Computer Vision over 4G/5G Private Network for Real-Time Draft Assessment to Estimate Vessel Productivity
Sensors · 16.04.2026 · 26 (8) · 2443
DOI: 10.3390/s26082443 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 16.04.2026. Verfasst von Tiago Novaes Mathias und 8 weiteren Autor:innen. Beteiligte Einrichtung: Infrastructure Digital Transformation Engineering Department, Port and Airport Research Institute, Yokosuka 239-0826, Japan. Die Arbeit nennt 35 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: CNPq-Conselho Nacional de Desenvolvimento Científico e Tecnológico, JSPS KAKENHI, CNPq—Conselho Nacional de Desenvolvimento Científico e Tecnológico.
Abstract (Originalsprache)
Background
Draft surveys are widely used to estimate cargo mass during bulk vessel loading and unloading; however, conventional procedures depend on manual draft readings that are episodic, labor-intensive, and sensitive to environmental conditions. Existing camera-based automated approaches rely on draft mark recognition or explicit waterline detection, which remain vulnerable to illumination variability, hull fouling, and wave-induced disturbances.
Methods
This paper proposes a computer vision framework deployed at the Port of Santos, Brazil, using fixed quay-side cameras and a private 4G network infrastructure for continuous image transmission. Unlike prior methods, the framework estimates emergent hull height by segmenting vessel hull contours from bow and stern viewpoints using customized YOLOv8 instance-segmentation models, without relying on draft marks or waterline detection. Pixel measurements are converted to metric units using a nearby bollard of known height as a local physical reference.
Results
Field experiments monitor a Panamax bulk carrier over approximately 6.5 days, processing more than 34,000 images from each camera at an average rate of 3.7 images per minute. Both bow and stern segmentation models achieve mAP50-95 mask scores of 0.980 and 0.965, respectively, confirming precise and stable hull boundary delineation. Hull height decreases from 8.27 m to 4.64 m at the bow and from 7.98 m to 3.98 m at the stern over the loading period, with coherent and temporally stable trends across independent viewpoints.
Conclusions
The proposed approach delivers repeatable and continuous hull-height estimates under real operational conditions, including variable lighting, background clutter, and partial occlusions, offering a practical and non-intrusive complement to traditional draft surveys for continuous vessel loading monitoring in modern ports.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Infrastructure Digital Transformation Engineering Department, Port and Airport Research Institute, Yokosuka 239-0826, Japan.
- Applied Computing, National Institute for Space Research, São José dos Campos 12227-010, Brazil.
- Department of Electrical and Automation Engineering, University of São Paulo, São Paulo 05508-010, Brazil.
- Department of Production Engineering, University of São Paulo, São Paulo 05508-010, Brazil.
- NLT Next Level Telecom, São Paulo 04576-060, Brazil.
- Department of Naval and Ocean Engineering, University of São Paulo, São Paulo 05508-010, Brazil.
ORCID-Profile: Tiago Novaes Mathias, Rui Carlos Botter, Daniel de Oliveira Mota
Förderung
- CNPq-Conselho Nacional de Desenvolvimento Científico e Tecnológico
- JSPS KAKENHI
- CNPq—Conselho Nacional de Desenvolvimento Científico e Tecnológico
Zitieren
APA
Mathias, T. N., Gonçalves, H. D. S. B., Paschoal, V. V., Lima, D. H. A., Duque, J. C. O., Lotenberg, A., Araújo, W. E., Botter, R. C., & Mota, D. O. (2026). Computer Vision over 4G/5G Private Network for Real-Time Draft Assessment to Estimate Vessel Productivity. Sensors, 26(8), 2443. https://doi.org/10.3390/s26082443
Vancouver
Mathias TN, Gonçalves HDSB, Paschoal VV, Lima DHA, Duque JCO, Lotenberg A, et al. Computer Vision over 4G/5G Private Network for Real-Time Draft Assessment to Estimate Vessel Productivity. Sensors. 2026;26(8):2443. doi:10.3390/s26082443
BibTeX
@article{Mathias2026,
author = {Mathias, Tiago Novaes and Gonçalves, Hugo da Silva Bernardes and Paschoal, Vinícius Veiga and Lima, Danillo Henrique Araujo de and Duque, Júlio César de Oliveira and Lotenberg, Arthur and Araújo, Willian Elias and Botter, Rui Carlos and Mota, Daniel de Oliveira},
title = {Computer Vision over 4G/5G Private Network for Real-Time Draft Assessment to Estimate Vessel Productivity},
journal = {Sensors},
year = {2026},
volume = {26},
number = {8},
pages = {2443},
doi = {10.3390/s26082443}
}
EUVIMED