4.7 Article

SAR Image Segmentation Using Region Smoothing and Label Correction

期刊

REMOTE SENSING
卷 12, 期 5, 页码 -

出版社

MDPI
DOI: 10.3390/rs12050803

关键词

synthetic aperture radar (SAR); image segmentation; region smoothing; majority voting; K-means

资金

  1. National Natural Science Foundation of China [61773304, 61836009, 61871306, 61772399, U1701267]
  2. Fund for Foreign Scholars in University Research and Teaching Programs (the 111 Project) [B07048]
  3. Program for Cheung Kong Scholars and Innovative Research Team in University [IRT1170]

向作者/读者索取更多资源

The traditional unsupervised image segmentation methods are widely used in synthetic aperture radar (SAR) image segmentation due to the simple and convenient application process. In order to solve the time-consuming problem of the common methods, an SAR image segmentation method using region smoothing and label correction (RSLC) is proposed. In this algorithm, the image smoothing results are used to approximate the results of the spatial information polynomials of the image. Thus, the segmentation process can be realized quickly and effectively. Firstly, direction templates are used to detect the directions at different coordinates of the image, and smoothing templates are used to smooth the edge regions according to the directions. It achieves the smoothing of the edge regions and the retention of the edge information. Then the homogeneous regions are presented indirectly according to the difference of directions. The homogeneous regions are smoothed by using isotropic operators. Finally, the two regions are fused for K-means clustering. The majority voting algorithm is used to modify the clustering results, and the final segmentation results are obtained. Experimental results on simulated SAR images and real SAR images show that the proposed algorithm outperforms the other five state-of-the-art algorithms in segmentation speed and accuracy.

作者

我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。

评论

主要评分

4.7
评分不足

次要评分

新颖性
-
重要性
-
科学严谨性
-
评价这篇论文

推荐

暂无数据
暂无数据