Ship-Iceberg Detection & Classification in Sentinel-1 SAR Images

H. Heiselberg*

*Corresponding author for this work

Research output: Contribution to conferencePaperResearchpeer-review

52 Downloads (Pure)

Abstract

The European Space Agency Sentinel-1 satellites provide good resolution all weather SAR images. We describe algorithms for detection and classification of ships, icebergs and other objects at sea. Sidelobes from strongly reflecting objects as large ships are suppressed for better determination of ship parameters. The resulting improved ship lengths and breadths are larger than the ground truth values known from Automatic Identification System (AIS) data due to the limited resolution in the processing of the SAR images as compared to previous analyses of Sentinel-2 optical images. The limited resolution in SAR imagery degrades spatial classification algorithms but it is found that the backscatter horizontal and vertical polarizations can be exploited to distinguish icebergs in the Arctic from large ships but not small boats or wakes.
Original languageEnglish
Publication date2019
Number of pages6
Publication statusPublished - 2019
Event13th International Conference on Marine Navigation and Safety of Sea Transportation - Gdynia, Poland
Duration: 12 Jun 201914 Jun 2019
Conference number: 13

Conference

Conference13th International Conference on Marine Navigation and Safety of Sea Transportation
Number13
CountryPoland
CityGdynia
Period12/06/201914/06/2019

Keywords

  • Sentinel-1
  • SAR
  • Ship detection
  • Ship lengths
  • Icebergs

Cite this

Heiselberg, H. (2019). Ship-Iceberg Detection & Classification in Sentinel-1 SAR Images. Paper presented at 13th International Conference on Marine Navigation and Safety of Sea Transportation, Gdynia, Poland.
Heiselberg, H. / Ship-Iceberg Detection & Classification in Sentinel-1 SAR Images. Paper presented at 13th International Conference on Marine Navigation and Safety of Sea Transportation, Gdynia, Poland.6 p.
@conference{ce614eaf3fa946109d4c55cb7da821b2,
title = "Ship-Iceberg Detection & Classification in Sentinel-1 SAR Images",
abstract = "The European Space Agency Sentinel-1 satellites provide good resolution all weather SAR images. We describe algorithms for detection and classification of ships, icebergs and other objects at sea. Sidelobes from strongly reflecting objects as large ships are suppressed for better determination of ship parameters. The resulting improved ship lengths and breadths are larger than the ground truth values known from Automatic Identification System (AIS) data due to the limited resolution in the processing of the SAR images as compared to previous analyses of Sentinel-2 optical images. The limited resolution in SAR imagery degrades spatial classification algorithms but it is found that the backscatter horizontal and vertical polarizations can be exploited to distinguish icebergs in the Arctic from large ships but not small boats or wakes.",
keywords = "Sentinel-1, SAR, Ship detection, Ship lengths, Icebergs",
author = "H. Heiselberg",
year = "2019",
language = "English",
note = "13th International Conference on Marine Navigation and Safety of Sea Transportation, TransNav 2019 ; Conference date: 12-06-2019 Through 14-06-2019",

}

Heiselberg, H 2019, 'Ship-Iceberg Detection & Classification in Sentinel-1 SAR Images' Paper presented at 13th International Conference on Marine Navigation and Safety of Sea Transportation, Gdynia, Poland, 12/06/2019 - 14/06/2019, .

Ship-Iceberg Detection & Classification in Sentinel-1 SAR Images. / Heiselberg, H.

2019. Paper presented at 13th International Conference on Marine Navigation and Safety of Sea Transportation, Gdynia, Poland.

Research output: Contribution to conferencePaperResearchpeer-review

TY - CONF

T1 - Ship-Iceberg Detection & Classification in Sentinel-1 SAR Images

AU - Heiselberg, H.

PY - 2019

Y1 - 2019

N2 - The European Space Agency Sentinel-1 satellites provide good resolution all weather SAR images. We describe algorithms for detection and classification of ships, icebergs and other objects at sea. Sidelobes from strongly reflecting objects as large ships are suppressed for better determination of ship parameters. The resulting improved ship lengths and breadths are larger than the ground truth values known from Automatic Identification System (AIS) data due to the limited resolution in the processing of the SAR images as compared to previous analyses of Sentinel-2 optical images. The limited resolution in SAR imagery degrades spatial classification algorithms but it is found that the backscatter horizontal and vertical polarizations can be exploited to distinguish icebergs in the Arctic from large ships but not small boats or wakes.

AB - The European Space Agency Sentinel-1 satellites provide good resolution all weather SAR images. We describe algorithms for detection and classification of ships, icebergs and other objects at sea. Sidelobes from strongly reflecting objects as large ships are suppressed for better determination of ship parameters. The resulting improved ship lengths and breadths are larger than the ground truth values known from Automatic Identification System (AIS) data due to the limited resolution in the processing of the SAR images as compared to previous analyses of Sentinel-2 optical images. The limited resolution in SAR imagery degrades spatial classification algorithms but it is found that the backscatter horizontal and vertical polarizations can be exploited to distinguish icebergs in the Arctic from large ships but not small boats or wakes.

KW - Sentinel-1

KW - SAR

KW - Ship detection

KW - Ship lengths

KW - Icebergs

M3 - Paper

ER -

Heiselberg H. Ship-Iceberg Detection & Classification in Sentinel-1 SAR Images. 2019. Paper presented at 13th International Conference on Marine Navigation and Safety of Sea Transportation, Gdynia, Poland.