PERFORMANCE EVALUATION OF YOLOV8 AND YOLOV9 ALGORITHMS IN SHIP DETECTION APPLICATION

Öz

The detection and classification of vessels represents a pivotal challenge in the domain of maritime surveillance and monitoring. Its applications encompass a diverse range of fields, including fisheries management, migrant monitoring, maritime rescue operations, and maritime warfare. The utilisation of remote sensing technologies for the tracking of ships is a consequence of the advantages they offer, including extensive coverage and low-cost accessibility. This study emphasizes the importance of human detection, counting and tracking of objects using computer vision and machine learning methods. In this study, the potential of YOLO architectures as a technology for rapid and precise ship detection and classification is explored. The YOLOv8 and YOLOv9 architectures were employed for the detection of ships utilising remote sensing techniques. This study compares the performance of the YOLOv8 and YOLOv9 architectures using a dataset, referred to as the "Ships in Google Earth" dataset, which consists of 1658 images for ship detection. The models were evaluated in terms of training and validation losses, precision, recall and average precision, and demonstrated a certain degree of success and learning speed during the training process. Both models were found to provide effective solutions for ship detection. However, the YOLOv9 model exhibited superior performance in terms of faster convergence and overall detection accuracy, particularly at the outset.

Anahtar Kelimeler

• Convolutional neural network
• deep learning
• ship detection
• yolov8
• yolov9

GEMİ TESPİTİ UYGULAMASINDA YOLOV8 VE YOLOV9 ALGORİTMALARININ PERFORMANS DEĞERLENDİRMESİ

Öz

Gemi tespiti ve sınıflandırması, deniz gözetimi ve izleme alanında kritik bir konu olup; balıkçılık yönetimi, göçmen izleme, deniz kurtarma ve deniz savaşlarına kadar geniş bir yelpazede uygulanmaktadır. Uzaktan algılama teknolojileri, geniş kapsama alanı ve düşük maliyetli erişim gibi avantajları nedeniyle gemi izleme için kullanılmaktadır. Bu çalışma, nesnelerin insan tarafından tespiti, sayımı ve takibi süreçlerinin bilgisayarlı görme ve makine öğrenmesi yöntemleri ile gerçekleştirilmesinin önemini vurgulamaktadır. Bu çalışmada, YOLO mimarileri, gemi tespiti ve sınıflandırmasının hızlı ve doğru bir şekilde yapılabilmesi için kullanılan bir teknoloji olarak ele alınmaktadır. YOLOv8 ve YOLOv9 mimarileri ile uzaktan algılama kullanılarak gemi tespiti çalışmaları gerçekleştirilmiştir. Gemi tespiti için 1658 görüntüden oluşan "Ships in Google Earth" adlı veri seti kullanılarak YOLOv8 ve YOLOv9 mimarilerinin performansını karşılaştırmaktadır. Eğitim ve doğrulama kayıpları, kesinlik, duyarlılık ve ortalama hassasiyet kriterleri açısından değerlendirilen modeller, eğitim sürecinde belirli bir başarı ve öğrenme hızı sergilemiştir. Her iki modelin de gemi tespitinde etkili çözümler sunduğu görülmüştür. Ancak, YOLOv9 modeli, özellikle başlangıçta daha hızlı yakınsama ve genel tespit performansında üstünlük sağlamıştır.

