Advertisement

Cognitive Computation

, Volume 11, Issue 6, pp 809–824 | Cite as

A New Algorithm for SAR Image Target Recognition Based on an Improved Deep Convolutional Neural Network

  • Fei Gao
  • Teng HuangEmail author
  • Jinping SunEmail author
  • Jun Wang
  • Amir Hussain
  • Erfu Yang
Article

Abstract

In an attempt to exploit the automatic feature extraction ability of biologically-inspired deep learning models, and enhance the learning of target features, we propose a novel deep learning algorithm. This is based on a deep convolutional neural network (DCNN) trained with an improved cost function, and combined with a support vector machine (SVM). Specifically, class separation information, which explicitly facilitates intra-class compactness and inter-class separability in the process of learning features, is added to an improved cost function as a regularization term, to enhance the DCNN’s feature extraction ability. The enhanced DCNN is applied to learn the features of Synthetic Aperture Radar (SAR) images, and the SVM is utilized to map features into output labels. Simulation experiments are performed using benchmark SAR image data from the Moving and Stationary Target Acquisition and Recognition (MSTAR) database. Comparative results demonstrate the effectiveness of our proposed method, with an average accuracy of 99% on ten types of targets, including variants and articulated targets. We conclude that our proposed DCNN method has significant potential to be exploited for SAR image target recognition, and can serve as a new benchmark for the research community.

Keywords

Synthetic-aperture radar (SAR) images Automatic target recognition (ATR) Deep convolutional neural network (DCNN) Support vector machine (SVM) Class separation information 

Notes

Funding Information

This work was supported by the National Natural Science Foundation of China (61771027; 61071139; 61471019; 61671035), the Scientific Research Foundation of Guangxi Education Department (KY 2015LX444), and the Scientific Research and Technology Development Project of Wuzhou, Guangxi, China (201402205). Dr E. Yang was supported in part under the RSE-NNSFC Joint Project (2017–2019) (6161101383) with China University of Petroleum (Huadong). Professor A. Hussain was supported by the UK Engineering and Physical Sciences Research Council (EPSRC) grant no. EP/M026981/1.

Compliance with Ethical Standards

Conflict of Interest

The authors declare that they have no conflict of interest.

Ethical Approval

This article does not contain any studies with human participants performed by any of the authors.

