The rapid growth of China's shipping industry demands improved maritime management. Efficient vessel monitoring using SAR images is vital, yet current satellite resources and diverse target scales in SAR images pose challenges. This paper applies the YOLO11 model, leveraging its optimized architecture to improve detection speed, accuracy, and robustness. Experiments on multiple SAR vessel datasets, evaluated by precision, recall, F1 score, and mAP (mean Average Precision), demonstrate YOLO11’s effectiveness in detecting small-scale, sparsely distributed vessels while maintaining low inference times. The results highlight YOLO11’s potential for enhancing maritime monitoring and vessel surveillance efficiency, providing valuable insights for intelligent waterborne transportation.
YOLOv11 for SAR ship detection: advancements, performance, and applications in sea or inland waterway transportation
International Conference on Computer Graphics, Artificial Intelligence, and Data Processing (ICCAID 2024) ; 2024 ; Nanchang, China
Proc. SPIE ; 13560
2025-04-10
Conference paper
Electronic Resource
English
SOME INLAND WATERWAY TRANSPORTATION PROBLEMS
SAE Technical Papers | 1920
|PROBLEMS OF INLAND WATERWAY TRANSPORTATION
SAE Technical Papers | 1920
|Demand for inland waterway transportation
Engineering Index Backfile | 1966
|Some inland waterway transportation problems
Engineering Index Backfile | 1921
|