Your browser does not support JavaScript!
http://iet.metastore.ingenta.com
1887

access icon free Automatic target recognition of synthetic aperture radar (SAR) images based on optimal selection of Zernike moments features

© The Institution of Engineering and Technology
Received 29/01/2013, Accepted 29/07/2013, Revised 06/06/2013, Published 25/09/2013

In the present study, a new algorithm for automatic target detection (ATR) in synthetic aperture radar (SAR) images has been proposed. First, moving and stationary target acquisition and recognition image chips have been segmented and then passed to a number of preprocessing stages such as histogram equalisation, position and size normalisation. Second, the feature extraction based on Zernike moments (ZMs) having linear transformation invariance properties and robustness in the presence of the noise has been introduced for the first time. Third, a genetic algorithm-based feature selection and a support vector machine classifier have been presented to select the optimal feature subset of ZMs for decreasing the computational complexity. Experimental results demonstrate the efficiency of the proposed approach in target recognition of SAR imagery. The authors obtained results show that just a small amount of ZMs features is sufficient to achieve the recognition rates that rival other established methods, and so ZMs features can be regarded as a powerful discriminatory feature for automatic target recognition applications relevant to SAR imagery. Furthermore, it can be observed that the classifier performs fairly well until the signal-to-noise ratio falls beneath 5 dB for noisy images.

Inspec keywords: radar computing; image recognition; radar imaging; synthetic aperture radar; support vector machines; feature extraction; genetic algorithms; computational complexity

Other keywords: SAR images; synthetic aperture radar images; support vector machine classifler; size normalisation; Zernike moments features; histogram equalisation; automatic target detection; genetic algorithm-based feature selection; moving target acquisition; noisy images; ATR; stationary target acquisition; optimal selection; automatic target recognition applications; SVM; invariance robustness; ZM features; computational complexity; feature extraction; position normalisation; preprocessing stages; optimal feature subset; signal-to-noise ratio; linear transformation invariance properties; recognition image chips

Subjects: Image recognition; Optimisation techniques; Electrical engineering computing; Computational complexity; Radar equipment, systems and applications; Optimisation techniques; Knowledge engineering techniques

