针对现行的凸锥体分析方法提取多光谱影像端元数目的有限性, 提出了基于空间全局聚类分析的多光谱遥感影像端元自适应提取方法。 该方法首先通过主成分分析对多光谱遥感影像进行降维处理, 去除波段间的相关性; 然后根据空间光谱间相似性, 采用经典的空间聚类算法ISODATA对影像全局聚类, 合并聚类后小斑块, 实现影像自动分块; 最后根据分块对象地物类型分布的复杂程度和散点图特征分析, 自适应确定端元数目, 再通过沙漏算法迅速地提取端元。 通过TM影像端元提取实验表明该方法能够有效的提取多光谱影像的端元; 同时克服了端元数目限制, 提高了端元提取的精度, 为多光谱遥感影像端元提取提供了新思路。

Due to the problem that the convex cone analysis (CCA) method can only extract limited endmember in multispectral imagery, this paper proposed a new endmember extraction method by spatial adaptive spectral feature analysis in multispectral remote sensing image based on spatial clustering and imagery slice. Firstly, in order to remove spatial and spectral redundancies, the principal component analysis (PCA) algorithm was used for lowering the dimensions of the multispectral data. Secondly, iterative self-organizing data analysis technology algorithm (ISODATA) was used for image cluster through the similarity of the pixel spectral. And then, through clustering post process and litter clusters combination, we divided the whole image data into several blocks (tiles). Lastly, according to the complexity of image blocks’ landscape and the feature of the scatter diagrams analysis, the authors can determine the number of endmembers. Then using hourglass algorithm extracts endmembers. Through the endmember extraction experiment on TM multispectral imagery, the experiment result showed that the method can extract endmember spectra form multispectral imagery effectively. What’s more, the method resolved the problem of the amount of endmember limitation and improved accuracy of the endmember extraction. The method has provided a new way for multispectral image endmember extraction.