The Effect of SRCNN-Based Preprocessing on YOLOv8 Performance in Ship Detection with SAR Images

Öz

This study investigates the effect of SRCNN-based preprocessing on the performance of the YOLOv8 model used for ship detection in Synthetic Aperture Radar (SAR) images. Comparative experiments were conducted on raw and enhanced images by using the open-source SSDD dataset. The findings indicate that models trained with preprocessed data provide improvements in precision, recall, mAP@0,50 and mAP@0,50:0,95 metrics, and generate more stable detections especially in scenes with complex backgrounds. 

Anahtar Kelimeler

• Synthetic Aperture Radar (SAR)
• Ship Detection
• YOLOv8
• SRCNN
• Deep Learning

SAR Görüntüleri ile Gemi Tespitinde SRCNN Tabanlı Ön İşlemenin YOLOv8 Performansına Etkisi

Öz

Bu çalışma, Sentetik Açıklıklı Radar (SAR) görüntülerinde gemi tespiti için kullanılan YOLOv8 modelinin performansı üzerinde SRCNN tabanlı ön işlemenin etkisini incelemektedir. Açık kaynaklı SSDD veri seti kullanılarak ham ve iyileştirilmiş görüntüler üzerinde karşılaştırmalı deneyler yürütülmüştür. Elde edilen bulgular, ön işleme uygulanan verilerle eğitilen modellerin kesinlik, duyarlılık ve mAP@0,50 ve mAP@0,50:0,95 ölçütlerinde iyileşme sağladığını ve özellikle yoğun arka plan içeren sahnelerde daha kararlı tespitler ürettiğini göstermektedir. 

Anahtar Kelimeler

• Sentetik Açıklıklı Radar (SAR)
• Gemi Tespiti
• YOLOv8
• SRCNN
• Derin Öğrenme

Etik Beyan

Bu çalışma etik kurul izni gerektiren insan veya hayvan deneyi içermemektedir. Araştırma açık erişimli veri setleri kullanılarak gerçekleştirilmiştir.

Teşekkür

Bu çalışmanın, 3-5 Şubat 2026 tarihleri arasında gerçekleşen Akademik Bilişim-2026 konferansında bildiri olarak sunumu yapılmış olup, emeği geçen tüm kurum, kuruluş ve kişilere teşekkürlerimi sunarım.

Kaynakça

1. Bao, W., Chen, S., Zhao, J., & Lin, X. (2025). YOLO-LDFI: A lightweight deformable feature-integrated detector for SAR ship detection. Journal of Marine Science and Engineering, 13(9), 1724. https://doi.org/10.3390/jmse13091724
2. Cao, S., Zhao, C., Dong, J., & Fu, X. (2024). Ship detection in synthetic aperture radar images under complex geographical environments, based on deep learning and morphological networks. Sensors, 24(13), 4290. https://doi.org/10.3390/s24134290
3. Cavli, B., & Çinarer, G. (2025). YOLO Based Ship Detection in SAR Images: In-Depth Analysis on HRSID, RSDD and SSDD Datasets. In 2025 IEEE 4th International Conference on Computing and Machine Intelligence (ICMI) (pp. 1-5). IEEE. https://doi.org/10.1109/ICMI65310.2025.11141036
4. Cruz, H., Véstias, M., Monteiro, J., Neto, H., & Duarte, R. P. (2022). A review of synthetic-aperture radar image formation algorithms and implementations: A computational perspective. Remote Sensing, 14(5), 1258. https://doi.org/10.3390/rs14051258
5. Dong, C., Loy, C. C., He, K., & Tang, X. (2015). Image super-resolution using deep convolutional networks. IEEE transactions on pattern analysis and machine intelligence, 38(2), 295-307. https://doi.org/ 10.1109/TPAMI.2015.2439281
6. Gonzalez, R. C., & Woods, R. E. (2018). Digital image processing (4. baskı). Pearson.
7. Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep feedforward networks. Deep learning, 1, 161-217.
8. Guan, T., Chang, S., Wang, C., & Jia, X. (2025). SAR small ship detection based on enhanced YOLO network. Remote Sensing, 17(5), 839. https://doi.org/10.3390/rs17050839

