浏览全部资源
扫码关注微信
收稿：2018-07-12，
修回：2018-8-26，
纸质出版：2019-02-16
移动端阅览
目的
2
深度学习已经大量应用于合成孔径宽达（SAR）图像目标识别领域，但大多数工作是基于MSTAR数据集的标准操作条件展开研究。当将深度学习应用于同类含变体目标时，例如T72子类，由于目标间差异小，所以仍存在着较大的挑战。本文从极大限度地保留SAR图像输入特征出发，设计一种适用于SAR变体目标识别的深度卷积神经网络结构。
方法
2
设计网络主要由多尺度空间特征提取模块和DenseNet中的稠密块、转移层构成。多尺度特征提取模块置于网络底层，通过使用尺寸分别为1×1、3×3、5×5、7×7、9×9的卷积核，提取丰富空间特征的同时保留输入图像信息。为使输入图像信息更加有效地向后传递，基于DenseNet中的稠密块和转移层进行后续网络层设计。在对训练样本进行样本扩充基础上，分析了输入图像分辨率及目标存在平移和不同噪声水平等情况对模型识别精度的影响，与用于SAR图像目标识别的深度模型识别精度在标准操作条件下进行了对比分析。
结果
2
实验结果表明，对T72 8类变体目标进行分类，设计的模型能够取得95.48%的识别精度，在存在目标平移和不同噪声水平情况下，平均识别精度分别达到了94.61%和86.36%。对10类目标（包括不含变体和含变体情况）在进行数据增强的情况下进行模型训练与测试，分别达到了99.38%和98.81%的识别精度，略优于其他对比模型结构识别精度。
结论
2
提出的模型可以充分利用输入图像以及各卷积层输出的特征，学习目标图像的细节差异，不仅适用于SAR图像变体目标的识别任务，同时在标准操作条件下的识别任务也取得了较高的识别结果。
Objective
2
Deep learning has been widely used in the field of synthetic aperture radar (SAR) target recognition and most studies have been conducted for target recognition under the standard operating conditions (SOCs) of MSTAR datasets. Many challenges exist due to the small differences among the targets when applied to target recognition with variants
such as T72 subclasses. To preserve the input features of SAR images
a deep convolutional neural network (CNN) architecture for SAR target recognition with variants is designed in this study.
Method
2
The proposed network is composed of one multiscale feature extraction module and several dense blocks and transition layers proposed in DenseNet. The multiscale feature extraction module
which is placed at the bottom of the network
uses multiple convolution kernels with sizes of 1×1
3×3
5×5
7×7
and 9×9 to extract rich spatial features. The convolution kernels with a size of 1×1 are adopted to preserve the detailed information from the input image
and convolution kernels with large sizes are used in multiscale feature extraction module to suppress the influence of speckle noise on extracted features because speckle noise is a main factor that affects recognition performance. To transfer the information from the input image effectively and utilize the feature learned from all layers
dense blocks and transition layers are adopted in designing the latter layers of the network. A full convolution layer is used behind three dense blocks and transition layers to transform the learned features to vectors
and a SoftMax layer is adopted to perform classification. Finally
training datasets are augmented by displacing and adding speckle noise to the original images
and the proposed model is implemented using TensorFlow and is trained by using these samples. The influences of input image resolution
target translation
and different noise levels on the recognition accuracy of the proposed network are determined after augmenting the training datasets
and performance comparisons with other deep learning models under SOCs.
Result
2
Experimental results demonstrate that the input image resolution has a considerable influence on the recognition accuracy for eight types of T72 targets
and the accuracy improves considerably with the increase of input resolution. However
the input resolution has minimal effect on the recognition accuracy for SOC due to the large differences among the targets in SOC. The image resolution as the input of the proposed model is set to 88×88×1 because the target and shadow information during data enhancement should be preserved. To verify the performance of the proposed multiscale feature extraction module
tests are performed using different multiscale feature extraction strategies
and the proposed model obtains a classification accuracy of approximately 95.48% in the classification of eight subclasses of T72 target with variants. Aside from the recognition of test samples under SOC
the classification accuracies of the proposed model are investigated in terms of target translation and different noise levels. The proposed model can achieve a recognition accuracy higher than 90%
especially when the target is displaced 16 pixels away from the center of the original image. The proposed model still exhibits a good performance when the noise intensity is set to 0.5 or 1 but causes a remarkable decline in recognition accuracy when the noise intensity is greater than 1. The average classification accuracy can reach 94.61% and 86.36% in the case of object translation and different noise levels. Recognition accuracies of 99.38% (SOC1-10)
99.50% (SOC1-14)
and 98.81% (SOC2) are achieved by using augmented training datasets in training the models for 10-class target recognition under SOC (without variants and with variants). Our model achieves comparable recognition performance with other deep models.
