Due to the limitations of current technology and budget, a single satellite sensor can not obtain high spatiotemporal resolution remote sensing images. Therefore, remote sensing image spatio-temporal fusion technology is considered as an effective solution and has attracted extensive attention. In the field of deep learning, due to the fixed size of the perception field of convolutional neural network, it is impossible to model the correlation of global features, and the features extracted only through convolution operation lack the ability to capture longdistance features, At the same time, complex fusion methods can not better integrate temporal and spatial features. In order to solve these problems, we propose a multi-stage remote sensing image spatio-temporal fusion model based on Texture Transformer and convolutional neural network. The model combines the advantages of Transformer and convolutional network, uses a lightweight convolution network to extract spatial features and temporal discrepancy features, uses Transformer to learn global temporal correlation, and finally fuses temporal features with spatial features. In order to make full use of the features obtained in different stages, we design a cross-stage adaptive fusion module CSAFM. The module adopts the self attention mechanism to adaptively integrate the features of different scales while considering the temporal and spatial characteristics. To test the robustness of the model, the experiments are carried out on three datasets of CIA, LGC and DX. Compared with five typical spatio-temporal fusion algorithms, we obtain excellent results, which prove the superiority of MSFusion model.

In the field of remote sensing, the classification of land cover is a pivotal and challenging issue. Standard models fail to capture global and semantic information in remote sensing images despite the fact that a convolutional neural network provides robust support for semantic segmentation. In addition, owing to disparities in semantic levels and spatial resolution, the simple fusion of low-level and high-level features may diminish the efficiency. To address these deficiencies, an attention-guided multi-level feature fusion network (AMFFNet) is proposed in this study. The proposed AMFFNet approach is designed as an encoder-decoder network with the inclusion of a multi-level feature fusion module (MFF) and a dual attention map module (DAM). A DAM models the semantic association of features from a spatial and channel perspective, and an MFF bridges the semantic and resolution gaps between high-level and low-level features. Furthermore, we propose a residual-based boundary refinement upsample module to further optimize the object boundaries. The experimental results indicate that the proposed strategy can considerably enhance the accuracy of land cover classification, achieving a mean intersection over union of 90.39% on the LandCover.ai dataset and 63.14% on the Gaofen Image Dataset with 15 categories (GID-15).

In road extraction from remote sensing images, the road environment is complex and blocked by trees, buildings, and other objects, making it impossible to extract practical (continuous and complete) road information. We propose a joint attention encoder-decoder network (JAED-Net) for road extraction from remote sensing images to solve these problems. First, JAED-Net encodes a modified residual network as the backbone for road feature extraction. A joint attention module is added to the encoder to enhance the network's ability to learn and express road features. Then, strip convolution is added to the decoder, so the network retains more spatial features, such as the width and connectivity of roads during upsampling. Finally, a hybrid weighted loss function is introduced to train the network and ensure stability because of the unbalanced ratio of road and background pixels in remote sensing images. Experimental validation of the proposed network is performed on three publicly available datasets.