Abstract
We present an approach to automatic target recognition (ATR) from synthetic aperture radar (SAR) imagery which combines advantages of both model-based and template-based approaches. Prior observations are used to estimate the statistical properties of reflectance over regions in the training scene. These target-centered statistical models can then be used to estimate the statistical properties of sensor output for arbitrary pose. Two-sided hypothesis tests which are maximally powerful at the most likely alternative are developed in a information-theoretic framework to address target model segmentation and confuser rejection. Segmentation of target from clutter is performed in the target-centered coordinate system using all prior observations to produce a consistent segmentation over all poses. We present performance and computation complexity results as a function of segmentation threshold, confuser-rejection threshold, and operating conditions for publicly available SAR data.
Similar content being viewed by others
Explore related subjects
Discover the latest articles, news and stories from top researchers in related subjects.References
H.-C. Chiang, R.L. Moses, and L.C. Potter, “Model-Based Classification of Radar Images,” IEEE Transactions on Information Theory, vol. 46, no. 5, Aug. 2000, pp. 1842–1854.
M.D. DeVore, A.D. Lanterman, and J.A. O'sullivan, “ATR Performance of a Rician Model for SAR Images,” in F.A. Sadjadi (Ed.), Automatic Target Recognition X, Proc. of SPIE, vol. 4050, 2000.
M.D. DeVore, J.A. O'sullivan, S. Anand, and N.A. Schmid, “Probabilistic Approach to Model Extraction from Training Data,” in E.G. Zelnio (Ed.), Algorithms for Synthetic Aperture Radar Imagery VIII, Proc. Of SPIE, 2001.
M.D. DeVore, N.A. Schmid, and J.A. O'sullivan, “Analytical and Experimental Performance-Complexity Tradeoffs in ATR,” in Proceedings of the Thirty-Fourth Asilomar Conference on Signals, Systems, and Computers, Oct. 2000.
U. Grenander, M.I. Miller, and A. Srivastava, “Hilbert-Schmidt Lower Bounds for Estimators on Matrix Lie Groups for ATR,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 20, no. 8, Aug. 1998, pp. 790–802.
W.W. Irving, L.M. Novak, and A.S. Willsky, “Multiresolution Approach to Discriminating Targets from Clutter in SAR Imagery,” IEEE Transactions on Aerospace and Electronic Systems, vol. 33, no. 4, Oct. 1997, pp. 1157–1169.
S.P. Jacobs, Automatic Target Recognition Using High Resolution Radar Range-Profiles. PhD thesis, Washington University, St. Louis, Missouri, May 1997.
E.R. Keydel and S.W. Lee, “Signature Prediction for Model-Based Automatic Target Recognition,” in E.G. Zelnio and R.J. Douglass (Eds.), Algorithms for Synthetic Aperture Radar Imagery III, Proc. of SPIE, vol. 2757, 1996, pp. 306–317.
E.R. Keydel, S.W. Lee, and J.T. Moore, “MSTAR Extended Operating Conditions: A Tutorial,” in E.G. Zelnio and R.J. Douglass (Eds.), Algorithms for Synthetic Aperture Radar Imagery III, Proc. of SPIE, vol. 2757, 1996, pp. 228–242.
J.A. O'sullivan, R.E. Blahut, and D.L. Snyder, “Information-Theoretic Image Formation,” IEEE Transactions on Information Theory, vol. 44, no. 6, Oct. 1998, pp. 2094–2123.
J.A. O'sullivan, M.D. DeVore, V. Kedia, and M.I. Miller, “Automatic Target Recognition Performance for SAR Imagery Using a Conditionally Gaussian Model,” IEEE Transactions on Aerospace and Electronic Systems, vol. 37, no. 1, Jan. 2001, pp. 91–108.
G.J. Owirka, S.M. Verbout, and L.M. Novak, “Template-Based SAR ATR Performance Using Different Image Enhancement Techniques,” in Algorithms for Synthetic Aperture Radar Imagery VI, Proc. of SPIE, vol. 3721, 1999, pp. 302–319.
J.A. Richards, J.W. Fisher III, and A.S. Willsky, “An Expectation-Maximization Approach to Target Model Generation from Multiple SAR Images,” in E.G. Zelnio (Ed.), Algorithms for Synthetic Aperture Radar Imagery VII, Proc. of SPIE, vol. 4053, 2000, pp. 652–664.
T.D. Ross, S.W. Worrell, J.C. Mossing, and M.L. Bryant, “Standard SAR ATR Evaluation Experiments Using the MSTAR Public Release Data Set,” in E.G. Zelnio (Ed.), Algorithms for Synthetic Aperture Radar Imagery V, Proc. of SPIE, vol. 3370, 1998, pp. 566–573.
G.G. Roussas, A Course in Mathematical Statistics, Academic Press, 2nd ed., 1997.
N.A. Schmid and J.A. O'sullivan, “Thresholding Method for Reduction of Dimensionality,” IEEE Transactions on Information Theory, vol. 47, no. 7, Nov. 2001, pp. 2903–2920.
S.M. Verbout, W.W. Irving, and A.S. Hanes, “Improving a Template-Based Classifier in a SAR Automatic Target Recognition System by Using 3-D Target Information,” Lincoln Laboratory Journal, vol. 6, no. 1, Spring 1993, pp. 53–76.
R.A. Weisenseel, W.C. Karl, D.A. Castañon, G.J. Power, and P. Douville, “Markov Random Field Segmentation Methods for SAR Target Chips,” in E.G. Zelnio (Ed.), Algorithms for Synthetic Aperture Radar Imagery VI, Proc. of SPIE, vol. 3721, 1999, pp. 462–473.
J. Wissinger, R.B. Washburn, N.S. Friedland, A. Nowicki, D.R. Morgan, C. Chong, and R. Fung, “Search Algorithms for Model Based SAR ATR,” in E.G. Zelnio and R.J. Douglass (Eds.), Algorithms for Synthetic Aperture Radar Imagery III, Proc. of SPIE, vol. 2757, 1996, pp. 279–293.
Rights and permissions
About this article
Cite this article
Devore, M.D., O'Sullivan, J.A. Target-Centered Models and Information-Theoretic Segmentation for Automatic Target Recognition. Multidimensional Systems and Signal Processing 14, 139–159 (2003). https://doi.org/10.1023/A:1022277209974
Issue Date:
DOI: https://doi.org/10.1023/A:1022277209974