基于支持向量机的高光谱影像分类研究.pdfVIP

第29 卷 第8 期 计算机工程与设计 2008 年4 月 Vol . 2 9 N o . 8 Computer Engineering and Design Apr. 2008 基于支持向量机的高光谱影像分类研究 杨国鹏， 余旭初， 刘 伟， 陈 伟 (信息工程大学 测绘学院，河南郑州450052) 摘 要：高光谱遥感技术，将反映目标辐射属性的光谱信息与反映目标空间几何关系的图像信息有机地结合在一起。高光 谱影像丰富的光谱信息使其较全色遥感、多光谱遥感能够更好的进行地面目标的分类识别。本文综合利用支持向量机分类 的若干关键技术，包括序列最小优化训练算法、多类支持向量机构造方法、核函数及其参数选择的交叉验证“网格搜索”，给 出了高光谱影像分类流程，进行了遥感数据试验分析。 关键词：高光谱影像; 支持向量机; 序列最小优化; 交叉验证; 网格搜索 中图法分类号：TP273 文献标识码：A 文章编号：1000-7024 (2008) 08-2029-03 Research of hyperspectral image classification based on support vector machine YANG Guo-peng, YU Xu-chu, LIU Wei, CHEN Wei (Institute of Surveying and Mapping, Information Engineering University, Zhengzhou 450052, China) Abstract ：Hyperspectral remote sensing technology organically combines the radiation information which relate to the targets attribute, and the space information which relate to the targets position and shape. The spectrum information, which the hyperspectral image en- riches are better to carry on the ground target classification, compare with panchromatic remote sensing image and multispectral remote sensing image. This paper introduces the key technologies of hyperspectral image classification based on support vector machine, in- cluding sequential minimal optimization, kernel functions parameter and regularization constant selection cross-validation via parallel grid search, and multi-classes classification problem. Then the method is applied to the hyperspectral image classification test. Key words ：hyperspectral image; support vector machine; sequential minimal optimization; cross-validation; grid search