Ship Detection Based on an Enhanced YOLOv5 Algorithm
Journal Title: Mechatronics and Intelligent Transportation Systems - Year 2024, Vol 3, Issue 4
Abstract
Advanced ship detection technologies play a critical role in improving maritime safety by enabling the rapid identification of vessels and other maritime targets, thereby mitigating the risk of collisions and optimizing traffic efficiency. Traditional detection methods often demonstrate high sensitivity to minor variations in target appearance but face significant limitations in generalization, making them ill-suited to the complex and dynamic nature of maritime environments. To address these challenges, an enhanced ship detection method, referred to as YOLOv5-SE, has been proposed, which builds upon the YOLOv5 framework. This approach incorporates attention mechanisms within the backbone network to improve the model's focus on key features of small targets, dynamically adjusting the importance of each channel to boost representational capacity and detection accuracy. In addition, a refined version of the Complete Intersection over Union (CIoU) loss function has been introduced to optimize the loss associated with target bounding box prediction, thereby improving localization accuracy and ensuring more precise alignment between predicted and ground-truth boxes. Furthermore, the conventional coupled detection head in YOLOv5 is replaced by a Decoupled Head, facilitating better adaptability to various target shapes and accelerating model convergence. Experimental results demonstrate that these modifications significantly enhance ship detection performance, with mean Average Precision (mAP) at IoU 0.5 reaching 94.9% and 95.1%, representing improvements of 3.1% and 1.2% over the baseline YOLOv5 model, respectively. These advancements underscore the efficacy of the proposed methodology in improving detection accuracy and robustness in challenging maritime settings.
Authors and Affiliations
Xin Liu, Qingfa Zhang, Yubo Tu, Mingzhi Shao, Tengwen Zhang, Yuhan Sun, Haiwen Yuan
Keywords
Related Articles
- EP ID EP755203
- DOI https://doi.org/10.56578/mits030403
- Views 27
- Downloads 0
Enhanced Vehicle Performance Through Nonlinear Finite Element Analysis of Tyre-Soil Interaction
In this investigation, critical insights into the complex interactions between tyres and soil are explored through the utilization of nonlinear finite element analysis (FEA), bearing significant implications for vehicle...
Preparation of the User Requirements Specification for ETCS Level 2 System in Serbia - Experiences and Challenges
This paper presents a strategy implemented for preparation of the national User Requirements Specifications (URS) for European Train Control System (ETCS) with Level 2 in the Republic of Serbia. The requirements were the...
Regional Classification of Serbian Railway Transport System Through Efficient Synthetic Indicator
The railway transport system is one of the most important elements in the development of the economy and the social space of any area. The main objective of the study is to analyse the regional differentiation in railway...
Objective-Subjective CRITIC-MARCOS Model for Selection Forklift in Internal Transport Technology Processes
In today transport technology processes, forklifts are one of the most important equipment for making handling operations in order to increase sustainability. They have a large influence in achieving the efficiency and s...
Evaluating the Road Environment Through the Lens of Professional Drivers: A Traffic Safety Perspective
In the context of traffic safety, the interplay between the road environment and the human factor emerges as a critical determinant of the severity of road crash consequences. This study was designed to explore the perce...