基于Landsat 8 OLI影像纹理特征的面向对象土地利用/覆盖分类

针对如何提高中低分辨率遥感影像分类精度,该研究以河北省石家庄市Landsat 8 OLI遥感影像为研究对象,对灰度共生矩阵(gray-level co-occurrence matrix,GLCM)纹理与伽博(Gabor)滤波器下的Gist纹理特征进行对比,应用J-M(Jeffries-Matusita)距离可分离性分析GLCM最优纹理特征,并利用最佳指数法(optimum index factor,OIF)获取GLCM与Gist纹理特征的最佳特征组合;其次对面向对象分类的分割尺度进行研究,提出整体最优分割尺度计算方法;最后进行基于纹理特征的面向对象分类识别与精度评价,并与基于原始数据的面向对...

Full description

Saved in:
Bibliographic Details
Published in农业工程学报 Vol. 34; no. 2; pp. 248 - 255
Main Author 裴欢;孙天娇;王晓妍
Format Journal Article
LanguageChinese
Published 燕山大学信息科学与工程学院,秦皇岛 066004 2018
河北省计算机虚拟技术与系统集成重点实验室,秦皇岛 066004
河北省软件工程重点实验室,秦皇岛 066004%燕山大学信息科学与工程学院,秦皇岛,066004
Subjects
Online AccessGet full text
ISSN1002-6819
DOI10.11975/j.issn.1002-6819.2018.02.034

Cover

More Information
Summary:针对如何提高中低分辨率遥感影像分类精度,该研究以河北省石家庄市Landsat 8 OLI遥感影像为研究对象,对灰度共生矩阵(gray-level co-occurrence matrix,GLCM)纹理与伽博(Gabor)滤波器下的Gist纹理特征进行对比,应用J-M(Jeffries-Matusita)距离可分离性分析GLCM最优纹理特征,并利用最佳指数法(optimum index factor,OIF)获取GLCM与Gist纹理特征的最佳特征组合;其次对面向对象分类的分割尺度进行研究,提出整体最优分割尺度计算方法;最后进行基于纹理特征的面向对象分类识别与精度评价,并与基于原始数据的面向对象分类结果进行对比。研究表明:Gist纹理特征使分类精度有了一定的提高,基于纹理数据的面向对象支持向量机(support vector machine,SVM)分类及面向对象K邻近法(K-nearest neighbor,KNN)分类的总体分类精度(overall accuracy,OA)分别比基于原始数据的2种方法分类精度提高3.67和3.33个百分点,基于纹理的面向对象SVM方法具有最高的精度,OA达到85.67%。不管是基于原始数据还是纹理数据,面向对象分类精度远高于最大似然分类(maximum likelihood classification,MLC)、马氏距离分类(mahalanobis distance classification,MDC)和SVM分类精度,且面向对象分类方法对纹理数据更为敏感。该文提出的基于纹理的面向对象分类方法有效提高了遥感影像分类精度,为区域土地利用/覆盖信息提取提供了有效的途径。
Bibliography:11-2047/S
Pei Huan1,2,3, Sun Tianjiao1, Wang Xiaoyan1,2,3 (1. College of Information Science and Engineering, Yanshan University, Qinhuangdao 066004, China; 2. Hebei Provincial Key Lab of Computer Virtual Technology and System Integration, Qinhuangdao 066004, China; 3. Hebei Provincial Key Lab of Software Engineering, Qinhuangdao 066004, China)
Remote sensing image classification is the main approach for rapidly obtaining regional land use/cover information and it has always been an important part in the field of remote sensing.How to improve the classification accuracy of remote sensing images is an urgent problem to be solved in remote sensing research.In traditional classification,only the spectral features of remote sensing image are used,while the texture and other features are ignored.Therefore,it is very common to see the object confusion in the classification result.In this paper,we took the Shijiazhuang Landsat 8 OLI remote sensing image data as the research area,and systematically studied object-orien
ISSN:1002-6819
DOI:10.11975/j.issn.1002-6819.2018.02.034