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
  • [41] Deep Frame Prediction for Video Coding
    Choi, Hyomin
    Bajic, Ivan V.
    IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2020, 30 (07) : 1843 - 1855
  • [42] Thai License Plate Detection From a Video Frame
    Pornpanomchai, Chomtip
    Anawatmongkon, Nuchakarn
    PROCEEDINGS OF THE 2009 WRI GLOBAL CONGRESS ON INTELLIGENT SYSTEMS, VOL IV, 2009, : 533 - 537
  • [43] Margin Learning Embedded Prediction for Video Anomaly Detection with A Few Anomalies
    Liu, Wen
    Luo, Weixin
    Li, Zhengxin
    Zhao, Peilin
    Gao, Shenghua
    PROCEEDINGS OF THE TWENTY-EIGHTH INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE, 2019, : 3023 - 3030
  • [44] Multi-scale Siamese prediction network for video anomaly detection
    Yang, Jingxian
    Cai, Yiheng
    Liu, Dan
    Xie, Jin
    SIGNAL IMAGE AND VIDEO PROCESSING, 2023, 17 (03) : 671 - 678
  • [45] TransAnomaly: Video Anomaly Detection Using Video Vision Transformer
    Yuan, Hongchun
    Cai, Zhenyu
    Zhou, Hui
    Wang, Yue
    Chen, Xiangzhi
    IEEE ACCESS, 2021, 9 : 123977 - 123986
  • [46] Spatio-temporal prediction and reconstruction network for video anomaly detection
    Liu, Ting
    Zhang, Chengqing
    Niu, Xiaodong
    Wang, Liming
    PLOS ONE, 2022, 17 (05):
  • [47] Multi-scale Siamese prediction network for video anomaly detection
    Jingxian Yang
    Yiheng Cai
    Dan Liu
    Jin Xie
    Signal, Image and Video Processing, 2023, 17 : 671 - 678
  • [48] Video Event Restoration Based on Keyframes for Video Anomaly Detection
    Yang, Zhiwei
    Liu, Jing
    Wu, Zhaoyang
    Wu, Peng
    Liu, Xiaotao
    2023 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2023, : 14592 - 14601
  • [49] Overlooked Video Classification in Weakly Supervised Video Anomaly Detection
    Tan, Weijun
    Yao, Qi
    Liu, Jingfeng
    2024 IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION WORKSHOPS, WACVW 2024, 2024, : 212 - 220
  • [50] Video Anomaly Detection and Localization Based on an Adaptive Intra-Frame Classification Network
    Xu, Ke
    Sun, Tanfeng
    Jiang, Xinghao
    IEEE TRANSACTIONS ON MULTIMEDIA, 2020, 22 (02) : 394 - 406