Abstract
Real-time assessment of high-value targets is an ongoing challenge for the defense community. Many automatic target recognition (ATR) approaches exist, each with specific advantages and limitations. An ATR system is presented here that integrates machine learning, expert systems, and other advanced image understanding concepts. The ATR system employs a hierarchical strategy relying primarily on abductive polynomial networks at each level of recognition. Advanced feature extraction algorithms are used at each level for pixel characterization and target description. Polynomial networks process feature data and situational information, providing input for subsequent levels of processing. An expert system coordinates individual recognition modules.
Heuristic processing of object likelihood estimates is also discussed. Here, separate estimators determine the likelihood that an object belongs to a particular class. Heuristic knowledge to resolve ambiguities that occur when more than one class appears likely is discussed. In addition, a comparison of model-based recognition with the primary polynomial network approach is presented. Model-based recognition is a goal-driven approach that compares a representation of the unknown target to a reference library of known targets. Each approach has advantages and limitations that should be considered for a specific implementation.
This ATR approach can potentially overcome limitations of current systems such as catastrophic degradation during unanticipated operating conditions, while meeting strict processing requirements. These benefits result from implementation of robust feature extraction algorithms that do not take explicit advantage of peculiar characteristics of the sensor imagery; and the compact, real-time processing capability provided by abductive polynomial networks.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
“Active/Passive Laser Radar Field Test, Oct.–Dec. 1989, Apr.–May 1990, Fort A.P. Hill Drop Zone Area,” Center for Night Vision and Electro-Optics, Fort Belvoir, Virginia, no date.
G.J. Montgomery, P. Hess, et al., “Learning Systems for Electronic Combat Applications,” Final Report, Contract F33615-88-C-1789, WRDC/AAAF, WPAFB, Ohio, March 1989.
K.C. Drake, “Highly-Automated, Non-Parametric Statistical Learning For Autonomous Target Recognition,”Proceedings of the SPIE 20th Applied Imagery Pattern Recognition Workshop, McLean, Virginia, October 1991.
D. Buck and D. Nelson, “Applying AIMTM to the Extrapolation of Chaotic Time Series,”Proceedings of the IEEE 1992 National Aerospace and Electronics Conference, Dayton, Ohio, May 1992.
K.C. Drake, “A Hybrid Pattern Recognition Paradigm Using Moment Invariants and Polynomial Networks for Segmenting Objects in Multi-Spectral Imagery,”Ph.D. Dissertation, Department of Electrical Engineering, University of Virginia, May 1993.
M.T. Shewhart, “Applications of Machine Learning and Expert Systems to Statistical Process Control (SPC) Chart Interpretation,”Proceedings of the 2nd CLIPS Conference, Johnson Space Center, Houston, Texas, September 1991.
K.C. Drake, T.E. Petty, and G.J. Montgomery, “Aeronautical Systems Applications of Abductive Technology (ASAAT),” Final Report, ASD/XRF, Wright-Patterson AFB, Contract Number F33657-90-C-2232, February 1991.
G.J. Montgomery, K.C. Drake, and K.M. Montgomery, “Real-Time Diagnostics Using Abductive Machine Learning,”Proceedings of the 9th Annual Control Engineering Conference, Rosemont, Ill., May 22–24, 1990.
K.C. Drake, T.E. Petty, and G.J. Montgomery, “Space Surveillance and Classification Abductive Networks (SSCAN),” Final Report, SSD/XRX, Los Angeles AFB, Contract Number F04701-90-C-0042, January 1991.
AIM User's Manual, AbTech Corporation, Charlottesville, Virginia, 1994.
S.J. Farlow (editor),Self-Organizing Methods in Modeling: GMDH Type Algorithms, Marcel-Dekker, Inc., New York, 1984.
K.C. Drake and R.Y. Kim, “Aeronautical Systems Applications of Advanced Technology (ASAAT),” Interim Report, ASD/XREDA, Wright-Patterson Air Force Base, contract number F33657-92-C-2035, October 1993.
