Deep Learning for Detecting and Classifying Ocean Objects:Application of YoloV3 for Iceberg–Ship Discrimination
Synthetic aperture radar (SAR) plays a remarkable role in ocean surveillance, with capabilities of detecting oil spills, icebergs, and marine traffic both at daytime and at night, regardless of clouds and extreme weather conditions. The detection of ocean objects using SAR relies on well-established...
Published in: | ISPRS International Journal of Geo-Information |
---|---|
Main Authors: | , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
2020
|
Subjects: | |
Online Access: | https://vbn.aau.dk/da/publications/915899e0-3627-484f-ab61-981440c7b429 https://doi.org/10.3390/ijgi9120758 https://vbn.aau.dk/ws/files/412113933/ijgi_09_00758_v3.pdf http://www.scopus.com/inward/record.url?scp=85105179318&partnerID=8YFLogxK |
id |
ftalborgunivpubl:oai:pure.atira.dk:publications/915899e0-3627-484f-ab61-981440c7b429 |
---|---|
record_format |
openpolar |
spelling |
ftalborgunivpubl:oai:pure.atira.dk:publications/915899e0-3627-484f-ab61-981440c7b429 2024-09-15T18:02:20+00:00 Deep Learning for Detecting and Classifying Ocean Objects:Application of YoloV3 for Iceberg–Ship Discrimination Hass, Frederik Seerup Arsanjani, Jamal Jokar 2020-12 application/pdf https://vbn.aau.dk/da/publications/915899e0-3627-484f-ab61-981440c7b429 https://doi.org/10.3390/ijgi9120758 https://vbn.aau.dk/ws/files/412113933/ijgi_09_00758_v3.pdf http://www.scopus.com/inward/record.url?scp=85105179318&partnerID=8YFLogxK eng eng https://vbn.aau.dk/da/publications/915899e0-3627-484f-ab61-981440c7b429 info:eu-repo/semantics/openAccess Hass , F S & Arsanjani , J J 2020 , ' Deep Learning for Detecting and Classifying Ocean Objects : Application of YoloV3 for Iceberg–Ship Discrimination ' , ISPRS International Journal of Geo-Information , vol. 9 , no. 12 , 758 . https://doi.org/10.3390/ijgi9120758 Classification Deep learning Object detection Ocean objects Synthetic aperture radar YoloV3 article 2020 ftalborgunivpubl https://doi.org/10.3390/ijgi9120758 2024-08-15T00:20:50Z Synthetic aperture radar (SAR) plays a remarkable role in ocean surveillance, with capabilities of detecting oil spills, icebergs, and marine traffic both at daytime and at night, regardless of clouds and extreme weather conditions. The detection of ocean objects using SAR relies on well-established methods, mostly adaptive thresholding algorithms. In most waters, the dominant ocean objects are ships, whereas in arctic waters the vast majority of objects are icebergs drifting in the ocean and can be mistaken for ships in terms of navigation and ocean surveillance. Since these objects can look very much alike in SAR images, the determination of what objects actually are still relies on manual detection and human interpretation. With the increasing interest in the arctic regions for marine transportation, it is crucial to develop novel approaches for automatic monitoring of the traffic in these waters with satellite data. Hence, this study aims at proposing a deep learning model based on YoloV3 for discriminating icebergs and ships, which could be used for mapping ocean objects ahead of a journey. Using dual-polarization Sentinel-1 data, we pilot-tested our approach on a case study in Greenland. Our findings reveal that our approach is capable of training a deep learning model with reliable detection accuracy. Our methodical approach along with the choice of data and classifiers can be of great importance to climate change researchers, shipping industries and biodiversity analysts. The main difficulties were faced in the creation of training data in the Arctic waters and we concluded that future work must focus on issues regarding training data. Article in Journal/Newspaper Climate change Greenland Iceberg* Aalborg University's Research Portal ISPRS International Journal of Geo-Information 9 12 758 |
institution |
Open Polar |
collection |
Aalborg University's Research Portal |
op_collection_id |
ftalborgunivpubl |
language |
English |
topic |
