中文核心期刊
CSCD来源期刊
中国科技核心期刊
RCCSE中国核心学术期刊

Journal of Chongqing Jiaotong University(Natural Science) ›› 2012, Vol. 31 ›› Issue (6): 1194-1197.DOI: 10.3969/j.issn.1674-0696.2012.06.23

Previous Articles     Next Articles

Object-Oriented Rural Roads Extraction Based on eCognition

He Yong1,Chen Changming2,Xiong Zenglian1,Wu Yakun1   

  1. 1. School of River & Ocean Engineering,Chongqing Jiaotong University,Chongqing 400074,China; 2. Chongqing Cybercity Science & Technology Co. ,Ltd. ,Chongqing 400020,China
  • Received:2011-10-31 Revised:2012-09-03 Online:2012-12-15 Published:2014-10-31

基于eCognition 的面向对象农村公路提取

何勇1,陈昌鸣2,熊增连1,吴亚坤1   

  1. 1. 重庆交通大学河海学院,重庆400074; 2. 重庆数字城市科技有限公司,重庆400020
  • 作者简介:何勇(1973—),男,重庆人,副教授,博士,主要从事地理信息系统工程方面的工作。E-mail:fly26242002@yahoo.com.cn。

Abstract: By object-oriented thought,the rural roads are extracted by the use of a single band CBERS 02B HR image method.Firstly,the images are segmented. And then the spectral information and object geometry information of images objects are comprehensively applied to build the road extraction knowledge base. Thirdly,the results of rural roads extraction are improved and completed. The results show that better accuracy of road extraction can be obtained by the proposed method,in contrast to the pixel-oriented method.

Key words: object-oriented, road extraction, image segmentation, eCognition

摘要: 采用面向对象思想,使用高分辨率CBERS 02B HR 全色影像对农村公路进行提取。在对影像进行分割后,综合利用影像对象的光谱信息和几何信息,构建道路提取知识库,并使用道路生长法对提取结果进行完善,增加了道路的完整性。与面向像元的方法对比,该方法能取得较好的精度。

关键词: 面向对象, 道路提取, 影像分割, eCognition

CLC Number: