Radar ve Elektro-Optik Görüntüler Kullanılarak Derin Öğrenme Tabanlı Deniz Aracı Sınıflandırması ve Hedef Tanıma

Abstract

Kritik deniz alanları, stratejik öneme sahip gelişmiş askerî teçhizatlara dayalı olarak sürekli gözetim ve koruma gerektirmektedir. Bu sistemlerden elde edilen görüntülerin yorumlanması, durumsal farkındalık ve karar verme süreçleri açısından büyük önem taşımaktadır. Bunun yanı sıra, deniz lojistiği küresel ticaretin temel taşlarından biri hâline gelmiş olup, gemi türlerinin sınıflandırılması ve birbirinden ayırt edilmesi; taşımacılık verimliliğinin artırılması, depolama maliyetlerinin azaltılması ve güvenliğin güçlendirilmesi açısından kritik bir rol oynamaktadır. Bu çalışma, farklı deniz görevlerinde faaliyet gösteren gemilerin sınıflandırılmasına odaklanmakta olup, özellikle askerî gemilerin tespiti ve tanımlanmasını ön plana çıkarmaktadır. Yüksek doğrulukta gemi sınıflandırması elde edebilmek amacıyla derin öğrenme tabanlı bir yaklaşım benimsenmiştir. Kamuya açık kaynaklardan web kazıma (web scraping) teknikleri kullanılarak kapsamlı bir gemi görüntü veri kümesi oluşturulmuştur. Derin öğrenme, yüksek seviyeli anlamsal özellikleri çıkarabilme ve karmaşık örüntüleri daha etkin şekilde öğrenebilme yeteneği nedeniyle geleneksel makine öğrenmesi yöntemlerine tercih edilmiştir. Derin öğrenme modelleri, sınıflandırma performansını optimize etmek amacıyla bu veri kümesi üzerinde eğitilmiş ve test edilmiştir. Deneysel sonuçlar, %94 ile %99 arasında değişen sınıflandırma doğrulukları elde edildiğini göstermiş olup, önerilen yaklaşımın etkinliğini açıkça ortaya koymaktadır. Bu çalışma, elde edilen bilimsel bulguları sunmakta, sonuçların etkilerini tartışmakta ve deniz gözetleme ile güvenlik alanındaki potansiyel uygulamaları irdelemektedir.

Keywords

• Derin Öğrenme
• Gemi Sınıflandırması
• Radar Görüntüleri
• Elektro-Optik Sistemler
• Yapay Zekâ
• Görüntü İşleme

Deep Learning-Based Maritime Vessel Classification for Target Recognition Using Radar and Electro-Optic Imaging

Abstract

Critical maritime areas require continuous surveillance and protection, relying on advanced military equipment of strategic importance. The interpretation of images obtained from these systems is essential for situational awareness and decision-making. Moreover, maritime logistics has become a cornerstone of global trade, making the classification and differentiation of ship types crucial for optimizing transportation efficiency, reducing storage costs, and enhancing security. This study focuses on the classification of ships engaged in various maritime missions, with an emphasis on military vessel detection and identification. To achieve high-accuracy ship classification, a deep learning-based approach was adopted. A comprehensive dataset of ship images was constructed using web scraping techniques from publicly available sources. Deep learning was preferred over traditional machine learning techniques due to its ability to extract high-level semantic features and learn complex patterns more effectively. The deep learning models were trained and evaluated on this dataset to optimize classification performance. Experimental results demonstrated classification accuracies ranging from 94% to 99%, highlighting the effectiveness of the proposed approach. This study presents the scientific findings, discusses the implications of the results, and explores potential applications in maritime surveillance and security.

Keywords

• Deep Learning
• Ship Classification
• Radar Images
• Electro-Optic Systems
• Artificial Intelligence
• Image Processing