References

  1. 1.
    Gao F, Ma F, Zhang Y, Wang J, Sun J, Yang E, Hussain A. Biologically inspired progressive enhancement target detection from heavy cluttered sar images. Cogn Comput 2016;8(5):1–12.CrossRefGoogle Scholar
  2. 2.
    Gao F, Zhang Y, Wang J, Sun J, Yang E, Hussain A. Visual attention model based vehicle target detection in synthetic aperture radar images: a novel approach. Cogn Comput 2015;7(4):434–44.CrossRefGoogle Scholar
  3. 3.
    Owirka GJ, Verbout SM, Novak LM. Template-based SAR ATR performance using different image enhancement techniques. Proc Spie 1999;3721:302–19.CrossRefGoogle Scholar
  4. 4.
    Zhao Q, Principe JC. Support vector machines for sar automatic target recognition. IEEE Trans Aerospace Electron Syst 2001;37(2):643–54.CrossRefGoogle Scholar
  5. 5.
    Ren J, Jiang J, Vlachos T. High-accuracy sub-pixel motion estimation from noisy images in Fourier domain. IEEE Trans Image Process 2010;19(5):1379–84.CrossRefGoogle Scholar
  6. 6.
    Zabalza J, Ren J, Yang M, Zhang Y, Wang J, Marshall S, Han J. Novel Folded-PCA for improved feature extraction and data reduction with hyperspectral imaging and SAR in remote sensing. Isprs J Photogrammetry Remote Sens 2014;93(7):112–22.CrossRefGoogle Scholar
  7. 7.
    Zabalza J, Ren J, Ren J, Liu Z, Marshall S. Structured covariance principal component analysis for real-time onsite feature extraction and dimensionality reduction in hyperspectral imaging. Appl Opt 2014;53(20): 4440.CrossRefGoogle Scholar
  8. 8.
    Lin C, Wang B, Zhao X, Pang M. Optimizing kernel PCA using sparse representation-based classifier for MSTAR SAR image target recognition. Math Problems Eng, 2013,(2013-5-2) 2013;2013(6):707–24.Google Scholar
  9. 9.
    Liu H, Li S. Decision fusion of sparse representation and support vector machine for SAR image target recognition. Neurocomputing 2013;113(7):97–104.CrossRefGoogle Scholar
  10. 10.
    Hinton G, Salakhutdinov RR. Reducing the dimensionality of data with neural networks. Science July 2006;313(5786):504–7.CrossRefGoogle Scholar
  11. 11.
    Han J, Zhang D, Cheng G, Guo L, Ren J. Object detection in optical remote sensing images based on weakly supervised learning and high-level feature learning. IEEE Trans Geoscience Remote Sens 2015;53(6): 3325–37.CrossRefGoogle Scholar
  12. 12.
    Montufar G, Ay N. Refinements of universal approximation results for deep belief networks and restricted Boltzmann machines. Neural Comput 2011;23(5):1306.CrossRefGoogle Scholar
  13. 13.
    Won S, Young SS. Assessing the accuracy of image tracking algorithms on visible and thermal imagery using a deep restricted Boltzmann machine. Proc Spie 2012;8401(7):6.Google Scholar
  14. 14.
    Zabalza J, Ren J, Zheng J, Zhao H, Qing C, Yang Z, Du P, Marshall S. Novel segmented stacked autoencoder for effective dimensionality reduction and feature extraction in hyperspectral imaging. Neurocomputing 2016;214(C):1062.CrossRefGoogle Scholar
  15. 15.
    Sun M, Zhang D, Ren J, Wang Z, Jin JS. Brushstroke based sparse hybrid convolutional neural networks for author classification of chinese ink-wash paintings. IEEE International Conference on Image Processing; 2015. p. 626–630.Google Scholar
  16. 16.
    Wen G, Hou Z, Li H, Li D, Jiang L, Xun E. Ensemble of deep neural networks with probability-based fusion for facial expression recognition. Cogn Comput 2017;9(5):597–610.CrossRefGoogle Scholar
  17. 17.
    Zhong G, Yan S, Huang K, Cai Y, Dong J. Reducing and stretching deep convolutional activation features for accurate image classification. Cogn Comput 2018;10(1):179–86.CrossRefGoogle Scholar
  18. 18.
    He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. (2015) 770–8.Google Scholar
  19. 19.
    Lecun Y, Bengio Y, Hinton G. Deep learning. Nature 2015;521(7553):436.CrossRefGoogle Scholar
  20. 20.
    Theodoridis S. 2015. Neural networks and deep learning.CrossRefGoogle Scholar
  21. 21.
    Chen S, Wang H. SAR target recognition based on deep learning. International Conference on Data Science and Advanced Analytics; 2015. p. 541–547.Google Scholar
  22. 22.
