Video Anomaly Detection Based on Global-Local Convolutional Autoencoder

被引:0
作者
Sun, Fusheng [1 ,2 ,3 ]
Zhang, Jiahao [1 ,2 ,3 ]
Wu, Xiaodong [4 ]
Zheng, Zhong [1 ,2 ,3 ]
Yang, Xiaowen [1 ,2 ,3 ]
机构
[1] Shanxi Key Lab Machine Vis & Virtual Real, Taiyuan 030051, Peoples R China
[2] North Univ China, Sch Comp Sci & Technol, Taiyuan 030051, Peoples R China
[3] Shanxi Prov Vis Informat Proc & Intelligent Robot, Taiyuan 030051, Peoples R China
[4] 49TH Res Inst China Elect Technol Grp Corp, Harbin 150028, Peoples R China
基金
中国国家自然科学基金;
关键词
video abnormal behavior detection; interactive fusion module; dual encoder for appearance and motion; memory module; NETWORK;
D O I
10.3390/electronics13224415
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Video anomaly detection (VAD) plays a crucial role in fields such as security, production, and transportation. To address the issue of overgeneralization in anomaly behavior prediction by deep neural networks, we propose a network called AMFCFBMem-Net (appearance and motion feature cross-fusion block memory network), which combines appearance and motion feature cross-fusion blocks. Firstly, dual encoders for appearance and motion are employed to separately extract these features, which are then integrated into the skip connection layer to mitigate the model's tendency to predict abnormal behavior, ultimately enhancing the prediction accuracy for abnormal samples. Secondly, a motion foreground extraction module is integrated into the network to generate a foreground mask map based on speed differences, thereby widening the prediction error margin between normal and abnormal behaviors. To capture the latent features of various models for normal samples, a memory module is introduced at the bottleneck of the encoder and decoder structures. This further enhances the model's anomaly detection capabilities and diminishes its predictive generalization towards abnormal samples. The experimental results on the UCSD Pedestrian dataset 2 (UCSD Ped2) and CUHK Avenue anomaly detection dataset (CUHK Avenue) demonstrate that, compared to current cutting-edge video anomaly detection algorithms, our proposed method achieves frame-level AUCs of 97.5% and 88.8%, respectively, effectively enhancing anomaly detection capabilities.
引用
收藏
页数:18
相关论文
共 43 条
[1]   Cross-Domain Video Anomaly Detection without Target Domain Adaptation [J].
Aich, Abhishek ;
Peng, Kuan-Chuan ;
Roy-Chowdhury, Amit K. .
2023 IEEE/CVF WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION (WACV), 2023, :2578-2590
[2]  
Cai RC, 2021, AAAI CONF ARTIF INTE, V35, P938
[3]   Collaborative Discrepancy Optimization for Reliable Image Anomaly Localization [J].
Cao, Yunkang ;
Xu, Xiaohao ;
Liu, Zhaoge ;
Shen, Weiming .
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS, 2023, 19 (11) :10674-10683
[4]   Privacy preserving crowd monitoring: Counting people without people models or tracking [J].
Chan, Antoni B. ;
Liang, Zhang-Sheng John ;
Vasconcelos, Nuno .
2008 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, VOLS 1-12, 2008, :1766-1772
[5]   Video anomaly detection with spatio-temporal dissociation [J].
Chang, Yunpeng ;
Tu, Zhigang ;
Xie, Wei ;
Luo, Bin ;
Zhang, Shifu ;
Sui, Haigang ;
Yuan, Junsong .
PATTERN RECOGNITION, 2022, 122
[6]   A Fast Adaptive Binarization Method for QR Code Images Based on Dynamic Illumination Equalization [J].
Chen, Rongjun ;
Huang, Yue ;
Lan, Kailin ;
Li, Jiawen ;
Ren, Yongqi ;
Hu, Xianglei ;
Wang, Leijun ;
Zhao, Huimin ;
Lu, Xu .
ELECTRONICS, 2023, 12 (19)
[7]   Look Around for Anomalies: Weakly-supervised Anomaly Detection via Context-Motion Relational Learning [J].
Cho, MyeongAh ;
Kim, Minjung ;
Hwang, Sangwon ;
Park, Chaewon ;
Lee, Kyungjae ;
Lee, Sangyoun .
2023 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2023, :12137-12146
[8]   Sparse Reconstruction Cost for Abnormal Event Detection [J].
Cong, Yang ;
Yuan, Junsong ;
Liu, Ji .
2011 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2011, :1807-+
[9]   Residual spatiotemporal autoencoder for unsupervised video anomaly detection [J].
Deepak, K. ;
Chandrakala, S. ;
Mohan, C. Krishna .
SIGNAL IMAGE AND VIDEO PROCESSING, 2021, 15 (01) :215-222
[10]   Dual Discriminator Generative Adversarial Network for Video Anomaly Detection [J].
Dong, Fei ;
Zhang, Yu ;
Nie, Xiushan .
IEEE ACCESS, 2020, 8 (88170-88176) :88170-88176