Two dimensional entropy and short time Fourier Transform application on ground penetrating radar data analysis

2013 ◽  
Author(s):  
Panglijen Candra ◽  
Tian Xia ◽  
Dryver Huston ◽  
Guoan Wang
Keyword(s):  
Fourier Transform ◽  
Data Analysis ◽  
Ground Penetrating Radar ◽  
Radar Data ◽  
Two Dimensional ◽  
Short Time Fourier Transform ◽  
Ground Penetrating ◽  
Short Time

scholarly journals On the Use of Short-Time Fourier Transform for the Analysis of Tree Root Systems using Ground Penetrating Radar

2021 ◽  
Author(s):  
Livia Lantini ◽  
Fabio Tosti ◽  
Luca Bianchini Ciampoli ◽  
Amir M. Alani
Keyword(s):  
Remote Sensing ◽  
Fourier Transform ◽  
Ground Penetrating Radar ◽  
Mass Density ◽  
Root Systems ◽  
Short Time Fourier Transform ◽  
Charitable Trust ◽  
Ground Penetrating ◽  
Short Time ◽  
Root Mapping

<p>Monitoring and protecting natural assets is increasingly important today, as aggressive pathogens are negatively impacting the trees' survival. In this regard, root systems are affected by fungal infections that cause roots’ rot and eventually lead to trees' death. Such disease can spread rapidly to the adjacent trees and affect larger areas. Since these decays generally do not display visible signs, early identification is the key to tree preservation.</p><p>Within this context, non-destructive testing (NDT) methods are becoming popular, being more versatile than destructive methods. Specifically, ground penetrating radar (GPR) is emerging as an accurate geophysical method for tree root mapping. Recent research has focused on implementing automated algorithms for 3D root mapping, improving root detection through advanced GPR signal processing and the estimation of tree roots' mass density [1]. Also, recent studies have proven that GPR is effective in mapping the root system's architecture of street trees [2].</p><p>The present research reports the preliminary results of an experimental study, conducted to investigate the feasibility of a novel tree root assessment methodology based on the analysis of GPR data both in time and frequency domain. To this end, data were processed using a short-time Fourier transform (STFT) approach [3], which allows the evaluation of how the frequency spectrum changes across the signal propagation time window. The suggested processing system may be implemented for expeditious analyses or on trees challenging to access, such as in urban environments, where more comprehensive survey methods are not applicable. The objectives of this study, therefore, are to investigate how different features (i.e., roots, layers) affect the time-frequency analysis of GPR data, and to identify recurring patterns in the results to set a coherent data processing methodology.</p><p>Results' interpretation has shown the viability of the presented approach in recognising the influence of different features on the analysis of GPR data as it changes over time. This also allowed the detection of recurring patterns in the analysed data, proving that this method is worthy of further investigations.</p><p>Acknowledgements<br>The authors would like to express their sincere thanks and gratitude to the following trusts, charities, organisations and individuals for their generosity in supporting this project: Lord Faringdon Charitable Trust, The Schroder Foundation, Cazenove Charitable Trust, Ernest Cook Trust, Sir Henry Keswick, Ian Bond, P. F. Charitable Trust, Prospect Investment Management Limited, The Adrian Swire Charitable Trust, The John Swire 1989 Charitable Trust, The Sackler Trust, The Tanlaw Foundation, and The Wyfold Charitable Trust.</p><p><br>References<br>[1]     Lantini, L., Tosti, F., Giannakis, I., Zou, L., Benedetto, A. and Alani, A. M., 2020. "An Enhanced Data Processing Framework for Mapping Tree Root Systems Using Ground Penetrating Radar," Remote Sensing 12(20), 3417.<br>[2]     Lantini, L., Alani, A., Giannakis, I., Benedetto, A. and Tosti, F., 2020. "Application of ground penetrating radar for mapping tree root system architecture and mass density of street trees," Advances in Transportation Studies (3), 51-62.<br>[3]     Bianchini Ciampoli, L., Calvi, A. and D'Amico, F., 2019. "Railway Ballast Monitoring by GPR: A Test Site Investigation," Remote Sensing 11(20), 238</p>

Three-dimensional convolutional neural network–based underground object classification using three-dimensional ground penetrating radar data

2020 ◽  
Vol 19 (6) ◽  
pp. 1884-1893
Author(s):  
Shekhroz Khudoyarov ◽  
Namgyu Kim ◽  
Jong-Jae Lee
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Convolutional Neural Network ◽  
Ground Penetrating Radar ◽  
Three Dimensional ◽  
Object Classification ◽  
Radar Data ◽  
Two Dimensional ◽  
Underground Cavities ◽  
Ground Penetrating

Ground-penetrating radar is a typical sensor system for analyzing underground facilities such as pipelines and rebars. The technique also can be used to detect an underground cavity, which is a potential sign of urban sinkholes. Multichannel ground-penetrating radar devices are widely used to detect underground cavities thanks to the capacity of informative three-dimensional data. Nevertheless, the three-dimensional ground-penetrating radar data interpretation is unclear and complicated when recognizing underground cavities because similar ground-penetrating radar data reflected from different underground objects are often mixed with the cavities. As it is prevalently known that the deep learning algorithm-based techniques are powerful at image classification, deep learning-based techniques for underground object detection techniques using two-dimensional GPR (ground-penetrating radar) radargrams have been researched upon in recent years. However, spatial information of underground objects can be characterized better in three-dimensional ground-penetrating radar voxel data than in two-dimensional ground-penetrating radar images. Therefore, in this study, a novel underground object classification technique is proposed by applying deep three-dimensional convolutional neural network on three-dimensional ground-penetrating radar data. First, a deep convolutional neural network architecture was developed using three-dimensional convolutional networks for recognizing spatial underground objects such as, pipe, cavity, manhole, and subsoil. The framework of applying the three-dimensional convolutional neural network into three-dimensional ground-penetrating radar data was then proposed and experimentally validated using real three-dimensional ground-penetrating radar data. In order to do that, three-dimensional ground-penetrating radar block data were used to train the developed three-dimensional convolutional neural network and to classify unclassified three-dimensional ground-penetrating radar data collected from urban roads in Seoul, South Korea. The validation results revealed that four underground objects (pipe, cavity, manhole, and subsoil) are successfully classified, and the average classification accuracy was 97%. In addition, a false alarm was rarely indicated.

Sign in / Sign up

Export Citation Format

Share Document