Anahtar Kelimeler

• Evrişimsel sinir ağı
• derin öğrenme
• gemi tespiti
• yolov8
• yolov9

Kaynakça

1. M. Çelik, F. Akar, C. Bayılmış, D. Akgün, A real-time valve counting system based on YOLOv8, in: 2024 8th International Artificial Intelligence and Data Processing Symposium (IDAP), IEEE, 2024, pp. 1–5, https://doi.org/10.1109/IDAP64064.2024.10710962.
2. H. Li, L. Deng, C. Yang, J. Liu, Z. Gu, Enhanced YOLO v3 Tiny Network for Real-Time Ship Detection from Visual Image, IEEE Access 9 (2021) 16692–16706, https://doi.org/10.1109/ACCESS.2021.3053956.
3. C. Zhang, X. Zhang, G. Gao, H. Lang, G. Liu, C. Cao, Y. Song, Y. Guan, Y. Dai, Development and Application of Ship Detection and Classification Datasets: A review, IEEE Geosci Remote Sens Mag (2024), https://doi.org/10.1109/MGRS.2024.3450681.
4. B. Li, X. Xie, X. Wei, W. Tang, Ship detection and classification from optical remote sensing images: A survey, Chinese Journal of Aeronautics 34 (2021) 145–163, https://doi.org/10.1016/j.cja.2020.09.022.
5. Z. Zhao, K. Ji, X. Xing, H. Zou, S. Zhou, Ship surveillance by integration of space-borne SAR and AIS - Review of current research, Journal of Navigation 67 (2014) 177–189, https://doi.org/10.1017/S0373463313000659.
6. E. Chuvieco, Fundamentals of Satellite Remote Sensing: An Environmental Approach, n.d.
7. T. Zhao, Y. Wang, Z. Li, Y. Gao, C. Chen, H. Feng, Z. Zhao, Ship Detection with Deep Learning in Optical Remote-Sensing Images: A Survey of Challenges and Advances, Remote Sens (Basel) 16 (2024), https://doi.org/10.3390/rs16071145.
8. M.J. Er, Y. Zhang, J. Chen, W. Gao, Ship detection with deep learning: a survey, Artif Intell Rev 56 (2023) 11825–11865, https://doi.org/10.1007/s10462-023-10455-x.

