| 基于核PCA方法的高分辨率遥感图像自动解译 |
| |
| 引用本文： | 张微,张伟,刘世英,杨金中,茅晟懿.基于核PCA方法的高分辨率遥感图像自动解译[J].国土资源遥感,2011(3):82-87. |
| |
| 作者姓名： | 张微 张伟 刘世英 杨金中 茅晟懿 |
| |
| 作者单位： | 中国国土资源航空物探遥感中心;四川省地质调查院;青海省地质调查院;中国科学院广州地球化学研究所; |
| |
| 基金项目： | 中国地质调查局地质调查项目“青藏铁路沿线矿产资源遥感调查”(编号:1212010781043)资助 |
| |
| 摘 要： | 针对基于像元的高分辨率遥感图像自动解译存在的缺点,提出一种分三步走的高分辨率遥感图像自动解译技术流程:首先采用核PCA进行特征提取,然后采用支持向量机(Support Vector Machine,SVM)进行分类,最后采用择多滤波器进行分类后处理。通过对覆盖西藏山南地区的IKONOS图像的解译实验表明,本文方法能够有效地实现遥感图像自动解译,其结果与人工目视解译图基本一致,取得了理想的效果。
|
| 关 键 词： | IKONOS 核PCA 支持向量机 分类后处理 |
Automatic Interpretation of High Resolution Remotely Sensed Images by Using Kernel Method |
| |
| ZHANG Wei,ZHANG Wei,LIU Shi-ying,YANG Jin-zhong,MAO Sheng-yi.Automatic Interpretation of High Resolution Remotely Sensed Images by Using Kernel Method[J].Remote Sensing for Land & Resources,2011(3):82-87. |
| |
| Authors: | ZHANG Wei ZHANG Wei LIU Shi-ying YANG Jin-zhong MAO Sheng-yi |
| |
| Institution: | ZHANG Wei1,ZHANG Wei2,LIU Shi-ying3,YANG Jin-zhong1,MAO Sheng-yi4(1.China Aero Geophysical Survey & Remote Sensing Center for Land and Resources,Beijing 100083,China,2.Institute of Geological Survey of Sichuan Province,Chengdu 610081,3.Institute of Geological Survey of Qinghai Province,Xining 810012,4.Guangzhou Institute of Geochemistry,Chinese Academy of Science,Guangzhou 510640,China) |
| |
| Abstract: | To tackle the limitation of conventional pixel-based classification methods,this paper proposes a new approach composed of three steps,namely kernel principal component analysis(KPCA) based feature extraction,support vector machine(SVM) classification and majority filtering post-classification.An experiment with an IKONOS image covering a study area in Tibet indicates the effectiveness of this approach.The resultant image from this automatic method shows a pattern very similar to the pattern of the referenc... |
| |
| Keywords: | IKONOS Kernel PCA SVM Post-classification |
| 本文献已被 CNKI 等数据库收录！ |
|
