首页  科学研究  学术论文  2010年
 
Chen J, He YP, Wang J (2010) Building and Environment 45(5), 1113-1122.
文章来源:WOS    作者:SKLFS    发布时间:2011-08-15
Chen J, He YP, Wang J (2010) Multi-feature fusion based fast video flame detection. Building and Environment 45(5), 1113-1122. [In English]

Web link: http://dx.doi.org/10.1016/j.buildenv.2009.10.017

Keywords:

Motion detection; Gaussian mixture model; Color mapping; Flickering; analysis; real-time tracking; fire-detection; system; image; model

Abstract: A video flame detection method based on the multi-feature fusion is presented in this paper. The temporal and spatial characteristics of flames, such as ordinary flame movement and color clues a flame, flickering detection algorithm is incorporated into the scheme to detect fires in color video sequences. An improved Gaussian mixture model method is firstly adopted to extract moving foreground objects from the still background of detection scenes; secondly, detected moving objects are then categorized into candidate and non-candidate flame regions by using a flame color filtering algorithm; finally, a flame flicker identification algorithm based on statistical frequency counting is used to distinguish true flames from fire-like objects in video images. Testing results show that the proposed algorithms are effective, robust and efficient. The processing rate of the flame detection method can achieve 24 fps with image size of 320 x 240 pixels on a PC with an AMD 2.04 GHz processor. (C) 2009 Elsevier Ltd. All rights reserved.

 
 
相关链接
Chen J, He YP, Wang J (2010) Building and Environment 45(5), 1113-1122.
联系我们
安徽省合肥市金寨路96号
中国科学技术大学
火灾科学国家重点实验室
邮政编码:230026
   
Tel:(+86)551 63601651
Fax:(+86)551 63601669
E-mail:sklfs@ustc.edu.cn
Copyright © 1990-2011 State Key Laboratory of Fire Science, University of Science and Technology of China
火灾科学国家重点实验室 版权所有 皖ICP备:002106505 号