多源遥感影像数据融合的理论与技术  

The theory and techniques for data fusion of multi-sources remotely sensed imagery

作　　者：韩玲[1] 吴汉宁[1] 

机构地区：[1]西北大学地质学系

出　　处：《西北大学学报（自然科学版）》2004年第4期457-460,共4页Journal of Northwest University（Natural Science Edition）

基　　金：国家"973"基金资助项目(2003cb214600);国家自然科学基金资助项目(40374020)

摘　　要：目的　探讨多源遥感影像数据融合技术,包括融合概念、融合原理、融合算法、融合效果评价。方法　对于不同空间分辨率、时间分辨率和波谱分辨率的遥感图像进行综合分析,提出像素级、特征级、决策级遥感影像融合的方法及用信息论的理论建立融合影像评价系统。结果　信息融合可分为3个层次:像素级、特征级和决策级融合;像素级融合信息损失最小,决策级融合信息损失最大;像素级融合精度最高,决策级融合精度最低。结论　对同一地区的多源遥感影像数据进行融合,可以产生比单一信息源更准确、更完全、更可靠的估计和判断,可以提高影像的空间分辨率和清晰度,有效提高遥感影像数据的利用率等。Aim Exploring the techniques of the efficient integration of remote sensing images with multiple spatial, temporal and spectrum resolution.The techniques for data fusion in multi-sources remotely sensed imagery are reviewed including the concept of fusion,the algorithms of fusion and the evaluate of fusion effects.Methods Analyzing the remotely sensed imagery for multiple spatial, temporal and spectrum resolution giving three method for data fusion is pixel-based, featuee-based and decision-based.Using the information theory to build a system for appraiseing the quality of fusion imagery.Results The multi-source image data fusion can be classified into three levels:pixel-based, featuee-based and decision-based.Using pixel-based method,the information loss is the lowest, using decision-based method the information loss is the highest.The accuracy of the pixel-based is the higest,and of decision-based method is the lowest.Conclusion Comparing multi-source image data fusion as single image data fusion can get more accuracy more safety more reliable image, it can raise the resolution and definition,effectively rasie the utilization of the remotely sensed imagery.

关 键 词：多源遥感影像 数据融合 信息 属性说明 

分 类 号：TP75[自动化与计算机技术—检测技术与自动化装置]