融合层次聚类的高分辨率遥感影像超像素分割方法
投稿时间:2019-07-25  修订日期:2020-04-02  点此下载全文
引用本文:黄亮,姚丙秀,陈朋弟,任爱萍,夏炎.融合层次聚类的高分辨率遥感影像超像素分割方法[J].红外与毫米波学报,2020,39(2):263~272].HUANG Liang,YAO Bing-Xiu,CHEN Peng-Di,REN Ai-Ping,XIA Yan.Superpixel segmentation method of high resolution remote sensing images based on hierarchical clustering[J].J.Infrared Millim.Waves,2020,39(2):263~272.]
摘要点击次数: 166
全文下载次数: 462
作者单位E-mail
黄亮 昆明理工大学 国土资源工程学院 kmhuangliang@163.com 
姚丙秀 昆明理工大学 国土资源工程学院 1366711008@qq.com 
陈朋弟 昆明理工大学 国土资源工程学院  
任爱萍 昆明理工大学 国土资源工程学院  
夏炎 昆明理工大学 国土资源工程学院  
基金项目:国家自然科学基金 41961039;云南省应用基础研究计划面上项目 2018FB078;自然资源部经费资助项目 201911国家自然科学基金(41961039),云南省应用基础研究计划面上项目(2018FB078),自然资源部经费资助项目(201911)
中文摘要:为解决遥感影像分割尺度自动选取难的问题,提出了融合层次聚类的高分辨率遥感影像超像素分割方法。首先采用自适应形态重建的分水岭分割算法将影像分割成多个超像素;然后提取各超像素的灰度特征向量;最后利用层次聚类方法进行超像素合并,实现高分辨率遥感影像的精确分割。实验选用4组景遥感影像;采用定性和定量相结合的方法评价实验结果。实验结果表明,该方法有效提高了遥感影像分割精度,并取得了较好的分割视觉效果。
中文关键词:高空间分辨率遥感影像  超像素分割  自适应形态学重建  分水岭  层次聚类
 
Superpixel segmentation method of high resolution remote sensing images based on hierarchical clustering
Abstract:To solve the problem of automatic selection the segmentation scale in remote sensing image, a superpixel segmentation method of high resolution remote sensing image based on hierarchical clustering is proposed. Firstly, the watershed segmentation algorithm based on adaptive morphological reconstruction is used to segment the image into multiple superpixels. Then, the gray feature vectors of each superpixel is extracted. Finally, the hierarchical clustering method is adopted to merge the superpixels, the accurate segmentation of high-resolution remote sensing images is realized. Four sets of remote sensing images are selected in the experiment, and the experimental results are evaluated by a combination of qualitative and quantitative methods. Experimental results shown that the proposed method effectively improves the segmentation accuracy of remote sensing images, and better segmentation visual effects are obtained.
keywords:high spatial resolution remote sensing image  adaptive morphological reconstruction  watershed  hierarchical clustering
查看全文  HTML  查看/发表评论  下载PDF阅读器

版权所有:《红外与毫米波学报》编辑部