计算机科学

计算机科学 ›› 2024, Vol. 51 ›› Issue (8): 217-223.doi: 10.11896/jsjkx.230600148

• 计算机图形学&多媒体 • 上一篇    下一篇

基于双鉴别器和伪视频生成的视频异常检测方法

郭方圆, 吉根林   

  1. 南京师范大学计算机与电子信息学院/人工智能学院 南京 210023
  • 收稿日期:2023-06-19 修回日期:2023-11-24 出版日期:2024-08-15 发布日期:2024-08-13
  • 通讯作者: 吉根林(glji@njnu.edu.cn)
  • 作者简介:(212202032@njnu.edu.cn)
  • 基金资助:
    国家自然科学基金(41971343)

Video Anomaly Detection Method Based on Dual Discriminators and Pseudo Video Generation

GUO Fangyuan, JI Genlin   

  1. School of Computer and Electronic Information/School of Artificial Intelligence,Nanjing Normal University,Nanjing 210023,China
  • Received:2023-06-19 Revised:2023-11-24 Online:2024-08-15 Published:2024-08-13
  • About author:GUO Fangyuan,born in 1999,master.Her main research interests include big data analysis and mining technology.
    JI Genlin,born in 1964,Ph.D,professor,is a member of CCF(No.09027S).His main research interests include big data analysis and mining technology.
  • Supported by:
    National Natural Science Foundation of China(41971343).

PDF (PC)

378

摘要： 在无监督的视频异常检测任务中,通常使用深度自编码器在仅包含正常事件的数据集上进行训练,并根据重构(预测)误差来识别异常帧。然而,这种假设在实践中并不总是成立,有时自编码器对异常事件也可以进行很好的重构(预测),从而导致异常的误检测。为了解决这一问题,提出了一种基于双鉴别器和伪视频生成的视频异常检测方法,通过鉴别器和生成器之间的对抗训练来提高生成模型对正常帧的预测能力,并抑制生成模型对伪视频帧的预测能力。此外,在生成模型中引入协调注意力,以进一步提升模型的生成能力。同时,将以往方法中的预测未来帧改为预测中间帧,有利于模型学习前向和后向的运动信息,从而提升模型的检测性能。在公开数据集UCSD Ped2和CUHK Avenue上进行实验,结果表明,AUC值在两个公开数据集上分别达到了98.6％和85.9％,相比其他视频异常检测方法,所提方法可显著提高视频异常检测的性能。

关键词: 视频异常检测, 深度学习, 生成对抗网络, 伪视频, 预测

Abstract: In unsupervised video anomaly detection tasks,deep autoencoders are typically trained on datasets containing only normal events and use reconstruction(prediction) error to identify anomalous frames.However,this assumption does not always true in practice because sometimes autoencoders can reconstruct(predict) anomalous events well,leading to false alarms.To address this issue,this paper proposes a video anomaly detection method based on dual discriminators and pseudo video generation,which enhances the generation model’s prediction capability of normal frames and suppresses its prediction capability of pseudo video frames through adversarial training between the discriminator and the generator.Moreover,the introduction of coordinated attention in the generation model further improves its detection performance.Additionally,by predicting intermediate frames instead of future frames in previous methods,the model can learn forward and backward motion information,which further enhances its detection performance.Experimental results on the publicly available datasets UCSD Ped2 and CUHK Avenue demonstrate that the proposed method achieves AUC values of 98.6% and 85.9%,respectively,outperforming other video anomaly detection methods significantly.

Key words: Video anomaly detection, Deep learning, Generative adversarial network, Pseudo-video, Prediction

中图分类号: 

  • TP183
[1]MUNAWAR A,VINAYAVEKHIN P,DE MAGISTRIS G.Limiting the reconstruction capability of generative neural network using negative learning[C]//2017 IEEE 27th Interna-tional Workshop on Machine Learning for Signal Processing(MLSP).IEEE,2017:1-6.
[2]ZONG B,SONG Q,MIN M R,et al.Deep autoencoding gaussian mixture model for unsupervised anomaly detection[C]//International Conference on Learning Representations.2018.
[3]ZAHEER M Z,LEE J,ASTRID M,et al.Old is gold:Redefining the adversarially learned one-class classifier training paradigm[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2020:14183-14193.
[4]GONG D,LIU L,LE V,et al.Memorizing normality to detectanomaly:Memory-augmented deep autoencoder for unsupervised anomaly detection[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision.2019:1705-1714.
[5]LIU W,LUO W,LIAN D,et al.Future frame prediction foranomaly detection-a new baseline[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2018:6536-6545.
[6]SONG H,SUN C,WU X,et al.Learning normal patterns via adversarial attention-based autoencoder for abnormal event detection in videos[J].IEEE Transactions on Multimedia,2019,22(8):2138-2148.
[7]ISOLA P,ZHU J Y,ZHOU T,et al.Image-to-image translation with conditional adversarial networks[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2017:1125-1134.
[8]DONG F,ZHANG Y,NIE X.Dual discriminator generative adversarial network for video anomaly detection[J].IEEE Access,2020,8:88170-88176.
[9]GEORGESCU M I,IONESCU R T,KHAN F S,et al.A background-agnostic framework with adversarial training for abnormal event detection in video[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2021,44(9):4505-4523.
[10]POURREZA M,MOHAMMADI B,KHAKI M,et al.G2d:Generate to detect anomaly[C]//Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision.2021:2003-2012.
[11]RONNEBERGER O,FISCHER P,BROX T.U-net:Convolu-tional networks for biomedical image segmentation[C]//Medical Image Computing and Computer-Assisted Intervention-MICCAI 2015:18th International Conference,Munich,Germany,October 5－9,2015,Proceedings,Part III 18.Springer Inter-national Publishing,2015:234-241.
[12]HOU Q,ZHOU D,FENG J.Coordinate attention for efficient mobile network design[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2021:13713-13722.
[13]LE V T,KIM Y G.Attention-based residual autoencoder forvideo anomaly detection[J].Applied Intelligence,2023,53(3):3240-3254.
[14]LI H,SUN X,LI C,et al.MPAT:multi-path attention temporal method for video anomaly detection[J].Multimedia Tools and Applications,2023,82(8):12557-12575.
[15]SHIN W,BU S J,CHO S B.3D-convolutional neural networkwith generative adversarial network and autoencoder for robust anomaly detection in video surveillance[J].International Journal of Neural Systems,2020,30(6):2050034.
[16]PARK H,NOH J,HAM B.Learning memory-guided normality for anomaly detection[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2020:14372-14381.
[17]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.
[18]LU C,SHI J,AND JIA J.Abnormal event detection at 150 fps in matlab[C]//Proceedings of the IEEE International Confe-rence on Computer Vision.2013:2720-2727.
[19]NAWARATNE R,ALAHAKOON D,DE SILVA D,et al.Spatiotemporal anomaly detection using deep learning for real-time video surveillance[J].IEEE Transactions on Industrial Informatics,2019,16(1):393-402.
[20]JI X,LI B,ZHU Y.Tam-net:Temporal enhanced appearance-to-motion generative network for video anomaly detection[C]//2020 International Joint Conference on Neural Networks(IJCNN).IEEE,2020:1-8.
[21]YANG Y,ZHAN D,YANG F,et al.Improving video anomaly detection performance with patch-level loss and segmentation map[C]//2020 IEEE 6th International Conference on Computer and Communications(ICCC).IEEE,2020:1832-1839.
[22]LU Y,YU F,REDDY M K K,et al.Few-shot scene-adaptiveanomaly detection[C]//Computer Vision－ECCV 2020:16th European Conference,Glasgow,UK,Part V 16.Springer International Publishing,2020:125-141.
[23]PARK C,CHO M A,LEE M,et al.FastAno:Fast anomaly detection via spatio-temporal patch transformation[C]//Procee-dings of the IEEE/CVF Winter Conference on Applications of Computer Vision.2022:2249-2259.
[24]ZHANG Q,WEI H,CHEN J,et al.Video Anomaly Detection Based on Attention Mechanism[J].Symmetry,2023,15(2):528.
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