Landmine detection using the discrete spectrum of relaxation frequencies

Several landmine detection techniques using electromagnetic induction (EMI) sensors have been proposed in the past decade. In this paper, we propose a class of detection techniques based on the discrete spectrum of relaxation frequencies (DSRF). Two DSRF detection methods are demonstrated: one using the support vector machine and one using the k-nearest neighbor method. A soil model is also proposed to identify EMI response from the magnetic properties of the soil. A detection framework is suggested to incorporate the soil model and the classifier. The robustness of landmine detection using the DSRF is demonstrated. Approved for public release; distribution is unlimited.

[1]  Carl E. Baum,et al.  On the Singularity Expansion Method for the Solution of Electromagnetic Interaction Problems , 1971 .

[2]  Leonidas J. Guibas,et al.  A metric for distributions with applications to image databases , 1998, Sixth International Conference on Computer Vision (IEEE Cat. No.98CH36271).

[3]  Joseph N. Wilson,et al.  GRANMA: Gradient Angle Model Algorithm on Wideband EMI Data for Land-Mine Detection , 2010, IEEE Geoscience and Remote Sensing Letters.

[4]  James H. McClellan,et al.  Robust Estimation of the Discrete Spectrum of Relaxations for Electromagnetic Induction Responses , 2010, IEEE Transactions on Geoscience and Remote Sensing.

[5]  Y. Das,et al.  Effects of magnetic soil on metal detectors: preliminary experimental results , 2007, SPIE Defense + Commercial Sensing.

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

[7]  Waymond R. Scott,et al.  Broadband Array of Electromagnetic Induction Sensors for Detecting Buried Landmines , 2008, IGARSS 2008 - 2008 IEEE International Geoscience and Remote Sensing Symposium.

[8]  Patrick Haffner,et al.  Support vector machines for histogram-based image classification , 1999, IEEE Trans. Neural Networks.

[9]  Leslie M. Collins,et al.  Performance of a four parameter model for modeling landmine signatures in frequency domain wideband electromagnetic induction detection systems , 2007, SPIE Defense + Commercial Sensing.

[10]  Cordelia Schmid,et al.  Local Features and Kernels for Classification of Texture and Object Categories: A Comprehensive Study , 2006, 2006 Conference on Computer Vision and Pattern Recognition Workshop (CVPRW'06).

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

[12]  James H. McClellan,et al.  Estimation of the Discrete Spectrum of Relaxations for Electromagnetic Induction Responses Using $\ell_{p}$-Regularized Least Squares for $0 \leq p \leq 1$ , 2011, IEEE Geoscience and Remote Sensing Letters.