Enhancing object detection and classification using deep learning: A novel approach with annotated dataset and YOLO-C3GTR architecture

  • Rana Muhammad Usman Department of Space Optoelectronic Information, College of Astronautics, Nanjing University of Aeronautics and Astronautics (NUAA), Nanjing 211106, China
  • Junhua Yan Department of Space Optoelectronic Information, College of Astronautics, Nanjing University of Aeronautics and Astronautics (NUAA), Nanjing 211106, China
  • Saqib Mehmood Department of Open and Environmental systems, Graduate School of Science and Technology, Keio University, Tokyo 223-0061, Japan
  • Muhammad Jamil Department of Computer Science Comsats University Islamabad, Sahiwal Campus, Sahiwal 57000, Pakistan

Abstract

In the rapidly evolving field of computer vision, the need for advancements in object detection is paramount. For a variety of reasons, including security, maritime surveillance, and environmental monitoring, the identification and categorization of ships in aerial pictures is an essential component. In this study, two distinctive approaches are proposed to improve the accuracy of ship detection and categorization in satellite imagery. In the beginning, the dataset for ship detection that was provided by Airbus was separated into five distinct categories: oil tanker, bulk carrier, container ship, sand carrier, and general ship class. Setting up this division was done with the idea of increasing the precision of the ship classification in the imagery. Moreover, we deployed the YOLO-C3GTR model, which is part of our Object Detection framework and helped us to distinguish ships using the technique of Object Detection. The application of the methodology that we have proposed has the potential to significantly improve the precision of these systems when they are used in real-world scenarios and to make a novel addition to the field of ship identification and classification. We have used multiple algorithms of YOLOv5 tested on this dataset like TPHYOLOv5, YOLOv5x, YOLOv5l and our proposed architecture YOLO-C3GTR and it surpassed all the existing approaches by the mAP of 0.83. Furthermore, we intend to perform additional research in this field while simultaneously working to improve our technique. A comparison was made between the performance of the model and that of other deep learning approaches. The model was evaluated and trained with the categorized dataset.

Published
Apr 1, 2024
How to Cite
USMAN, Rana Muhammad et al. Enhancing object detection and classification using deep learning: A novel approach with annotated dataset and YOLO-C3GTR architecture. Mehran University Research Journal of Engineering and Technology, [S.l.], v. 43, n. 2, p. 205-219, apr. 2024. ISSN 2413-7219. Available at: <https://publications.muet.edu.pk/index.php/muetrj/article/view/3186>. Date accessed: 18 july 2024. doi: http://dx.doi.org/10.22581/muet1982.3186.
Section
Articles
This is an open Access Article published by Mehran University of Engineering and Technolgy, Jamshoro under CCBY 4.0 International License