遥感图像像素级融合方法的建模与分析  

Modeling and Analysis of the Pixel-Level Fusion Methods for Remote Sensing Images

作　　者：王攀峰[1] 杜云飞[1] 周海芳[1] 贾佳[1] 杨学军[1] 

机构地区：[1]并行与分布处理国家重点实验室,湖南长沙410073

出　　处：《计算机工程与科学》2007年第11期22-26,共5页Computer Engineering & Science

基　　金：国家自然科学基金资助项目(60621003;60603081)

摘　　要：遥感图像像素级融合方法众多,但缺乏统一的定义,使得各种方法的差异不明确,不利于有针对性的应用;各种方法的融合质量差异悬殊,缺乏选用合适融合方法的理论指导,往往只能根据操作者的经验进行判断。为此,本文首先对融合方法的一般处理过程进行建模,提出了基于融合过程中图像信息表示的遥感图像融合方法的形式化定义RSPF;然后,基于RSPF从理论上分析了现有融合方法的融合质量差异;最后,通过实验定量分析了各种典型融合方法的融合质量。结果表明,融合过程中图像信息的表示形式是影响融合质量的关键因素。There are many pixel-level fusion methods for remote sensing images, but the differences of those are ambiguous because of lacking a unique description,which makes it difficult to apply image fusion purposefully. On the other hand, the qualities of those fusion methods depend on the operators＇ experience as a result of lacking the theory of methods selection. Pointing to this status, the general process of image fusion is modeled at first, and the remote sensing image fusion methods are defined formally. Then the difference of the fusion quality of the existing methods is analyzed theoretically. Finally qualities of some classic fusion methods are quantified through experiments. Conclusions indicate that the representation of information during the fusion process is the key to fusion quality.

关 键 词：遥感图像 建模 像素级融合 融合质量 IKONOS图像 

分 类 号：TP751[自动化与计算机技术—检测技术与自动化装置]