地球信息科学学报 ›› 2020, Vol. 22 ›› Issue (8): 1642-1653.doi: 10.12082/dqxxkx.2020.190383

• 遥感科学与应用技术 • 上一篇    下一篇

基于加权指数函数模型的高光谱图像分类方法

李玉1(), 李奕燃1,*(), 王光辉2, 石雪1   

  1. 1.辽宁工程技术大学 测绘与地理科学学院 遥感科学与应用研究所,阜新 123000
    2.自然资源部国土卫星遥感应用中心,北京 100048
  • 收稿日期:2019-07-18 修回日期:2019-11-27 出版日期:2020-08-25 发布日期:2020-10-25
  • 通讯作者: 李奕燃 E-mail:liyu@lntu.edu.cn;939902034@qq.com
  • 作者简介:李 玉(1963— ),男,辽宁康平人,教授,博士生导师,主要从事遥感数据处理理论与应用基础研究,包括空间统计学、随机几何、模糊数学在遥感数据建模与分析方面的应用。E-mail:liyu@lntu.edu.cn
  • 基金资助:
    国家自然科学基金项目(41301479);辽宁省高校创新人才支持计划项目(LR2016061)

A Hyperspectral Image Classification Algorithm based on the Weighted Exponential Function Model

LI Yu1(), LI Yiran1,*(), WANG Guanghui2, SHI Xue1   

  1. 1. The Institute for Remote Sensing, School of Geomatics, Liaoning Technology University, Fuxin 123000, China
    2. Land Satellite Remote Sensing Application Center, Ministry of Natural Resources, Beijing 100048, China
  • Received:2019-07-18 Revised:2019-11-27 Online:2020-08-25 Published:2020-10-25
  • Contact: LI Yiran E-mail:liyu@lntu.edu.cn;939902034@qq.com
  • Supported by:
    National Natural Science Foundation of China(41301479);Innovative Talents Support Program for Colleges and Universities in Liaoning Province(LR2016061)

摘要:

高光谱图像的众多波段为地物分类提供了充分的特征信息,同时也为如何有效利用这些特性带来难题。为了充分利用高光谱图像的光谱信息实现地物目标的精确分类,根据其像素光谱曲线所呈现出的多峰特性,提出一种基于加权指数函数模型(Weighted Exponential Function, WEF))的高光谱图像分类方法。首先,采用WEF建立像素光谱曲线的理想模型,其中WEF模型由多个具有不同权重的指数函数相加而成。由于该模型中参数较多,导致参数求解较为困难。因此,为简单起见固定所有像素WEF模型中的峰值位置,并将由所有峰值位置构建矢量集。然后,根据最小二乘原理求解WEF模型的参数,以拟合光谱曲线。利用求得的参数集代替光谱测度矢量作为像素特征。最后,采用模糊C均值(Fuzzy C-means, FCM)算法实现图像分类。为了验证提出方法的可行性和有效性,分别以提出的分类方法、基于主成分分析(Principal Component Analysis, PCA)的分类方法、基于最小噪声分离(Minimum Noise Fraction, MNF)的分类方法和以光谱测度矢量为分类特征的FCM方法对Salinas和PaviaU图像进行分类实验,并据此对实验结果进行定性和定量评价。在Salinas图像中提出的分类方法比其它方法的分类精度从51%提高到了60%,在PaviaU图像中分类精度从43%提高到了51%。此外,提出的分类方法在降低了高光谱图像数据量的同时,保留了高光谱图像丰富的光谱信息。

关键词: 高光谱图像分类, 加权指数函数模型, 最小二乘法, 模糊C均值, 光谱曲线, 曲线拟合, 主成分分析, 最小噪声分离

Abstract:

In recent years, the hyperspectral remote sensing technology has developed rapidly. Hyperspectral images obtained by hyperspectral sensors contain abundant spectral information of ground objects, such that they are good for fine spectral recognition. In hyperspectral image processing, its accurate classification is a solid foundation for the subsequent interpretation tasks. However, the numerous bands in hyperspectral imagery not only provide sufficient characteristics information for classification, but also bring the problem of how to use these characteristics effectively. In this paper, to make full use of the spectral information of hyperspectral images so to achieve accurate classification, a hyperspectral image classification method based on the Weighted Exponential Function (WEF) was proposed that considers the multi-peak characteristics of the spectral response curve of pixels. Firstly, the WEF model was used to build an ideal model of the spectral response curve of pixels, composed of several exponential functions with different weights. Because there are many parameters in the model (including weight, peak position and peak width), it is difficult to solve them. Therefore, the WEF model with fixed peak positions and number of exponential functions was used to model the spectral response curve of all pixels. Then, the parameters of the WEF model were determined according to the least square principle to fit the spectral response curve. Finally, the parameter set was used to replace the spectral measure vector, and the WEF model parameter vector of the pixel was used as its feature. Fuzzy C-means (FCM) algorithm was used for image classification. To validate the feasibility and effectiveness of the proposed method, the classification experiments of Salinas and PaviaU hyperspectral images were conducted by using respectively the proposed method, Principal Component Analysis (PCA) based classification method, Minimum Noise Fraction (MNF) based classification method, and FCM method with the spectral measure vector as the classification feature. The user accuracy, product accuracy, overall accuracy and Kappa coefficient of the results from these classification methods were calculated, and the experimental results were evaluated qualitatively and quantitatively. Compared with other methods, the classification accuracy of the proposed classification method for the Salinas image increased from 51% to 60%, and for the PaviaU image from 43% to 51%. In addition, the proposed classification method reduced the amount of hyperspectral image data while preserving the rich spectral information of hyperspectral images.

Key words: hyperspectral image classification, weighted exponential function model, least square method, Fuzzy C-means, spectral curve, curve fitting, principal component analysis, Minimum Noise Fraction