Change Detection in Constellations of Buried Objects Extracted From Ground-Penetrating Radar Data

Paglieroni, David W.; Pechard, Christian T.; Beer, N. Reginald

doi:10.1109/TGRS.2014.2360097

Change Detection in Constellations of Buried Objects Extracted From Ground-Penetrating Radar Data

Journal Article · Mon Oct 13 00:00:00 EDT 2014 · IEEE Transactions on Geoscience and Remote Sensing

DOI:https://doi.org/10.1109/TGRS.2014.2360097· OSTI ID:1481092

Paglieroni, David W. ^[1]; Pechard, Christian T. ^[1]; Beer, N. Reginald ^[1]

Lawrence Livermore National Lab. (LLNL), Livermore, CA (United States)

Detection of deliberately buried objects in ground-penetrating radar (GPR) data acquired along a path is a clutter-limited problem. Detection-false alarm rate performance can be improved by replacing the detection statistic with a change statistic that incorporates information from previous path traversals. A constellation matching approach is developed for buried-object change detection in GPR data. Network topologies of buried objects detected in GPR data from previous path traversals are maintained in a constellation database. Localized groups of buried objects newly detected on the latest path traversal are matched to the constellation. Buried objects from the latest path traversal whose locations or strengths cannot be reconciled with the constellation are identified as changes. The system has one component that generates constellation databases offline and another component suitable for change detection in real time. It can tolerate paths with significant translational misalignments. The system uses the following: 1) a customized translational relaxation algorithm for point pattern matching that incorporates detection strength and a probabilistic uncertainty model for buried-object location into the objective function and 2) a change statistic that accounts for the magnitude of change relative to predicted detection strength. A constellation database can typically be generated offline from a single path traversal roughly two orders of magnitude faster than the time typically required for a vehicle to travel the extent of the path. Database sizes are typically four to five orders of magnitude smaller than the data sets of GPR signal scans or focused 3-D GPR images that they were generated from. On bumpy dirt roads buried exclusively with nonmetallic objects at various depths, detection-false alarm rate performance is shown to be significantly better for our change statistics than for our detection statistics.

Research Organization:: Lawrence Livermore National Lab. (LLNL), Livermore, CA (United States)

Sponsoring Organization:: USDOE National Nuclear Security Administration (NNSA)

DOE Contract Number:: AC52-07NA27344

OSTI ID:: 1481092

Report Number(s):: LLNL--JRNL-649638; 769517

Journal Information:: IEEE Transactions on Geoscience and Remote Sensing, Journal Name: IEEE Transactions on Geoscience and Remote Sensing Journal Issue: 5 Vol. 53; ISSN 0196-2892

Publisher:: IEEE

Country of Publication:: United States

Language:: English

References (33)