References

1. [1] Yang, S., Cao, Z., Liu, N., Sun, Y., Wang, Z. 2024. Maritime Electro-Optical Image Object Matching Based on Improved YOLOv9. Electronics, 13(14), 1-16.
2. [2] Javed, M. F., Imam, M. O., Adnan, M., Murtza, I., Kim, J. Y. 2024. Maritime Object Detection by Exploiting Electro-Optical and Near-Infrared Sensors Using Ensemble Learning. Electronics, 13(18), 3604.
3. [3] Wang, L. vd. 2021. A Review of Methods for Ship Detection with Electro-Optical Images in Marine Environments. Journal of Marine Science and Engineering, 9(12), 1351.
4. [4] Zhao, T. vd. 2024. Ship Detection with Deep Learning in Optical Remote-Sensing Images: A Survey of Challenges and Advances. Remote Sensing, 16(7), 1185.
5. [5] Yu, M., Han, S., Wang, T., Wang, H. 2022. An Approach to Accurate Ship Image Recognition in a Complex Maritime Transportation Environment. Journal of Marine Science and Engineering, 10(12), 1840.
6. [6] Wang, Y., Wang, C., Zhang, H. 2018. Ship Classification in High-Resolution SAR Images Using Deep Learning of Small Datasets. Sensors, 18(9), 2929.
7. [7] Kim, K., Hong, S., Choi, B., Kim, E. 2018. Probabilistic Ship Detection and Classification Using Deep Learning. Applied Sciences, 8(6), 936.
8. [8] Patel, K., Bhatt, C., Mazzeo, P. L. 2022. Deep Learning-Based Automatic Detection of Ships: An Experimental Study Using Satellite Images. Journal of Imaging, 8(7), 179.

