SAR变体目标识别的卷积神经网络法  

SAR target recognition with variants based on convolutional neural network

作　　者：冯秋晨 彭冬亮[1] 谷雨[1] Feng Qiuchen;Peng Dongliang;Gu Yu(Fundamental Science on Communication Information Transmission and Fusion Technology Laboratory,Hangzhou Dianzi University,Hangzhou 310018,China)

机构地区：[1]杭州电子科技大学通信信息传输与融合技术国防重点学科实验室,杭州310018

出　　处：《中国图象图形学报》2019年第2期258-268,共11页Journal of Image and Graphics

基　　金：国家自然科学基金项目(61673146)~~

摘　　要：目的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。方法设计网络主要由多尺度空间特征提取模块和Dense Net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Dense Net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 Deep learning has been widely used in the field of synthetic aperture radar( SAR)target recognitionand most studies have been conducted for target recognition under the standard operating conditions( SOCs)of MSTARdatasets.Many challenges exist due to the small differences among the targets when applied to target recognition with vari-ants,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 The proposed network is composedof one multiscale feature extraction module and several dense blocks and transition layers proposed in Dense Net.The multi-scale feature extraction module,which is placed at the bottom of the network,uses multiple convolution kernels with sizesof 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 SoftM ax 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 TensorF low 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

关 键 词：SAR目标识别 变体目标 深度学习 多尺度特征 DenseNet 

分 类 号：TP753[自动化与计算机技术—检测技术与自动化装置]