Land Mine and Clutter Object Discrimination Using Wavelet and Time Domain Spatially Distributed Features from Metal Detectors and Their Fusion with GPR Features for Hand-Held Units

AbstractThis paper presents some advances in discrimination and fusion algorithms using metal detector (MD) and ground penetrating radar (GPR) sensors in a robotic wand unit. Previously investigated spatially distributed features are extended and fused with discrete wavelet transform representations of MD data. A multilayer perceptron technique is then applied to discriminate between land mine and land mine-like objects based on the wavelet coefficient and time domain features separately. Using MD wavelet and time domain fusion, the probability of false alarms is reduced by 46.0% and 18.0% over the wavelet and time domain models, respectively, at 0.95 probability of detection. Fusion results are presented for the MD and GPR sensors to demonstrate that the two sensors provide complementary information for significantly reducing the probability of false alarm. Blind test results from a government test facility are presented to evaluate the effectiveness of the algorithms.

[1]  Lawrence Carin,et al.  Improved decision-theoretic approach to the optimum detection of mines , 1997, Defense, Security, and Sensing.

[2]  Paul D. Gader,et al.  A linear prediction land mine detection algorithm for hand held ground penetrating radar , 2002, IEEE Trans. Geosci. Remote. Sens..

[3]  Ingrid Daubechies,et al.  Ten Lectures on Wavelets , 1992 .

[4]  Marc Acheroy,et al.  Characterization of mine detection sensors in terms of belief functions and their fusion, first results , 2000, Proceedings of the Third International Conference on Information Fusion.

[5]  Leslie M. Collins,et al.  Single-sensor processing and sensor fusion of GPR and EMI data for land mine detection , 1999, Defense, Security, and Sensing.

[6]  Nada Milisavljevic,et al.  Comparison of three methods for shape recognition in the case of mine detection , 1999, Pattern Recognit. Lett..

[7]  Paul D. Gader,et al.  Feature and decision level sensor fusion of electromagnetic induction and ground penetrating radar sensors for landmine detection with hand-held units , 2002, Inf. Fusion.

[8]  Paul D. Gader,et al.  Impact of weighted density distribution function features on land mine detection using hand-held units , 2002, SPIE Defense + Commercial Sensing.

[9]  Leslie M. Collins,et al.  Discrimination mode processing for EMI and GPR sensors for hand-held land mine detection , 2004, IEEE Transactions on Geoscience and Remote Sensing.

[10]  Paul D. Gader,et al.  Detecting landmines using weighted density distribution function features , 2001, SPIE Defense + Commercial Sensing.

[11]  J. Piper,et al.  On fully automatic feature measurement for banded chromosome classification. , 1989, Cytometry.