测绘学报 ›› 2017, Vol. 46 ›› Issue (1): 83-89.doi: 10.11947/j.AGCS.2017.20160389

• 摄影测量学与遥感 • 上一篇    下一篇

融合直角点和直角边特征的高分辨率遥感影像居民点提取方法

林祥国, 宁晓刚   

  1. 中国测绘科学研究院, 北京 100830
  • 收稿日期:2016-08-17 修回日期:2016-12-01 出版日期:2017-01-20 发布日期:2017-02-06
  • 作者简介:林祥国(1981-),男,博士后,副研究员,硕士生导师,主要从事遥感影像理解、LiDAR数据处理方法研究。E-mail:linxiangguo@gmail.com
  • 基金资助:
    国家自然科学基金(41371405;41671440);遥感青年科技人才创新资助计划;中央级公益性科研院所基本科研业务费项目(777161103)

Extraction of Human Settlements from High Resolution Remote Sensing Imagery by Fusing Features of Right Angle Corners and Right Angle Sides

LIN Xiangguo, NING Xiaogang   

  1. Chinese Academy of Surveying and Mapping, Beijing 100830, China
  • Received:2016-08-17 Revised:2016-12-01 Online:2017-01-20 Published:2017-02-06
  • Supported by:
    The National Natural Science Foundations of China (Nos.41371405;41671440);The Foundation for Remote Sensing Young Talents by the National Remote Sensing Center of China;The Basic Research Fund of the Chinese Academy of Surveying and Mapping(No.777161103)

摘要: 提出了一种融合直角点和直角边两种特征的高分辨率遥感影像居民点提取方法:首先,分别检测高分辨率遥感影像的角点和直线段,通过两种特征交叉验证确定直角点和直角边,并对二者进行栅格化;然后,基于局部直角点和直角边点的密度和距离特征生成居民点指数图像;最后,通过指数图像二值化、栅格转矢量、剔除小图斑等操作确定居民点多边形。使用3景影像进行了试验。试验结果表明,本文方法提高了居民点提取精度,其正确率、完整率、质量等3个指标的平均值比已有方法的相关值分别高6.76%、10.12%、12.14%。

关键词: 高分辨率遥感影像, 居民点, Harris角点, 直线段, 空间投票

Abstract: A method for human settlements extraction from high resolution remote sensing imagery using feature-level-based fusion of right-angle-corners and right-angle-sides is proposed in this paper. First, the corners and line segments are detected, the right-angle-corners and right-angle-sides are determined by cross verification of the detected corners and line segments, and these two types of features are rasterized. Second, a human settlement index image is built based on the density and distance of the right-angle-corners and right-angle-sides in a local region. Finally, the polygons of human settlements are generated through binary thresholding of the index image, conversion from raster format to vector format, and sieving. Three images are used for testing the proposed method. The experimental results show that our proposed method has higher accuracy than the existed method. Specifically, the correctrate, completeness, and quality of our method is higher 6.76%, 10.12%, 12.14% respectively than the existed method.

Key words: high resolution remote sensing image, human settlement, Harris corners, line segment, spatial voting

中图分类号: