Coastline detection in SAR images using discriminant cuts segmentation

6th Digital Earth Summit

地球科学;计算机科学

Ding, Xianwen^1 ; Zou, Xiaolin^2 ; Yu, Tan^1

College of Marine Sciences, Shanghai Ocean University, Shanghai

201306, China^1

School of Mathematics and Statistics, Zhaoqing University, Zhaoqing

526061, China^2

关键词: Coastline detections;    Cosmo skymed;    GPS data;    Region-based;    SAR Images;    Spatial informations;    Synthetic aperture radar (SAR) images;   

Others  :  https://iopscience.iop.org/article/10.1088/1755-1315/46/1/012035/pdf
DOI  :  10.1088/1755-1315/46/1/012035

学科分类：计算机科学（综合）

来源: IOP

【 摘 要 】

The discriminant cut algorithm is used to detect coastlines in synthetic aperture radar (SAR) images. The proposed approach is a region-based one, which is able to capture and utilize spatial information in the image. The real SAR images, e.g. ALOS-1 PALSAR and COSMO-SkyMed SAR images, together with in-situ GPS data were collected and used to validate the performance of the proposed approach for coastline detection in SAR images. The accuracy is better than 4 times the image resolution. The efficiency is also tested.