基于小波融合的双色空间火焰分割方法

Two-color Space Flame Segmentation Method Based on Wavelet Fusion

目前火焰分割方法主要局限于灰度图像分割和单彩色空间分割,这两种方法对光照变化都非常敏感。文中依据可见光呈现的图像目标特性不同,提出了基于小波融合的HSI和RGB双彩色空间的火焰分割方法。利用火焰图像在HSI空间特性对火焰进行分割;利用火焰在RGB空间特性对火焰进行分割;使用小波方法对HSI和RGB空间单独分割后的图像进行融合。仿真试验对比结果表明,该方法相比于传统的单色空间分割方法,充分利用了各原图信息的互补,提高了分割的精度。

At present,flame segmentation methods are mainly limited to grayscale image segmentation and single-color space segmentation,which are generally very sensitive to light changes. In this paper,according to the different characteristics of visible images,a method of flame segmentation based on wavelet fusion in HSI and RGB dual color space is proposed. Flames are segmented using the spatial characteristics of flame images in HSI. Flames are segmented by using the spatial characteristics of flame in RGB. Wavelet method is used to fuse the separately segmented images in HSI and RGB space. The simulation results show that compared with the traditional monochrome space segmentation method,this method makes full use of the complementary information of each original image and improves the segmentation accuracy.