基于2DPCA的遥感图像融合算法研究  

2DPCA-Based Image Fusion Algorithm in Remote Sensing

作　　者：吴学明[1] 杨武年[1] 

机构地区：[1]成都理工大学地质灾害防治与地质环境保护国家重点实验室

出　　处：《地质科技情报》2008年第5期97-101,共5页Geological Science and Technology Information

基　　金：地质灾害防治与地质环境保护国家重点实验室“科技减灾、重建家园”开放研究基金项目

摘　　要：基于PCA的遥感图像融合算法思想简单,实现起来较容易,而且遥感图像融合的性能也较好。但这种方法也有一些缺点:①不能有效利用图像的结构信息;②光谱信息损失较多;③灵活性较差。针对这些问题,首次提出了一种基于2DPCA的遥感图像融合算法。与PCA融合算法相比,基于2DPCA的融合算法的主要特点是:①直接对图像矩阵进行2DPCA分析,因而可以有效利用图像的二维结构信息;②多光谱图像的特征矩阵主成分的替换个数可以是一个或多个,这样就可以调节光谱信息的保持程度和空间分辨率的改善程度,从而获得不同融合质量的图像,具有更好的灵活性;③融合后的图像不仅光谱信息得到了较好保持,空间分辨率获得了明显改善,而且图像色彩也得到了增强。PCA-Based image fusion algorithm, widely applied in remote sensing, is a typical technique in image fusion with easy implementation and good performance. However, an image must be transformed into a 1-D vector when PCA is applied to the image and can not utilize its structural information. On the other hand, the spectral information is badly lost in the fused image, although the spatial resolution is apparently improved. Moreover, the degree of the loss of the spectral information and that of the improvement of the spatial resolution can not be adjusted. To avoid these disadvantages of PCA, this paper shows a novel image fusion method based on two-dimensional PCA （2DPCA）, which is directly applied to the image matrices instead of 1D vector. Therefore, the structural information of the image is effectively utilized. Furthermore, with this new technique, not only the spatial resolution of the fused image is greatly improved, but also the spectral information is well preserved. Finally, in the new algorithm, not only the principal components number of the eigen-matrices of the multi-spectral images can be replaced with numbers that equal to or larger than 1, if only the number is not larger than the total number of the principal components, but also the degree of the spectral information loss and that of the spatial resolution improvement could be adjusted by assigning different number of the replaced principal components. The experimental results show the better flexibility of this method proposed.

关 键 词：图像融合 遥感 PCA 2DPCA 

分 类 号：P407.8[天文地球—大气科学及气象学]