Ground-penetrating radar (GPR) is a powerful and rapidly maturing technology for subsurface threat identification. However, sophisticated processing of GPR data is necessary to reduce false alarms ...due to naturally occurring subsurface clutter and soil distortions. Most currently fielded GPR-based landmine detection algorithms utilize feature extraction and statistical learning to develop robust classifiers capable of discriminating buried threats from inert subsurface structures. Analysis of these techniques indicates strong underlying similarities between efficient landmine detection algorithms and modern techniques for feature extraction in the computer vision literature. This paper explores the relationship between and application of one modern computer vision feature extraction technique, namely histogram of oriented gradients (HOG), to landmine detection in GPR data. The results presented indicate that HOG features provide a robust tool for target identification for both classification and prescreening and suggest that other techniques from computer vision might also be successfully applied to target detection in GPR data.
An innovative inverse scattering (IS) technique for the simultaneous processing of multifrequency (MF) ground-penetrating radar (GPR) measurements is proposed. The nonlinear IS problem is solved by ...profitably integrating a customized MF version of the particle swarm optimizer (PSO) within the iterative multiscaling approach (IMSA) to jointly exploit the reduction of the ratio between unknowns and uncorrelated data with a pervasive exploration of the multidimensional search space for minimizing the probability that the solution is trapped into local minima corresponding to false solutions of the problem at hand. Both numerical and experimental test cases are reported to assess the reliability of the MF-IMSA-PSO method toward accurate GPR tomography as well as improvements with respect to the competitive state-of-the-art inversion approaches.
Horizontally stratified media are commonly used to represent naturally occurring and man-made structures, such as soils, roads, and pavements, when probed by ground-penetrating radar (GPR). ...Electromagnetic (EM) wave scattering from such multilayered media is dependent on the roughness of the interfaces. In this paper, we developed a closed-form asymptotic EM model considering random rough layers based on the scalar Kirchhoff-tangent plane approximation (SKA) model that we combined with planar multilayered media Green's functions. In order to validate our extended SKA model, we conducted simulations using a numerical EM solver based on the finite-difference time-domain (FDTD) method. We modeled a medium with three layers-a base layer of perfect electric conductor (PEC) overlaid by two layers of different materials with rough interfaces. The reflections at the first and at the second interface were both well reproduced by the SKA model for each roughness condition. For the reflection at the PEC surface, the extended SKA model slightly overestimated the reflection, and this overestimation increased with the roughness amplitude. Good agreement was also obtained between the FDTD simulation input values and the inverted root mean square (rms) height estimates of the top interface, while the inverted rms heights of the second interface were slightly overestimated. The accuracy and the performances of our asymptotic forward model demonstrate the promising perspectives for simulating rough multilayered media and, hence, for the full waveform inversion of GPR data to noninvasively characterize soils and materials.
The non-destructive evaluation (NDE) of civil infrastructure has been an active area of research in recent decades. The traditional inspection of civil infrastructure mostly relies on visual ...inspection using human inspectors. To facilitate this process, different sensors for data collection and techniques for data analyses have been used to effectively carry out this task in an automated fashion. This review-based study will examine some of the recent developments in the field of autonomous robotic platforms for NDE and the structural health monitoring (SHM) of bridges. Some of the salient features of this review-based study will be discussed in the light of the existing surveys and reviews that have been published in the recent past, which will enable the clarification regarding the novelty of the present review-based study. The review methodology will be discussed in sufficient depth, which will provide insights regarding some of the primary aspects of the review methodology followed by this review-based study. In order to provide an in-depth examination of the state-of-the-art, the current research will examine the three major research streams. The first stream relates to technological robotic platforms developed for NDE of bridges. The second stream of literature examines myriad sensors used for the development of robotic platforms for the NDE of bridges. The third stream of literature highlights different algorithms for the surface- and sub-surface-level analysis of bridges that have been developed by studies in the past. A number of challenges towards the development of robotic platforms have also been discussed.
Ground penetrating radar (GPR) is widely used in detection localization of underground structure anomalous bodies. However, it is impossible to achieve accurate imaging localization of underground ...structures targets only by the waveform of GPR detection profiles due to the interference of clutter signals in engineering application. In this paper, a RefineNet deep learning network based on hybrid loss function is proposed to remove clutter signals in GPR profiles, and a reverse time migration (RTM) imaging algorithm based on total variation(TV) regularization is developed to perform migration imaging on GPR profiles processed by RefineNet network to realize accurate imaging localization of underground structures targets. Numerical simulations demonstrate that the developed RefineNet deep learning network can significantly remove clutter signals and improve GPR profiles quality, and the proposed RTM imaging algorithm based on TV regularization can accurately obtain location and shape information of underground structures targets. The full-scale experiment and field detection show that the proposed algorithm can accurately obtain the location of underground pipelines, cavities and other anomaly bodies. It is concluded that the developed algorithm provides a strong technical support for the GPR detection localization of underground structures targets.
