计算机科学与探索 ›› 2012, Vol. 6 ›› Issue (4): 377-384.DOI: 10.3778/j.issn.1673-9418.2012.04.010

• 学术研究 • 上一篇    

自助银行服务中暴力异常事件检测

陈 龙,尹 彪   

  1. 重庆邮电大学 计算机取证研究所,重庆 400065
  • 出版日期:2012-04-01

Violent Abnormal Event Detection for Self-Service Banking

CHEN Long, YIN Biao   

  1. Institute of Computer Forensics, Chongqing University of Posts and Telecommunications, Chongqing 400065, China
  • Online:2012-04-01

摘要: 针对自助银行服务中出现的暴力事件,提出了一种基于目标空间位置关系和事件语义模板的检测方法。该方法对划定区域选用背景自适应更新的背景减法得到侧影图,并统计人体个数;采用粒子滤波和均值漂移相结合的机制,跟踪人体并计算相关距离;将侧影图与异常事件的语义模板,采用快速模板匹配方法及改进伪Zernike矩构建的一个7维形状向量实现相似匹配来判定是否出现异常事件。实验结果表明,事件检测准确性较高,能够较好地满足实际应用需求。

关键词: 事件检测, 事件语义模板, 空间位置关系, 改进伪Zernike矩(IPZM), 目标跟踪

Abstract: This paper presents a new method based on spatial relationship among objects and event semantics template to detect violent event in self-service banking. The method gets the silhouette by the background subtraction algorithm in which the background updates adaptively, and counts the number of the people in the video. Then, it tracks the people using particle filter and mean shift method, and computes the distance between the persons. The fast event semantics match template method and a shape description vector consisting of seven improved pseudo-
Zernike moments (IPZM) are combined to detect abnormal event. Experimental results show the method is effective for the practical application.

Key words: event detection, event semantics template, spatial relationship, improved pseudo-Zernike moments (IPZM), object tracking