Recent self-supervised learning (SSL) methods have demonstrated impressive results in learning visual representations from unlabeled remote sensing (RS) images. However, most RS images predominantly consist of scenographic scenes containing multiple ground objects without explicit foreground targets, which limits the performance of existing SSL methods that focus on foreground targets. This raises the question: Is there a method that can automatically aggregate similar objects within scenographic RS images, thereby enabling models to differentiate knowledge embedded in various geospatial patterns for improved feature representation? In this work, we present the pattern integration and enhancement vision transformer (PIEViT), a novel SSL framework designed specifically for RS imagery. PIEViT utilizes a teacher-student architecture to address both image-level and patch-level tasks. It employs a proposed, geospatial pattern cohesion (GPC) module to explore the natural clustering of patches, enhancing the differentiation of individual features. A feature integration projection (FIP) module is employed to further refine masked token reconstruction using geospatially clustered patches. We validated PIEViT across multiple downstream tasks, including object detection, semantic segmentation, and change detection. Experiments demonstrated that PIEViT enhances the representation of internal patch features, providing significant improvements over existing self-supervised baselines. It achieves excellent results in object detection, land cover classification, and change detection, underscoring its robustness, generalization, and transferability for RS image interpretation tasks.

In the realm of remote sensing change detection, deep learning-based pixel-level methods have shown commendable accuracy and speed. However, due to the difficulty in distinguishing between each changed object and the high matching accuracy required, there are still limitations in practical applications. To address these issues, we propose Change DINO, a novel unified object-level change detection and segmentation framework and the inaugural Transformer-based object-level change detection framework, which leverages the Hierarchical Temporal Fusion Module (HTFM) with dual branches to extract change features from bi-temporal images, integrating these features into the Transformer's encoder-decoder and segmentation branches. Experimental results show that compared to other pixel-level (including Transformer-based) change detection methods, Change DINO exhibits superior performance even on pixel-level evaluation strategy, achieving F1 score improvements of 5.09% and 10.31% compared with Transformer-based methods. This capability significantly mitigates the limitations inherent in pixel-level detection, showcasing Change DINO's substantial potential for diverse applications in change detection tasks.

In remote sensing image change detection (CD), leveraging distant contextual information is crucial for accuracy. Traditional neural network training, which involves image cropping, limits the perception of such information in large-scale images. To overcome this, we propose the "Panoramic Change Analysis Framework (PCA-F)" for high-resolution remote sensing CD. This innovative framework features a dual-branch architecture to integrate broad area information and uses advanced spatial alignment for merging wide-area and local features. PCA-F overcomes traditional method limitations and integrates well with various CD networks. The experimental results demonstrate a significant improvement in accuracy for the three baseline methods on two datasets (BIT: 3.51%, 4.66%; Changeformer: 1.49%, 2.64%; RDPNet: 1.97%, 5.31%), offering a new direction for enhancing CD performance in remote sensing imagery.

Urban functional zones (UFZs) contain abundant landscape information that can be adopted to better understand the surroundings. Various landscape compositions and configurations reflect different human activities, which may affect the particulate matter (PM2.5) concentrations. The very high-resolution (VHR) image features can reflect the physical and spatial structures of the UFZs. However, the existing PM2.5 estimation methods neither have been based on the scale of UFZs, nor have the VHR image features of UFZs as independent variables. Hence, this article proposes a spatiotemporal interpolation graph convolutional network (STI-GCN) model and introduces VHR image features to achieve PM2.5 estimation in UFZs. First, UFZs are split, and VHR image features are extracted by the visual geometry group 16 (VGG16). Subsequently, meteorological factors, aerosol optical depth (AOD), and VHR image features are used to estimate the PM2.5 concentrations at the scale of the UFZs. The two metropolises, Beijing and Shanghai, are chosen to assess the validity of the STI-GCN model. As for Beijing and Shanghai, the overall accuracy${R^{2}}$of the STI-GCN model can reach 0.96 and 0.89, the root-mean-square errors (RMSEs) are 8.15 and 6.40$\mu \text {g}/{\text {m}^{3}}$, the mean absolute errors (MAEs) are 5.51 and 4.78$\mu \text {g}/{\text {m}^{3}}$, and the relative prediction errors (RPEs) are 18.53% and 17.38%, respectively. Experiments show that the STI-GCN consistently outperforms other models. What’s more, the PM2.5 values are relatively high in commercial and official zones (COZs) and relatively low in urban green zones (UGZs).

