One of the basic concepts affecting the technical-operational characteristics of the vessel is its draft, which in the conventional sense means vertical distance from water level to the lowest point of the bottom of the vessel. The displacement of the vessel can be calculated from the observed draft. Currently there are a number of ways to determine the draft, among which visual observation of marks of the vessel board of the officer responsible for this is the basic of world practice. However, all existing methods have different restrictions on the installation and use of systems necessary for their implementations or give a significant error when measuring the draft. As the main instrument to fix this problem in this paper the use of artificial neural networks of deep learning is proposed. An algorithm for frame-by-frame video processing using a system of technical vision for detection of marks on the vessel board and detection of operating waterline is given. Solving these two challenges will give a conclusion about the ship’s draft based on the extracted visual information. On the basis of experimental data, the possibility of introducing a technical vision system in solving the considered problem is assessed.
- Deep learning
- Draft marks
- Computer vision
This is a preview of subscription content, access via your institution.
Review of Maritime Transport 2018 (UNCTAD)
Popov AP, Sayarkin KS, Zhilenkov AA (2018) Analysis of perspective models of artificial neural networks for control of robotic objects. In: Paper presented at the 2018 IEEE conference of Russian young researchers in electrical and electronic engineering (EIConRus), pp 958–961. https://doi.org/10.1109/EIConRus.2018.8317248.
Karpov AD, Zhilenkov AA (2017) Designing the platform for monitoring and visualization orientation in Euler angles. In: Paper presented at the 2017 IEEE conference of Russian young researchers in electrical and electronic engineering (EIConRus), pp 301–305. https://doi.org/10.1109/EIConRus.2017.7910551
Choi J, Ahn M, Kim J (2015) Implementation of hardware model for spiking neural network. In: Paper presented at the international conference on artificial intelligence
Zhilenkov AA, Gilyazov DD, Matveev II, Krishtal YV (2017) Power line communication technologies in automated control systems. In: Paper presented at the 2017 IEEE conference of Russian young researchers in electrical and electronic engineering (EIConRus), pp 246–249. https://doi.org/10.1109/EIConRus.2017.7910539
Editors and Affiliations
Rights and permissions
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Kirilenko, Y., Epifantsev, I. (2023). Automatic Recognition of Draft Marks on a Ship’s Board Using Deep Learning System. In: Guda, A. (eds) Networked Control Systems for Connected and Automated Vehicles. NN 2022. Lecture Notes in Networks and Systems, vol 510. Springer, Cham. https://doi.org/10.1007/978-3-031-11051-1_143
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-11050-4
Online ISBN: 978-3-031-11051-1
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)