[1]陈智铭,谢维波,许华滨.利用图像频度特征的稀薄烟雾检测算法[J].华侨大学学报(自然科学版),2014,35(2):151-155.[doi:10.11830/ISSN.1000-5013.2014.02.0151]
　CHEN Zhi-ming,XIE Wei-bo,XU Hua-bin.Thin and Slow Smoke Detection Based on Frequency Image[J].Journal of Huaqiao University(Natural Science),2014,35(2):151-155.[doi:10.11830/ISSN.1000-5013.2014.02.0151]
点击复制

利用图像频度特征的稀薄烟雾检测算法()
分享到：

《华侨大学学报（自然科学版）》[ISSN:1000-5013/CN:35-1079/N]

卷:
第35卷
期数:
2014年第2期
页码:
151-155
栏目:
出版日期:
2014-03-20

文章信息/Info

Title:
Thin and Slow Smoke Detection Based on Frequency Image
文章编号:
1000-5013(2014)02-0151-05
作者:
陈智铭1; 2;  谢维波1; 2;  许华滨1; 2
1. 华侨大学 计算机科学与技术学院, 福建 厦门 361021;2. 华侨大学 厦门软件园嵌入式技术开放实验室, 福建 厦门 361008
Author(s):
CHEN Zhi-ming;  XIE Wei-bo;  XU Hua-bin
1. College of Computer Science and Technology, Huaqiao University, Xiamen 361021, China; 2. Open Laboratory of Embedded Technology of Xiamen Software Park, Huaqiao University, Xiamen 361008, China
关键词:
烟雾检测;  彩色直方图;  频度图像;  灰度图像;  相关系数
Keywords:
smoke detection;  color histogram;  frequency image;  gray image;  correlation coefficient
分类号:
TP391
DOI:
10.11830/ISSN.1000-5013.2014.02.0151
文献标志码:
A
摘要:
基于图像的频度特征,不考虑薄烟自身的颜色,通过比较烟不存在时的图像(基准图)和实时视频当前帧的灰度值的相关系数的变化,以及基准图和当前帧频度值的相关系数的变化,实现稀薄烟雾“透明性”特征的有效识别.把非常稀薄的烟雾实时的检测出来.实际烟雾视频数据分析结果表明:该算法是实用有效的,能够在火灾初期阶段把薄烟检测出来,且具有鲁棒性.
Abstract:
It presents a method which is without considering the color of smoke and base on the image frequency characteristics for detecting thin smoke. By calculating the correlation coefficient of the frequency image and the gray image between current stage and the initial stage, and making a comparison so that the recognition of thin smoke transparent characteristics can be realized efficiently. The actual results of the smoke video data analysis show that this method is practical. It also has the ability to detect the smoke in the early fire stage, and equips robustness.

参考文献/References:

[1] NODA S,UEDA K.Fire detection in tunnels using an image processing method[C]//IEEE Processing of Vehicle Navigation Information Systems Conference.Yokohama:IEEE Press, 1994: 57-62.
[2] YAMAGISHI H, YAMAGUCHI J. Fire flame detection algorithm using a color camera[C]//Micromechatronics and Human Science.Nagoya:IEEE Press,1999:255-260.
[3] YAMAGISHI H, YAMAGUCHI J. A contour fluctuation data processing method for fire flame detection using a color camera[C]//26th Annual Conference of the IEEE Industrial Electronics Society.Nagoya:IEEE Press,2000: 824-829.
[4] 袁非牛,廖光煊,张永明,等.计算机视觉火灾探测中的特征提取[J].中国科学技术大学学报,2006,36(1):39-43.
[5] ZHENG G,OE S. Thin and slow smoke detection by using frequency image[J].IEEE Transactions on Electronics, Information and Systems,2010,130(7):1168-1176.
[6] TOREYIN B U,DEDEOGLU Y,Cetin A E.Wavelet based real-time smoke detection in video[C]//European Signal Processing Conference.Istanbul:[s.n.],2005:4-8.
[7] 邓彬,刘辉,连国云,等.基于视频的烟雾检测[J].长沙大学学报,2007,21(5):87-89.
[8] KASHIWAGI T,OE S.Introduction of frequency image and applications[C]//Annual Conference of SICE.Takamatsu:IEEE Press,2007:584-591.
[9] KASHIWAGI T,OE S.Theory and applications of frequency image of color vectors[C]//Proceedings of SPIE, Image Processing: Machine Vision Applications Ⅱ,2009:72510H(doi:10.1117/12.805429).
[10] CHAN C N,OE S.Active eye-tracking system using frequency image processing method[J].The Journal of the Institute of Image Electronics Engineers of Japan,2010,39(2):185-194.

备注/Memo

备注/Memo:
收稿日期: 2013-02-28
通信作者: 谢维波(1964-),男,教授,主要从事嵌入式技术、数字信号处理的研究.E-mail::xwblxf@hqu.edu.cn.
基金项目: 福建省自然科学基金资助项目(2010J01334); 华侨大学高层次人才科研启动项目(11BS120)
更新日期/Last Update: 2014-03-20