当前位置: X-MOL 学术GISci. Remote Sens. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Superpixel-based time-series reconstruction for optical images incorporating SAR data using autoencoder networks
GIScience & Remote Sensing ( IF 6.0 ) Pub Date : 2020-11-04 , DOI: 10.1080/15481603.2020.1841459
Ya’nan Zhou 1 , Xianzeng Yang 1 , Li Feng 1 , Wei Wu 2 , Tianjun Wu 3 , Jiancheng Luo 4, 5 , Xiaocheng Zhou 6 , Xin Zhang 4, 5
Affiliation  

ABSTRACT Time-series reconstruction for cloud/shadow-covered optical satellite images has great significance for enhancing the data availability and temporal change analysis. In this study, we proposed a superpixel-based prediction transformation-fusion (SPTF) time-series reconstruction method for cloud/shadow-covered optical images. Central to this approach is the incorporation between intrinsic tendency from multi-temporal optical images and sequential transformation information from synthetic aperture radar (SAR) data, through autoencoder networks (AE). First, a modified superpixel algorithm was applied on multi-temporal optical images with their manually delineated cloud/shadow masks to generate superpixels. Second, multi-temporal optical images and SAR data were overlaid onto superpixels to produce superpixel-wise time-series curves with missing values. Third, these superpixel-wise time series were clustered by an AE-LSTM (long short-term memory) unsupervised method into multiple clusters (searching similar superpixels). Four, for each superpixel-wise cluster, a prediction-transformation-based reconstruction model was established to restore missing values in optical time series. Finally, reconstructed data were merged with cloud-free regions to produce cloud-free time-series images. The proposed method was verified on two datasets of multi-temporal cloud/shadow-covered Landsat OLI images and Sentinel-1A SAR data. The reconstruction results, showing an improvement of greater than 20% in normalized mean square error compared to three state-of-the-art methods (including a spatially and temporally weighted regression method, a spectral–temporal patch-based method, and a patch-based contextualized AE method), demonstrated the effectiveness of the proposed method in time-series reconstruction for multi-temporal optical images.

中文翻译:

使用自动编码器网络对包含 SAR 数据的光学图像进行基于超像素的时间序列重建

摘要 云/阴影覆盖光学卫星图像的时间序列重建对于提高数据可用性和时间变化分析具有重要意义。在这项研究中,我们提出了一种基于超像素的预测变换融合(SPTF)时间序列重建方法,用于云/阴影覆盖的光学图像。这种方法的核心是通过自动编码器网络 (AE) 将多时态光学图像的内在趋势与合成孔径雷达 (SAR) 数据的顺序变换信息结合起来。首先,将修改后的超像素算法应用于具有手动描绘的云/阴影蒙版的多时相光学图像以生成超像素。第二,多时相光学图像和 SAR 数据叠加到超像素上,以生成具有缺失值的超像素级时间序列曲线。第三,这些超像素时间序列通过 AE-LSTM(长短期记忆)无监督方法聚类成多个集群(搜索相似的超像素)。四,对于每个超像素级簇,建立基于预测转换的重建模型来恢复光学时间序列中的缺失值。最后,重建数据与无云区域合并以生成无云时间序列图像。所提出的方法在多时相云/阴影覆盖的 Landsat OLI 图像和 Sentinel-1A SAR 数据的两个数据集上得到验证。重建结果,
更新日期:2020-11-04
down
wechat
bug