Marine Target Detection and Ranging Algorithm Based on Monocular Camera and YOLOv5 Algorithm

DOI

10.2991/978-94-6463-514-0_55How to use a DOI?

Keywords

YOLOv5; Monocular camera; Edge detection; Target Detection

Abstract

In order to improve the detection efficiency and accuracy of target ships during navigation, as well as the distance measurement of target ships. This article uses the YOLOv5 model trained with ship data saturation to detect target ships. Using the Canny algorithm to detect the horizon on the sea surface, and measuring the distance of ships based on the geometric form of the Earth’s radius. This article uses non training set ocean images to validate the algorithm as an example. The experimental results show that the algorithm can achieve class detection of ships and distance measurement of distant targets, with a detection mAP (mean average accuracy) of 94.3%. The error value of the distance measurement results for targets compared to GPS data is 8.2% of the actual distance.

Copyright

© 2024 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  - Guoyu Shao
AU  - Hongyu Fu
AU  - Lei Zhao
PY  - 2024
DA  - 2024/09/28
TI  - Marine Target Detection and Ranging Algorithm Based on Monocular Camera and YOLOv5 Algorithm
BT  - Proceedings of the 2024 7th International Symposium on Traffic Transportation and Civil Architecture (ISTTCA 2024)
PB  - Atlantis Press
SP  - 575
EP  - 580
SN  - 2352-5401
UR  - https://doi.org/10.2991/978-94-6463-514-0_55
DO  - 10.2991/978-94-6463-514-0_55
ID  - Shao2024
ER  -