Pub Date : 2021-12-01DOI: 10.1109/iwagpr50767.2021.9843143
M. Solla, N. Fernández, Carlos Fidalgo-Lopez
This paper presents the development of different amplitude-based GPR imaging techniques aiming to improve the detection of subsidence and settlement phenomena in a reinforced concrete floor slab, and the underlying anthropic filling, servicing a manufacturing facility. GPR is a non-invasive method that provides a high-resolution imaging of the subsoil while covering a wide area in a relatively short period of time (saving time and money). The purpose in this study is to detect internal damage and failure affecting the structural stability of the foundation system. GPR measurements were performed using a ground-coupled antenna of 500 MHz central frequency. Additionally, traditional invasive tests such as sample drilling and penetration tests were carried out closest to the most important anomalies interpreted with GPR in order to validate the results obtained. The approach developed herein has demonstrated to be an efficient tool that can be successfully used to detect settlement of reinforcement and subsidence in critical areas.
{"title":"Amplitude-based GPR imaging to detect subsidence under a reinforced concrete floor slab","authors":"M. Solla, N. Fernández, Carlos Fidalgo-Lopez","doi":"10.1109/iwagpr50767.2021.9843143","DOIUrl":"https://doi.org/10.1109/iwagpr50767.2021.9843143","url":null,"abstract":"This paper presents the development of different amplitude-based GPR imaging techniques aiming to improve the detection of subsidence and settlement phenomena in a reinforced concrete floor slab, and the underlying anthropic filling, servicing a manufacturing facility. GPR is a non-invasive method that provides a high-resolution imaging of the subsoil while covering a wide area in a relatively short period of time (saving time and money). The purpose in this study is to detect internal damage and failure affecting the structural stability of the foundation system. GPR measurements were performed using a ground-coupled antenna of 500 MHz central frequency. Additionally, traditional invasive tests such as sample drilling and penetration tests were carried out closest to the most important anomalies interpreted with GPR in order to validate the results obtained. The approach developed herein has demonstrated to be an efficient tool that can be successfully used to detect settlement of reinforcement and subsidence in critical areas.","PeriodicalId":170169,"journal":{"name":"2021 11th International Workshop on Advanced Ground Penetrating Radar (IWAGPR)","volume":"186 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127514930","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-12-01DOI: 10.1109/iwagpr50767.2021.9843144
Lucy Buck, Charles S Bristow
Deposits from the Second Storegga Slide tsunami can be seen at outcrop at the beach in Whale Firth. Ground-penetrating radar has been used to track the sand layer inland until it truncates against the underlying glacial deposits. The elevation of the end of the tsunami deposits combined with the sea level rise since the tsunami can be used to estimate a minimum run-up height. Much thinner sand layers were resolved with the GPR than would be expected. This is due to a combination of factors that optimized the return signal allowing the sand layer to be traced almost 150 m inland from the outcrop at the coastline.
