计算机科学

计算机科学 ›› 2023, Vol. 50 ›› Issue (5): 146-154.doi: 10.11896/jsjkx.220400227

• 计算机图形学&多媒体 • 上一篇    下一篇

伪异常选择驱动学习的视频异常检测

赵松, 傅豪, 王洪星   

  1. 重庆大学信息物理社会可信服务计算教育部重点实验室 重庆 400044
    重庆大学大数据与软件学院 重庆 400044
  • 收稿日期:2022-04-22 修回日期:2022-09-12 出版日期:2023-05-15 发布日期:2023-05-06
  • 通讯作者: 王洪星(ihxwang@cqu.edu.cn)
  • 作者简介:(zhaosong@cqu.edu.cn)
  • 基金资助:
    国家自然科学基金(61976029);重庆市技术创新与发展应用专项重点项目(cstc2021jscx-gksbX0033)

Pseudo-abnormal Sample Selection for Video Anomaly Detection

ZHAO Song, FU Hao, WANG Hongxing   

  1. Key Laboratory of Dependable Service Computing in Cyber Physical Society(Chongqing University), Ministry of Education, Chongqing 400044, China
    School of Big Data & Software Engineering,Chongqing University,Chongqing 400044,China
  • Received:2022-04-22 Revised:2022-09-12 Online:2023-05-15 Published:2023-05-06
  • About author:ZHAO Song,born in 1997,postgra-duate,is a student member of China Computer Federation.His main research interests include computer vision and video anomaly detection.
    WANG Hongxing,born in 1985,Ph.D,associate professor,Ph.D supervisor,is a member of China Computer Federation.His main research interests include computer vision and pattern recognition.
  • Supported by:
    National Natural Science Foundation of China(61976029) and Key Project of Chongqing Technology Innovation and Application Development(cstc2021jscx-gksbX0033).

PDF (PC)

374

摘要： 无监督视频异常检测方法通常使用正常的监控视频数据通过帧重构/帧预测方法来训练视频异常检测模型。然而,正常视频中往往包含大量的相似画面和背景帧,数据集冗余的问题尤为明显,因此不能高效地进行异常检测模型训练。针对该问题,提出了伪异常选择驱动学习的视频异常检测方法,从原始视频训练数据中迭代选取部分异常分数高的正常视频帧(伪异常帧)来构建新的训练池,用于学习和优化视频异常检测模型。在检测模型方面,设计了基于后继帧预测的双路U-Net骨干网络,以不同采样率的视频段分别作为两个支路的输入,从而从多个粒度上更好地提取和利用视频的时空特征。为了加强典型训练数据对帧预测任务和异常检测的影响,双路U-Net中设计了多层的记忆学习模块。在常用视频异常检测数据集上进行实验,验证了所提方法在检测精度和训练效率上的有效性。

关键词: 视频监控, 异常检测, 样本选择, 记忆模型, 时空特征

Abstract: Unsupervised video anomaly detection methods generally use normal video data to train an anomaly detection model through frame reconstruction or frame prediction.However,normal videos usually contain a large number of background frames and similar scenes,which are quite redundant,leading to inefficient modeling for video anomaly detection.To address this issue,this paper proposes a pseudo-abnormal sample selection method,which iteratively selects video frames with high abnormal scores from original videos to build a new concise training pool for video anomaly detection based on future frame prediction.As for the detection model,this paper designs a two-path U-Net architecture,where each path has a different sampling frequency on video frames so that spatial-temporal features of videos can be better extracted and utilized from multiple scales.In the two-path U-Net,each layer shares a memory module to strengthen the impact of typical training data for future frame prediction and video anomaly detection.Experimental evaluation on benchmark video datasets demonstrates the efficiency and effectiveness of the proposed method.

Key words: Video surveillance, Anomaly detection, Sample selection, Memory model, Spatial-Temporal feature

中图分类号: 

