Search Results (985)

With the increasing diversity of remote sensing image acquisition conditions and imaging scenarios, building extraction models often experience significant performance degradation in cross-dataset applications due to variations in sensors and scene characteristics. Improving their cross-domain generalization ability has therefore become a critical research problem. To address the challenges of appearance style discrepancy and feature distribution shift in cross-domain building extraction, this paper proposes WCMNet, a wavelet-guided and CNN–Mamba hybrid network for unsupervised domain adaptation in building extraction. Specifically, a Mamba Wavelet Alignment (MWA) module is designed to align low-frequency style information in the wavelet domain while preserving directional high-frequency edge structures, thereby mitigating cross-domain appearance discrepancies and reducing structural degradation during domain translation. In addition, a Global–Local Mamba Block (GLMB) is developed to jointly model local textures and global semantic dependencies. In GLMB, the CNN branch captures fine-grained local details and boundary cues, while the Mamba branch models long-range contextual information; an adaptive gated fusion mechanism further integrates the two types of features. Experimental results on six cross-domain transfer tasks across the WHU, Massachusetts, and Potsdam datasets demonstrate that WCMNet consistently outperforms existing state-of-the-art domain adaptation methods. In particular, WCMNet achieves an average IoU of 65.13% and an average BIoU of 74.80% across all transfer settings, with improvements of up to 27.35 percentage points in IoU and 38.32 percentage points in BIoU compared with the strongest competing methods. These results demonstrate that the proposed MWA and GLMB effectively improve building completeness, boundary delineation accuracy, and cross-domain robustness. Full article

Few-shot remote sensing scene classification aims to accurately recognize unseen scene categories using only a scarce number of labeled samples, which has emerged as a research hotspot in the field of remote sensing image interpretation. However, remote sensing images intrinsically suffer from large intra-class variations, high inter-class similarities, and complex background interferences. Traditional few-shot learning methods typically perform feature metric learning in Euclidean space, making it difficult to capture the non-Euclidean geometric distribution characteristics of remote sensing features, and they often neglect the spatial structural information embedded in feature maps. To address these issues, this paper proposes a novel few-shot remote sensing scene classification method, termed ZSFS-RGBN, which integrates a Zigzag Scanning Feature Sequence with a Riemannian Geometric Barycenter Network. Specifically, ResNet12 is first employed as the backbone to extract deep convolutional feature maps from both the support and query sets. Second, a Zigzag scanning strategy is introduced to reorganize the two-dimensional feature maps into one-dimensional feature sequences, thereby effectively preserving the spatial locality and structural continuity of the features. Third, an autoregressive moving average (ARMA) model is constructed to characterize the spatial dependencies of the feature sequences, and its state parameters are mapped onto a symmetric positive definite (SPD) matrix manifold, enabling the deep semantic representations of remote sensing scenes in a non-Euclidean geometric space. Finally, a Riemannian geometric barycenter network is designed to learn the Riemannian barycenter of each category on the SPD manifold, where a joint loss function is introduced to simultaneously optimize intra-class compactness and inter-class separability. Comprehensive experiments are conducted on three public remote sensing scene datasets: NWPU-RESISC45, UC Merced Land-Use, and WHU-RS19. Experimental results demonstrate that the proposed method consistently outperforms several representative state-of-the-art approaches under both 5-way 1-shot and 5-way 5-shot settings. Furthermore, ablation studies verify the effectiveness of each component within the proposed framework. Full article

In optical remote sensing 3D reconstruction, high-resolution satellite stereo matching is a critical task, yet it is challenged by extreme imaging geometries, texture-less and repetitive patterns, occlusions, and scene variations caused by spatio-temporal heterogeneity. To address these issues, we propose IFMA-Stereo, an innovative binocular disparity estimation method that leverages a monocular depth foundation model. Our approach constructs a multi-scale spatial information pyramid to jointly integrate the foundation model with a disparity extraction network. At the feature level, an attention interaction mechanism captures multi-dimensional contextual dependencies and transforms general scene understanding priors into long-range associative features suitable for stereo cost volume construction. At the pixel level, a cyclic iterative refinement module embeds depth information from the foundation model throughout the iteration process and performs joint optimization, enhancing the model’s adaptability in geometrically complex regions. Experiments on the US3D and GaoFen-7 datasets demonstrate that IFMA-Stereo achieves superior performance in challenging areas (texture-less regions, disparity discontinuities, repetitive patterns) and effectively mitigates prediction errors caused by spatio-temporal heterogeneity, albeit at the cost of increased inference time compared to baseline methods. Quantitatively, the method achieves an end-point error (EPE) of 1.347 and a D1 error of 7.26% on the US3D dataset, and an EPE of 1.585 and a D1 error of 13.41% on the GaoFen-7 dataset. Notably, the method also yields precise predictions for unseen urban areas, indicating strong generalization. These results confirm that IFMA-Stereo achieves state-of-the-art accuracy in remote sensing disparity estimation. Full article

