Title :
Fire flame detection algorithm using a color camera
Author :
Yamagishi, Hideaki ; Yamaguchi, Jun´ichi
Author_Institution :
Eng. Inst., Sogo Keibi Hosho Co. Ltd., Tokyo, Japan
Abstract :
In fire detection using image processing, it is required that a system has enough robustness and elimination of an influence of a disturbance. The authors have developed a method which fire flame can be detected by calculating a space-time fluctuation data on a contour of the flame area extracted by a color information. In this paper, the fire flame detection algorithm using a color CCD camera is explained and the results of the experiment, which is performed to verify the effectiveness of our method, are demonstrated
Keywords :
CCD image sensors; fires; image colour analysis; neural nets; physics computing; Fourier transforms; RGB data; color CCD camera; disturbance; fire contour; fire flame detection algorithm; neural net; robustness; space-time fluctuation; time series; Cameras; Charge coupled devices; Charge-coupled image sensors; Data mining; Detection algorithms; Fires; Fluctuations; Image processing; Layout; Robustness;
Conference_Titel :
Micromechatronics and Human Science, 1999. MHS '99. Proceedings of 1999 International Symposium on
Conference_Location :
Nagoya
Print_ISBN :
0-7803-5790-6
DOI :
10.1109/MHS.1999.820014