| 152 | 1 | 36 |
| 下载次数 | 被引频次 | 阅读次数 |
遥感影像的云修复是改善影像质量、降低数据成本的一种重要手段。使用Landsat 8影像研究卷积神经网络在云修复中的应用，提出一种影像信息重建的新式网络结构——边缘辅助的门控卷积网络（edge-guided gated convolutional network,EGCN）。该网络以多时相数据作为含云影像上被遮挡信息的辅助数据，主干网络为多时空门控卷积网络（spatial-temporal based gated convolutional network,STGCN），在多尺度特征融合模块引入一种改进的非局部（non-local,NL）模块——门控非局部（gated non-local,GNL）来替代传统的卷积层，并以边缘特征提取网络（edge network,ENet）为分支，从边缘信息层面进行特征引导。实验结果表明，GNL模块和ENet的加入均有助于提升云修复效果。
Abstract：Cloud removal of remote sensing images is one of the important technologies to improve data quality and reduce data cost. A novel network structure to reconstruct missing information in images, which is called edge-guided gated convolutional network(EGCN), is put forward via the applications of convolutional neural network in cloud removal task using Landsat 8 images. This network uses multi-temporal data as auxiliary data for padding cloudy images. Spatial-temporal based gated convolutional network(STGCN) is used as the main trunk and an improved non-local(NL) block called gated non-local(GNL) is introduced to replace the traditional convolution layers. Besides, an edge network(ENet) is used as a branch to guide the feature from the edge information level.The experimental results show that GNL and ENet both benefit cloud removal task.
[1] Cihlar J, Howarth J. Detection and Removal of Cloud Contamination from AVHRR Images[J]. IEEE Trans Geoscience and Remote Sensing, 1994, 32(3):583-589
[2] Shuai T, Zhang X, Wang S D, et al. A Spectral Angle Distance-Weighting Reconstruction Method for Filled Pixels of the MODIS Land Surface Temperature Product[J]. IEEE Geoscience and Remote Sensing Letters,2014, 11(9):1 514-1 518
[3] Cheng Q, Shen H F, Zhang L P, et al. Inpainting for Remotely Sensed Images with a Multichannel Nonlocal Total Variation Model[J]. IEEE Transactions on Geoscience and Remote Sensing, 2014, 52(1):175-187
[4] Lin C H, Lai K H, Chen Z B, et al. Patch-Based Information Reconstruction of Cloud-Contaminated Multitemporal Images[J]. IEEE Transactions on Geoscience and Remote Sensing, 2014, 52(1):163-174
[5] Gao G M, Gu Y F. Multitemporal Landsat Missing Data Recovery Based on Tempo-Spectral Angle Model[J]. IEEE Transactions on Geoscience and Remote Sensing, 2017, 55(7):3 656-3 668
[6] Chen B, Huang B, Chen L F, et al. Spatially and Temporally Weighted Regression:A Novel Method to Produce Continuous Cloud-Free Landsat Imagery[J].IEEE Transactions on Geoscience and Remote Sensing,2017, 55(1):27-37
[7] Zhang C Y, Li Z W, Cheng Q, et al. Cloud Removal by Fusing Multi-source and Multi-temporal Images[C].IEEE International Geoscience and Remote Sensing Symposium, Fort Worth, TX, USA, 2017
[8] Li W B, Li Y, Chan J C W. Thick Cloud Removal with Optical and SAR Imagery via Convolutional-Mapping-Deconvolutional Network[J]. IEEE Transactions on Geoscience and Remote Sensing, 2020, 58(4):2 865-2 879
[9] Zeng C, Shen H F, Zhang L P. Recovering Missing Pixels for Landsat ETM+SLC-off Imagery Using Multi-temporal Regression Analysis and a Regularization Method[J]. Remote Sensing of Environment,2013, 131:182-194
[10] Zhang Q, Yuan Q Q, Zeng C, et al. Missing Data Reconstruction in Remote Sensing Image with a Unified Spatial-Temporal-Spectral Deep Convolutional Neural Network[J]. IEEE Transactions on Geoscience and Remote Sensing, 2018, 56(8):4 274-4 288
[11] Malek S, Melgani F, Bazi Y, et al. Reconstructing Cloud-Contaminated Multispectral Images with Contextualized Autoencoder Neural Networks[J]. IEEE Transactions on Geoscience and Remote Sensing,2018, 56(4):2 270-2 282
[12] Enomoto K, Sakurada K, Wang W M, et al. Filmy Cloud Removal on Satellite Imagery with Multispectral Conditional Generative Adversarial Nets[C]. IEEE Conference on Computer Vision and Pattern Recognition Workshops, Honolulu, HI, USA, 2017
[13] Singh P, Komodakis N. Cloud-Gan:Cloud Removal for Sentinel-2 Imagery Using a Cyclic Consistent Generative Adversarial Networks[C]. IEEE International Geoscience and Remote Sensing Symposium,Valencia, Spain, 2018
[14] Zhang R, Xie F Y, Chen J J. Single Image Thin Cloud Removal for Remote Sensing Images Based on Conditional Generative Adversarial Nets[C]. Tenth International Conference on Digital Image Processing, Shanghai,China, 2018
[15] Dai P Y, Ji S P, Zhang Y J. Gated Convolutional Networks for Cloud Removal from Bi-temporal Remote Sensing Images[J]. Remote Sensing, 2020, 12(20):3427
[16] Ronneberger O, Fischer P, Brox T. U-Net:Convolutional Networks for Biomedical Image Segmentation[C]. Medical Image Computing and Computer-Assisted Intervention, Munich, Germany, 2015
基本信息:
DOI：10.14188/j.2095-6045.2022140
中图分类号:TP183;TP751;P237
引用信息:
[1]张雨姝,戴佩玉.一种边缘辅助的卫星影像云修复卷积神经网络[J].测绘地理信息,2024,49(02):81-86.DOI:10.14188/j.2095-6045.2022140.
基金信息:
国家自然科学基金（41471288）
2024-03-09
2024-03-09
2024-03-09