Ship detection from optical satellite images with deep learning

Mesut Kartal; Osman Duman

doi:10.1109/RAST.2019.8767844

Ship detection from optical satellite images with deep learning

Mesut Kartal, Osman Duman

Department of Electronics and Communication Engineering

Istanbul Technical University

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

14 Citations (Scopus)

Abstract

The effective use and control of maritime routes in the commercial/military area is an increasing and important need for states. There are some motivations for this purpose: Safe traffic of the ships in narrow canals, avoiding illegal usage of anchoring areas of ships, monitoring fishing activities to avoid illegal fishing or protect fish population, detection of lost ships, boats or debris in the ocean, detection and identification of warships (intelligence, defense, offensive, etc.). This paper proposed an open source, fast running ship detection system from optical satellite images with the deep learning algorithm. The system does not need any comprehensive hardware, even can work on an average laptop. Tensorflow Object Detection Application Programming Interface (API)is trained by optical satellite images with ships and used as object detection API.

Original language	English
Title of host publication	Proceedings of 9th International Conference on Recent Advances in Space Technologies, RAST 2019
Editors	S. Menekay, O. Cetin, O. Alparslan
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	479-484
Number of pages	6
ISBN (Electronic)	9781538694480
DOIs	https://doi.org/10.1109/RAST.2019.8767844
Publication status	Published - Jun 2019
Event	9th International Conference on Recent Advances in Space Technologies, RAST 2019 - Istanbul, Turkey Duration: 11 Jun 2019 → 14 Jun 2019

Publication series

Name	Proceedings of 9th International Conference on Recent Advances in Space Technologies, RAST 2019

Conference

Conference	9th International Conference on Recent Advances in Space Technologies, RAST 2019
Country/Territory	Turkey
City	Istanbul
Period	11/06/19 → 14/06/19

Bibliographical note

Publisher Copyright:
© 2019 IEEE.

Keywords

artificial neural networks
deep learning
optical satellite image
python
ship detection
tensorflow

Access to Document

10.1109/RAST.2019.8767844

Cite this

Kartal, M., & Duman, O. (2019). Ship detection from optical satellite images with deep learning. In S. Menekay, O. Cetin, & O. Alparslan (Eds.), Proceedings of 9th International Conference on Recent Advances in Space Technologies, RAST 2019 (pp. 479-484). Article 8767844 (Proceedings of 9th International Conference on Recent Advances in Space Technologies, RAST 2019). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/RAST.2019.8767844

Kartal, Mesut ; Duman, Osman. / Ship detection from optical satellite images with deep learning. Proceedings of 9th International Conference on Recent Advances in Space Technologies, RAST 2019. editor / S. Menekay ; O. Cetin ; O. Alparslan. Institute of Electrical and Electronics Engineers Inc., 2019. pp. 479-484 (Proceedings of 9th International Conference on Recent Advances in Space Technologies, RAST 2019).

@inproceedings{a6cbf4c09af64e3db1e889c3d40e4805,

title = "Ship detection from optical satellite images with deep learning",

abstract = "The effective use and control of maritime routes in the commercial/military area is an increasing and important need for states. There are some motivations for this purpose: Safe traffic of the ships in narrow canals, avoiding illegal usage of anchoring areas of ships, monitoring fishing activities to avoid illegal fishing or protect fish population, detection of lost ships, boats or debris in the ocean, detection and identification of warships (intelligence, defense, offensive, etc.). This paper proposed an open source, fast running ship detection system from optical satellite images with the deep learning algorithm. The system does not need any comprehensive hardware, even can work on an average laptop. Tensorflow Object Detection Application Programming Interface (API)is trained by optical satellite images with ships and used as object detection API.",

keywords = "artificial neural networks, deep learning, optical satellite image, python, ship detection, tensorflow",

author = "Mesut Kartal and Osman Duman",

note = "Publisher Copyright: {\textcopyright} 2019 IEEE.; 9th International Conference on Recent Advances in Space Technologies, RAST 2019 ; Conference date: 11-06-2019 Through 14-06-2019",

year = "2019",

month = jun,

doi = "10.1109/RAST.2019.8767844",

language = "English",

series = "Proceedings of 9th International Conference on Recent Advances in Space Technologies, RAST 2019",

