中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 计算技术研究所
  3. 中国科学院计算技术研究所
  4. 中国科学院计算技术研究所期刊论文
  5. 英文
Contour-motion feature (CMF): A space-time approach for robust pedestrian detection

文献类型：期刊论文

作者Liu, Yazhou1; Chen, Xilin2; Yao, Hongxun1; Cui, Xinyi1; Liu, Chaoran2; Gao, Wen2
刊名PATTERN RECOGNITION LETTERS
出版日期2009-01-15
卷号30期号:2页码:148-156
关键词Contour-motion feature Space-time analysis Pedestrian detection Human activity analysis Event analysis 3D Haar filter
ISSN号0167-8655
DOI10.1016/j.patrec.2008.03.007
英文摘要This paper presents a contour-motion feature for robust pedestrian detection. The space-time contours are used as the low level representation of the pedestrian. Then we apply 3D distance transform to extend the I-dimensional contour into 3-dimensional space. By this way, the relations between the local contours can be maintained implicitly. Further, by encapsulating the static and dynamic information by 3D Haar-like filters, we can generate the middle level pedestrian representation: contour-motion features. Then we use boosting method to select the most representative features. Our experiments demonstrate that the proposed approach can Outperform Viola's well-known pedestrian detector in both detection accuracy and generalization ability. In addition, even though our approach is presented in pedestrian detection scenario, it has been extended to human activity recognition application and remarkable performance has been achieved. (C) 2008 Elsevier B.V. All rights reserved.
资助项目National Natural Science Foundation of China[60332010] ; National Natural Science Foundation of China[60673091] ; National Natural Science Foundation of China[60772071] ; Hi-Tech Research and Development Program of China[2006AA01Z122] ; Hi-Tech Research and Development Program of China[2007AA01Z163] ; Program of New Century Excellent Talents in University[NCET-04-0320] ; Natural Science Foundation of Beijing municipal[4061001] ; Natural Science Foundation of Beijing municipal[4072023] ; ISVISION Technology Co. Ltd
WOS研究方向Computer Science
语种英语
WOS记录号WOS:000261857200009
出版者ELSEVIER SCIENCE BV
源URL[http://119.78.100.204/handle/2XEOYT63/11679]  
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, Yazhou
作者单位1.Harbin Inst Technol, Sch Comp Sci & Technol, Harbin 150001, Peoples R China
2.Chinese Acad Sci, Inst Comp Technol, Beijing 100080, Peoples R China
推荐引用方式
GB/T 7714		 Liu, Yazhou,Chen, Xilin,Yao, Hongxun,et al. Contour-motion feature (CMF): A space-time approach for robust pedestrian detection[J]. PATTERN RECOGNITION LETTERS,2009,30(2):148-156.
APA Liu, Yazhou,Chen, Xilin,Yao, Hongxun,Cui, Xinyi,Liu, Chaoran,&Gao, Wen.(2009).Contour-motion feature (CMF): A space-time approach for robust pedestrian detection.PATTERN RECOGNITION LETTERS,30(2),148-156.
MLA Liu, Yazhou,et al."Contour-motion feature (CMF): A space-time approach for robust pedestrian detection".PATTERN RECOGNITION LETTERS 30.2(2009):148-156.

入库方式： OAI收割

来源：计算技术研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。