Cloud contamination greatly limits the potential utilization of optical images for geoscience applications. An effective alternative is to extract data from synthetic aperture radar (SAR) images to remove clouds due to the strong penetration ability of microwaves. In this article, we propose a novel unified spatial–spectral residual network that utilizes SAR images as auxiliary data to remove clouds from optical images. The method can better establish the relationship between SAR and optical images and be divided into two modules: feature extraction and fusion module and reconstruction module. In the feature extraction and fusion module, a gated convolutional layer is introduced to discriminate cloud pixels from clean pixels, which makes up for the lack of distinguishing ability of vanilla convolutional layers and avoids the error of cloud areas in feature extraction. In the reconstruction module, spatial and channel attention mechanisms are introduced to obtain global spatial and spectral information. The network is tested on three datasets with different spatial resolutions and compositions of land covers to verify the effectiveness and applicability of the method. The results show that the method outperforms other mainstream algorithms that simultaneously use SAR images as auxiliary data with a gain of about 2.3 dB in terms of peak signal-to-noise ratio PSNR on the SEN12MS-CR dataset.

Single-image super-resolution (SISR) for high-resolution (HR) remote sensing image (RSI) acquisition is becoming increasingly valuable and important, and convolutional neural networks (CNNs) have produced considerable progress in this field. In RSIs, many similar geo-objects recur within the same scene, maintaining the same positions in both low resolution (LR) and HR. Based on this observation, we found that these similar geo-objects could be utilized to reconstruct texture details in LR by exploiting the consistent non-local relationships between these geo-objects in LR and HR, thereby improving the quality of SISR. Therefore, we propose a novel graph convolutional network (GCN) for SISR including a dynamic graph attention mechanism to learn the in-scale and cross-scale non-local features of RSIs. In scale, we propose a dynamic graph attention block (DGAB) that adaptively determines non-local patches upon the scene correlation derived from RSIs and further fuses patch-wise non-local information weighed by the attention scores of topological relationships and radiation characteristics in RSIs. Across different scales, we also introduce a dynamic graph attention mixing block (DGAMB) to upsample LR non-local information to HR non-local information. Most SISR methods have the upsampling blocks at the end of the network, ignoring feature extraction in high-dimensional space. To address this problem, DGAMB was designed as an upsampler in the middle of the model, enhancing the level of high-dimensional information extraction from the model. The experiments based on the WHU Building and UC Merced datasets show that our proposed method outperforms state-of-the-art methods. Our code is available athttps://github.com/WenjuanZhang-aircas/NSGCN.

Full-spectrum remote sensing images can simultaneously provide reflectance and emission information about objects, which has great application value. Hyperspectral imaging can record hundreds of spectral bands, but due to technical and space limitations, full-spectrum hyperspectral images (HSI) are difficult to obtain. Recently, we proposed a spectral super-resolution method based on the Linear Spectral Mixing Model (LSMM), which can generate full-spectrum hyperspectral images (HSI) from multispectral images (MSI). After the spectral-unmixing of MSI, we transform MS endmembers into full-spectrum HS endmembers by spectral library. Since the abundance of MSI and HSI with the same spatial resolution is consistent, we linearly mixed the abundance and HS endmember to obtain the full spectrum HSI. In this work, we use Sentinel-2 dataset and EO-1 ALI/Hyperion images to verify the accuracy and applicability. Compared with other works, our method can simulate full-spectrum HSI of large-area scenes without real HSI, which has a certain accuracy and provides more comprehensive information for applications.

Cloud cover is a common problem in optical satellite imagery, which leads to missing information in images. To rapidly acquire noncloud images, we design a cloud removal method to recover single-temporal remote sensing image based on land cover data which is easier to obtain than multitemporal data. Considering that the same features have the same radiation characteristics, we extract the similar pixels from same category around the missing pixels and calculate the value of missing pixels according to the distance weights of these pixels. The performance of the proposed method was evaluated on MODIS images and Landsat images and the results also prove that universal applicability of this algorithm in different resolutions and surface contents.

Single image super-resolution (SISR) algorithm is to recover a high-resolution image from a single low-resolution one and has been widely applied in remote sensing (RS) reconstruction. Numerous SISR models have been proposed for RS ap-plications. However, most existing methods suffer from an inability to reconstruct multi-scale RS images using one fixed pre-trained model. Here, we design a scale-adaptive SISR algorithm for RS images. The main contributions are three-fold: (1) to be applied for the multi-scale reconstruction, we first employ the bicubic interpolation to stretch the images before import so that our convolutional neural network can focus on refining the details of reconstruction images; (2) to extract the deep information of ground surface from RS images, we design multi-scale residual network to recover the image details; (3) we adopt the least-absolute-error loss to constraint our network for reconstructing the RS images. It is demonstrated that our model achieves excellent performance for super-resolution of RS images.

Cloud detection is an important task in remote sensing (RS) image processing. Numerous cloud detection algorithms have been developed. However, most existing methods suffer from the weakness of omitting small and thin clouds, and from an inability to discriminate clouds from photometrically similar regions, such as buildings and snow. Here, we derive a novel cloud detection algorithm for optical RS images, whereby test images are separated into three classes: thick clouds, thin clouds, and noncloudy. First, a simple linear iterative clustering algorithm is adopted that is able to segment potential clouds, including small clouds. Then, a natural scene statistics model is applied to the superpixels to distinguish between clouds and surface buildings. Finally, Gabor features are computed within each superpixel and a support vector machine is used to distinguish clouds from snow regions. The experimental results indicate that the proposed model outperforms state-of-the-art methods for cloud detection.

Most of the existing image blurriness assessment algorithms are proposed based on measuring image edge width, gradient, high-frequency energy, or pixel intensity variation. However, these methods are content sensitive with little consideration of image content variations, which causes variant estimations for images with different contents but same blurriness degrees. In this paper, a content-insensitive blind image blurriness assessment metric is developed utilizing Weibull statistics. Inspired by the property that the statistics of image gradient magnitude (GM) follows Weibull distribution, we parameterize the GM using$\beta$(scale parameter) and$\gamma$(shape parameter) of Weibull distribution. We also adopt skewness ($\eta$) to measure the asymmetry of the GM distribution. In order to reduce the influence of image content and achieve more robust performance, divisive normalization is then incorporated to moderate the$\beta$,$\gamma$, and$\eta$. The final image quality is predicted using a sparse extreme learning machine. Performances evaluation on the blur image subsets in LIVE, CSIQ, TID2008, and TID2013 databases demonstrate that the proposed method is highly correlated with human perception and robust with image contents. In addition, our method has low computational complexity which is suitable for online applications.