A global energy optimization framework for 2.1D sketch extraction from monocular images

doi:10.1016/j.gmod.2014.03.015

	A global energy optimization framework for 2.1D sketch extraction from monocular images
	Yu,Cheng-Chi 1; Liu,Yong-Jin 1; Wu,MattTianfu 2; Li,Kai-Yun 3; Fu,Xiaolan3
第一作者	Yu, Cheng-Chi
通讯作者邮箱	liuyongjin@tsinghua.edu.cn
心理所单位排序	3
摘要	The 2.1D sketch is a layered image representation, which assigns a partial depth ordering of over-segmented regions in a monocular image. This paper presents a global optimization framework for inferring the 2.10 sketch from a monocular image. Our method only uses over-segmented image regions (i.e., superpixels) as input, without any information of objects in the image, since (1) segmenting objects in images is a difficult problem on its own and (2) the objective of our proposed method is to be generic as an initial module useful for downstream high-level vision tasks. This paper formulates the inference of the 2.1D sketch using a global energy optimization framework. The proposed energy function consists of two components: (1) one is defined based on the local partial ordering relations (i.e., figure-ground) between two adjacent over-segmented regions, which captures the marginal information of the global partial depth ordering and (2) the other is defined based on the same depth layer relations among all the over-segmented regions, which groups regions of the same object to account for the over-segmentation issues. A hybrid evolution algorithm is utilized to minimize the global energy function efficiently. In experiments, we evaluated our method on a test data set containing 100 diverse real images from Berkeley segmentation data set (BSDS500) with the annotated ground truth. Experimental results show that our method can infer the 2.10 sketch with high accuracy. (C) 2014 Elsevier Inc. All rights reserved.
关键词	2.1D sketch Global optimization Local features Hybrid differential evolution
学科领域	Computer Science, Software Engineering
	2014-09-15
语种	英语
DOI	10.1016/j.gmod.2014.03.015
发表期刊	GRAPHICAL MODELS
ISSN	1524-0703
卷号	76 页码:507-521
期刊论文类型	Article
URL	查看原文
收录类别	SCI ; SSCI
WOS关键词	DEPTH ; MODEL
WOS研究方向	Computer Science
WOS类目	Computer Science, Software Engineering
WOS记录号	WOS:000347018500042
引用统计	被引频次：18[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.psych.ac.cn/handle/311026/14181
专题	脑与认知科学国家重点实验室
作者单位	1.Tsinghua Univ, Dept Comp Sci & Technol, TNList, Beijing 100084, Peoples R China; 2.Univ Calif Los Angeles, Dept Stat, Ctr Vis Cognit Learning & Art, Los Angeles, CA 90024 USA; 3.Chinese Acad Sci, Inst Psychol, State Key Lab Brain & Cognit Sci, Beijing 100101, Peoples R China
推荐引用方式 GB/T 7714	Yu,Cheng-Chi,Liu,Yong-Jin,Wu,MattTianfu,et al. A global energy optimization framework for 2.1D sketch extraction from monocular images[J]. GRAPHICAL MODELS,2014,76:507-521.
APA	Yu,Cheng-Chi,Liu,Yong-Jin,Wu,MattTianfu,Li,Kai-Yun,&Fu,Xiaolan.(2014).A global energy optimization framework for 2.1D sketch extraction from monocular images.GRAPHICAL MODELS,76,507-521.
MLA	Yu,Cheng-Chi,et al."A global energy optimization framework for 2.1D sketch extraction from monocular images".GRAPHICAL MODELS 76(2014):507-521.

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
2014 A global energy（3948KB）			暂不开放	--	请求全文