Detection and classification of land mine targets in ground penetrating radar images

2002 ◽  
Author(s):  
Naga R. Mudigonda ◽  
Ray Kacelenga ◽  
David Palmer
Keyword(s):  
Ground Penetrating Radar ◽  
Radar Images ◽  
Land Mine ◽  
Ground Penetrating

Texture-based classification of ground-penetrating radar images

Geophysics ◽  
2006 ◽  
Vol 71 (6) ◽  
pp. K111-K118 ◽  
Author(s):  
Stephen Moysey ◽  
Rosemary J. Knight ◽  
Harry M. Jol
Keyword(s):  
Spatial Structure ◽  
Ground Penetrating Radar ◽  
Mellin Transform ◽  
Radar Data ◽  
River Delta ◽  
Radar Images ◽  
Human Interpretation ◽  
Ground Penetrating ◽  
Fourier Mellin Transform

Image texture is one of the key features used for the interpretation of radar facies in ground-penetrating radar (GPR) data. Establishing quantitative measures of texture is therefore a critical step in the effective development of advanced techniques for the interpretation of GPR images. This study presents the first effort to evaluate whether different measures of a GPR image capture the features of the data that, when coupled with a neural network classifier, are able to reproduce a human interpretation. The measures compared in this study are instantaneous amplitude and frequency, as well as the variance, covariance, Fourier-Mellin transform, R-transform, and principle components (PCs) determined for a window of radar data. A [Formula: see text] GPR section collected over the William River delta in Saskatchewan, Canada, is used for the analysis. We found that measures describing the local spatial structure of the GPR image (i.e., covariance, Fourier-Mellin, R-transform, and PCs) were able to reproduce human interpretations with greater than 93% accuracy. In contrast, classifications based on image variance and the instantaneous attributes agreed with the human interpretation less than 68% of the time. Among the textural measures that preserve spatial structure, we found that the best ones are insensitive to within facies variability while emphasizing differences between facies. For the specific case of the William River delta, the Fourier-Mellin transform, which retains information about the spatial correlation of reflections while remaining insensitive to their orientation, outperformed the other measures. Our work in describing radar texture provides an important first step in defining quantitative criteria that can be used to aid in the classification of radar data.

Seismic reflection and ground‐penetrating radar imaging of a shallow aquifer

Geophysics ◽  
1998 ◽  
Vol 63 (4) ◽  
pp. 1310-1317 ◽  
Author(s):  
Steven J. Cardimona ◽  
William P. Clement ◽  
Katharine Kadinsky‐Cade
Keyword(s):  
Water Table ◽  
Ground Penetrating Radar ◽  
Low Frequency ◽  
Shallow Aquifer ◽  
Cone Penetrometer ◽  
Gradual Change ◽  
Cone Penetration ◽  
Geotechnical Data ◽  
Radar Images ◽  
Ground Penetrating

In 1995 and 1996, researchers associated with the US Air Force’s Phillips and Armstrong Laboratories took part in an extensive geophysical site characterization of the Groundwater Remediation Field Laboratory located at Dover Air Force Base, Dover, Delaware. This field experiment offered an opportunity to compare shallow‐reflection profiling using seismic compressional sources and low‐frequency ground‐penetrating radar to image a shallow, unconfined aquifer. The main target within the aquifer was the sand‐clay interface defining the top of the underlying aquitard at 10 to 14 m depth. Although the water table in a well near the site was 8 m deep, cone penetration geotechnical data taken across the field do not reveal a distinct water table. Instead, cone penetration tests show a gradual change in electrical properties that we interpret as a thick zone of partial saturation. Comparing the seismic and radar data and using the geotechnical data as ground truth, we have associated the deepest coherent event in both reflection data sets with the sand‐clay aquitard boundary. Cone penetrometer data show the presence of a thin lens of clays and silts at about 4 m depth in the north part of the field. This shallow clay is not imaged clearly in the low‐frequency radar profiles. However, the seismic data do image the clay lens. Cone penetrometer data detail a clear change in the soil classification related to the underlying clay aquitard at the same position where the nonintrusive geophysical measurements show a change in image character. Corresponding features in the seismic and radar images are similar along profiles from common survey lines, and results of joint interpretation are consistent with information from geotechnical data across the site.

scholarly journals Object Detection in Ground-Penetrating Radar Images Using a Deep Convolutional Neural Network and Image Set Preparation by Migration

2018 ◽  
Vol 2018 ◽  
pp. 1-8 ◽  
Author(s):  
Kazuya Ishitsuka ◽  
Shinichiro Iso ◽  
Kyosuke Onishi ◽  
Toshifumi Matsuoka
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Ground Penetrating Radar ◽  
Deep Convolutional Neural Network ◽  
Training Data ◽  
Neural Network Approach ◽  
Radar Images ◽  
Image Set ◽  
Ground Penetrating ◽  
Better Than

Ground-penetrating radar allows the acquisition of many images for investigation of the pavement interior and shallow geological structures. Accordingly, an efficient methodology of detecting objects, such as pipes, reinforcing steel bars, and internal voids, in ground-penetrating radar images is an emerging technology. In this paper, we propose using a deep convolutional neural network to detect characteristic hyperbolic signatures from embedded objects. As a first step, we developed a migration-based method to collect many training data and created 53510 categorized images. We then examined the accuracy of the deep convolutional neural network in detecting the signatures. The accuracy of the classification was 0.945 (94.5%)–0.979 (97.9%) when using several thousands of training images and was much better than the accuracy of the conventional neural network approach. Our results demonstrate the effectiveness of the deep convolutional neural network in detecting characteristic events in ground-penetrating radar images.

scholarly journals Particle Center Supported Plane for Subsurface Target Classification based on Full Polarimetric Ground Penetrating Radar

2019 ◽  
Vol 11 (4) ◽  
pp. 405
Author(s):  
Xuan Feng ◽  
Haoqiu Zhou ◽  
Cai Liu ◽  
Yan Zhang ◽  
Wenjing Liang ◽  
...  
Keyword(s):  
Ground Penetrating Radar ◽  
Decomposition Methods ◽  
Support Vector ◽  
Classification Methods ◽  
Target Classification ◽  
Data Set ◽  
Particle Center ◽  
Ground Penetrating ◽  
New Criterion

The subsurface target classification of ground penetrating radar (GPR) is a popular topic in the field of geophysics. Among the existing classification methods, geometrical features and polarimetric attributes of targets are primarily used. As polarimetric attributes contain more information of targets, polarimetric decomposition methods, such as H-Alpha decomposition, have been developed for target classification of GPR in recent years. However, the classification template used in H-Alpha classification is preset depending on the experience of synthetic aperture radar (SAR); therefore, it may not be suitable for GPR. Moreover, many existing classification methods require excessive human operation, particularly when outliers exist in the sample (the data set containing the features of targets); therefore, they are not efficient or intelligent. We herein propose a new machine learning method based on sample centers, i.e., particle center supported plane (PCSP). The sample center is defined as the point with the smallest sum of distances from all points in the same sample, which is considered as a better representation of the sample without significant effect of the outliers. In this proposed method, particle swarm optimization (PSO) is performed to obtain the sample centers; the new criterion for subsurface target classification is achieved. We applied this algorithm to full polarimetric GPR data measured in the laboratory and outdoors. The results indicate that, comparing with support vector machine (SVM) and classical H-Alpha classification, this new method is more efficient and the accuracy is relatively high.

Sign in / Sign up

Export Citation Format

Share Document