Advancing Maritime Vision: Enhanced Ship Detection with YOLO V5-V8 Architectures

DOI

10.2991/978-94-6463-858-5_91How to use a DOI?

Keywords

Ship detection; YOLO; Maritime applications; Deep learning; Object recognition; Vision systems; Adaptability; YOLO architectures

Abstract

Detecting and recognizing ships at sea presents unique challenges due to their irregular shapes, complex features, and varying sizes. This study explores the capabilities of different YOLO(YouOnlyLookOnce) architectures—specifically versions V5, V6, V7, and V8—for maritime applications. Each version introduces improvements in model design, detection accuracy, and efficiency, with V8 serving as the benchmark for comparison. Through detailed experimentation, the findings show that while all YOLO models exhibit strong detection capabilities, the advancements from V5 to V8 lead to significant improvements in accuracy and adaptability to diverse ship characteristics.

This progression highlights the strengths and limitations of each version and demonstrates how the evolution of YOLO architectures enhances maritime vision systems. The insights gained from this research pave the way for more effective solutions in ship detection, recognition, and tracking, showcasing the potential of deep learning to address real-world challenges at sea.

Copyright

© 2025 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - R. Priyanka
AU  - D. Shruthi
AU  - T. Sahithya
AU  - S. Lakshmi Sai Iswarya
AU  - U. Gouri Silpa
PY  - 2025
DA  - 2025/11/04
TI  - Advancing Maritime Vision: Enhanced Ship Detection with YOLO V5-V8 Architectures
BT  - Proceedings of International Conference on Computer Science and Communication Engineering (ICCSCE 2025)
PB  - Atlantis Press
SP  - 1097
EP  - 1107
SN  - 2352-538X
UR  - https://doi.org/10.2991/978-94-6463-858-5_91
DO  - 10.2991/978-94-6463-858-5_91
ID  - Priyanka2025
ER  -