Journal of Computer Applications ›› 2019, Vol. 39 ›› Issue (1): 298-304.DOI: 10.11772/j.issn.1001-9081.2018051114

Previous Articles     Next Articles

Land parcel boundary extraction of UAV remote sensing image in agricultural application

WU Han1, LIN Xiaolong2,3, LI Xirong1, XU Xin1   

  1. 1. Electronic Information School, Wuhan University, Wuhan Hubei 430072, China;
    2. Wuhan Investigation Team, National Bureau of Statistics, Wuhan Hubei 430013, China;
    3. Faculty of Geographical Science, Beijing Normal University, Beijing 100875, China
  • Received:2018-05-30 Revised:2018-08-06 Online:2019-01-10 Published:2019-01-21
  • Supported by:
    This work is partially supported by the High-resolution Monitoring and Service Industrialization Application Project in Xiantao City, Hubei Province (81-Y40G25-9001-18/20).

面向农业应用的无人机遥感影像地块边界提取

吴晗1, 林晓龙2,3, 李曦嵘1, 徐新1   

  1. 1. 武汉大学 电子信息学院, 武汉 430072;
    2. 国家统计局 武汉调查队, 武汉 430013;
    3. 北京师范大学 地理科学学部, 北京 100875
  • 通讯作者: 林晓龙
  • 作者简介:吴晗(1994-),女,湖北咸宁人,硕士研究生,主要研究方向:遥感图像处理、信号处理;林晓龙(1987-),男,福建上杭人,工程师,主要研究方向:农业遥感统计调查;李曦嵘(1997-),男,湖南常德人,硕士研究生,主要研究方向:遥感图像处理、深度学习;徐新(1967-),男,湖北武汉人,教授,博士生导师,博士,主要研究方向:信号与信息处理。
  • 基金资助:
    湖北省仙桃市高分监测与服务产业化应用项目(81-Y40G25-9001-18/20)。

Abstract: Aiming at the over-segmentation problem caused by inconsistency of large-format, high-resolution and inconsistency of parcel size in extraction of Unmanned Aerial Vehicle (UAV) remote sensing image of farmland scene, an automatic extraction process for land boundary based on multi-scale segmentation was proposed. In this process, the block segmentation strategy was adopted under the framework of Multi-scale Combinatorial Grouping (MCG) segmentation method. The optimal ground sampling distance was selected by comparing experimental research and optimal segmentation scale was selected by analyzing the variation curve of boundary extraction accuracy with scale, therefore automatic extraction process of parcel boundaries was achieved. Experiments were conducted on the data collected from Xiantao City, Hubei Province. The experimental results show that the most suitable ground sampling distance for extracting land parcel boundary is about 30 cm and the optimal segmentation scale is[0.2,0.4]. The accuracy of land parcel boundary extraction can be more than 90%. In addition, the proposed method can accurately extract large-scale agricultural parcel boundary and also can provide a reference for later aerial program of agriculture UAV.

Key words: Unmanned Aerial Vehicle (UAV) image, segmentation, boundary extraction, Ground Sampling Distance (GSD), agricultural application

摘要: 针对无人机(UAV)影像农田场景地块边界提取过程中由于大幅面、高分辨率和地块尺寸大小不一致等带来的过分割问题,提出了一种基于多尺度分割的地块边界自动化提取流程。该流程采用分块分割策略,在多尺度组合聚合(MCG)分割方法框架下,通过对比实验研究并选取最佳地面采样距离和分析边界提取准确率关于尺度变化曲线选择最优分割尺度,进而实现了地块边界自动提取。以湖北省仙桃市为数据源进行的实验结果表明:面向地块边界提取的最佳地面采样距离为30 cm,最优分割尺度为[0.2,0.4],整场景总体地块边界提取准确率可达90%以上。该方法不仅能准确提取大幅面的农业地块边界,也可为后期农业无人机航拍规划提供参考依据。

关键词: 无人机影像, 分割, 边界提取, 地面采样距离, 农业应用

CLC Number: