Superpixel Segmentation Method of High Resolution Remote Sensing Images Based on Hierarchical Clustering
投稿时间:2019-07-25  修订日期:2020-01-01  download
摘要点击次数: 181
全文下载次数: 35
黄亮 昆明理工大学 国土资源工程学院
姚丙秀 昆明理工大学 国土资源工程学院 
陈朋弟 昆明理工大学 国土资源工程学院  
任爱萍 云南云天化股份有限公司云南 昆明650093  
夏炎 昆明理工大学 国土资源工程学院  
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
  HTML  查看/发表评论  下载PDF阅读器

Copyright:《Journal of Infrared And Millimeter Waves》