论文部分内容阅读
本文主要介绍基于主成分分析的混合象元分解。通常,主成分分析用于图象增强和数据空间维数的压缩,不改变数据的空间结构。文中引入了目标检验方法,利用它可达到对混合象元的分解。由于卫片的分辨率有限,混合象元大量存在于遥感图象中,而混合象元的存在是导致异物同谱和同物异谱的一个重要原因。若能实现混合象元的分解,就可为深入应用遥感资料提供有力帮助。
This paper mainly introduces mixed pixel decomposition based on principal component analysis. In general, principal component analysis is used for image enhancement and compression of data space dimensions without changing the spatial structure of the data. In this paper, we introduce a target test method, which can be used to decompose mixed pixels. Due to the limited resolution of the patch, mixed pixels exist in a large number of remote sensing images, and the existence of mixed pixels is one of the important causes of the same spectrum and the same spectrum. If we can realize the decomposition of mixed pixels, we can provide powerful help for the further application of remote sensing data.