宇航计测技术 ›› 2021, Vol. 41 ›› Issue (4): 38-44.doi: 10.12060/j.issn.1000-7202.2021.04.08

• 精密测试技术 • 上一篇    下一篇

基于地物信息的高光谱遥感图像分类方法

闫钧华1，2; 苏恺1，2; 苏荣华3; 张寅1，2; 王吉远3; 谷安鑫3;   

  1. 1 南京航空航天大学空间光电探测与感知工业和信息化部重点实验室，江苏 南京 211106 2 南京航空航天大学航天学院，江苏 南京 211106 3 军事科学院国防工程研究院，北京，100850
  • 出版日期:2021-08-25 发布日期:2022-02-17
  • 作者简介:闫钧华（1972-），女，博士，教授，主要研究方向：图像质量评价，多源信息融合，目标检测、跟踪与识别。

Classification method of hyperspectral remote sensing image based on feature information

Yan Junhua1,2, Su Kai1,2, Su Ronghua3, Zhang Yin1,2, Wang Jiyuan3, Gu Anxin3   

  1. 1 Key Laboratory of Space Photoelectric Detection and Perception , Ministry of Industry and Information Technology, Nanjing University of Aeronautics and Astronautics ,Nanjing, 211106, China; 2 College of Astronautics, Nanjing University of Aeronautics and Astronautics, Nanjing, 211106, China; 3 Institue of defense engineering, AMS, PLA,Beijing, 100850, China
  • Online:2021-08-25 Published:2022-02-17

PDF (PC)

48

摘要： 利用主成分分析法滤除 n 维高光谱遥感图像中的大部分冗余信息，得到尽可能保留光谱信息的 m 维高光谱遥感图像，融合其地物空间分布信息，将 m 维高光谱遥感图像中的每一个像素点构建为一个 2 维谱-空信息向量。再次利用主成分分析法法对 m 维高光谱遥感图像进行降维，得到 q 维融合地物空间分布信息与光谱信息的结果图。通过高斯混合模型预测聚类中心，基于改进的迭代自组织数据分析算法 ISODATA(Iterative Selforganizing Data Analysis Techniques Algorithm)对高光谱遥感图像进行聚类，得到最终的分类结果。实验结果表明本文方法的地物分类精度优于 K-means、ISODATA 和 SVM 方法，总体分类精度提升 10.14%-13.99%，kappa 系数提升 3.2%-12.85%。

关键词: 高光谱遥感图像, 地物分类, 地物空间分布信息, 主成分分析法, 聚类

Abstract:

Principal component analysis to filter out most of the redundant information in the n-dimensional hyperspectral remote sensing image is used, and the m-dimensional hyperspectral remote sensing image that retains the spectral information is obtained as much as possible, and fuses its spatial distribution information, each pixel in the m-dimensional hyperspectral remote sensing image is constructed as a 2-dimensional spectrum-space information vector. The principal component analysis method is used to reduce the dimension of the m-dimensional hyperspectral remote sensing image again, and the result map of the q-dimensional fusion of the spatial distribution information of the ground features and the spectral information is obtained. The Gaussian mixture model is used to predict the clustering center, and the hyperspectral remote sensing image is clustered based on the improved ISODATA (Iterative Selforganizing Data Analysis Techniques Algorithm) to obtain the final classification result. Experimental results show that the classification accuracy of the proposed method is better than that of K-means, ISODATA and SVM, the overall classification accuracy is increased by 10.14%-13.99%, and the kappa coefficient is increased by 3.2%-12.85%.

Key words: Hyperspectral remote sensing images, Classification of features, Spatial distribution information of features, Principal component analysis, Clustering

京ICP备09048426号-4　 京公网安备 11010602060144号　版权所有 © 《宇航计测技术》编辑部