测绘学报 ›› 2017, Vol. 46 ›› Issue (6): 734-742.doi: 10.11947/j.AGCS.2017.20160514

• 摄影测量学与遥感 • 上一篇    下一篇

一种融合超像素与最小生成树的高分辨率遥感影像分割方法

董志鹏1, 王密1,2, 李德仁1,2   

  1. 1. 武汉大学测绘遥感信息工程国家重点实验室, 湖北 武汉 430079;
    2. 地球空间信息协同创新中心, 湖北 武汉 430079
  • 收稿日期:2016-10-24 修回日期:2017-05-26 出版日期:2017-06-20 发布日期:2017-06-28
  • 通讯作者: 王密 E-mail:wangmi@whu.edu.cn
  • 作者简介:董志鹏(1991—),男,博士,研究方向为高分辨遥感影像处理及信息提取。E-mail:zhipengdong@foxmail.com
  • 基金资助:
    国家自然科学基金(91438203);国家973计划(2014CB744201)

A High Resolution Remote Sensing Image Segmentation Method by Combining Superpixels with Minimum Spanning Tree

DONG Zhipeng1, WANG Mi1,2, LI Deren1,2   

  1. 1. State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan 430079, China;
    2. Collaborative Innovation Center of Geospatial Technology, Wuhan 430079, China
  • Received:2016-10-24 Revised:2017-05-26 Online:2017-06-20 Published:2017-06-28
  • Supported by:
    The National Natural Science Foundation of China (No.91438203);National Key Basic Research Program of China (973 Program) (No.2014CB744201)

摘要: 影像分割是面向对象高分辨率遥感影像分析的基础与关键。针对传统影像分割方法易受噪声影响,且难以确定合适的影像分割尺度的问题,本文提出了一种融合超像素与最小生成树的高分辨率遥感影像分割方法。首先用简单线性迭代聚类算法对影像进行过分割生成超像素;然后初始设定影像分割数,采用区域动态约束聚类算法对超像素进行合并,获得分割数-方差和、分割数-局部方差、分割数-局部方差变化率指标图,依据3个指标图确定合适的影像分割数;最后根据确定的合适影像分割数,采用区域动态约束聚类算法对超像素重新合并得到分割结果。定性对比试验和定量评价结果表明,本文方法可以有效地克服影像噪声对分割结果的影响,获得良好的影像分割结果。

关键词: 高分辨率遥感影像, 影像分割, 超像素, 聚类, 区域合并

Abstract: Image segmentation is the basic and key step of object-oriented remote sensing image analysis. Conventional image segmentation method is sensitive to image noise and hard to determine the correct segmentation scale. To solve these problems, a novel image segmentation method by combining superpixels with minimum spanning tree was proposed in this paper. First, the image is over-segmented by simple linear iterative clustering algorithm to obtain superpixels. Then, superpixels are firstly clustered by regionalization with dynamically constrained agglomerative clustering and partitioning algorithm using the initial segmentation number and the sum of squared deviations (SSD), local variance (LV), rate of LV change (ROC-LV) index of graphs corresponding to the segmentation number are obtained. So the suitable image segmentation number is determined according to the SSD, LV, ROC-LV index of graphs corresponding to segmentation number. Finally, superpixels are reclustered by regionalization with dynamically constrained agglomerative clustering and partitioning algorithm based on the suitable segmentation number. The experimental results showed that the proposed method can obtain good segmentation results.

Key words: high resolution remote sensing image, remote sensing image segmentation, superpixels, clustering, region merging

中图分类号: