Maritime vessel detection in satellite images address real time issues such as maritime security, illegal fishing and environmental monitoring, which require efficient tracking of vessels in large scale. Maritime vessel detection is challenged by limited annotated satellite datasets, varying sea conditions, and the presence of small or overlapping vessels. YOLOv10 is best for maritime vessel detection in satellite images due to its high accuracy, speed and efficiency in handling complex environments. It is able to detect small vessels against vast and cluttered backgrounds. YOLOv10 addresses these challenges through architectural features, which able to detect small objects like ships. It is scalable for tasks like illegal fishing detection and coastal security using satellite images. Using Masati-V2 dataset we have trained algorithms like YOLOv10s and YOLOv10m which are family of YOLOv10.Evaluation is performed using performance metrics which include precision and recall. According to our research, YOLOv10m model gives the best prediction for maritime vessel detection in satellite imagery.  Future research will concentrate on enhancing classification models to identify various vessel types, including smaller or overlapping ones, under diverse environmental conditions and also need to explore real-time vessel tracking using temporal data and predictive analytics can be explored to monitor vessels continuously across multiple satellite images for improved situational awareness.

Keywords - Satellite images, YOLOv10s, YOLOv10m, Maritime Vessel, YOLOv10

[1] M Mohidul Hossain Khan, Zonghua Liu, Radhakrishna Prabhu, Haiyong Zheng, and Asad Javied. “Ship detection and identification for maritime security and safety based on IMO numbers using deep learning”. In: Artificial Intelligence for Security and Defence Applications II. Vol. 13206. SPIE. 2024, pp. 70–77.

[2] ScienceDirect Topics. Satellite Imagery. Accessed: 2025- 04-16. 2024. URL: https://www.sciencedirect.com/topics/ nursing-and-health-professions/satellite-imagery.

[3] Serdar Kızılkaya, Ugur Alganci, and Elif Sertel. “Vhrships: An extensive benchmark dataset for scalable deep learningbased ship detection applications”. In: ISPRS International Journal of Geo-Information 11.8 (2022), p. 445.

[4] D. K. Prasad et al. “Challenges in video based object detection in maritime scenario using computer vision”. In: Journal Name or Conference Proceedings Volume Number.Issue Number (2021), Page Range. DOI: DOIorURL(ifavailable).

[5] Wei Li, Ming Zhang, and Hui Chen. “Enhancing Maritime Domain Awareness Through AI-Enabled Technologies”. In: Sensors 25.6 (2025), p. 1930. DOI: 10.3390/s25061930.

[6] “Monitoring vessel deadweight tonnage for maritime transportation surveillance using high resolution satellite image”. In: Ocean Coastal Management 239 (2023), p. 106607. ISSN: 0964-5691. DOI: https://doi.org/10.1016/ j.ocecoaman.2023.106607

[7] Xiu Ji, Zheyu Yue, Hongliu Yang, and Zehong Zhang. “Infrared Image Classification and Detection Algorithm for Power Equipment Based on Improved YOLOv10”. In: IEEE Access 12 (2024), pp. 184976–184988. DOI: 10.1109/ ACCESS.2024.3514103.

[8] Shizhao Kang, Ziyu Hu, Lianjun Liu, Kexin Zhang, and Zhiyu Cao. “Object Detection YOLO Algorithms and Their Industrial Applications: Overview and Comparative Analysis”. In: Electronics 14.6 (2025). ISSN: 2079-9292. DOI: 10 . 3390 / electronics14061104. URL: https : / / www. mdpi.com/2079-9292/14/6/1104.

[9] Hongrui Liu et al. “An Enhanced Algorithm for Detecting Small Traffic Signs Using YOLOv10”. In: Electronics 14.5 (2025). ISSN: 2079-9292. URL: https://www.mdpi.com/ 2079-9292/14/5/955.

[10] Chunling Chen et al. “YOLO-Based UAV Technology: A Review of the Research and Its Applications”. In: Drones 7.3 (2023). ISSN: 2504-446X. DOI: 10 . 3390 / drones7030190. URL: https://www.mdpi.com/2504-446X/ 7/3/190.

[11] “GD-YOLO: A lightweight model for household waste image detection”. In: Expert Systems with Applications 279 (2025), p. 127525. ISSN: 0957-4174. DOI: https://doi.org/ 10.1016/j.eswa.2025.127525.

[12] Suthir Sriram, Aburvan P., Arun Kaarthic T. P., Nivethitha Vijayaraj, and Thangavel Murugan. “Enhanced YOLOv10 Framework Featuring DPAM and DALSM for Real-Time Underwater Object Detection”. In: IEEE Access 13 (2025), pp. 8691–8708. DOI: 10.1109/ACCESS.2025.3527315.

[13] Navneet Dalal and Bill Triggs. “Histograms of oriented gradients for human detection”. In: 2005 IEEE computer society conference on computer vision and pattern recognition (CVPR’05). Vol. 1. Ieee. 2005, pp. 886–893.

[14] TechRadar. What are Convolutional Neural Networks? https://www.techradar.com/pro/what- are- convolutionalneural-networks. Accessed: 2025-04-16. 2025.

[15] Hao Li, Lianbing Deng, Cheng Yang, Jianbo Liu, and Zhaoquan Gu. “Enhanced YOLO v3 tiny network for realtime ship detection from visual image”. In: Ieee Access 9 (2021), pp. 16692–16706.

[16] Wang Pu et al. “YOLOv5 ship: An improved ship target detection algorithm study”. In: Proceedings of the 2023 7th International Conference on Advances in Artificial Intelligence. 2023, pp. 106–116.

[17] SeaDronesSee Dataset. https : / / paperswithcode . com / dataset/seadronessee. Accessed: 2025-04-16

[18] Airbus Ship Detection Dataset. https : / / www . researchgate . net / publication / 335459260 Airbus Ship Detection Dataset. Accessed: 2025-04-16.

[19] Ao Wang et al. “Yolov10: Real-time end-to-end object detection”. In: Advances in Neural Information Processing Systems 37 (2024), pp. 107984–108011.

[20] Connor Shorten and Taghi M Khoshgoftaar. “A survey on image data augmentation for deep learning”. In: Journal of big data 6.1 (2019), pp. 1–48.