使用深度卷积神经网络实现SAR图像的自动目标识别在训练过程中需要大量的标注数据。为解决由SAR实测数据获取成本高、标注数据量不足带来的问题，提出一种在由CReLU激活函数和批归一化改进的卷积神经网络上，使用仿真SAR图像提升最终目标识别性能的方法，把从大量仿真SAR图像学习到的有效知识迁移到实测SAR图像数据上。在训练中，先用仿真SAR图像预训练卷积神经网络，结合迁移学习的方法，有效地解决由SAR图像数据不足带来的过拟合问题。在MSTAR数据集上验证方法的有效性，识别准确率提高到99.78%，并在少量SAR图像样本数据上也取得不错的识别效果。
Using deep convolutional neural networks to realize automatic target recognition of SAR requires a large amount of labeled data. In order to solve the problem caused by the scarcity of SAR real images, we propose a method for improving the target recognition performance of SAR by using simulated SAR images on convolutional neural networks improved by CReLU activation function and batch normalization. The method transfers the effective knowledge learned from a large number of simulated SAR images onto the real SAR images. In the training, the pre-trained convolutional neural networks can be obtained by training by using the simulated SAR images firstly, and the deep transfer learning method is used to effectively solve the problem caused by the insufficiency of SAR image data. The validation experiment is carried out on the MSTAR dataset. The highest recognition accuracy reaches 99.78%, and good recognition results are obtained based on a small amount of SAR image data.
[1] Cummimg I, Wong F. 合成孔径雷达成像:算法与实现[M]. 北京:电子工业出版社, 2012:2-11.
[2] Mcnairn H, Brisco B. The application of C-band polarimetric SAR for agriculture:a review[J]. Canadian Journal of Remote Sensing, 2004, 30(3):525-542.
[3] Ross T D, Worrell S W, Velten V J, et al. Standard SAR ATR evaluation experiments using the MSTAR public release data set[C]//Algorithms for Synthetic Aperture Radar Imagery V. Orlando, United States:International Society for Optics and Photonics, 1998, 3370:566-574.
[4] Anagnostopoulos G C. SVM-based target recognition from synthetic aperture radar images using target region outline descriptors[J]. Nonlinear Analysis:Theory, Methods & Applications, 2009, 71(12):e2934-e2939.
[5] Song S, Xu B, Yang J. SAR target recognition via supervised discriminative dictionary learning and sparse representation of the SAR-HOG feature[J]. Remote Sensing, 2016, 8(8):683.
[6] Park J I, Kim K T. Modified polar mapping classifier for SAR automatic target recognition[J]. IEEE Transactions on Aerospace and Electronic Systems, 2014, 50(2):1092-1107.
[7] Krizhevsky A, Sutskever I, Hinton G E. ImageNet classification with deep convolutional neural networks[C]//Advances in neural information processing systems. Nevada, USA:Curran Associates Inc, 2012:1097-1105.
[8] Schmidhuber J. Deep learning in neural networks:an overview[J]. Neural Networks, 2015, 61:85-117.
[9] Szegedy C, Liu W, Jia Y, et al. Going deeper with convolutions[C]//IEEE Conference on Computer Vision and Pattern Recognition. Boston:IEEE Computer Society, 2015:1-9.
[10] He K, Zhang X, Ren S, et al. Deep residual learning for image recognition[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas:IEEE Computer Society, 2016:770-778.
[11] Malmgren-Hansen D, Kusk A, Dall J, et al. Improving SAR automatic target recognition models with transfer learning from simulated data[J]. IEEE Geoscience and Remote Sensing Letters, 2017, 14(9):1484-1488.
[12] Morgan D A E. Deep convolutional neural networks for ATR from SAR imagery[C]//Algorithms for Synthetic Aperture Radar Imagery XXII. Maryland, United States:International Society for Optics and Photonics, 2015, 9475:94750F.
[13] 李松, 魏中浩, 张冰尘, 等. 深度卷积神经网络在迁移学习模式下的SAR目标识别[J]. 中国科学院大学学报, 2018, 35(1):75-83.
[14] Huang Z, Pan Z, Lei B. Transfer learning with deep convolutional neural network for SAR target classification with limited labeled data[J]. Remote Sensing, 2017, 9(9):907.
[15] 徐丰, 王海鹏, 金亚秋. 深度学习在SAR目标识别与地物分类中的应用[J]. 雷达学报, 2017, 6(2):136-148.
[16] 董纯柱, 胡利平, 朱国庆,等. 地面车辆目标高质量SAR图像快速仿真方法[J]. 雷达学报, 2015, 4(3):351-360.
[17] Kusk A, Abulaitijiang A, Dall J. Synthetic SAR image generation using sensor, terrain and target models[C]//Proceedings of EUSAR 2016:11th European Conference on Synthetic Aperture Radar. Hamburg, Germany:VDE, 2016:1-5.
[18] Shang W, Sohn K, Almeida D, et al. Understanding and improving convolutional neural networks via concatenated rectified linear units[C]//International Conference on Machine Learning. New York:ICML, 2016:2217-2225.
[19] Ioffe S. Batch renormalization:Towards reducing minibatch dependence in batch-normalized models[C]//Advances in Neural Information Processing Systems. Long Beach:NIPS, 2017:1945-1953.
[20] Glorot X, Bengio Y. Understanding the difficulty of training deep feedforward neural networks[C]//Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics. Sardinia:AISTATS, 2010:249-256.
[21] He K, Zhang X, Ren S, et al. Delving deep into rectifiers:Surpassing human-level performance on imagenet classification[C]//Proceedings of the IEEE International Conference on Computer Vision. Washington, DC, USA:IEEE Computer Society, 2015:1026-1034.
[22] Vaswani A, Shazeer N, Parmar N, et al. Attention is all you need[C]//Advances in Neural Information Processing Systems. Long Beach, NIPS, 2017:5998-6008.
