Congested scene classification via efficient unsupervised feature learning and density estimation

doi:10.1016/j.patcog.2016.03.020

OPT OpenIR > 光谱成像技术研究室

	Congested scene classification via efficient unsupervised feature learning and density estimation
	Yuan, Yuan1 ; Wan, Jia 2,3; Wang, Qi 2,3
作者部门	光学影像学习与分析中心
	2016-08-01
发表期刊	PATTERN RECOGNITION
ISSN	0031-3203
卷号	56 页码:159-169
产权排序	1
摘要	An unsupervised learning algorithm with density information considered is proposed for congested scene classification. Though many works have been proposed to address general scene classification during the past years, congested scene classification is not adequately studied yet. In this paper, an efficient unsupervised feature learning approach with density information encoded is proposed to solve this problem. Based on spherical k-means, a feature selection process is proposed to eliminate the learned noisy features. Then, local density information which better reflects the crowdedness of a scene is encoded by a novel feature pooling strategy. The proposed method is evaluated on the assembled congested scene data set and UIUC-sports data set, and intensive comparative experiments justify the effectiveness of the proposed approach. (C) 2016 Elsevier Ltd. All rights reserved.
文章类型	Article
关键词	Computer Vision Unsupervised Feature Learning Scene Classification Density Estimation Spherical K-means Feature Pooling
WOS标题词	Science & Technology ; Technology
DOI	10.1016/j.patcog.2016.03.020
收录类别	SCI ; EI
关键词[WOS]	IMAGE CLASSIFICATION ; OBJECT DETECTION ; CONTEXT ; SCALE ; MODEL
语种	英语
WOS研究方向	Computer Science ; Engineering
项目资助者	National Basic Research Program of China (Youth 973 Program)(2013CB336500) ; State Key Program of National Natural Science of China(61232010) ; National Natural Science Foundation of China(61105012 ; Fundamental Research Funds for the Central Universities(3102014JC02020G07 ; Natural Science Foundation Research Project of Shaanxi Province(2015JM6264) ; Open Research Fund of Key Laboratory of Spectral Imaging Technology, Chinese Academy of Sciences ; 61379094) ; 3102015BJ(II)JJZ01)
WOS类目	Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS记录号	WOS:000375360900013
引用统计	被引频次：45[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/181661/28102
专题	光谱成像技术研究室
作者单位	1.Chinese Acad Sci, Xian Inst Opt & Precis Mech, Ctr OPT IMagery Anal & Learning OPTIMAL, State Key Lab Transient Opt & Photon, Xian 710119, Shaanxi, Peoples R China 2.Northwestern Polytech Univ, Sch Comp Sci, Xian 710072, Shaanxi, Peoples R China 3.Northwestern Polytech Univ, Ctr OPT IMagery Anal & Learning OPTIMAL, Xian 710072, Shaanxi, Peoples R China
推荐引用方式 GB/T 7714	Yuan, Yuan,Wan, Jia,Wang, Qi. Congested scene classification via efficient unsupervised feature learning and density estimation[J]. PATTERN RECOGNITION,2016,56:159-169.
APA	Yuan, Yuan,Wan, Jia,&Wang, Qi.(2016).Congested scene classification via efficient unsupervised feature learning and density estimation.PATTERN RECOGNITION,56,159-169.
MLA	Yuan, Yuan,et al."Congested scene classification via efficient unsupervised feature learning and density estimation".PATTERN RECOGNITION 56(2016):159-169.

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
Congested scene clas（2339KB）	期刊论文	作者接受稿	限制开放	CC BY-NC-SA	请求全文