{"title":"Using GPR to Track Tsunami Deposits Inland at Whale Firth, the Shetland Islands","authors":"Lucy Buck, Charles S Bristow","doi":"10.1109/iwagpr50767.2021.9843144","DOIUrl":"https://doi.org/10.1109/iwagpr50767.2021.9843144","url":null,"abstract":"Deposits from the Second Storegga Slide tsunami can be seen at outcrop at the beach in Whale Firth. Ground-penetrating radar has been used to track the sand layer inland until it truncates against the underlying glacial deposits. The elevation of the end of the tsunami deposits combined with the sea level rise since the tsunami can be used to estimate a minimum run-up height. Much thinner sand layers were resolved with the GPR than would be expected. This is due to a combination of factors that optimized the return signal allowing the sand layer to be traced almost 150 m inland from the outcrop at the coastline.","PeriodicalId":170169,"journal":{"name":"2021 11th International Workshop on Advanced Ground Penetrating Radar (IWAGPR)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128928072","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-12-01DOI: 10.1109/iwagpr50767.2021.9843179
S. Santos-Assunçao, Tin Wai Phoebe Wong, W. Lai
Bandpass filter is a critical GPR signal processing step for enhancing visibility of buried objects. But its setting of thresholds of upper and lower limits are subjective. This paper describes a more objective method for setting of the thresholds by Gabor Transform in time-frequency domain for determining the frequency thresholds after identifying the actual frequency responses of objects of interests, while others like direct wave and noises in other time window are not considered. The method was tested with the data extracted from a real case study with a Proceq GS8000 dual frequency Ground Penetrating Radar. Among the high-frequency data, four-A scans were selected from the same B-Scan with a deep object, a shallow pipe, reinforcement rebar and a last scan in natural soil (with no utilities or other structural elements). In the time domain, standard filtering processes were applied in both 2D and 3D spaces to identify the targets and enhance the imaging of the radagram. In the frequency domain, each target at different time of reflection lead to a different response or distribution in the frequency spectrum trough the fast Fourier transform (FFT). Depending on each element and respective material type, the frequency spectrum distribution could lead to a specific response pattern and relative amplitude over a 1D array. The Gabor Wavelet Transform could segregate the direct and reflected waves and therefore permit to interpret in a contour map (2D) the behaviour of the frequency exactly where the target is located, and allows for setting of the frequency thresholds for bandpass filter. There are observed patterns that could be useful to discriminate and categorise specific targets based on the amplitude and shape. From each (wavelet transform) spectrogram, the frequency spectrum was extracted and compared with the full spectrum delivered from the FFT. Results could enhance the resolution and improve the location of the target by determining the ideal band pass filter (with respect to low and high cut-off frequencies) for each target, instead of the traditional band pass filter applied to the whole radagram. It also alleviates the cognitive bias problem “I want to show what I want to show” which is used to be a manual and operator-dependent process.
{"title":"Optimising thresholding of bandpass filter through GPR wavelet transform in time-frequency domain","authors":"S. Santos-Assunçao, Tin Wai Phoebe Wong, W. Lai","doi":"10.1109/iwagpr50767.2021.9843179","DOIUrl":"https://doi.org/10.1109/iwagpr50767.2021.9843179","url":null,"abstract":"Bandpass filter is a critical GPR signal processing step for enhancing visibility of buried objects. But its setting of thresholds of upper and lower limits are subjective. This paper describes a more objective method for setting of the thresholds by Gabor Transform in time-frequency domain for determining the frequency thresholds after identifying the actual frequency responses of objects of interests, while others like direct wave and noises in other time window are not considered. The method was tested with the data extracted from a real case study with a Proceq GS8000 dual frequency Ground Penetrating Radar. Among the high-frequency data, four-A scans were selected from the same B-Scan with a deep object, a shallow pipe, reinforcement rebar and a last scan in natural soil (with no utilities or other structural elements). In the time domain, standard filtering processes were applied in both 2D and 3D spaces to identify the targets and enhance the imaging of the radagram. In the frequency domain, each target at different time of reflection lead to a different response or distribution in the frequency spectrum trough the fast Fourier transform (FFT). Depending on each element and respective material type, the frequency spectrum distribution could lead to a specific response pattern and relative amplitude over a 1D array. The Gabor Wavelet Transform could segregate the direct and reflected waves and therefore permit to interpret in a contour map (2D) the behaviour of the frequency exactly where the target is located, and allows for setting of the frequency thresholds for bandpass filter. There are observed patterns that could be useful to discriminate and categorise specific targets based on the amplitude and shape. From each (wavelet transform) spectrogram, the frequency spectrum was extracted and compared with the full spectrum delivered from the FFT. Results could enhance the resolution and improve the location of the target by determining the ideal band pass filter (with respect to low and high cut-off frequencies) for each target, instead of the traditional band pass filter applied to the whole radagram. It also alleviates the cognitive bias problem “I want to show what I want to show” which is used to be a manual and operator-dependent process.","PeriodicalId":170169,"journal":{"name":"2021 11th International Workshop on Advanced Ground Penetrating Radar (IWAGPR)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124977860","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-12-01DOI: 10.1109/iwagpr50767.2021.9843147
L. Bossi, P. Falorni, F. Crawford, T. Bechtel, V. Plakhtii, L. Capineri
The characterization of microwave subsurface holographic RADAR sensors is not simple because the investigated medium is generally not homogeneous, and the soil electromagnetic properties change with moisture content. Commonly, holographic radars designed for terrain investigations use sand-box testbeds. To ensure the homogeneity of the medium and a well-defined value of dielectric permittivity and conductivity (attenuation), we designed and fabricated a testbed filled with water. With a solution of Sodium Chloride concentration at room temperature, it is possible to obtain a specific dielectric permittivity and the desired attenuation. In this paper we describe the design process, the fabrication, and a preliminary experiment with distilled water using a plastic candy box as a target. This approach to the fabrication of a RADAR testbed guarantees the repeatability of the measurements reducing the number of uncontrolled variables in laboratory experiments.
