• Mr. Madhusudhan S
• Suresha D

This research presents a rigorously engineered approach for the precise detection of ships in Synthetic Aperture Radar (SAR) imagery, employing the cutting-edge YOLOv8 deep learning framework. SAR data, inherently robust to variations in weather and lighting, is extensively utilized in maritime surveillance operations due to its capacity to deliver high-resolution imaging in complex environments. A high-quality dataset comprising 5,604 expertly annotated SAR images from the HRSID repository was employed to train and validate the detection model. The YOLOv8 architecture, recognized for its superior convergence characteristics and optimal trade-off between computational efficiency and detection accuracy, was meticulously optimized to capture the unique radiometric and geometric characteristics of SAR scenes. Quantitative assessments of the model yielded a precision of 89.32%, a recall of 78.72%, and a mean Average Precision (mAP) of 88.30%, demonstrating its robustness and high reliability. The results affirm the model’s suitability for real-time operational deployment in ship detection tasks, contributing significantly to the advancement of autonomous maritime monitoring and strategic situational awareness systems.

Synthetic Aperture Radar (SAR), Ship Detection, YOLOv8, Maritime Surveillance, Deep Learning

"YOLOV8-BASED ROBUST SHIP DETECTION IN SYNTHETIC APERTURE RADAR IMAGERY FOR MARITIME SURVEILLANCE", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.12, Issue 7, page no.100-105, July-2025, Available :http://www.jetir.org/papers/JETIRGX06018.pdf

"YOLOV8-BASED ROBUST SHIP DETECTION IN SYNTHETIC APERTURE RADAR IMAGERY FOR MARITIME SURVEILLANCE", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.12, Issue 7, page no. pp100-105, July-2025, Available at : http://www.jetir.org/papers/JETIRGX06018.pdf