Visible and infrared (IR) image fusion has become an important strategy for improving computer vision performance under low illumination, occlusion, and some poor-visibility conditions. By integrating complementary textural information from visible images with thermal or IR cues, VIR fusion can enhance object localization, detection robustness, and facial-expression recognition (FER). This review examines VIR fusion techniques and datasets for computer vision applications, with object detection (OD) considered as a relatively mature scene-level task and FER considered as an emerging human-centered application. It summarizes major multimodal datasets, compares early-fusion approaches, including sensor- and feature-level fusion, with late-fusion approaches, including score- and decision-level fusion, and discusses representative machine learning and deep learning methods. The review also evaluates commonly used performance metrics and identifies current limitations, including dataset imbalance, sensor misalignment, limited demographic diversity in facial-expression datasets, computational complexity, and weak real-time generalization. Finally, key application areas, including surveillance, healthcare, remote sensing, autonomous systems, and human–computer interaction, are discussed. This review highlights the need for better-aligned multimodal datasets, standardized evaluation protocols, lightweight fusion architectures, and robust models capable of operating in dynamic real-world environments. Full article

In recent years, there has been growing interest in applying vision–language models (VLMs) to quantitative remote sensing. This study evaluates whether three commercial VLMs (GPT-4o, GPT-5.5, and Claude Sonnet 4.6) can detect and classify the severity of harmful algal blooms (HABs) from Sentinel-2 satellite imagery of western Lake Erie and compares them against classical machine learning classifiers (Random Forest (RF), Support Vector Machine (SVM), and eXtreme Gradient Boosting (XGBoost)) trained on both a three-band red, green, blue (RGB) composite representation of the imagery and a 10-band multi-spectral reflectance representation. Forty bloom events identified from the National Oceanic and Atmospheric Administration (NOAA) Harmful Algal Bloom Operational Forecast System (HAB-OFS) severity assessments were assembled into the evaluation dataset, spanning seven bloom seasons (2019–2025). For binary bloom detection, the VLMs did not match the classical RGB classifiers; their F1 scores (0.69–0.75) fell below the best RGB classifier (Random Forest, 0.76) and below a trivial always-present baseline (F1 = 0.77), and they carried false positive rates of 73–93% on bloom-absent images, against 27–40% for the RGB classifiers. The VLMs reached high recall by labeling most scenes as bloom-positive, which makes them operationally unreliable in this configuration. For severity classification, the VLMs assigned 60–70% of their predictions to the “moderate” category regardless of actual conditions and identified at most one of the two severe blooms, whereas the classical classifiers tracked the ground-truth distribution and delivered two to nearly three times the exact-match accuracy (0.44–0.59 vs. 0.20–0.225). The strongest method across all metrics was the multi-spectral SVM (F1 = 0.833, false positive rate 27%, accuracy 0.795). Switching the same SVM from RGB to multi-spectral features raised accuracy from 0.675 to 0.795, a 12-percentage-point gain that measures the spectral information carried by red-edge and shortwave infrared bands that are accessible through multi-spectral sensors but unavailable to standard VLM vision encoders. Feature-importance analysis showed that the multi-spectral classifiers ranked chlorophyll-specific indices, the Normalized Difference Chlorophyll Index (NDCI) and the Floating Algae Index (FAI), among their top predictors, the same signatures used in established operational algorithms, while the RGB classifiers relied on red-channel variability and green-dominant pixel fractions because RGB inputs cannot compute those indices. Two compounded limitations therefore constrain off-the-shelf VLMs for aquatic remote sensing: the limited spectral information available through standard RGB channels and a mismatch between the land-dominated training distributions of these models and aquatic optical conditions. Domain-specific classifiers operating on multi-spectral data remain the more suitable tools for continued development of HAB monitoring and water-quality retrieval. Full article

In recent years, research on remote sensing scene classification (RSSC) has mainly focused on high-resolution imagery, which provides limited spectral information, whereas hyperspectral imaging (HSI) offers richer cues about material properties and compositional structure. Despite its potential, hyperspectral scene classification (HSI-SC) remains challenging because pixel- or patch-based representations fail to preserve spatial structures and regional boundaries. In addition, labeled hyperspectral samples are often scarce, making it difficult to learn stable class-discriminative representations from high-dimensional spectral observations. To address these issues, this paper proposes a dual-branch fusion framework. Superpixels are used to aggregate high-dimensional spectral signals into compact, boundary-aware tokens. The spectral branch is initialized with pretrained model weights and further adapted via a lightweight adaptation strategy for efficient transfer under limited supervision. In parallel, a pseudo-RGB spatial branch complements structural and textural information. Spectral and spatial features are fused additively to generate a more discriminative scene representation. Experimental results demonstrate that the proposed method outperforms compared hyperspectral scene classification approaches. Full article

