Remote sensing images (RSIs) Spatiotemporal fusion (STF) make a significant contribution to acquisition RSIs sequence with simultaneously high temporal and spatial resolution, which broadens its application fields. However, the existing RSIs STF methods lack effective strategies for extracting global information and fusion features between different images. Conversely, the existing State-Of-The-Art (SOTA) methods generally require more than two RSIs from different satellites as reference, which increases the difficulty of data collection and limits the application in practice. To address these problems, this paper proposed an end-to-end CNN and Transformer combined RSIs STF model (CTSTFM) based on two reference RSIs. Specifically, the proposed CTSTFM consists of three basic modules: Multi Kernel Convolutional Transformer encoder (MKCE), Cross Fusion module (CFM) and Convolutional-based Compression decoder (CCD). The MKCE combines Multi Kernel Channel Attention block and Multi Kernel Spatial Attention block to extract shadow features and long-term interdependencies in reference RSIs. The CFM uses the unique Cross Exchange Transformer block and Combine Fusion Transformer block to enhance the feature fusion results. Due to the powerful Encoder and Fusion Module, in the CCD part we only use a simple design convolution module to save the consumption of computational resources. Experiments on two well-known open access datasets shows that CTSTFM achieves competitive results in both qualitative and quantitative comparisons compared to the SOTA methods. Meanwhile, we conduct experiment to analyze the image Tessellation Effects and its solution. The effectiveness of the proposed module will be demonstrated through ablation experiments

Urban green spaces (UGS) play a crucial role in the urban environmental system by aiding in mitigating the urban heat island effect, promoting sustainable urban development, and ensuring the physical and mental well-being of residents. The utilization of remote sensing imagery enables the real-time surveying and mapping of UGS. By analyzing the spatial distribution and spectral information of a UGS, it can be found that the UGS constitutes a kind of low-rank feature. Thus, the accuracy of the UGS segmentation model is not heavily dependent on the depth of neural networks. On the contrary, emphasizing the preservation of more surface texture features and color information contributes significantly to enhancing the model’s segmentation accuracy. In this paper, we proposed a UGS segmentation model, which was specifically designed according to the unique characteristics of a UGS, named the Green Space Reverse Pixel Shuffle Network (GSRPnet). GSRPnet is a straightforward but effective model, which uses an improved RPS-ResNet as the feature extraction backbone network to enhance its ability to extract UGS features. Experiments conducted on GaoFen-2 remote sensing imagery and the Wuhan Dense Labeling Dataset (WHDLD) demonstrate that, in comparison with other methods, GSRPnet achieves superior results in terms of precision, F1-score, intersection over union, and overall accuracy. It demonstrates smoother edge performance in UGS border regions and excels at identifying discrete small-scale UGS. Meanwhile, the ablation experiments validated the correctness of the hypotheses and methods we proposed in this paper. Additionally, GSRPnet’s parameters are merely 17.999 M, and this effectively demonstrates that the improvement in accuracy of GSRPnet is not only determined by an increase in model parameters.

Remote sensing image fusion (RSIF) integrates observations from multiple sensors, spectral domains, and temporal acquisitions to exploit complementary and differential information, thereby producing more complete, consistent, and analytically valuable representations of the Earth system. However, existing fusion approaches are predominantly designed for specific tasks or modalities, which restricts their generalization and scalability. To this end, we propose a fusion network with dual-path learning strategy (DPLNet) that provides a unified framework for three fusion tasks: spatiotemporal fusion, change detection, and pan-sharpening. DPLNet comprises two primary stages: Feature Extraction (FE) stage and Multiscale Feature Fusion (MFF) stage. In the FE stage, the two remote sensing images (RSIs) are independently processed through one stream of the dual-path encoder. Subsequently, in the MFF stage, all multiscale features are adaptively integrated within a unified fusion module, where features from corresponding scales are fused adaptively without predefined task-specific interaction rules, allowing the model to learn cross-source feature relationships in a data-driven manner for final prediction. Experiments on multiple datasets demonstrate that DPLNet achieves state-of-the-art performance, consistently surpassing specialized models in both quantitative accuracy and qualitative comparison. These results highlight the potential of DPLNet as a task-general framework for representative optical remote sensing fusion tasks, offering a scalable and efficient solution for Earth observation. The implementation code, evaluation scripts, and pretrained model weights will be released at https://github.com/Pablo-8974/DPLNet after this paper has been accepted.