References

    1. 1)
      • 42. Osuna, E., Freund, R., Girosi, F.: ‘Support vector machine: training and applications’. Technical Report, Massachusetts Institute of Technology, 1997.
    2. 2)
    3. 3)
    4. 4)
    5. 5)
    6. 6)
    7. 7)
    8. 8)
    9. 9)
    10. 10)
    11. 11)
    12. 12)
    13. 13)
    14. 14)
    15. 15)
    16. 16)
    17. 17)
    18. 18)
    19. 19)
    20. 20)
    21. 21)
      • 3. Yuan, C., Casasent, D.: ‘A new SVM for distorted SAR object classification’, Proc. SPIE, 2005, 5816, pp. 1–10 (doi: 10.1117/12.606025).
    22. 22)
      • 1. Bhanu, B., Dudgeon, D.E., Zelnio, E.G., et al: ‘Guest editorial introduction to the special issue on automatic target detection and recognition’, IEEE Trans. Image Process., 1997, 6, (1), pp. 1–6 (doi: 10.1109/TIP.1997.552076).
    23. 23)
      • 25. Saghri, J., Guilas, C.: ‘Hausdorff probabilistic feature analysis in SAR image recognition’. Proc. SPIE’, Applications of Digital Image Processing XXVIII 5909, 2004, pp. 21–32.
    24. 24)
      • 8. Chen, Y., Blasch, E., Qian, T., Blasch, E.: ‘Experimental feature-based SAR ATR performance evaluation under different operational conditions’. Proc. 17th SPIE – Signal Processing, Sensor Fusion, and Target Recognition, May 2008, vol. 6968, pp. 69680F-1–69680F-12.
    25. 25)
      • 16. Jones, G.III, Bhanu, B.: ‘Quasi-invariants for recognition of articulated and non-standard objects in SAR images’. IEEE Workshop on Computer Vision Beyond the Visible Spectrum: Methods and Applications, 1999.
    26. 26)
      • 30. Wang, W., Mottershead, J.E., Mares, C.: ‘Mode-shape recognition and finite element model updating using the Zernike moment descriptor’, Mech. Syst. Signal Process., 2009, 23, pp. 2088–2112 (doi: 10.1016/j.ymssp.2009.03.015).
    27. 27)
      • 38. Bhanu, B., Lin, Y.: ‘Genetic algorithm based feature selection for target detection in SAR images’, Image Vis. Comput., 2003, 21, (7), pp. 591–608 (doi: 10.1016/S0262-8856(03)00057-X).
    28. 28)
      • 15. Zhao, Q., Principe, J.S., Brennan, V., Xu, D., Wang, Z.: ‘Synthetic aperture radar automatic target recognition with three strategies of learning and representation’, Opt. Eng., 2000, 39, (5), pp. 1230–1244 (doi: 10.1117/1.602495).
    29. 29)
      • 35. Dash, M., Liu, H.: ‘Feature selection for classification’, Intell. Data Anal., 1997, 1, (3), pp. 131–156 (doi: 10.1016/S1088-467X(97)00008-5).
    30. 30)
      • 42. Osuna, E., Freund, R., Girosi, F.: ‘Support vector machine: training and applications’. Technical Report, Massachusetts Institute of Technology, 1997.
    31. 31)
      • 26. Krawiec, K., Bhanu, B.: ‘Visual learning by co-evolutionary feature synthesis’, IEEE Trans. Syst. Man Cybern. B, Cybern., 2005, 35, (3), pp. 409–425 (doi: 10.1109/TSMCB.2005.846644).
    32. 32)
      • 31. Li, Sh., Lee, M.Ch., Pun, Ch.M.: ‘Complex Zernike moments features for shape- based image retrieval’, IEEE Trans. Syst. Man Cybern. A,: Syst. Hum., 2009, 39, pp. 227–237 (doi: 10.1109/TSMCA.2008.2007988).
    33. 33)
      • 14. Wissinger, J., Washburn, R.B., Friedland, N.S., et al: ‘Search algorithms for model based SAR ATR’, in: Zelnio, E.G., Douglass, R.J., (Ed.), Algorithms for Synthetic Aperture Radar Imagery III (Proc. SPIE), 1996, vol. 2757, pp. 279–293.
    34. 34)
      • 37. Lin, Y., Bhanu, B.: ‘Evolutionary feature synthesis for object recognition’, IEEE Trans. Syst. Man Cybern. C, Appl. Rev., 2005, 35, (2), pp. 156–171 (doi: 10.1109/TSMCC.2004.841912).
    35. 35)
      • 17. Patnaik, R., Casasent, D.: ‘SAR classification and confuser and clutter rejection tests on MSTAR ten-class data using MINACE filters’, Opt. Pattern Recognit., 2007, 6574, pp. 657402.1–657402.15.
    36. 36)
      • 28. Gao, G.: ‘An improved scheme for target discrimination in high-resolution SAR images’, IEEE Trans. Geosci. Remote Sens., 2011, 49, (1), pp. 277–294 (doi: 10.1109/TGRS.2010.2052623).
    37. 37)
      • 21. Anagnostopoulos, G.C.: ‘SVM-based target recognition from synthetic aperture radar images using target region outline descriptors’, Nonlinear Anal., 2009, 71, (2), pp. 2934–2939 (doi: 10.1016/j.na.2009.07.030).
    38. 38)
      • 12. Owirka, G.J., Novak, L.M.: ‘A new SAR ATR algorithm suite’. Algorithms for Synthetic Aperture Radar Imagery (Proc. SPIE), 1994, vol. 2230, pp. 336–343.
    39. 39)
      • 19. Principe, J.C., Xu, D., Fisher, J.W.III: ‘Pose estimation in SAR using an information theoretic criterion’, Proc. SPIE, 1998, 3370, pp. 218–229 (doi: 10.1117/12.321826).
    40. 40)
      • 39. Gonzalez, R., Woods, R.: ‘Digital image processing’ (Addison-Wesley Longman Publishing Co., Inc., Boston, MA, 1992, 2nd edn.).
    41. 41)
      • 20. Sun, Y., Liu, Z-P., Todorovic, S., Li, J.: ‘Adaptive boosting for SAR automatic target recognition’, IEEE Trans. Aerosp. Electron. Syst., 2007, 43, (1), pp. 112–125 (doi: 10.1109/TAES.2007.357120).
