中国科学技术大学学报 ›› 2020, Vol. 50 ›› Issue (8): 1181-1186.DOI: 10.3969/j.issn.0253-2778.2020.08.019

• 论著 • 上一篇    下一篇

基于改进CycleGAN的合成孔径雷达图像仿真

白江波,杨阳,张文生   

  1. 中国科学院 自动化研究所,北京 100080
  • 收稿日期:2020-07-15 修回日期:2020-08-18 接受日期:2020-08-18 出版日期:2020-08-31 发布日期:2020-08-18
  • 通讯作者: 张文生
  • 作者简介:白江波,男,1994年生,工程师. 研究方向: 计算机视觉,生成式对抗网络,人工智能. E-mail: jiangbo.bai@ia.ac.cn
  • 基金资助:
    国家重点研发计划 (2019YFB2103103);NSFC-通用技术基础研究联合基金 (U1936206);国家自然科学基金面上项目 (61976213)资助.

A simulation of the synthetic aperture radar image based on improved CycleGAN

BAI Jiangbo, YANG Yang, ZHANG Wensheng   

  1. Institute of Automation, Chinese Academy of Sciences, Beijing 100080, China
  • Received:2020-07-15 Revised:2020-08-18 Accepted:2020-08-18 Online:2020-08-31 Published:2020-08-18

摘要: 目标和场景的跨模态数据对于以深度神经网络为基础的跨模态检测与多模态融合算法的性能提升有着极其重大的意义.由于SAR图像的特殊性,获得成对的数据集成本很高,且现有的SAR图像生成算法大多集中在提升图像多样性与小范围场景生成,对于特定场景的图像配对转化鲜有涉及.本文利用改进的循环一致性对抗网络CycleGAN实现SAR图像目标和场景的SAR图像的仿真,并利用最小二乘损失对网络进行改进,使网络性能获得提升,提高了成像的质量,论文所提方法对SAR图像进行了仿真实验,结果表明,本文方法生成图像的精细度与稳定度最优,实现了更好的仿真结果.

关键词: 循环一致性对抗网络, SAR图像仿真,深度残差网络,最小二乘生成对抗网络

Abstract: The cross-modal data of targets is of great significance to the improvement of the performance of cross-modal detection and multi-modal fusion algorithms based on deep neural networks. Due to the particularity of SAR images, the cost of obtaining paired data is very high, and most of the existing SAR image generation algorithms focus on improving image diversity and small-scale scene generation, and rarely involve image pairing conversion for specific scenes. In this paper, the improved cycle consistency against network CycleGAN is used to achieve the simulation of SAR images of SAR image targets and scenes, and the least square loss is used to improve the network, which improves the network performance and improves the imaging quality. The simulation experiment of SAR image is carried out. The results show that the method produced in this paper has the best fineness and stability, and achieves better simulation results.

Key words: CycleGAN, SAR image simulation, ResNet, LSGAN

中图分类号: