Detection of Abnormal Events via Optical Flow Feature Analysis
In this paper, a novel algorithm is proposed to detect abnormal events in video streams. The algorithm is based on the histogram of the optical flow orientation descriptor and the classification method. The details of the histogram of the optical flow orientation descriptor are illustrated for descr...
Main Authors: | , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2015-03-01
|
Series: | Sensors |
Subjects: | |
Online Access: | http://www.mdpi.com/1424-8220/15/4/7156 |
_version_ | 1811185072208871424 |
---|---|
author | Tian Wang Hichem Snoussi |
author_facet | Tian Wang Hichem Snoussi |
author_sort | Tian Wang |
collection | DOAJ |
description | In this paper, a novel algorithm is proposed to detect abnormal events in video streams. The algorithm is based on the histogram of the optical flow orientation descriptor and the classification method. The details of the histogram of the optical flow orientation descriptor are illustrated for describing movement information of the global video frame or foreground frame. By combining one-class support vector machine and kernel principal component analysis methods, the abnormal events in the current frame can be detected after a learning period characterizing normal behaviors. The difference abnormal detection results are analyzed and explained. The proposed detection method is tested on benchmark datasets, then the experimental results show the effectiveness of the algorithm. |
first_indexed | 2024-04-11T13:24:30Z |
format | Article |
id | doaj.art-441944b266224249af433054fe6c34b8 |
institution | Directory Open Access Journal |
issn | 1424-8220 |
language | English |
last_indexed | 2024-04-11T13:24:30Z |
publishDate | 2015-03-01 |
publisher | MDPI AG |
record_format | Article |
series | Sensors |
spelling | doaj.art-441944b266224249af433054fe6c34b82022-12-22T04:22:07ZengMDPI AGSensors1424-82202015-03-011547156717110.3390/s150407156s150407156Detection of Abnormal Events via Optical Flow Feature AnalysisTian Wang0Hichem Snoussi1School of Automation Science and Electrical Engineering, Beihang University, Beijing 100191, ChinaInstitut Charles Delaunay-LM2S-UMR STMR 6279 CNRS, University of Technology of Troyes, Troyes 10004, FranceIn this paper, a novel algorithm is proposed to detect abnormal events in video streams. The algorithm is based on the histogram of the optical flow orientation descriptor and the classification method. The details of the histogram of the optical flow orientation descriptor are illustrated for describing movement information of the global video frame or foreground frame. By combining one-class support vector machine and kernel principal component analysis methods, the abnormal events in the current frame can be detected after a learning period characterizing normal behaviors. The difference abnormal detection results are analyzed and explained. The proposed detection method is tested on benchmark datasets, then the experimental results show the effectiveness of the algorithm.http://www.mdpi.com/1424-8220/15/4/7156abnormal detectionoptical flowone-class SVMKPCA |
spellingShingle | Tian Wang Hichem Snoussi Detection of Abnormal Events via Optical Flow Feature Analysis Sensors abnormal detection optical flow one-class SVM KPCA |
title | Detection of Abnormal Events via Optical Flow Feature Analysis |
title_full | Detection of Abnormal Events via Optical Flow Feature Analysis |
title_fullStr | Detection of Abnormal Events via Optical Flow Feature Analysis |
title_full_unstemmed | Detection of Abnormal Events via Optical Flow Feature Analysis |
title_short | Detection of Abnormal Events via Optical Flow Feature Analysis |
title_sort | detection of abnormal events via optical flow feature analysis |
topic | abnormal detection optical flow one-class SVM KPCA |
url | http://www.mdpi.com/1424-8220/15/4/7156 |
work_keys_str_mv | AT tianwang detectionofabnormaleventsviaopticalflowfeatureanalysis AT hichemsnoussi detectionofabnormaleventsviaopticalflowfeatureanalysis |