复杂背景的红外图像过渡区提取与分割  

Transition Region Extraction and Segmentation of Infrared Image on Complex Background

作　　者：李洪周[1] 袁胜智[1] 陈榕[1] 高义侠[2] 

机构地区：[1]海军航空工程学院,山东烟台264001 [2]中国海洋大学计算机科学系,山东青岛266100

出　　处：《激光与红外》2009年第2期217-219,共3页Laser & Infrared

摘　　要：在基于个数判断噪声的中值滤波器进行平滑处理的基础上,提出了一种改进的过渡区提取方法,并将该方法应用于对比度低、宽谷直方图的复杂背景红外图像的分割。Matlab仿真实验表明,该方法减少了图像分割的运算量,并能将具有复杂背景的红外图像目标分割得较好。A median filter based on estimation of noise is designed for smoothing processing, and put forward an improved transition region extraction method. Finally, this method is used to deal with segmentation problems for those infrared images whose peak values of histogram have great difference. Matlab simulation experiments showed that the proposed method can decrease the time of calculation and provide satisfactory segmentation for those infrared images on complex background.

关 键 词：过渡区 红外图像 直方图 图像分割 

分 类 号：V271.4[航空宇航科学与技术—飞行器设计] TP317.4[自动化与计算机技术—计算机软件与理论]