OS20-1 An effective method for detecting snatch thieves in video surveillance

Title:	OS20-1 An effective method for detecting snatch thieves in video surveillance
Publication:	ICAROB2017
Volume:	22
Pages:	303-306
ISSN:	2188-7829
DOI:	10.5954/ICAROB.2017.OS20-1
Author(s):	Hiroaki Tsushita, Thi Thi Zin
Publication Date:	January 19, 2017
Keywords:	snatching, detecting, intersection, feature extraction,
Abstract:	Nowadays, a tremendous amount of accidents and terrorisms has been occurred all over the world no exception in Japan. Thus, detection of suspicious activities in public areas such as railway stations, shopping malls and many other areas using video surveillance becomes important. However, very little has been achieved regarding real-time event recognition of two person interactions such as snatch theft events. Moreover the way of snatch theft has been increasing like using a motorcycle and so on. In this paper, we propose an effective method for detecting the snatch theft event between two persons. Specifically, the proposed method consists of several steps: pedestrian tracking, feature computation and snatch theft detection. For feature computation, shape and motion features are used. To confirm the validity of proposed method some experimental results in a various situations are shown by using some collected video sequences.
PDF File:	https://alife-robotics.co.jp/members2017/icarob/data/html/data/OS_pdf/OS20/OS20-1.pdf
Copyright:	© The authors. This article is distributed under the terms of the Creative Commons Attribution License 4.0, which permits non-commercial use, distribution and reproduction in any medium, provided the original work is properly cited. See for details: https://creativecommons.org/licenses/by-nc/4.0/

HOME