测绘通报 ›› 2017, Vol. 0 ›› Issue (6): 36-39.doi: 10.13474/j.cnki.11-2246.2017.0185

• 学术研究 • 上一篇    下一篇

一种遥感图像建筑物直线特征提取算法

朱添翼, 范强, 杜漫飞   

  1. 辽宁工程技术大学测绘与地理科学学院, 辽宁 阜新 123000
  • 收稿日期:2016-11-03 出版日期:2017-06-25 发布日期:2017-07-03
  • 作者简介:朱添翼(1992-),男,硕士生,研究方向为影像信息提取理论与方法。E-mail:494765448@qq.com

A Linear Feature Extraction Algorithm for Buildings in Remote Sensing Images

ZHU Tianyi, FAN Qiang, DU Manfei   

  1. School of Mapping and Geographical Science, Liaoning Technical University, Fuxin 123000, China
  • Received:2016-11-03 Online:2017-06-25 Published:2017-07-03

摘要: 随着遥感技术的不断发展,高效、快速的遥感影像处理成为人们不断研究的热点。作为内业处理的基础,人们对影像直线特征提取的重视不断加强。本次试验采用辽宁科技大学1:2000正射影像图,针对教学区内建筑物、绿化区和道路混合的特点,提出了一种自动识别并高效提取建筑物直线特征的算法。该算法将直线拟合和Hough变换进行结合,加入角度先验方法。试验结果表明:该算法的直线提取性能优于传统Hough变换,能很好地适应教学区域,对建筑物的识别能力、直线提取效率及精度有很大的提高。

关键词: Hough变换, 直线拟合, 教学区域, 建筑物, 直线提取

Abstract: With the continuous development of remote sensing technology, efficient and fast remote sensing image processing has become a hot research topic. As the basis of internal processing, people pay more and more attention to the feature extraction. Using the 1:2000 orthophoto map of the university of science and technology of Liaoning according to the teaching area, building area and road greening characteristics mixed, this experiment puts forward a kind of automatic recognition and extraction of building linear feature algorithm. The algorithm combines straight line fitting and Hough transform, and adds a priori method. The experimental results show that the algorithm is superior to the traditional Hough transform in line extraction, and it can well adapt to the teaching area, and has a great improvement in the recognition ability and the linear extraction efficiency of the building.

Key words: Hough transform, linear fitting, teaching area, building, straight line extraction

中图分类号: