Coastline detection in SAR images using multiscale normalized cut segmentation

Author

Xianwen Ding ; Xiaofeng Li

Author_Institution

Int. Center for Marine Studies, Shanghai Ocean Univ., Shanghai, China

fYear

2014

fDate

13-18 July 2014

Firstpage

4447

Lastpage

4449

Abstract

The multiscale normalized cut technique is used to detect land/sea boundary in synthetic aperture radar (SAR) images. The proposed method is a region-based one, which is able to capture and utilize spatial information in the image. The real SAR images, e.g. ERS, ENVISAT and COSMO-SkyMed (CSK) SAR images, together with the Landsat-7 ETM+ optical data and in-situ GPS data were collected and used to validate the performance of the proposed method for coastline detection in SAR images.

Keywords

Global Positioning System; oceanographic techniques; synthetic aperture radar; COSMO-SkyMed SAR image; CSK SAR image; ENVISAT SAR image; ERS SAR image; Landsat-7 ETM+ optical data; SAR image coastline detection; image spatial information capture; image spatial informationutilization; in-situ GPS data; land-sea boundary detection; method performance validation; multiscale normalized cut segmentation; multiscale normalized cut technique; real SAR image; region-based method; synthetic aperture radar image; Accuracy; Earth; Image segmentation; Remote sensing; Satellites; Synthetic aperture radar; Tides; SAR; coastline; image segmentation; normalized cut;

fLanguage

English

Publisher

ieee

Conference_Titel

Geoscience and Remote Sensing Symposium (IGARSS), 2014 IEEE International

Conference_Location

Quebec City, QC

Type

conf

DOI

10.1109/IGARSS.2014.6947478

Filename

6947478