{"title":"Water-filled testbed modeling, design, and fabrication for performance validation of a holographic subsurface RADAR antenna","authors":"L. Bossi, P. Falorni, F. Crawford, T. Bechtel, V. Plakhtii, L. Capineri","doi":"10.1109/iwagpr50767.2021.9843147","DOIUrl":"https://doi.org/10.1109/iwagpr50767.2021.9843147","url":null,"abstract":"The characterization of microwave subsurface holographic RADAR sensors is not simple because the investigated medium is generally not homogeneous, and the soil electromagnetic properties change with moisture content. Commonly, holographic radars designed for terrain investigations use sand-box testbeds. To ensure the homogeneity of the medium and a well-defined value of dielectric permittivity and conductivity (attenuation), we designed and fabricated a testbed filled with water. With a solution of Sodium Chloride concentration at room temperature, it is possible to obtain a specific dielectric permittivity and the desired attenuation. In this paper we describe the design process, the fabrication, and a preliminary experiment with distilled water using a plastic candy box as a target. This approach to the fabrication of a RADAR testbed guarantees the repeatability of the measurements reducing the number of uncontrolled variables in laboratory experiments.","PeriodicalId":170169,"journal":{"name":"2021 11th International Workshop on Advanced Ground Penetrating Radar (IWAGPR)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128015164","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-12-01DOI: 10.1109/iwagpr50767.2021.9843142
O. Patsia, A. Giannopoulos, I. Giannakis
Electromagnetic (EM) forward solvers, such as the finite-difference time-domain (FDTD) method are an essential part for the interpretation of the GPR data. Their drawback is that they are still computationally expensive algorithms and not easily applicable for simulating real scenarios in the absence of high performance computing (HPC). Machine learning (ML) can provide a solution to this problem for specific applications by providing near real time solutions to the forward problem. In this paper, we have developed an ML-based forward solver that is used in full-waveform inversion (FWI) schemes and is applied to concrete slab scenarios. A model of a real GPR transducer was used in the simulations and as a result the algorithm can be used for the inversion of real data. The coupled ML solver/FWI algorithm was tested with both synthetic and real data to assess its performance. Although the algorithm was tuned for a concrete slab case, it can be adjusted and applied to different GPR applications.
