access icon openaccess RBM-based joint dictionary learning for ISAR resolution enhancement

This is an open access article published by the IET under the Creative Commons Attribution License (http://creativecommons.org/licenses/by/3.0/)
Received 25/02/2019, Accepted 02/05/2019, Published 13/08/2019

In this study, an inverse synthetic aperture radar (ISAR) image resolution enhancement algorithm based on joint dictionary learning is proposed, by which two special sets of sparse signals called dictionaries are solved by exploiting numerous high-resolution (HR) and low-resolution (LR) ISAR images. Herein a new coupled dictionary learning algorithm based on restricted Boltzmann machine (RBM) is designed to learn a LR and a HR dictionary using LR and HR image patches. Since the echoes are equivalent to similar scattering-centre models when an object is illuminated by radar signals with same centre frequency and different bandwidth, respectively, it is reasonable to assume the object's LR ISAR image shares the same sparse representation coefficients with its HR ISAR image. When a LR ISAR image is represented sparsely with a LR dictionary, a HR ISAR images can be reconstructed based on a HR dictionary owing to the similar sparse representation coefficients. Experiment results with simulation data demonstrate the superior performance of the proposed method over other classical dictionary training algorithms.

Inspec keywords: Boltzmann machines; learning (artificial intelligence); dictionaries; image enhancement; image resolution; image representation; radar imaging; image reconstruction; synthetic aperture radar

Other keywords: HR ISAR image; RBM-based joint dictionary; image patches; HR dictionary; ISAR resolution enhancement; similar scattering-centre models; radar signals; coupled dictionary learning algorithm; sparse signals; inverse synthetic aperture radar image resolution enhancement algorithm; similar sparse representation coefficients; LR dictionary; classical dictionary training algorithms; restricted Boltzmann machine; LR ISAR image shares; joint dictionary learning

Subjects: Optical, image and video signal processing; Knowledge engineering techniques; Computer vision and image processing techniques; Radar equipment, systems and applications

References

    1. 1)
      • 7. Vann, L.D., Cuomo, K.M., Piou, J.E., et al: ‘Multisensor fusion processing for enhanced radar imaging Lincoln Lab’, Tech. Rep. TR-1056, Lexington, MA, USA, 2000.
    2. 2)
      • 10. Mairal, J., Bach, F., Ponce, J., et al: ‘Online dictionary learning for sparse coding’. Int. Conf. on Machine Learning, Montreal, Canada, 2009.
    3. 3)
      • 13. Gao, J., Guo, Y., Yin, M.: ‘Restricted Boltzmann machine approach to couple dictionary training for image super-resolution’. IEEE Int. Conf. on Image Processing, Melbourne, Australia, 2013, pp. 499–503.
    4. 4)
      • 11. Engan, K., Aase, S.O., Husoy, J.H.: ‘Method of optimal direction for frame design’. IEEE Int. Conf. on Acoustics, Speech and Signal Processing(ICASSP), Phoenix, AZ, USA, 1999.
    5. 5)
      • 1. Nuthalapati, R.M.: ‘High resolution reconstruction of SAR image’, IEEE Aerosp. Electron. Syst., 1992, 8, (2), pp. 462–472.
    6. 6)
      • 6. Li, J., Stocia, P.: ‘Efficient mixed-spectrum estimation with application to target feature extraction’, IEEE Trans Signal Proc., 1996, 44, (2), pp. 281–295.
    7. 7)
      • 9. Huang, J., Adviser-Metaxas, D.N.: ‘Structure sparsity: theorems, algorithms and applications’ PHD Thesis, Rutgers University, 2011.
    8. 8)
      • 4. DeGraaf, S.R.: ‘SAR imaging 2-D spectral estimation methods’. SPE proc. On Optical Engineering in Aerospace Sensing, Orlando, FL, USA, 1994, 2230, pp. 36–49.
    9. 9)
      • 15. LeCun, Y., Bengio, Y.: ‘Convolutional networks for images, speech and time series’, In Arbib, M.A. (Ed.): ‘The handbookof brain theory and neural networks’ (MIT Press, Cambridge, MA, USA, 1995), pp. 505–512.
    10. 10)
      • 16. Yang, J.C., Wright, J., Huang, T.S., et al: ‘Image super-resolution via sparse representation’, IEEE Trans. Image Process., 2010, 19, (11), pp. 2861–2873.
    11. 11)
      • 14. Ye, J., Gao, X., Zhang, Y.: ‘ISAR super resolution reconstruction based on couple dictionary learning’. Int. Conf. on Communication, Network and Artificial Intelligence, Beijing, China, 2018.
    12. 12)
      • 5. Li, J., Stoica, P.: ‘An adaptive filtering approach to spectral estimation and SAR imaging’, IEEE Trans. Signal Proc., 1996, 44, (6), pp. 1469–1484.
    13. 13)
      • 2. Kim, K.T., Bae, J.H., Kim, H.T.: ‘Effect of AR model-based data extrapolation on target recognition performance’, IEEE Trans. Antennas Propag., 2003, 51, (4), pp. 912–914.
    14. 14)
      • 12. Aharon, M., Elad, M., Bruckstein, A.: ‘K-SVD: an algorithm for designing overcomplete dictionaries for sparse representation’, IEEE Trans. Signal Process., 2006, 54, (11), pp. 4311–4322.
    15. 15)
      • 8. Cuomo, K.M., Piou, J.E., Mayhan, J.T.: ‘Ultrawideband sensor fusion for BMD discrimination’. Proc. IEEE Int. Radar Conf., Alexandria, VA, USA, May 7–12 2000, pp. 31–34.
    16. 16)
      • 17. Hinton, G.E., Osindero, S., Teh, Y.W.: ‘A fast learning algorithm for deep belief nets’, Neural Comput., 2006, 18, (7), pp. 1527–1554.
    17. 17)
      • 3. Borison, S.L., Bowling, S.B., Cuomo, K.M.: ‘Super-resolution methods for wideband radar’, Lincoln Lab. J., 1992, 5, (3), pp. 441–461.
http://iet.metastore.ingenta.com/content/journals/10.1049/joe.2019.0732
Loading

Related content

content/journals/10.1049/joe.2019.0732
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading