The haze in remote sensing images can cause the decline of image quality and bring many obstacles to the applications of remote sensing images. Considering the non-uniform distribution of haze in remote sensing images, we propose a single remote sensing image dehazing method based on the encoder–decoder architecture, which combines both wavelet transform and deep learning technology. To address the clarity issue of remote sensing images with non-uniform haze, we preliminary process the input image by the dehazing method based on the atmospheric scattering model, and extract the first-order low-frequency sub-band information of its 2D stationary wavelet transform as an additional channel. Meanwhile, we establish a large-scale hazy remote sensing image dataset to train and test the proposed method. Extensive experiments show that the proposed method obtains greater advantages over typical traditional methods and deep learning methods qualitatively. For the quantitative aspects, we take the average of four typical deep learning methods with superior performance as a comparison object using 500 random test images, and the peak-signal-to-noise ratio (PSNR) value using the proposed method is improved by 3.5029 dB, and the structural similarity (SSIM) value is improved by 0.0295, respectively. Based on the above, the effectiveness of the proposed method for the problem of remote sensing non-uniform dehazing is verified comprehensively.

Different from the ground image with uniform haze, the haze in remote sensing (RS) image has the characteristics of irregular shape and uneven concentration in hazy weather. It brings a great challenge to the application of RS image data in advanced image processing tasks. A novel dehazing network for non-uniform hazy remote sensing image, named as KFA-Net, is proposed to solve the aforementioned issues. The designed asymmetric size feature cascade (ASFC), k-means pixel attention (KPA) and FFT channel attention (FCA) in KFA-Net all show excellent effects. Compared with symmetrically linked typical Unet, ASFC can more easily extract shallow features for feature reconstruction. Furthermore, different from the commonly used pixel attention that compresses feature maps directly, KPA introduces k-means clustering algorithm in machine learning into the attention mechanism, which facilitates network training to focus on the thick hazy region. Compared to typical squeeze-and-excitation block, FCA uses the low-frequency region feature of spectrogram to obtain the attention weight coefficient in the frequency domain, making network training pay more attention to the feature of image low-frequency region. Extensive comparison experiments verify that the proposed KFA-Net has the great superiority. PSNR/SSIM of KFA-Net are 31.0952% and 6.6401% higher than DCP with the highest citation in traditional dehazing methods, respectively. PSNR/SSIM of KFA-Net are 2.2049% and 0.4966% higher than the recently proposed 4KDehazing with the best performance among all comparison dehazing methods, respectively. The KFA-Net proposed in this research can greatly enhance the temporal and spatial scope of RS image application in hazy weather conditions.

Target detection technology has been greatly improved for the synthetic aperture radar (SAR) images recently, due to the advancement in deep learning (DL) domain. However, because of the existence of clutter in the SAR images, it's still a challenge to detect small targets with high accuracy and low computational complexity. To solve this problem, a detection algorithm based on feature fusion and cross-layer connection (FFCLC) network is proposed in this paper. Firstly, the attention feature fusion (AFF) is applied to improve the feature fusion ability for the small targets through allocating weights to various feature maps adaptively. Meanwhile, the depthwise separable convolution (DW-Conv) is used to reduce the computational complexity caused by the increasement of network layers. Then, a cross-layer connection (Cross-Connect) submodule is proposed to fuse shallow features with deep features further. Finally, a multi-scale target detection (Multi-Detect) submodule is designed to improve the detection ability for the small targets. We compare the proposed algorithm with the other representative methods on the SAR-Ship-Dataset and SSDD, quantitative evaluations show that our proposed algorithm's can reach the highest computational efficiency. Therefore, because of the superior performance in terms of accuracy and efficiency, the algorithm proposed in this paper is more suitable to detect small targets for the SAR images.