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

pages = "479--484",

editor = "S. Menekay and O. Cetin and O. Alparslan",

booktitle = "Proceedings of 9th International Conference on Recent Advances in Space Technologies, RAST 2019",

address = "United States",

}

Kartal, M & Duman, O 2019, Ship detection from optical satellite images with deep learning. in S Menekay, O Cetin & O Alparslan (eds), Proceedings of 9th International Conference on Recent Advances in Space Technologies, RAST 2019., 8767844, Proceedings of 9th International Conference on Recent Advances in Space Technologies, RAST 2019, Institute of Electrical and Electronics Engineers Inc., pp. 479-484, 9th International Conference on Recent Advances in Space Technologies, RAST 2019, Istanbul, Turkey, 11/06/19. https://doi.org/10.1109/RAST.2019.8767844

Ship detection from optical satellite images with deep learning. / Kartal, Mesut; Duman, Osman.
Proceedings of 9th International Conference on Recent Advances in Space Technologies, RAST 2019. ed. / S. Menekay; O. Cetin; O. Alparslan. Institute of Electrical and Electronics Engineers Inc., 2019. p. 479-484 8767844 (Proceedings of 9th International Conference on Recent Advances in Space Technologies, RAST 2019).

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

TY - GEN

T1 - Ship detection from optical satellite images with deep learning

AU - Kartal, Mesut

AU - Duman, Osman

PY - 2019/6

Y1 - 2019/6

N2 - The effective use and control of maritime routes in the commercial/military area is an increasing and important need for states. There are some motivations for this purpose: Safe traffic of the ships in narrow canals, avoiding illegal usage of anchoring areas of ships, monitoring fishing activities to avoid illegal fishing or protect fish population, detection of lost ships, boats or debris in the ocean, detection and identification of warships (intelligence, defense, offensive, etc.). This paper proposed an open source, fast running ship detection system from optical satellite images with the deep learning algorithm. The system does not need any comprehensive hardware, even can work on an average laptop. Tensorflow Object Detection Application Programming Interface (API)is trained by optical satellite images with ships and used as object detection API.

AB - The effective use and control of maritime routes in the commercial/military area is an increasing and important need for states. There are some motivations for this purpose: Safe traffic of the ships in narrow canals, avoiding illegal usage of anchoring areas of ships, monitoring fishing activities to avoid illegal fishing or protect fish population, detection of lost ships, boats or debris in the ocean, detection and identification of warships (intelligence, defense, offensive, etc.). This paper proposed an open source, fast running ship detection system from optical satellite images with the deep learning algorithm. The system does not need any comprehensive hardware, even can work on an average laptop. Tensorflow Object Detection Application Programming Interface (API)is trained by optical satellite images with ships and used as object detection API.

KW - artificial neural networks

KW - deep learning

KW - optical satellite image

KW - python

KW - ship detection

KW - tensorflow

UR - http://www.scopus.com/inward/record.url?scp=85073898483&partnerID=8YFLogxK

U2 - 10.1109/RAST.2019.8767844

DO - 10.1109/RAST.2019.8767844

M3 - Conference contribution

AN - SCOPUS:85073898483

T3 - Proceedings of 9th International Conference on Recent Advances in Space Technologies, RAST 2019

SP - 479

EP - 484

BT - Proceedings of 9th International Conference on Recent Advances in Space Technologies, RAST 2019

A2 - Menekay, S.

A2 - Cetin, O.

A2 - Alparslan, O.

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 9th International Conference on Recent Advances in Space Technologies, RAST 2019

Y2 - 11 June 2019 through 14 June 2019

ER -

Kartal M, Duman O. Ship detection from optical satellite images with deep learning. In Menekay S, Cetin O, Alparslan O, editors, Proceedings of 9th International Conference on Recent Advances in Space Technologies, RAST 2019. Institute of Electrical and Electronics Engineers Inc. 2019. p. 479-484. 8767844. (Proceedings of 9th International Conference on Recent Advances in Space Technologies, RAST 2019). doi: 10.1109/RAST.2019.8767844

Ship detection from optical satellite images with deep learning

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this