Solving pattern recognition problems in shipping monitoring systems based on CNN-models
Keywords:
Convolutional neural networks, pattern recognition, vessel classification, shipping monitoring systems, deep learning, computer vision, feature extraction, optimization, batch normalization, river transport, visual information processing, machine learning, transport security, environmental monitoringSynopsis
The chapter examines modern approaches to solving pattern recognition problems in shipping monitoring systems using convolutional neural network (CNN) models. Traditional rule-based and classical classification methods remain ineffective for complex visual tasks in inland and maritime transport due to high variability of vessel shapes, viewing angles, illumination conditions, and significant intraclass differences. Deep learning architectures – particularly CNNs – are shown to provide robust and scalable solutions by automatically extracting hierarchical features and forming stable, noise-resistant image representations.
The chapter provides a comprehensive review of the fundamental principles of CNN construction, including convolutional layers, feature maps, activation functions, pooling operations, regularization techniques, batch normalization, and optimization strategies. Special attention is devoted to the mechanisms of training neural networks: gradient-based optimization, stochastic gradient descent, hyperparameter tuning, prevention of overfitting, and the use of computational graphs for backpropagation.
Experimental evaluation was conducted using a dataset comprising more than 12,000 annotated images of inland waterway vessels, including tugboats, barges, passenger ships, and dry cargo vessels, captured in real river-port conditions under varying illumination, viewpoints, partial occlusions, and noise. The proposed CNN model achieved an overall classification accuracy of 93.4%, with precision of 92.1%, recall of 91.7%, and an F1-score of 91.9%. Comparative analysis demonstrates that the proposed approach outperforms classical methods such as k-nearest neighbors, linear classifiers, and feature-based support vector machines by 8 – 12% on average.
The practical importance of CNN-based methods for real-time monitoring of river port water areas in Ukraine is emphasized. The proposed models enable automated classification and recognition of surface vessels, enhancing the efficiency, accuracy, and adaptability of intelligent surveillance systems. The results contribute to the development of advanced decision-support tools in maritime transport, improving safety, environmental monitoring, and operational management of shipping flows.
References
Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S. et al. (2015). ImageNet Large Scale Visual Recognition Challenge. International Journal of Computer Vision, 115 (3), 211–252. https://doi.org/10.1007/s11263-015-0816-y
Krizhevsky, A., Sutskever, I., Hinton, G. E. (2012). ImageNet classification with deep convolutional neural networks. Advances in Neural Information Processing Systems, 25, 1097–1105.
Er, M. J., Zhang, Y., Chen, J., & Gao, W. (2023). Ship detection with deep learning: a survey. Artificial Intelligence Review, 56(10), 11825-11865. https://doi.org/10.1007/s10462-023-10455-x
Zhang, B., Liu, J., Liu, R. W., Huang, Y. (2025). Deep-learning-empowered visual ship detection and tracking: Literature review and future direction. Engineering Applications of Artificial Intelligence, 141, 109754. https://doi.org/10.1016/j.engappai.2024.109754
Awais, C. M., Reggiannini, M., Moroni, D., Salerno, E. (2025). A Survey on SAR ship classification using Deep Learning. arXiv preprint arXiv:2503.11906. https://doi.org/10.48550/arXiv.2503.11906
Liu, D. (2023). TS2Anet: Ship detection network based on transformer. Journal of Sea Research, 195, 102415. https://doi.org/10.1016/j.seares.2023.102415
Wang, Y., Li, X. (2025). Ship-DETR: A Transformer-Based Model for EfficientShip Detection in Complex Maritime Environments. IEEE Access, 13, 66031–66039. https://doi.org/10.1109/access.2025.3559107
Galdelli, A., Narang, G., Pietrini, R., Zazzarini, M., Fiorani, A., Tassetti, A. N. (2025). Multimodal AI-enhanced ship detection for mapping fishing vessels and informing on suspicious activities. Pattern Recognition Letters, 191, 15–22. https://doi.org/10.1016/j.patrec.2025.02.022
Salem, M. H., Li, Y., Liu, Z., AbdelTawab, A. M. (2023). A Transfer Learning and Optimized CNN Based Maritime Vessel Classification System. Applied Sciences, 13 (3), 1912. https://doi.org/10.3390/app13031912
Agorku, G., Hernandez, S., Falquez, M., Poddar, S., Amankwah-Nkyi, K. (2024). Real-Time Barge Detection Using Traffic Cameras and Deep Learning on Inland Waterways. Transportation Research Record: Journal of the Transportation Research Board, 2679 (2), 703–720. https://doi.org/10.1177/03611981241263574
Simonyan, K., Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv:1409.1556. https://doi.org/10.48550/arXiv.1409.1556
Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D. et al. (2015). Going deeper with convolutions. 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 1–9. https://doi.org/10.1109/cvpr.2015.7298594
He, K., Zhang, X., Ren, S., Sun, J. (2016). Deep Residual Learning for Image Recognition. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, 770–778. https://doi.org/10.1109/cvpr.2016.90
LeCun, Y., Bengio, Y., Hinton, G. (2015). Deep learning. Nature, 521 (7553), 436–444. https://doi.org/10.1038/nature14539
Lecun, Y., Bottou, L., Bengio, Y., Haffner, P. (1998). Gradient-based learning applied to document recognition. Proceedings of the IEEE, 86 (11), 2278–2324. https://doi.org/10.1109/5.726791
Goodfellow, I., Bengio, Y., Courville, A. (2016). Deep Learning. Cambridge: MIT Press, 775.