High-quality remote sensing images play important roles in the development of ecological indicators’ mapping, urban-rural management, urban planning, and other fields. Compared with natural images, remote sensing images have more abundant land cover along with lower spatial resolutions. Given the embedded longitude and latitude information of remote sensing images, reference (Ref) images with similar scenes could be more accessible. However, existing traditional super-resolution (SR) approaches always depend on increases in network depth to improve performance, which limits the acquisition and application of high-quality remote sensing images. In this paper, we proposed a novel, reference-image-based, super-resolution method with feature compression module (FCSR) for remote sensing images to alleviate the above issue while effectively utilizing high-resolution (HR) information from Ref images. Specifically, we exploited a feature compression branch (FCB) to extract relevant features in feature detail matching with large measurements. This branch employed a feature compression module (FCM) to extract features from low-resolution (LR) and Ref images, which enabled texture transfer from different perspectives. To decrease the impact of environmental factors such as resolution, brightness and ambiguity disparities between the LR and Ref images, we designed a feature extraction encoder (FEE) to ensure accuracy in feature extraction in the feature acquisition branch. The experimental results demonstrate that the proposed FCSR achieves significant performance and visual quality compared to state-of-the-art SR methods. Explicitly, when compared with the best method, the average peak signal-to-noise ratio (PSNR) index on the three test sets is improved by 1.0877%, 0.8161%, 1.0296%, respectively, and the structural similarity (SSIM) index on four test sets is improved by 1.4764%, 1.4467%, 0.0882%, and 1.8371%, respectively. Simultaneously, FCSR obtains satisfactory visual details following qualitative evaluation.

Remote sensing images are very vulnerable to cloud interference during the imaging process. Cloud occlusion, especially thick cloud occlusion, significantly reduces the imaging quality of remote sensing images, which in turn affects a variety of subsequent tasks using the remote sensing images. The remote sensing images miss ground information due to thick cloud occlusion. The thick cloud removal method based on a temporality global–local structure is initially suggested as a solution to this problem. This method includes two stages: the global multi-temporal feature fusion (GMFF) stage and the local single-temporal information restoration (LSIR) stage. It adopts the fusion feature of global multi-temporal to restore the thick cloud occlusion information of local single temporal images. Then, the featured global–local structure is created in both two stages, fusing the global feature capture ability of Transformer with the local feature extraction ability of CNN, with the goal of effectively retaining the detailed information of the remote sensing images. Finally, the local feature extraction (LFE) module and global–local feature extraction (GLFE) module is designed according to the global–local characteristics, and the different module details are designed in this two stages. Experimental results indicate that the proposed method performs significantly better than the compared methods in the established data set for the task of multi-temporal thick cloud removal. In the four scenes, when compared to the best method CMSN, the peak signal-to-noise ratio (PSNR) index improved by 2.675, 5.2255, and 4.9823 dB in the first, second, and third temporal images, respectively. The average improvement of these three temporal images is 9.65%. In the first, second, and third temporal images, the correlation coefficient (CC) index improved by 0.016, 0.0658, and 0.0145, respectively, and the average improvement for the three temporal images is 3.35%. Structural similarity (SSIM) and root mean square (RMSE) are improved 0.33% and 34.29%, respectively. Consequently, in the field of multi-temporal cloud removal, the proposed method enhances the utilization of multi-temporal information and achieves better effectiveness of thick cloud restoration.

Remarkable strides have been made in super-resolution methods based on deep learning for hyperspectral images (HSIs), which are capable of enhancing the spatial resolution. However, these methods predominantly focus on capturing local features using convolutional neural networks (CNNs), neglecting the comprehensive utilization of global spatial-spectral information. To address this limitation, we innovatively propose a Multi-scale Spatial-spectral CNN-transformer network for Hyperspectral image Super Resolution, namely MSHSR. MSHSR not only applies the local spatial-spectral characteristics but also innovatively facilitates the collaborative exploration and application of spatial details and spectral data globally. Specifically, we first design a multi-scale spatial-spectral fusion module (MSSFM), which integrates dilated-convolution parallel branches (DPB) and a hybrid spectral attention mechanism (HSAM) to address the strong local correlations in HSIs, effectively capturing and fusing multi-scale local spatial-spectral information. Furthermore, in order to fully exploit the global contextual consistency in HSIs, we introduce a sparse spectral transformer module (SSTM). This module processes the previously obtained local spatial-spectral features, thoroughly exploring the elaborate global inter-relationship and long-range dependencies among different spectral bands through a coarse-to-fine strategy. Extensive experimental results on three hyperspectral datasets demonstrate the superior performance of our method, outperforming comparison methods both in quantitative metrics and visual performance.