Deep learning algorithms for detecting explosive hazards in ground penetrating radar data

Proceedings of SPIE - The International Society for Optical Engineering

Volumn 9072, Issue , 2014, Pages

  Besaw, Lance E ^a   Stimac, Philip J ^a  

^a APPLIED RESEARCH ASSOCIATES   (United States)

Author keywords

Anomaly detection; buried explosive hazard; deep learning; ground penetrating radar; neural networks; signal processing; unsupervised learning

Indexed keywords

ERRORS; EXPLOSIVES; FEATURE EXTRACTION; GEOLOGICAL SURVEYS; GROUND PENETRATING RADAR SYSTEMS; HAZARDS; LEARNING ALGORITHMS; NEURAL NETWORKS; PRINCIPAL COMPONENT ANALYSIS; SIGNAL PROCESSING; UNSUPERVISED LEARNING;

ANOMALY DETECTION; BURIED EXPLOSIVE HAZARDS; DEEP BELIEF NETWORK (DBN); DEEP LEARNING; FEATURE EXTRACTION TECHNIQUES; GROUND PENETRATING RADAR; GROUND PENETRATING RADAR (GPR); PROBABILITY OF DETECTION;

EXPLOSIVES DETECTION;

EID: 84905695247     PISSN: 0277786X     EISSN: 1996756X     Source Type: Conference Proceeding    
DOI: 10.1117/12.2052592     Document Type: Conference Paper

References (25)

1. Geneva International Centre for Humanitarian Demining, "Mines other than anti-personnel mines," (March 2012).
2. Joint Improvised Explosive Device Defeat Organization, "Annual report," (2010).
3. Smock, B., Gader, P., and Wilson, J., "DynaMax+ ground-tracking algorithm," Proc. SPIE 8017, 80171I (2011).
4. Torrione, P., Morton, K. Jr. and Besaw, L. E., "Adaptive Gaussian mixture models for pre-screening in GPR data," Proc. SPIE 8017, 80171P (2011).
5. Frigui H. and Gader, P., "Detection and discrimination of land mines in ground-penetrating radar based on edge histogram descriptors and a possibilistic k-nearest neighbor classifier," Fuzzy Systems, IEEE Transactions on 17(1), pp. 185-199 (2009).
6. Horng, M. H., "Texture feature coding method for texture classification," Optical Engineering, 42(1), pp. 228-238 (2003).
7. Frigui, H., Zhang, L., Gader, P., Wilson, J. N., Ho, K. and Mendez-Vazquez, A., "An evaluation of several fusion algorithms for anti-tank landmine detection and discrimination," Information Fusion, (2009).
8. Wilson, J. N., Gader, P. D. and Suh, H. J., "Compactometry, the density distribution, and their use in discriminating landmines and clutter," in Detection and Remediation Technologies for Mines and Minelike Targets X, (2005).
9. Ngan, P., Burke, S., Cresci, R., Wilson, J. N., Gader, P., Ho, K. C., Bartosz, E. and Duvoisin, H., "Development of region processing algorithms for HSTAMIDS: Status and field test results," in Proc. SPIE Detection and Remediation Technologies for Mines and Minelike Targets X, (2007).
10. Ho, K. C. and Gader, P. D., "A linear prediction land mine detector algorithms for handheld ground penetrating radar," IEEE Trans. Geosci. Remote Sensing, 40(6), pp. 1374-1384 (2002).
11. Ho, K. C., Gader, P., Wilson, J. N. and Glenn, T. C., "Landmine detection using frequency domain features from GPR measurements and their fusion with time domain features," Development of region processing algorithms for HSTAMIDS: Status and field test results," in Proc. SPIE Detection and Remediation Technologies for Mines and Minelike Targets X, (2005).
12. Wilson, J. N., Gader, P. D., Ho, K. C., Lee, W. H., Stanely, R. J. and Glenn, T. C., "Region processing of ground penetrating radar and electromagnetic induction for handheld landmine detection" in Proc. SPIE Detection and Remediation Technologies for Mines and Minelike Targets IX, (2004).
13. Bengio, Y., Courville, A. and Vincent, P., "Unsupervised feature learning and deep learning: A review and new perspectives," arXiv preprint arXiv:1206.5538v1, (2012).
14. Hinton, G. E. and Salakhutdinov, R. R., "Reducing the dimensionality of data with neural networks", Science 313(5786), 504-507 (2006).
15. Hinton, G. E., Srivastava, N., Krizhevsky, A., Sutskever, I. and Salakhutdinov, R. R., "Improving neural networks by preventing co-adaption of feature detectors," arXiv preprint arXiv:1207.0580, (2012).
16. Wang, T., Wu, D. J., Coates, A. and Ng, A. Y., "End-to-end text recognition with convolutional neural networks," In Proceedings of the Twenty-First International Conference on Pattern Recognition, (2012).
17. Coates, A. and Ng, A. Y., "Selecting Receptive Fields in Deep Networks," NIPS 5, 8 (2011).
18. Le, Q. V., Ranzato, M. A., Monga, R., Devin, M., Chen, K., Corrado, G. S., Dean, J. and Ng, A. Y., "Building highlevel features using large scale unsupervised learning," arXiv preprint arXiv:1112.6209v5, (2012).
19. Lee, H., Largman, Y., Pham, P. and Ng, A. Y., "Unsupervised feature learning for audio classification using convolutional deep belief networks," NIPS 9, 1096 (2009).
20. Mohamed, A. and Hinton, G. E., "Phone recognition using restricted Boltzmann Machines", Acoustics Speech and Signal Processing (ICASSP), IEEE International Conference on, 4354-4357 (2010).
21. Wulsin, D. F., Gupta, J. R., Main, R., Blanco, J. A. and Litt, B., "Modeling electroencephalography waveforms with semi-supervised deep belief nets: fast classification and anomaly measurement," Journal of Neural Engineering. 8(3), 036015 (2011).
22. Salakhutdinov, R. and Hinton, G., "An efficient learning procedure for deep Boltzmann machines," Neural computation, 24(8), 1967-2006 (2012).
23. Hinton, G. E. "Training products of experts by minimizing contrastive divergence," Neural computation, 14(8), 1711-1800 (2002).
24. Schmidt, M. (2006) minFunc [Software]. Available from http://www.cs.ubc.ca/~schmidtm.
25. Torrione, P.A., Morton, K. Jr. and Collins, L.M., "The Viterbi Algorithm as an Approach for Incorporating Spatial Information Into Air/Ground Interface Inference in GPR Data," Proc. SPIE 8017, 80171H-1 (2011).