Ocean feature extraction from SAR Quicklook Imagery using Convolutional Neural Networks
We used a large dataset of Sentinel-1 and TerraSAR-X quicklook images downloaded from the internet in order to classify the imagery into different classes of subscenes including: open ocean, land, sea ice and ships using Convolutional Neural Network (CNN) classifiers. We construct a training dataset...
Main Authors: | , , |
---|---|
Format: | Conference Object |
Language: | German |
Published: |
2018
|
Subjects: | |
Online Access: | https://elib.dlr.de/117706/ https://elib.dlr.de/117706/1/hashemi_1570417418.pdf |
id |
ftdlr:oai:elib.dlr.de:117706 |
---|---|
record_format |
openpolar |
spelling |
ftdlr:oai:elib.dlr.de:117706 2024-05-19T07:48:21+00:00 Ocean feature extraction from SAR Quicklook Imagery using Convolutional Neural Networks Hashemi, M. Rabus, B. Lehner, Susanne 2018-06 application/pdf https://elib.dlr.de/117706/ https://elib.dlr.de/117706/1/hashemi_1570417418.pdf de ger https://elib.dlr.de/117706/1/hashemi_1570417418.pdf Hashemi, M. und Rabus, B. und Lehner, Susanne (2018) Ocean feature extraction from SAR Quicklook Imagery using Convolutional Neural Networks. EUSAR 2018, 2018-06-04 - 2018-06-07, Aachen, Deutschland. Photogrammetrie und Bildanalyse Konferenzbeitrag PeerReviewed 2018 ftdlr 2024-04-25T00:44:08Z We used a large dataset of Sentinel-1 and TerraSAR-X quicklook images downloaded from the internet in order to classify the imagery into different classes of subscenes including: open ocean, land, sea ice and ships using Convolutional Neural Network (CNN) classifiers. We construct a training dataset of subscenes of the images using visual inspection and AIS data. We then focused on the open ocean scenes acquired under different environmental conditions to classify them into different wind speed and sea state categories. We compare the results to wind speed, sea state model results and NOAA buoy measurements. In order to find the subscenes containing ships, icebergs and oil slicks we further utilize the CNN over open ocean and coastal SAR scenes. Statistics on validation is given using categorical cross entropy loss. In addition several high resolution images are used in order to test the performance of the trained Convolutional Neural Network. This study will help to retrieve such images relevant to maritime investigations of ships, oil and environmental parameters using big data methods. Conference Object Sea ice German Aerospace Center: elib - DLR electronic library |
institution |
Open Polar |
collection |
German Aerospace Center: elib - DLR electronic library |
op_collection_id |
ftdlr |
language |
German |
topic |
Photogrammetrie und Bildanalyse |
spellingShingle |
Photogrammetrie und Bildanalyse Hashemi, M. Rabus, B. Lehner, Susanne Ocean feature extraction from SAR Quicklook Imagery using Convolutional Neural Networks |
topic_facet |
Photogrammetrie und Bildanalyse |
description |
We used a large dataset of Sentinel-1 and TerraSAR-X quicklook images downloaded from the internet in order to classify the imagery into different classes of subscenes including: open ocean, land, sea ice and ships using Convolutional Neural Network (CNN) classifiers. We construct a training dataset of subscenes of the images using visual inspection and AIS data. We then focused on the open ocean scenes acquired under different environmental conditions to classify them into different wind speed and sea state categories. We compare the results to wind speed, sea state model results and NOAA buoy measurements. In order to find the subscenes containing ships, icebergs and oil slicks we further utilize the CNN over open ocean and coastal SAR scenes. Statistics on validation is given using categorical cross entropy loss. In addition several high resolution images are used in order to test the performance of the trained Convolutional Neural Network. This study will help to retrieve such images relevant to maritime investigations of ships, oil and environmental parameters using big data methods. |
format |
Conference Object |
author |
Hashemi, M. Rabus, B. Lehner, Susanne |
author_facet |
Hashemi, M. Rabus, B. Lehner, Susanne |
author_sort |
Hashemi, M. |
title |
Ocean feature extraction from SAR Quicklook Imagery using Convolutional Neural Networks |
title_short |
Ocean feature extraction from SAR Quicklook Imagery using Convolutional Neural Networks |
title_full |
Ocean feature extraction from SAR Quicklook Imagery using Convolutional Neural Networks |
title_fullStr |
Ocean feature extraction from SAR Quicklook Imagery using Convolutional Neural Networks |
title_full_unstemmed |
Ocean feature extraction from SAR Quicklook Imagery using Convolutional Neural Networks |
title_sort |
ocean feature extraction from sar quicklook imagery using convolutional neural networks |
publishDate |
2018 |
url |
https://elib.dlr.de/117706/ https://elib.dlr.de/117706/1/hashemi_1570417418.pdf |
genre |
Sea ice |
genre_facet |
Sea ice |
op_relation |
https://elib.dlr.de/117706/1/hashemi_1570417418.pdf Hashemi, M. und Rabus, B. und Lehner, Susanne (2018) Ocean feature extraction from SAR Quicklook Imagery using Convolutional Neural Networks. EUSAR 2018, 2018-06-04 - 2018-06-07, Aachen, Deutschland. |
_version_ |
1799466567317061632 |