测绘学报 ›› 2020, Vol. 49 ›› Issue (5): 589-597.doi: 10.11947/j.AGCS.2020.20190135

• 摄影测量学与遥感 • 上一篇    下一篇

高分辨率遥感影像超像素的模糊聚类分割法

黄亮1,2, 姚丙秀1, 陈朋弟1, 杨兴3, 付必环1   

  1. 1. 昆明理工大学国土资源工程学院, 云南 昆明 650093;
    2. 云南省高校高原山区空间信息测绘技术应用工程研究中心, 云南 昆明 650093;
    3. 成都理工大学地球科学学院, 四川 成都 610059
  • 收稿日期:2019-04-15 修回日期:2019-12-25 发布日期:2020-05-23
  • 通讯作者: 姚丙秀 E-mail:1366711008@qq.com
  • 作者简介:黄亮(1985-),男,博士,讲师,主要研究方向遥感影像变化检测。E-mail:kmhuangliang@163.com
  • 基金资助:
    云南省应用基础研究计划面上项目(2018FB078);自然资源部地球观测与时空信息科学重点实验室经费资助项目(201911)

Superpixel segmentation method of high-resolution remote sensing image based on fuzzy clustering

HUANG Liang1,2, YAO Bingxiu1, CHEN Pengdi1, YANG Xing3, FU Bihuan1   

  1. 1. Faculty of Land Resource Engineering, Kunming University of Science and Technology, Kunming 650093, China;
    2. Surveying and Mapping Geo-Informatics Technology Research Center on Plateau Mountains of Yunnan Higher Education, Kunming 650093, China;
    3. College of Earth Science, Chengdu University of Technology, Chengdu 650093, China
  • Received:2019-04-15 Revised:2019-12-25 Published:2020-05-23
  • Supported by:
    Applied Basic Research Programs of Science and Technology Department of Yunnan Province (No. 2018FB078);The Key Laboratory of Surveying and Mapping Science and Geospatial Information Technology of Ministry of Natural Resources (No. 201911)

摘要: 传统模糊C均值聚类在影像分割中只考虑影像的灰度特征,导致该算法用于高空间分辨率遥感影像分割时分割结果不理想。针对该问题,本文提出了一种高分辨率遥感影像超像素的模糊聚类分割方法。该方法首先利用分水岭变换算法产生多个超像素子区域;然后比较各个子区域间光谱特征的相似性;最后利用融合光谱特征的模糊C均值聚类对这些超像素子区域进行合并。试验选用4组不同场景的遥感影像,采用定性和定量相结合的方法评价试验结果。试验结果表明,该方法有效提高了分割区域的分割精度,并取得了较好的分割视觉效果。

关键词: 高空间分辨率遥感影像, 超像素, 影像分割, 分水岭变换, 模糊聚类

Abstract: Traditional fuzzy C-means clustering (FCM) only considers the gray features of image in image segmentation, which results in unsatisfactory segmentation results when the algorithm is applied to high-resolution remote sensing image segmentation. In order to solve this problem, a new method of superpixel segmentation method of high-resolution remote sensing image based on fuzzy C-means clustering is proposed in this paper. Firstly, watershed transform algorithm is used to generate multiple superpixels, and then the similarity of spectrum features among superpixels are compared. Finally, these superpixels are merged by a FCM method combined with spectrum features. Four sets of remote sensing images of different scenes were selected in the experiment, and the experimental results were evaluated by combining qualitative and quantitative methods. The experimental results show that the method can effectively improve accuracy of the segmentation and achieve better visual effect of the segmentation.

Key words: high spatial resolution remote sensing image, superpixel, image segmentation, watershed transformation, fuzzy clustering

中图分类号: