In this study, identification of the different metallic objects with various burial depths was considered. Metal Detector
(MD) and Ground Penetrating Radar (GPR) were used to obtain metallic content and dielectric characteristic of the
buried objects. Discriminative features were determined and calculated for data set. Six features were selected for metal
detector and one for Ground Penetrating Radar. Twenty classification algorithms were examined to obtain the best
classification method, for this data set. A Meta learner algorithm completed the classification process with 100%
performance.
KEYWORDS: Sensors, General packet radio service, Digital filtering, Signal processing, Monte Carlo methods, Statistical analysis, Antennas, Signal detection, Receivers, Electronic filtering
In this study buried object detection on the GPR data is examined using CA-CFAR detector. In the first part of the study
the background signals of B-scan frames from a pulse GPR is statistically inspected. The results revealed that the
background signals residual from a removing process of the dominant GPR signals due to air-to-ground interface have
shown K-Distributed statistics. The form and scale parameters of K-Distribution are estimated using the fractional
moments. The background or the clutter signals from three different soils have resulted in distinctive shape parameters.
The shape parameter of the distribution could generally discriminate three soils. In the second part of the study the
receiver loss of CA-CFAR detector is estimated using a numerical method and the Monte-Carlo simulation. The
receiver loss is also associated to the K-Distribution and CA-CFAR detector parameters in the simulation. Time series
with statistical properties similar to those of the real measurements are obtained using SIRV and employed in the
Monte-Carlo simulation. In the third part of the study effectiveness of CA-CFAR detector on B-scan frames is analyzed
by measuring the ROC of the detector. High detection probabilities of buried objects at relatively low SNR data are
obtained by CA-CFAR detector.
Electromagnetic Induction sensor (Metal Detector) has wide application areas for buried metallic object searching, such
as detection of buried pipes, mine and mine like-targets, etc. In this paper, identification of buried metallic objects was
studied. The distinctive features of the signal were obtained, than classification process was performed. Identification
process was realized by utilizing k-Nearest neighbor and Neural Network Classifiers.
KEYWORDS: General packet radio service, Signal detection, Dielectric filters, Linear filtering, Dielectrics, Target detection, Signal processing, Land mines, Detection and tracking algorithms, Inspection
In this paper, we studied the effects of the preprocessing techniques over buried object detection performance. We examined different preprocessing techniques applied before the detection algorithm proposed by Sezgin [1]. It is obtained that used preprocessing techniques decreases false alarm rates in real environment. We used different size of objects and burial depths for both metallic and non-metallic targets.
A new preprocessing and feature extracting approach for classification of non-metallic buried objects are aimed using GPR B-scan data. A frequency-domain adaptive filter without a reference channel effectively removes the background signal resulting mostly from the discontinuity on the air-to-ground path of the electromagnetic waves. The filter only needs average of the first five A-scans as the reference signal for this elimination, and also serves for masking of the B-scan in the frequency-domain. A preprocessed GPR data with significantly suppressed clutter is then obtained by precisely positioning the Hanning window in the frequency-domain. A directional correlation function defined over a B-scan frame gives distinctive curves of buried objects. The main axis of directional correlation, on which the pivotal correlating pixels and short lines of pixels being correlated are considered, makes an angle to the scanning direction of the B-scan. This form of correlation is applied to the frame from the left-hand and the right-hand side and two over-plotted curves are obtained. Nine measures as features emphasizing directional signatures are extracted from these curves. Nine-element feature vectors are applied to the two-layer Artificial Neural Network and preliminary results over test set are promising to continue to comprehensive training and testing processes.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.