[1]周晓雨,余博思,丁恩杰.基于稀疏表示和低秩逼近的自适应异常事件 检测算法[J].南京理工大学学报(自然科学版),2016,40(06):666.[doi:10.14177/j.cnki.32-1397n.2016.40.06.005]
　Zhou Xiaoyu,Yu Bosi,Ding Enjie.Adaptive abnormal event detection algorithm based on sparse representation and low rank approximation[J].Journal of Nanjing University of Science and Technology,2016,40(06):666.[doi:10.14177/j.cnki.32-1397n.2016.40.06.005]
点击复制

基于稀疏表示和低秩逼近的自适应异常事件 检测算法
分享到：

《南京理工大学学报》（自然科学版）[ISSN:1005-9830/CN:32-1397/N]

卷:
40卷
期数:
2016年06期
页码:
666
栏目:
出版日期:
2016-12-30

文章信息/Info

Title:
Adaptive abnormal event detection algorithm based on sparse representation and low rank approximation
文章编号:
1005-9830(2016)06-0666-08
作者:
周晓雨1; 2; 余博思3; 丁恩杰1
1.中国矿业大学 物联网(感知矿山)研究中心,江苏 徐州 221008; 2.江苏省财经职业技术学院 机械电子与信息工程学院,江苏 淮安 223003; 3.南京理工大学 计算机科学与工程学院,江苏 南京 210094
Author(s):
Zhou Xiaoyu1; 2; Yu Bosi3; Ding Enjie1
1.Research Center of Internet of Things(Sensory Mine),China University of Mining and Technology, Xuzhou 221008,China; 2.Faculty of Mechanical Electronic and Information Engineering,Jiangsu Vocational College of Finance and Economics,Huai'an 223003,China; 3.School of Computer Science and Engineering,Nanjing University of Science and Technology,Nanjing 210094,China
关键词:
稀疏表示;  低秩逼近;  异常事件检测;  低秩稀疏编码模型;  字典学习;  K-均值聚类
Keywords:
sparse representation;  low rank approximation;  abnormal event detection;  low rank sparse coding model;  dictionary learning;  K-means clustering
分类号:
TP391.4
DOI:
10.14177/j.cnki.32-1397n.2016.40.06.005
摘要:
针对传统异常事件检测算法没有考虑视频数据低秩特性的问题,提出了基于低秩稀疏编码模型的字典学习算法。对提取的多尺度三维时空梯度特征进行K-均值聚类。利用低秩稀疏编码模型进行每一个特征聚类的字典学习。通过迭代聚类和字典学习获取所有的正常行为模式。采用公共数据集UCSD Ped1和Avenue检测该算法的性能。与社会力(SF)、混合概率主成分分析(MPPCA)、社会力-混合概率主成分分析(SF-MPPCA)、混合动态纹理(MDT),Adam、子空间(Suspace)、稀疏组合学习框架(SCLF)7种方法对比,该文算法具有较高的正确率和较强的实时性。
Abstract:
A dictionary learning algorithm based on a low rank sparse coding model is proposed aiming at the problem that traditional abnormal event detection algorithm doesn't consider the low rank characteristic of video sequences.Multi scale gradient characteristics of three-dimensional space-time are extracted and clustered using K-means clustering.Dictionary learning of every feature clustering is carried out using the low rank sparse coding model.Every normal behavior pattern is obtained using iteration clustering and dictionary learning.The performance of this algorithm is tested using two public data sets UCSD Ped1 and Avenue.Compared with social force(SF),mixture of probabilistic principal component analyzers(MPPCA),SF-MPPCA,mixture of dynamic texture(MDT),Adam,subspace and sparse combination learning framework(SCLF),the result of this algorithm is more correct and real-time.

参考文献/References:

