Low-light images have low brightness and contrast, which presents a huge obstacle to computer vision tasks. Low-light image enhancement is challenging because multiple factors (such as brightness, contrast, artifacts, and noise) must be considered simultaneously. In this study, we propose a neural network—a progressive-recursive image enhancement network (PRIEN)—to enhance low-light images. The main idea is to use a recursive unit, composed of a recursive layer and a residual block, to repeatedly unfold the input image for feature extraction. Unlike in previous methods, in the proposed study, we directly input low-light images into the dual attention model for global feature extraction. Next, we use a combination of recurrent layers and residual blocks for local feature extraction. Finally, we output the enhanced image. Furthermore, we input the global feature map of dual attention into each stage in a progressive way. In the local feature extraction module, a recurrent layer shares depth features across stages. In addition, we perform recursive operations on a single residual block, significantly reducing the number of parameters while ensuring good network performance. Although the network structure is simple, it can produce good results for a range of low-light conditions. We conducted experiments on widely adopted datasets. The results demonstrate the advantages of our method compared with other methods, from both qualitative and quantitative perspectives.

The absorption and scattering caused by the underwater medium degrade the quality of underwater optical imaging, which limits the further development of underwater tasks. Recently, transformer-based methods have shown the same excellent performance as convolutional neural networks (CNNs) in various vision tasks, but the huge parameters of such networks hinder their application deployment. In this article, we propose novel adaptive group attention (AGA), which can dynamically select visually complementary channels based on the dependencies, reducing the number of further attention parameters. The AGA is applied in the Swin Transformer module and used to design an end-to-end underwater image enhancement network. The network also introduces the multiscale cascade module and the channel attention mechanism. This article conducted ablation study and qualitative and quantitative comparisons on public datasets, and the results show that the application of AGA significantly compresses the model size while ensuring performance, and other application components have the significant gain on the network. Compared with other advanced methods, the network in this article has outstanding performance.

The pansharpening entails obtaining images with uniform spectral distribution and rich spatial details by fusing multispectral images and panchromatic images, which has become a major image fusion problem in the field of remote sensing. Convolutional neural networks are widely used in image processing. We propose a transformer-based regression network (DR-NET) architecture. The first stage was feature extraction, which entailed extracting spectral information and spatial details from multispectral images and panchromatic images. The second stage was feature fusion, which entailed integrating the extracted feature information. In the third stage, image reconstruction, images with uniform distribution of spectral information, and sufficient spatial details were obtained. The fourth stage entailed optimizing the network performance and calculating the loss of shallow feature image and the image result after downsampling during image reconstruction. The performance of the DR-NET was optimized by optimizing the sum of all the loss values, which could be considered double regression. Simulated and real data experiments were conducted on the GF-2, QuickBird, and WorldView2 datasets to compare the proposed method with classical pansharpening methods. The qualitative and quantitative analyses proved that the spectral distribution of the image pansharpened using our method was uniform, the spatial details were completely retained, and the evaluation indicators were also optimal, which fully demonstrated the superior performance of the DR-NET.

Change detection (CD) of high-resolution remote sensing (RS) images is a basic task in RS image processing tasks. In recent years, CD tasks have made many attempts in pure convolutional networks, attention mechanism, and transformer, and have achieved good results. Based on the power of attention and transformers, we hope to find a method that can handle the details of the image better and has better generalization ability. In this article, we propose a dual-feature mixed attention-based transformer network (DMATNet). First, we adopt a dual-feature extraction method, using a simple convolutional neural network (CNN) to extract coarse features, and a CNN based on progressive sampling to extract fine features. Then, we fuse the fine and coarse features with dual-feature mixed attention (DFMA) module. It can not only extract more specific regions of interest, but also overcome the misjudgment caused by oversampling, and synchronize feature extraction and target information integration. Finally, we use transformer to optimize these extracted information and feedback into the original features in the encoder to help remodel the pixel space. We merged the DMAT network into a deep feature difference-based CD framework and conducted extensive experiments on four datasets, LEVIR-CD, DSIFN-CD, WHU-CD, and CLCD, respectively, with tested F1 and interconnection over union (IoU) results of 90.75%/84.13%, 71.23%/55.32%, 85.70%/74.98%, and 66.56%/59.87%. Experimental results show that our DMAT-based model performs significantly better than the existing state-of-the-art attention and transformer-based methods.

Automatic extraction of water bodies from various satellite images containing complex targets is a very important and challenging task in remote sensing and image interpretation. In recent years, convolutional neural networks (CNNs) have become an important choice in the field of semantic segmentation of remote sensing images. However, generic CNN models present many problems when performing water body segmentation, such as: 1) blurred water body boundaries; 2) difficulty in accommodating different scales of rivers, often losing information about many small-scale rivers; and 3) a large number of trainable parameters. This article proposes an end-to-end CNN structure based on multiscale residuals and squeeze-and-excitation (SE)-attention for water segmentation, called MRSE-Net. MRSE-Net consists of an encoder–decoder and a skip connection, which captures contextual information at different scales using the encoder, and then passes the encoder feature mapping through the improved skip connection, while localization is achieved by the decoder is implemented. With the multiscale residual module, the number of parameters in our model can be significantly reduced and water pixels can be extracted accurately. The SE-attention module is used to enhance the prediction results, mitigate the blurring effect, and make the segmented water boundaries more continuous. Landsat-8 images are used to train our model and validate our proposed method’s performance and effectiveness. In addition, we evaluate our method on Landsat-7 and Sentinel-2 images and obtain the best water segmentation results. Preliminary results on Sentinel-2 images show that the cross-sensor generalization capability of our model is beyond the range of the Landsat sensor family.

Existing change detection techniques exhibit significant deficiencies in the recognition of building edges and detailed textures, making it challenging to accurately distinguish building boundaries from the background. Consequently, these methods struggle to precisely capture complex building contours and subtle texture variations. To address this problem, a Spatio-Temporal Wavelet Attention Aggregation Network (STWANet) is proposed in this paper. This network uses a pretrained Resnet18 to extract multi-scale features to obtain features with sufficient spatial details and semantic information. We introduce the Spatio-Temporal Differential Self-Attention (STDSA) Module to extract the Spatio-Temporal difference information between two Multi-Scale temporal features, and the introduction of the self-Attention mechanism is able to focus on the regions with the most significant changes in the multi-scale feature maps. In order to extract the changes of detailed features such as building edges, we introduce the Wavelet Feature Enhancement Module (WFEM) to enhance the representation of the frequency domain feature information of the changing features, especially the enhancement of high-frequency detail information (e.g., building edges). In order to make up for the shortcomings of WFEM in capturing specific details and global spatial features, we also introduce the Dual Attention Aggregation Module (DAAM) to extract the feature information of the changing areas in parallel with WFEM, which can process the spatial context information in a more detailed way, and can better retain the detailed features, especially the complex spatial structure and shape information. spatial structure and shape information. We verify the effectiveness and advancement of STWANet on three classical datasets (LEVIR-CD, WHU-CD, GZ-CD), and the experimental results show that STWANet reaches the state-of-the-art performance level. The code will be available at https://github.com/boshizhang123/STWANet.