• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>IEEE Geoscience and Remote Sensing Letters >Cloud-Aware Generative Network: Removing Cloud From Optical Remote Sensing Images
【24h】

Cloud-Aware Generative Network: Removing Cloud From Optical Remote Sensing Images

机译：云感知生成网络：从光学遥感图像中移除云

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

In the optical remote sensing and earth observation fields, clouds severely obscure the land's visibility and degrade the image. In recent years, there have been many excellent efforts to mitigate the effects of cloud cover. However, it has been found that there will be some blurs in the area if a single degraded image is restored by autoencoder-based methods. This letter focuses on removing clouds from single optical remote sensing images by autoencoder-based methods without multitemporal information while at the same time mitigating blurs caused by missing information. Therefore, we propose a novel cloud removal method that combines image inpainting and image denoising, called the Cloud-Aware Generative Network (CAGN). The CAGN consists of two stages: the first stage is a recurrent convolution network for potential cloud region detection and the second is an autoencoder for cloud removal. The method uses a side-guided method that adds attention mechanisms in the first stage to assist in predicting the mask. Furthermore, to update the mask adaptively for restoring degraded image areas greedily, the method embeds partial convolution in the autoencoder to condition the convolution calculation of pixels in the regions of thick clouds at different layers. Extensive experiments demonstrate clearly that CAGN can easily achieve a considerable increase in the peak signal-to-noise ratio (PSNR) and the structural similarity index (SSIM) compared with a competitive baseline model.
机译：在光学遥感和地球观测领域，云严重掩盖了土地的可见性并降低了图像。近年来，有许多出色的努力来减轻云覆盖的影响。然而，已经发现，如果基于AutoEncoder的方法恢复了单个劣化的图像，则该区域将存在一些模糊。这封信侧重于通过基于AutoEncoder的方法从单一光远程感测图像中删除云，而无需多立体信息，同时由缺少信息引起的缓解模糊。因此，我们提出了一种新的云移除方法，该方法结合了图像染色和图像去噪，称为云感知生成网络（CAGN）。 CAGN由两个阶段组成：第一阶段是用于潜在云区域检测的反复卷积网络，第二级是用于云移除的AutoEncoder。该方法使用侧向导向的方法，该方法在第一阶段中增加注意机制，以帮助预测掩模。此外，为了使掩模更新贪婪地贪婪地恢复劣化的图像区域，该方法将AutoEncoder中的部分卷积嵌入到条件在不同层处的厚云区域中的像素的卷积计算。与竞争基线模型相比，广泛的实验表明CAGN可以容易地实现峰值信噪比（PSNR）和结构相似性指数（SSIM）的相当大的增加。

著录项

  • 来源
    《IEEE Geoscience and Remote Sensing Letters》 |2020年第4期|691-695|共5页
  • 作者

    Sun Linjian; Zhang Ye; Chang Xuling; Wang Yanjie; Xu Jiajia;

  • 作者单位

    Chinese Acad Sci Image Proc Dept Key Lab Airborne Opt Imaging & Measurement Changchun Inst Opt Fine Mech & Phys Changchun 130033 Peoples R China|Univ Chinese Acad Sci Coll Mat Sci & Optoelect Technol Beijing 100059 Peoples R China;

    Chinese Acad Sci State Key Lab Appl Opt Changchun Inst Opt Fine Mech & Phys Changchun 130033 Peoples R China|Changchun Spirits Technol Co Ltd AI Lab Changchun 130033 Peoples R China;

    Chinese Acad Sci State Key Lab Appl Opt Changchun Inst Opt Fine Mech & Phys Changchun 130033 Peoples R China|Changchun Spirits Technol Co Ltd AI Lab Changchun 130033 Peoples R China;

    Chinese Acad Sci Image Proc Dept Key Lab Airborne Opt Imaging & Measurement Changchun Inst Opt Fine Mech & Phys Changchun 130033 Peoples R China;

    Chinese Acad Sci State Key Lab Appl Opt Changchun Inst Opt Fine Mech & Phys Changchun 130033 Peoples R China|Changchun Spirits Technol Co Ltd AI Lab Changchun 130033 Peoples R China;

  • 收录信息
  • 原文格式 PDF
  • 正文语种 eng
  • 中图分类
  • 关键词

    Convolution; Remote sensing; Optical imaging; Optical sensors; Image reconstruction; Training; Attention mechanism; cloud detection; cloud removal; generative network; remote sensing;

    机译：卷积;遥感;光学成像;光学传感器;图像重建;训练;注意机制;云检测;云移除;生成网络;遥感;遥感;

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号