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
  • [21] A Survey of Single-Scene Video Anomaly Detection
    Ramachandra, Bharathkumar
    Jones, Michael J.
    Vatsavai, Ranga Raju
    IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2022, 44 (05) : 2293 - 2312
  • [22] An Intra-frame Classification Network for Video Anomaly Detection and Localization
    Xu, Ke
    Jiang, Xinghao
    Sun, Tanfeng
    2018 11TH INTERNATIONAL CONGRESS ON IMAGE AND SIGNAL PROCESSING, BIOMEDICAL ENGINEERING AND INFORMATICS (CISP-BMEI 2018), 2018,
  • [23] Attention-guided residual frame learning for video anomaly detection
    Jun-Hyung Yu
    Jeong-Hyeon Moon
    Kyung-Ah Sohn
    Multimedia Tools and Applications, 2023, 82 : 12099 - 12116
  • [24] Attention-guided residual frame learning for video anomaly detection
    Yu, Jun-Hyung
    Moon, Jeong-Hyeon
    Sohn, Kyung-Ah
    MULTIMEDIA TOOLS AND APPLICATIONS, 2023, 82 (08) : 12099 - 12116
  • [25] Bi-directional Frame Interpolation for Unsupervised Video Anomaly Detection
    Deng, Hanqiu
    Zhang, Zhaoxiang
    Zou, Shihao
    Li, Xingyu
    2023 IEEE/CVF WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION (WACV), 2023, : 2633 - 2642
  • [26] Drone Video Anomaly Detection by Future Segmentation Prediction and Spatio- Temporal Relational Modeling
    Fakhry, Ahmed
    Lee, Janghoon
    Lee, Jong Taek
    IEEE ACCESS, 2025, 13 : 22395 - 22406
  • [27] Optimizing Video Prediction via Video Frame Interpolation
    Wu, Yue
    Wen, Qiang
    Chen, Qifeng
    2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2022), 2022, : 17793 - 17802
  • [28] A comparative study between single and multi-frame anomaly detection and localization in recorded video streams
    Bahrami, Maedeh
    Pourahmadi, Majid
    Vafaei, Abbas
    Shayesteh, Mohammad Reza
    JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION, 2021, 79
  • [29] VEHICLE DETECTION AND COUNTING FROM A VIDEO FRAME
    Pornpanomchai, Chomtip
    Liamsanguan, Thitinut
    Vannakosit, Vissakorn
    PROCEEDINGS OF 2008 INTERNATIONAL CONFERENCE ON WAVELET ANALYSIS AND PATTERN RECOGNITION, VOLS 1 AND 2, 2008, : 356 - 361
  • [30] Future Frame Prediction Using Convolutional VRNN for Anomaly Detection
    Lu, Yiwei
    Kumar K, Mahesh
    Nabavi, Seyed shahabeddin
    Wang, Yang
    2019 16TH IEEE INTERNATIONAL CONFERENCE ON ADVANCED VIDEO AND SIGNAL BASED SURVEILLANCE (AVSS), 2019,