混合像元线性分解技术是进行高光谱影像处理的常用方法,应用这种方法的一个主要问题是难以有效、自动地确定影像的端元光谱。利用非监督的方法快速自动提取高光谱遥感图像的端元光谱是解决这个问题的主要技术手段。根据迭代误差分析思路,通过对线性混合像元模型分解的误差传播分析后,得到了端元选择的约束条件。结合端元存在的空间信息,自动提取出端元光谱并进行了混合像元分解。利用不同地区、不同传感器的高光谱数据实例测试了该文的方法,分析和讨论了选择迭代初始值与参数阈值的敏感性问题。研究结果表明此方法可以自动提取端元光谱,并且精度较高。

Linear pixel unmixing is a straightforward and efficient approach to the spectral decomposition ofmulti-channel&hy\nperspectral remotely sensed scenes. Amain drawbackto itsutilization inoperational cases isthatthe endmemberofspectral com\nponents can not be retrieved correctly and automatically. Developing unsupervised methods to automatically abstract endmembe\nis a difficult but significant job. The authors presented an iterative error analysis algorithmto retrieve endmembers and unmixin\nhyperspectral imagery automatically after obtaining some constraint conditions of selecting endmembers by analyzing error propa\ngation in linearspectral unmixingmodel, and combinedwiththe propertyof endmemberwhich is cohesive in spatial.The experi\nmental results showthe algorithm isrobustbytestingvariousthresholds and initial iterative value. Other experiments fortest effi\nciency and accuracy of the algorithm by employingAVIRIS and PHI hyperspectral data were also done.