Conclusion
2
Our model utilizes the input information and features of each convolutional layer and captures the detailed difference among the targets from the images. Our model not only can be applied to target recognition task with variants but also achieve satisfactory recognition results under SOC.
Wu L B. SAR Image processing and target recognition[M]. Peking:Aviation industry press, 2013.
吴良斌. SAR图像处理与目标识别[M].北京:航空工业出版社, 2013.
El-Darymli K, Gill E W, Mcguire P, et al. Automatic target recognition in synthetic aperture radar imagery:a state-of-the-art review[J]. IEEE Access, 2016, 4:6014-6058.[DOI:10.1109/ACCESS.2016.2611492]
Liu Z J, Zhuang L K, Cao Y F, et al. Target recognition of SAR images using principal component analysis and sparse representation[J]. Systems Engineering and Electronics, 2013, 35(2):282-286.
刘中杰, 庄丽葵, 曹云峰, 等.基于主元分析和稀疏表示的SAR图像目标识别[J].系统工程与电子技术, 2013, 35(2):282-286. [DOI:10.3969/j.issn.1001-506X.2013.02.08]
Huan R H, Yang R L. Synthetic Aperture Radar Images Target Recognition Based on Wavelet Domain NMF Feature Extraction[J]. Journal of electronics and information technology, 2009, 31(3):588-591.
宦若虹, 杨汝良.基于小波域NMF特征提取的SAR图像目标识别方法[J].电子与信息学报, 2009, 31(3):588-591. [DOI:10.3724/SP.J.1146.2007.01889]
He Z G, Lu J, Kuang G Y. A survey on feature extraction and selection of SAR images[J]. Signal Processing, 2008, 24(5):813-823.
贺志国, 陆军, 匡纲要. SAR图像特征提取与选择研究[J].信号处理, 2008, 24(5):813-823. [DOI:10.3969/j.issn.1003-0530.2008.05.024]
Lou J, Jin T, Song Q, et al. Feature extraction of scattering centers in high-resolution SAR image[J]. Journal of Electronics&Information Technology, 2011, 33(7):1661-1666.
娄军, 金添, 宋千, 等.高分辨率SAR图像散射中心特征提取[J].电子与信息学报, 2011, 33(7):1661-1666. [DOI:10.3724/SP.J.1146.2010.00960]
Ross T D, Worrell S W, Velten V J, et al. Standard SAR ATR evaluation experiments using the MSTAR public release data set[C]//Proceedings of 3370, Algorithms for Synthetic Aperture Radar Imagery V. Orlando, FL, USA: SPIE, 1998, 3370: 566-573.[ DOI: 10.1117/12.321859 http://dx.doi.org/10.1117/12.321859 ]
Zhao Q, Principe J C. Support vector machines for SAR automatic target recognition[J]. IEEE Transactions on Aerospace and Electronic Systems, 2001, 37(2):643-654.[DOI:10.1109/7.937475]
Sun Y J, Liu Z P, Todorovic S, et al. Adaptive boosting for SAR automatic target recognition[J]. IEEE Transactions on Aerospace and Electronic Systems, 2007, 43(1):112-125.[DOI:10.1109/TAES.2007.357120]
Dong G G, Kuang G Y, Wang N, et al. SAR target recognition via joint sparse representation of monogenic signal[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2015, 8(7):3316-3328.[DOI:10.1109/JSTARS.2015.2436694]
Fan X Y. Reserch of SAR target recognition methods based on deep learning[D]. Chengdu: Universicty of electronic science and technology of China, 2016. http://cdmd.cnki.com.cn/Article/CDMD-10614-1016176931.htm .
樊旭云.基于深度学习的SAR目标识别方法研究[D].成都: 电子科技大学, 2016.
Yu K, Jia L, Chen Y Q, et al. Deep Learning:Yesterday, today, and tomorrow[J]. Journal of computer research and development, 2013, 50(9):1799-1804.
余凯, 贾磊, 陈雨强, 等.深度学习的昨天、今天和明天[J].计算机研究与发展, 2013, 50(9):1799-1804.
