基于全局-局部判别GAN的天空偏振图像修复方法
DOI:
CSTR:
作者:
作者单位:

1.太原科技大学 电子信息工程学院 山西 太原;2.太原工业学院 理学系 山西 太原

作者简介:

通讯作者:

中图分类号:

基金项目:

国家自然科学基金青年基金;山西省基础研究计划面上项目;山西省科技创新人才团队;山西省科技合作交流专项;山西省科技成果转化引导专项


Sky Polarization Image Inpainting Method Based on Global-Local Discriminative GAN
Author:
Affiliation:

1.School of Electronics Information Engineering,Taiyuan University of Science Technology,Taiyuan, China;2.Department of Science,Taiyuan Institute of Technology,Taiyuan, China

Fund Project:

  • 摘要
  • |
  • 图/表
  • |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • |
  • 引证文献
  • |
  • 资源附件
  • |
  • 文章评论
    摘要:

    偏振图像复原是保障偏振光导航定向精度的关键前提。现有研究多关注云层遮挡对偏振信息的影响与修复,对建筑物等不透明硬质遮挡导致的偏振信息完全缺失问题重视不足。传统图像修复方法在硬遮挡场景下易出现边缘模糊、纹理失真等问题。为此,本文提出一种基于生成对抗网络(GAN)的天空偏振图像修复方法。该方法采用兼顾全局与局部特征的上下文判别器,训练中融合均方误差(MSE)重建损失、感知损失与边缘保真损失,并采用分步训练策略以提升生成器优化效果。实验结果表明,在建筑物遮挡条件下,所提方法可恢复出纹理细节丰富、过渡自然平滑的偏振图像;航向角均值误差由4.12°降至1.46°,方向定位精度提升约64.7%。该方法能有效恢复被建筑物遮挡区域的天空偏振特征,为复杂遮挡环境下生物启发式偏振导航提供可靠的图像预处理支撑。

    Abstract:

    Polarization image restoration is a critical prerequisite for ensuring the orientation accuracy of polarized light navigation. Most existing studies focus on the influence and restoration of polarization information caused by cloud occlusion, while insufficient attention has been paid to the complete loss of polarization information resulting from opaque hard occlusions such as buildings. Traditional image inpainting methods tend to suffer from edge blurring and texture distortion in hard occlusion scenarios. To address these problems, this paper proposes a sky polarization image inpainting method based on Generative Adversarial Network (GAN). The method adopts a context discriminator that takes both global and local features into account, integrates mean square error (MSE) reconstruction loss, perceptual loss and edge fidelity loss during training, and adopts a step-by-step training strategy to improve the optimization effect of the generator. Experimental results show that under building occlusion conditions, the proposed method can restore polarization images with rich texture details and natural and smooth transitions. The mean heading angle error is reduced from 4.12° to 1.46°, and the directional positioning accuracy is improved by approximately 64.7%. This method can effectively recover the sky polarization features in regions occluded by buildings, providing reliable image preprocessing support for bio-inspired polarized light navigation in complex occlusion environments.

    参考文献
    相似文献
    引证文献
引用本文
分享
相关视频

文章指标
  • 点击次数:
  • 下载次数:
  • HTML阅读次数:
  • 引用次数:
历史
  • 收稿日期:2026-07-21
  • 最后修改日期:2026-07-21
  • 录用日期:2026-08-19
  • 在线发布日期:
  • 出版日期:
文章二维码