{"title":"Full Waveform Inversion of common offset GPR data using a fast deep learning based forward solver","authors":"O. Patsia, A. Giannopoulos, I. Giannakis","doi":"10.1109/iwagpr50767.2021.9843142","DOIUrl":"https://doi.org/10.1109/iwagpr50767.2021.9843142","url":null,"abstract":"Electromagnetic (EM) forward solvers, such as the finite-difference time-domain (FDTD) method are an essential part for the interpretation of the GPR data. Their drawback is that they are still computationally expensive algorithms and not easily applicable for simulating real scenarios in the absence of high performance computing (HPC). Machine learning (ML) can provide a solution to this problem for specific applications by providing near real time solutions to the forward problem. In this paper, we have developed an ML-based forward solver that is used in full-waveform inversion (FWI) schemes and is applied to concrete slab scenarios. A model of a real GPR transducer was used in the simulations and as a result the algorithm can be used for the inversion of real data. The coupled ML solver/FWI algorithm was tested with both synthetic and real data to assess its performance. Although the algorithm was tuned for a concrete slab case, it can be adjusted and applied to different GPR applications.","PeriodicalId":170169,"journal":{"name":"2021 11th International Workshop on Advanced Ground Penetrating Radar (IWAGPR)","volume":"58 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116969993","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-12-01DOI: 10.1109/iwagpr50767.2021.9843160
Aldis Zalaiskalns
This paper is focusing on the possibilities to determine pavement layer thickness and void content in pavement by using the ground-penetrating radar (GPR) owned by SJSC “Latvian State Roads”. The research reflects the analysis of results from three sites in the territory of Latvia. In the sites with the total length of 85 km GPR data was gathered after taking 86 core samples to determine pavement layer thickness. The void content in these drilled core samples was measured with laboratory methods. Void content was also measured with laboratory methods. The results show that dielectric permittivity coefficient (ε′), determined with the metal plate test, was equal to the one estimated from the drilling on sites if road pavement materials were similar in all layers. Void content test results have showed no correlation with the ε′ determined with the metal plate test.
{"title":"The use of Ground-Penetrating Radar in determining pavement layer thickness and void content in Latvia","authors":"Aldis Zalaiskalns","doi":"10.1109/iwagpr50767.2021.9843160","DOIUrl":"https://doi.org/10.1109/iwagpr50767.2021.9843160","url":null,"abstract":"This paper is focusing on the possibilities to determine pavement layer thickness and void content in pavement by using the ground-penetrating radar (GPR) owned by SJSC “Latvian State Roads”. The research reflects the analysis of results from three sites in the territory of Latvia. In the sites with the total length of 85 km GPR data was gathered after taking 86 core samples to determine pavement layer thickness. The void content in these drilled core samples was measured with laboratory methods. Void content was also measured with laboratory methods. The results show that dielectric permittivity coefficient (ε′), determined with the metal plate test, was equal to the one estimated from the drilling on sites if road pavement materials were similar in all layers. Void content test results have showed no correlation with the ε′ determined with the metal plate test.","PeriodicalId":170169,"journal":{"name":"2021 11th International Workshop on Advanced Ground Penetrating Radar (IWAGPR)","volume":"68 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122714291","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-12-01DOI: 10.1109/iwagpr50767.2021.9843158
F. Crawford, T. Bechtel, G. Pochanin, P. Falorni, K. Asfar, L. Capineri, M. Dimitri
We present an overview of a system under development, with NATO funding, wherein a team of robots uses multiple sensors to identify and characterize buried landmines or other explosive threats. Two of these sensors are ground penetrating radars (GPRs). One is an ultra-wideband impulse radar and the other is a continuous wave holographic subsurface imaging radar. In an earlier phase of the project, these sensors were successfully tested using a prototype robot on which both GPRs were mounted. The separate robots are connected via a central unit with shared data and communication. We describe the planned strategy using these two key sensors and others to automatically navigate and efficiently survey a minefield. With this novel approach, and with tripwire detection enabled on the first robot, the complex task of threat detection will be automatic and rendered completely safe for the operator. The risk of unexpected blasts from undetected tripwires or triggered pressure plates will also be mitigated.
