A New Algorithm for SAR Image Target Recognition Based on an Improved Deep Convolutional Neural Network
- 439 Downloads
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.
KeywordsSynthetic-aperture radar (SAR) images Automatic target recognition (ATR) Deep convolutional neural network (DCNN) Support vector machine (SVM) Class separation 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.
This article does not contain any studies with human participants performed by any of the authors.
- 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
- 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
- 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
- 18.He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. (2015) 770–8.Google Scholar
- 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.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.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.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.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.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
- 29.Kreucher C. Modern approaches in deep learning for SAR ATR. Algorithms for Synthetic Aperture Radar Imagery XXIII; 2016. p. 98430N.Google Scholar
- 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.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.Kingma DP, Ba J. 2014. Adam: A method for stochastic optimization. Computer Science.Google Scholar
- 36.Guo C, Pleiss G, Sun Y, Weinberger KQ. 2017. On calibration of modern neural networks.Google Scholar
- 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.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