{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,13]],"date-time":"2025-11-13T07:11:52Z","timestamp":1763017912725,"version":"build-2065373602"},"reference-count":40,"publisher":"MDPI AG","issue":"9","license":[{"start":{"date-parts":[[2018,9,14]],"date-time":"2018-09-14T00:00:00Z","timestamp":1536883200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"the National Key R&amp;D Program of China","award":["2016YFB1200100"],"award-info":[{"award-number":["2016YFB1200100"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Remote Sensing"],"abstract":"<jats:p>Despite the fact that automatic target recognition (ATR) in Synthetic aperture radar (SAR) images has been extensively researched due to its practical use in both military and civil applications, it remains an unsolved problem. The major challenges of ATR in SAR stem from severe data scarcity and great variation of SAR images. Recent work started to adopt convolutional neural networks (CNNs), which, however, remain unable to handle the aforementioned challenges due to their high dependency on large quantities of data. In this paper, we propose a novel deep convolutional learning architecture, called Multi-Stream CNN (MS-CNN), for ATR in SAR by leveraging SAR images from multiple views. Specifically, we deploy a multi-input architecture that fuses information from multiple views of the same target in different aspects; therefore, the elaborated multi-view design of MS-CNN enables it to make full use of limited SAR image data to improve recognition performance. We design a Fourier feature fusion framework derived from kernel approximation based on random Fourier features which allows us to unravel the highly nonlinear relationship between images and classes. More importantly, MS-CNN is qualified with the desired characteristic of easy and quick manoeuvrability in real SAR ATR scenarios, because it only needs to acquire real-time GPS information from airborne SAR to calculate aspect differences used for constructing testing samples. The effectiveness and generalization ability of MS-CNN have been demonstrated by extensive experiments under both the Standard Operating Condition (SOC) and Extended Operating Condition (EOC) on the MSTAR dataset. Experimental results have shown that our proposed MS-CNN can achieve high recognition rates and outperform other state-of-the-art ATR methods.<\/jats:p>","DOI":"10.3390\/rs10091473","type":"journal-article","created":{"date-parts":[[2018,9,14]],"date-time":"2018-09-14T10:57:59Z","timestamp":1536922679000},"page":"1473","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":75,"title":["Multi-Stream Convolutional Neural Network for SAR Automatic Target Recognition"],"prefix":"10.3390","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0319-3667","authenticated-orcid":false,"given":"Pengfei","family":"Zhao","sequence":"first","affiliation":[{"name":"School of Electronics and Information Engineering, Beihang University, Beijing 100191, China"},{"name":"Beijing Key Lab for Network-Based Cooperative ATM, Beijing 100191, China"},{"name":"Beijing Laboratory for General Aviation Technology, Beijing 100191, China"}]},{"given":"Kai","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Electronics and Information Engineering, Beihang University, Beijing 100191, China"},{"name":"Beijing Key Lab for Network-Based Cooperative ATM, Beijing 100191, China"},{"name":"Beijing Laboratory for General Aviation Technology, Beijing 100191, China"}]},{"given":"Hao","family":"Zou","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences, Beijing 100190, China"}]},{"given":"Xiantong","family":"Zhen","sequence":"additional","affiliation":[{"name":"School of Electronics and Information Engineering, Beihang University, Beijing 100191, China"},{"name":"Beijing Key Lab for Network-Based Cooperative ATM, Beijing 100191, China"},{"name":"Beijing Laboratory for General Aviation Technology, Beijing 100191, China"}]}],"member":"1968","published-online":{"date-parts":[[2018,9,14]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"6","DOI":"10.1109\/MGRS.2013.2248301","article-title":"A tutorial on synthetic aperture radar","volume":"1","author":"Moreira","year":"2013","journal-title":"IEEE Geosci. Remote Sens. Mag."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"1225","DOI":"10.1109\/TGRS.2014.2336241","article-title":"A high-order imaging algorithm for high-resolution spaceborne SAR based on a modified equivalent squint range model","volume":"53","author":"Wang","year":"2014","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_3","first-page":"5","article-title":"Radar Automatic Target Recognition (ATR) and Non-Cooperative Target Recognition (NCTR)","volume":"296","author":"Blacknell","year":"2013","journal-title":"IET Digit. Libr."},{"key":"ref_4","first-page":"6014","article-title":"Automatic target recognition in synthetic aperture radar imagery: A state-of-the-art review","volume":"4","author":"Gill","year":"2017","journal-title":"IEEE Access"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"79","DOI":"10.1109\/83.552098","article-title":"Attributed scattering centers for SAR ATR","volume":"6","author":"Potter","year":"1997","journal-title":"IEEE Trans. Image Process."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"102","DOI":"10.1109\/7.570713","article-title":"Effects of polarization and resolution on SAR ATR","volume":"33","author":"Novak","year":"1997","journal-title":"IEEE Trans. Aerosp. Electron. Syst."},{"key":"ref_7","first-page":"3","article-title":"An overview of automatic target recognition","volume":"6","author":"Dudgeon","year":"1993","journal-title":"Linc. Lab. J."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"112","DOI":"10.1109\/TAES.2007.357120","article-title":"Adaptive boosting for SAR automatic target recognition","volume":"43","author":"Sun","year":"2007","journal-title":"IEEE Trans. Aerosp. Electron. Syst."},{"key":"ref_9","unstructured":"Hummel, R. (2000, January 12). Model-based ATR using synthetic aperture radar. Proceedings of the Record of the IEEE 2000 International Radar Conference, Alexandria, VA, USA."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"643","DOI":"10.1109\/7.937475","article-title":"Support vector machines for SAR automatic target recognition","volume":"37","author":"Zhao","year":"2001","journal-title":"IEEE Trans. Aerosp. Electron. Syst."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"4806","DOI":"10.1109\/TGRS.2016.2551720","article-title":"Target classification using the deep convolutional networks for SAR images","volume":"54","author":"Chen","year":"2016","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_12","first-page":"364","article-title":"Convolutional neural network with data augmentation for SAR target recognition","volume":"13","author":"Ding","year":"2016","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Morgan, D.A. (2015, January 13). Deep convolutional neural networks for ATR from SAR imagery. Proceedings of the Algorithms for Synthetic Aperture Radar Imagery XXII, Baltimore, MD, USA.","DOI":"10.1117\/12.2176558"},{"key":"ref_14","first-page":"1","article-title":"Modern approaches in deep learning for SAR ATR","volume":"9843","author":"Wilmanski","year":"2016","journal-title":"Int. Soc. Opt. Photonics"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"1285","DOI":"10.1109\/TMI.2016.2528162","article-title":"Deep convolutional neural networks for computer-aided detection: CNN architectures, dataset characteristics and transfer learning","volume":"35","author":"Shin","year":"2016","journal-title":"IEEE Trans. Med. Image"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Li, X., Li, C.S., Wang, P.B., Men, Z.R., and Xu, H.P. (2015, January 1\u20134). SAR ATR based on dividing CNN into CAE and SNN. Proceedings of the 5th Asia-Pacific Conference on Synthetic Aperture Radar.","DOI":"10.1109\/APSAR.2015.7306296"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Su, H., Maji, S., Kalogerakis, E., and Learned-Miller, E. (2015, January 7\u201313). Multi-view convolutional neural networks for 3D shape recognition. Proceedings of the International Conference on Computer Vision, Washington, DC, USA.","DOI":"10.1109\/ICCV.2015.114"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Johns, E., Leutenegger, S., and Davison, A.J. (2016). Pairwise decomposition of image sequences for active multi-view recognition. Comput. Vis. Pattern Recognit., 3813\u20133822.","DOI":"10.1109\/CVPR.2016.414"},{"key":"ref_19","unstructured":"Loffe, S., and Szegedy, C. (2015, January 6\u201311). Batch normalization: Accelerating deep network training by reducing internal covariate shift. Proceedings of the International Conference on Machine Learning, Lille, France."},{"key":"ref_20","unstructured":"Nair, V., and Hinton, G.E. (2010, January 21\u201324). Rectified linear units improve restricted boltzmann machines. Proceedings of the International Conference on International Conference on Machine Learning, Haifa, Isreal."},{"key":"ref_21","first-page":"253","article-title":"Convolutional networks and applications in vision","volume":"14","author":"Lecun","year":"2011","journal-title":"IEEE Int. Symp. Circuits Syst."},{"key":"ref_22","unstructured":"Li, F., and Sminchisescu, C. (2012, January 8\u201316). Fourier kernel learning. Proceedings of the European Conference on Computer Vision, Amsterdam, The Netherlands."},{"key":"ref_23","unstructured":"Cho, Y., and Saul, K.L. (2009). Kernel Methods for Deep Learning. Advances in Neural Information, Proceedings of Neural Information Processing Systems 2009, Vancouver, BC, Canada, 7-10 December 2009, Curran Associates, Inc."