Accurately identifying targets in the presence of noise remains a major challenge for Synthetic Aperture Radar (SAR) systems, particularly under low Signal-to-Noise Ratio (SNR) conditions. This study presents a Deep Learning (DL)-based framework for Single and Multiple Target Localization (SMTL) in SAR systems. A Linear Frequency Modulated Continuous Wave (LFMCW) signal model is formulated within a Compressive Sensing (CS) framework to enhance sparsity and resolution. The resulting Sample Covariance Matrix (SCM) is processed as a multi-channel input by a Convolutional Neural Network (CNN) to enable precise range estimation. The proposed model exhibits robust performance under severe noise conditions, achieving high localization accuracy even at SNR levels as low as −15 dB, thereby outperforming existing state-of-the-art methods in both accuracy and noise resilience.

This paper presents a novel Compressive Sensing (CS) algorithm for Synthetic Aperture Radar (SAR) imaging, designed to overcome the resolution limitations found in conventional methods, particularly in low Signal-to-Noise Ratio (SNR) scenarios. By employing Millimeter-wave SAR, the proposed approach offers a robust solution for precise object detection and localization challenges. The study models SAR imaging using Linear Frequency Modulated signals to meet the requirements of the CS framework. Performance evaluations are conducted across various noise levels to assess the effectiveness of the proposed Modified-Orthogonal Matching Pursuit (M-OMP) algorithm. This algorithm is compared with other established algorithms, including Orthogonal Matching Pursuit, Compressive Sampling Matching Pursuit (CoSaMP), and Adaptive CoSaMP (A-CoSaMP). Results indicate that the M-OMP algorithm outperforms the other algorithms presented in this paper and surpasses existing methods in the literature in accurately identifying and localizing targets, even in low SNR conditions as -10 dB.

This paper presents an innovative Compressive Sensing (CS) based algorithm for synthetic aperture radar (SAR) imaging, aimed at achieving high-resolution imaging. Traditional imaging algorithms often need large amounts of raw data and substantial storage capacity to generate clear target images. In this context, we propose the utilization of a Linear Frequency Modulated (LFM) signal, which offers superior range resolution while reducing complexity even under low Signal-to-Noise Ratio (SNR) conditions. Initially, our proposed work formulates the LFMCW SAR imaging model with the CS framework. Subsequently, we apply both 1D and 2D Orthogonal Matching Pursuit (OMP) methods to reconstruct the SAR images. Additionally, we extend this approach to handle the reconstruction with non-uniform sampled signals, leveraging their inherent sparsity. By adopting our proposed algorithm, we achieve clear target localization and enhanced image quality by effectively mitigating computational complexity, particularly in noisy environments. These results surpass the capabilities of existing methods documented in the literature.

In the Synthetic Aperture Radar (SAR) research environment Imaging concept plays a very important role. However, many challenges and complexities to forming an image, and many algorithms were developed accordingly. Most of the algorithms were developed by approaching the conventional SAR imaging algorithms like Delay and Sum algorithm (DAS) and Back Projection Algorithm (BPA). This paper presents an overview of these two significant SAR imaging algorithms. The preliminary objective of this paper is to summarize the fundamentals, challenges, and latest advancements in SAR imaging by providing their mathematical framework. We briefly presented the state of the art of SAR imaging and implementations. Also, we compared the algorithms in metrics of noisy environments, execution time, and image resolution for the different algorithms used.