方向非抽样小波变换在多传感器图像融合中的应用  

The application of directional undecimated wavelet transform in multi_sensor image fusion

作　　者：李其申[1] 李俊峰[1] 赵喜玲[1] 江泽涛[1] 

机构地区：[1]南昌航空大学,江西南昌330063

出　　处：《南昌航空大学学报（自然科学版）》2008年第2期76-81,共6页Journal of Nanchang Hangkong University(Natural Sciences)

基　　金：国家自然科学基金项目(60673055)

摘　　要：本文分析和研究非下采样方向滤波器组及具有平移不变性的非抽样小波变换的优点,提出了基于方向非抽样小波变换的图像融合方法。首先利用非抽样小波变换将待融合源图像分解成不同尺度,不同分辨率的高低频分量,再对高频分量利用非下采样方向滤波器组进行方向分解,然后采取不同的融合方法对分解的高低频分量进行融合处理,最后将融合的各频带进行相应逆变换得到融合图像。实验表明,在不同评价标准下,本文方法优于传统小波变换和拉普拉斯金字塔变换的融合效果,并能有效地消除小波变换所带来的光谱扭曲和假边缘现象。The construction of Nonsubsampled Directional Filter Bank （NSDFB） and undecimated wavelet transform which is full shift invariant are introduced, and a novel multi -sensor image fusion scheme based on NSDFB combining undecimated wavelet transform for multi sensor images is proposed. Each source image is decomposed in highpass subbands and lowpass subbands by undecimated wavelet transform, and the highpass subbands are decomposed in multi -directional high pass -bands respectively by NSDFB. Then different fusion rules are used in different subbands, and the fused image is reconstructed by taking inverse NSDFB transform and inverse undecimated wavelet transform. The experimental results show that the performance of the novel algorithm is better than the traditional fusion algorithms based on wavelet transformation and Laplacian pyramid decomposed, and especially, the novel fusion algorithm could effectively eliminate the spectrum warping and the artificial edges caused by wavelet transform.

关 键 词：图像融合 非下采样方向滤波器组 非抽样小波变换 平移不变性 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]