利用流形技术的遥感高光谱图像边缘检测  

Edge Detection on Hyperspectral Imagery Via Manifold Techniques

作　　者：刘行波[1] 武小军[1] 周源[2] 

机构地区：[1]江苏今迈数字空间技术股份有限公司,江苏南京210019 [2]武汉大学遥感信息工程学院,湖北武汉430079

出　　处：《城市勘测》2010年第B06期94-96,共3页Urban Geotechnical Investigation & Surveying

摘　　要：对于遥感高光谱影像,"光谱边界"还未被明确的定义,这是因为谱空间中存在多维的复杂性。一个新的光学边界定义的提出要基于流形学习的数学趋近方法。要考虑谱空间中的光谱特性以及像空间的像函数不连续性。使用EO-1高光谱图像试验分析表明基于光谱边界的方法拥有描述高光谱影像边界轮廓的令人期待的表现。For hyperspectral imagery,the term＂ spectral edge＂ has not been clearly defined because of the complexity of the high dimensional properties in spectral space. In this paper, a new definition of the spectral edge is presented based on a data-driven mathematic approach Manifold Learning. It considers both the spectral features in spectral space and the discontinuity of image function in image space. Experimental analysis using EO-1 hyperspectral imagery shows that the spectral edge based method has desired performance to describe the edge contours in the hyperspectral imagery.

关 键 词：遥感高光谱影像 光学边界 边界检测 流形学习 LTSA 

分 类 号：P231.1[天文地球—摄影测量与遥感]