9. A.F. Bayram, V. Nabiyev, Derin öğrenme tabanlı saklanan kamufle tankların tespiti: son teknoloji YOLO ağlarının karşılaştırmalı analizi, Gümüşhane Üniversitesi Fen Bilimleri Enstitüsü Dergisi (2023), https://doi.org/10.17714/gumusfenbil.1271208.
10. S. Wang, Y. Li, S. Qiao, ALF-YOLO: Enhanced YOLOv8 based on multiscale attention feature fusion for ship detection, Ocean Engineering 308 (2024), https://doi.org/10.1016/j.oceaneng.2024.118233.
11. Y. Gong, Z. Chen, W. Deng, J. Tan, Y. Li, Real-Time Long-Distance Ship Detection Architecture Based on YOLOv8, IEEE Access 12 (2024) 116086–116104, https://doi.org/10.1109/ACCESS.2024.3445154.
12. L. Ting, Z. Baijun, Z. Yongsheng, Y. Shun, Ship Detection Algorithm based on Improved YOLO V5, in: Proceedings - 2021 6th International Conference on Automation, Control and Robotics Engineering, CACRE 2021, Institute of Electrical and Electronics Engineers Inc., 2021, pp. 483–487, https://doi.org/10.1109/CACRE52464.2021.9501331.
13. X. Cao, J. Shen, T. Wang, C. Zhang, Ship Detection Based on Improved YOLOv8 Algorithm, in: 2024 3rd International Conference on Robotics, Artificial Intelligence and Intelligent Control, RAIIC 2024, Institute of Electrical and Electronics Engineers Inc., 2024, pp. 20–23, https://doi.org/10.1109/RAIIC61787.2024.10670907.
14. S. Liang, X. Liu, Z. Yang, M. Liu, Y. Yin, Offshore Ship Detection in Foggy Weather Based on Improved YOLOv8, J Mar Sci Eng 12 (2024), https://doi.org/10.3390/jmse12091641.
15. Z. Zhang, L. Tan, R.L.K. Tiong, Ship-Fire Net: An Improved YOLOv8 Algorithm for Ship Fire Detection, Sensors 24 (2024), https://doi.org/10.3390/s24030727.
16. C. Niu, D. Han, B. Han, Z. Wu, SAR-LtYOLOv8: A Lightweight YOLOv8 Model for Small Object Detection in SAR Ship Images, Computer Systems Science and Engineering 48 (2024) 1723–1748, https://doi.org/10.32604/csse.2024.056736.
17. T. Singh, T. Babu, R.R. Nair, P. Duraisamy, Ship Detection in Synthetic Aperture Radar Imagery: An Active Contour Model Approach in Computer Vision Deep Learning, in: Procedia Comput Sci, Elsevier B.V., 2024, pp. 1793–1802, https://doi.org/10.1016/j.procs.2024.04.170.
18. J. Redmon, S. Divvala, R. Girshick, A. Farhadi, You only look once: Unified, real-time object detection, in: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, IEEE Computer Society, 2016, pp. 779–788, https://doi.org/10.1109/CVPR.2016.91.
19. Y. Yin, H. Li, W. Fu, Faster-YOLO: An accurate and faster object detection method, Digital Signal Processing: A Review Journal 102 (2020), https://doi.org/10.1016/j.dsp.2020.102756.
20. M. Hussain, YOLO-v1 to YOLO-v8, the Rise of YOLO and Its Complementary Nature toward Digital Manufacturing and Industrial Defect Detection, Machines 11 (2023), https://doi.org/10.3390/machines11070677.
21. J. Terven, D.M. Córdova-Esparza, J.A. Romero-González, A Comprehensive Review of YOLO Architectures in Computer Vision: From YOLOv1 to YOLOv8 and YOLO-NAS, Mach Learn Knowl Extr 5 (2023) 1680–1716, https://doi.org/10.3390/make5040083.
22. J. Redmon, A. Farhadi, YOLO9000: Better, Faster, Stronger, (2016), http://arxiv.org/abs/1612.08242.
23. J. Redmon, A. Farhadi, YOLOv3: An Incremental Improvement, (2018), http://arxiv.org/abs/1804.02767.
24. A. Bochkovskiy, C.-Y. Wang, H.-Y.M. Liao, YOLOv4: Optimal Speed and Accuracy of Object Detection, (2020), http://arxiv.org/abs/2004.10934.
25. Q. Yu, Y. Han, X. Gao, W. Lin, Y. Han, Comparative Analysis of Improved YOLO v5 Models for Corrosion Detection in Coastal Environments, J Mar Sci Eng 12 (2024), https://doi.org/10.3390/jmse12101754.
26. C. Li, L. Li, H. Jiang, K. Weng, Y. Geng, L. Li, Z. Ke, Q. Li, M. Cheng, W. Nie, Y. Li, B. Zhang, Y. Liang, L. Zhou, X. Xu, X. Chu, X. Wei, X. Wei, YOLOv6: A Single-Stage Object Detection Framework for Industrial Applications, (2022), http://arxiv.org/abs/2209.02976.
27. C.-Y. Wang, A. Bochkovskiy, H.-Y.M. Liao, YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors, (2022), http://arxiv.org/abs/2207.02697.
28. M. Talib, A.H.Y. Al-Noori, J. Suad, YOLOv8-CAB: Improved YOLOv8 for Real-time Object Detection, Karbala International Journal of Modern Science 10 (2024) 56–68, https://doi.org/10.33640/2405-609X.3339.
29. J.J. Yen, Y.H. Pan, C.H. Wang, Deer Species and Gender Detection system based on YOLO v9, in: 11th IEEE International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2024, Institute of Electrical and Electronics Engineers Inc., 2024, pp. 463–464, https://doi.org/10.1109/ICCE-Taiwan62264.2024.10674650.
30. M. Sohan, T. Sai Ram, Ch.V. Rami Reddy, A Review on YOLOv8 and Its Advancements, in: 2024, pp. 529–545, https://doi.org/10.1007/978-981-99-7962-2_39.
31. S. Du, W. Pan, N. Li, S. Dai, B. Xu, H. Liu, C. Xu, X. Li, TSD-YOLO: Small traffic sign detection based on improved YOLO v8, IET Image Process 18 (2024) 2884–2898, https://doi.org/10.1049/ipr2.13141.
32. Y. Li, M. Wang, C. Wang, M. Zhong, A method for maize pest detection based on improved YOLO-v9 model, in: 2024 7th International Conference on Computer Information Science and Application Technology, CISAT 2024, Institute of Electrical and Electronics Engineers Inc., 2024, pp. 858–861, https://doi.org/10.1109/CISAT62382.2024.10695307.
33. Robin Public, Roboflow Universe, Https://Universe.Roboflow.Com/Robin-Public/Kaggle-Ships-in-Google-Earth-Dfqwt (2022).