Underground utilities (UUs) are key infrastructures in urban life operations. The localization of UUs is vital to governments and residents in terms of asset management, utility planning, and ...construction safety. UUs localization has been investigated extensively via the automatic interpretation of ground-penetrating radar B-scan images. However, conventional image processing methods are time consuming and susceptible to noise. Deep learning-based methods cannot optimize parameters globally because of their box-fitting mode, which requires the separation of a task into region detection and hyperbola fitting problems. Thus, the accuracy and robustness of the localization task are reduced. Hence, an end-to-end deep learning model based on a key point–regression mode is proposed and validated in this study. Experimental results show that the proposed method outperforms the current mainstream models in terms of localization accuracy (97.01%), inference speed (125 fps), and robustness on the same platform (NVDIA RTX 3090 GPU).
•An End-to-end deep learning model is proposed for localization of underground utilities.•Key point-regression and Attention Mechanisms are used to improve the model performance.•The model was trained and verified using real GPR data.•The model is lightweight and can be used on common computing platforms.
The Remote Sensing (RS) field has an increasing research interest in using deep learning (DL) models to recognize kinds of RS data, leading to a great demand for training data annotation. Due to the ...high cost of expertise, employing non-experts to label data has become an important way to improve labeling efficiency. Commonly, a single data sample is labeled by multiple annotators and the most voted label is accepted to promise accuracy. But in the RS context, the widely admitted strategy could lose effect. Usually RS data involves considerable classes on account of the complexity of surface environments, which is prone to inter-class similarity difficult to distinguish. Annotators without expertise probably make mistakes on these indistinguishable classes, thus causing error voted labels. Although classification of different characteristics in RS data have been widely documented, the non-expert annotators are unfamiliar with these expertise, and it is difficult to force them to handle specialized labeling skills. To address the issues, this paper bases multi-annotator label selection on the investigation of annotators' own ability in distinguishing similar classes of images. A quality evaluation process is designed which weights the labels from capable annotators higher than those from weak ones. By a multi-round quality evaluation algorithm, correct labels could out-compete the wrong ones even disadvantaged in numbers. Experimental results demonstrate the advance of the proposed method on RS datasets.
•A detailed literature review is given regarding the different signal features for moisture measurement in civil engineering.•Applied signal features can be grouped into amplitude, time and frequency ...features.•An Overview of applied signal features is presented regarding their group, wave type, preceding survey method and use for moisture content estimation.•Quantitative estimations deliver good results in laboratory conditions, on site measurements underly a lot of uncertainties and mostly allow only qualitative estimations.•Most reviewed publications consider only one signal feature, thus future approaches may include multiple features for further development.
When applying Ground Penetrating Radar (GPR) to assess the moisture content of building materials, different medium properties, dimensions, interfaces and other unknown influences may require specific strategies to achieve useful results. Hence, we present an overview of the various approaches to carry out moisture measurements with GPR in civil engineering (CE). We especially focus on the applied signal features such as time, amplitude and frequency features and discuss their limitations. Since the majority of publications rely on one single feature when applying moisture measurements, we also hope to encourage the consideration of approaches that combine different signal features for further developments.
Active evaporite karst processes in the Baltic states are associated with a few relatively small regions where gypsum rocks can be found close to the Earth's surface. One of these areas lies in the ...vicinity of the Pandu bog. However, such a possibly active karst region, which is covered by peat and in which the mapping of karst formations is complex, has not been previously investigated. In this study, we present a buried and peat‐filled karst cover‐collapse sinkhole mapping approach that involves a combination of ground‐penetrating radar (GPR), electrical resistivity tomography (ERT) and conventional boreholes. A detailed map of the bog's substratum topography was constructed from a geophysical surveying dataset. It reveals 15 distinctly expressed sinkholes with diameters of several tens of metres. Overall, 140 potential sinkholes were also mapped using remote sensing data in the vicinity of the bog. Higher electrical resistivity anomalies were identified inside the peat; they coincide with scatter‐free zones in GPR data and water layers in boreholes. Highly disturbed internal peat layering was also detected in these sinkholes. It is suggested that these water layers and disturbed peat layering may have formed due to the subsidence of the lower peat layers, and thus they represent relatively younger sinkholes. This is also supported by evidence from orthophoto maps, which showed the formation and disappearance of surficial lakes and depressions on the bog surface. Our results revealed the presence of active and widespread karst processes under the bog that have not been previously noticed despite the fact that they have implications for the assessment of geohazards in this area.
