Designing a YOLOv8n-based Video Surveillance System for Ship Aspect Recognition

ABSTRACT: According to the Convention on the International Regulations for Preventing Collisions at Sea (COLREGs), vessels must maintain an effective lookout by sight, hearing, and all available technical means, taking into account prevailing circumstances and environmental conditions. In this context, automated visual surveillance systems represent an important enhancement of conventional navigational tools, enabling early detection and interpretation of surrounding vessel behaviour. This study proposes a video surveillance system based on the lightweight YOLOv8n deep learning model for the detection and classification of eight vessel aspects. The model was trained on an initial dataset of 925 images, which was further expanded to 1,742 annotated images. The dataset was designed to reflect real maritime operating conditions, including different times of day, weather scenarios, vessel categories, and geographical regions. To improve robustness, data augmentation techniques such as colour space transformations, geometric modifications, and classification-specific augmentations were applied. Class imbalance was mitigated through the use of class weighting. The paper also describes the system architecture and camera configuration, providing effective surveillance coverage up to 6 nautical miles. The proposed approach enables not only vessel aspect recognition but also the estimation of relative and true bearings, thereby contributing to improved situational awareness and collision avoidance in maritime navigation.

KEYWORDS: Safety of Navigation, e-Navigation, Collision Avoidance, Computer Vision, Methods and Algorithms, Artificial Intelligence, Autonomous Ships, Marine Traffic Control and Automatic Identification Systems

REFERENCES

A. Vekinis and S. Perantonis, “Aeolus Ocean – A simulation environment for the autonomous COLREG-compliant navigation of unmanned surface vehicles using deep reinforcement learning and maritime object detection,” arXiv, arXiv:2307.06688, 2023.

International Maritime Organization, Convention on the International Regulations for Preventing Collisions at Sea (COLREGs), adopted Oct. 20, 1972, entered into force Jul. 15, 1977, London, U.K., 1977.

D. Qiao, G. Liu, J. Zhang, and Y. Zhou, “Marine vision-based situational awareness using discriminative deep learning: A survey,” J. Mar. Sci. Eng., vol. 9, no. 4, p. 397, 2021, doi:10.3390/jmse9040397. - doi:10.3390/jmse9040397

J. R. Terven and D. M. Cordova-Esparaza, “A comprehensive review of YOLO: From YOLOv1 to YOLOv8 and beyond,” arXiv, arXiv:2304.00501, 2023.

Stereolabs Inc., “Performance benchmark of YOLO v5, v7 and v8,” 2023. [Online]. Available: https://www.stereolabs.com/blog/performance-of-yolo-v5-v7-and-v8

Z. He, K. Wang, T. Fang, L. Su, R. Chen, and X. Fei, “Comprehensive performance evaluation of YOLOv11, YOLOv10, YOLOv9, YOLOv8 and YOLOv5 on object detection of power equipment,” arXiv, arXiv:2411.18871, 2024. - doi:10.1109/CCDC65474.2025.11090973

M. Yasir, S. Ahmed, F. Khan, Y. Zhang, A. H. Aslam, and A. J. Malik, “YOLOShipTracker: Tracking ships in SAR images using lightweight YOLOv8,” Int. J. Appl. Earth Obs. Geoinf., vol. 134, p. 104137, 2024, doi:10.1016/j.jag.2024.104137. - doi:10.1016/j.jag.2024.104137

Y. Li and S. Wang, “EGM-YOLOv8: A lightweight ship detection model with efficient feature fusion and attention mechanisms,” J. Mar. Sci. Eng., vol. 13, no. 4, p. 757, 2025, doi:10.3390/jmse13040757. - doi:10.3390/jmse13040757

J. Di, L. Sun, R. Zhang, and Q. Wu, “An enhanced YOLOv8 model for accurate detection of solid floating waste,” Sci. Rep., vol. 15, no. 1, p. 1632, 2025, doi:10.1038/s41598-025-10163-2. - doi:10.1038/s41598-025-10163-2

B. Zhao, H. Chen, X. Liu, and J. Huang, “Modular YOLOv8 optimization for real-time UAV maritime rescue object detection,” Sci. Rep., vol. 14, no. 1, p. 1158, 2024, doi:10.1038/s41598-024-75807-1. - doi:10.1038/s41598-024-75807-1

P. Liu, “A high-accuracy YOLOv8-ResAttNet framework for maritime object recognition,” IET Image Process., vol. 19, no. 3, pp. 145–157, 2025, doi:10.1049/ipr2.70085. - doi:10.1049/ipr2.70085

X. Zhao and Y. Song, “Improved ship detection with YOLOv8 enhanced with MobileViT and GSConv,” Electronics, vol. 12, no. 22, p. 4666, 2023, doi:10.3390/electronics12224666. - doi:10.3390/electronics12224666

M. E. Lopez, C. Schönlieb, A. Aviles-Rivero, R. Mester, and E. Brekke, “Heading estimation of ships using deep learning and synthetic non-aerial images,” J. Phys.: Conf. Ser., vol. 3123, no. 1, 012027, 2025, doi:10.1088/1742-6596/3123/1/012027. - doi:10.1088/1742-6596/3123/1/012027

B. Kiefer, Y. Quan, and A. Zell, “Approximate supervised object distance estimation on unmanned surface vehicles,” arXiv, arXiv:2501.05567, 2025. - doi:10.1109/ICAR65334.2025.11338699

A. Gorad, S. S. Hassan, and S. Särkkä, “Vessel bearing estimation using visible and thermal imaging,” in Lecture Notes in Computer Science, vol. 13886, Springer, 2023, pp. 373–381, doi:10.1007/978-3-031-31438-4_25. - doi:10.1007/978-3-031-31438-4_25

O. Pashenko and O. Pipchenko, “Design of a YOLO-based computer vision model for ships' aspect angle detection,” Shipping & Navigation, no. 38, pp. 10–21, 2025, doi:10.31653/2306-5761.38.2025.10-21. - doi:10.31653/2306-5761.38.2025.10-21

Z. Yang et al., “Does negative sampling matter? A review with insights into its theory and applications,” arXiv, arXiv:2402.17238, 2024.

