Automated marine oil spill detection using deep learning instance segmentation model
This study developed a novel deep learning oil spill instance segmentation model using Mask-Region-based Convolutional Neural Network (Mask R-CNN) model which is a state-of-the-art computer vision model. A total of 2882 imageries containing oil spill, look-alike, ship, and land area after conducting...
Saved in:
Main Authors: | , |
---|---|
Format: | Conference or Workshop Item |
Published: |
International Society for Photogrammetry and Remote Sensing
2020
|
Online Access: | https://www.scopus.com/inward/record.uri?eid=2-s2.0-85091137521&doi=10.5194%2fisprs-archives-XLIII-B3-2020-1271-2020&partnerID=40&md5=4c78a479f05be1034fa1109e27c175ca http://eprints.utp.edu.my/30064/ |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
id |
my.utp.eprints.30064 |
---|---|
record_format |
eprints |
spelling |
my.utp.eprints.300642022-03-25T03:23:08Z Automated marine oil spill detection using deep learning instance segmentation model Yekeen, S.T. Balogun, A.-L. This study developed a novel deep learning oil spill instance segmentation model using Mask-Region-based Convolutional Neural Network (Mask R-CNN) model which is a state-of-the-art computer vision model. A total of 2882 imageries containing oil spill, look-alike, ship, and land area after conducting different pre-processing activities were acquired. These images were subsequently sub-divided into 88 training and 12 for testing, equating to 2530 and 352 images respectively. The model training was conducted using transfer learning on a pre-trained ResNet 101 with COCO data as a backbone in combination with Feature Pyramid Network (FPN) architecture for the extraction of features at 30 epochs with 0.001 learning rate. The model's performance was evaluated using precision, recall, and F1-measure which shows a higher performance than other existing models with value of 0.964, 0.969 and 0.968 respectively. As a specialized task, the study concluded that the developed deep learning instance segmentation model (Mask R-CNN) performs better than conventional machine learning models and semantic segmentation deep learning models in detection and segmentation of marine oil spill. © 2020 International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives. International Society for Photogrammetry and Remote Sensing 2020 Conference or Workshop Item NonPeerReviewed https://www.scopus.com/inward/record.uri?eid=2-s2.0-85091137521&doi=10.5194%2fisprs-archives-XLIII-B3-2020-1271-2020&partnerID=40&md5=4c78a479f05be1034fa1109e27c175ca Yekeen, S.T. and Balogun, A.-L. (2020) Automated marine oil spill detection using deep learning instance segmentation model. In: UNSPECIFIED. http://eprints.utp.edu.my/30064/ |
institution |
Universiti Teknologi Petronas |
building |
UTP Resource Centre |
collection |
Institutional Repository |
continent |
Asia |
country |
Malaysia |
content_provider |
Universiti Teknologi Petronas |
content_source |
UTP Institutional Repository |
url_provider |
http://eprints.utp.edu.my/ |
description |
This study developed a novel deep learning oil spill instance segmentation model using Mask-Region-based Convolutional Neural Network (Mask R-CNN) model which is a state-of-the-art computer vision model. A total of 2882 imageries containing oil spill, look-alike, ship, and land area after conducting different pre-processing activities were acquired. These images were subsequently sub-divided into 88 training and 12 for testing, equating to 2530 and 352 images respectively. The model training was conducted using transfer learning on a pre-trained ResNet 101 with COCO data as a backbone in combination with Feature Pyramid Network (FPN) architecture for the extraction of features at 30 epochs with 0.001 learning rate. The model's performance was evaluated using precision, recall, and F1-measure which shows a higher performance than other existing models with value of 0.964, 0.969 and 0.968 respectively. As a specialized task, the study concluded that the developed deep learning instance segmentation model (Mask R-CNN) performs better than conventional machine learning models and semantic segmentation deep learning models in detection and segmentation of marine oil spill. © 2020 International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives. |
format |
Conference or Workshop Item |
author |
Yekeen, S.T. Balogun, A.-L. |
spellingShingle |
Yekeen, S.T. Balogun, A.-L. Automated marine oil spill detection using deep learning instance segmentation model |
author_facet |
Yekeen, S.T. Balogun, A.-L. |
author_sort |
Yekeen, S.T. |
title |
Automated marine oil spill detection using deep learning instance segmentation model |
title_short |
Automated marine oil spill detection using deep learning instance segmentation model |
title_full |
Automated marine oil spill detection using deep learning instance segmentation model |
title_fullStr |
Automated marine oil spill detection using deep learning instance segmentation model |
title_full_unstemmed |
Automated marine oil spill detection using deep learning instance segmentation model |
title_sort |
automated marine oil spill detection using deep learning instance segmentation model |
publisher |
International Society for Photogrammetry and Remote Sensing |
publishDate |
2020 |
url |
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85091137521&doi=10.5194%2fisprs-archives-XLIII-B3-2020-1271-2020&partnerID=40&md5=4c78a479f05be1034fa1109e27c175ca http://eprints.utp.edu.my/30064/ |
_version_ |
1738657054775574528 |
score |
13.214268 |