lanzhou 730050, Peoples R China;
推荐引用方式 GB/T 7714	Wan, Teng,Du, Shaoyi,Cui, Wenting,et al. RGB-D Point Cloud Registration Based on Salient Object Detection[J]. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,2022.
APA	Wan, Teng.,Du, Shaoyi.,Cui, Wenting.,Yao, Runzhao.,Ge, Yuyan.,...&Zheng, Nanning.(2022).RGB-D Point Cloud Registration Based on Salient Object Detection.IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS.
MLA	Wan, Teng,et al."RGB-D Point Cloud Registration Based on Salient Object Detection".IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS (2022).