Application of Support Vector Machines for Estimating Wall Parameters in Through-Wall Radar Imaging

In through-wall radar imaging (TWRI), ambiguities in wall characteristics including the thickness and the relative permittivity will distort the image and shift the imaged target position. To quickly and accurately estimate the wall parameters, an approach based on a support vector machine (SVM) is proposed. In TWRI problem, the nonlinearity is embodied in the relationship between backscatter data and the wall parameters, which can be obtained through the SVM training process. Measurement results reveal that once the training phase is completed, the technique only needs no more than one second to estimate wall parameters with acceptable errors. Then through-wall images are reconstructed using a back-projection (BP) algorithm by a finite-difference time-domain (FDTD) simulation. Noiseless and noisy measurements are discussed; the simulation results demonstrate that noisy contamination has little influence on the imaging quality. Furthermore, the feasibility and the validity are tested by a more realistic situation. The results show that high-quality and focused images are obtained regardless of the errors in the wall parameter estimates.

[1]  Pan Li,et al.  GPR identification of voids inside concrete based on support vector machine (SVM) algorithm , 2012, 2012 14th International Conference on Ground Penetrating Radar (GPR).

[2]  Fang-Fang Wang,et al.  THE SUPPORT VECTOR MACHINE FOR DIELECTRIC TARGET DETECTION THROUGH A WALL , 2011 .

[3]  Sandeep Kaushal,et al.  Role of signal processing for estimating the wall thickness for TWI system , 2013, 2013 Fourth International Conference on Computing, Communications and Networking Technologies (ICCCNT).

[4]  M.G. Amin,et al.  Imaging Through Unknown Walls Using Different Standoff Distances , 2006, IEEE Transactions on Signal Processing.

[5]  L. Kong,et al.  A new approach for wall parameters estimation in through-the-wall radar imaging , 2011, 2011 IEEE RadarCon (RADAR).

[7]  Fang Li,et al.  Autofocusing imaging through the unknown building walls , 2008, 2008 Asia-Pacific Microwave Conference.

[8]  J. Machac,et al.  Estimation of Wall Parameters From Time-Delay-Only Through-Wall Radar Measurements , 2011, IEEE Transactions on Antennas and Propagation.

[9]  M. Amin,et al.  New approach for target locations in the presence of wall ambiguities , 2006, IEEE Transactions on Aerospace and Electronic Systems.

[10]  Henry Leung,et al.  An intelligent through-the-wall recognition system for homeland security , 2008, 2008 IEEE International Joint Conference on Neural Networks (IEEE World Congress on Computational Intelligence).

[11]  J. Macháč,et al.  An improved technique for estimating wall parameters from time-delay through-wall radar measurements , 2012, Proceedings of 22nd International Conference Radioelektronika 2012.

[12]  F.-F. Wang,et al.  A Real-Time Through-Wall Detection Based on Support Vector Machine , 2011 .

[13]  Yunhua Zhang,et al.  Autofocus imaging simulation for through-wall radar by using FDTD with unknown wall characteristics , 2010, 2010 Asia-Pacific Microwave Conference.

[14]  Zhimin Zhou,et al.  Image-Domain Estimation of Wall Parameters for Autofocusing of Through-the-Wall SAR Imagery , 2013, IEEE Transactions on Geoscience and Remote Sensing.

[15]  S. Kassam,et al.  Synthetic aperture beamformer for imaging through a dielectric wall , 2005, IEEE Transactions on Aerospace and Electronic Systems.

[16]  Y. Kim,et al.  Through-Wall Human Tracking With Multiple Doppler Sensors Using an Artificial Neural Network , 2009, IEEE Transactions on Antennas and Propagation.

[17]  Yimin Zhang,et al.  Three-Dimensional Wideband Beamforming for Imaging Through a Single Wall , 2008, IEEE Geoscience and Remote Sensing Letters.

[18]  李廉林,et al.  A Novel Autofocusing Approach for Real-Time Through-Wall Imaging Under Unknown Wall Characteristics , 2010 .