• 技术交流 • 上一篇    下一篇

基于多种空间信息的高光谱遥感图像分类方法

刘咏梅*,马潇,门朝光   

  1. 哈尔滨工程大学计算机科学与技术学院  哈尔滨150001
  • 收稿日期:2018-09-13 修回日期:2018-10-19 出版日期:2019-04-25 发布日期:2019-03-19
  • 作者简介:刘咏梅(1973-),女,副教授,liuyongmei@hrbeu.edu.cn,研究方向为图像处理与模式识别

A hyperspectral remote sensing image classification method based on multispatial information

LIU Yongmei*,MA Xiao,MEN Chaoguang   

  1. School of Computer Science and Technology,Harbin Engineering University,Harbin 150001,China
  • Received:2018-09-13 Revised:2018-10-19 Online:2019-04-25 Published:2019-03-19

摘要: 在高光谱遥感图像分类方法中,空间特征和光谱特征的融合可以有效地改善分类效果。针对单一空间特征的信息表达不充分问题,提出了一种联合多种空间特征的高光谱图像空谱分类方法。利用超像素信息对分类结果进行后处理去掉椒盐噪声,并创造性地将超像素信息应用于分类前处理,提出了一种利用超像素信息对像素点的特征向量进行线性加权融合的方法。试验结果表明,所提方法的性能优于目前的通常方法。

关键词: 高光谱遥感图像分类, 空间特征, 光谱特征, 超像素, 线性加权融合

Abstract: In the field of hyperspectral remote sensing image classification, spatial and spectral feature fusion can improve the effect of classification. A multifeature spectral and spatial classification method for hyperspectral images was proposed. In the postprocessing procedure, the saltandpepper noises were removed by using superpixel information. It was also used in the preprocessing procedure, and the feature vector of pixels was weighted by superpixel information. The experiment results show that the results of proposed method are better than the present methods.

Key words: hyperspectral remote sensing image classification, spatial feature, spectral feature, superpixel, linear weighted fusion