Histogram of Maximal Optical Flow Projection for Abnormal Events Detection in Crowded Scenes

Abnormal events detection plays an important role in the video surveillance, which is a challenging subject in the intelligent detection. In this paper, based on a novel motion feature descriptor, that is, the histogram of maximal optical flow projection (HMOFP), we propose an algorithm to detect ab...

Full description

Saved in:
Bibliographic Details
Main Authors: Ang Li, Zhenjiang Miao, Yigang Cen, Tian Wang, Viacheslav Voronin
Format: Article
Language:English
Published: Wiley 2015-11-01
Series:International Journal of Distributed Sensor Networks
Online Access:https://doi.org/10.1155/2015/406941
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850160301421363200
author Ang Li
Zhenjiang Miao
Yigang Cen
Tian Wang
Viacheslav Voronin
author_facet Ang Li
Zhenjiang Miao
Yigang Cen
Tian Wang
Viacheslav Voronin
author_sort Ang Li
collection DOAJ
description Abnormal events detection plays an important role in the video surveillance, which is a challenging subject in the intelligent detection. In this paper, based on a novel motion feature descriptor, that is, the histogram of maximal optical flow projection (HMOFP), we propose an algorithm to detect abnormal events in crowded scenes. Following the extraction of the HMOFP of the training frames, the one-class support vector machine (SVM) classification method is utilized to detect the abnormality of the testing frames. Compared with other methods based on the optical flow, experiments on several benchmark datasets show that our algorithm is effective with satisfying results.
format Article
id doaj-art-b6d4d818faf345f6907f76f00fe94d46
institution OA Journals
issn 1550-1477
language English
publishDate 2015-11-01
publisher Wiley
record_format Article
series International Journal of Distributed Sensor Networks
spelling doaj-art-b6d4d818faf345f6907f76f00fe94d462025-08-20T02:23:11ZengWileyInternational Journal of Distributed Sensor Networks1550-14772015-11-011110.1155/2015/406941406941Histogram of Maximal Optical Flow Projection for Abnormal Events Detection in Crowded ScenesAng Li0Zhenjiang Miao1Yigang Cen2Tian Wang3Viacheslav Voronin4 Institute of Information Science, Beijing Jiaotong University, Beijing 100044, China Institute of Information Science, Beijing Jiaotong University, Beijing 100044, China Institute of Information Science, Beijing Jiaotong University, Beijing 100044, China School of Automation Science and Electrical Engineering, Beihang University, Beijing 100191, China Department of Radio-Electronic Systems, Don State Technical University, Shakhty 346500, RussiaAbnormal events detection plays an important role in the video surveillance, which is a challenging subject in the intelligent detection. In this paper, based on a novel motion feature descriptor, that is, the histogram of maximal optical flow projection (HMOFP), we propose an algorithm to detect abnormal events in crowded scenes. Following the extraction of the HMOFP of the training frames, the one-class support vector machine (SVM) classification method is utilized to detect the abnormality of the testing frames. Compared with other methods based on the optical flow, experiments on several benchmark datasets show that our algorithm is effective with satisfying results.https://doi.org/10.1155/2015/406941
spellingShingle Ang Li
Zhenjiang Miao
Yigang Cen
Tian Wang
Viacheslav Voronin
Histogram of Maximal Optical Flow Projection for Abnormal Events Detection in Crowded Scenes
International Journal of Distributed Sensor Networks
title Histogram of Maximal Optical Flow Projection for Abnormal Events Detection in Crowded Scenes
title_full Histogram of Maximal Optical Flow Projection for Abnormal Events Detection in Crowded Scenes
title_fullStr Histogram of Maximal Optical Flow Projection for Abnormal Events Detection in Crowded Scenes
title_full_unstemmed Histogram of Maximal Optical Flow Projection for Abnormal Events Detection in Crowded Scenes
title_short Histogram of Maximal Optical Flow Projection for Abnormal Events Detection in Crowded Scenes
title_sort histogram of maximal optical flow projection for abnormal events detection in crowded scenes
url https://doi.org/10.1155/2015/406941
work_keys_str_mv AT angli histogramofmaximalopticalflowprojectionforabnormaleventsdetectionincrowdedscenes
AT zhenjiangmiao histogramofmaximalopticalflowprojectionforabnormaleventsdetectionincrowdedscenes
AT yigangcen histogramofmaximalopticalflowprojectionforabnormaleventsdetectionincrowdedscenes
AT tianwang histogramofmaximalopticalflowprojectionforabnormaleventsdetectionincrowdedscenes
AT viacheslavvoronin histogramofmaximalopticalflowprojectionforabnormaleventsdetectionincrowdedscenes