基于角度内插仿真的飞机目标多角度SAR数据集构建方法研究  

Multiangle SAR Dataset Construction of Aircraft Targets Based on Angle Interpolation Simulation

作　　者：王汝意 张汉卿 韩冰 张月婷[1,2,3] 郭嘉逸 洪文[1,2,3] 孙巍 胡文龙 WANG Ruyi;ZHANG Hanqing;HAN Bing;ZHANG Yueting;GUO Jiayi;HONG Wen;SUN Wei;HU Wenlong(Aerospace Information Research Institute,Chinese Academy of Sciences,Beijing 100190,China;Key Laboratory of Technology in Geo-spatial Information Processing and Application System,Beijing 100190,China;School of Electronic,Electrical and Communication Engineering,University of Chinese Academy of Sciences,Beijing 100049,China)

机构地区：[1]中国科学院空天信息创新研究院,北京100190 [2]中国科学院空间信息处理与应用系统技术重点实验室,北京100190 [3]中国科学院大学电子电气与通信工程学院,北京100049

出　　处：《雷达学报（中英文）》2022年第4期637-651,共15页Journal of Radars

基　　金：国家自然科学基金(61431018)。

摘　　要：随着SAR技术应用领域的扩大以及SAR数据获取技术的发展,构建各种典型目标的多角度SAR数据集的需求日益迫切。针对飞机目标,目前尚未有比较完备的多角度SAR图像数据集。该文探索了一种基于实测数据和智能仿真相结合的数据集构建方法,通过飞行试验采集飞机目标SAR多角度数据,并基于散射分析和自注意力生成对抗网络实现特定角度的SAR图像内插仿真,从而为数据集构建和扩容提供新的解决方案。最后,在假定部分数据缺失的情况下,通过6种评价指标对仿真图像和实际采集图像的相似度进行了评价,验证了所提方法的有效性。With the expansion of Synthetic Aperture Radar(SAR)applications and the development of SAR data acquisition technology,multiangle SAR datasets of various typical targets need to be constructed.Presently,a comprehensive multiangle SAR image dataset for aircraft targets is still lacking.This study explores a method of dataset construction based on the acquisition of actual data and intelligent simulation.Multiangle SAR images of aircraft targets are collected through flight tests,and the interpolation simulations of SAR images of specific angles are realized based on scattering analysis and self-attention generative adversarial network,which provide a new solution for dataset construction and expansion.Finally,under the assumption that some data are missing,the similarities between the simulated and actual images are evaluated using six evaluation indices,which verify the effectiveness of the proposed method.

关 键 词：数据集构建 飞机目标 图像仿真 生成对抗网络 自注意力 

分 类 号：TN959[电子电信—信号与信息处理]