[1] Kratz L,Nishino K.Anomaly detection in extremely crowded scenes using spatio-temporal motion pattern models[C]//IEEE Conference on Computer Vision and Pattern Recognition.Florida,USA:IEEE,2009:1446-1453.
[2]Ma Xiaoxu,Wang Xiaogang,Grimson W E L.Unsupervised activity perception in crowded and complicated scenes using hierarchical Bayesian models[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2009,31(3):539-555.
[3]Mahadevan V,Li Weixin,Bhalodia W,et al.Anomaly detection in crowded scenes[C]//IEEE Conference on Computer Vision and Pattern Recognition.San Francisco,USA:IEEE,2010:1975-1981.
[4]Wu Shandong,Moore B E,Shah M.Chaotic invariants of Lagrangian particle trajectories for anomaly detection in crowded scenes[C]//IEEE Conference on Computer Vision and Pattern Recognition.San Francisco,USA:IEEE,2010:2054-2060.
[5]Li Weixin,Mahadevan V,Vasconcelos N.Anomaly detection and localization in crowded scenes[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2014,36(2):18-32.
[6]Stauffer C,Grimson W E L.Learning patterns of activity using real-time tracking[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2000,22(8):747-757.
[7]Kim J,Grauman K.Observe locally,infer globally:A space-time MRF for detecting abnormal activities with incremental updates[C]//IEEE Conference on Computer Vision and Pattern Recognition.Florida,USA:IEEE,2009:2921-2928.
[8]Benezeth Y,Jodoin P M,Saligrama V.Abnormality detection using low-level co-occurring events[J].Pattern Recognition Letters,2011,32(4):423-431.
[9]Tran D,Yuan J,Forsyth D.Video event detection:From subvolume localization to spatiotemporal path search[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2014,36(2):404-416.
[10]Basharat A,Gritai A,Shah M.Learning object motion patterns for anomaly detection and improved object detection[C]//IEEE Conference on Computer Vision and Pattern Recognition.Alaska,USA:IEEE,2008:1-8.
[11]Li Jian,Gong Shaogang,Xiang Tao.Global behaviour inference using probabilistic latent semantic analysis[C]//British Machine Vision Conference.Leeds,UK:BMVA,2008:1-12.
[12]Li Jian,Hospedales T M,Gong Shaogang,et al.Learning rare behaviours[C]//Asian Conference on Computer Vision.Queenstown,NZ:AFCV,2010:293-307.
[13]Hospedales T M,Li Jian,Gong Shaogang.Identifying rare and subtle behaviors:A weakly supervised joint topic model[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2011,33(12):2451-2464.
[14]Boiman O,Irani M.Detecting irregularities in images and in video[C]//IEEE International Conference on Computer Vision.Beijing:IEEE,2005:462-469.
[15]Xiang Tao,Gong Shaogang.Video behaviour profiling and abnormality detection without manual labelling[C]//International Conference on Computer Vision.Beijing:IEEE,2005:1238-1245.
[16]Boiman O,Irani M.Detecting irregularities in images and in video[J].International Journal of Computer Vision,2007,74(1):17-31.
[17]周红志,程向阳,一种基于局部时空特征的视频异常检测方案[J].计算机工程,2014,40(4):203-208.
Zhou Hongzhi,Chen Xiangyang.A video anomaly detection scheme based on local spatio-temporal features[J].Computer Engineering,2014,40(4):203-208.
[18]胡芝兰,江帆,王贵锦,等,基于运动方向的异常行为检测[J].自动化学报,2008,34(11):1348-1357.
Hu Zhilan,Jiang Fan,Wang Guijin,et al.Anomaly detection based on motion direction[j].Acta Automatica Sinica,2008,34(11):1348-1357.
[19]郑怀兵,翟济云,基于视频分析的森林火灾烟雾检测方法[J].南京理工大学学报,2015,39(6):686-691.
Zheng Huaibing,Zhai Jiyun.Forest fire smoke detection based on video analysis[J].Journal of Nanjing University of Science and Technology,2015,39(6):686-691.
[20]赵小强,岳宗达.一种面向图像拼接的快速匹配算法[J].南京理工大学学报,2016,40(2):165-171.
Zhao Xiaoqiang,Yue Zongda.Fast matching algorithm for image mosaic[J].Journal of Nanjing University of Science and Technology,2016,40(2):165-171.
[21]王方圆,张树武,李和平.基于时空灰度序特征的视频片段定位算法[J].软件学报,2013,24(12):2921-2935.
Wang Fangyuan,Zhang Shuwu,Li Heping.Video clip identification algorithm based on spatio-temporal ordinal measures[J].Journal of Software,2013,24(12):2921-2935.
[22]Lu C,Shi Jianping,Jia Jiaya.Abnormal event detection at 150 FPS in MATLAB[C]//IEEE International Conference on Computer Vision.Sydney,Australia:IEEE,2013:2720-2727.
[23]Yang Cong,Yuan Junsong,Liu Ji.Sparse reconstruction cost for abnormal event detection[C]//IEEE Conference on Computer Vision and Pattern Recognition.Colorado,USA:IEEE,2011:3449-3456.
[24]Cai Jianfeng,Shen Zuowei.A singular value thresholding algorithm for matrix completion[J].Siam Journal on Optimization,2010,20(4):1956-1982.
[25]Dong Weishen,Shi Guangming,Li Xin.Nonlocal image restoration with bilateral variance estimation:A low-rank approach[J].IEEE Transactions on Image Processing,201,22(2):700-711.
[26]Yang Cong,Yuan Junsong,Liu Ji.Abnormal event detection in crowded scenes using sparse representation[J].Pattern Recognition,2013,46(7):1851-1864.
[27]Adam A,Rivlin E,Reinitz D.Robust real-time unusual event detection using multiple fixed-location monitors[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2008,30(3):555-560.
[28]Elhamifar E,Vidal R.Sparse subspace clustering[C]//IEEE Conference on Computer Vision and Pattern Recognition.Florida,USA:IEEE,2009:2790-2797.

相似文献/References:

[1]宋晓宁,薛益时,於东军,等.一种优化恢复压缩传感矩阵的模糊自适应方法[J].南京理工大学学报(自然科学版),2013,37(04):479.
　Song Xiaoning,Xue Yishi,Yu Dongjun,et al.Fuzzy adaptive method for optimizing recovery of compressive sensing matrix[J].Journal of Nanjing University of Science and Technology,2013,37(06):479.

备注/Memo

备注/Memo:
收稿日期:2016-08-24 修回日期:2016-11-04
基金项目:淮安市科技支撑计划(HAS2014023)
作者简介:周晓雨(1980-),男,博士生,主要研究方向:计算机网络通信、传感器、路由算法,E-mail: zxy_zxy@163.com。
引文格式:周晓雨,余博思,丁恩杰.基于稀疏表示和低秩逼近的自适应异常事件检测算法[J].南京理工大学学报,2016,40(6):666-673.
投稿网址:http://zrxuebao.njust.edu.cn
更新日期/Last Update: 2016-12-30