基于SLIC超像素分割的SAR图像海陆分割算法

发布时间：2018-03-27 23:27

本文选题：海陆分割　切入点：合成孔径雷达图像　出处：《雷达科学与技术》2017年04期

【摘要】：海陆分割在合成孔径雷达(SAR)图像的海面目标检测以及海岸线提取等海洋应用方面具有非常重要的意义。针对合成孔径雷达图像的特点,提出了基于SLIC超像素分割的SAR图像海陆分割算法。首先为抑制SAR图像固有相干斑噪声并较好地保留图像的边缘信息,采用精致Lee滤波对图像进行预处理。然后对图像进行SLIC超像素分割,再将分割后的图像进行FT区域显著性检测以及显著值相似度聚类。最后将处理后的图片二值化得到海陆分割结果。实验结果表明,本文所提海陆分割算法具有很高的处理精度以及较高的处理效率。
[Abstract]:Land and sea segmentation plays an important role in sea surface target detection and shoreline extraction of synthetic Aperture Radar (SAR) images, aiming at the characteristics of synthetic Aperture Radar (SAR) images. In this paper, a SAR image segmentation algorithm based on SLIC super-pixel segmentation is proposed. Firstly, in order to suppress the inherent speckle noise of SAR image and preserve the edge information of the image, a new algorithm is proposed. The fine Lee filter is used to preprocess the image. Then the image is segmented by SLIC super-pixel. Then the segmentation image is detected by FT region significance detection and significant value similarity clustering. Finally, the processed image is binarized to get the result of land and sea segmentation. The experimental results show that, The algorithm proposed in this paper has high processing accuracy and high processing efficiency.
【作者单位】：海军航空工程学院电子信息工程系;
【分类号】：TN957.52

【相似文献】