Abnormal event detection in crowded scenes using one-class SVM

被引:49
|
作者
Amraee, Somaieh [1 ]
Vafaei, Abbas [1 ]
Jamshidi, Kamal [1 ]
Adibi, Peyman [1 ]
机构
[1] Univ Isfahan, Fac Comp Engn, Esfahan, Iran
关键词
Anomaly detection; Crowded scenes; One-class SVM; Optical flow; ANOMALY DETECTION; HISTOGRAMS; FLOW;
D O I
10.1007/s11760-018-1267-z
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
In this paper, a new method for detecting abnormal events in public surveillance systems is proposed. In the first step of the proposed method, candidate regions are extracted, and the redundant information is eliminated. To describe appearance and motion of the extracted regions, HOG-LBP and HOF are calculated for each region. Finally, abnormal events are detected using two distinct one-class SVM models. To achieve more accurate anomaly localization, the large regions are divided into non-overlapping cells, and the abnormality of each cell is examined separately. Experimental results show that the proposed method outperforms existing methods based on the UCSD anomaly detection video datasets.
引用
收藏
页码:1115 / 1123
页数:9
相关论文
共 50 条
  • [1] Abnormal event detection in crowded scenes using one-class SVM
    Somaieh Amraee
    Abbas Vafaei
    Kamal Jamshidi
    Peyman Adibi
    Signal, Image and Video Processing, 2018, 12 : 1115 - 1123
  • [2] Abnormal event detection in crowded scenes using sparse representation
    Cong, Yang
    Yuan, Junsong
    Liu, Ji
    PATTERN RECOGNITION, 2013, 46 (07) : 1851 - 1864
  • [3] Detection of Abnormal Segments in Finger Tapping Waveform using One-class SVM
    Sano, Yuko
    Yin, Ying
    Mizuguchi, Tomohiko
    Kandori, Akihiko
    2019 41ST ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY (EMBC), 2019, : 1378 - 1381
  • [4] Abnormal Event Detection in Crowded Video Scenes
    Gnanavel, V. K.
    Srinivasan, A.
    PROCEEDINGS OF THE 3RD INTERNATIONAL CONFERENCE ON FRONTIERS OF INTELLIGENT COMPUTING: THEORY AND APPLICATIONS (FICTA) 2014, VOL 2, 2015, 328 : 441 - 448
  • [5] Player detection using One-Class SVM
    Bai, Xuefeng
    Zhang, Tiejun
    Wang, Chuanjun
    Li, Qiong
    Niu, Xiamu
    FOURTH INTERNATIONAL CONFERENCE ON DIGITAL IMAGE PROCESSING (ICDIP 2012), 2012, 8334
  • [6] Abnormal event detection for video surveillance using deep one-class learning
    Jiayu Sun
    Jie Shao
    Chengkun He
    Multimedia Tools and Applications, 2019, 78 : 3633 - 3647
  • [7] Abnormal event detection for video surveillance using deep one-class learning
    Sun, Jiayu
    Shao, Jie
    He, Chengkun
    MULTIMEDIA TOOLS AND APPLICATIONS, 2019, 78 (03) : 3633 - 3647
  • [8] Deep Representation for Abnormal Event Detection in Crowded Scenes
    Feng, Yachuang
    Yuan, Yuan
    Lu, Xiaoqiang
    MM'16: PROCEEDINGS OF THE 2016 ACM MULTIMEDIA CONFERENCE, 2016, : 591 - 595
  • [9] Parallelizing Abnormal Event Detection in Crowded Scenes with GPU
    Yavari, Mohammadreza
    Li, Maozhen
    Li, Maozhen
    Li, Siguang
    Qi, Man
    2015 12TH INTERNATIONAL CONFERENCE ON FUZZY SYSTEMS AND KNOWLEDGE DISCOVERY (FSKD), 2015, : 274 - 277
  • [10] Abnormal event detection in crowded scenes using two sparse dictionaries with saliency
    Yu, Yaping
    Shen, Wei
    Huang, He
    Zhang, Zhijiang
    JOURNAL OF ELECTRONIC IMAGING, 2017, 26 (03)