Abstract:Smoke detection is very important for preventing forest-fire in the fire early process. Because the traditional technologies based on video and image processing are easily affected by the background dynamic information, three limitations exist in these technologies, i.e. lower anti-interference ability, higher false detection rate and the fire smoke and water fog being not easily distinguished. A novel detection method for detecting smoke based on the multispectral image was proposed in the present paper. Using the multispectral digital imaging technique, the multispectral image series of fire smoke and water fog were obtained in the band scope of 400 to 720 nm, and the images were divided into bins. The Euclidian distance among the bins was taken as a measurement for showing the difference of spectrogram. After obtaining the spectral feature vectors of dynamic region, the regions of fire smoke and water fog were extracted according to the spectrogram feature difference between target and background. The indoor and outdoor experiments show that the smoke detection method based on multispectral image can be applied to the smoke detection, which can effectively distinguish the fire smoke and water fog. Combined with video image processing method, the multispectral image detection method can also be applied to the forest fire surveillance, reducing the false alarm rate in forest fire detection.
卫颖卓,张绍武*,刘彦伟. 基于多光谱图像的烟雾检测[J]. 光谱学与光谱分析, 2010, 30(04): 1061-1064.
WEI Ying-zhuo, ZHANG Shao-wu*, LIU Yan-wei. Detecting Fire Smoke Based on the Multispectral Image. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2010, 30(04): 1061-1064.
[1] WANG Xi-shi, WU Xiao-ping, QIN Jun, et al(王喜世,伍小平,秦 俊,等). Laser & Infrared(激光与红外), 2001, 31(3): 169. [2] Phillips III W, Shah M, Lobo N V. Pattern Recognition Letters, 2002, 23(1-3): 319. [3] Vicente J,Guillemant P. International Journal of Thermal Sciences, 2002, 41: 113. [4] Celik T, Demirel H, Ozkaramanli H, et al. Journal of Visual Communication and Image Representation, 2007, 18: 176. [5] SHUAI Shi, ZHOU Ping, WANG Ya-ming, et al(帅 师, 周 平, 汪亚明, 等). Application Research of Computers(计算机应用研究), 2007, 24(3): 309. [6] YUAN Fei-niu, ZHANG Yong-ming, LIU Shi-xing, et al(袁非牛, 张永明, 刘士兴, 等). Joumal of Image and Graphics(中国图象图形学报), 2008, 13(4): 1006. [7] PU Rui-liang, GONG Peng(浦瑞良,宫 鹏). Hyperspectral Remot Sensing and Its Applications(高光谱遥感及其应用). Beijing: Higher Education Press(北京:高等教育出版社),2000. [8] QIAN Le-xiang, PAN Xue-qin, ZHAO Qian(钱乐祥,泮学芹,赵 芊). Remote Sensing for Land & Resources(国土资源遥感),2004,(2):1. [9] CHEN Xiao-jing, WU Di, HE Yong, et al(陈孝敬,吴 迪,何 勇,等). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2009,29(1): 222.