测绘通报 ›› 2019, Vol. 0 ›› Issue (7): 12-16.doi: 10.13474/j.cnki.11-2246.2019.0210

• 学术研究 • 上一篇    下一篇

GF-2影像城市地物分类方法探讨

王芳1,2, 杨武年1, 王建3, 谢兵4, 杨鑫1, 任金铜1   

  1. 1. 成都理工大学国土资源部地学空间信息技术重点实验室, 四川 成都 610059;
    2. 内江师范学院土壤资源与生态调控研究中心, 四川 内江 641100;
    3. 内江职业技术学院土木工程系, 四川 内江 641000;
    4. 四川建筑职业技术学院测绘工程系, 四川 德阳 618000
  • 收稿日期:2019-01-02 修回日期:2019-04-16 出版日期:2019-07-25 发布日期:2019-07-31
  • 通讯作者: 杨武年。E-mail:ywn@cdut.edu.cn E-mail:ywn@cdut.edu.cn
  • 作者简介:王芳(1983-),女,博士生,讲师,研究方向为3S技术与数字国土。E-mail:lasttear@163.com
  • 基金资助:
    国家自然科学基金(41671432;41372340);四川省国土资源厅项目(KJ-2016-12)

Discussion on classification methods of urban features based on GF-2 images

WANG Fang1,2, YANG Wunian1, WANG Jian3, XIE Bing4, YANG Xin1, REN Jintong1   

  1. 1. Key Laboratory of Geo-spatial Information Technology of Ministry of Land and Resources of China, Chengdu University of Technology, Chengdu 610059, China;
    2. Research Center for Soil Resources and Ecological Regulation, Neijiang Normal University, Neijiang 641100, China;
    3. Department of Civil Engineering, Neijiang Vocational & Technical Cllege, Neijiang 641000, China;
    4. Department of Surveying and Mapping Engineering, Sichuan College of Architectural Technology, Deyang 618000, China
  • Received:2019-01-02 Revised:2019-04-16 Online:2019-07-25 Published:2019-07-31

摘要: GF-2影像具有较高的分辨率和丰富的光谱、几何及纹理信息。为了深入探索GF-2影像城市地物分类方法,本文以四川省隆昌县城为研究区,提出了一种基于最优尺度和规则的面向对象分类法。在影像分割的基础上,通过构建评价函数,并结合最大面积法选取最优尺度,进而构建分层体系,提取影像的光谱、几何及纹理特征建立规则并分类,且将其与单尺度下的面向对象和基于像素分类法进行对比分析。结果表明,本文方法的总体精度和Kappa系数分别为93.33%和0.92。

关键词: 高分二号, 面向对象, 多尺度分割, 分类规则, 城市地物

Abstract: The GF-2 image has higher resolution as well as more detailed characteristics of spectral, features, geometric and texture. In order to explore the classification method of the GF-2 image in urban features, an object oriented classification method based on optimal scale and rules is proposed in the study area of Longchang County, Sichuan Province. Based on segmentations, the evaluation function is constructed, combining with the maximum area method, optimal segmentation scales are selected to construct multiple layers. The spectral, geometric and texture features of the image are extracted to establish rules for classification and compared with the classification methods of object-oriented with the single scale and pixel based. The results show that the overall accuracy and Kappa coefficient of the proposed method are 93.33% and 0.92, respectively.

Key words: GF-2 image, object-oriented, multi-scale segmentation, classification rule, urban features

中图分类号: