Maritime Ship Detection using Convolutional Neural Networks from Satellite Images

Jaafar Alghazo, Abul Bashar, Ghazanfar Latif, Mohammed Zikria

Research output: Chapter in Book/Report/Conference proceedingConference contribution

14 Scopus citations

Abstract

The significance of efficient monitoring and control of marine traffic for the purpose of safety and security of the ships cannot be overemphasized in the current scenario where global trade and commerce is at its pinnacle. Various stakeholders are concerned with serious maritime issues related to hijacking of ships, illegal fishing, encroachments of sea borders, and illicit exchange of sea cargo, accidents, and military attacks. This requires an automated, accurate, fast, and robust sea monitoring system which can avoid or mitigate the negative effects of such issues. This paper proposes, implements, and evaluates a CNN based deep learning model which can accurately identify ships from the images captured from satellite images. Two models CNN Model 1 and CNN Model 2 having different architectures are trained, validated, and tested on the Airbus satellite images dataset. Both classification accuracy and loss functions are measured by varying the number of the epochs. Also, the complexity comparison of the two models is performed by measuring the training time. The paper concludes that the proposed models are automatic, fast and accurate in terms of their performance on the Airbus dataset by achieving a maximum accuracy of 89.7%.

Original languageEnglish (US)
Title of host publicationProceedings - 2021 IEEE 10th International Conference on Communication Systems and Network Technologies, CSNT 2021
EditorsGeetam S. Tomar
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages432-437
Number of pages6
ISBN (Electronic)9780738105239
DOIs
StatePublished - 2021
Externally publishedYes
Event10th IEEE International Conference on Communication Systems and Network Technologies, CSNT 2021 - Bhopal, India
Duration: Jun 18 2021Jun 19 2021

Publication series

NameProceedings - 2021 IEEE 10th International Conference on Communication Systems and Network Technologies, CSNT 2021

Conference

Conference10th IEEE International Conference on Communication Systems and Network Technologies, CSNT 2021
Country/TerritoryIndia
CityBhopal
Period6/18/216/19/21

Bibliographical note

Publisher Copyright:
© 2021 IEEE.

Keywords

  • Convolutional neural networks
  • Deep CNN
  • Deep learning
  • Maritime ship detection
  • Sea surveillance

Fingerprint

Dive into the research topics of 'Maritime Ship Detection using Convolutional Neural Networks from Satellite Images'. Together they form a unique fingerprint.

Cite this