Learning-Based Online Tracking Algorithms for Marine Litter in Multibeam Water Column Images
IEEE Access · 2026 · 14 · 47666-47685
DOI: 10.1109/access.2026.3677642 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Access, 2026. Verfasst von Pedro Alves Guedes und 2 weiteren Autor:innen. Die Arbeit nennt 62 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Funds through the Portuguese funding agency, FCT—Fundação para a Ciência e a Tecnologia with the Studentship for Doctoral Research Funding Programme, FCT – Fundação para a Ciência e a Tecnologia, I.P., European Union under the Horizon Europe Program.
Abstract (Originalsprache)
Marine litter is a growing environmental threat, with severe ecological and socio-economic impacts. Most monitoring strategies rely on optical sensors to detect surface pollution, however these approaches fail to capture submerged plastics dispersed throughout the water column. Multibeam acoustic imaging offers a complementary solution, but the scarcity of annotated sonar datasets and the high noise levels of acoustic imagery make automated detection and tracking particularly challenging. This study presents a comparative evaluation of deep learning based multi-object tracking (MOT) algorithms applied to water column acoustic data. Pre-trained YOLOv8 detectors were integrated with tracking-by-detection frameworks including BoT-SORT, OC-SORT, ByteTrack, and DeepOC-SORT. Performance was assessed across acoustic frequencies and preprocessing strategies using standard MOT metrics. Results show that adaptive Gaussian thresholding and opening morphology improved robustness at lower frequencies ( $\mathrm {950~\text {kHz} }$ and $\mathrm {1200~\text {kHz} }$ ), while unprocessed inputs proved more resilient to severe clutter at $\mathrm {1400~\text {kHz} }$ . BoostTrack and ByteTrack achieved the most consistent tracking, effectively managing intermittent detections to maximise MOTA and IDF1. In contrast, OC-SORT underperformed, struggling with fragmented sonar trajectories. Furthermore, while efficient Nano models dominated at lower frequencies, Medium models were required under higher noise. These findings demonstrate the feasibility of applying MOT methods to sonar-based litter monitoring. Future work will explore unsupervised learning approaches to leverage intrinsic sonar data structure, reduce annotation needs, and enable scalable marine litter tracking.
Förderung
- National Funds through the Portuguese funding agency, FCT—Fundação para a Ciência e a Tecnologia with the Studentship for Doctoral Research Funding Programme
- FCT – Fundação para a Ciência e a Tecnologia, I.P.
- European Union under the Horizon Europe Program
Zitieren
APA
Guedes, P. A., Silva, H. M., & Wang, S. (2026). Learning-Based Online Tracking Algorithms for Marine Litter in Multibeam Water Column Images. IEEE Access, 14, 47666-47685. https://doi.org/10.1109/access.2026.3677642
Vancouver
Guedes PA, Silva HM, Wang S. Learning-Based Online Tracking Algorithms for Marine Litter in Multibeam Water Column Images. IEEE Access. 2026;14:47666-47685. doi:10.1109/access.2026.3677642
BibTeX
@article{Guedes2026,
author = {Guedes, Pedro Alves and Silva, Hugo Miguel and Wang, Sen},
title = {Learning-Based Online Tracking Algorithms for Marine Litter in Multibeam Water Column Images},
journal = {IEEE Access},
year = {2026},
volume = {14},
pages = {47666--47685},
doi = {10.1109/access.2026.3677642}
}
EUVIMED