GPR Closed-Loop Denoising Based on Bandpass Filtering Constraints

• Published in: IEEE transactions on geoscience and remote sensing 2024, Vol.62, p.1-14
• Main Authors: Liu, Xianghao, Liu, Sixin, Jia, Zhuo, Vogt, Declan, Tian, Sen, Liu, Xintong, Lu, Qi
• Format: Article
• Language: English
• Subjects: Artificial neural networks; Bandpass filters; Closed loops; Closed-loop network; convolutional neural network (CNN); Data analysis; Data processing; Data recovery; Datasets; Deep learning; Effectiveness; Filtering; Finite difference methods; Ground penetrating radar; ground penetrating radar (GPR); Image enhancement; Machine learning; Neural networks; Noise; noise attenuation; Noise prediction; Noise reduction; Permittivity; Radar; Radar attenuation; Redundancy; Reflection; Separation; Signal reconstruction; Signal reflection; Time-domain analysis; Training; Transforms
• ISSN: 0196-2892; 1558-0644
• DOI: 10.1109/TGRS.2024.3498868

Noise attenuation is crucial in ground-penetrating radar (GPR) data processing. In recent years, deep learning (DL) methods have shown excellent performance in GPR denoising tasks, but they typically focus only on recovering the target signal, which can lead to over-denoising. To enhance the generalizability and the practicality of denoising networks, we propose a strategy to generate random dielectric models from natural image datasets, which can quickly construct model datasets with low redundancy and reasonable distribution. To enhance the fidelity of GPR denoising, we leverage the powerful nonlinear fitting capabilities of convolutional neural networks (CNNs) and introduce a closed-loop denoising network framework for GPR. The framework consists of a denoising sub-network and a noise extraction sub-network, effectively achieving signal-noise separation in noised GPR data. Specifically, the denoising sub-network is used to recover weak reflection signals and initially remove noise, while the noise extraction sub-network is used to restore the true noise, mitigating the problem of over-denoising. A key innovation of our approach is the integration of bandpass filtering, which enhances the robustness of network training and supports effective weak signal recovery. This network framework forms a closed loop through the residual loss between the signal-noise separation results and the noised GPR data, the closed-loop structure is capable of further refining the signal and noise prediction results of the two subnetworks, thereby enhancing the numerical accuracy of the signal-to-noise separation results. Finally, the effectiveness of the GPR closed-loop denoising network is verified from multiple perspectives using both synthetic and field measured data. The results indicate that our proposed method is more competitive in GPR denoising tasks.