一种改进的U-Net相位解缠方法

An Improved U-Net Phase Unwrapping Method

针对合成孔径雷达干涉测量技术中的相位解缠问题,以深度学习U-Net框架为基础,结合空间金字塔池化(atrous spatial pyramid pooling,ASPP)网络和瓶颈模式残差单元,提出一种基于深度学习的相位解缠方法。该方法以U-Net架构为基础,建立从缠绕相位到真实相位的映射关系,搭建鲁棒性较强的相位解缠网络。ASPP结合多尺度信息和扩张卷积的优势,将不同扩张率的扩张卷积特征图结合到一起来捕获上下文信息,能在不牺牲特征空间分辨率的同时扩大特征接收野,有利于精确获取缠绕干涉图特征信息,增强相位解缠算法的稳健性;瓶颈残差网络可使网络模型在减小参数计算量的同时防止网络退化,提高网络训练精度与效率。模拟与实测干涉图解缠结果表明,该方法可获得与其他同类方法相比更稳健的结果。

Aiming at the problem of phase unwrapping in interferometric synthetic aperture radar,a phase unwrapping method based on deep learning is proposed by combining an atrous spatial pyramid pooling(ASPP)network,a bottleneck mode residual unit,and U-Net framework.This method builds a robust phase unwrapping network based on the U-Net architecture to establish the mapping relationship from the wrapped phase to the unwrapped phase.The ASPP combines the advantages of multi-scale information and dilated convolution,gathers feature maps with different dilation rates to capture rich contextual information,and expands the feature receiving field without sacrificing feature spatial resolution,which is conducive to obtain the characteristic information of the wrapping interferogram accurately,and enhance the robustness of the phase unwrapping network.The bottleneck residual unit can make the network model reduce the amount of parameter calculation while preventing network degradation,and improve the accuracy and efficiency of network training.The results obtained with simulated and measured data show that the proposed method can obtain more robust results,compared with other similar methods.