基于多元统计模型的 TM 影象融合  

FUSION OF TM IMAGES BASED ON MULTIVARIATE STATISTICAL MODEL

作　　者：罗忠[1] 朱重光[1] 

机构地区：[1]中国科学院遥感应用研究所,北京100101

出　　处：《测试技术学报》1998年第4期6-10,共5页Journal of Test and Measurement Technology

摘　　要：基于多元统计模型的TM影象的融合策略,可利用其它6个高分辨率波段的信息来增强第6波段的空间分辨率。将TM影象各象元上7个波段的亮度值视为一个随机向量的7个分量,利用多元统计模型建立由其它6个波段的亮度值得出第7波段亮度增强值的数学关系。实验结果证明这种方法对于增强第6波段的分辨率具有较为显著的效果。An information fusion strategy based on a multivariate statistical model for TM images is investigated in this paper for purpose of enhancing the spatial resolution of the 6th band of a scene of TM images using the information of the other 6 bands with higher resolution. The intensity values in the 7 bands of the same pixel are considered the 7 components of a random vector and a multivariate statistical model is employed to established the mathematical relation for obtaining the enhanced intensity value of band 6 from the intensities of the other 6 bands. Experimental results showed that this method is significantly effective in enhancing the 6th band.

关 键 词：信息融合 多元统计模型 分辨率 遥感技术 

分 类 号：TP751[自动化与计算机技术—检测技术与自动化装置]