ISSN 0253-2778

CN 34-1054/N

open
Free to Publish. Free to Read.
Open AccessOpen Access JUSTC Original Paper

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

  • Institute of Automation, Chinese Academy of Sciences, Beijing 100080, China

Cite this:
https://doi.org/10.3969/j.issn.0253-2778.2020.08.019
  • Received Date: 15 July 2020
  • Accepted Date: 18 August 2020
  • Rev Recd Date: 18 August 2020
  • Publish Date: 31 August 2020
    Abstract

  • 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.

    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.
    • FullText(HTML)
  • loading
    • References(20)
  • [1]
    黄佳琦,祝明波,侯建国,董巍,邹建武.两种海面舰船SAR图像仿真方法对比[J].雷达科学与技术,2015,13(02):149-153.
    HUANG J Q, ZHU M B, HOU J G, et al. Comparison between two methods for SAR imaging simulation of ships and sea background[J]. Radar Science and Technology, 2015, 13(02):149-153.
    [2]
    董刚刚.基于单演信号的SAR图像目标识别技术研究[D].合肥:国防科学技术大学,2016.
    [3]
    杨俊涛.基于分数谱时频特征的SAR目标检测与识别方法研究[D].成都:电子科技大学,2014.
    [4]
    王少娜.基于稀疏特征学习的SAR图像目标识别和变化检测[D].西安:西安电子科技大学,2016.
    [5]
    陈玉洁. SAR图像飞机目标分类识别技术研究[D]. 合肥:国防科学技术大学,2016.
    [6]
    贺丰收,何友,刘准钆,徐从安.卷积神经网络在雷达自动目标识别中的研究进展[J].电子与信息学报,2020,42(01):119-131.
    [7]
    胡显,姚群力,侯冰倩,等.基于卷积神经网络的合成孔径雷达图像目标识别[J].科学技术与工程,2019,19(21):228-232.
    [8]
    米野. 基于生成对抗网络的雷达图像增强技术研究[D]. 北京:北京邮电大学,2019.
    [9]
    王雷雷. 基于GAN的SAR图像生成研究[D]. 成都:电子科技大学,2019.
    [10]
    祝明波,黄佳琦,侯建国,等.舰船及其海面背景SAR成像模拟研究综述[J].航天电子对抗,2014,30(04):15-17.
    [11]
    XU F, JIN Y Q. Imaging simulation of polarimetric SAR for a comprehensive terrain scene using the mapping and projection algorithm[J]. IEEE Transactions on Geoscience& Remote Sensing, 2006, 44(11):3219-3234.
    [12]
    陈权,李震,魏小兰.基于几何特性和辐射特性的HJ-1 C星SAR图像模拟[J].遥感学报，2006, 10(5):722-726.
    [13]
    陈杰，周荫清，李春升.星载SAR自然地面场景仿真方法研究[J].电子学报, 2001, 29(9):1202-1205.
    [14]
    贺召卿,张冰尘,詹学丽,李建雄.利用机SAR图像仿真星载SAR图像[J].现代雷达, 2006(06):4-7.
    [15]
    李仁杰,计科峰,邹焕新,周石琳.基于电磁散射特性计算的目标SAR图像仿真[J].雷达科学与技术,2010,8(05):395-400.
    [16]
    董纯柱,胡利平,朱国庆,殷红成.地面车辆目标高质量SAR图像快速仿真方法[J].雷达学报,2015,4(03):351-360.
    [17]
    夏伟杰. 合成孔径雷达回波仿真与图像模拟[D].南京:南京航空航天大学,2010.
    [18]
    刁桂杰,许小剑,倪虹,路军杰.舰船目标宽带单脉冲雷达三维成像建模与仿真[J].系统仿真学报,2018,30(07):2515-2524.
    [19]
    KARRAS T, LAINE S, AILA T. A Style-Based Generator Architecture for Generative Adversarial Networks[C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, 2019.
    [20]
    ZHU J Y, PARK T, ISOLA P, et al. Unpaired image-to-image translation using cycle-consistent adversarial networks[J]. IEEE, 2017.
    • Supplements(0)
    • Related Articles
    • Track Citations
  • 加载中