Optimizing the Area Under a Receiver Operating Characteristic Curve With Application to Landmine Detection Lee, Wen-Hsiung; Gader, Paul D.; Wilson, Joseph N. IEEE Transactions on Geoscience and Remote Sensing, Vol. 45, Issue 2, p. 389-397 https://doi.org/10.1109/TGRS.2006.887018	journal	February 2007
Point pattern matching by relaxation Ranade, Sanjay; Rosenfeld, Azriel Pattern Recognition, Vol. 12, Issue 4, p. 269-275 https://doi.org/10.1016/0031-3203(80)90067-9	journal	January 1980
The Automated Change Detection and Classification Real-time (ACDC-RT) System Gendron, Marlin L.; Lohrenz, Maura C. OCEANS 2007 - Europe https://doi.org/10.1109/OCEANSE.2007.4302387	conference	June 2007
Landmine Feature Extraction and Classification of GPR Data Based on SVM Method Zhang, Jing; Liu, Qun; Nath, Baikunth Advances in Neural Networks – ISNN 2004 https://doi.org/10.1007/978-3-540-28647-9_104	book	January 2004
Comparison of algorithms for land mine detection and discrimination using ground penetrating radar Tantum, Stacy L.; Wei, Yuchuan; Munshi, Vivek S. SPIE Proceedings https://doi.org/10.1117/12.479146	conference	August 2002
The Hungarian method for the assignment problem Kuhn, H. W. Naval Research Logistics Quarterly, Vol. 2, Issue 1-2, p. 83-97 https://doi.org/10.1002/nav.3800020109	journal	March 1955
A Large-Scale Systematic Evaluation of Algorithms Using Ground-Penetrating Radar for Landmine Detection and Discrimination Wilson, Joseph N.; Gader, Paul; Lee, Wen-Hsiung IEEE Transactions on Geoscience and Remote Sensing, Vol. 45, Issue 8, p. 2560-2572 https://doi.org/10.1109/TGRS.2007.900993	journal	August 2007
Imaging Modes for Ground Penetrating Radar and Their Relation to Detection Performance Paglieroni, David W.; Chambers, David H.; Mast, Jeffrey E. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, Vol. 8, Issue 3 https://doi.org/10.1109/JSTARS.2014.2357718	journal	March 2015
Landmine detection using fuzzy sets with GPR images Gader, P.; Keller, J. M.; Frigui, H. 1998 IEEE International Conference on Fuzzy Systems Proceedings. IEEE World Congress on Computational Intelligence (Cat. No.98CH36228) https://doi.org/10.1109/FUZZY.1998.687489	conference	August 2002
A control point matching algorithm Skea, D.; Barrodale, I.; Kuwahara, R. Pattern Recognition, Vol. 26, Issue 2 https://doi.org/10.1016/0031-3203(93)90035-U	journal	February 1993
Performance of an adaptive feature-based processor for a wideband ground penetrating radar system Torrione, P. A.; Throckmorton, C. S.; Collins, L. M. IEEE Transactions on Aerospace and Electronic Systems, Vol. 42, Issue 2, p. 644-658 https://doi.org/10.1109/TAES.2006.1642579	journal	April 2006
Training DHMMs of mine and clutter to minimize landmine detection errors No authors listed IEEE Transactions on Geoscience and Remote Sensing, Vol. 41, Issue 5 https://doi.org/10.1109/TGRS.2003.811761	journal	May 2003
Detection and Discrimination of Land Mines in Ground-Penetrating Radar Based on Edge Histogram Descriptors and a Possibilistic $K$-Nearest Neighbor Classifier Frigui, H.; Gader, P. IEEE Transactions on Fuzzy Systems, Vol. 17, Issue 1 https://doi.org/10.1109/TFUZZ.2008.2005249	journal	February 2009
Algorithms for land mine detection using the NIITEK ground penetrating radar Collins, Leslie M.; Torrione, Peter A.; Munshi, Vivek S. SPIE Proceedings https://doi.org/10.1117/12.479144	conference	August 2002
Change detection for detecting potential threats in forward-looking video and downward-looking ground-penetrating radar data Torrione, Peter; Morton, Jr., Kenneth; Ratto, Christopher SPIE Proceedings https://doi.org/10.1117/12.884122	conference	May 2011
A review of GPR for landmine detection Daniels, David J. Sensing and Imaging: An International Journal, Vol. 7, Issue 3, p. 90-123 https://doi.org/10.1007/s11220-006-0024-5	journal	September 2006
Rigid data association for shallow water surveys Coiras, E.; Baralli, F.; Evans, Benjamin IET Radar, Sonar & Navigation, Vol. 1, Issue 5 https://doi.org/10.1049/iet-rsn:20070028	journal	January 2007
Application of feature extraction methods for landmine detection using the Wichmann/Niitek ground-penetrating radar Zhu, Quan; Collins, L. M. IEEE Transactions on Geoscience and Remote Sensing, Vol. 43, Issue 1, p. 81-85 https://doi.org/10.1109/TGRS.2004.839431	journal	January 2005