Ioffe, S., Szegedy, C. (2015). Batch normalization: accelerating deep network training by reducing internal covariate shift. Proceedings of the 32nd International Conference on Machine Learning, 448–456.
Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., Salakhutdinov, R. (2014). Dropout: a simple way to prevent neural networks from overfitting. Journal of Machine Learning Research, 15, 1929–1958.
Kingma, D. P., Ba, J. (2014). Adam: a method for stochastic optimization. arXiv:1412.6980. https://doi.org/10.48550/arXiv.1412.6980
Hastie, T., Tibshirani, R., Friedman, J. (2009). The Elements of Statistical Learning. New York: Springer, 745.
Huang, I.-L., Lee, M.-C., Nieh, C.-Y., Huang, J.-C. (2023). Ship Classification Based on AIS Data and Machine Learning Methods. Electronics, 13 (1), 98. https://doi.org/10.3390/electronics13010098
Ren, S., He, K., Girshick, R., Sun, J. (2015). Faster r-cnn: Towards real-time object detection with region proposal networks. Advances in neural information processing systems, 28, 91–99.
Leonidas, L. A., Jie, Y. (2021). Ship Classification Based on Improved Convolutional Neural Network Architecture for Intelligent Transport Systems. Information, 12 (8), 302. https://doi.org/10.3390/info12080302
Gallego, A.-J., Pertusa, A., Gil, P. (2018). Automatic Ship Classification from Optical Aerial Images with Convolutional Neural Networks. Remote Sensing, 10 (4), 511. https://doi.org/10.3390/rs10040511
Zhao, T., Wang, Y., Li, Z., Gao, Y., Chen, C., Feng, H., Zhao, Z. (2024). Ship Detection with Deep Learning in Optical Remote-Sensing Images: A Survey of Challenges and Advances. Remote Sensing, 16 (7), 1145. https://doi.org/10.3390/rs16071145
Redmon, J., Farhadi, A. (2017). YOLO9000: Better, Faster, Stronger. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Honolulu, 6517–6525. https://doi.org/10.1109/cvpr.2017.690
Girshick, R. (2015). Fast R-CNN. 2015 IEEE International Conference on Computer Vision (ICCV). IEEE, 1440–1448. https://doi.org/10.1109/iccv.2015.169
Niranjan, A., Patial, S., Aryan, A., Mittal, A., Choudhury, T., Rabiei-Dastjerdi, H., Kumar, P. (2024). A Deep Learning Approach for Ship Detection Using Satellite Imagery. EAI Endorsed Transactions on Internet of Things, 10. https://doi.org/10.4108/eetiot.5435
Cherniavska, T., Nadtochii, V., Nadtochyi, A., Lomonosov, D., Cieślak, R., Cherniavskyi, B. et al.; Cherniavska, T. (Ed.) (2025). Organizational and structural modeling of the integration of marine robotics into multilevel environmental and ecological monitoring systems. Ecological systems modeling. Tallinn: Scientific Route OÜ, 169–195. https://doi.org/10.21303/978-9908-9706-6-0.ch8
Downloads
Pages
43-72
Text Identifier of this Chapter
Chapter 2
Published
February 23, 2026
Copyright (c) 2026 Pavlo Mykhalichenko, Tetiana Cherniavska, Bohdan Cherniavskyi, Viktor Nadtochii, Anatolii Nadtochyi, Maiia Korkh
How to Cite
Mykhalichenko, P., Cherniavska, T., Cherniavskyi, B., Nadtochii, V., Nadtochyi, A., & Korkh, M. (2026). Solving pattern recognition problems in shipping monitoring systems based on CNN-models. In V. Lukin, S. Kryvenko, F. Li, S. Abramov, V. Abramova, B. Kovalenko, I. Dohtiev, O. Arkhipov, N. Stojanović, B. Bondžulić, P. Mykhalichenko, T. Cherniavska, B. Cherniavskyi, V. Nadtochii, A. Nadtochyi, M. Korkh, Zghurska О., S. Kasian, K. Nakonechna, … I. Kalinichenko, Pattern recognition in surveillance systems and diagnostics (pp. 43-72). Scientific Route OÜ®. https://doi.org/10.21303/978-9908-845-05-0.ch2
