论文部分内容阅读
混合像元的存在不仅影响了基于高光谱图像的地物识别和分类精度,而且已经成为遥感科学向定量化发展的主要障碍。目前的混合像元分解算法大多采用线性混合模型,其关键步骤为端元提取。文中从线性混合模型的定义出发,总结了近年来提出的端元提取算法,并重点对SMACC、VCA、SGA等算法进行了深入的分析,最后总结了混合像元分解的发展趋势。
The existence of mixed pixels not only affects the accuracy of object recognition and classification based on hyperspectral images, but also has become the major obstacle to the quantitative development of remote sensing science. The current mixed pixel decomposition algorithms mostly use the linear mixed model, the key step for the end-element extraction. Starting from the definition of linear mixed model, this paper summarizes the endmember extraction algorithm proposed in recent years, and focuses on the analysis of SMACC, VCA, SGA and other algorithms in depth, and finally summarizes the development trend of hybrid pixel decomposition.