.png){kind=icon}
.png){kind=icon}
Return
Violence detection using Oriented VIolent Flows
.png){kind=icon}
PRE
AI
DOI：10.1016/j.imavis.2016.01.006.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Nowadays, with so many surveillance cameras having been installed, the market demand for intelligent violence detection is continuously growing, while it is still a challenging topic in research area. Therefore, we attempt to make some improvements of existing violence detectors. The primary contributions of this paper are two-fold. Firstly, a novel feature extraction method named Oriented VIolent Flows (OViF), which takes full advantage of the motion magnitude change information in statistical motion orientations, is proposed for practical violence detection in videos. The comparison of OViF and baseline approaches on two public databases demonstrates the efficiency of the proposed method. Secondly, feature combination and multi classifier combination strategies are adopted and excellent results are obtained. Experimental results show that using combined features with AdaBoost+Linear-SVM achieves improved performance over the state-of-the-art on the Violent-Flows benchmark. (C) 2016 Elsevier B.V. All rights reserved.
Keywords:
Violence detection
Oriented VIolent Flows
AdaBoost
SVM
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.