基于SLIC超像素分割的SAR图像海陆分割算法  

A Sea-Land Segmentation Algorithm of SAR Image Based on the SLIC Superpixel Division

作　　者：李智[1] 曲长文[1] 周强[1] 刘晨[1] 

机构地区：[1]海军航空工程学院电子信息工程系,山东烟台264001

出　　处：《雷达科学与技术》2017年第4期354-358,共5页Radar Science and Technology

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。The sea-land segmentation of SAR image is important in the marine applications,such as target detection,coastline extraction,etc.According to the characteristics of SAR image,a sea-land segmentation algorithm of SAR image based on the SLIC superpixel division is put forward.First,the delicate Lee filter is used for image preprocessing to suppress coherent noise and to retain the image edge information.Then,the SLIC superpixel division is used to process the images.The divided images are experienced FT regional significance tests and significant value similarity clustering.Finally,the binary conversion is performed on the processed images to get the sea-land segmentation results.The experiment results show that the proposed algorithm has high processing precision and quick processing speed.

关 键 词：海陆分割 合成孔径雷达图像 SLIC超像素分割 FT区域显著性检测 显著值相似度聚类 图像二值化 

分 类 号：TN957.52[电子电信—信号与信息处理]