QQ客服 官方微博 反馈留言

浏览/检索结果: 共1条，第1-1条 帮助 限定条件 内容类型：会议论文     已选(0)清除 条数/页：5101520253035404550556065707580859095100   排序方式：请选择作者升序作者降序题名升序题名降序发表日期升序发表日期降序提交时间升序提交时间降序 Approach for detecting crowd panic behavior based on fluid kinematic features and entropy (EI CONFERENCE) 会议论文 International Workshop on Advanced Computational Intelligence and Intelligent Informatics, IWACIII 2011, November 19, 2011 - November 23, 2011, Suzhou, China Cao S.; Zhang X.; Cao W.; Liu C.; Li Y.; Li P. C. 收藏  |  浏览/下载：21/0  |  提交时间：2013/03/25 Crowd panic behavior detection is an important task in video analysis and event recognition  whose purpose is to detect when the panic behavior happened and alarming the abnormal event timely. In this paper  the crowd is regard as a fluid  and the crowd motion is described by four fluid kinematic features (divergence  vorticity  gradient tensor invariant and rotation tensor invariant). To discriminate the panic event from normal crowd behavior  an information entropy is calculated as a high level feature based on the fluid kinematic features. Experimental results show that the entropy raised dramatically once a panic event happened.