[1]林国余,柏云,张为公.基于耦合隐马尔可夫模型的异常交互行为识别[J].东南大学学报(自然科学版),2013,43(6):1217-1221.[doi:10.3969/j.issn.1001-0505.2013.06.016]
 Lin Guoyu,Bai Yun,Zhang Weigong.Recognition of abnormal interactions based on coupled hidden Markov models[J].Journal of Southeast University (Natural Science Edition),2013,43(6):1217-1221.[doi:10.3969/j.issn.1001-0505.2013.06.016]
点击复制

基于耦合隐马尔可夫模型的异常交互行为识别()
分享到:

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

卷:
43
期数:
2013年第6期
页码:
1217-1221
栏目:
计算机科学与工程
出版日期:
2013-11-20

文章信息/Info

Title:
Recognition of abnormal interactions based on coupled hidden Markov models
作者:
林国余12柏云1张为公12
1东南大学仪器科学与工程学院, 南京 210096; 2东南大学苏州研究院, 苏州 215123
Author(s):
Lin Guoyu12 Bai Yun1 Zhang Weigong12
1School of Instrument Science and Engineering, Southeast University, Nanjing 210096, China
2Suzhou Institute, Southeast University, Suzhou 215123, China
关键词:
异常交互行为 耦合隐马尔可夫模型 运动特征 形态特征
Keywords:
abnormal interactions coupled hidden Markov models motion feature shape feature
分类号:
TP391
DOI:
10.3969/j.issn.1001-0505.2013.06.016
摘要:
为了有效识别视频监控领域中的打斗和抢劫等异常交互行为,提出一种基于耦合隐马尔可夫模型(CHMM)的异常交互行为识别方法.首先对人与人之间异常交互行为与正常交互行为的特征差别进行分析,然后提取了包括速度、面积变化率、目标外接矩形长宽比变化率、目标间距、目标运动方向角度差以及方向梯度直方图6类人体目标的运动特征和形态特征,并组成训练数据集,在此基础上使用耦合隐马尔可夫方法构建异常交互行为模型.实验中引入一些典型的行为数据库,如CASIA和CAVIAR数据集,通过和传统的基于隐马尔可夫模型(HMM)的识别方法进行对比,表明CHMM方法更适合于识别少数人的异常交互行为,且识别率更高.
Abstract:
To effectively recognize the abnormal interactions such as fighting and robbing in an intelligent video surveillance area, a recognition method for abnormal interactions based on coupled hidden Markov models(CHMM)is presented. First, the difference between the features of abnormal interactions and that of normal interactions is analyzed. Then the motion features and shape features of the object are extracted to construct the training data set, which are the speed, area change rate, change rate of the bounding rectangle aspect ratio, distance, angle difference of motion direction and the histogram of oriented gradients. Based on them, the CHMM is exploited to construct the abnormal interactions model. In the experiments, some classical test cases such as CASIA and CAVIAR are used, and the traditional recognition based on hidden Markov models(HMM)is adopted for comparison. By these experiments, it is proved that the CHMM is more suitable for recognizing the abnormal interactions between fewer people than the HMM, and the recognition rate of the CHMM is higher than that of the HMM.

参考文献/References:

[1] Oliver N M, Rosario B, Pentland A P. A Bayesian computer vision system for modeling human interactions [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000, 22(8): 831-843.
[2] 杜友田, 陈峰, 徐文立. 基于多层动态贝叶斯网络的人的行为多尺度分析及识别方法[J].自动化学报, 2009, 35(3): 225-227.
  Du Youtian, Chen Feng, Xu Wenli. Approach to human activity multi-scale analysis and recognition based on multi-layer dynamic Bayesian network [J]. Acta Automatica Sinica, 2009, 35(3): 225-227.(in Chinese)
[3] Xiang Tao, Gong Shaogang. Beyond tracking: modeling activity and understanding behavior [J]. Computer Vision, 2006, 67(1): 21-51.
[4] 朱旭东, 刘志镜. 基于主题隐马尔科夫模型的人体异常行为识别[J]. 计算机科学, 2012, 39(3): 251-255, 275.
  Zhu Xudong, Liu Zhijing. Human abnormal behavior recognition based on topic hidden Markov model[J]. Computer Science, 2012, 39(3): 251-255, 275.(in Chinese)
[5] Brand M, Oliver N, Pentland A. Coupled hidden Markov models for complex action recognition [C]//Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. San Juan, PR, USA, 1997: 994-999.
[6] Che Hao, Tao Jianhua, Pan Shifeng. Letter-to-sound conversion using coupled hidden Markov models for lexicon compression[C]//Proceedings of the 2012 International Conference on Speech Database and Assessments. Macau, China, 2012: 141-144.
[7] Luo Ronghua, Min Huaqing, Xu Yonghui, et al. Coupled hidden semi-Markov conditional random fields based context model for semantic map building[C]//Proceedings of International Conference on Machine Learning and Cybernetics. Xi’an, China, 2012: 785-791.
[8] Alippi C, Ntalampiras S, Roveri M. A cognitive fault diagnosis system for distributed sensor networks [J]. IEEE Transactions on Neural Networks and Learning Systems, 2013, 24(8): 1213-1226.
[9] Cao Longbing, Ou Yuming, Yu P S. Coupled behavior analysis with applications [J]. IEEE Transactions on Knowledge and Data Engineering, 2012, 24(8): 1378-1392.
[10] 任海兵. 非特定人自然的人体动作识别[D]. 北京: 清华大学计算机科学与技术系, 2003.
[11] 王建东. 基于视频图像的人体异常行为识别技术研究[D]. 重庆: 重庆大学通信工程学院, 2009.
[12] 杜鉴豪, 许力. 基于区域光流特征的异常行为检测[J]. 浙江大学学报:工学版, 2011, 45(7): 1161-1166.
  Du Jianhao, Xu Li. Abnormal behavior detection based on regional optical flow [J]. Journal of Zhejiang University: Engineering Science, 2011, 45(7): 1161-1166.(in Chinese)
[13] Dalal N, Triggs B. Histograms of oriented gradients for human detection [C]//IEEE Computer Society Conference on Computer Vision and Pattern Recognition. San Diego, CA,USA, 2005, 1: 886-893.

备注/Memo

备注/Memo:
作者简介: 林国余(1979—),男,博士,副教授, Andrew.Lin@seu.edu.cn.
基金项目: 国家自然科学基金资助项目(60972001)、苏州市科技计划资助项目(SG201076).
引文格式: 林国余,柏云,张为公.基于耦合隐马尔可夫模型的异常交互行为识别[J].东南大学学报:自然科学版,2013,43(6):1217-1221. [doi:10.3969/j.issn.1001-0505.2013.06.016]
更新日期/Last Update: 2013-11-20