针对高光谱遥感图像中可能并不存在图像端元这一问题,试探的提出一种基于线性混合模型下对初步提取的最近似于端元的像元进行再分析的端元提取算法,即高光谱遥感图像的端元递进提取算法.首先针对3个端元线性混合的图像进行提取,在图像中找到最大近似于端元的像元,利用凸面单形体的几何性质,找出初步提取像元附近位于图像端元构成的凸面单形体边界上的像元,通过计算图像端元在边界像元中的含量,应用线性反解提取出图像端元.模拟图像中的初步结果表明在不存在图像端元的图像中,该算法可以有效的提取3个端元,应用于实际Hyperion图像取得了较好的实验效果.

In circumstance when there are no pure pixels exits in hyperspectral image, the endmembers extracted by traditional algorithms are usuallymixing ones stil.l In order to solve the problem, this paperproposes an endmemberextraction algorithm based on the re-analysis ofnear-endmemberusing the linear mixing mode.l After extracting the pixelswhichweremost close to the pure endmembers in the image, using the convex polyhedron s geometric characters the algorithm searches the pixels around the nearend memberand finds out the pixels in the edge of the convex polyhedron formed by the pure endmembers. Calculating themixing coefficients of every endmember in these pixels by the laws of sins, thus, with these coefficients the pure endmember vectors could be extracted according to the constraints of linearmixing mode.l A hyperspectral image simulated by the real spectrums is used to investigate the performance of the algorithm. Preliminary result indicates the effectivity of the algorithm. Applying the algorithm to a realHyperion image itcan also geta better resul.t