Radar target detection under correlated non-Gaussian clutter using transfer learning

Date

2025-1

Author

Ürgüp, Mehmet Zeki

Metadata

Show full item record

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

Item Usage Stats

154
views

123
downloads

Cite This

In radar signal processing, accurate detection of targets in the presence of noise and clutter is critical for systems like autonomous vehicles and military defense. In linear frequency modulated continuous wave radar, reflected signals are often degraded by noise and clutter, complicating target detection. Recent advancements in deep learning, particularly convolutional neural networks and transfer learning, offer promising solutions for enhancing signal detection. This thesis explores the integration of ResNet models for multi-target detection, comparing their performance with traditional constant false alarm rate algorithms and adaptive normalized matched filters in addressing correlated non-Gaussian clutter and low signal-to-clutter-plus-noise ratios. Our method outperforms conventional and state-of-the-art techniques using pretrained models with high nonlinear representation capability in terms of probability of detection, offering a robust solution for radar signal processing.

Subject Keywords

Target detection, Deep learning, Transfer learning, Non-Gaussian, Correlated clutter

URI

https://hdl.handle.net/11511/113378

Collections

Graduate School of Natural and Applied Sciences, Thesis