LeCun Y, Bottou L, Bengio Y, et al. Gradient-based learning applied to document recognition[J]. Proceedings of the IEEE, 1998, 86(11):2278-2324.[DOI:10.1109/5.726791]
Krizhevsky A, Sutskever I, Hinton G E. ImageNet classification with deep convolutional neural networks[C]//Proceedings of the 25th International Conference on Neural Information Processing Systems. Lake Tahoe, Nevada: Curran Associates Inc., 2012: 1097-1105. https://papers.nips.cc/paper/4824-imagenet-classification-with-deep-convolutional-neural-networks.pdf .
Szegedy C, Liu W, Jia Y Q, et al. Going deeper with convolutions[C]//Proceedings of 2015 IEEE Conference on Computer Vision and Pattern Recognition. Boston, MA, USA: IEEE, 2015: 1-9.[ DOI: 10.1109/CVPR.2015.7298594 http://dx.doi.org/10.1109/CVPR.2015.7298594 ]
Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition[EB/OL].[2018-07-01] . https://arxiv.org/pdf/1409.1556.pdf https://arxiv.org/pdf/1409.1556.pdf
Srivastava R K, Greff K, Schmidhuber J. Highway networks[EB/OL].[2018-07-01] . https://arxiv.org/pdf/1505.00387.pdf https://arxiv.org/pdf/1505.00387.pdf
He K M, Zhang X Y, Ren S Q, et al. Deep residual learning for image recognition[C]//Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas, NV, USA: IEEE, 2016: 770-778.[ DOI: 10.1109/CVPR.2016.90 http://dx.doi.org/10.1109/CVPR.2016.90 ]
Wagner S A. SAR ATR by a combination of convolutional neural network and support vector machines[J]. IEEE Transactions on Aerospace and Electronic Systems, 2016, 52(6):2861-2872.[DOI:10.1109/TAES.2016.160061]
Ding J, Chen B, Liu H W, et al. Convolutional neural network with data augmentation for SAR target recognition[J]. IEEE Geoscience and Remote Sensing Letters, 2016, 13(3):364-368.[DOI:10.1109/LGRS.2015.2513754]
Chen S Z, Wang H P, Xu F, et al. Target classification using the deep convolutional networks for SAR images[J]. IEEE Transactions on Geoscience and Remote Sensing, 2016, 54(8):4806-4817.[DOI:10.1109/TGRS.2016.2551720]
Furukawa H. Deep learning for target classification from SAR imagery: data augmentation and translation invariance[EB/OL].[2018-07-01] . https://arxiv.org/pdf/1708.07920.pdf https://arxiv.org/pdf/1708.07920.pdf
Lin Z, Ji K F, Kang M, et al. Deep convolutional highway unit network for SAR target classification with limited labeled training data[J]. IEEE Geoscience and Remote Sensing Letters, 2017, 14(7):1091-1095.[DOI:10.1109/LGRS.2017.2698213]
Chen S Q, Zhan R H, Hu J M, et al. Feature fusion based on convolutional neural network for SAR ATR[C]//Proceedings of ITM Web of Conferences. 2017: 12, 05001.[ DOI: 10.1051/itmconf/20171205001 http://dx.doi.org/10.1051/itmconf/20171205001 ]
Gu Y, Xu Y. Architecture design of deep convolution neural network for SAR target recognition[J]. Journal of Image and Graphics, 2018, 23(6):928-936.
谷雨, 徐英.面向SAR目标识别的深度卷积神经网络结构设计[J].中国图象图形学报, 2018, 23(6):928-936. [DOI:10.11834/jig.170473]
Du K N, Deng Y K, Wang R, et al. SAR ATR based on displacement and rotation-insensitive CNN[J]. Remote Sensing Letters, 2016, 7(9):895-904.[DOI:10.1080/2150704X.2016.1196837]
Cheng G, Zhao W, Pan J F. Research on MSTAR SAR Target Recognition Based on Wavelet Analysis and Support Vector Machine[J]. Journal of Image and Graphics, 2009, 14(2):317-322.
成功, 赵巍, 潘锦峰.基于小波分解和支持向量机的MSTAR SAR目标分类识别研究[J].中国图象图形学报, 2009, 14(2):317-322. [DOI:10.11834/jig.20090219]
Huang G, Liu Z, Maaten L V, et al. Densely connected convolutional networks[C]//Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu, Hawaii, USA: IEEE, 2017: 2261-2269.[ DOI: 10.1109/CVPR.2017.243 http://dx.doi.org/10.1109/CVPR.2017.243 ]
相关作者
相关机构
京公网安备11010802024621