{"title":"Demining Robots: Overview and Mission Strategy for Landmine Identification in the Field","authors":"F. Crawford, T. Bechtel, G. Pochanin, P. Falorni, K. Asfar, L. Capineri, M. Dimitri","doi":"10.1109/iwagpr50767.2021.9843158","DOIUrl":"https://doi.org/10.1109/iwagpr50767.2021.9843158","url":null,"abstract":"We present an overview of a system under development, with NATO funding, wherein a team of robots uses multiple sensors to identify and characterize buried landmines or other explosive threats. Two of these sensors are ground penetrating radars (GPRs). One is an ultra-wideband impulse radar and the other is a continuous wave holographic subsurface imaging radar. In an earlier phase of the project, these sensors were successfully tested using a prototype robot on which both GPRs were mounted. The separate robots are connected via a central unit with shared data and communication. We describe the planned strategy using these two key sensors and others to automatically navigate and efficiently survey a minefield. With this novel approach, and with tripwire detection enabled on the first robot, the complex task of threat detection will be automatic and rendered completely safe for the operator. The risk of unexpected blasts from undetected tripwires or triggered pressure plates will also be mitigated.","PeriodicalId":170169,"journal":{"name":"2021 11th International Workshop on Advanced Ground Penetrating Radar (IWAGPR)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127801833","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-12-01DOI: 10.1109/iwagpr50767.2021.9843156
Lilong Zou, F. Tosti, Livia Lantini, A. Alani
Ground penetrating radar (GPR) is one of the most commonly used technologies for non-destructive testing (NDT). With the development of GPR signal processing methodologies, researchers are becoming more concerned not just with the detection of the target itself, but also with their physical properties and main features. In general, full waveform inversion algorithm is required to achieve this aim. But, full waveform inversion problem is a costive approach which need a huge computation. Thus, the ultimate goal of this study is to explore an effective strategy for estimating the relative permittivity of the target using polarimetric GPR data. We have investigated the relation between relative permittivity and polarimetric alpha angle based on the data collected by dualpolarization antennas GPR system. Laboratory experiments that measures different moisture sand targets (simulating for different relative permittivity target) in tree trunk holes have been carried out, taken as analog models for the physiological process representing decays in trees. After signal processing, the rough results that alpha angle versus with relative permittivity were obtained. The results show that for a dry sand the polarimetric alpha angle is small and the polarimetric alpha angle increases with increasing water content.
{"title":"Polarimetric Alpha Angle versus Relative Permittivity with Dual-Polarimetric GPR Experiments","authors":"Lilong Zou, F. Tosti, Livia Lantini, A. Alani","doi":"10.1109/iwagpr50767.2021.9843156","DOIUrl":"https://doi.org/10.1109/iwagpr50767.2021.9843156","url":null,"abstract":"Ground penetrating radar (GPR) is one of the most commonly used technologies for non-destructive testing (NDT). With the development of GPR signal processing methodologies, researchers are becoming more concerned not just with the detection of the target itself, but also with their physical properties and main features. In general, full waveform inversion algorithm is required to achieve this aim. But, full waveform inversion problem is a costive approach which need a huge computation. Thus, the ultimate goal of this study is to explore an effective strategy for estimating the relative permittivity of the target using polarimetric GPR data. We have investigated the relation between relative permittivity and polarimetric alpha angle based on the data collected by dualpolarization antennas GPR system. Laboratory experiments that measures different moisture sand targets (simulating for different relative permittivity target) in tree trunk holes have been carried out, taken as analog models for the physiological process representing decays in trees. After signal processing, the rough results that alpha angle versus with relative permittivity were obtained. The results show that for a dry sand the polarimetric alpha angle is small and the polarimetric alpha angle increases with increasing water content.","PeriodicalId":170169,"journal":{"name":"2021 11th International Workshop on Advanced Ground Penetrating Radar (IWAGPR)","volume":"71 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115741627","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-12-01DOI: 10.1109/iwagpr50767.2021.9843155
V. Plakhtii, G. Pochanin, P. Falorni, V. Ruban, T. Bechtel, L. Bossi
We investigated the implementation of artificial neural networks in the detection and discrimination of landmines and similar objects. The experimental data were obtained by using impulse GPR with a 1 Tx + 4Rx antenna system. The possibility of improving the input data by the moving average method was shown. Object identifications and positions are perfect for low noise and for object positions directly under the antenna array. Accuracy declines with increased noise and with distance from the antenna array. For positions of objects that are offset from the training data, the position is still determined with the greatest possible accuracy. The artificial neural network has proven successful in the task of determining the type and positions of the test objects.
