基于HOG3D描述器与稀疏编码的异常行为检测方法

何聪芹; 朱煜; 陈宁

doi:10.14135/j.cnki.1006-3080.2016.01.018

何聪芹 , 朱煜 , 陈宁

引用本文:

Citation:

基于HOG3D描述器与稀疏编码的异常行为检测方法

1.
华东理工大学信息科学与工程学院, 上海 200237

通讯作者: 朱煜, zhuyu@ecust.edu.cn ;

基金项目: 国家自然科学基金(61271349)
中央高校基本科研业务费专项资金(WH1214015)
中图分类号: TP181

Abnormal Behavior Detection Using Sparse Coding and HOG3D Descriptor

HE Cong-qin ¹ ,
ZHU Yu ^{1
,

,} ,
CHEN Ning ¹

1.
School of Information Science and Engineering, East China University of Science and Technology, Shanghai 200237, China

Corresponding author: ZHU Yu, zhuyu@ecust.edu.cn ;

CLC number: TP181

摘要: 提出了一种基于稀疏编码理论的视频异常行为检测方法,并使用HOG3D空-时描述器表征视频序列的形态及运动信息。首先,从正常视频序列中提取空-时兴趣点,获得其特征向量作为训练样本。通过K-SVD字典训练算法构建过完备字典,使得正常样本在所构建字典上的表达具有很好的稀疏性。在稀疏编码过程中,按视频段读取测试视频序列,求解特征信息在字典上的关于其稀疏系数的凸优化问题,然后根据稀疏编码改进公式求得重构误差数值。最后的判断阶段,计算视频段的相对重构误差,相对重构误差为正表明为异常视频段,否则为正常视频段。在UMN数据库3个场景及Weizmann数据库上进行实验,验证了本文算法的有效性。将实验拓展到现实监控视频中,结果表明本文方法在实践中同样具有较好的应用价值。
- 稀疏编码 /
- 异常行为检测 /
- 重构误差 /
- HOG3D描述器 /
- K-SVD
Abstract: In this paper,an abnormality behavior detect method based on sparse coding is proposed and the HOG3D descriptor is utilized to capture appearance and motion information of the surveillance videos.Firstly,a set of training data are extracted from normal events.And then,K-SVD method is utilized to construct the dictionary atoms such that each normal member attains the best representation under the strict sparsity constraints.In the process of sparse coding,by taking a video session as a sample,we introduce the relative sparse reconstruction error over the normal dictionary to measure the level of normal of the testing sample.When the relative sparse reconstruction error is positive,the sample would be judged as abnormal.The proposed method is tested via UMN database,Weizmann database and real world surveillance videos,which show that the proposed method can reliably detect the unusual events in the video sequence.
- sparse coding /
- abnormal behavior detection /
- sparse reconstruction error /
- HOG3D descriptor /
- K-SVD

[1]	ADAM A,RIVLIN E,SHIMSHONI I,et al.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.
[2]	KIM J,GRAUMAN K.Observe locally,infer globally:A space-time MRF for detecting abnormal activities with incremental updates[C]//2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2009). Miami,Florida,USA:IEEE,2009:2921-2928.
[3]	KRATZ L,NISHINO K.Anomaly detection in extremely crowded scenes using spatio-temporal motion pattern models[C]//2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2009). Miami,Florida,USA: IEEE,2009:1446-1453.
[4]	MEHRAN R,OYAMA A,SHAH M.Abnormal crowd behavior detection using social force model[C]//2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2009).Miami,Florida,USA: IEEE,2009:935-942.
[5]	LAPTEV I.On space-time interest points[J].International Journal of Computer Vision,2005,64(2/3):107-123.
[6]	DOLLÁR P,RABAUD V,COTTRELL G,et al.Behavior recognition via sparse spatio-temporal features[C]//2nd Joint IEEE International Workshop on Visual Surveillance and Performance Evaluation of Tracking and Surveillance,2005.USA: IEEE,2005:65-72.
[7]	BLANK M,GORELICK L,SHECHTMAN E,et al.Actions as space-time shapes[C]//Tenth IEEE International Conference on Computer Vision2005,ICCV 2005.Beijing:IEEE,2005,2:1395-1402.
[8]	HELBING D,MOLNAR P.Social force model for pedestrian dynamics[J].Physical Review E,1995,51(5):4282.
[9]	KLASER A,MARSZAŁEK M,SCHMID C.A spatio-temporal descriptor based on 3d-gradients[C]//BMVC 2008-19th British Machine Vision Conference.UK: British Machine Vision Association,2008,275:1-10.
[10]	WILLEMS G,TUYTELAARS T,VAN GOOL L.An efficient dense and scale-invariant spatio-temporal interest point detector[M]//10th European Conference on Computer Vision.Marseille.France:Springer Berlin Heidelberg,2008:650-663.
[11]	CONG Yang,YUAN Junsong,LIU Ji.Sparse reconstruction cost for abnormal event detection[C]//2011 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).Providence,RI:IEEE,2011:3449-3456.
[12]	ZHANG Tianzhu,GHANEM B,LIU S,et al.Robust visual tracking via structured multi-task sparse learning[J].International Journal of Computer Vision,2013,101(2):367-383.
[13]	ZHAO B,FEI-FEI L,XING E P.Online detection of unusual events in videos via dynamic sparse coding[C]//2011 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).Colorado Springs,USA:IEEE,2011:3313-3320.
[14]	AHARON M,ELAD M,BRUCKSTEIN A.K-SVD:An algorithm for designing overcomplete dictionaries for sparse representation[J].IEEE Transactions on Signal Processing,2006,54(11):4311-4322.
[15]	MEHRAN R,OYAMA A,SHAH M.Abnormal crowd behavior detection using social force model[C]//IEEE Conference on Computer Vision and Pattern Recognition,2009.CVPR 2009.Miami:IEEE,2009:935-942.
[16]	谢锦生,郭立,赵龙,等.一种基于稀疏编码模型的视频异常发现方法[J].小型微型计算机系统,2014,35(4):917-921.
[17]	谢锦生,郭立,赵龙.基于快速稀疏编码与惊奇计算的视频异常检测方法[J].中国科学技术大学学报,2013,43(7):561-568.

点击查看大图

计量

文章访问数: 9737
HTML全文浏览量: 584
PDF下载量: 2346
被引次数: 0

基于HOG3D描述器与稀疏编码的异常行为检测方法

通讯作者: 朱煜, zhuyu@ecust.edu.cn;

1. 华东理工大学信息科学与工程学院, 上海 200237

收稿日期: 2015-03-24
网络出版日期: 2016-02-29

基金项目: 国家自然科学基金(61271349)中央高校基本科研业务费专项资金(WH1214015)

关键词:

摘要: 提出了一种基于稀疏编码理论的视频异常行为检测方法,并使用HOG3D空-时描述器表征视频序列的形态及运动信息。首先,从正常视频序列中提取空-时兴趣点,获得其特征向量作为训练样本。通过K-SVD字典训练算法构建过完备字典,使得正常样本在所构建字典上的表达具有很好的稀疏性。在稀疏编码过程中,按视频段读取测试视频序列,求解特征信息在字典上的关于其稀疏系数的凸优化问题,然后根据稀疏编码改进公式求得重构误差数值。最后的判断阶段,计算视频段的相对重构误差,相对重构误差为正表明为异常视频段,否则为正常视频段。在UMN数据库3个场景及Weizmann数据库上进行实验,验证了本文算法的有效性。将实验拓展到现实监控视频中,结果表明本文方法在实践中同样具有较好的应用价值。