Share Email Print
cover

Proceedings Paper • new

A new method for violence detection based on the three dimensional scene flow
Author(s): Wu Wang; Yunfei Cheng; Yuexia Liu
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

Violence detection from surveillance video is a challenging and attractive task. This paper introduce a new violence detection using binocular stereo vision. We use the sparse stereo matching method to extract the feature points of both rectified images and obtain the vision disparity of the point. The 3D coordinates of the points are calculated through the standard 3D measurement theory. To describe the spatio-temporal property, we extract features aligned with the trajectories to characterize depth information (Three-dimensional motion vector), appearance (histograms of oriented gradients) and motion (histograms of optical flow). In order to obtain the discriminative feature, this paper adopts sparse coding scheme and support vector machine (SVM) to classify the feature vector as normal or abnormal.

Paper Details

Date Published: 12 December 2018
PDF: 6 pages
Proc. SPIE 10845, Three-Dimensional Image Acquisition and Display Technology and Applications, 108450N (12 December 2018); doi: 10.1117/12.2505418
Show Author Affiliations
Wu Wang, The Third Research Institute of The Ministry of Public Security (China)
Yunfei Cheng, The Third Research Institute of The Ministry of Public Security (China)
Yuexia Liu, The Third Research Institute of The Ministry of Public Security (China)


Published in SPIE Proceedings Vol. 10845:
Three-Dimensional Image Acquisition and Display Technology and Applications
Byoungho Lee; Yongtian Wang; Liangcai Cao; Guohai Situ, Editor(s)

© SPIE. Terms of Use
Back to Top