›› 2011, Vol. 24 ›› Issue (6): 38-.

• 论文 • 上一篇    下一篇

高分辨率遥感影像面向对象的分类方法

王林   

  1. (新疆生产建设兵团 勘测规划设计研究院,新疆 乌鲁木齐 830002)
  • 出版日期:2011-06-15 发布日期:2011-06-14
  • 作者简介:王林(1982—),女,助理工程师。研究方向:地理信息系统与遥感技术。

Object-Oriented Classification of the High-resolution Remote Sensing Image

WANG Lin   

  1. (Xinjiang Political Commissary Institute of Suvey,Planning,Design & Research,Xinjiang Production and Construction Corps,Urumqi 830002,China)
  • Online:2011-06-15 Published:2011-06-14

摘要:

通过高分辨率遥感影像分类软件eCogniton的面向对象的图像分类技术,对影像进行分类和信息提取。采用多尺度对象分割方法生成图像对象,提高了分类信息的信噪比。通过eCogniton分类结果与传统分类结果的对比,其面向对象的特征提取算法,更适用于几何信息和结构信息丰富的高分辨率图像。

关键词: eCognition;高分辨率遥感;面向对象

Abstract:

Special high-resolution remote sensing classification software eCognition adopts a classification technology of the bran-new object-oriented to classify the image and extract information.eCognition adopts the method of multi-resolution object cutting to produce the image object,and it improves the SNR of the classification information.A comparison of the classification results of eCognition and that of the traditional classification method indicates that the feature extraction operator of eCognition is more suitable for the classification of high-resolution remote sensing whose information is abundant in structure and geometry.

Key words: eCognition;remote sensing high-resolution;object oriented

中图分类号: 

  • TN911.73