地球信息科学学报

地球信息科学学报 ›› 2014, Vol. 16 ›› Issue (6): 941-948.doi: 10.3724/SP.J.1047.2014.00941

• • 上一篇    下一篇

面向对象的航空高光谱图像混合分类方法

李雪轲1,2(), 王晋年1,*(), 张立福1, 杨杭1, 刘凯3   

  1. 1. 中国科学院遥感与数字地球研究所,北京 100101
    2. 中国科学院大学,北京 100049
    3. 中国科学院地理科学与资源研究所,北京 100101
  • 收稿日期:2014-04-23 修回日期:2014-06-26 出版日期:2014-11-10 发布日期:2014-11-01
  • 通讯作者: 王晋年 E-mail:shakerlee88@126.com;jwang@irsa.ac.cn
  • 作者简介:

    作者简介：李雪轲(1989-),女,硕士生,主要从事高光谱遥感识别分类等应用研究。E-mail:shakerlee88@126.com

  • 基金资助:
    国家自然科学基金项目(41371362、41272364、41201348)

A Hybrid of Object-based and Pixel-based Classification Method with Airborne Hyperspectral Imagery

LI Xueke1,2(), WANG Jinnian1,*(), ZHANG Lifu1, YANG Hang1, LIU Kai3   

  1. 1. Institute of Remote Sensing and Digital Earth, Chinese Academy of Sciences, Beijing 100101, China
    2. University of Chinese Academy of Sciences,Beijing 100049, China
    3. Institute of Geographic Sciences and Natural Resources Research, Chinese Academy of Sciences, Beijing 100101, China
  • Received:2014-04-23 Revised:2014-06-26 Online:2014-11-10 Published:2014-11-01
  • Contact: WANG Jinnian E-mail:shakerlee88@126.com;jwang@irsa.ac.cn
  • About author:

    *The author: CHEN Nan, E-mail:fjcn99@163.com

RichHTML

PDF (PC)

赞

被引次数

7

摘要：

传统的高光谱分类通常仅考虑单一像元的光谱或纹理特征,分类后容易出现地物破碎的现象。鉴于此,本文提出了一种面向对象的混合分类方法,将面向对象的分割结果与传统的像元级分类结果进行有机融合,充分利用对象的光谱特征和空间结构特征。在此基础上,引入了2种具体的混合分类方法,即多尺度分割的SVM分类和多波段分水岭分割的SVM分类。前者将地物光谱的可变性进行弱化处理,转化为多尺度均质对象单元进行分类;后者融入了地物的空间信息和形态学特征,对分割得到的同质区域进行分类。将这2种分类方法应用于航空高光谱数据,实验结果表明：面向对象的混合分类方法的总体精度分别为92.63%和96.13%,与传统的像元级分类法相比,分别提高了10.14%和13.64%,有效地解决了分类后地物的破碎现象。

关键词: 航空高光谱, 面向对象图像分类, 支持向量机(SVM)

Abstract:

Hyperspectral imagery generally contains hundreds of contiguous narrow bands, which could provide detailed spectral information for target detection and image classification. Traditional hyperspectral classification fails to generate expected results since it simply considers spectral or textural properties at the pixel scale in the context of natural complexity. In this article, a hybrid classification method was proposed which takes full advantages of spectral and spatial features by fusing object-based segmentation results with traditional per-pixel classification results. Based on this concept, two specific hybrid classification approaches were employed: (1) the mixture of multi-scale segmentation and SVM classification and (2) the mixture of multi-band watershed segmentation and SVM classification. In the first proposed method, spectral variations were attenuated by converting them into homogenous image objects at multiple scales; while, the latter method aggregates spatial information and morphological profiles into the segmented objects to achieve the homogeneous classification. The two classification algorithms were applied to airborne hyperspectral imagery and the results show that the overall accuracy based on traditional pixel-wise classification reaches about 82.49%, relatively lower compared with the hybrid object-based classification methods, which are 92.63% (Method 1) and 96.13% (Method 2) respectively. In addition, Method 2 performs better than Method 1 since it produced a smoother boundary, partly because Method 2 needs less user-defined parameters, and the iterative “trial-and-error” of which may affect the classification results. In conclusion, this study demonstrates that the hybrid of object-based classification is a significantly more robust approach than the traditional per-pixel classifier. The proposed method overcomes the spectral confusion, solves the problem of land fragmentation, and provides a solution to map complex environments accurately.

Key words: airborne hyperspectral imagery, object-based, Support Vector Machines (SVM)