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Bochner, S. (1959). Lectures on Fourier Integrals, Princeton University Press.","DOI":"10.1515\/9781400881994"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"591","DOI":"10.1109\/TAES.2013.120340","article-title":"SAR automatic target recognition using discriminative graphical models","volume":"50","author":"Srinivas","year":"2014","journal-title":"IEEE Trans. Aerosp. Electron. Syst."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"952","DOI":"10.1109\/LSP.2014.2321565","article-title":"Sparse representation of monogenic signal: With application to target recognition in SAR Images","volume":"21","author":"Dong","year":"2014","journal-title":"IEEE Signal. Process. Lett."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"2527","DOI":"10.1109\/TIP.2015.2421440","article-title":"Classification on the monogenic scale space: application to target recognition in SAR image","volume":"24","author":"Dong","year":"2015","journal-title":"IEEE Trans. Image Process."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"1092","DOI":"10.1109\/TAES.2013.120378","article-title":"Modified polar mapping classifier for SAR automatic target recognition","volume":"50","author":"Park","year":"2014","journal-title":"IEEE Trans. Aerosp. Electron. Syst."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"7186120","DOI":"10.1155\/2017\/7186120","article-title":"Automatic target recognition strategy for synthetic aperture radar images based on combined discrimination Trees","volume":"2017","author":"Zhao","year":"2017","journal-title":"Comput. Intell. Neurosci."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"1527","DOI":"10.1162\/neco.2006.18.7.1527","article-title":"A fast learning algorithm for deep belief nets","volume":"18","author":"Hinton","year":"2006","journal-title":"Neural Comput."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"270","DOI":"10.1162\/neco.1989.1.2.270","article-title":"A learning algorithm for continually running fully recurrent neural networks","volume":"1","author":"Williams","year":"1989","journal-title":"Neural Comput."},{"key":"ref_32","unstructured":"Krizhevsky, A., Sutskever, I., and Hinton, G.E. (2012, January 3\u20136). In imageNet classification with deep convolutional neural networks. Proceedings of the International Conference on Neural Information Processing Systems, Nevada, NV, USA."},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erthan, D., Vanhoucke, V., and Rabinovich, A. (2015, January 7\u201312). Going deeper with convolutions. Proceedings of the Computer Vision and Pattern Recognition, Boston, MA, USA.","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (2015, January 9). Delving deep into rectifiers: Surpassing human-level performance on imageNet classification. Proceedings of the IEEE International Conference on Computer Vision, Washington DC, WA, USA.","DOI":"10.1109\/ICCV.2015.123"},{"key":"ref_35","unstructured":"Chen, S., and Wang, H. (November, January 30). SAR target recognition based on deep learning. Proceedings of the International Conference on Data Science and Advanced Analytics, Shanghai, China."},{"key":"ref_36","first-page":"11","article-title":"Deep learning for target classification from SAR imagery: Data augmentation and translation invariance","volume":"117","author":"Furukawa","year":"2017","journal-title":"IEICE Tech. Rep."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"2481","DOI":"10.1109\/TAES.2012.6237604","article-title":"Multi-view automatic target recognition using joint sparse representation","volume":"48","author":"Zhang","year":"2012","journal-title":"IEEE Trans. Aerosp. Electron. Syst."},{"key":"ref_38","unstructured":"Zhang, F., Hu, C., Yin, Q., Li, W., Li, H., and Hong, W. (arXiv, 2017). SAR target recognition using the multi-aspect-aware bidirectional LSTM recurrent neural networks, arXiv."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"2196","DOI":"10.1109\/TGRS.2017.2776357","article-title":"SAR automatic target recognition based on multiview deep learning framework","volume":"56","author":"Pei","year":"2017","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"158","DOI":"10.1016\/j.patcog.2017.05.025","article-title":"Handcrafted vs. non-handcrafted features for computer vision classification","volume":"71","author":"Nanni","year":"2017","journal-title":"Pattern Recognit."}],"container-title":["Remote Sensing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-4292\/10\/9\/1473\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T15:20:37Z","timestamp":1760196037000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-4292\/10\/9\/1473"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,9,14]]},"references-count":40,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2018,9]]}},"alternative-id":["rs10091473"],"URL":"https:\/\/doi.org\/10.3390\/rs10091473","relation":{},"ISSN":["2072-4292"],"issn-type":[{"type":"electronic","value":"2072-4292"}],"subject":[],"published":{"date-parts":[[2018,9,14]]}}}