|
|||||
|
|
| 基于面向对象和规则的遥感影像分类研究 | |
| 引用本文： | 陈云浩,冯通,史培军,王今飞.基于面向对象和规则的遥感影像分类研究[J].武汉大学学报(信息科学版),2006,31(4):316-320. |
| 作者姓名： | 陈云浩 冯通 史培军 王今飞 |
| 作者单位： | 1. 北京师范大学资源学院,北京市新街口外大街19号,100875;香港中文大学地理与资源管理系,香港新界沙田 2. 香港中文大学地理与资源管理系,香港新界沙田 3. 北京师范大学资源学院,北京市新街口外大街19号,100875 4. 加拿大西安大略大学地理系,加拿大,N6A 5C2 |
| 基金项目： | RGC Grant资助项目;中国科学院资助项目;国家测绘科技发展基金 |
| 摘 要： | 讨论了面向对象和规则的光学遥感影像分类方法。首先利用多尺度分割形成影像对象，建立对象的层次结构，计算对象的光谱特征、几何特征、拓扑特征等，利用对象、特征形成分类规则，并通过不同对象层间信息的传递和合并实现对影像的分类。并以北京城市土地利用分类为例，对该方法进行了验证。 |
| 关 键 词： | 面向对象 多尺度分割 规则 分类 |
| 文章编号： | 1671-8860(2006)04-0316-05 |
| 修稿时间： | 2006年1月15日 |
Classification of Remot Sensing Image Based on Object Oriented and Class Rules |
|
| CHEN Yunhao,FENG Tong,SHI Peijun,WANG Jinfei.Classification of Remot Sensing Image Based on Object Oriented and Class Rules[J].Geomatics and Information Science of Wuhan University,2006,31(4):316-320. | |
| Authors: | CHEN Yunhao FENG Tong SHI Peijun WANG Jinfei |
| Abstract: | A classification method for remote sensing image based on object oriented and class rules is presented in this paper.The whole image is firstly segmented into image objects and object hierarchy is built using multi-resolution segmentation.Then,the features of objects,such as spectral,geometrical and topological characteristics,are measured.The class rules are constructed based on these features.Classification of remote sensing image is carried out using the rules and information transfering and merging among these objects.The accuracy of the classification approach based on object(oriented) and class rules is checked by a case study of land use classification of Beijing. |
| Keywords: | object oriented multi-resolution segmentation class rules classification |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ | |