Ship-Iceberg Discrimination in Sentinel-2 Multispectral Imagery by Supervised Classification
The European Space Agency Sentinel-2 satellites provide multispectral images with pixel sizes down to 10 m. This high resolution allows for fast and frequent detection, classification and discrimination of various objects in the sea, which is relevant in general and specifically for the vast Arctic...
Published in: | Remote Sensing |
---|---|
Main Authors: | , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
MDPI AG
2017
|
Subjects: | |
Online Access: | https://doi.org/10.3390/rs9111156 https://doaj.org/article/3b0a67c1352c4056bc1af3915c440a0a |
id |
ftdoajarticles:oai:doaj.org/article:3b0a67c1352c4056bc1af3915c440a0a |
---|---|
record_format |
openpolar |
spelling |
ftdoajarticles:oai:doaj.org/article:3b0a67c1352c4056bc1af3915c440a0a 2023-05-15T14:55:13+02:00 Ship-Iceberg Discrimination in Sentinel-2 Multispectral Imagery by Supervised Classification Peder Heiselberg Henning Heiselberg 2017-11-01T00:00:00Z https://doi.org/10.3390/rs9111156 https://doaj.org/article/3b0a67c1352c4056bc1af3915c440a0a EN eng MDPI AG https://www.mdpi.com/2072-4292/9/11/1156 https://doaj.org/toc/2072-4292 2072-4292 doi:10.3390/rs9111156 https://doaj.org/article/3b0a67c1352c4056bc1af3915c440a0a Remote Sensing, Vol 9, Iss 11, p 1156 (2017) Sentinel-2 multispectral ship iceberg detection discrimination classification Arctic Science Q article 2017 ftdoajarticles https://doi.org/10.3390/rs9111156 2022-12-31T15:21:26Z The European Space Agency Sentinel-2 satellites provide multispectral images with pixel sizes down to 10 m. This high resolution allows for fast and frequent detection, classification and discrimination of various objects in the sea, which is relevant in general and specifically for the vast Arctic environment. We analyze several sets of multispectral image data from Denmark and Greenland fall and winter, and describe a supervised search and classification algorithm based on physical parameters that successfully finds and classifies all objects in the sea with reflectance above a threshold. It discriminates between objects like ships, islands, wakes, and icebergs, ice floes, and clouds with accuracy better than 90%. Pan-sharpening the infrared bands leads to classification and discrimination of ice floes and clouds better than 95%. For complex images with abundant ice floes or clouds, however, the false alarm rate dominates for small non-sailing boats. Article in Journal/Newspaper Arctic Greenland Iceberg* Directory of Open Access Journals: DOAJ Articles Arctic Greenland Remote Sensing 9 11 1156 |
institution |
Open Polar |
collection |
Directory of Open Access Journals: DOAJ Articles |
op_collection_id |
ftdoajarticles |
language |
English |
topic |
Sentinel-2 multispectral ship iceberg detection discrimination classification Arctic Science Q |
spellingShingle |
Sentinel-2 multispectral ship iceberg detection discrimination classification Arctic Science Q Peder Heiselberg Henning Heiselberg Ship-Iceberg Discrimination in Sentinel-2 Multispectral Imagery by Supervised Classification |
topic_facet |
Sentinel-2 multispectral ship iceberg detection discrimination classification Arctic Science Q |
description |
The European Space Agency Sentinel-2 satellites provide multispectral images with pixel sizes down to 10 m. This high resolution allows for fast and frequent detection, classification and discrimination of various objects in the sea, which is relevant in general and specifically for the vast Arctic environment. We analyze several sets of multispectral image data from Denmark and Greenland fall and winter, and describe a supervised search and classification algorithm based on physical parameters that successfully finds and classifies all objects in the sea with reflectance above a threshold. It discriminates between objects like ships, islands, wakes, and icebergs, ice floes, and clouds with accuracy better than 90%. Pan-sharpening the infrared bands leads to classification and discrimination of ice floes and clouds better than 95%. For complex images with abundant ice floes or clouds, however, the false alarm rate dominates for small non-sailing boats. |
format |
Article in Journal/Newspaper |
author |
Peder Heiselberg Henning Heiselberg |
author_facet |
Peder Heiselberg Henning Heiselberg |
author_sort |
Peder Heiselberg |
title |
Ship-Iceberg Discrimination in Sentinel-2 Multispectral Imagery by Supervised Classification |
title_short |
Ship-Iceberg Discrimination in Sentinel-2 Multispectral Imagery by Supervised Classification |
title_full |
Ship-Iceberg Discrimination in Sentinel-2 Multispectral Imagery by Supervised Classification |
title_fullStr |
Ship-Iceberg Discrimination in Sentinel-2 Multispectral Imagery by Supervised Classification |
title_full_unstemmed |
Ship-Iceberg Discrimination in Sentinel-2 Multispectral Imagery by Supervised Classification |
title_sort |
ship-iceberg discrimination in sentinel-2 multispectral imagery by supervised classification |
publisher |
MDPI AG |
publishDate |
2017 |
url |
https://doi.org/10.3390/rs9111156 https://doaj.org/article/3b0a67c1352c4056bc1af3915c440a0a |
geographic |
Arctic Greenland |
geographic_facet |
Arctic Greenland |
genre |
Arctic Greenland Iceberg* |
genre_facet |
Arctic Greenland Iceberg* |
op_source |
Remote Sensing, Vol 9, Iss 11, p 1156 (2017) |
op_relation |
https://www.mdpi.com/2072-4292/9/11/1156 https://doaj.org/toc/2072-4292 2072-4292 doi:10.3390/rs9111156 https://doaj.org/article/3b0a67c1352c4056bc1af3915c440a0a |
op_doi |
https://doi.org/10.3390/rs9111156 |
container_title |
Remote Sensing |
container_volume |
9 |
container_issue |
11 |
container_start_page |
1156 |
_version_ |
1766326997281144832 |