Ground-penetrating radar (GPR), as a non-invasive instrument, has been widely used in civil engineering. In GPR B-scan images, there may exist random noise due to the influence of the environment and equipment hardware, which complicates the interpretability of the useful information. Many methods have been proposed to eliminate or suppress the random noise. However, the existing methods have an unsatisfactory denoising effect when the image is severely contaminated by random noise. This paper proposes a multi-scale convolutional autoencoder (MCAE) to denoise GPR data. At the same time, to solve the problem of training dataset insufficiency, we designed the data augmentation strategy, Wasserstein generative adversarial network (WGAN), to increase the training dataset of MCAE. Experimental results conducted on both simulated, generated, and field datasets demonstrated that the proposed scheme has promising performance for image denoising. In terms of three indexes: the peak signal-to-noise ratio (PSNR), the time cost, and the structural similarity index (SSIM), the proposed scheme can achieve better performance of random noise suppression compared with the state-of-the-art competing methods (e.g., CAE, BM3D, WNNM).
24 April 2024 in Journal of Inverse and Ill-posed Problems
Full waveform inversion (FWI) is a high-resolution technique to estimate the parameters of dielectric permittivity (ϵ) and electrical conductivity (σ) and identify the structure of the subsurface for Ground Penetrating Radar (GPR) application. However, permittivity and conductivity parameters can be coupled in bi-parameter GPR inversion. This coupling effect leads to the crosstalk in the FWI result. To solve this problem, we propose a novel approach to use the multi-scale FWI with the hybrid regularization method, which combines Tikhonov and total-variation (TV) regularizers that simultaneously invert the ϵ and the σ parameters, which improve the inversion accuracy and reduce the crosstalk effect. The multi-scale strategy uses the Wiener filtering to process the GPR data in different frequency ranges. Then, the low frequencies signal updates the bottom part and subsequently increases the frequencies to invert for the shallow areas. The Tikhonov regularization stabilizes the reconstruction of the smoothly varying background part. In contrast, Total Variation (TV) regularization can recover the large contrasts associated with the LNAPL model. The new Tikhonov-TV (TT) regularization can mitigate the crosstalk caused by the parameter coupling effect. Numerical tests with typical GPR models demonstrate that the proposed multi-scale TT-FWI strategy can effectively eliminate the crosstalk and improve the reconstruction accuracy when the model parameters have a different structure.
In recent years, the building insulation layer peeling caused by quality problems has brought about safety hazards to human life. Existing means of non-destructive testing of building insulation layers, including laser scanning, infrared thermal imaging, ultrasonic testing, acoustic emission, ground-penetrating radar, etc., are unable to simultaneously guarantee the detection depth and resolution of the insulation layer defects, not to mention high-precision imaging of the insulation layer structure. A new type of high-precision imaging radar is specifically designed for the quantitative quality inspection of external building insulation layers in this paper. The center frequency of the radar is 8800 MHz and the −10 dB bandwidth is 3100 MHz, which means it can penetrate the insulated panel not less than 48.4 mm thick and catch the reflected wave from the upper surface of the bonding mortar. When the bonding mortar is 120 mm away from the radar, the radar can achieve a lateral resolution of about 45 mm (capable of distinguishing two parties of bonding mortar with a 45 mm gap). Furthermore, an ultra-wideband high-bunching antenna is designed in this paper combining the lens and the sinusoidal antenna, taking into account the advantages of high directivity and ultra-wideband. Finally, the high-precision imaging of data collected from multiple survey lines can visually reveal the distribution of bonded mortar and the bonding area. This helps determine whether the bonding area meets construction standards and provides data support for evaluating the quality of the insulation layer.