Detection and localization of rebar in concrete by deep learning using ground penetrating radar

Liu, Hai; Lin, Chunxu; Cui, Jie; Fan, Lisheng; Xie, Xu; Spencer, Billie F.

doi:10.1016/j.autcon.2020.103279

Cited by 130 publications

(77 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The migration velocity is an essential parameter, which affects the focusing result of hyperbolas. Here, we adopt the iterative velocity estimation method, i.e., an estimation method by a trialand-error process, to determine the migrated velocity [21,30]. Then, the recorded data is inserted at each receiver position as boundary conditions for constant-time iteration.…”

Section: Workflow Of Rtmmentioning

confidence: 99%

See 1 more Smart Citation

Reverse-Time Migration Imaging of Ground-Penetrating Radar in NDT of Reinforced Concrete Structures

Shen

Zhao

et al. 2021

Remote Sensing

View full text Add to dashboard Cite

The evaluation and inspection of steel bars in reinforced concrete structures are critical for prolonging the service life of buildings. In this regard, ground-penetrating radar (GPR) has been a crucial alternative due to its non-invasiveness and convenience. This paper reports the experimental activities on a test-site area inside a camp in Shanghai, China. To assess the concrete structures of the building, GPR was employed for the detection and localization of rebars in columns, beams, and floors. From the GPR B-scan profiles acquired using a high-frequency antenna, the exact quantity of reinforcements was identified according to the hyperbola responses. Considering the difficulty of inferring the exact position and the scale of the rebars, we applied reverse time migration (RTM) to collapse the hyperbolic response and retrieve the target in a migrated image. To verify the effectiveness of the RTM algorithm, we carried out an experiment on a concrete model with three reinforced bars. We also utilized the RTM algorithm to process the B-scan profiles collected in a column that was later excavated. The imaging results validated the capacity of RTM in localizing and shaping rebars. Then, we employed the RTM algorithm for the GPR B-scan data collected from the other column. Based on the imaging profile, the quantity and positions of the rebars were correctly determined. Moreover, the thickness of the protective layer was evaluated according to the migrated result. These results demonstrate that GPR combined with RTM could provide useful foundation data for structural evaluation.

show abstract

Section: Workflow Of Rtmmentioning

confidence: 99%

“…For detection and localization of reinforced bars, Remote Sens. 2021, 13, 2020 2 of 16 Liu et al [21] and Giannakis et al [22] utilized machine-learning methods to estimate the diameter of reinforcements. Moreover, the evaluation of concrete parameters is an essential research subject.…”

Section: Introductionmentioning

confidence: 99%

Reverse-Time Migration Imaging of Ground-Penetrating Radar in NDT of Reinforced Concrete Structures

Shen

Zhao

et al. 2021

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…I N modelling the responses of electromagnetic (EM) surveys for geophysical exploration, it is usually necessary to separate the EM fields into the primary (background) field in the subsurface background (i.e., the subsurface without the specific scatterers) and the secondary (scattered) field due to the responses of the specific scatterers (i.e., anomalies) in the subsurface background. The secondary fields are widely employed in various EM exploration methods such as multicomponent induction tools [1], controlled-source electromagnetic (CSEM) method [2], the marine controlled-source electromagnetic (MCSEM) method [3], inversion of airborne electromagnetic data [4], helicopter-borne electromagnetic (HEM) measurements [5], semi-airborne electromagnetic method (SAEM) [6], the ground-airborne frequency-domain electromagnetic (GAFDEM) survey [7], ground penetrating radar [8], [9] and other detection methods [10], [11].…”

Section: Introductionmentioning

confidence: 99%

Mixed Spectral Element Method for Electromagnetic Secondary Fields in Stratified Inhomogeneous Anisotropic Media

et al. 2021

View full text Add to dashboard Cite

The spectral element method (SEM) is widely used for analyzing high frequency electromagnetic wave propagation and scattering in complex structures. At low frequencies, however, the primary (direct) fields are usually much larger than the secondary fields caused by scattering, thus making it much more difficult to accurately simulate the secondary (scattered) fields because of the source singularity in the primary fields. To more effectively and accurately simulate the low-frequency secondary fields in subsurface structures, in this work the vector Helmholtz equation for the scattered fields is used to directly obtain the secondary field data in inhomogeneous anisotropic media. The computational method for the secondary electromagnetic fields is based on the mixed spectral element method (mixed SEM) for anisotropic objects in a layered anisotropic background medium. The electromagnetic field is separated into the background fields that are evaluated analytically using the dyadic Green's functions (DGFs) of a layered uniaxially anisotropic medium, and the secondary fields caused by anomalous bodies with arbitrary shapes are numerically computed by the mixed SEM. This avoids the source singularity, and allows the transmitters to be located outside the computational domain. By enforcing Gauss' law as the constraint condition, the mixed SEM efficiently eliminates the low frequency breakdown problem. Numerical results verify the proposed method over the traditional SEM in low-frequency scattering from objects in subsurface layered anisotropic media.INDEX TERMS Mixed spectral element method, secondary field, anisotropic media, source singularity.

show abstract

“…For instance, 84 original radargrams in [15] are insufficient for training the AlexNet CNN model containing 60 million parameters. Either extending the datasets over thousands by translation and scaling [15,16] or generating radargrams by numerical simulation [14,17,18] can complement data shortage, but these sources bring doubts on training excessive duplicates or time-consuming problems in data production, respectively. Therefore, a deep learning equivalent framework intended for non-intensive datasets is necessary to expand GPR-related learning researches.…”

Section: Introductionmentioning

confidence: 99%

Wavelet Scattering Network-Based Machine Learning for Ground Penetrating Radar Imaging: Application in Pipeline Identification

Yang

Duan

2020

Remote Sensing

View full text Add to dashboard Cite

Automatic and efficient ground penetrating radar (GPR) data analysis remains a bottleneck, especially restricting applications in real-time monitoring systems. Deep learning approaches have good practice in automatic object identification, but their intensive data requirement has reduced their applicability. This paper developed a machine learning framework based on wavelet scattering networks to analyze GPR data for subsurface pipeline identification. Wavelet scattering network is functionally equivalent to convolutional neural networks, and its null-parameter property is intended for non-intensive datasets. A double-channel framework is designed with wavelet scattering networks followed by support vector machines to determine the existence of pipelines on vertical and horizontal traces separately. Classification accuracy rates arrive around 98% and 95% for datasets without and with noises, respectively, as well as 97% for considering surface roughness. Pipeline locations and diameters are convenient to determine from the reconstructed profiles of both simulated and practical GPR signals. However, the results of 5 cm pipelines are sensitive to noises. Nonetheless, the developed machine learning approach presents promising applicability in subsurface pipeline identification.

show abstract

Detection and localization of rebar in concrete by deep learning using ground penetrating radar

Cited by 130 publications

References 38 publications

Reverse-Time Migration Imaging of Ground-Penetrating Radar in NDT of Reinforced Concrete Structures

Reverse-Time Migration Imaging of Ground-Penetrating Radar in NDT of Reinforced Concrete Structures

Mixed Spectral Element Method for Electromagnetic Secondary Fields in Stratified Inhomogeneous Anisotropic Media

Wavelet Scattering Network-Based Machine Learning for Ground Penetrating Radar Imaging: Application in Pipeline Identification

Contact Info

Product

Resources

About