Ultralytics, “YOLO data augmentation,” 2025. [Online]. Available: https://docs.ultralytics.com/guides/yolo-data-augmentation/

Z. Wu, “Image data augmentation techniques based on deep learning: A survey,” Math. Biosci. Eng., vol. 21, no. 6, pp. 6190–6224, 2024, doi:10.3934/mbe.2024272. - doi:10.3934/mbe.2024272

B. Zoph, E. D. Cubuk, G. Ghiasi et al., “Learning data augmentation strategies for object detection,” arXiv, arXiv:1906.11172, 2019. - doi:10.1007/978-3-030-58583-9_34

O. L. Pashenko, “Impact of data augmentation on training computer vision model for ships’ aspect angle detection,” Scientific Bulletin Kherson State Maritime Academy, no. 2(31), pp. 52–63, 2025, doi:10.33815/2313-4763.2025.2.31.052-063. - doi:10.33815/2313-4763.2025.2.31.052-063

S. Fefilatyev, D. Goldgof, and C. Lembke, “Detection and tracking of ships in open sea with rapidly moving buoy-mounted camera system,” Ocean Eng., vol. 54, pp. 1–12, 2012, doi:10.1016/j.oceaneng.2012.06.028. - doi:10.1016/j.oceaneng.2012.06.028

J. Guo, L. Fan, B. Wu, J. Gu, S. Cao, and J. Ye, “PTZ-Calib: Robust Pan-Tilt-Zoom camera calibration,” arXiv, arXiv:2502.09075, 2025. - doi:10.1109/ICRA55743.2025.11128129

N. Wawrzyniak, T. Hyla, and A. Popik, “Vessel detection and tracking method based on video surveillance,” Sensors, vol. 19, no. 23, 5230, 2019, doi:10.3390/s19235230. - doi:10.3390/s19235230

X. Liu, Y. Hu, H. Ji, M. Zhang, and Q. Yu, “A deep learning method for ship detection and traffic monitoring in an offshore wind farm area,” J. Mar. Sci. Eng., vol. 11, no. 7, p. 1259, 2023, doi:10.3390/jmse11071259. - doi:10.3390/jmse11071259

M. Ud Din, A. B. Bakht, W. Akram, Y. Dong, L. Seneviratne, and I. Hussain, “Benchmarking vision-based object tracking for USVs in complex maritime environments,” arXiv, arXiv:2412.07392, 2024. - doi:10.1109/ACCESS.2025.3532299

W. Ding, H. Li, C.-M. Chew, X. Zhang, and H. Huang, “Deep learning-based recognition of small maritime targets for obstacle avoidance in visual wave gliders,” Ocean Eng., vol. 322, 120471, 2025, doi:10.1016/j.oceaneng.2025.120471. - doi:10.1016/j.oceaneng.2025.120471

International Association of Marine Aids to Navigation and Lighthouse Authorities, Vessel Traffic Services Manual, 8th ed., Saint-Germain-en-Laye, France, 2025.

Illuminating Engineering Society, IES Lighting Handbook: Reference and Application, 10th ed., New York, NY, USA, 2011.

B. Wang, L. Dong, M. Zhao, H. Wu, and W. Xu, “An infrared maritime target detection algorithm applicable to heavy sea fog,” Infrared Phys. Technol., vol. 71, pp. 56–62, 2015, doi:10.1016/j.infrared.2015.04.009. - doi:10.1016/j.infrared.2015.01.031

International Electrotechnical Commission, IEC 60945: Maritime navigation and radiocommunication equipment and systems – General requirements – Methods of testing and required test results, Geneva, Switzerland, 2002.

International Electrotechnical Commission, IEC 60068: Environmental testing, Geneva, Switzerland, 2015.

International Maritime Organization, Resolution A.708(17): Navigation bridge visibility and functions, London, U.K., 1991.

International Maritime Organization, Resolution MSC.192(79): Adoption of the revised performance standards for radar equipment, London, U.K., 2004.

National Marine Electronics Association, NMEA 0183 Standard for Interfacing Marine Electronic Devices, ver. 4.30, 2023. [Online]. Available: https://www.nmea.org

International Maritime Organization, Resolution MSC.232(82): Guidelines for the use of electronic navigation systems, London, U.K., 2006.

International Electrotechnical Commission, IEC 61162-1: Maritime navigation and radiocommunication equipment and systems – Digital interfaces – Part 1: Single talker and multiple listeners, 6th ed., Geneva, Switzerland, 2024.

Citation note:

Pashenko O., Pipchenko O.D., Shevchenko V.: Designing a YOLOv8n-based Video Surveillance System for Ship Aspect Recognition. TransNav, the International Journal on Marine Navigation and Safety of Sea Transportation, Vol. 20, No. 2, doi:10.12716/1001.20.02.12, pp. 375-385, 2026

BibTeX EndNote

Authors in other databases:

Olena Pashenko: ORCID iD icon

orcid.org/0000-0002-0462-0130 Scopus icon