基于多尺度显著性检测的SAR图像海岸线检测

Coastline detection in SAR image based on multi-scale saliency detection

SAR图像岸线检测是SAR近岸海洋目标检测的一项重要环节。提出了一种基于多尺度显著性检测的SAR图像海岸线检测方法,用以检测低对比度SAR图像的海岸线。首先将SAR图像依据尺度系数进行多尺度变换,然后对于每种尺度图像进行谱残差法显著性检测,得到一系列显著性子图;而后应用NSCT变换融合各显著子图得到最终显著图,将显著图代入到活动轮廓模型中进行检测,得到检测结果。SAR图像实验结果表明,该方法相比于传统方法,提升了对于低对比度图像的适应性,增强了抗噪性能。

SAR image coastline detection is an important part of SAR nearshore ocean target detection.A coastline detection method for SAR images based on multi-scale saliency detection is proposed to detect the coastline of low contrast SAR images.Firstly,the SAR image is subjected to multi-scale transformation based on the scale coefficients,and then the spectral residual method is used to detect the saliency of each scale image,resulting in a series of saliency subgraphs.Then,the NSCT transform is applied to fuse each salient sub image to obtain the final salient map,which is then substituted into the active contour model for detection,and the detection result is obtained.The experimental results of SAR images show that compared to traditional methods,this method improves its adaptability to low contrast images and enhances its noise immunity.