Algorithm fusion for automated sea mine detection and classification

The fusion of multiple detection/classification algorithms is proving a very powerful approach for dramatically reducing false alarm rate, while still maintaining a high probability of detection and classification. This has been demonstrated in several Navy sea tests. The high-resolution sonar is one of the principal sensors used by the Navy to detect and classify sea mines in mine hunting operations. For such sonar systems, substantial effort has been devoted to the development of automated detection and classification (D/C) algorithms. These have been spurred by several factors including (1) aids for operators to reduce work overload, (2) more optimal use of all available data, and (3) the introduction of unmanned mine hunting systems. The environments where sea mines are typically laid (harbor areas, shipping lanes, and the littorals) give rise to many false alarms caused by natural, biologic, and man-made clutter. The objective of the automated D/C algorithms is to eliminate most of these false alarms while still maintaining a very high probability of mine detection and classification (PdPc). The benefits of fusing the outputs of multiple D/C algorithms have been studied. We refer to this as algorithm fusion. The results have been remarkable, including reliable robustness to new environments. Even though our experience has been gained in the area of sea mine detection and classification, the principles described herein are general and can be applied to fusion of any D/C problem (e.g., automated medical diagnosis or automatic target recognition for ballistic missile defense).

[1]  Tom Aridgides,et al.  Adaptive order-statistic filters for sea mine classification , 1998, Defense, Security, and Sensing.

[2]  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.

[3]  David H. Kil,et al.  Bandwidth reduction of high-frequency sonar imagery in shallow water using content-adaptive hybrid image coding , 1998, Defense, Security, and Sensing.

[4]  Henrik Storm,et al.  Target detection with local discriminant bases and wavelets , 1999, Defense, Security, and Sensing.

[5]  Weiming Guo,et al.  Pseudo multisensor fusion schemes for mine detection in side-scan sonar images , 1999, Defense, Security, and Sensing.

[6]  Gerald J. Dobeck,et al.  Adaptive clutter suppression and fusion processing string for sea mine detection and classification in sonar imagery , 1998, Defense, Security, and Sensing.

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

[8]  Charles M. Ciany,et al.  Data fusion of computer-aided detection/computer-aided classification algorithms for classification of mines in very shallow water environments , 2000, Defense, Security, and Sensing.

[9]  Susan R. Nelson,et al.  Fractal-based image processing for mine detection , 1995, Defense, Security, and Sensing.

[10]  Lisa H. Tubridy.  Environmental optimization in mine countermeasures , 1999, Defense, Security, and Sensing.

[11]  Weiming Guo,et al.  Mine detection using variational methods for image enhancement and feature extraction , 1998, Defense, Security, and Sensing.

[12]  Gerald J. Dobeck,et al.  Automated detection and classification of sea mines in sonar imagery , 1997, Defense, Security, and Sensing.

[13]  Anthony Sacramone,et al.  Real-time detection of undersea mines: a complete screening and acoustic fusion processing system , 1999, Defense, Security, and Sensing.

[14]  Martin G. Bello.  Hierarchical multilayer perceptron network-based fusion algorithms for detection/classification of mines using multiple acoustic images and magnetic data , 1996, Defense, Security, and Sensing.

[15]  Susan R. Nelson,et al.  Automated recognition of acoustic-image clutter , 1996, Defense, Security, and Sensing.

[16]  Christopher F. Barnes,et al.  Detection of mine and minelike objects in forward-looking sonar data with direct sum successive approximation templates , 1999, Defense, Security, and Sensing.

[17]  Quyen Q. Huynh,et al.  Image enhancement for pattern recognition , 1998, Defense, Security, and Sensing.

[18]  Gerald J. Dobeck.  On the power of algorithm fusion , 2001, SPIE Defense + Commercial Sensing.

[19]  Gerald J. Dobeck,et al.  Adaptive clutter suppression, sea mine detection/classification, and fusion processing string for sonar imagery , 1999, Defense, Security, and Sensing.

[20]  Martin G. Bello.  Markov random-field-based anomaly screening algorithm , 1995, Defense, Security, and Sensing.

[21]  Gerald J. Dobeck.  Fusing sonar images for mine detection and classification , 1999, Defense, Security, and Sensing.

[22]  Weiming Guo,et al.  Multiresolution neural networks for mine detection in side scan sonar images , 1998, Defense, Security, and Sensing.

[23]  Tom Aridgides,et al.  Adaptive nonstationary filtering procedure for sea mine classification , 1999, Defense, Security, and Sensing.

[24]  Gerald J. Dobeck,et al.  Adaptive-filter/feature-orthogonalization processing string for optimal LLRT mine classfication in side-scan sonar imagery , 1996, Defense, Security, and Sensing.

[25]  Bjarne Stage,et al.  Sonar image enhancements for improved detection of sea mines , 1999, Defense, Security, and Sensing.

[26]  Gerald J. Dobeck,et al.  Adaptive filter for mine detection and classification in side-scan sonar imagery , 1995, Defense, Security, and Sensing.

[27]  Martin G. Bello.  Acoustic/magnetic fusion system architecture variants and their classification performance , 1997, Defense, Security, and Sensing.

[28]  Weiming Guo,et al.  Mine detection using model-trained multiresolution neural networks and variational methods , 1999, Defense, Security, and Sensing.

[29]  Vinod Chandran,et al.  Detection of sea mines in sonar imagery using higher-order spectral features , 1999, Defense, Security, and Sensing.

[30]  Ling Guan,et al.  Enhancing mine signatures in sonar images using nested neural networks , 1999, Defense, Security, and Sensing.

[31]  Charles M. Ciany,et al.  Performance of fusion algorithms for computer-aided detection and classification of mines in very shallow water obtained from testing in navy Fleet Battle Exercise-Hotel 2000 , 2001, SPIE Defense + Commercial Sensing.

[32]  D. H. Kil,et al.  Integrated approach to bandwidth reduction and mine detection in shallow water with reduced-dimension image compression and automatic target recognition algorithms , 1997, Defense, Security, and Sensing.

[33]  Sinan Batman,et al.  Robust morphological detection of sea mines in side-scan sonar images , 2001, SPIE Defense + Commercial Sensing.

[34]  Tien-Hsin Chao,et al.  Aided target recognition processing of MUDSS sonar data , 1998, Defense, Security, and Sensing.

[35]  S. G. Johnson,et al.  The application of automated recognition techniques to side-scan sonar imagery , 1994 .

[36]  Gerald J. Dobeck.  Algorithm fusion for the detection and classification of sea mines in the very shallow water region using side-scan sonar imagery , 2000, Defense, Security, and Sensing.

[37]  Gerald J. Dobeck,et al.  Sea mine detection and classification using side-looking sonar , 1995, Defense, Security, and Sensing.