Remote sensing semantic segmentation plays a crucial role in the fields of land cover classification, disaster monitoring, and urban planning. However, due to the high complexity and category imbalance of remote sensing data sets, traditional image segmentation network tend to be slow to train and difficult to capture deep semantic information, which leads to the accuracy failing to meet the requirements of practical applications. Inspired by the powerful transfer learning capability of visual foundation models, we introduce a semantic segmentation network for remote sensing images called SAM2Former, which utilizes the Segment Anything Model 2 (SAM2) to assist a UNet-like Transformer. The SAM2Former is a dual-encoder and single-decoder structure composed of the efficient ResNet18 and SAM2’s Image Encoder as dual encoders, with Transformer as the decoder. Firstly, we incorporate the lightweight Adapter to perform parameter-efficient fine-tuning on SAM2 and design a multi-scale information aggregation module (MIAM) to connect the dual-encoder, which weighted multi-scale features layer by layer of SAM2 Block and CNN, preserving key information in the image. Secondly, we devise a decoder based on global-local transformer module (GLTM) to effectively extract global context information and local detail information, improving the segmentation ability of edge texture. Finally, we construct the feature enhancement module (FEM) to improve the recognition accuracy of similar categories by combining channel and spatial attention features. Moreover, our SAM2Former performed com-prehensive comparative and ablation experiments on the ISPRS Vaihingen and Potsdam datasets, showing notable improvements in segmentation performance.

Accurate segmentation of single tree crowns enables precise measurement of tree height, DBH, and stock volume, facilitating effective assessment of forest growth and productivity. However, single tree crown segmentation currently faces several challenges, including insufficient segmentation accuracy, mis-segmentation and crown adhesion. To address these issues, this study conducts experiments using UAV data and proposes a model named CIA-UNet. In this model, the multiscale feature extraction capability of the InceptionV2 module is leveraged to compensate for U-Net's limitation in capturing different scales of tree crowns and fine details using fixed convolutional kernels. The Convolutional Block Attention Module (CBAM) is employed to increase the weight of key features, and mitigate false segmentation caused by feature confusion. Additionally, the Attention Gate module is utilized to improve the model's sensitivity to foreground pixels, adjust the weighting of skip connection features and prevent segmentation errors due to semantic mismatches. The experimental results show that CIA-UNet achieves outstanding performance on TREE512 dataset, with overall accuracy (OA), mean precision (mPrecision), mean recall (mRecall) and mean intersection over union (mIoU) reaching 90.79%, 88.08%, 89.41% and 79.9% respectively. Compared with U-Net, these metrics have improved by 1.07%, 1.63%, 1.5%, and 2.41% respectively. Furthermore, CIA-UNet performs better than DeepLabV3+, PSPNet and FCN in accuracy evaluation indicators and visual segmentation results. The results demonstrate the efficacy of CIA-UNet model in enhancing the accuracy of tree crown segmentation and minimizing mis-segmentation, and provide experience for the study of single tree crown segmentation in the Millennium Forest of Xiongan New Area.

High-resolution remote sensing imagery, reaching meter or sub-meter levels, provides essential data for extracting and identifying road information. However, rural roads are often narrow, elongated, and have blurred boundaries, with textures that resemble surrounding environments such as construction sites, vegetation, and farmland. These features often lead to incomplete extraction and low extraction accuracy of rural roads. To address these challenges, this study introduces the RC-MSFNet model, based on the U-Net architecture, to enhance rural road extraction performance. The RC-MSFNet model mitigates the vanishing gradient problem in deep networks by incorporating residual neural networks in the downsampling stage. In the upsampling stage, a connectivity attention mechanism is added after dual convolution layers to improve the model’s ability to capture road completeness and connectivity. Additionally, the bottleneck section replaces the traditional dual convolution layers with a multi-scale fusion atrous convolution module to capture features at various scales. The study focuses on rural roads in the Xiong’an New Area, China, using high-resolution imagery from China’s Gaofen-2 satellite to construct the XARoads rural road dataset. Roads were extracted from the XARoads dataset and DeepGlobe public dataset using the RC-MSFNet model and compared with some models such as U-Net, FCN, SegNet, DeeplabV3+, R-Net, and RC-Net. Experimental results showed that: (1) The proposed method achieved precision (P), intersection over union (IOU), and completeness (COM) scores of 0.8350, 0.6523, and 0.7489, respectively, for rural road extraction in Xiong’an New Area, representing precision improvements of 3.8%, 6.78%, 7.85%, 2.14%, 0.58%, and 2.53% over U-Net, FCN, SegNet, DeeplabV3+, R-Net, and RC-Net. (2) The method excelled at extracting narrow roads and muddy roads with unclear boundaries, with fewer instances of omission or false extraction, demonstrating advantages in complex rural terrain and areas with indistinct road boundaries. Accurate rural road extraction can provide valuable reference data for urban development and planning in the Xiong’an New Area.

Multi-temporal remote sensing image matching plays a crucial role in tasks such as detecting changes in urban buildings, monitoring agriculture, and assessing ecological dynamics. Due to temporal variations in images, significant changes in land features can lead to low accuracy or even failure when matching results. To address these challenges, in this study, a remote sensing image matching framework is proposed based on multi-perception and enhanced feature description. Specifically, the framework consists of two core components: a feature extraction network that integrates multiple perceptions and a feature descriptor enhancement module. The designed feature extraction network effectively focuses on key regions while leveraging depthwise separable convolutions to capture local features at different scales, thereby improving the detection capabilities of feature points. Furthermore, the feature descriptor enhancement module optimizes feature point descriptors through self-enhancement and cross-enhancement phases. The enhanced descriptors not only extract the geometric information of the feature points but also integrate global contextual information. Experimental results demonstrate that, compared to existing remote sensing image matching methods, our approach maintains a strong matching performance under conditions of angular and scale variation.

Synthetic aperture radar (SAR), as an active microwave imaging system, has the capability of all-weather and all-time observation. In response to the challenges of aircraft detection in SAR images due to the complex background interference caused by the continuous scattering of airport buildings and the demand for real-time processing, this paper proposes a YOLOv7-MTI recognition model that combines the attention mechanism and involution. By integrating the MTCN module and involution, performance is enhanced. The Multi-TASP-Conv network (MTCN) module aims to effectively extract low-level semantic and spatial information using a shared lightweight attention gate structure to achieve cross-dimensional interaction between “channels and space” with very few parameters, capturing the dependencies among multiple dimensions and improving feature representation ability. Involution helps the model adaptively adjust the weights of spatial positions through dynamic parameterized convolution kernels, strengthening the discrete strong scattering points specific to aircraft and suppressing the continuous scattering of the background, thereby alleviating the interference of complex backgrounds. Experiments on the SAR-AIRcraft-1.0 dataset, which includes seven categories such as A220, A320/321, A330, ARJ21, Boeing737, Boeing787, and others, show that the mAP and mRecall of YOLOv7-MTI reach 93.51% and 96.45%, respectively, outperforming Faster R-CNN, SSD, YOLOv5, YOLOv7, and YOLOv8. Compared with the basic YOLOv7, mAP is improved by 1.47%, mRecall by 1.64%, and FPS by 8.27%, achieving an effective balance between accuracy and speed, providing research ideas for SAR aircraft recognition.