A geophysical study from a bog located over karst susceptible bedrock show karst activity, which has not been appropriately evaluated before. Both GPR and ERT results show water layers within peat‐filled sinkholes.
Highway bridges are primarily reinforced concrete structures. They have multilayer steel mesh sheets, corrugated pipes, and steel strands inside. As a result, detecting defects in bridge concrete ...structures requires high technical expertise and can be challenging. This article presents a new device of ground-penetrating radar (GPR) designed specifically for highway bridge inspection. It employs antenna array technology, multichannel radar control technology, and real-time 3-D data acquisition and display technology to achieve reliable detection of various concrete structures commonly found in bridges. Using a 1.3 GHz central frequency antenna array and a multichannel control unit, the system enables simultaneous surveying along five lines, the detection depth can exceed 600 mm in concrete. This significantly enhances detection efficiency. By employing specialized software processing, the detection results are presented in a specific and visually comprehensive 3-D format. Moreover, the system provides 3-D slice images from any position and direction, facilitating the interpretation of detection results for various targets, including reinforcement layout, protective layer thickness, corrugated pipes, steel strands, and other quality defects. It provides advanced and reliable technical means for construction quality control and bridge health monitoring of highway bridges. The results indicate that the device performs well not only in controlled experimental environments, but also in real-world bridge structure environments.
The most crucial parameter to be determined in an archaeological ground‐penetrating radar (GPR) survey is the velocity of the subsurface material. Precision velocity estimates comprise the basis for ...depth estimation, topographic correction and migration, and can therefore be the difference between spurious interpretations and/or efficient GPR‐guided excavation with sound archaeological interpretation of the GPR results. Here, we examine the options available for determining the GPR velocity and for assessing the precision of velocity estimates from GPR data, using data collected at a small‐scale iron‐working site in Rhode Island, United States. In the case study, the initial velocity analysis of common‐offset GPR profile data, using the popular method of hyperbola fitting, produced some unexpectedly high subsurface signal velocity estimates, while analysis of common midpoint (CMP) GPR data yielded a more reasonable subsurface signal velocity estimate. Several reflection analysis procedures for CMP data, including hand and automated signal picking using cross‐correlation and semblance analysis, are used and discussed here in terms of efficiency of processing and yielded results. The case study demonstrates that CMP data may offer more accurate and precise velocity estimates than hyperbola fitting under certain field conditions, and that semblance analysis, though faster than hand‐picking or cross‐correlation, offers less precision.
The problem of automatically recognizing and fitting hyperbolae from ground-penetrating radar (GPR) images is addressed, and a novel technique computationally suitable for real-time on-site ...application is proposed. After preprocessing of the input GPR images, a novel thresholding method is applied to separate the regions of interest from background. A novel column-connection clustering (C3) algorithm is then applied to separate the regions of interest from each other. Subsequently, a machine learnt model is applied to identify hyperbolic signatures from outputs of the C3 algorithm, and a hyperbola is fitted to each such signature with an orthogonal-distance hyperbola fitting algorithm. The novel clustering algorithm C3 is a central component of the proposed system, which enables the identification of hyperbolic signatures and hyperbola fitting. Only two features are used in the machine learning algorithm, which is easy to train using a small set of training data. An orthogonal-distance hyperbola fitting algorithm for "south-opening" hyperbolae is introduced in this work, which is more robust and accurate than algebraic hyperbola fitting algorithms. The proposed method can successfully recognize and fit hyperbolic signatures with intersections with others, hyperbolic signatures with distortions, and incomplete hyperbolic signatures with one leg fully or largely missed. As an additional novel contribution, formulas to compute an initial "south-opening" hyperbola directly from a set of given points are derived, which make the system more efficient. The parameters obtained by fitting hyperbolae to hyperbolic signatures are very important features; they can be used to estimate the location and size of the related target objects and the average propagation velocity of the electromagnetic wave in the medium. The effectiveness of the proposed system is tested on both synthetic and real GPR data.
