基于最小熵准则与生成对抗网络的SAR三维转动舰船目标重聚焦方法

Refocusing for Three-Dimensional Rotating Ship Targets in SAR Images Based on Minimum Entropy Criteria and Generative Adversarial Network

在合成孔径雷达(Synthetic Aperture Radar,SAR)系统中,舰船目标在中高海情下的三维转动会导致多普勒频谱时变和图像散焦,并对后续SAR舰船目标的信息解释造成不利影响.针对三维转动舰船目标的重聚焦问题,本文提出一种基于最小熵准则与生成对抗网络的SAR三维转动舰船目标重聚焦方法,设计了生成器和判别器的网络结构.生成器将散焦SAR舰船复图像变换到距离-多普勒域,利用相位误差系数估计网络逐距离单元估计相位误差系数,并实现对多阶次相位误差的补偿.判别器由一个复数域卷积神经网络构成,其所有元素,包括卷积层、激活函数、特征图和网络参数,均被扩展到复数域.损失函数中引入最小熵准则和对抗损失进行无监督训练,避免非合作舰船目标标注样本难以获取的问题.在仿真数据和高分三号SAR数据上的实验表明,该方法在重聚焦精度和效率上均有显著提升.

In synthetic aperture radar(SAR)system,the three-dimensional rotation of ship targets in the presence of a medium and high sea state would lead to time-varying Doppler spectrum and image defocusing,which will adversely affect the subsequent information interpretation of ship targets in SAR images.Aiming at the refocusing problem of three-dimen⁃sional rotating ship targets,this paper proposes a SAR refocusing method for three-dimensional rotating ship target based on minimum entropy criterion and generative adversarial network,and designs the network structure of generator and discrimi⁃nator.The generator transforms the defocused complex SAR ship image into range-Doppler domain,and estimates the phase error coefficient by range unit using phase error coefficient estimation network,and realizes the compensation of multi-order phase errors.The discriminator is composed of a complex-valued convolutional neural network,and all its ele⁃ments,including convolution layer,activation function,feature mapping and parameters,are extended to the complex do⁃main.The minimum entropy criterion and adversarial loss are introduced into the loss function to achieve unsupervised training and avoid the problem that it is difficult to obtain the target labeling samples of non-cooperative ships.Experiments on simulated data and Gaofen-3 data show that the proposed method achieves significant improvements in both refocusing accuracy and efficiency.