Wavelet-based Texture Model for Crowd Dynamic Analysis

WANG, Jing, XU, Zhijie, CAO, Yanlong and YUANPING, Xu (2017). Wavelet-based Texture Model for Crowd Dynamic Analysis. In: 23rd International Conference on Automation & Computing, Huddersfield, 7-8 September 2017. (In Press)

[img]
Preview
PDF
PID4859177.pdf - Accepted Version
Available under License All rights reserved.

Download (918kB) | Preview

Abstract

Crowd event detection techniques aim at solving real-world surveillance problems, such as detecting crowd anomaly and tracking specific person in a highly dynamic crowd scene. In this paper, we proposed an innovate texture-based analysis method to model crowd dynamics and us it to distinguish the crowd behaviours. To describe complicated crowd scenes, homogeneous random features have been deployed in the research for behavioural template matching. Experiment results have shown that the anomaly appearing in crowd scenes can be effectively and efficiently identified by using the devised methods.

Item Type: Conference or Workshop Item (Paper)
Departments: Arts, Computing, Engineering and Sciences > Computing
Related URLs:
Depositing User: Jing Wang
Date Deposited: 31 Jul 2017 14:37
Last Modified: 31 Jul 2017 14:47
URI: http://shura.shu.ac.uk/id/eprint/15929

Actions (login required)

View Item View Item

Downloads

Downloads per month over past year

View more statistics