森林火灾早期预警的多光谱检测技术  

Early Warning of Forest Fire Based on Multispectral Detection

作　　者：崔金刚[1] 马翔宇[1] 李景奎[1] 

机构地区：[1]东北林业大学,哈尔滨150040

出　　处：《东北林业大学学报》2009年第7期128-129,共2页Journal of Northeast Forestry University

基　　金：东北林业大学青年科研基金项目(09026)资助

摘　　要：传统的红外检测方法难以区分森林火灾初期起火点的红外图像,不利于火灾初始控制,为此对利用多光谱图像探测林火的滤波算法进行了研究。首先采用主成分分析法进行森林背景及干扰信息提取,再根据最小二乘准则,得到适当的权值向量,对多谱图像序列进行处理。理论分析表明,该方法可以有效地探测起火点等红外小目标。计算机模拟结果表明,该方法是实时而有效的。The traditional algorithm of feeble signal detecting can not be used to differentiate the infrared small targets of the fire point, so the fire disaster can not be controlled at the primary stage. In this paper, a new algorithm of multispectral data is used to detect the multiband infrared imagery by the principle components method, and the multispectral imagery was processed with a weight vector obtained by herative least-squares （ILS） algorithm. Theoretical analysis shows that the new algorithm can effectively detect the infrared small target of forest fire. Computer simulation results demonstrate that the proposed algorithm is quick and efficient.

关 键 词：森林火灾 红外图像 检测 多光谱图像 

分 类 号：S762.2[农业科学—森林保护学] O434.3[农业科学—林学]