Pine wilt disease (PWD) can spread rapidly after the disease occurs and often causes large-scale death of the pine. Therefore, the timely identification of infected trees is critical for forest conservation and effective disease management. However, early infected trees are difficult to distinguish in satellite remote sensing images. Their visual differences from healthy trees and complex background features are often subtle, and existing image-processing methods do not fully exploit heterogeneous information. To address this problem, we constructed the Naro dataset for satellite-based PWD detection and proposed SGM-RTDETR based on Real-Time Detection Transformer (RT-DETR). The proposed model consists of a Semantic–Visual Fusion Module (SVFM) and a Disease Feature Refinement Module (DFRM). In SVFM, ExG, VARI, and GLI are concatenated with RGB imagery to form a six-channel visual input, which enhances the spectral differences between diseased and non-diseased targets. In addition, textual prior knowledge is introduced into the decoder input through a Stackelberg game-based visual–text fusion strategy. This strategy helps the encoded memory features maintain clearer disease-related semantics in complex backgrounds. DFRM then performs channel recalibration, feature refinement, and residual enhancement on the fused memory features to better extract fine-grained disease cues in remote sensing scenes. Experiments on the Naro dataset show that SGM-RTDETR achieves 80.75% mAP@0.5 and 35.43% mAP@0.5:0.95, which is 2.74 percentage points higher than RT-DETR-L on mAP@0.5:0.95. Overall, the results indicate that the dual-module structure improves the precision and robustness of PWD detection in satellite remote sensing images. Full article

Haze commonly degrades visible-spectrum remote sensing (RS) images by reducing contrast and distorting colors. Existing RS dehazing methods still face two limitations. Prior-driven methods rely on handcrafted assumptions that may become unreliable in complex wide-area scenes without explicit sky regions. Learning-based methods require paired training data, yet real aligned hazy/haze-free RS image pairs are difficult to collect, which limits their real-world generalization. To address these limitations, we propose a method called Remote Sensing Image Dehazing via RGB-Space Physical Constraints (RDPC). The new method revisits the atmospheric scattering model (ASM) from the perspective of RS imaging and builds the restoration process on several physical properties of hazy image formation. For atmospheric light estimation, the RGB-space line-convergence behavior of local regions with similar reflectance and slight depth variations is exploited, allowing atmospheric light to be estimated without explicit sky areas. For transmission estimation, the geometric relation between observed pixels and atmospheric light is used in RGB space, where local perpendicularity provides physically plausible haze-removal guidance and global compensation helps avoid excessive darkening and color degradation. The estimated transmission and albedo guidance are further refined by enforcing ASM consistency and variation sparsity through joint optimization. Experiments on synthetic and real-world RS image dehazing benchmarks demonstrate that RDPC achieves competitive performance against representative prior-based and learning-based methods, including Image Dehazing and Exposure (IDE), Iterative Predictor-Critic (IPC), Curvature-to-Plane Prior (C2P), Adaptive Structure-Texture Awareness (ASTA), Asymmetric U-Net (AU-Net), Efficient Multi-scale Prior Fusion (EMPF), and Lightweight Feature Dehazing (LFD), in terms of peak signal-to-noise ratio (PSNR), structural similarity index measure (SSIM), learned perceptual image patch similarity (LPIPS), Blind/Referenceless Image Spatial Quality Evaluator (BRISQUE), neural image assessment (NIMA), and processing time. Full article

Hyperspectral image (HSI) and LiDAR data fusion is valuable for land-cover classification in complex surface scenes. Existing methods typically extract features from each modality independently and then consider how to fuse them, ignoring the semantic consistency between features of different modalities and across different hierarchical levels. Moreover, fully mining and exploiting the complementary information between multimodal remote sensing data remains a critical issue. To address these challenges, this paper proposes a hierarchical semantic consistency constraint (HSCC) framework for HSI and LiDAR data joint classification. The framework is co-constructed by a progressive interactive fusion network (PIFNet) and a semantic consistency constraint (SCC) strategy. Specifically, PIFNet progressively calibrates the semantic representations of multimodal features at different abstraction levels through Cross-Modal Shared Attention and Symmetric Cross-Attention mechanisms, promoting information parity in deep interactions. The SCC strategy establishes multi-level semantic associations and employs a semantic consistency constraint loss to guide the network to autonomously maintain the consistency of the same land-cover object across heterogeneous feature representations, thereby further enhancing the discriminative power of the fused features. Experiments on three public datasets, MUUFL, Houston2013, and Augsburg, demonstrate that HSCC outperforms current state-of-the-art methods, validating its effectiveness in multi-source remote sensing data fusion classification tasks. Full article