    42. 42)
      • 6. DeVore, M.D., O'Sullivan, J.A.: ‘A performance-complexity study of several approaches to automatic target recognition from synthetic aperture radar images’, IEEE Trans. Aerosp. Electron. Syst., 2002, 38, (2), pp. 632–648 (doi: 10.1109/TAES.2002.1008992).
    43. 43)
      • 36. Guyon, I., Elisseeff, A.: ‘An introduction to variable and feature selection’, J. Mach. Learn. Res., 2003, 3, pp. 1157–1182.
    44. 44)
      • 41. Li, S., Lee, M.-C., Pun, C.-M.: ‘Complex Zernike moments features for shape-based image retrieval’, IEEE Trans. Syst. Man Cybern. A, Syst. Hum., 2009, 39, (1), pp. 227–237 (doi: 10.1109/TSMCA.2008.2007988).
    45. 45)
      • 7. Novak, L.M., Halversen, S.D., Owirka, G., Hiett, M.: ‘Effects of polarization and resolution on SAR ATR’, IEEE Trans. Aerosp. Electron. Syst., 1997, 33, (1), pp. 102–116 (doi: 10.1109/7.570713).
    46. 46)
      • 11. Novak, L.M., Owirka, G.J., Brower, W.S., Weaver, A.L.: ‘The automatic target recognition system in SAIP’, Linc. Lab. J., 1997, 10, (2), pp. 187–201.
    47. 47)
      • 23. Pink, T., Ramanathan, U.: ‘Intelligent selection of useful features for optimal feature-based classification’. IEEE Int. Geoscience and Remote Sensing Symp., 2000, vol. 7, pp. 3012–3014.
    48. 48)
      • 24. Bhanu, B., Jones, G.III: ‘Exploiting azimuthal variance of scatterers for multiple look SAR recognition’. Proc. SPIE Algorithms for Synthetic Aperture Radar Imagery IX 4727, 2002, pp. 290–298.
    49. 49)
      • 4. Schumacher, R., Rosenbach, K.: ‘ATR of battlefield targets by SAR classification results using the public MSTAR dataset compared with a dataset by QinetiQ UK’. RTO SET Symp. Target Identification and Recognition Using RF Systems, 2004.
    50. 50)
      • 2. Zhao, Q., Principle, J.S.: ‘Support vector machines for SAR automatic target recognition’, IEEE Trans. Aerosp. Electron. Syst., 2001, 37, (2), pp. 643–654 (doi: 10.1109/7.937475).
    51. 51)
      • 9. Mossing, J.C., Ross, T.D.: ‘An evaluation of SAR ATR algorithm performance sensitivity to MSTAR extended operating conditions’, in: Zelnio, E.G. (Ed.), Algorithms for synthetic aperture radar imagery V (Proc. SPIE), 1998, vol. 3370, pp. 554–565.
    52. 52)
      • 27. Yang, Y., Qiu, Y., Lu, C.: ‘Automatic target classification experiments on the MSTAR SAR images’ (SNPD/SAWN, 2005) pp. 2–7.
    53. 53)
      • 32. Li, X., Song, A.: ‘A new edge detection method using Gaussian–Zernike moment operator’. Proc. IEEE, Second Int. Asia Conf. Informatics in Control, Automation and Robotics, 2010, pp. 276–279.
    54. 54)
      • 33. Haddadnia, J., Ahmadi, M., Faez, K.: ‘An efficient feature extraction method with pseudo-Zernike moment in RBF neural network-based human face recogni- tion system’, J. Appl. Signal Process., 2003, 9, pp. 890–901 (doi: 10.1155/S1110865703305128).
    55. 55)
      • 34. Tahmasbi, A., Saki, F., Shokouhi, S.B.: ‘Classification of benign and malignant masses based on Zernike moments’, Comput. Biol. Med., 2011, 41, pp. 726–735 (doi: 10.1016/j.compbiomed.2011.06.009).
    56. 56)
      • 13. Worrell, S.W., Parker, S., Bryant, M.L.: ‘Class separability assessments and MSE algorithm robustness’, in Zelnio, E.G. (Ed.), Algorithms for synthetic aperture radar imagery IV (Proc. SPIE), 1997, vol. 3070, pp. 294–304.
    57. 57)
      • 10. Ross, T.D., Bradley, J.J., Hudson, L.J., O'Connor, M.P.: ‘SAR ATR–so what's the problem? An MSTAR perspective’, in Zelnio, E.G. (Ed.), Algorithms for Synthetic Aperture Radar Imagery VI (Proc. SPIE), 1999, vol. 3721, pp. 566–573.
    58. 58)
      • 40. Sun, Y., Liu, Z., Todorovic, S., Li, J.: ‘Adaptive boosting for SAR automatic target recognition’, IEEE Trans. Aerosp. Electron. Syst., 2007, 43, (1), pp. 112–125 (doi: 10.1109/TAES.2007.357120).
    59. 59)
      • 22. Pham, Q.H., Brosnan, T.M., Smith, M.J.T., Mersereau, R.M.: ‘An efficient end-to-end feature based system for SAR ATR’. SPIE 3370, Algorithms for Synthetic Aperture Radar Imagery V, September, 1998, vol. 519.
    60. 60)
      • 18. Patnaik, R., Casasent, D.: ‘MINACE filter classification algorithms for ATR using MSTAR data’. Proc. SPIE, Automatic Target Recognition XV 5807, 2005, pp. 101–111.
    61. 61)
      • 5. Moving and Stationary Target Acquisition and Recognition (MSTAR) Public Dataset. Available at https://www.sdms.afrl.af.mil/datasets/mstar/index.php.
    62. 62)
      • 29. Hwang, S.K., Kim, W.Y.: ‘A novel approach to the fast computation of Zernike moments’, Pattern Recognit., 2006, 39, pp. 2065–2076 (doi: 10.1016/j.patcog.2006.03.004).
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-cvi.2013.0027
Loading

Related content

content/journals/10.1049/iet-cvi.2013.0027
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading
Print this page
This is a required field
Please enter a valid email address