    Li X, Li C, Wang P, Men Z, Xu H. SAR ATR based on dividing CNN into CAE and SNN. Synthetic Aperture Radar; 2015. p. 676–679.Google Scholar
  23. 23.
    Wagner S. Combination of convolutional feature extraction and support vector machines for radar ATR. International Conference on Information Fusion; 2014. p. 1–6.Google Scholar
  24. 24.
    Huang FJ, Lecun Y. Large-scale learning with SVM and convolutional for generic object categorization. IEEE Computer Society Conference on Computer Vision and Pattern Recognition; 2006. p. 284–291.Google Scholar
  25. 25.
    Wagner S. Morphological component analysis in SAR images to improve the generalization of ATR systems. International Workshop on Compressed Sensing Theory and ITS Applications To Radar, Sonar and Remote Sensing; 2015. p. 46–50.Google Scholar
  26. 26.
    Ding J, Chen B, Liu H, Huang M. Convolutional neural network with data augmentation for SAR target recognition. IEEE Geoscience Remote Sens Lett 2016;13(3):364–8.Google Scholar
  27. 27.
    Chen S, Wang H, Xu F, Jin YQ. Target classification using the deep convolutional networks for SAR images. IEEE Trans Geoscience Remote Sens 2016;54(8):4806–17.CrossRefGoogle Scholar
  28. 28.
    Du K, Deng Y, Wang R, Zhao T, Li N. SAR ATR based on displacement- and rotation-insensitive CNN. Remote Sens Lett 2016;7(9):895–904.CrossRefGoogle Scholar
  29. 29.
    Kreucher C. Modern approaches in deep learning for SAR ATR. Algorithms for Synthetic Aperture Radar Imagery XXIII; 2016. p. 98430N.Google Scholar
  30. 30.
    Pathak G, Singh B, Panigrahi BK. Back propagation algorithm based controller for autonomous wind-DG microgrid. IEEE Trans Ind Appl 2016;52(5):4408–15.CrossRefGoogle Scholar
  31. 31.
    Mossing JC, Ross TD. Evaluation of SAR ATR algorithm performance sensitivity to MSTAR extended operating conditions. Proceedings of SPIE—The International Society for Optical Engineering 1998;3370:13.Google Scholar
  32. 32.
    Ross TD, Velten VJ, Mossing JC. Standard SAR ATR evaluation experiments using the MSTAR public release data set. Algorithms for Synthetic Aperture Radar Imagery V; 1998. p. 566– 573.Google Scholar
  33. 33.
    Kingma DP, Ba J. 2014. Adam: A method for stochastic optimization. Computer Science.Google Scholar
  34. 34.
    Iii GJ, Bhanu B. Recognizing articulated objects in SAR images. Pattern Recogn 2001;34(2):469–85.CrossRefGoogle Scholar
  35. 35.
    Li G, Deng L, Xu Y, Wen C, Wang W, Jing P, Shi L. Temperature based restricted Boltzmann machines. Sci Rep 2016;6:19133.CrossRefGoogle Scholar
  36. 36.
    Guo C, Pleiss G, Sun Y, Weinberger KQ. 2017. On calibration of modern neural networks.Google Scholar
  37. 37.
    Singh R, Kumar BV. Performance of the extended maximum average correlation height (EMACH) filter and the polynomial distance classifier correlation filter (PDCCF) for multiclass SAR detection and classification. Proceedings of SPIE—The International Society for Optical Engineering 2002;4727:265–76.Google Scholar
  38. 38.
    Srinivas U. SAR automatic target recognition using discriminative graphical models. IEEE International conference on image processing, ICIP 2011, Brussels, Belgium; 2014. p. 33–36.Google Scholar
  39. 39.
    Dong G, Wang N, Kuang G. Sparse representation of monogenic signal: with application to target recognition in SAR images. IEEE Signal Process Lett 2014;21(8):952–6.CrossRefGoogle Scholar
  40. 40.
    Dong G, Kuang G. Classification on the monogenic scale space: application to target recognition in SAR image. IEEE Trans Image Process 2015;24(8):2527–39.CrossRefGoogle Scholar
  41. 41.
    Park JI, Kim KT. Modified polar mapping classifier for SAR automatic target recognition. IEEE Trans Aerospace Electron Syst Aes 2014;50(2):1092–107.CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2018

Authors and Affiliations

  1. 1.School of Electronic and Information EngineeringBeihang UniversityBeijingChina
  2. 2.Division of Computing Science and MathsUniversity of StirlingScotlandUK
  3. 3.Space Mechatronic Systems Technology Laboratory, Department of Design, Manufacture and Engineering ManagementUniversity of StrathclydeGlasgowUK

Personalised recommendations