Exploiting Ground-Penetrating Radar Phenomenology in a Context-Dependent Framework for Landmine Detection and Discrimination

A technique for making landmine detection with a ground-penetrating radar (GPR) sensor more robust to fluctuations in environmental conditions is presented. Context-dependent feature selection (CDFS) counteracts environmental uncertainties that degrade detection and discrimination performances by modifying decision rules based on inference of the environmental context. This paper utilized both physics-based and statistical methods for extracting features from GPR data to characterize surface texture and subsurface electrical properties, and a nonparametric hypothesis test was used to identify the environmental context from which the data were collected. The results of probabilistic context identification were then used to fuse an ensemble of classifiers for discriminating landmines from clutter under diverse environmental conditions. CDFS was evaluated on a large set of GPR data collected over several years in different weather and terrain conditions. Results indicate that our context-dependent technique improved landmine discrimination performance over conventional fusion of several currently fielded algorithms from the recent literature.

[1]  Farid Melgani,et al.  Automatic Analysis of GPR Images: A Pattern-Recognition Approach , 2009, IEEE Transactions on Geoscience and Remote Sensing.

[2]  Alexey Tsymbal,et al.  The problem of concept drift: definitions and related work , 2004 .

[3]  Carl E. Rasmussen,et al.  Factorial Hidden Markov Models , 1997 .

[4]  Jan M. H. Hendrickx,et al.  Radar Detection of Buried Landmines in Field Soils , 2004 .

[5]  Stefan Finsterle,et al.  Estimation of field‐scale soil hydraulic and dielectric parameters through joint inversion of GPR and hydrological data , 2005 .

[6]  Ying Wang,et al.  Measurement of Layer Thickness and Permittivity Using a New Multilayer Model From GPR Data , 2007, IEEE Transactions on Geoscience and Remote Sensing.

[7]  Carl V. Nelson,et al.  Wide bandwidth time-domain electromagnetic sensor for metal target classification , 2001, IEEE Trans. Geosci. Remote. Sens..

[8]  Yi Li,et al.  Bayesian automatic relevance determination algorithms for classifying gene expression data. , 2002, Bioinformatics.

[9]  Yan Zhang,et al.  Profiling the Rough Surface by Migration , 2009, IEEE Geoscience and Remote Sensing Letters.

[10]  A. Wayne Whitney,et al.  A Direct Method of Nonparametric Measurement Selection , 1971, IEEE Transactions on Computers.

[11]  P.A. Torrione,et al.  Performance of an adaptive feature-based processor for a wideband ground penetrating radar system , 2006, IEEE Transactions on Aerospace and Electronic Systems.

[12]  Joseph N. Wilson,et al.  Detecting landmines with ground-penetrating radar using feature-based rules, order statistics, and adaptive whitening , 2004, IEEE Transactions on Geoscience and Remote Sensing.

[13]  Michael I. Jordan,et al.  Factorial Hidden Markov Models , 1995, Machine Learning.

[14]  P. van Genderen,et al.  Convolutional models for buried target characterization with ground penetrating Radar , 2005, IEEE Transactions on Antennas and Propagation.

[15]  Marnik Vanclooster,et al.  Modeling of ground-penetrating Radar for accurate characterization of subsurface electric properties , 2004, IEEE Transactions on Geoscience and Remote Sensing.

[16]  Joseph N. Wilson,et al.  An Investigation of Using the Spectral Characteristics From Ground Penetrating Radar for Landmine/Clutter Discrimination , 2008, IEEE Transactions on Geoscience and Remote Sensing.

[17]  Leslie M. Collins,et al.  Decision Fusion of Ground-Penetrating Radar and Metal Detector Algorithms—A Robust Approach , 2007, IEEE Transactions on Geoscience and Remote Sensing.

[18]  James Byrnes,et al.  Unexploded Ordnance Detection and Mitigation , 2008 .

[19]  Leslie M. Collins,et al.  Texture Features for Antitank Landmine Detection Using Ground Penetrating Radar , 2007, IEEE Transactions on Geoscience and Remote Sensing.

[20]  S. Haykin,et al.  Adaptive Filter Theory , 1986 .

[21]  Paul D. Gader,et al.  Random Set Framework for Context-Based Classification With Hyperspectral Imagery , 2009, IEEE Transactions on Geoscience and Remote Sensing.

[22]  Levent Gürel,et al.  Simulations of ground-penetrating radars over lossy and heterogeneous grounds , 2001, IEEE Trans. Geosci. Remote. Sens..

[23]  Evert C. Slob,et al.  Filtering Soil Surface and Antenna Effects From GPR Data to Enhance Landmine Detection , 2007, IEEE Transactions on Geoscience and Remote Sensing.

[24]  K. C. Ho,et al.  Particle Filtering Based Approach for Landmine Detection Using Ground Penetrating Radar , 2008, IEEE Transactions on Geoscience and Remote Sensing.

[25]  Lutgarde M. C. Buydens,et al.  KNN-kernel density-based clustering for high-dimensional multivariate data , 2006, Comput. Stat. Data Anal..

[26]  George Eastman House,et al.  Sparse Bayesian Learning and the Relevance Vector Machine , 2001 .

[27]  Gerhard Widmer,et al.  Learning in the presence of concept drift and hidden contexts , 2004, Machine Learning.

[28]  Motoyuki Sato,et al.  Investigation of Time–Frequency Features for GPR Landmine Discrimination , 2007, IEEE Transactions on Geoscience and Remote Sensing.

[29]  Thomas Marill,et al.  On the effectiveness of receptors in recognition systems , 1963, IEEE Trans. Inf. Theory.

[30]  Hagai Attias,et al.  A Variational Bayesian Framework for Graphical Models , 1999 .

[31]  Michael I. Jordan,et al.  Variational inference for Dirichlet process mixtures , 2006 .

[32]  Paul D. Gader,et al.  Landmine detection with ground penetrating radar using hidden Markov models , 2001, IEEE Trans. Geosci. Remote. Sens..

[33]  Eric R. Ziegel,et al.  The Elements of Statistical Learning , 2003, Technometrics.

[34]  Carey M. Rappaport,et al.  Quantifying the effects of different rough surface statistics for mine detection using the FDTD technique , 2000, Defense, Security, and Sensing.

[35]  Alexander G. Yarovoy,et al.  A Novel Clutter Suppression Algorithm for Landmine Detection With GPR , 2007, IEEE Transactions on Geoscience and Remote Sensing.

[36]  Zhimin Zhou,et al.  Feature Extraction and Discriminator Design for Landmine Detection on Double-Hump Signature in Ultrawideband SAR , 2008, IEEE Transactions on Geoscience and Remote Sensing.

[37]  Jacques R. Ernst,et al.  Full-Waveform Inversion of Crosshole Radar Data Based on 2-D Finite-Difference Time-Domain Solutions of Maxwell's Equations , 2007, IEEE Transactions on Geoscience and Remote Sensing.

[38]  Johan Alexander Huisman,et al.  Measuring soil water content with ground penetrating radar , 2003 .

[39]  Paul D. Gader,et al.  Context-Dependent Multisensor Fusion and Its Application to Land Mine Detection , 2010, IEEE Transactions on Geoscience and Remote Sensing.

[40]  David J. Daniels,et al.  Ground Penetrating Radar for Buried Landmine and IED Detection , 2009 .

[41]  Lawrence Carin,et al.  Multi-Task Learning for Classification with Dirichlet Process Priors , 2007, J. Mach. Learn. Res..

[42]  Paul D. Gader,et al.  Detection and Discrimination of Land Mines in Ground-Penetrating Radar Based on Edge Histogram Descriptors and a Possibilistic $K$-Nearest Neighbor Classifier , 2009, IEEE Transactions on Fuzzy Systems.

[43]  Waymond R. Scott,et al.  Adaptive Multimodality Sensing of Landmines , 2007, IEEE Transactions on Geoscience and Remote Sensing.

[44]  Eric L. Miller,et al.  Subsurface Sensing of Buried Objects Under a Randomly Rough Surface Using Scattered Electromagnetic Field Data , 2007, IEEE Transactions on Geoscience and Remote Sensing.

[45]  Joseph N. Wilson,et al.  Optimizing the Area Under a Receiver Operating Characteristic Curve With Application to Landmine Detection , 2007, IEEE Transactions on Geoscience and Remote Sensing.

[46]  A. P. Annan,et al.  Measuring Soil Water Content with Ground Penetrating Radar: A Review , 2003 .

[47]  Vsevolod O. Kovalenko,et al.  Advanced GPR data processing algorithms for detection of anti-personnel landmines , 2006 .

[48]  K. D. Sherbondy.  Status of vehicular mounted mine detection (VMMD) program , 1998 .

[49]  Joseph N. Wilson,et al.  A Large-Scale Systematic Evaluation of Algorithms Using Ground-Penetrating Radar for Landmine Detection and Discrimination , 2007, IEEE Transactions on Geoscience and Remote Sensing.

[50]  Lawrence R. Rabiner,et al.  A tutorial on hidden Markov models and selected applications in speech recognition , 1989, Proc. IEEE.

[51]  Christopher M. Bishop,et al.  Bayesian Hierarchical Mixtures of Experts , 2002, UAI.

[52]  L. Peters,et al.  Ground penetrating radar as a subsurface environmental sensing tool , 1994, Proc. IEEE.

[53]  Carey M. Rappaport.  Accurate Determination of Underground GPR Wavefront and B-Scan Shape From Above-Ground Point Sources , 2007, IEEE Transactions on Geoscience and Remote Sensing.