Ground penetrating radar (GPR) has become an effective tool for asphalt pavement inspection. However, a ground-coupled GPR system cannot facilitate a high-speed survey due to the complex road ...environment and traffic condition. In this paper, an air-coupled antenna array is designed for measurement of common midpoint (CMP) GPR data. From the CMP data, an improved velocity spectrum algorithm considering the refraction on the pavement surface is proposed to simultaneously estimate the thickness and dielectric permittivity of the pavement layer. The results of a laboratory experiment demonstrate that the improved velocity spectrum method can greatly enhance the accuracy of the velocity and thickness estimations, compared with the traditional inversion method. A field measurement conducted on a highway pavement shows that the maximum error of the thickness estimation of the asphalt layer is less than 10 mm (7.1%). It is concluded that the developed CMP technique can be used for quantitative characterization of asphalt pavement.
•An air-coupled antenna array is designed for measurement of CMP GPR data.•An improved velocity spectrum algorithm considering the refraction is proposed.•The thickness and dielectric permittivity can be estimated with a high accuracy.•The thickness estimation error on a highway pavement is less than 10 mm (7.1%).
This work offers a defect segmentation approach for the nondestructive testing of tunnel lining internal defects using Ground Penetrating Radar (GPR) data. Given GPR synthetic data, it maps the ...internal defect structure, using a CNN named Segnet coupled with the Lovász softmax loss function, which enhances the accuracy, automation, and efficiency of defect identification. Experiments with both synthetic and actual data show that our innovative method overcomes problems in standard GPR data interpretation. A physical test model with a known defect was developed and manufactured, and GPR data was acquired and analyzed to verify the approach.
•Defect segmentation is our proposed tunnel lining defect detection.•Inputting GPR directly into CNNs profiles internal lining defects.•CNN correctly identified defect types and location, and achieved reliable results.•Segnet was introduced to the defect segmentation method for more accurate results.•Model building and data processing verified the proposed method.
Denoising is a crucial step in ground penetrating radar (GPR) data processing. Conventional denoising algorithms for ground penetrating radar typically require selecting optimal processing ...parameters, which can be challenging to achieve in practical applications, resulting in unsatisfactory processing outcomes. In recent years, in order to address the issue of low accuracy in conventional ground penetrating radar denoising algorithms, denoising neural networks have been applied in the field of ground penetrating radar. Though conventional denoising neural networks have shown improvements in signal-to-noise ratio in some cases, their performance is often inadequate when facing real ground penetrating radar data with complex random noise, due to the training methods of the networks. To address the challenges in denoising of ground penetrating radar data, a two-stage denoising method based on deep learning has been proposed. Initially, conventional ground penetrating radar data processing is conducted, followed by training a denoising network model using both the processed and unprocessed signals. Leveraging the powerful nonlinear fitting capability of convolutional neural networks, an end-to-end mapping relationship is established to obtain the final denoising network model, completing the two-stage denoising process. Finally, this letter validates the proposed two-stage denoising method using synthetic and field data. The radar data obtained through this two-stage denoising method not only improves MSE by 0.17 compared to conventional methods but also increases PSNR by 8.1. Furthermore, there is a significant enhancement in the integrity of the waveform and the recovery of weak signals.
A deep-neural-network-based identification method for multipolarimetric ground-penetrating radar (GPR) data was proposed to address the challenges of unbalanced polarimetric data and take advantage ...of multipolarimetric GPR data for subsurface defect identification. The proposed method comprised two subnetworks-namely, an unbalanced polarimetric data augmentation module based on a cycle generative adversarial network (CycleGAN) to generate a large number of paired multipolarimetric GPR data, and an identification module based on multipolarimetric GPR data to accurately identify internal defects with irregular shapes and occlusions. Specifically, the proposed physics-informed convolution (PIC) in the identification module could enhance the scattering features of different polarimetric data and extract location-sensitive physical properties from multipolarimetric GPR data; thus, defects with occlusions could be effectively identified. Additionally, the identification module adopted a criss-cross attention (CCA) module and a global attention module (GAM) channel, which could reduce information reduction and magnify global interactive representations to accurately identify the shape of irregular targets. Validation experiments were conducted at two levels-that is, first, using synthetic multipolarimetric data based on the subsurface defect model, and second, using a sandbox model test in a realistic scenario. The results demonstrated that the proposed method was capable of effectively identifying internal defects with irregular shapes and occlusions from multipolarimetric GPR data.