3D entity-based stereo matching with ground control points and joint second-order smoothness prior

doi:10.1007/s00371-014-1009-3

CORC > 计算技术研究所 > 中国科学院计算技术研究所 > 中国科学院计算技术研究所期刊论文 > 英文

	3D entity-based stereo matching with ground control points and joint second-order smoothness prior
	Liu, Jing 1,2; Li, Chunpeng 1; Mei, Feng 1,2; Wang, Zhaoqi 1
刊名	VISUAL COMPUTER
	2015-09-01
卷号	31 期号:9 页码:1253-1269
关键词	Stereo matching Joint second-order smoothness prior GCPs-plane Fusion-move 3D entity
ISSN号	0178-2789
DOI	10.1007/s00371-014-1009-3
英文摘要	Disparity estimation for a scene with complex geometric characteristics such as slanted or highly curved surfaces is a basic and important issue in stereo matching. Traditional methods often use first-order smoothness priors that always lead to low-curvature frontal-parallel disparity maps. We propose a stereo framework that views the scene as a set of 3D entities with compact and smooth disparity distributions. The 3D entity-based representation enables some contributions to obtain a precise disparity estimation. A GCPs-plane constraint based on ground control points is used to strengthen the compact distributions of the disparities in each entity by restricting the scope of the disparity variance and reducing matching ambiguities in repetitive or low-texture areas. Furthermore, we have formulated a joint second-order smoothness prior, which combines a geometric weight with the derivative of disparity values. This prior encourages smooth disparity variations inside each entity and means that each entity is biased towards being a 3D planar surface. Segmentation is incorporated as soft constraint by effectively fusing the advantages of the image color gradient and GCPs-plane. This avoids blending of the foreground and background and retains only the disparity discontinuities from geometrically smooth regions with strong texture gradients. Our framework is formulated as a maximum a posteriori probability estimation problem that is optimized using the fusion-move approach. Evaluation results on the Middlebury benchmark show that the proposed method ranks second among the approximately listed algorithms. In addition, it performs well in real-world scenes.
资助项目	National Natural Science Foundation of China[61300131] ; National Key Technology Research and Development Program of China[2013BAK03B07] ; National High Technology Research and Development Program of China (863 Program)[2013AA013902]
WOS研究方向	Computer Science
语种	英语
出版者	SPRINGER
WOS记录号	WOS:000359388100008
内容类型	期刊论文
源URL	[http://119.78.100.204/handle/2XEOYT63/9476]
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Liu, Jing
作者单位	1.Chinese Acad Sci, Beijing Key Lab Mobile Comp & Pervas Device, Inst Comp Technol, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Beijing 100049, Peoples R China
推荐引用方式 GB/T 7714	Liu, Jing,Li, Chunpeng,Mei, Feng,et al. 3D entity-based stereo matching with ground control points and joint second-order smoothness prior[J]. VISUAL COMPUTER,2015,31(9):1253-1269.
APA	Liu, Jing,Li, Chunpeng,Mei, Feng,&Wang, Zhaoqi.(2015).3D entity-based stereo matching with ground control points and joint second-order smoothness prior.VISUAL COMPUTER,31(9),1253-1269.
MLA	Liu, Jing,et al."3D entity-based stereo matching with ground control points and joint second-order smoothness prior".VISUAL COMPUTER 31.9(2015):1253-1269.