Automatic target detection and discrimination algorithm applicable to ground penetrating radar data

Ground Penetrating Radar (GPR) is considered as one of the promising technologies to address the challenges of detecting buried threat objects. However, the success rate of the GPR systems are limited by operational conditions and the robustness of automatic target recognition (ATR) algorithms embedded with the systems. In this paper an alternate ATR algorithm applicable to GPR is developed by combining image pre-processing and machine learning techniques. The aim of this research was to design a potential solution for detection of threat alarms using GPR data and reducing the number of false alarms through classification into one of the predefined categories of target types. The proposed ATR algorithm has been validated using a data set acquired by a vehicle-mounted GPR array. The data set utilized in this investigation involved greyscale GPR images of threat objects (both conventional and improvised) commonly found in realistic operational scenarios. Target based summaries of the algorithm performance are presented in terms of the probability of detection, false alarm rate, and confidence of allocating detections to a predefined target class.

[1]  L. van Kempen,et al.  Signal processing techniques for clutter parameters estimation and clutter removal in GPR data for landmine detection , 2001, Proceedings of the 11th IEEE Signal Processing Workshop on Statistical Signal Processing (Cat. No.01TH8563).

[2]  Peihua Li,et al.  A clustering-based color model and integral images for fast object tracking , 2006, Signal Process. Image Commun..

[3]  Leslie M. Collins,et al.  Context-dependent landmine detection with ground-penetrating radar using a Hidden Markov Context Model , 2010, 2010 IEEE International Geoscience and Remote Sensing Symposium.

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

[5]  Paul D. Gader,et al.  Land-Mine Detection With Ground-Penetrating Radar Using Multistream Discrete Hidden Markov Models , 2011, IEEE Transactions on Geoscience and Remote Sensing.

[7]  Udo Seiffert,et al.  Fast image segmentation based on boosted random forests, integral images, and features on demand , 2014, 2014 IEEE Symposium on Computational Intelligence in Ensemble Learning (CIEL).

[8]  Udo Seiffert,et al.  Cascaded Reduction and Growing of Result Sets for Combining Object Detectors , 2013, MCS.

[9]  Leslie M. Collins,et al.  Application of Markov random fields to landmine detection in ground penetrating radar data , 2008, SPIE Defense + Commercial Sensing.

[10]  Hichem Frigui,et al.  Comparison of different classification algorithms for landmine detection using GPR , 2010, Defense + Commercial Sensing.

[11]  Paul D. Gader,et al.  Detection and Discrimination of Land Mines based on Edge Histogram Descriptors and Fuzzy K-Nearest Neighbors , 2006, 2006 IEEE International Conference on Fuzzy Systems.

[12]  Ehud Rivlin,et al.  Robust Fragments-based Tracking using the Integral Histogram , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[13]  Paul D. Gader,et al.  Model level fusion of edge histogram descriptors and gabor wavelets for landmine detection with ground penetrating radar , 2010, 2010 IEEE International Geoscience and Remote Sensing Symposium.

[14]  Lakhmi C. Jain,et al.  Detection of Targets in Characteristic GPR Sensor Data Using Machine Learning Techniques , 2013 .

[15]  Paul A. Viola,et al.  Rapid object detection using a boosted cascade of simple features , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[16]  Leslie M. Collins,et al.  A hidden Markov context model for GPR-based landmine detection incorporating stick-breaking priors , 2011, 2011 IEEE International Geoscience and Remote Sensing Symposium.

[17]  Beate Meffert,et al.  Fast Computation of Region Homogeneity with Application in a Surveillance Task , 2010 .

[18]  Leslie M. Collins,et al.  Statistical Models for Landmine Detection in Ground Penetrating Radar: Applications to Synthetic Data Generation and Pre-Screening , 2008, IGARSS 2008 - 2008 IEEE International Geoscience and Remote Sensing Symposium.

[19]  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.

[20]  Braham Barkat,et al.  Signal processing techniques for landmine detection using impulse ground penetrating radar , 2002 .

[21]  H.B.D. Sorensen,et al.  Comparison of PCA and ICA based clutter reduction in GPR systems for anti-personal landmine detection , 2001, Proceedings of the 11th IEEE Signal Processing Workshop on Statistical Signal Processing (Cat. No.01TH8563).

[22]  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.

[23]  Antonio Criminisi,et al.  Object Class Segmentation using Random Forests , 2008, BMVC.

[24]  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 , 2009 .

[25]  Linda G. Shapiro,et al.  Computer and Robot Vision , 1991 .