A Novel Ship-Detection Technique for Sentinel-1 SAR Data

P Iervolino; R Guida; P Whittaker

doi:10.1109/APSAR.2015.7306324

Back

A Novel Ship-Detection Technique for Sentinel-1 SAR Data

Conference presentation

Peer reviewed

A Novel Ship-Detection Technique for Sentinel-1 SAR Data

P Iervolino, R Guida and P Whittaker

Proceedings of 2015 IEEE 5th Asia-Pacific Conference on Synthetic Aperture Radar (APSAR), pp.797-801

APSAR 2015 (2015 IEEE 5th Asia-Pacific Conference on Synthetic Aperture Radar) (Marina Bay Sands, Singapore, 01/09/2015 - 04/09/2015)

30/09/2015

DOI: https://doi.org/10.1109/APSAR.2015.7306324

Abstract

CFAR

Synthetic Aperture Radar (SAR)

Sentinel-1 ship detection

Ship-detection

GLRT

Electronic Engineering

The paper shows a novel algorithm for ship-detection in Synthetic Aperture Radar (SAR) imagery. The algorithm is divided in three main steps: land mask rejection, detection and discrimination. In the first step land pixels are rejected by using Shuttle Radar Topography Mission (SRTM) data; in the second stage the potential ships are detected on a method based on the Generalized Likelihood Ratio Test (GLRT) and, finally, some targets are rejected by removing the azimuth ambiguities and by gathering the target pixels in clusters. The algorithm is tested on a Sentinel-1 image acquired over the Portsmouth harbour and compared with the outcomes coming from a Constant False Alarm Algorithm (CFAR).

Metrics

75 Record Views

Details

Title: A Novel Ship-Detection Technique for Sentinel-1 SAR Data
Creators: P Iervolino
R Guida
P Whittaker
Publication Details: Proceedings of 2015 IEEE 5th Asia-Pacific Conference on Synthetic Aperture Radar (APSAR), pp.797-801
Conference: APSAR 2015 (2015 IEEE 5th Asia-Pacific Conference on Synthetic Aperture Radar) (Marina Bay Sands, Singapore, 01/09/2015 - 04/09/2015)
Date published: 30/09/2015
Date submitted: 19/09/2016
Grant note: Funder: Engineering and Physical Science Research Council (EPSRC) | Grant ID: EP/J502224
Identifiers: 99511905302346
Academic Unit: School of Computer Science and Electronic Engineering; School of Computer Science and Electronic Engineering
Resource Type: Conference presentation

A Novel Ship-Detection Technique for Sentinel-1 SAR Data

Abstract

Metrics

Details

Usage Policy