Catalog

    |
    Get Citation
    PDF
    XML
    [1]
    黄佳琦,祝明波,侯建国,董巍,邹建武.两种海面舰船SAR图像仿真方法对比[J].雷达科学与技术,2015,13(02):149-153.
    HUANG J Q, ZHU M B, HOU J G, et al. Comparison between two methods for SAR imaging simulation of ships and sea background[J]. Radar Science and Technology, 2015, 13(02):149-153.
    [2]
    董刚刚.基于单演信号的SAR图像目标识别技术研究[D].合肥:国防科学技术大学,2016.
    [3]
    杨俊涛.基于分数谱时频特征的SAR目标检测与识别方法研究[D].成都:电子科技大学,2014.
    [4]
    王少娜.基于稀疏特征学习的SAR图像目标识别和变化检测[D].西安:西安电子科技大学,2016.
    [5]
    陈玉洁. SAR图像飞机目标分类识别技术研究[D]. 合肥:国防科学技术大学,2016.
    [6]
    贺丰收,何友,刘准钆,徐从安.卷积神经网络在雷达自动目标识别中的研究进展[J].电子与信息学报,2020,42(01):119-131.
    [7]
    胡显,姚群力,侯冰倩,等.基于卷积神经网络的合成孔径雷达图像目标识别[J].科学技术与工程,2019,19(21):228-232.
    [8]
    米野. 基于生成对抗网络的雷达图像增强技术研究[D]. 北京:北京邮电大学,2019.
    [9]
    王雷雷. 基于GAN的SAR图像生成研究[D]. 成都:电子科技大学,2019.
    [10]
    祝明波,黄佳琦,侯建国,等.舰船及其海面背景SAR成像模拟研究综述[J].航天电子对抗,2014,30(04):15-17.
    [11]
    XU F, JIN Y Q. Imaging simulation of polarimetric SAR for a comprehensive terrain scene using the mapping and projection algorithm[J]. IEEE Transactions on Geoscience& Remote Sensing, 2006, 44(11):3219-3234.
    [12]
    陈权,李震,魏小兰.基于几何特性和辐射特性的HJ-1 C星SAR图像模拟[J].遥感学报，2006, 10(5):722-726.
    [13]
    陈杰，周荫清，李春升.星载SAR自然地面场景仿真方法研究[J].电子学报, 2001, 29(9):1202-1205.
    [14]
    贺召卿,张冰尘,詹学丽,李建雄.利用机SAR图像仿真星载SAR图像[J].现代雷达, 2006(06):4-7.
    [15]
    李仁杰,计科峰,邹焕新,周石琳.基于电磁散射特性计算的目标SAR图像仿真[J].雷达科学与技术,2010,8(05):395-400.
    [16]
    董纯柱,胡利平,朱国庆,殷红成.地面车辆目标高质量SAR图像快速仿真方法[J].雷达学报,2015,4(03):351-360.
    [17]
    夏伟杰. 合成孔径雷达回波仿真与图像模拟[D].南京:南京航空航天大学,2010.
    [18]
    刁桂杰,许小剑,倪虹,路军杰.舰船目标宽带单脉冲雷达三维成像建模与仿真[J].系统仿真学报,2018,30(07):2515-2524.
    [19]
    KARRAS T, LAINE S, AILA T. A Style-Based Generator Architecture for Generative Adversarial Networks[C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, 2019.
    [20]
    ZHU J Y, PARK T, ISOLA P, et al. Unpaired image-to-image translation using cycle-consistent adversarial networks[J]. IEEE, 2017.
    Recommended articles
    TrendMD
    Volume 50 Issue 8 page: 1181-1186
    Cover

    Article Metrics

    Article views (75) PDF downloads(200)
    Proportional views

    Copyright © Editorial Office of JUSTC, All Rights Reserved. 皖ICP备05002528号

    Supported by: Beijing Renhe Information Technology Co. Ltd    

    /

    DownLoad:  Full-Size Img  PowerPoint
    Return
    Return