Land use mapping (LUM) of a coal mining subsidence area (CMSA) is a significant task. The application of convolutional neural networks (CNNs) has become prevalent in LUM, which can achieve promising performances. However, CNNs cannot process irregular data; as a result, the boundary information is overlooked. The graph convolutional network (GCN) flexibly operates with irregular regions to capture the contextual relations among neighbors. However, the global context is not considered in the GCN. In this paper, we develop the deep global context construction with enabled boundary (DGCC-EB) for the LUM of the CMSA. An original Google Earth image is partitioned into nonoverlapping processing units. The DGCC-EB extracts preliminary features from the processing unit that are further divided into nonoverlapping superpixels with irregular edges. The superpixel features are generated and then embedded into the GCN and vision transformer (ViT). In the GCN, the graph convolution is applied to superpixel features; therefore, the boundary information of objects can be preserved. In the ViT, the multihead attention blocks and positional encoding build the global context among the superpixel features. The feature constraint is calculated to fuse the advantages of the features extracted from the GCN and ViT. To improve the LUM accuracy, the cross-entropy (CE) loss is calculated. The DGCC-EB integrates all modules into a whole end-to-end framework and is then optimized by a customized algorithm. The results of case studies show that the proposed DGCC-EB obtained acceptable OA (89.06%/88.68%) and Kappa (0.86/0.87) values for Shouzhou city and Zezhou city, respectively.

Urban boundary is the first important indicator for urban expansion analysis. However, little attention has been paid to reveal urban expansion with urban boundary at large region scale due to lacking high-precision and consistent urban boundaries. In this study, high-precision urban boundaries of China's 337 prefecture level cities from 2000 to 2016 were extracted by using high-resolution images and a series of geographic rules. Analysis results showed that (1) China had undergone a rapid urbanization with the urban area increased by 122.6% from 2000 to 2016. (2) 73.3% of the 337 cities had the urban expansion form of edge-expansion (3) Urban expansion was not coordinated with urban population growth. Urban expansion rate of 24 provinces was ahead of urban population growth rate. 4) The two major land source of urban expansion areas was cultivated land and construction land, which was 56.4% and 23.9% of the total urban expansion area respectively.

Sparse coding algorithms with geometrical constraints have received much attention recently. However, these methods are unsupervised and might lead to less discriminative representations. In this paper, we propose a supervised locality-constrained sparse coding method for classification. Two graphs are constructed, a labeled graph and an unlabeled graph. Sparse codes with a labeled geometrical constraint will be more discriminative, however we cannot embed test samples with unknown label into a labeled graph. By coupling the two graphs, we aim to make the difference between sparse codes with labeled and unlabeled geometrical constraints as small as possible. As a result, sparse codes of test data can be obtained with the unlabeled geometrical constraint and the discrimination of the labeled geometrical constraint is maintained. Experiments on some benchmark datasets demonstrate the effectiveness of the proposed method.

Recently, some sparse coding methods with geometrical constraint have been proposed, in which local geometrical structure of the data points was preserved during sparse coding process. These methods have been applied to classification problems and gained much success. However, they failed to use label information which has been proved to be useful in supervised sparse coding and discriminant manifold learning. In this paper, we propose a discriminant sparse coding approach with geometrical constraint. Labels are used to learn an intrinsic graph and a penalty graph, and these graphs are then embedded into sparse coding framework as constraints. The local geometric structure within each class is preserved and the separability between different classes is enforced. As a result, the discrimination of sparse coding will be improved. Experiments on benchmark databases demonstrate the effectiveness of the proposed method.