Future Video Prediction from a Single Frame for Video Anomaly Detection

被引:2
|
作者
Baradaran, Mohammad [1 ]
Bergevin, Robert [1 ]
机构
[1] Univ Laval, 065 Ave Med, Quebec City, PQ G1V 0A6, Canada
关键词
Video anomaly detection; long-term motion modeling; future video prediction; semi-supervised learning; NETWORK;
D O I
10.1007/978-3-031-47969-4_37
中图分类号
TP301 [理论、方法];
学科分类号
081202 ;
摘要
Video anomaly detection (VAD) is an important but challenging task in computer vision. The main challenge rises due to the rarity of training samples to model all anomaly cases. Hence, semi-supervised anomaly detection methods have gotten more attention, since they focus on modeling normals and they detect anomalies by measuring the deviations from normal patterns. Despite impressive advances of these methods in modeling normal motion and appearance, long-term motion modeling has not been effectively explored so far. Inspired by the abilities of the future frame prediction proxy-task, we introduce the task of future video prediction from a single frame, as a novel proxy-task for video anomaly detection. This proxy-task alleviates the challenges of previous methods in learning longer motion patterns. Moreover, we replace the initial and future raw frames with their corresponding semantic segmentation map, which not only makes the method aware of object class but also makes the prediction task less complex for the model. Extensive experiments on the benchmark datasets (ShanghaiTech, UCSD-Ped1, and UCSD-Ped2) show the effectiveness of the method and the superiority of its performance compared to SOTA prediction-based VAD methods.
引用
收藏
页码:472 / 486
页数:15
相关论文
共 50 条
  • [31] Wavelet Residual Learning for Efficient Future Frame Prediction from Natural Video Sequences
    Gupta, Sonam
    Das, Sukhendu
    PATTERN RECOGNITION AND MACHINE INTELLIGENCE, PREMI 2021, 2024, 13102 : 63 - 71
  • [32] Adversarial composite prediction of normal video dynamics for anomaly detection
    Li, Gang
    He, Ping
    Li, Huibin
    Zhang, Fan
    COMPUTER VISION AND IMAGE UNDERSTANDING, 2023, 232
  • [33] Video Prediction and Anomaly Detection Algorithm Based On Dual Discriminator
    Fan, Sinuo
    Meng, Fanjie
    2020 5TH INTERNATIONAL CONFERENCE ON COMPUTATIONAL INTELLIGENCE AND APPLICATIONS (ICCIA 2020), 2020, : 123 - 127
  • [34] Online Video Anomaly Detection
    Zhang, Yuxing
    Song, Jinchen
    Jiang, Yuehan
    Li, Hongjun
    SENSORS, 2023, 23 (17)
  • [35] Anomaly Detection In Compressed Video
    Cavas, Sumeyye
    Beratoglu, Muhammet Sebul
    Toreyin, Behcet Ugur
    29TH IEEE CONFERENCE ON SIGNAL PROCESSING AND COMMUNICATIONS APPLICATIONS (SIU 2021), 2021,
  • [36] Video anomaly detection based on frame memory bank and decoupled asymmetric convolutions
    Zhao, Min
    Wang, Chuanxu
    Li, Jiajiong
    Jiang, Zitai
    JOURNAL OF ELECTRONIC IMAGING, 2024, 33 (05)
  • [37] Progressive prediction: Video anomaly detection via multi-grained prediction
    Zeng, Xianlin
    Jiang, Yalong
    Wang, Yufeng
    Fu, Qiang
    Ding, Wenrui
    IET IMAGE PROCESSING, 2024, 18 (10) : 2568 - 2583
  • [38] Scalable video transformer for full-frame video prediction
    Li, Zhan
    Liu, Feng
    Computer Vision and Image Understanding, 2024, 249
  • [39] Analysis of anomaly detection in surveillance video: recent trends and future vision
    Raja, Rohit
    Sharma, Prakash Chandra
    Mahmood, Md Rashid
    Saini, Dinesh Kumar
    MULTIMEDIA TOOLS AND APPLICATIONS, 2023, 82 (08) : 12635 - 12651
  • [40] Analysis of anomaly detection in surveillance video: recent trends and future vision
    Rohit Raja
    Prakash Chandra Sharma
    Md Rashid Mahmood
    Dinesh Kumar Saini
    Multimedia Tools and Applications, 2023, 82 : 12635 - 12651