YOLO-Driven Vessel Detection and Multi-Object Tracking in Fixed-Camera Marina Environments
Open Access
- 3 August 2026
- journal article
- research article
- Published by MDPI AG in Technologies
- Vol. 14 (8) , 482
Abstract
Vessel detection and multi-object tracking (MOT) in marinas remain challenging because of occlusions, small targets, cluttered backgrounds, and changing illumination. This paper presents a controlled, feasibility-focused comparative evaluation of YOLO-driven vessel detection and tracking in a fixed-camera marina environment, comparing YOLOv11 with the more attention-oriented YOLOv12 detector family. A dataset of 3546 annotated images was collected using a static ground-level camera at a marina in the northern Adriatic, Croatia. YOLOv11s, YOLOv11m, YOLOv12s, and YOLOv12m were fine-tuned using transfer learning, evaluated across five random seeds, and integrated into a common tracking-by-detection pipeline with Kalman filter (KF) and extended Kalman filter (EKF) motion models. Detection was assessed using COCO-style mAP metrics, while tracking was evaluated using MOT and HOTA-based metrics. YOLOv11m achieved the highest mean test-set mAP@50–95 (0.7458 ± 0.0027) and significantly outperformed YOLOv11s and YOLOv12s. Although YOLOv12m did not achieve the highest frame-level mAP, it obtained the highest mean AssA and IDF1 when averaged across the two motion models. KF achieved higher mean HOTA, DetA, AssA, MOTA, and IDF1 than EKF, whereas EKF achieved only marginally higher MOTP; the KF advantage was statistically significant for IDF1. Overall, the results show that frame-level detection accuracy does not necessarily determine downstream tracking performance, thereby supporting the joint evaluation of detector and motion-model choices.Keywords
Funding Information
- European Union—NextGeneration EU (SEALEARN–uniri-mz-25-49)
- European Union—NextGeneration EU (NPOO.C3.2.R3-I1.01.0124)
- European Regional Development Fund (PK.1.1.13.0083)
This publication has 35 references indexed in Scilit:
- Machine learning for ship-motion-based sea-state estimationOcean Engineering, 2026
- Multi-object tracking: a systematic literature reviewMultimedia Tools and Applications, 2023
- CRAS-YOLO: A Novel Multi-Category Vessel Detection and Classification Model Based on YOLOv5s AlgorithmIEEE Access, 2023
- Unmanned Surface Vessel Visual Object Detection Under All-Weather Conditions with Optimized Feature Fusion Network in YOLOv4Journal of Intelligent & Robotic Systems, 2021
- Multiple object tracking: A literature reviewArtificial Intelligence, 2021
- Enhanced YOLO v3 Tiny Network for Real-Time Ship Detection From Visual ImageIEEE Access, 2021
- HOTA: A Higher Order Metric for Evaluating Multi-object TrackingInternational Journal of Computer Vision, 2020
- Big data and artificial intelligence in the maritime industry: a bibliometric review and future research directionsMaritime Policy & Management, 2020
- FUSAR-Ship: building a high-resolution SAR-AIS matchup dataset of Gaofen-3 for ship detection and recognitionScience China Information Sciences, 2020
- Ship detection in SAR images based on an improved faster R-CNN2017