基于Contourlet变换的多波段SAR图像融合  

Fusion Algorithm for Multiband SAR Images Based on Contourlet Transform

作　　者：郑永安[1] 宋建社[1] 周文明[1] 张杰[1] 

机构地区：[1]第二炮兵工程学院,西安710025

出　　处：《计算机工程》2007年第18期34-36,58,共4页Computer Engineering

基　　金：国家自然科学基金资助项目(60272022)

摘　　要：针对不同波段SAR图像的融合,该文提出了一种在Contourlet变换域融合的方法,利用Contourlet变换的充分表示图像边缘信息的能力,将图像分解为低通系数和不同方向的高频系数,对方向高频系数定义一个边缘信息量测指标,选择量测指标大的系数作为融合系数,解决了小波变换融合中图像边缘信息容易丢失的问题。通过对两波段SAR图像进行融合实验并与小波变换融合结果比较,在视觉特性与统计因子客观评价上均取得了更好的效果。The fusion of multiband SAR（synthetic aperture radar）images is an important application of SAR system.This paper presents a new fusion algorithm in the Contourlet transform domain.Compared with the wavelet transform,the Contourlet transform not only can capture the multiresolution and local information of an image,but also obtain its directional information in a flexible way by using different number of directions at different scales.The multiband SAR images are decomposed into different low-frequency coefficients and directional high-frequency coefficients.An edge information measurement is designed to select the fused directional high-frequency coefficients and weighted averaging method is employed for obtaining the fused low-frequency coefficients.Experiments show that the proposed algorithm works better in preserving the edge and texture information than the wavelet transform method do in image fusion.

关 键 词：CONTOURLET变换 图像融合 多波段 合成孔径雷达图像 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]