DETECTION OF SMALL AND MEDIUM SIZED SHIPS IN SATELLITE IMAGES USING YOLO MODELS

Year 2025, Volume: 3 Issue: 1, 17 - 27, 27.06.2025

Mohamed Emara , Yasmeen Abushawareb , Eftal Şehirli

https://doi.org/10.71074/CTC.1636434

Abstract

Ship detection in satellite images is an essential part of maritime security and surveillance. This work presents a helper tool for its growth. The three models presented in this paper use YOLOv8 and YOLOv5 with colored and grayscale satellite photos to recognize small and medium-sized ships, which are frequently hard to spot in satellite photographs. Performance parameters such as mean average precision (mAP), recall, and accuracy were assessed. The models’ accuracy and recall ranged from 0.87 to 0.93 and 0.84 to 0.86, respectively, according to the results. This work uncovered a comparable performance for both grayscale and colored images and acceptable detection accuracy. In satellite images, Model 2 and Model 3 demonstrated efficacy in identifying small and medium-sized ships.

Keywords

Ship detection , YOLO , satellite images , image preprocessing , maritime surveillance.

References

• P. Heiselberg, H. B. Pedersen, K. A. Sørensen, and H. Heiselberg, “Identification of Ships in Satellite Images,” IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol. 17, pp. 6045–6055, 2024.
• B. Lebona, W. Kleynhans, T. Celik, and L. Mdakane, “Ship Detection Using VIIRS Sensor Specific Data,” in Proc. 2016 IEEE Int. Geoscience and Remote Sensing Symp. (IGARSS), Beijing, China, July 10–15, 2016, pp. 7729315. DOI: 10.1109/IGARSS.2016.7729315.
• G. Cheng, X. Xie, J. Han, L. Guo, and G.-S. Xia, “Remote Sensing Image Scene Classification Meets Deep Learning: Challenges, Methods, Benchmarks, and Opportunities,” IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol. 13, pp. 3735–3756, 2020.
• Z. Lin, K. Ji, X. Leng, and G. Kuang, “Squeeze and Excitation Rank Faster R-CNN for Ship Detection in SAR Images”, IEEE Geoscience and Remote Sensing Letters, vol. 16, no. 5, pp. 751–755, May 2019.
• T. Zhang, X. Zhang, J. Li, X. Xu, B. Wang, X. Zhan, Y. Xu, X. Ke, T. Zeng, H. Su, I. Ahmad, D. Pan, C. Liu, Y. Zhou, and J. Shi, “SAR Ship Detection Dataset (SSDD): Official Release and Comprehensive Data Analysis,” Remote Sensing, vol. 13, no. 18, article 3690, 2021. DOI: 10.3390/rs13183690.
• D. Barretta, L. M. Millefiori, and P. Braca, “Analytical Classification Performance Analysis of Machine-Learning-Based Ship Detection from Optical Satellite Imagery,” in Proc. 2024 IEEE Int. Geoscience and Remote Sensing Symp. (IGARSS), Athens, Greece, 2024, DOI: 10.1109/IGARSS53475.2024.10642217.
• J. S. Rubikumar, “Efficient ship detection system for maritime surveillance using deep learning approach,” International Journal for Multidisciplinary Research (IJFMR), vol. 6, no. 5, pp. 1–11, Sept.–Oct. 2024. E-ISSN: 2582-2160. Available: https://www.ijfmr.com.
• B. C. Perez, “Real-time Ship Recognition and Georeferencing for the Improvement of Maritime Situational Aware- ness,” Doctoral Thesis, Faculty 3 – Mathematics and Computer Science, University of Bremen, 2024. Available: arXiv:2410.04946 [cs.CV].
• C. Tian, Z. Lv, F. Xue, X. Wu, and D. Liu, “Multi-Domain Joint Synthetic Aperture Radar Ship Detection Method Integrating Complex Information with Deep Learning,” Remote Sensing, vol. 16, no. 19, article 3555, 2024. DOI: 10.3390/rs16193555.
• M. J. Er, Y. Zhang, J. Chen, and W. Gao, “Ship detection with deep learning: a survey,” Artificial Intelligence Review, vol. 56, no. 10, pp. 11825–11865, Mar. 2023. doi: 10.1007/s10462-023-10455-x.
• B. Li, X. Xie, X. Wei, and W. Tang, “Ship detection and classification from optical remote sensing images: A survey,”Chinese Journal of Aeronautics, vol. 33, no. 10, pp. 1000-9361, 2020. DOI: 10.1016/j.cja.2020.09.022.
• Z. Liu, L. Yuan, L. Weng, and Y. Yang, “A High Resolution Optical Satellite Image Dataset for Ship Recognition and Some New Baselines,” in Proc. 6th Int. Conf. Pattern Recognition Applications and Methods (ICPRAM 2017), 2017, pp. 324-331. DOI: 10.5220/0006120603240331.
• Z. Liu, J. Hu, L. Weng, and Y. Yang, “Rotated Region Based CNN for Ship Detection,” in Proc. 2017 IEEE Int. Conf. Image Processing (ICIP), Beijing, China, 2017, pp. 900-904. DOI: 10.1109/ICIP.2017.8296411.
• R. Girshick, J. Donahue, T. Darrell, and J. Malik, “Rich feature hierarchies for accurate object detection and semantic segmentation,” in Proc. 2014 IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), Columbus, OH, USA, 2014, pp. 580–587. DOI: 10.1109/CVPR.2014.81.
• J. Koo, J. Seo, S. Jeon, J. Choe, and T. Jeon, “RBox-CNN: Rotated bounding box based CNN for ship detection in remote sensing image,” in Proc. 26th ACM SIGSPATIAL Int. Conf. Adv. Geographic Inf. Syst. (SIGSPATIAL ’18), Seattle, WA, USA, Nov. 2018, pp. 420–423. doi: 10.1145/3274895.3274915.
• X. Yang, H. Sun, K. Fu, J. Yang, X. Sun, M. Yan, and Z. Guo, “Automatic ship detection in remote sensing images from Google Earth of complex scenes based on multiscale rotation dense feature pyramid networks,” Remote Sens., vol. 10, no. 1, p. 132, 2018. DOI: 10.3390/rs10010132.
• M. Li, W. Guo, Z. Zhang, W. Yu, and T. Zhang, “Rotated region based fully convolutional network for ship detection,” in Proc. IGARSS, 2018, pp. 673. IEEE. DOI: 10.1109/IGARSS.2018.8517926.
• M. Liao, Z. Zhu, B. Shi, G. Xia, and X. Bai, “Rotation-sensitive regression for oriented scene text detection,” in Proc. CVPR, 2018, pp. 5909–5918. IEEE. DOI: 10.1109/CVPR.2018.00619.
• L. Liu, Y. Bai, and Y. Li, “Locality-aware rotated ship detection in high-resolution remote sensing imagery based on multiscale convolutional network,” IEEE Geoscience and Remote Sensing Letters, vol. 19, p. 3502805, 2022. DOI: 10.1109/LGRS.2021.3115732.