测绘通报 ›› 2017, Vol. 0 ›› Issue (12): 63-67.doi: 10.13474/j.cnki.11-2246.2017.0380

• 学术研究 • 上一篇    下一篇

基于对象直方图G统计量的遥感影像道路提取

楚恒1,2,3, 李洪川1, 刘红彬1   

  1. 1. 重庆邮电大学光通信与网络重点实验室, 重庆 400065;
    2. 西南大学地理科学学院, 重庆 400715;
    3. 重庆市勘测院, 重庆 400020
  • 收稿日期:2017-03-14 出版日期:2017-12-25 发布日期:2018-01-05
  • 作者简介:楚恒(1976-),男,博士,高级工程师,主要研究方向为遥感影像融合与分类、模式识别。E-mail:1007533013@qq.com
  • 基金资助:
    重庆市2013西南大学博士后科研项目(Rc201336);重庆高校创新团队建设计划(CXTDX201601020)

Road Extraction of Remote Sensing Imagery Using G Statistics of Object Histogram

CHU Heng1,2,3, LI Hongchuan1, LIU Hongbin1   

  1. 1. School of Communication and Information Engineering, Chongqing University of Posts and Telecommunications, Chongqing 400065, China;
    2. School of Geographical Sciences, Southwest University, Chongqing 400715, China;
    3. Chongqing Survey Institute, Chongqing 400020, China
  • Received:2017-03-14 Online:2017-12-25 Published:2018-01-05

摘要: 提出了一种基于对象直方图G统计量的遥感影像道路提取方法。首先基于标记分水岭算法分割高分辨率遥感影像获取对象像斑,提取对象光谱特征并利用SVM从影像中分离出光谱相似的建成区(道路、建筑物等);然后从建成区选择合适的对象作为训练样本,采用G统计量度量测试样本与训练样本的LBP纹理直方图距离,以表达对象纹理特征的异质性,并利用最小距离分类器完成建成区内道路与建筑物等的分离;最后结合几何形状特征和数学形态学处理对提取的道路进行优化,获得最终的道路提取结果。试验结果表明:该方法能较好地提取出道路信息。

关键词: G统计量, 道路提取, 分水岭分割, LBP纹理直方图, 数学形态学

Abstract: This paper proposes a new road extraction method of remote sensing imagery based on G statistics of object histogram.Firstly,the original imagery is segmented using marked-watershed algorithm to obtain imagery objects, and the imagery objects' spectral features are extracted,the built-up areas containing roads and buildings are separated based on SVM. Then the appropriate objects are chosen as training samples.G statistics is used to measure the histogram distance between test samples and training samples which describes the heterogeneity of two objects.Minimum distance classifier is employed to separate the road information and buildings in built-up areas. Finally,the final road information is extracted integrating the shape features and mathematics morphology.The result of experiment shows that the proposed method can fairly well extract the road information.

Key words: G statistics, road extraction, watershed segmentation, LBP texture histogram, mathematics morphology

中图分类号: