Vessel Detection from Optical Remote Sensing Images with Deep Learning Methods

Furkan Buyukkanber; Mustafa Yanalak; Nebiye Musaoglu

doi:10.1109/RAST57548.2023.10197948

Vessel Detection from Optical Remote Sensing Images with Deep Learning Methods

Furkan Buyukkanber
, Mustafa Yanalak
, Nebiye Musaoglu

Department of Geomatics Engineering

Istanbul Technical University

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

7 Citations (Scopus)

Abstract

Vessel detection from remote sensing images is becoming exponentially crucial component in marine surveillance applications including maritime traffic control, anti-illegal fishing applications, oil discharge control, marine pollution and safety. Applying deep learning methods to vessel detection applications ineluctably improve the detection results and overcome unforeseen errors that could be made by analysts. Publicly available datasets play vital role for development and evaluation process of deep learning models. In this paper, open source DOTA dataset has been revised and trained with single-staged deep learning methods. The results show that YOLOv8 model has the most efficient value on detecting ships and fastest to detect instances from given test images on inference.

Original language	English
Title of host publication	Proceedings of 10th International Conference on Recent Advances in Air and Space Technologies, RAST 2023
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9798350323023
DOIs	https://doi.org/10.1109/RAST57548.2023.10197948
Publication status	Published - 2023
Event	10th International Conference on Recent Advances in Air and Space Technologies, RAST 2023 - Istanbul, Turkey Duration: 7 Jun 2023 → 9 Jun 2023

Publication series

Name	Proceedings of 10th International Conference on Recent Advances in Air and Space Technologies, RAST 2023

Conference

Conference	10th International Conference on Recent Advances in Air and Space Technologies, RAST 2023
Country/Territory	Turkey
City	Istanbul
Period	7/06/23 → 9/06/23

Bibliographical note

Publisher Copyright:
© 2023 IEEE.

Funding

We would like to express our sincere thanks to Istanbul Technical University Center for Satellite Communication and Remote Sensing (ITU-CSCRS) for the support given.

Funders
Istanbul Technical University Center for Satellite Communication and Remote Sensing

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 14 Life Below Water

Keywords

YOLO series
convolutional neural networks
deep learning
optical remote sensing images
ship dataset
vessel detection

Access to Document

10.1109/RAST57548.2023.10197948

Cite this

Buyukkanber, F., Yanalak, M., & Musaoglu, N. (2023). Vessel Detection from Optical Remote Sensing Images with Deep Learning Methods. In Proceedings of 10th International Conference on Recent Advances in Air and Space Technologies, RAST 2023 (Proceedings of 10th International Conference on Recent Advances in Air and Space Technologies, RAST 2023). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/RAST57548.2023.10197948

Buyukkanber, Furkan ; Yanalak, Mustafa ; Musaoglu, Nebiye. / Vessel Detection from Optical Remote Sensing Images with Deep Learning Methods. Proceedings of 10th International Conference on Recent Advances in Air and Space Technologies, RAST 2023. Institute of Electrical and Electronics Engineers Inc., 2023. (Proceedings of 10th International Conference on Recent Advances in Air and Space Technologies, RAST 2023).

@inproceedings{58d749f59e5e4e678a8c180a39428089,

title = "Vessel Detection from Optical Remote Sensing Images with Deep Learning Methods",

abstract = "Vessel detection from remote sensing images is becoming exponentially crucial component in marine surveillance applications including maritime traffic control, anti-illegal fishing applications, oil discharge control, marine pollution and safety. Applying deep learning methods to vessel detection applications ineluctably improve the detection results and overcome unforeseen errors that could be made by analysts. Publicly available datasets play vital role for development and evaluation process of deep learning models. In this paper, open source DOTA dataset has been revised and trained with single-staged deep learning methods. The results show that YOLOv8 model has the most efficient value on detecting ships and fastest to detect instances from given test images on inference.",

keywords = "YOLO series, convolutional neural networks, deep learning, optical remote sensing images, ship dataset, vessel detection",

author = "Furkan Buyukkanber and Mustafa Yanalak and Nebiye Musaoglu",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 10th International Conference on Recent Advances in Air and Space Technologies, RAST 2023 ; Conference date: 07-06-2023 Through 09-06-2023",

year = "2023",

doi = "10.1109/RAST57548.2023.10197948",

language = "English",

series = "Proceedings of 10th International Conference on Recent Advances in Air and Space Technologies, RAST 2023",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "Proceedings of 10th International Conference on Recent Advances in Air and Space Technologies, RAST 2023",

address = "United States",

}

Buyukkanber, F, Yanalak, M & Musaoglu, N 2023, Vessel Detection from Optical Remote Sensing Images with Deep Learning Methods. in Proceedings of 10th International Conference on Recent Advances in Air and Space Technologies, RAST 2023. Proceedings of 10th International Conference on Recent Advances in Air and Space Technologies, RAST 2023, Institute of Electrical and Electronics Engineers Inc., 10th International Conference on Recent Advances in Air and Space Technologies, RAST 2023, Istanbul, Turkey, 7/06/23. https://doi.org/10.1109/RAST57548.2023.10197948

Vessel Detection from Optical Remote Sensing Images with Deep Learning Methods. / Buyukkanber, Furkan; Yanalak, Mustafa ; Musaoglu, Nebiye.
Proceedings of 10th International Conference on Recent Advances in Air and Space Technologies, RAST 2023. Institute of Electrical and Electronics Engineers Inc., 2023. (Proceedings of 10th International Conference on Recent Advances in Air and Space Technologies, RAST 2023).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Vessel Detection from Optical Remote Sensing Images with Deep Learning Methods

AU - Buyukkanber, Furkan

AU - Yanalak, Mustafa

AU - Musaoglu, Nebiye

PY - 2023

Y1 - 2023

N2 - Vessel detection from remote sensing images is becoming exponentially crucial component in marine surveillance applications including maritime traffic control, anti-illegal fishing applications, oil discharge control, marine pollution and safety. Applying deep learning methods to vessel detection applications ineluctably improve the detection results and overcome unforeseen errors that could be made by analysts. Publicly available datasets play vital role for development and evaluation process of deep learning models. In this paper, open source DOTA dataset has been revised and trained with single-staged deep learning methods. The results show that YOLOv8 model has the most efficient value on detecting ships and fastest to detect instances from given test images on inference.

AB - Vessel detection from remote sensing images is becoming exponentially crucial component in marine surveillance applications including maritime traffic control, anti-illegal fishing applications, oil discharge control, marine pollution and safety. Applying deep learning methods to vessel detection applications ineluctably improve the detection results and overcome unforeseen errors that could be made by analysts. Publicly available datasets play vital role for development and evaluation process of deep learning models. In this paper, open source DOTA dataset has been revised and trained with single-staged deep learning methods. The results show that YOLOv8 model has the most efficient value on detecting ships and fastest to detect instances from given test images on inference.

KW - YOLO series

KW - convolutional neural networks

KW - deep learning

KW - optical remote sensing images

KW - ship dataset

KW - vessel detection

UR - https://www.scopus.com/pages/publications/85168413254

U2 - 10.1109/RAST57548.2023.10197948

DO - 10.1109/RAST57548.2023.10197948

M3 - Conference contribution

AN - SCOPUS:85168413254

T3 - Proceedings of 10th International Conference on Recent Advances in Air and Space Technologies, RAST 2023

BT - Proceedings of 10th International Conference on Recent Advances in Air and Space Technologies, RAST 2023

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 10th International Conference on Recent Advances in Air and Space Technologies, RAST 2023

Y2 - 7 June 2023 through 9 June 2023

ER -

Buyukkanber F, Yanalak M , Musaoglu N. Vessel Detection from Optical Remote Sensing Images with Deep Learning Methods. In Proceedings of 10th International Conference on Recent Advances in Air and Space Technologies, RAST 2023. Institute of Electrical and Electronics Engineers Inc. 2023. (Proceedings of 10th International Conference on Recent Advances in Air and Space Technologies, RAST 2023). doi: 10.1109/RAST57548.2023.10197948

Vessel Detection from Optical Remote Sensing Images with Deep Learning Methods

Abstract

Publication series

Conference

Bibliographical note

Funding

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this