  • TP391.4
[1]CHANDOLA V,BANERJEEA,KUMAR V.Anomaly detec-tion:A survey[J].ACM Computing Surveys,2009,41(3):1-58.
[2]CHALAPATHY R,CHAWLA S.Deep learning for anomalydetection:A survey[J].arXiv:1901.03407,2019.
[3]FU Z,HU W,TAN T.Similarity based vehicle trajectory clustering and anomaly detection[C]//Proceedings of the IEEE International Conference on Image Processing.2005:II-602.
[4]HASANM,CHOI J,NEUMANN J,et al.Davis.Learning temporal regularity in video sequences[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2016:733-742.
[5]ABATI D,PORRELLO A,CALDERARA S,et al.Latent space autoregression for novelty detection[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2019:481-490.
[6]LIU W,LUO W,LIAN D,et al.Future frame prediction for anomaly detection-a new baseline[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2018:6536-6545.
[7]HAO H W,JIANG R R.Training sample selection method for neural networks based on nearest neighbor rule[J].Acta Automatica Sinica,2007,33(12):1247-1251.
[8]MARKOVITZ A,SHARIR G,FRIEDMAN I,et al.Graph embedded pose clustering for anomaly detection[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2020:10536-10544.
[9]FEICHTENHOFER C,FAN H,MALIK J,et al.Slowfast networks for video recognition[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision.2019:6202-6211.
[10]LENG J X,TAN M P,HU B,et al.Video Anomaly Detection Based on Implicit View Transformation[J].Computer Science,2022,49(2):142-148.
[11]PARK H,NOH J,HAM B.Learning memory guided normality for anomaly detection[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2020:14372-14381.
[12]RONNEBERGER O,FISCHER P,BROX T.U-Net:convolu-tional networks for biomedical image segmen-tation[C]//Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention.2015:234-241.
[13]FANG Z,LIANG J,ZHOU J,et al.Anomaly Detection with Bidirectional Consistency in Videos[J].IEEE Transactions on Neural Networks and Learning Systems,2022,33(3):1079-1092.
[14]XU D,YAN Y,RICCI E,et al.Detecting anomalous events invideos by learning deep representations of appearance and motion[J].Computer Vision and Image Understanding,2017,156:117-127.
[15]YU G,WANG D,CAI X,et al.Cloze test helps:Effective video anomaly detection via learning to complete video events[C]//Proceedings of the ACM International Conference on Multimedia.2020:583-591.
[16]CHANG Y,TU Z,XIE W,et al.Clustering driven deep autoencoder for video anomaly detection[C]//Proceedings of the European Conference on Computer Vision.2020:329-345.
[17]HAO Y,LI J,WANG N,et al.Spatiotemporal consistency-enhanced network for video anomaly detection[J].Pattern Recognition,2022,121:108232.
[18]GEORGESCU M,BARBALAU A,IONESCU R,et al.Anomaly detection in video via self-supervised and multi-task learning[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2021:12742-12752.
[19]GRAVES A,MOHAMED A,HINTON G.Speech recognition with deep recurrent neural networks[C]//Proceedings of the IEEE International Conference on Acoustics,Speech and Signal Processing.2013:6645-6649.
[20]SHI X,CHEN Z,WANG H,et al.Convolutional LSTM Net-work:A machine learning approach for precipitation nowcasting[C]//Advances in Neural Information Processing Systems.2015:802-810.
[21]WESTON J,CHOPRA S,BORDES A.Memory networks[J].arXiv:1410.3916,2014.
[22]WANG X,DU Y,LIN S,et al.adVAE:a self-adversarial variational autoencoder with Gaussian anomaly prior knowledge for anomaly detection[J].Knowledge-Based Systems,2019,190:105187.
[23]HAN T,XIE W A.Zisserman.Memory augmented dense predictive coding for video representation learning[C]//Proceedings of the European Conference on Computer Vision.2020:312-329.
[24]SUKHBAATAR S,SZLAM A,WESTON J,et al.End-to-end memory networks[J].arXiv:1503.08895,2015.
[25]MILLER A,FISCH A,DODGE J,et al.Key-value memory networks for directly reading documents[J].arXiv:1606.03126,2016.
[26]GONG D,LIU L,LE V,et al.Memorizing normality to detect anomaly:Memory-augmented deep autoencoder for unsupervised anomaly detection[C]//Proceedings of the IEEE International Conference on Computer Vision.2019:1705-1714.
[27]ZHOU Y,REN Q C,NIU H B.Research on training sample data selection methods[J].Computer Science,2020,47(11A):402-408.
[28]PLUTOWSKI M,WHITE H.Selecting concise training setsfrom clean data[J].IEEE Transactions on Neural Networks,1993,4(2):305-318
[29]WANG J,NESKOVIC P,COOPER L N.Training data selection for support vector machines[C]//International Conference on Natural Computation,2005:554-564.
[30]CORTES C,VAPNIK V.Support-vector networks[J].Machine learning,1995,20(3):273-297.
[31]TANG K,LIN M,MINKU F,et al.Selective negative correla-tion learning approach to incremental learning[J].Neurocomputing,2009,72(13/14/15):2796-2805.
[32]CONG Y,YUAN J,LIU J.Sparse reconstruction cost for abnormal event detection[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2011:3449-3456.
[33]MAHADEVAN V,LI W,BHALODIA V,et al.Anomaly detection in crowded scenes[C]//Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition.2010:1975-1981.
[34]LU C,SHI J,AND JIA J.Abnormal event detection at 150 fps in matlab[C]//Proceedings of the IEEE International Conference on Computer Vision.2013:2720-2727.
[35]WANG Z,ZOU Y,ZHANG Z.Cluster Attention Contrast for Video Anomaly Detection[C]//Proceedings of the International Conference on Multimedia.2020:2463-2471.
[36]LI B,LEROUX S,SIMOENS P.Decoupled appearance and motion learning for efficient anomaly detection in surveillance video[J].Computer Vision and Image Understanding,2021,210:103249.
[37]ZHONG Y,CHEN X,JIANG J,et al.A cascade reconstruction model with generalization ability evaluation for anomaly detection in videos[J].Pattern Recognition,2022,122:108336.
[38]CHANG Y,TU Z,XIE W,et al.Video anomaly detection with spatio-temporal dissociation[J].Pattern Recognition,2022,122:108213.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
渝ICP备16013121号-4
地址：重庆市渝北区洪湖西路18号    邮编：401121  
电话：023-63500828（编辑部） 023-67039612（会议/专题） 023-67039623（财务/发票）
E-mail：jsjkx12@163.com
本系统由北京玛格泰克科技发展有限公司设计开发