{"title":"Determining the coordinates of objects detected by a 1Tx + 4Rx antenna system using an artificial neural network; free space case","authors":"V. Plakhtii, G. Pochanin, P. Falorni, V. Ruban, T. Bechtel, L. Bossi","doi":"10.1109/iwagpr50767.2021.9843155","DOIUrl":"https://doi.org/10.1109/iwagpr50767.2021.9843155","url":null,"abstract":"We investigated the implementation of artificial neural networks in the detection and discrimination of landmines and similar objects. The experimental data were obtained by using impulse GPR with a 1 Tx + 4Rx antenna system. The possibility of improving the input data by the moving average method was shown. Object identifications and positions are perfect for low noise and for object positions directly under the antenna array. Accuracy declines with increased noise and with distance from the antenna array. For positions of objects that are offset from the training data, the position is still determined with the greatest possible accuracy. The artificial neural network has proven successful in the task of determining the type and positions of the test objects.","PeriodicalId":170169,"journal":{"name":"2021 11th International Workshop on Advanced Ground Penetrating Radar (IWAGPR)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122722090","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-12-01DOI: 10.1109/iwagpr50767.2021.9843163
Rajat Mehta, Ahtisham Fazeel, Petrit Rama, Michael Danner, N. Bajçinca, Paul-Benjamin Riedel, Jakob Schwabe
Ground Penetrating Radar (GPR) has a wide range of applications such as scanning underground surface, locating utilities and detecting road damages by analysing the radargrams. Detecting sub-surface road damages is of great importance to the road maintenance authorities as it serves for monitoring of construction processes and helps in early detection of the damages leading to reduced repair costs. The road damages are detected by manual processing and require interpretation of domain experts. This often is too uneconomic for large scale application, therefore one way to solve this problem is to use an AI approach. In this work, this problem is addressed by developing a single-stage object detection system based on the YOLO series for detecting various patterns under the road surface including sub-surface damages. Advanced machine learning techniques like data augmentation and transfer learning are used to improve the detection results. We also present a model ensembling technique that can be used to combine multiple models for making better predictions. The ensemble helps in reducing the generalization errors and dispersion of predictions coming from the individual models. Experimental results verify that YOLO combined with model ensembling provides considerable performance improvements in comparison to the classical computer vision methods.
{"title":"CNN-Based Sub-Surface Object Detection Using Ground Penetrating Radar","authors":"Rajat Mehta, Ahtisham Fazeel, Petrit Rama, Michael Danner, N. Bajçinca, Paul-Benjamin Riedel, Jakob Schwabe","doi":"10.1109/iwagpr50767.2021.9843163","DOIUrl":"https://doi.org/10.1109/iwagpr50767.2021.9843163","url":null,"abstract":"Ground Penetrating Radar (GPR) has a wide range of applications such as scanning underground surface, locating utilities and detecting road damages by analysing the radargrams. Detecting sub-surface road damages is of great importance to the road maintenance authorities as it serves for monitoring of construction processes and helps in early detection of the damages leading to reduced repair costs. The road damages are detected by manual processing and require interpretation of domain experts. This often is too uneconomic for large scale application, therefore one way to solve this problem is to use an AI approach. In this work, this problem is addressed by developing a single-stage object detection system based on the YOLO series for detecting various patterns under the road surface including sub-surface damages. Advanced machine learning techniques like data augmentation and transfer learning are used to improve the detection results. We also present a model ensembling technique that can be used to combine multiple models for making better predictions. The ensemble helps in reducing the generalization errors and dispersion of predictions coming from the individual models. Experimental results verify that YOLO combined with model ensembling provides considerable performance improvements in comparison to the classical computer vision methods.","PeriodicalId":170169,"journal":{"name":"2021 11th International Workshop on Advanced Ground Penetrating Radar (IWAGPR)","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123176664","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：