9. Ha, C. K., Nguyen, H., & Van, V. D. (2025). Yolo-sr: An optimized convolutional architecture for robust ship detection in sar imagery. Intelligent Systems with Applications, 26, 200538. https://doi.org/10.1016/j.iswa.2025.200538
10. He, R., Han, D., Shen, X., Han, B., Wu, Z., & Huang, X. (2025). AC-YOLO: A lightweight ship detection model for SAR images based on YOLO11. Plos one, 20(7), e0327362. https://doi.org/10.1371/journal.pone.0327362
11. Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2012). Imagenet classification with deep convolutional neural networks. Advances in neural information processing systems, 25.
12. Lin, T. Y., Dollár, P., Girshick, R., He, K., Hariharan, B., & Belongie, S. (2017). Feature pyramid networks for object detection. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 2117-2125).
13. Lu, P., Hao, X., Li, W., Yi, C., Kong, R., & Wang, T. (2025). ECF-YOLO: An enhanced YOLOv8 algorithm for ship detection in SAR images. Electronic Research Archive, 33(5). https://doi.org/ 10.3934/era.2025150
14. Meyer, F. (2019). Spaceborne synthetic aperture radar: Principles, data access, and basic processing techniques. Synthetic aperture radar (SAR) handbook: Comprehensive methodologies for forest monitoring and biomass estimation, 21-64.
15. Moreira, A., Prats-Iraola, P., Younis, M., Krieger, G., Hajnsek, I., & Papathanassiou, K. P. (2013). A tutorial on synthetic aperture radar. IEEE Geoscience and remote sensing magazine, 1(1), 6-43.
16. Rabbi, J., Ray, N., Schubert, M., Chowdhury, S., & Chao, D. (2020). Small-object detection in remote sensing images with end-to-end edge-enhanced GAN and object detector network. Remote Sensing, 12(9), 1432. https://doi.org/10.3390/rs12091432
17. Redmon, J., Divvala, S., Girshick, R., & Farhadi, A. (2016). You Only Look Once: Unified, Real-Time Object Detection. https://arxiv.org/abs/1506.02640. https://doi.org/10.48550/arXiv.1506.02640
18. Sapkota, R., Flores-Calero, M., Qureshi, R., Badgujar, C., Nepal, U., Poulose, A., ... & Karkee, M. (2025). YOLO advances to its genesis: A decadal and comprehensive review of the You Only Look Once (YOLO) series. Artificial Intelligence Review, 58(9), 274. https://doi.org/10.1007/s10462-025-11253-3
19. Shermeyer, J., & Van Etten, A. (2019). The effects of super-resolution on object detection performance in satellite imagery. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops.
20. Szeliski, R. (2022). Computer vision: algorithms and applications. Springer Nature.
21. Ultralytics. (2023). YOLOv8: Real-time object detection documentation and benchmarks. https://docs.ultralytics.com/
22. Wang, Z., Han, D., Han, B., & Wu, Z. (2025). OD-YOLOv8: A Lightweight and Enhanced New Algorithm for Ship Detection. Computer Systems Science & Engineering, 49(1), 377. https://doi.org/10.32604/csse.2025.059634
23. Yasir, M., Liu, S., Pirasteh, S., Xu, M., Sheng, H., Wan, J., ... & Li, J. (2024). YOLOShipTracker: Tracking ships in SAR images using lightweight YOLOv8. International Journal of Applied Earth Observation and Geoinformation, 134, 104137. https://doi.org/10.1016/j.jag.2024.104137
24. Yu, C., & Shin, Y. (2024). An efficient YOLO for ship detection in SAR images via channel shuffled reparameterized convolution blocks and dynamic head. ICT Express, 10(3), 673-679. https://doi.org/10.1016/j.icte.2024.02.007
25. Zhang, T., Zhang, X., Li, J., Xu, X., Wang, B., Zhan, X., ... & Wei, S. (2021). SAR ship detection dataset (SSDD): Official release and comprehensive data analysis. Remote Sensing, 13(18), 3690. https://doi.org/10.3390/rs13183690
26. Zhao, X., Li, S., Chu, Z., Zhang, Y., Hao, P., Yan, T., ... & Ning, H. (2026). Denoising-Enhanced YOLO for Robust SAR Ship Detection. arXiv preprint arXiv:2602.23820. https://doi.org/10.48550/arXiv.2602.23820