9. [9] Gupta, H., Verma, O. P., Sharma, T. K., Varshney, H., Agarwal, S., Pak, W. 2024. Ship Detection Using Ensemble Deep Learning Techniques from Synthetic Aperture Radar Imagery. Scientific Reports, 14, 1963.
10. [10] Yang, J., Zheng, Y., Xu, W., Sun, P., Bai, S. 2024. An Accurate and Robust Multimodal Template Matching Method Based on Center-Point Localization in Remote Sensing Imagery. Remote Sensing, 16(15), 2765.
11. [11] Lowe, D. G. 2004. Distinctive Image Features from Scale-Invariant Keypoints. International Journal of Computer Vision, 60(2), 91-110.
12. [12] Dolapci, B., Özcan, C. 2021. Automatic Ship Detection and Classification Using Machine Learning from Remote Sensing Images on Apache Spark. Journal of Intelligent Systems: Theory and Applications, 4(1), 94-102.
13. [13] Wang, P. vd. 2023. Understanding Deep Representation Learning via Layerwise Feature Compression and Discrimination. arXiv:2311.02960. http://arxiv.org/abs/2311.02960 (Erişim Tarihi: 25.03.2025).
14. [14] Kaya, M., Ulutürk, S., Çetin Kaya, Y., Altıntaş, O., Karaca, Y. 2023. Optimization of Several Deep CNN Models for Waste Classification. Sakarya University Journal of Computer and Information Sciences, 6(2), 91-104.
15. [15] Shi, Q., Li, W., Tao, R., Sun, X., Gao, L. 2019. Ship Classification Based on Multifeature Ensemble with Convolutional Neural Network. Remote Sensing, 11(4), 419.
16. [16] Ramakrishnan, P., Sivagurunathan, P. T., Kumar, N. S. 2019. Fruit Classification Based on Convolutional Neural Network. International Journal of Control and Automation, 12(6), 232-239.
17. [17] Jiang, P., Ergu, D., Liu, F., Cai, Y., Ma, B. 2021. A Review of YOLO Algorithm Developments. Procedia Computer Science, 199, 1066-1073.
18. [18] Woo, S., Park, J., Lee, J. Y., Kweon, I. S. 2018. CBAM: Convolutional Block Attention Module. Proceedings of the European Conference on Computer Vision, 3-19.
19. [19] Chen, L., Hu, Z., Chen, J., Sun, Y. 2025. SVIADF: Small Vessel Identification and Anomaly Detection Based on Wide-Area Remote Sensing Imagery and AIS Data Fusion. Remote Sensing, 17(2), 336.
20. [20] Buscema, P. M., Massini, G., Raimondi, G., Caporaso, G., Breda, M., Petritoli, R. 2023. A Pattern Recognition Analysis of Vessel Trajectories. Algorithms, 16(9), 420.
21. [21] Zhang, T., Zhang, X., Shi, J., Wei, S. 2019. Balance Scene Learning Mechanism for Ship Detection in Optical Remote Sensing Images. IEEE Transactions on Geoscience and Remote Sensing, 57(7), 4645-4658.
22. [22] Petković, M., Vujović, I., Lušić, Z., Šoda, J. 2023. Image Dataset for Neural Network Performance Estimation with Application to Maritime Ports. Journal of Marine Science and Engineering, 11(3), 487.
23. [23] Yang, Z., Lai, Y., Zhou, H., Tian, Y., Qin, Y., Lv, Z. 2023. Improving Ship Detection Based on Decision Tree Classification for High Frequency Surface Wave Radar. Journal of Marine Science and Engineering, 11(3), 541.
24. [24] Yan, Z., Song, X., Zhong, H., Yang, L., Wang, Y. 2022. Ship Classification and Anomaly Detection Based on Spaceborne AIS Data Considering Behavior Characteristics. Sensors, 22(20), 7848.
25. [25] Chen, L., Shi, W., Fan, C., Zou, L., Deng, D. 2020. A Novel Coarse-to-Fine Method of Ship Detection in Optical Remote Sensing Images Based on a Deep Residual Dense Network. Remote Sensing, 12(19), 3112.
26. [26] Wang, Y., Wang, C., Zhang, H., Dong, Y., Wei, S. 2019. Automatic Ship Detection Based on RetinaNet Using Multi-Resolution Gaofen-3 Imagery. Remote Sensing, 11(5), 531.
27. [27] Choi, K., Yi, J., Park, C., Yoon, S. 2021. Deep Learning for Anomaly Detection in Time-Series Data: Review, Analysis and Guidelines. IEEE Access, 9, 120043-120065.
28. [28] Li, J., Du, X., Martins, J. R. R. A. 2022. Machine Learning in Aerodynamic Shape Optimization. Progress in Aerospace Sciences, 134, 100849.
29. [29] Azam, Z., Islam, M. M., Huda, M. N. 2023. Comparative Analysis of Intrusion Detection Systems and Machine Learning-Based Model Analysis Through Decision Tree. IEEE Access, 11, 80348-80391.
30. [30] Ali, S. vd. 2023. Explainable Artificial Intelligence (XAI): What We Know and What Is Left to Attain Trustworthy Artificial Intelligence. Information Fusion, 99, 101805.
31. [31] Baduge, S. K. vd. 2022. Artificial Intelligence and Smart Vision for Building and Construction 4.0: Machine and Deep Learning Methods and Applications. Automation in Construction, 141, 104440.
32. [32] Shafiq, M., Gu, Z. 2022. Deep Residual Learning for Image Recognition: A Survey. Applied Sciences, 12(18), 8972.
33. [33] Cuomo, S., Di Cola, V. S., Giampaolo, F., Rozza, G., Raissi, M., Piccialli, F. 2022. Scientific Machine Learning Through Physics-Informed Neural Networks: Where We Are and What’s Next. Journal of Scientific Computing, 92(3), 81.
34. [34] Tan, M., Le, Q. V. 2019. EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks. Proceedings of the International Conference on Machine Learning, 6105-6114.
35. [35] He, K., Zhang, X., Ren, S., Sun, J. 2016. Deep Residual Learning for Image Recognition. Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, 770-778.
36. [36] Fakhrabadi, A. K., Shahbazzadeh, M. J., Jalali, N., Eslami, M. 2025. A Hybrid Inception-Dilated-ResNet Architecture for Deep Learning-Based Prediction of COVID-19 Severity. Scientific Reports, 15, 6490.
37. [37] Isohanni, J. 2025. Customised ResNet Architecture for Subtle Color Classification. International Journal of Computer Applications, 187(21), 7-12.
38. [38] Mondal, M. K., Debnath, S. 2025. HHT Based Protection for Series Compensated Double Circuit Transmission Lines Considering Evolving and Cross-Country Faults. Engineering Research Express, 7(1), 015003.
39. [39] Bowman, D. C., Lees, J. M. 2013. The Hilbert-Huang Transform: A High Resolution Spectral Method for Nonlinear and Nonstationary Time Series. Seismological Research Letters, 84(6), 1074-1080.
40. [40] Dong, R., Cai, D., Asai, N. 2017. Nonlinear Dance Motion Analysis and Motion Editing Using Hilbert-Huang Transform. Proceedings of the 2017 ACM International Conference on Computer Graphics and Interactive Techniques in Australasia and Southeast Asia, 1-4.