Classification Deep learning Object detection Ocean objects Synthetic aperture radar YoloV3 |
spellingShingle |
Classification Deep learning Object detection Ocean objects Synthetic aperture radar YoloV3 Hass, Frederik Seerup Arsanjani, Jamal Jokar Deep Learning for Detecting and Classifying Ocean Objects:Application of YoloV3 for Iceberg–Ship Discrimination |
topic_facet |
Classification Deep learning Object detection Ocean objects Synthetic aperture radar YoloV3 |
description |
Synthetic aperture radar (SAR) plays a remarkable role in ocean surveillance, with capabilities of detecting oil spills, icebergs, and marine traffic both at daytime and at night, regardless of clouds and extreme weather conditions. The detection of ocean objects using SAR relies on well-established methods, mostly adaptive thresholding algorithms. In most waters, the dominant ocean objects are ships, whereas in arctic waters the vast majority of objects are icebergs drifting in the ocean and can be mistaken for ships in terms of navigation and ocean surveillance. Since these objects can look very much alike in SAR images, the determination of what objects actually are still relies on manual detection and human interpretation. With the increasing interest in the arctic regions for marine transportation, it is crucial to develop novel approaches for automatic monitoring of the traffic in these waters with satellite data. Hence, this study aims at proposing a deep learning model based on YoloV3 for discriminating icebergs and ships, which could be used for mapping ocean objects ahead of a journey. Using dual-polarization Sentinel-1 data, we pilot-tested our approach on a case study in Greenland. Our findings reveal that our approach is capable of training a deep learning model with reliable detection accuracy. Our methodical approach along with the choice of data and classifiers can be of great importance to climate change researchers, shipping industries and biodiversity analysts. The main difficulties were faced in the creation of training data in the Arctic waters and we concluded that future work must focus on issues regarding training data. |
format |
Article in Journal/Newspaper |
author |
Hass, Frederik Seerup Arsanjani, Jamal Jokar |
author_facet |
Hass, Frederik Seerup Arsanjani, Jamal Jokar |
author_sort |
Hass, Frederik Seerup |
title |
Deep Learning for Detecting and Classifying Ocean Objects:Application of YoloV3 for Iceberg–Ship Discrimination |
title_short |
Deep Learning for Detecting and Classifying Ocean Objects:Application of YoloV3 for Iceberg–Ship Discrimination |
title_full |
Deep Learning for Detecting and Classifying Ocean Objects:Application of YoloV3 for Iceberg–Ship Discrimination |
title_fullStr |
Deep Learning for Detecting and Classifying Ocean Objects:Application of YoloV3 for Iceberg–Ship Discrimination |
title_full_unstemmed |
Deep Learning for Detecting and Classifying Ocean Objects:Application of YoloV3 for Iceberg–Ship Discrimination |
title_sort |
deep learning for detecting and classifying ocean objects:application of yolov3 for iceberg–ship discrimination |
publishDate |
2020 |
url |
https://vbn.aau.dk/da/publications/915899e0-3627-484f-ab61-981440c7b429 https://doi.org/10.3390/ijgi9120758 https://vbn.aau.dk/ws/files/412113933/ijgi_09_00758_v3.pdf http://www.scopus.com/inward/record.url?scp=85105179318&partnerID=8YFLogxK |
genre |
Climate change Greenland Iceberg* |
genre_facet |
Climate change Greenland Iceberg* |
op_source |
Hass , F S & Arsanjani , J J 2020 , ' Deep Learning for Detecting and Classifying Ocean Objects : Application of YoloV3 for Iceberg–Ship Discrimination ' , ISPRS International Journal of Geo-Information , vol. 9 , no. 12 , 758 . https://doi.org/10.3390/ijgi9120758 |
op_relation |
https://vbn.aau.dk/da/publications/915899e0-3627-484f-ab61-981440c7b429 |
op_rights |
info:eu-repo/semantics/openAccess |
op_doi |
https://doi.org/10.3390/ijgi9120758 |
container_title |
ISPRS International Journal of Geo-Information |
container_volume |
9 |
container_issue |
12 |
container_start_page |
758 |
_version_ |
1810439801159024640 |