High-Order Energies for Stereo Segmentation

doi:10.1109/TCYB.2015.2453091

OPT OpenIR > 光谱成像技术研究室

	High-Order Energies for Stereo Segmentation
	Peng, Jianteng 1; Shen, Jianbing 1; Li, Xuelong2
作者部门	光学影像学习与分析中心
	2016-07-01
发表期刊	IEEE TRANSACTIONS ON CYBERNETICS
ISSN	2168-2267
卷号	46 期号:7 页码:1616-1627
产权排序	2
摘要	In this paper, we propose a novel segmentation approach for stereo images using the high-order energy optimization, which utilizes the disparity maps and statistical information of stereo images to enrich the high-order potential functions. To the best of our knowledge, our approach is the first one to formulate the problem of stereo segmentation as a high-order energy optimization problem, which simultaneously segments the foreground objects in left and right images using the proposed high-order potential function. A new method for designing the penalty function in our high-order term is proposed by the corresponding pixels and their neighboring pixels between left and right images. The relationships of stereo correspondence by disparity maps are further employed to enhance the connections between the left and right stereo images. Experimental results demonstrate that the proposed approach can effectively improve the performance of two kinds of stereo segmentation, including the automatic saliency-aware stereocut and the interactive stereo segmentation with user scribbles.
文章类型	Article
关键词	Disparity High-order Energy Optimization Saliency Segmentation Stereo Images
WOS标题词	Science & Technology ; Technology
DOI	10.1109/TCYB.2015.2453091
收录类别	SCI ; EI
关键词[WOS]	IMAGE SEGMENTATION ; GRAPH CUTS ; SALIENCY ; OPTIMIZATION ; ATTENTION ; TEXTURES
语种	英语
WOS研究方向	Computer Science
项目资助者	National Basic Research Program of China (973 Program)(2013CB328805) ; National Natural Science Foundation of China(61272359) ; Fok Ying-Tong Education Foundation for Young Teachers ; Shaanxi Key Innovation Team of Science and Technology(2012KCT-04) ; Specialized Fund for Joint Building Program of Beijing Municipal Education Commission
WOS类目	Computer Science, Artificial Intelligence ; Computer Science, Cybernetics
WOS记录号	WOS:000379757900011
引用统计	被引频次：43[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.opt.ac.cn/handle/181661/28181
专题	光谱成像技术研究室
作者单位	1.Beijing Inst Technol, Sch Comp Sci, Beijing Lab Intelligent Informat Technol, Beijing 100081, Peoples R China 2.Chinese Acad Sci, Ctr Opt IMagery Anal & Learning OPTIMAL, State Key Lab Transient Opt & Photon, Xian Inst Opt & Precis Mech, Xian 710119, Peoples R China
推荐引用方式 GB/T 7714	Peng, Jianteng,Shen, Jianbing,Li, Xuelong. High-Order Energies for Stereo Segmentation[J]. IEEE TRANSACTIONS ON CYBERNETICS,2016,46(7):1616-1627.
APA	Peng, Jianteng,Shen, Jianbing,&Li, Xuelong.(2016).High-Order Energies for Stereo Segmentation.IEEE TRANSACTIONS ON CYBERNETICS,46(7),1616-1627.
MLA	Peng, Jianteng,et al."High-Order Energies for Stereo Segmentation".IEEE TRANSACTIONS ON CYBERNETICS 46.7(2016):1616-1627.

条目包含的文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
High-Order Energies （1736KB）	期刊论文	作者接受稿	限制开放	CC BY-NC-SA	请求全文