电子学报 ›› 2019, Vol. 47 ›› Issue (1): 73-81.DOI: 10.3969/j.issn.0372-2112.2019.01.010

• 学术论文 • 上一篇    下一篇

基于边缘修正的高光谱图像超像素空谱核分类方法

陈允杰1, 马辰阳1, 孙乐2, 詹天明3   

  1. 1. 南京信息工程大学数学与统计学院, 江苏南京 210044;
    2. 南京信息工程大学计算机与软件学院, 江苏南京 210044;
    3. 南京审计大学信息与工程学院, 江苏南京 211815
  • 收稿日期:2017-09-09 修回日期:2018-03-22 出版日期:2019-01-25 发布日期:2019-01-25
  • 通讯作者: 孙乐
  • 作者简介:陈允杰 男,1980年生于江苏盐城.南京信息工程大学数学与统计学院教授,研究方向为数值计算、模式识别、图像处理.E-mail:priestcyj@nuist.edu.cn;马辰阳 男,1995年生于山西运城.南京信息工程大学数学与统计学院硕士研究生,研究方向为高光谱图像分类.E-mail:15189826258@163.com;詹天明 男,1984年10月生于江苏高邮,南京审计大学信息与工程学院副教授,研究方向为模式识别、图像处理与大数据分析.E-mail:ztm@nau.edu.cn
  • 基金资助:
    国家自然科学基金(No.61672291,No.61601236,No.61502206);江苏省自然科学(No.BK20150923,No.BK20150523)

Edge-Modified Superpixel Based Spectral-Spatial Kernel Method for Hyperspectral Image Classification

CHEN Yun-jie1, MA Chen-yang1, SUN Le2, ZHAN Tian-ming3   

  1. 1. College of Math and Statistics, Nanjing University of Information Science and Technology, Nanjing, Jiangsu 210044, China;
    2. School of Computer and Software, Nanjing University of Information Science and Technology, Nanjing, Jiangsu 210044, China;
    3. School of Information and Engineering, Nanjing Audit University, Nanjing, Jiangsu 211815, China
  • Received:2017-09-09 Revised:2018-03-22 Online:2019-01-25 Published:2019-01-25

摘要: 本文提出了一种边缘修正的超像素空间光谱核分类方法,该方法能够有效解决构建空谱核时超像素方法提取的空间信息完全依赖于同一个超像素特征,边缘处像素空间信息刻画不准确这一缺陷,从而有效提升分类精度.首先本文提出一种固定窗口与超像素结合的同质区域选择方法,对提取的邻域像素进行赋权,将超像素中固定窗口外的像素权值置零,得到修正的空间光谱核;其次,进一步考虑相邻超像素之间的相关性,得到相邻超像素间的空间特征光谱核,并与上一步中的空间光谱核进行凸组合得到修正的超像素空间光谱核,最后采用支持向量机进行分类.真实高光谱数据实验结果表明:本文方法能有效克服超像素空谱核的空间信息不稳定性,分类精度优于现有的最新的分类方法.

关键词: 高光谱图像分类, 空谱核, 超像素核, 核方法

Abstract: In order to alleviate the drawback that the spatial information of any pixel in a superpixel for generating the spatial-spectral kernel is totally determined by the same biased superpixel feature,especially for spatial information of the pixels located at the boundary,we propose an edge-modified superpixel based spatial-spectral kernel method for hyperspectral classification.On one hand,we combine the fixed window and superpixel to determine the homogeneous regions in a weighting strategy,in which the weights for pixels outside the fixed window are set to zero.Then we obtain the modified spectral-spatial kernel based on the weighted homogeneous regions.On the other hand,by considering the correlation among adjacent superpixels,we extract the spatial features among those superpixels to generate the inter-superpixel based spectral-spatial kernel.Finally,we combine the two spatial-spectral kernels in a convex way and employ support vector machine (SVM) for classification.Experimental results on two real hyperspectral data sets indicate that the proposed method could overcome the instability caused by superpixel-based spatial information extraction technique,and lead to better classification results than other state-of-the-art classifiers.

Key words: hyperspectral classification, spatial-spectral kernel, superpixel based kernel, kernel-based method

中图分类号: