Study of background subtraction for ground penetrating radar

Sharma, Prabhat; Gaba, S.P.; Singh, Dharmendra

doi:10.1109/raece.2015.7510234

Cited by 4 publications

(6 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Training Method 17,23 is also used to remove the Ground reflection in Ground Penetrating Radar. The ground reflections depends on the surface roughness and on the soil conditions, which degrade the performance of background subtraction techniques.…”

Section: Training Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Critical Analysis of Background Subtraction Techniques on Real GPR Data

et al. 2017

Self Cite

View full text Add to dashboard Cite

Ground penetrating radar (GPR) is used to detect the underground buried objects for civil as well as defence applications under varying conditions of soil moisture content. The capability of detection depends upon soil moisture, target characteristics and subsurface characteristics, which are mainly responsible for contaminating the GPR images with clutter. Researchers earlier have used averaging, mean, median, Eigen values, etc. for subtracting the background from GPR images. To analyse the background subtraction or clutter reduction problems, in this paper, we have experimentally reviewed background subtraction techniques with or without target conditions to enhance the target detection under variable soil moisture content. Indigenously developed GPR has been used to collect the data for different soil conditions and several background subtraction signal processing techniques were critically reviewed like, mean, median, singular value decomposition (SVD), principal component analysis (PCA), independent component analysis (ICA) and training methods. The signal to clutter ratio (SCR) measurement has been used for performance evaluation of each technique. The relative merits and demerits of each technique has also been analysed. The background subtraction techniques have been appliedto experimental GPR data and it is observed that in comparison of mean, SVD, median, ICA, PCA, the training method shows the highest SCR with buried target. Finally, this review helps to select the comparatively better background subtraction technique to enhance the detection capability in GPR.

show abstract

Section: Training Methodsmentioning

confidence: 99%

“…The GPR system 23 , which has been developed indigenously using VNA for detecting underground buried objects as shown in Fig. 1.…”

Section: Gpr System Descriptionmentioning

confidence: 99%

Critical Analysis of Background Subtraction Techniques on Real GPR Data

et al. 2017

Self Cite

View full text Add to dashboard Cite

show abstract

“…In radar signal processing, when the target's range R is an integer multiple of the range resolution, it can be expressed using Equation (5). Applying Equation (5) from Equation ( 2) results in the expression given by Equation (7).…”

Section: Proposed Algorithmmentioning

confidence: 99%

FMCW Radar Sensors with Improved Range Precision by Reusing the Neural Network

Cho,

Jung,

Lee

2023

Sensors

View full text Add to dashboard Cite

This paper addresses the challenge of enhancing range precision in radar sensors through supervised learning. However, when the range precision surpasses the range resolution, it leads to a rapid increase in the number of labels, resulting in elevated learning costs. The removal of background noise in indoor environments is also crucial. In response, this study proposes a methodology aiming to increase range precision while mitigating the issue of a growing number of labels in supervised learning. Neural networks learned for a specific section are reused to minimize learning costs and maximize computational efficiency. Formulas and experiments confirmed that identical fractional multiple patterns in the frequency domain can be applied to analyze patterns in other FFT bin positions (representing different target positions). In conclusion, the results suggest that neural networks trained with the same data can be repurposed, enabling efficient hardware implementation.

show abstract

“…CheckT arg et = min(cov(timegated)) < min(cov(synthetic)) Ground/Clutter Else T arget (6) where CheckTarget is the target check to detect the buried target, min(cover(timegated)) the overall minimum value of covariance matrix of timegated data of real GPR data, and min(cov(synthetic)) the overall minimum value of synthetic Gaussian data. (v) Once it is decided that the target is buried, there is a need to check whether the buried target is non-cracked or cracked PVC pipe.…”

Section: Algorithm and Implementationmentioning

confidence: 99%

“…High dielectric constant targets can be detected by estimating the signal of interest and noise using singular value decomposition (SVD) for nonlinear surface [3]. Principal component analysis (PCA) [4,6] is a second order statistical (zero mean) method, which reduces the dimension of data and uses decorrelation property. Primarily, independent component analysis (ICA) [4] is used to solve blind source separation problem.…”

Section: Introductionmentioning

confidence: 99%

Novel Adaptive Buried Nonmetallic Pipe Crack Detection Algorithm for Ground Penetrating Radar

Sharma¹,

Kumar²,

Singh³

2018

PIER M

Self Cite

View full text Add to dashboard Cite

Abstract-Ground penetrating radar (GPR) may be used to detect cracks in a buried pipe. Using GPR, there are only a few techniques, such as statistical approach robust principal component analysis (RPCA). to detect cracks in buried objects. Buried nonmetallic pipe crack detection is an important application for GPR to analyze the structural health of underground pipelines. The strength of a reflected signal may be feeble from a cracked location as compared to position with respect to that from other positions of the pipe. Currently, crack detection is a challenging task, especially when the buried pipe is nonmetallic, and soil moisture varies. In this paper, the problem of crack detection in a PVC pipe using GPR is attempted. It is a challenge to detect small sized cracks in an underground PVC pipe because the GPR image is flooded with correlated background signal or clutter, and the image patterns are typically irregularly distributed. In order to efficiently detect the crack in a buried PVC pipe, a novel adaptive crack detection algorithm has been developed with the help of covariance of real GPR data and covariance of normal distributed synthetic Gaussian data. Results are evaluated and validated to show the effectiveness of crack detection algorithm.

show abstract

Study of background subtraction for ground penetrating radar

Cited by 4 publications

References 13 publications

Critical Analysis of Background Subtraction Techniques on Real GPR Data

Critical Analysis of Background Subtraction Techniques on Real GPR Data

FMCW Radar Sensors with Improved Range Precision by Reusing the Neural Network

Novel Adaptive Buried Nonmetallic Pipe Crack Detection Algorithm for Ground Penetrating Radar

Contact Info

Product

Resources

About