Histograms of Optical Flow Orientation for Visual Abnormal Events Detection - Université de technologie de Troyes Access content directly
Conference Papers Year : 2012

Histograms of Optical Flow Orientation for Visual Abnormal Events Detection

Abstract

In this paper, we propose an algorithm to detect abnormal events based on video streams. The algorithm is based on histograms of the orientation of optical flow descriptor and one-class SVM classifier. We introduce grids of Histograms of the Orientation of Optical Flow (HOFs) as the descriptors for motion information of the monolithic video frame. The one-class SVM, after a learning period characterizing normal behaviors, detects the abnormal events in the current frame. Extensive testing on benchmark dataset corroborates the effectiveness of the proposed detection method.
No file

Dates and versions

hal-02319094 , version 1 (17-10-2019)

Identifiers

Cite

Tian Wang, Hichem Snoussi. Histograms of Optical Flow Orientation for Visual Abnormal Events Detection. 2012 9th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS), Sep 2012, Beijing, China. pp.13-18, ⟨10.1109/AVSS.2012.39⟩. ⟨hal-02319094⟩
18 View
0 Download

Altmetric

Share

Gmail Mastodon Facebook X LinkedIn More