[1]满君丰,李倩倩,温向兵.视频监控中可变人体行为的识别[J].东南大学学报(自然科学版),2011,41(3):492-497.[doi:10.3969/j.issn.1001-0505.2011.03.012]
 Man Junfeng,Li Qianqian,Wen Xiangbing.Recognition for changable human behaviors in video surveillance[J].Journal of Southeast University (Natural Science Edition),2011,41(3):492-497.[doi:10.3969/j.issn.1001-0505.2011.03.012]
点击复制

视频监控中可变人体行为的识别()
分享到:

《东南大学学报(自然科学版)》[ISSN:1001-0505/CN:32-1178/N]

卷:
41
期数:
2011年第3期
页码:
492-497
栏目:
计算机科学与工程
出版日期:
2011-05-20

文章信息/Info

Title:
Recognition for changable human behaviors in video surveillance
作者:
满君丰1李倩倩2温向兵1
(1湖南工业大学计算机与通信学院,株洲 412008)(2湖南化工职业技术学院信息工程系,株洲 412004)
Author(s):
Man Junfeng1Li Qianqian2Wen Xiangbing1
(1School of Computer and Communication, Hunan University of Technology, Zhuzhou 412008, China)
(2 Department of Information and Engineering, Hunan Chemical Vocation Technology College, Zhuzhou 412004, China)
关键词:
视频监控行为模式行为识别前景提取多层Dirichlet过程
Keywords:
video surveillance behavior pattern behavior recognition foreground extraction hierarchical Dirichlet process
分类号:
TP391.4
DOI:
10.3969/j.issn.1001-0505.2011.03.012
摘要:
为有效识别视频监控中的人体行为,提出了新的人体行为识别模型和前景提取方法. 对前景提取,采用背景边缘模型与背景模型相结合的前景检测方法,有效避免了光照、阴影等外部因素的影响. 为了快速发现人体运动过程中产生的新行为,采用分层Dirichlet过程聚类人体特征数据来判断是否有未知人体行为产生,用无限HMM对含有未知行为模式的特征向量进行有监督学习,由管理者将其添加到知识库中. 当知识库的行为模式达到一定规模时,系统可以无监督地对人体行为进行分析. 通过仿真实验证实了提出的方法在人体行为识别方面较其他方法具有独特的优势.
Abstract:
For effectively recognizing human behaviors in video surveillance, a novel behavior recognition model and a foreground extraction method are presented. For foreground detection, combining background edge model and background model, a foreground detection method is proposed, which can effectively avoid the light, shadows and other external factors. To quickly find new behaviors produced in the process of human motion, a hierarchical Dirichlet process is adopted to aggregate monitored feature data for human body to determine whether unknown behaviors are produced or not. The infinite hidden Markov model(HMM) is adopted to learn unknown behavior patterns with supervised method, and then update the knowledge base. When knowledge base reaches a certain scale, system can analyze human behaviors with unsupervised method. Simulation experiments show that the proposed method has unique advantage over others for human behavior detection in real-time video surveillance.

参考文献/References:

[1] 王 亮,胡卫明,谭铁牛.人运动的视觉分析综述[J].计算机学报,2002,25(3):225-237.
  Wang Liang,Hu Weiming,Tan Tieniu.A survey of visual analysis of human motion [J].Chinese Journal of Computers,2002,25(3):225-237.(in Chinese)
[2] Xang T,Gong S G.Video behavior profiling for anomaly detection [J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2008,30(5):893-908.
[3] Bobick A,Davis J.Real-time recognition of activity using temporal templates [C]//Proceedings of IEEE Workshop on Applications of Computer Vision.Sarasota,FL,USA,1996:39-42.
[4] Davis J,Bobick A.The representation and recognition of action using temporal templates,technical report 402 [R].Cambridge,MA,USA:Perceptual Computing Group,MIT Media Lab,2007.
[5] Bregler C.Learning and recognizing human dynamics in video sequences[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Puerto Rico,USA,1997:568-574.
[6] Man J F,Yang L M,Wan L J,et al.Research on online monitoring and analyzing of interactive behavior of distributed software [J].Journal of Software,2010,5(4):361-368.
[7] Teh Y W,Jordan M I,Beal M J.Hierarchical Dirichlet processes [J].Journal of the American Statistical Association,2006,101(476):1566-1581.
[8] Jurgen V G,Saatci Y,Teh Y W.Beam sampling for the infinite hidden Markov model [C]//Proceedings of the 25th International Conference on Machine Learning.Helsinki,Finland,2008:102-109.

相似文献/References:

[1]程旭,郭海燕,李拟珺,等.一种基于超像素的局部判别式跟踪算法[J].东南大学学报(自然科学版),2014,44(6):1105.[doi:10.3969/j.issn.1001-0505.2014.06.002]
 Cheng Xu,Guo Haiyan,Li Nijun,et al.Local discriminative tracking algorithm based on superpixel[J].Journal of Southeast University (Natural Science Edition),2014,44(3):1105.[doi:10.3969/j.issn.1001-0505.2014.06.002]

备注/Memo

备注/Memo:
作者简介:满君丰(1976—),男,博士,副教授,mjfok@qq.com.
基金项目:国家自然科学基金资助项目(60773110)、湖南省自然科学基金资助项目(09JJ6087)、中国包装总公司科研资助项目(2008-XK10)、湖南省科技计划资助项目(2010FJ3041)、湖南工业大学研究生创新基金资助项目(CX1003).
引文格式: 满君丰,李倩倩,温向兵.视频监控中可变人体行为的识别[J].东南大学学报:自然科学版,2011,41(3):492-497.[doi:10.3969/j.issn.1001-0505.2011.03.012]
更新日期/Last Update: 2011-05-20