Feature-based processing of prescreener-generated alarms for performance improvements in target identification using the NIITEK ground-penetrating radar system

In this paper we present a multi-stage algorithm for target/clutter discrimination and target identification using the Niitek/Wichmann ground penetrating radar (GPR). To identify small subsets of GPR data for feature-processing, a pre-screening algorithm based on the 2-D lattice least mean squares (LMS) algorithm is used to flag locations of interest. Features of the measured GPR data at these flagged locations are then generated and pattern recognition techniques are used to identify targets using these feature sets. It has been observed that trained human subjects are often quite successful at discriminating targets from clutter. Some features are designed to take advantage of the visual aberrations that a human observer might use. Other features based on a variety of image and signal processing techniques are also considered. Results presented indicate improvements for feature-based processors over pre-screener algorithms.

[1]  Dean Keiswetter,et al.  Electromagnetic Induction Spectroscopy , 1998 .

[2]  Leslie M. Collins,et al.  A comparison of optimal and suboptimal processors for classification of buried metal objects , 1999, IEEE Signal Processing Letters.

[3]  Waymond R. Scott,et al.  Experimental model for a seismic landmine detection system , 2001, IEEE Trans. Geosci. Remote. Sens..

[4]  Gunnar Rätsch,et al.  An introduction to kernel-based learning algorithms , 2001, IEEE Trans. Neural Networks.

[5]  Peter A. Torrione,et al.  Application of the LMC algorithm to anomaly detection using the Wichmann/NIITEK ground-penetrating radar , 2003, SPIE Defense + Commercial Sensing.

[6]  J. Suykens.  Nonlinear modelling and support vector machines , 2001, IMTC 2001. Proceedings of the 18th IEEE Instrumentation and Measurement Technology Conference. Rediscovering Measurement in the Age of Informatics (Cat. No.01CH 37188).

[7]  Erik G. Larsson,et al.  Elimination of leakage and ground-bounce effects in ground-penetrating radar data , 2001, Proceedings of the 11th IEEE Signal Processing Workshop on Statistical Signal Processing (Cat. No.01TH8563).

[8]  Y. Das,et al.  Analysis of an electromagnetic induction detector for real-time location of buried objects , 1990 .

[9]  L. Kleinmann,et al.  Image processing and pattern recognition in ground penetrating radar data , 1993, Proceedings of IGARSS '93 - IEEE International Geoscience and Remote Sensing Symposium.

[10]  Chiman Kwan,et al.  Target detection with texture feature coding method and support vector machines , 2004, 2004 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[11]  Thomas H. Bell,et al.  Subsurface discrimination using electromagnetic induction sensors , 2001, IEEE Trans. Geosci. Remote. Sens..

[12]  I. J. Won,et al.  Characterization of UXO-like targets using broadband electromagnetic induction sensors , 2003, IEEE Trans. Geosci. Remote. Sens..

[13]  Thomas H. Bell,et al.  Electromagnetic induction spectroscopy for clearing landmines , 2001, IEEE Trans. Geosci. Remote. Sens..

[14]  C. V. van Eijk,et al.  Landmine detection with the neutron backscattering method , 2000, 2000 IEEE Nuclear Science Symposium. Conference Record (Cat. No.00CH37149).

[15]  L. Carin,et al.  A new algorithm for independent component analysis with or without constraints , 2002, Sensor Array and Multichannel Signal Processing Workshop Proceedings, 2002.

[16]  Leslie M. Collins,et al.  Classification of landmine-like metal targets using wideband electromagnetic induction , 2000, IEEE Trans. Geosci. Remote. Sens..

[17]  Bruce Barrow,et al.  Model-based characterization of electromagnetic induction signatures obtained with the MTADS electromagnetic array , 2001, IEEE Trans. Geosci. Remote. Sens..

[18]  Thomas H. Bell,et al.  Simple phenomenological models for wideband frequency-domain electromagnetic induction , 2001, IEEE Trans. Geosci. Remote. Sens..

[19]  Nello Cristianini,et al.  An Introduction to Support Vector Machines and Other Kernel-based Learning Methods , 2000 .

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

[21]  L. Collins,et al.  Model-based statistical signal processing using electromagnetic induction data for landmine detection and classification , 2001, Proceedings of the 11th IEEE Signal Processing Workshop on Statistical Signal Processing (Cat. No.01TH8563).

[22]  Ning Xiang,et al.  An investigation of acoustic-to-seismic coupling to detect buried antitank landmines , 2001, IEEE Trans. Geosci. Remote. Sens..

[23]  Chi-Chih Chen,et al.  Ultrawide-bandwidth fully-polarimetric ground penetrating radar classification of subsurface unexploded ordnance , 2001, IEEE Trans. Geosci. Remote. Sens..

[24]  James A. Bucklew,et al.  Support vector machines and the multiple hypothesis test problem , 2001, IEEE Trans. Signal Process..

[25]  Leslie M. Collins,et al.  A statistical approach to landmine detection using broadband electromagnetic induction data , 2002, IEEE Trans. Geosci. Remote. Sens..