Symbolic Analysis of Sonar Data for Underwater Target Detection

This paper presents a symbolic pattern analysis method for robust feature extraction from sidescan sonar images that are generated from autonomous underwater vehicles (AUVs). The proposed data-driven algorithm, built upon the concepts of symbolic dynamics and automata theory, is used for detection of mines and mine-like objects in the undersea environment. This real-time algorithm is based on symbolization of the data space via coarse graining, i.e., partitioning of the two-dimensional sonar images. The statistical information, in terms of stochastic matrices that serve as features, is extracted from the symbolized images by construction of probabilistic finite state automata. A binary classifier is designed for discrimination of detected objects into mine-like and nonmine-like categories. The pattern analysis algorithm has been validated on sonar images generated in the exploration phase of a mine hunting operation; these data have been provided by the Naval Surface Warfare Center. The algorithm is formulated for real-time execution on limited-memory commercial-of-the-shelf platforms and is capable of detecting objects on the seabed-bottom.

[1]  Dong-Jo Park,et al.  Novel precision target detection with adaptive thresholding for dynamic image segmentation , 2001, Machine Vision and Applications.

[2]  Shalabh Gupta,et al.  Real-time fatigue life estimation in mechanical structures , 2007 .

[3]  R.E. Hansen,et al.  Signal processing for AUV based interferometric synthetic aperture sonar , 2003, Oceans 2003. Celebrating the Past ... Teaming Toward the Future (IEEE Cat. No.03CH37492).

[4]  Shalabh Gupta,et al.  Symbolic time series analysis of ultrasonic data for early detection of fatigue damage , 2007 .

[5]  H. Vincent Poor,et al.  An Introduction to Signal Detection and Estimation , 1994, Springer Texts in Electrical Engineering.

[6]  H. Vincent Poor,et al.  An introduction to signal detection and estimation (2nd ed.) , 1994 .

[7]  Jocelyn Chanussot,et al.  Higher-Order Statistics for the Detection of Small Objects in a Noisy Background Application on Sonar Imaging , 2007, EURASIP J. Adv. Signal Process..

[8]  Jeffrey D. Ullman,et al.  Introduction to automata theory, languages, and computation, 2nd edition , 2001, SIGA.

[9]  Jeffrey D. Ullman,et al.  Introduction to Automata Theory, Languages and Computation , 1979 .

[10]  Douglas Lind,et al.  An Introduction to Symbolic Dynamics and Coding , 1995 .

[11]  Asok Ray,et al.  Symbolic dynamic analysis of complex systems for anomaly detection , 2004, Signal Process..

[12]  M. Amate,et al.  Mean–Standard Deviation Representation of Sonar Images for Echo Detection: Application to SAS Images , 2007, IEEE Journal of Oceanic Engineering.

[13]  Patrick Pérez,et al.  Three-Class Markovian Segmentation of High-Resolution Sonar Images , 1999, Comput. Vis. Image Underst..

[14]  Gerald J. Dobeck.  Algorithm fusion for automated sea mine detection and classification , 2001, MTS/IEEE Oceans 2001. An Ocean Odyssey. Conference Proceedings (IEEE Cat. No.01CH37295).

[15]  Asok Ray,et al.  Review and comparative evaluation of symbolic dynamic filtering for detection of anomaly patterns , 2009, 2008 American Control Conference.

[16]  J.T. Cobb,et al.  Sonar processing for short range, very-high resolution autonomous underwater vehicle sensors , 2005, Proceedings of OCEANS 2005 MTS/IEEE.

[17]  Peter X. Liu,et al.  Sonar image segmentation based on GMRF and level-set models , 2010 .

[18]  G. Ginolhac,et al.  Morphological and statistical approaches to improve detection in the presence of reverberation , 2005, IEEE Journal of Oceanic Engineering.

[19]  Brian R. Calder,et al.  A Bayesian approach to object detection in sidescan sonar , 1997 .

[20]  Matthew B Kennel,et al.  Statistically relaxing to generating partitions for observed time-series data. , 2005, Physical review. E, Statistical, nonlinear, and soft matter physics.

[21]  Gerald J. Dobeck,et al.  Adaptive three-dimensional range-crossrange-frequency filter processing string for sea mine classification in side scan sonar imagery , 1997, Defense, Security, and Sensing.

[22]  Brian A. Baertlein,et al.  Feature-Level and Decision-Level Fusion of Noncoincidently Sampled Sensors for Land Mine Detection , 2001, IEEE Trans. Pattern Anal. Mach. Intell..

[23]  Jocelyn Chanussot,et al.  Fusion of Local Statistical Parameters for Buried Underwater Mine Detection in Sonar Imaging , 2008, EURASIP J. Adv. Signal Process..

[24]  Asok Ray,et al.  Statistical Mechanics of Complex Systems for Pattern Identification , 2009 .

[25]  G. Grimmett.  A THEOREM ABOUT RANDOM FIELDS , 1973 .

[26]  Asok Ray,et al.  Automated behaviour recognition in mobile robots using symbolic dynamic filtering , 2008 .

[27]  Gerald J. Dobeck,et al.  Application of fusion algorithms for computer-aided detection and classification of bottom mines to shallow water test data from the battle space preparation autonomous underwater vehicle (BPAUV) , 2003, SPIE Defense + Commercial Sensing.

[28]  Robert J. Urick,et al.  Principles of underwater sound , 1975 .

[29]  John E. Dennis,et al.  Normal-Boundary Intersection: A New Method for Generating the Pareto Surface in Nonlinear Multicriteria Optimization Problems , 1998, SIAM J. Optim..

[30]  Lawrence Carin,et al.  Infrared-Image Classification Using Hidden Markov Trees , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[31]  Yvan Petillot,et al.  Automated approach to classification of mine-like objects in sidescan sonar using highlight and shadow information , 2004 .

[32]  Trevor Darrell,et al.  Hidden Conditional Random Fields , 2007, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[33]  Sergio A. Velastin,et al.  How close are we to solving the problem of automated visual surveillance? , 2008, Machine Vision and Applications.

[34]  G.J. Dobeck.  A probabilistic model for score-based algorithm fusion , 2005, Proceedings of OCEANS 2005 MTS/IEEE.

[35]  Yu Hen Hu,et al.  Detection, classification, and tracking of targets , 2002, IEEE Signal Process. Mag..

[36]  David G. Stork,et al.  Pattern Classification (2nd ed.) , 1999 .

[37]  Asok Ray,et al.  Symbolic time series analysis via wavelet-based partitioning , 2006, Signal Process..

[38]  G.J. Dobeck,et al.  Active learning for detection of mine-like objects in side-scan sonar imagery , 2005, IEEE Journal of Oceanic Engineering.

[39]  Gerald J. Dobeck,et al.  Fusion of sea mine detection and classification processing strings for sonar imagery , 2000, Defense, Security, and Sensing.