地球信息科学学报

地球信息科学学报 ›› 2011, Vol. 13 ›› Issue (3): 409-417.doi: 10.3724/SP.J.1047.2011.00409

• 遥感技术与地图应用 • 上一篇    下一篇

最优分割尺度下的多层次遥感地物分类实验分析

李秦1,2, 高锡章2, 张涛1,2, 刘锟1,2, 龚剑明2   

  1. 1. 中国科学院地理科学与资源研究所,北京 100101;
    2. 中国科学院研究生院,北京 100049
  • 收稿日期:2010-10-20 修回日期:2011-05-23 出版日期:2011-06-25 发布日期:2011-06-15
  • 作者简介:高锡章(1976-),男,河南信阳人,博士后,研究方向为GIS理论与应用、生态环境GIS、海洋GIS等。 E-Mail:gaoxz@lreis.ac.cn
  • 基金资助:

    国家高技术研究发展计划(863)项目 (2008AA121706,2009AA12Z148);国家自然科学基金项目(40971224)。

Optimal Segmentation Scale Selection and Evaluation for Multi-layer Image Recognition and Classification

LI Qin1,2, GAO Xizhang2, ZHANG Tao1,2, LIU Kun1,2, GONG Jianming2   

  1. 1. Institute of Geographic Sciences and Natural Resources Research, CAS, Beijing 100101, China;
    2. GraduateUniversity of Chinese Academy of Sciences, Beijing 100049, China
  • Received:2010-10-20 Revised:2011-05-23 Online:2011-06-25 Published:2011-06-15

PDF (PC)

赞

被引次数

66 | 30

摘要： 为了快速、准确地提取我国海岸带地区土地利用及其变化信息,选择高分辨率遥感影像作为数据源,提出了最优分割尺度下的遥感多层次地物识别分类方法。首先,通过改进的局部方差法进行最优分割尺度的确定,建立影像中各对象的方差均值与变化率随分割尺度变化曲线,确定方差均值的峰值,以变化率开始呈现下降趋势时所对应的分割值为最优分割尺度参考;然后,针对地物分类特征差异选取各自适宜的分割尺度,建立多层次地物特征表达与规则,最后,实现最优尺度分割选择下的遥感多层次识别分类,即实现较大尺度下分割形成父对象,而较小尺度下分割出其若干子对象的目标,提出了快速、自动化获取土地利用/覆盖图的策略流程。本文选取了广东省珠海市海岸带地区作为实验区,利用多层次遥感分类方法进行地物识别分类。结果表明,其目视效果以及总体精度、Kappa系数,均优于传统方法和单一分割尺度下的影像分类方法。

关键词: 局部方差, 最优分割尺度, 多层次分类, 精度评价

Abstract: With the rapid increase of remote sensing image storage, it becomes more critical for the quick and effective information extraction from remote sensing imagery. As a widely-used method, object-based image analysis (OBIA) has been rapidly developed from the beginning of this century, but the automatic procedure for land use mapping is still problematic facing with geographical complexity. Regarding to the complex feature contents in the imagery of costal zones, this paper presents a method of optimal segmentation scale extraction and an object-based multi-layer classification procedure. The proposed approach mainly contains three parts: segmentation, optimal scale generation and multi-level classification. First, we select the high resolution images as the data source, segment the imagery with series of scale parameters. Then choose the appropriate scales with the curve of local variance (LV) variation. Variation in heterogeneity is explored by evaluating LV plotted against the corresponding scale in order to get different types of the landuse/cover with their own extraction scales. Finally, we classify the image with multi-features, including spectral, shape, texture and spatial relationship. This paper selects the coastal area of Zhuhai, Guangdong Province as the experiment zone, the classification results show that overall accuracy and Kappa index of the new method are better than those of the traditional pixel-based classifiers and object-oriented classifiers based on the single-level segmentation.

Key words: local variance, optimal segmentation scale, multi-level classification, precision evaluation