Scene Parsing From an MAP Perspective

doi:10.1109/TCYB.2014.2361489

OPT OpenIR > 光谱成像技术研究室

	Scene Parsing From an MAP Perspective
	Li, Xuelong; Mou, Lichao; Lu, Xiaoqiang
	2015-09-01
发表期刊	IEEE TRANSACTIONS ON CYBERNETICS
卷号	45 期号:9 页码:1876-1886
摘要	Scene parsing is an important problem in the field of computer vision. Though many existing scene parsing approaches have obtained encouraging results, they fail to overcome within-category inconsistency and intercategory similarity of superpixels. To reduce the aforementioned problem, a novel method is proposed in this paper. The proposed approach consists of three main steps: 1) posterior category probability density function (PDF) is learned by an efficient low-rank representation classifier (LRRC); 2) prior contextual constraint PDF on the map of pixel categories is learned by Markov random fields; and 3) final parsing results are yielded up to the maximum a posterior process based on the two learned PDFs. In this case, the nature of being both dense for within-category affinities and almost zeros for intercategory affinities is integrated into our approach by using LRRC to model the posterior category PDF. Meanwhile, the contextual priori generated by modeling the prior contextual constraint PDF helps to promote the performance of scene parsing. Experiments on benchmark datasets show that the proposed approach outperforms the state-of-the-art approaches for scene parsing.
文章类型	Article
关键词	Dynamic Dictionary Driven By Scene Low-rank Representation Classifier (Lrrc) Markov Random Field (Mrf) Maximum a Posterior (Map) Inference Prior Contextual Constraint Scene Parsing
WOS标题词	Science & Technology ; Technology
DOI	10.1109/TCYB.2014.2361489
收录类别	SCI ; EI
关键词[WOS]	IMAGE SUPERRESOLUTION ; FACE RECOGNITION ; SEGMENTATION ; CLASSIFICATION ; REPRESENTATION ; SURVEILLANCE ; FRAMEWORK
语种	英语
WOS研究方向	Computer Science
WOS类目	Computer Science, Artificial Intelligence ; Computer Science, Cybernetics
WOS记录号	WOS:000360019000014
引用统计	被引频次：21[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/181661/25360
专题	光谱成像技术研究室
作者单位	Chinese Acad Sci, Xian Inst Opt & Precis Mech, State Key Lab Transient Opt & Photon, Ctr Opt IMagery Anal & Learning OPTIMAL, Xian 710119, Shaanxi, Peoples R China
推荐引用方式 GB/T 7714	Li, Xuelong,Mou, Lichao,Lu, Xiaoqiang. Scene Parsing From an MAP Perspective[J]. IEEE TRANSACTIONS ON CYBERNETICS,2015,45(9):1876-1886.
APA	Li, Xuelong,Mou, Lichao,&Lu, Xiaoqiang.(2015).Scene Parsing From an MAP Perspective.IEEE TRANSACTIONS ON CYBERNETICS,45(9),1876-1886.
MLA	Li, Xuelong,et al."Scene Parsing From an MAP Perspective".IEEE TRANSACTIONS ON CYBERNETICS 45.9(2015):1876-1886.

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
Scene Parsing From a（1883KB）	期刊论文	出版稿	限制开放	CC BY-NC-SA	请求全文