欢迎访问《图学学报》 分享到：
图学学报

图学学报

• 专论：第十九届全国图象图形学学术会议(NCIG2018) • 上一篇    下一篇

基于多视图边界判别投影的高光谱图像分类

  

  1. 西北农林科技大学信息工程学院，陕西 杨凌 712100
  • 出版日期:2018-12-31 发布日期:2019-02-20
  • 基金资助:
    中国博士后科学基金项目(2018M633585)；陕西省自然科学基金项目(2018JQ6060)；西北农业科技大学大学生创新创业训练计划项 目(201710712064)

Hyperspectral Images Classification Based on Multiview Marginal  Discriminant Projection

  1. College of Information Engineering, Northwest A&F University, Yangling Shaanxi 712100, China
  • Online:2018-12-31 Published:2019-02-20

PDF (PC)

143

摘要： 高光谱图像分类是遥感领域研究的热点问题，其关键在于利用高光谱图谱合一的 优势，同时融合高光谱图像中各个像元位置的光谱信息和空间信息，提高光谱图像分类精度。 针对高光谱图像特征维数高和冗余信息多等问题，采用多视图子空间学习方法进行特征降维， 提出了图正则化的多视图边界判别投影算法。将每个像元处的光谱特征看作一个视图，该像元 处的空间特征看作另一个视图，通过同时优化每个视图上的投影方向来寻找最优判别公共子空 间。公开测试数据集上的分类实验表明，多视图学习在高光谱图像空谱融合分类方面具有显著 的优越性，在多视图降维算法中，该算法具有最高的分类准确性。

关键词: 多视图学习, 判别降维, 高光谱分类, 空谱融合

Abstract: Hyperspectral images classification is a research hotspot in the remote sensing field. The key point is to improve the classification accuracy by taking the advantage of spectral-spatial features of hyperspectral images, which fuse the spectral information and spatial information of each pixel in the hyperspectral image simultaneously. This paper employed multiview subspace learning for feature reduction with the problems of high feature dimension and redundant information of hyperspectral images, and proposed a graph regularized multiview marginal discriminant projection (GMMDP) algorithm. The multiview feature reduction algorithm took the spectral features of each pixels as a view and spatial features as another view, then searched the optimal discriminant common subspace by optimizing the projection direction of each view. Experiments on the open dataset showed that multiview learning had a significant advantage in spectral-spatial classification of hyperspectral images. Among all multiview dimensionality reduction algorithms, our GMMDP had the highest classification accuracy.

Key words: multiview learning, discriminant reduction, hyperspectral classification, spectral-spatial fusion