Abstract :

Ship Detection In Radar And Remote Sensing Imagery Is A Critical Component Of Maritime Surveillance, Navigation Safety, And National Defense. Recent Advances In Deep Learning Have Significantly Improved The Accuracy And Robustness Of Detection Frameworks For Synthetic Aperture Radar (SAR) And Airborne Radar Data. Traditional Ship Detection Methods Struggle With Complex Sea Clutter, Varying Target Scales, And Low Signal-to-noise Conditions, Prompting Research Into Convolutional Neural Networks (CNNs) And Region-based Detectors. Studies Have Demonstrated That Deep Learning Architectures Provide Superior Performance In SAR Ship Detection Tasks By Capturing Multiscale Spatial And Contextual Features [1]–[9]. Moreover, The Use Of Range-compressed Airborne Radar Data Has Enabled Enhanced Target Representation And Improved Detection Capability In Challenging Maritime Environments [10]– [14].Faster R-CNN And Its Improved Variants Have Emerged As Powerful Frameworks For Highprecision Object Detection Due To Their Efficient Region Proposal And Hierarchical Feature Extraction Mechanisms [15]–[18]. Alternative Single-shot Detectors Such As YOLO And SSD Have Contributed To Real-time Maritime Monitoring, Although With Varying Trade-offs Between Speed And Accuracy [19]–[22]. In Addition, Advancements In Remote Sensing– Oriented Deep Learning, Including Feature Pyramids, Residual Networks, And Transfer Learning, Have Expanded The Applicability Of CNN-based Models For Large-scale Maritime Datasets [23]–[25].This Research Leverages An Enhanced Faster R-CNN Architecture For Ship Detection On Range-compressed Airborne Radar Imagery, Aiming To Improve Detection Precision, Robustness In Complex Ocean Backgrounds, And Multi-scale Target Localization. The Study Integrates Insights From Recent SAR-based Detection Frameworks And Modern Object Detection Architectures To Deliver A More Reliable And Scalable Solution For Maritime Surveillance Applications. Keywords : Ship Detection, Faster R-CNN, Airborne Radar, Range-Compressed Data, SAR Imagery, Deep Learning, Maritime Surveillance, Object Detection, CNN, Remote Sensing.

Published:

29-11-2025

Issue:

Vol. 25 No. 11 (2025)

Page Nos:

315-321

Section:

Articles

License:

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

How to Cite