应用科学学报 ›› 2012, Vol. 30 ›› Issue (5): 511-516.doi: 10.3969/j.issn.0255-8297.2012.05.012

• 信号与信息处理 • 上一篇    下一篇

空间关系辅助的面向对象建筑物提取

周军其, 李志娟   

  1. 武汉大学遥感信息工程学院,武汉430079
  • 收稿日期:2011-10-09 修回日期:2011-12-23 出版日期:2012-09-24 发布日期:2012-09-25
  • 通信作者: 周军其,副教授,研究方向:遥感图像解译、遥感应用,E-mail: junqi_zhou@whu.edu.cn E-mail:junqi_zhou@whu.edu.cn
  • 作者简介:周军其,副教授,研究方向:遥感图像解译、遥感应用,E-mail: junqi_zhou@whu.edu.cn

Spatial Relation-Aided Method for Object-Oriented Extraction of Buildings from High Resolution Image

ZHOU Jun-qi, LI Zhi-juan   

  1. School of Remote Sensing and Information Engineering, Wuhan University, Wuhan 430079, China
  • Received:2011-10-09 Revised:2011-12-23 Online:2012-09-24 Published:2012-09-25

摘要:

根据高分辨率影像的特点提出一种采用面向对象的建筑物提取方法. 该方法以影像对象为处理单元,利用其丰富的光谱、形状以及隐含在影像中的深层空间语义关系等信息进行分类,然后结合空间关系特征对分类结果进行优化,并使用均值滤波对类别边缘进行修正. 实验表明,基于面向对象的方法能比较完整地提取出建筑物对象,且空间关系辅助能进一步提高建筑物提取的精度.

关键词: 面向对象, 高分辨率影像, 多尺度分割, 空间关系

Abstract:

Based on the characteristics of high spatial resolution images, an object-oriented approach to the building extraction is proposed. The method takes the object as a processing unit to perform classification using the rich information such as the spectrum, the object shape, and the implicit space semantic relations embedded in the images. The classification result is optimized based on the characteristics of the spatial relationship. Edges between different categories are modified using mean filtering. Experiments show that the object-oriented method can provide relatively complete extraction of the building, and improve precision of the extraction.

Key words: object-oriented, high resolution image, multi-scale image segmentation, spatial relationship

中图分类号: