YCbCr颜色模式下基于L-M算法优化的火焰识别方法  

Fire Recognition Algorithm Based on L-M in YCbCr Color Space

作　　者：韩殿元[1] 

机构地区：[1]潍坊学院计算机与通信工程学院,潍坊261061

出　　处：《计算机科学》2010年第8期287-289,共3页Computer Science

基　　金：山东省高等学校优秀青年教师国内访问学者项目经费资助

摘　　要：传统火灾探测技术存在许多缺陷。提出了一种基于图像的火焰识别方法。首先将图像由RGB模式转换为YCbCr模式,以Cb,Cr为轴建立坐标系并绘出火焰样本的Cb,Cr值。用一个椭圆将绘出的坐标点包括起来,并创建椭圆方程和二维正态分布函数,使正态分布函数在椭圆外部的值为零,并用L-M算法对正态分布函数中的参数进行优化。对火焰的识别转换为判断正态分布函数在像素对应的Cb,Cr处的值是否大于零。该方法具有很好的实时性和识别效果。As conventional fire detection technology has many limitations, this paper proposed a fire recognition method based on image. Firstly, the image color space was transformed from RGB to YCbCr and a coordinate system was set up then the Cb and Cr values of the fire sample pixels were depicted. Secondly, an ellipse was drawn up to ring up the most of the points so as to create an elliptic equation and a two-dimensional normal distribution function which value out of the ellipse was zero. Lastly L-M algorithm was used to optimize the parameters of normal distribution function. So the recognition of the fire was converted to judge if the normal distribution function value of a given couple of Cb and Cr is greater than zero. The method of this paper has good real-time and recognition performance.

关 键 词：火焰识别 YCbCr颜色模式 正态分布 L-M算法 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]