•An automatic recognition method to detect tunnel lining elements using GPR image.•Deep convolutional networks are used for target recognition.•The FDTD and DCGAN approaches augment the training ...dataset effectively.•High recognition accuracy is achieved on the real GPR dataset.
Tunnel lining inspection using ground penetrating radar (GPR) is a routine procedure to ensure construction quality. Yet, the interpretation of GPR data relies heavily on manual experience that may lead to low efficiency and recognition error when a large volume of data is involved. We introduced a deep learning-based automatic recognition method to identify tunnel lining elements, including steel ribs, voids, and initial linings from GPR images. Based on the mask region-based convolutional neural network (Mask R-CNN), this approach uses the 101-layer deep residual network (ResNet101) with the feature pyramid network (FPN) to extract features, the region proposal network (RPN) to generate candidate regions, a group of fully connected layers to detect the presence and locations of steel ribs and voids, and a fully convolutional network (FCN) to segment the area of the initial lining. To improve the recognition performance of the network, the finite-difference time-domain (FDTD) method and deep convolutional generative adversarial network (DCGAN) are employed to create synthetic GPR images for data augmentation. The test results on a synthetic example show that the mean absolute errors for steel rib, void, and initial lining thickness recognition are 1.2, 2.2, and 4.2mm, respectively, demonstrating the feasibility of the recognition network. In a field GPR survey experiment, the recognition accuracies achieved 96.02%, 91.17%, and 95.45% for the three targets. With the optimal proportions of synthetic images added to the training dataset, the accuracies were further improved to 98.86%, 94.53%, and 99.27%, respectively.
In this paper, we combine the multiple-input-multiple-output (MIMO) array antenna technology with a multipolarization component in a ground penetrating radar (GPR) system to improve target detection ...accuracy. The MIMO technology introduced in previous literature is widely applied in radar and other wireless communication fields. Here, we apply the MIMO technology with a "plane-wave like" (PWL) source that uses array antennas with small spacing to emit a pulse source at the same time in GPR detection. First, we analyze the physical mechanism of the MIMO GPR system with a "PWL" source to improve the target detection resolution. Then, we carry out a numerical simulation with a finite-difference time-domain method in 1-D and 2-D array antennas to compare the imaging results of the MIMO and traditional GPR systems. Finally, the synthetic data MIMO GPR experiment with a step-frequency GPR system is implemented. Compared with the traditional GPR system, our results demonstrate that the MIMO GPR system with a multipolarization detection mode can overcome the influence of target radar cross sections and antenna radiation directions, and improve target detection accuracy effectively. Meanwhile, the synthetic MIMO GPR system also provides a good idea to improve the system performance and reduce system design requirements and the manufacture cost.
This paper provides an overview of the existing health monitoring and assessment methods for masonry arch bridges. In addition, a novel “integrated” holistic non-destructive approach for structural ...monitoring of bridges using ground-based non-destructive testing (NDT) and the satellite remote sensing techniques is presented. The first part of the paper reports a review of masonry arch bridges and the main issues in terms of structural behaviour and functionality as well as the main assessment methods to identify structural integrity-related issues. A new surveying methodology is proposed based on the integration of multi-source, multi-scale and multi-temporal information collected using the Ground Penetrating Radar (GPR – 200, 600 and 2000 MHz central-frequency antennas) and the Interferometric Synthetic Aperture Radar (InSAR – C-band SAR sensors) techniques. A case study (the “Old Bridge” at Aylesford, Kent, UK – a 13th century bridge) is presented demonstrating the effectiveness of the proposed method in the assessment of masonry arch bridges. GPR has proven essential at providing structural detailing in terms of subsurface geometry of the superstructure as well as the exact positioning of the structural ties. InSAR has identified measures of structural displacements caused by the seasonal variation of the water level in the river and the river bed soil expansions. The above process forms the basis for the “integrated” holistic structural health monitoring approach proposed by this paper.
•An “integrated” holistic approach for structural health monitoring of masonry arch bridges.•Non-destructive assessment using multi-source, multi-scale and multi-temporal information.•Use of high-frequency (2000 MHz) and low-frequency (200–600 MHz) GPR antenna systems.•Use of the Interferometric Synthetic Aperture Radar (InSAR – C-band sensors) technique.•A case study (the “Old Bridge” at Aylesford, Kent, UK– a 13th century bridge) is presented.