SAR-Net: multi-scale direction-aware SAR network via global information fusion
Deep learning has driven significant progress in object detection using Synthetic Aperture
Radar (SAR) imagery. Existing methods, while achieving promising results, often struggle to …
Radar (SAR) imagery. Existing methods, while achieving promising results, often struggle to …
SAR image super-resolution and target detection closed-loop network with edge enhancement and feature feedback
J Yujia, Z Siqian, T Tao… - IET International Radar …, 2023 - ieeexplore.ieee.org
Current super-resolution (SR) methods can effectively restore the global features, but these
features may not be relevant to the detection task, which results in constrained …
features may not be relevant to the detection task, which results in constrained …