volume | PIER Journals

Abstract

As for the lack of the contribution by decision fusion in pose estimation and the demand for the combination of the feature fusion and the decision fusion in SAR ATR, in this paper, with the help of pose estimation, a new multi-look SAR ATR method is proposed in order to improve the performance, which is based on two-level decision fusion of neural network and sparse representation. The first-level decision fusion is acted for the combination of the pose estimation result by neural network and sparse representation. Based on the constraint of pose, these two models are exerted for the multi-look SAR ATR, and the second-level decision fusion is used to achieve the final recognition result. Several experiments based on MSTAR are conducted, and experimental results show that our method can achieve an acceptable result.

1. O’Sullivan, J. A., et al. "SAR ATR performance using a conditionally Gaussian model," IEEE Transactions on Aerospace and Electronic Systems, Vol. 37, No. 1, 91-108, 2001.

2. Brown, M. Z., "Analysis of multiple-view Bayesian classification for SAR ATR," AeroSense 2003. International Society for Optics and Photonics, 265-274, 2003.

3. Ruta, D. and B. Gabrys, "An overview of classifier fusion methods," Computing and Information Systems, Vol. 7, No. 1, 1-10, 2000.

4. Liu, H. and S. Li, "Decision fusion of sparse representation and support vector machine for SAR image target recognition," Neurocomputing, Vol. 113, 97-104, 2013.

5. Yu, X., Y. Li, and L. C. Jiao, "SAR automatic target recognition based on classifiers fusion," 2011 International Workshop on Multi-Platform/Multi-Sensor Remote Sensing and Mapping (M2RSM), IEEE, 1-5, 2011.

6. Ranney, K. I., H. Khatri, and L. H. Nguyen, "SAR prescreener enhancement through multi-look processing," Defense and Security. International Society for Optics and Photonics, 1065-1072, 2004.

7. Albrecht, T. W. and S. C. Gustafson, "Hidden Markov models for classifying SAR target images," Defense and Security. International Society for Optics and Photonics, 302-308, 2004.

8. Albrecht, T. W., K. W. Bauer, and Jr., "Classification of sequenced SAR target images via hidden Markov models with decision fusion," Defense and Security. International Society for Optics and Photonics, 306-313, 2005.

9. Zhang, H., et al. "Joint sparse representation based automatic target recognition in SAR images," SPIE Defense, Security, and Sensing. International Society for Optics and Photonics, 805112-805112, 2011.

10. Morgan, D. R. and T. D. Ross, "A Bayesian framework for ATR decision-level fusion experiments," Defense and Security Symposium. International Society for Optics and Photonics, 65710C-65710C, 2007.

11. Ettinger, G. J. and W. C. Snyder, "Model-based fusion of multi-look SAR for ATR," AeroSense 2002. International Society for Optics and Photonics, 277-289, 2002.

12. Huan, R. and Y. Pan, "Decision fusion strategies for SAR image target recognition," IET Radar, Sonar & Navigation, Vol. 5, No. 7, 747-755, 2011.

13. Huan, R.-H. and Y. Pan, "Target recognition for multi-aspect SAR images with fusion strategies," Progress In Electromagnetics Research, Vol. 134, 267-288, 2013.

14. Zhao, Q., et al. "Synthetic aperture radar automatic target recognition with three strategies of learning and representation," Optical Engineering, Vol. 39, No. 5, 1230-1244, 2000.

15. Kaplan, L. M. and R. Murenzi, "Pose estimation of SAR imagery using the two dimensional continuous wavelet transform," Pattern Recognition Letters, Vol. 24, No. 14, 2269-2280, 2003.

16. Voicu, L. I., R. Patton, and H. R. Myler, "Multicriterion vehicle pose estimation for SAR ATR," AeroSense’99. International Society for Optics and Photonics, 497-506, 1999.

17. Sun, Y., et al. "Adaptive boosting for SAR automatic target recognition," IEEE Transactions on Aerospace and Electronic Systems, Vol. 43, No. 1, 112-125, 2007.

18. Principe, J. C., D. Xu, J. W. Fisher, and III, "Pose estimation in SAR using an information theoretic criterion," Aerospace/Defense Sensing and Controls. International Society for Optics and Photonics, 218-229, 1998.

19. Roberts, D. J., "Applications of artificial neural networks to synthetic aperture radar for feature extraction in noisy environments,", Diss. California Polytechnic State University San Luis Obispo, California, 2013.

20. Xing, X., et al. "SAR vehicle classification based on sparse representation with aspect angle constraint," Eighth International Symposium on Multispectral Image Processing and Pattern Recognition. International Society for Optics and Photonics, 89180K-89180K, 2013.

21. Ng, A., "Sparse autoencoder," CS294A Lecture notes, Vol. 72, 2011.

22. Rennie, J. D. M., "Pose estimation in SAR using an information theoretic criterion,", Diss. Massachusetts Institute of Technology, 2001.

23. Azouzi, R. and M. Guillot, "On-line prediction of surface finish and dimensional deviation in turning using neural network based sensor fusion," International Journal of Machine Tools and Manufacture, Vol. 37, No. 9, 1201-1217, 1997.

24. Principe, J., Q. Zhao, and D. Xu, "A novel ATR classifier exploiting pose information," Proceedings of Image Understanding Workshop, 833-836, 1998.

25. Zhao, Q. and J. C. Principe, "Support vector machines for SAR automatic target recognition," IEEE Transactions on Aerospace and Electronic Systems, Vol. 37, No. 2, 643-654, 2001.

26. Huan, R. and R. Yang, "SAR target recognition using multiple views decision fusion," Journal of Remote Sensing, Vol. 14, No. 2, 252-256, 2010.

Dr. Xuan Li

Dr. Chun-Sheng Li

Dr. Pengbo Wang