Paper
21 September 2023 Ship detection using SAR images based on YOLO (you only look once)
George Melillos, Eleftheria Kalogirou, Despoina Makri, Diofantos G. Hadjimitsis
Author Affiliations +
Proceedings Volume 12786, Ninth International Conference on Remote Sensing and Geoinformation of the Environment (RSCy2023); 1278613 (2023) https://doi.org/10.1117/12.2681665
Event: Ninth International Conference on Remote Sensing and Geoinformation of the Environment (RSCy2023), 2023, Ayia Napa, Cyprus
Abstract
This paper proposes an automatic ship detection approach in Synthetic Aperture Radar (SAR) Images using YOLO deep learning framework. YOLO (You Only Look Once) is an object detection algorithm Object detection algorithms using region proposal includes RCNN, Fast RCNN, and Faster RCNN, etc. Region based Convolutional Neural Networks (RCNN) algorithm uses a group of boxes for the image and then analyses in each box if either of the boxes holds a target. It employs the method of selective search to pick those sections from the picture. YOLO can be used to assist in making safety checks for ships and mariners. We train the YOLO model on our dataset in this paper for our detector to learn to detect objects in SAR images such as ships. The preliminary YOLO test results showed an increase in the accuracy of ship detection at Cyprus’s Coast and can be applied in the field of ship detection.
© (2023) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
George Melillos, Eleftheria Kalogirou, Despoina Makri, and Diofantos G. Hadjimitsis "Ship detection using SAR images based on YOLO (you only look once)", Proc. SPIE 12786, Ninth International Conference on Remote Sensing and Geoinformation of the Environment (RSCy2023), 1278613 (21 September 2023); https://doi.org/10.1117/12.2681665
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Object detection

Synthetic aperture radar

Detection and tracking algorithms

Education and training

Satellites

Target detection

Deep learning

Back to Top