K.C. Drake and R.Y. Kim, “Pixel-Level Object Segmentation From Multi-Spectral Sensor Imagery,”Proceedings of the SPIE 22nd Applied Imagery Pattern Recognition Workshop, Washington, DC, October 1993.
R.Y. Kim and K.C. Drake, “A Hierarchical Polynomial Network Approach To Automated Target Recognition,”Proceedings of the SPIE 22nd Applied Imagery Pattern Recognition Workshop, Washington, DC, October 1993.
K.C. Drake, R.Y. Kim, T.C. Kim, and O.D. Johnson, “Comparison of Polynomial Network and Model-Based Target Recognition,”Proceedings of the SPIE Sensor Fusion and Aerospace Applications II Conference, Orlando, Florida, April 1994.
K.C. Drake and R.Y. Kim, “Pixel-Level Object Segmentation Using Moment Invariants As Characterization Features,”Proceedings of the SPIE Sensor Fusion and Aerospace Applications II Conference, Orlando, Florida, April 1994.
K.C. Drake, R.Y. Kim, and T.Y. Kim, “Decision Criterion Processing Methodology for Heuristic Assessment of Classification Models,”Proceedings of the SPIE Sensor Fusion and Aerospace Applications II Conference, Orlando, Florida, April 1994.
DeRouin, Ed, Joe R. Brown, Hal Beck, and Sue Archer, “Hyperspectral Data Fusion for Target Detection Using Neural Networks,”Proceedings of the SPIE 20th AIPR Workshop, McClean, Virginia, October 17–18, 1991.
Dennis W. Ruck, Steven K. Rogers, Matthew Kabrisky, and Mark E. Oxley, “Characterization of Multilayer Perceptrons for Target Recognition,” AFIT/ENG, Wright-Patterson Air Force Base, Ohio, 1990.
Anil, James, Tim Newman, and Michael Goulish, “Range-Intensity Histogram for Segmenting Ladar Images,”Pattern Recognition Letters, Vol. 13, pp. 51–55, January 1992.
Ming-Kuei Hu, “Pattern Recognition by Moment Invariants,”Proceedings of the IRE, Vol. 49, p. 1428, Sept. 1961.
Michael Reed Teague, “Image Analysis Via the General Theory of Moments,”Journal Optics Society America, Vol. 70, No.8, pp. 920–930, August 1980.
Robert Y. Wong, and Ernest L. Hall, “Scene Matching with Invariant Moments,”Computer Graphics and Image Processing, No. 8, pp. 16–24, August 1978.
Sidhartha Maitra, “Moment Invariants,”Proceedings of the IEEE, Vol. 67, No. 4, pp. 697–699, April 1979.
Ming-Kuei Hu, “Visual Pattern Recognition by Moment Invariants,”IRE Transactions on Information Theory, pp. 179–187, February 1962.
Yajin Li, “Reforming the Theory of Invariant Moments for Pattern Recognition,”Pattern Recognition, Vol. 25, No. 7, pp. 723–730, July 1992.
Firooz A. Sadjadi, Nasr Hatem, Hossien Amehdi, and Michael Bazakos, “Knowledge- and Model-Based Automatic Target Recognition Algorithm Adaptation,”Optical Engineering, Vol. 30, No. 2, pp. 183–188, Feb. 1991.
Dan E. Dudgeon, Verly G. Jacques, and Richard L. Delanoy, “An Experimental Target Recognition System for Laser Radar Imagery,”DAPRA Image Understanding Workshop Proceedings, Palo Alto, California, May 1989.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Drake, K.C., Kim, R.Y. Hierarchical integration of sensor data and contextual information for automatic target recognition. Appl Intell 5, 269–290 (1995). https://doi.org/10.1007/BF00872226
Issue Date:
DOI: https://doi.org/10.1007/BF00872226