Landmine Detection and Classification With Complex-Valued Hybrid Neural Network Using Scattering Parameters Dataset Yang, C. -C.; Bose, N. K. IEEE Transactions on Neural Networks, Vol. 16, Issue 3 https://doi.org/10.1109/TNN.2005.844906	journal	May 2005
Detecting landmines with ground-penetrating radar using feature-based rules, order statistics, and adaptive whitening Gader, P.; Lee, Wen-Hsiung; Wilson, J. N. IEEE Transactions on Geoscience and Remote Sensing, Vol. 42, Issue 11, p. 2522-2534 https://doi.org/10.1109/TGRS.2004.837333	journal	November 2004
Detection and classification of buried dielectric anomalies by means of the bispectrum method and neural networks Balan, A. N.; Azimi-Sadjadi, M. R. IEEE Transactions on Instrumentation and Measurement, Vol. 44, Issue 6 https://doi.org/10.1109/19.475145	journal	January 1995
A survey of point pattern matching techniques and a new approach to point pattern recognition Cox, G. S.; de Jager, G. Proceedings of the 1992 South African Symposium on Communications and Signal Processing https://doi.org/10.1109/COMSIG.1992.274276	conference	August 2022
Mine detection using scattering parameters Plett, G. L.; Doi, T.; Torrieri, D. IEEE Transactions on Neural Networks, Vol. 8, Issue 6 https://doi.org/10.1109/72.641468	journal	November 1997
Automatic Analysis of GPR Images: A Pattern-Recognition Approach Pasolli, E.; Melgani, F.; Donelli, M. IEEE Transactions on Geoscience and Remote Sensing, Vol. 47, Issue 7 https://doi.org/10.1109/TGRS.2009.2012701	journal	July 2009
Application of the LMC algorithm to anomaly detection using the Wichmann/NIITEK ground-penetrating radar Torrione, Peter A.; Collins, Leslie M.; Clodfelter, Fred AeroSense 2003 https://doi.org/10.1117/12.487241	conference	September 2003
Change detection as a tool for the maintenance of mine-free trackways using a forward-looking ground-penetrating radar Price, Gary H. AeroSense 2000, SPIE Proceedings https://doi.org/10.1117/12.396223	conference	August 2000
Landmine detection with ground penetrating radar using hidden Markov models Gader, P. D.; Mystkowski, M. IEEE Transactions on Geoscience and Remote Sensing, Vol. 39, Issue 6 https://doi.org/10.1109/36.927446	journal	June 2001
Detection and classification of buried dielectric anomalies using a separated aperture sensor and a neural network discriminator Azimi-Sadjadi, M. R.; Poole, D. E.; Sheedvash, S. IEEE Transactions on Instrumentation and Measurement, Vol. 41, Issue 1 https://doi.org/10.1109/19.126648	journal	January 1992
Landmine detection with ground penetrating radar using fuzzy k-nearest neighbors Frigui, H.; Gader, P.; Satyanarayana, K. 2004 IEEE International Conference on Fuzzy Systems (IEEE Cat. No.04CH37542) https://doi.org/10.1109/FUZZY.2004.1375447	conference	January 2005
Image registration and change detection feasibility study with ground-penetrating radar Mueller, R.; Lauziere, S.; Khanin, M. SPIE Defense, Security, and Sensing, SPIE Proceedings https://doi.org/10.1117/12.923576	conference	May 2012
New scaling algorithms for the assignment and minimum mean cycle problems Orlin, James B.; Ahuja, Ravindra K. Mathematical Programming, Vol. 54, Issue 1-3, p. 41-56 https://doi.org/10.1007/BF01586040	journal	February 1992
Matching Random Tree Models of Spatio-Temporal Patterns to Tables or Graphs Paglieroni, David W.; Nekoogar, Faranak 2007 IEEE Symposium on Computational Intelligence and Data Mining https://doi.org/10.1109/CIDM.2007.368925	conference	April 2007
Investigation of Time–Frequency Features for GPR Landmine Discrimination Savelyev, Timofey Grigorievich; van Kempen, Luc; Sahli, Hichem IEEE Transactions on Geoscience and Remote Sensing, Vol. 45, Issue 1 https://doi.org/10.1109/TGRS.2006.885077	journal	January 2007

Similar Records

Attribute and topology based change detection in a constellation of previously detected objects

Patent · Mon Jan 18 23:00:00 EST 2016 · OSTI ID:1236556

Imaging Modes for Ground Penetrating Radar and Their Relation to Detection Performance

Journal Article · Mon Oct 13 00:00:00 EDT 2014 · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · OSTI ID:1481055

Point pattern match-based change detection in a constellation of previously detected objects

Patent · Tue Jun 07 00:00:00 EDT 2016 · OSTI ID:1255963

Related Subjects

47 OTHER INSTRUMENTATION

Change Detection in Constellations of Buried Objects Extracted From Ground-Penetrating Radar Data

Citation Formats

References (33)

Similar Records

Related Subjects