Zero-shot remote sensing is attractive for scene classification because new regions, sensors, and label taxonomies often appear before sufficient annotated data are available for supervised adaptation. We present OATS-RS, an inference-centric framework that keeps a remote sensing vision–language model (VLM) backbone frozen and improves zero-shot decisions through ontology-aware prompt construction, hierarchical and contrastive scoring, adaptive multi-view aggregation, unlabeled transductive refinement, ambiguity-aware local re-ranking, and selective prediction. The method targets the common remote sensing regime in which neighboring classes such as annual crop, permanent crop, forest, pasture, herbaceous vegetation, river, and sea or lake overlap strongly in red–green–blue (RGB) appearance, meaning that they require more than a single class-name prompt. On the supplied final EuroSAT RGB evaluation with a GeoRSCLIP Contrastive Language–Image Pre-training (CLIP)-family Vision Transformer Base with 32 × 32-pixel patches (ViT-B-32) backbone, the complete pipeline obtains top-1 accuracy of 0.522, balanced accuracy of 0.522, macro-averaged F1 score (macro-F1) of 0.535, and top-3 accuracy of 0.887. The strongest classes are industrial area, residential area, river, highway, and pasture, whereas the weakest classes remain herbaceous vegetation and several fine-grained vegetation categories. Selective prediction increases accepted-example accuracy to 0.538 at 0.934 coverage, but the expected calibration error (ECE) remains high at 0.384. These results support a qualified conclusion: ontology-guided zero-shot inference can already recover useful semantic shortlists for structured remote-sensing scenes, but fine-grained natural-class disambiguation, calibrated confidence, multi-dataset transfer, component-level ablations, and measured runtime remain essential before dependable deployment claims can be made. Full article

Recent advances in deep learning have substantially improved remote sensing change detection. However, most existing models still describe bi-temporal differences mainly from the spatial domain, making it difficult to fully capture complementary frequency domain cues in complex scenes. To address this limitation, this paper introduces a Spatial-Frequency Collaborative Learning Network (SFCLNet) for remote sensing change detection. In particular, hierarchical features are extracted from bi-temporal images using a Siamese backbone. A Spatial Domain Feature Fusion (SDFF) module is then designed to enhance local structural variation details by modeling the structural consistency between bi-temporal features. Meanwhile, a Frequency Domain Feature Fusion (FDFF) module is introduced to characterize frequency domain cues by separately modeling phase and amplitude components. Furthermore, a Spatial-Frequency Collaborative Fusion (SFCF) module is developed to obtain more discriminative change feature representations by integrating the fused spatial domain and frequency domain features in a channel-wise competitive way. Finally, the pixel-wise results are predicted using a UNet-based decoder that progressively aggregates the fused multi-level features. Experimental results on Google, LEVIR, and MSRS benchmark datasets show that SFCLNet achieves F1 scores of 88.94%, 91.39%, and 74.97%, respectively, outperforming several recently published methods. These results verify the effectiveness of jointly exploiting the frequency domain and spatial domain for remote sensing change detection. Full article

High-resolution remote sensing image segmentation is important for urban mapping but remains challenging because of spectral ambiguity, large scale variations, fragmented elongated structures, and background interference. This study aims to improve semantic segmentation in complex aerial scenes by combining local feature extraction, selective multi-scale fusion, and global sequence modeling. We propose DSD-Mamba, an asymmetric dual-stream architecture with a ResNet-18 encoder. The Dense-Sparse Pyramid Fusion Module aligns multi-level features and applies dual Top-k selective value aggregation for cross-scale response filtering and background-response suppression. This Top-k operation is used as a feature-selection mechanism and is not intended to reduce the theoretical memory footprint of dense attention. Scale-Aware Strip Attention refines skip connections through horizontal and vertical dependency modeling, and the Dual-Stream Context Decoder combines a Mamba-based global branch with a CNN-based local branch during upsampling. Experiments were conducted on UAVid, ISPRS Vaihingen, and ISPRS Potsdam under a single-model inference protocol without test-time augmentation. DSD-Mamba achieved mIoU scores of 73.4%, 85.2%, and 87.2%, respectively. Ablation experiments on Vaihingen showed that DSPFM, SASA, and DSCD improved performance over the baseline when evaluated in this setting, with the full model reaching the highest mIoU. The method improves segmentation accuracy under the tested protocols, although its higher FLOPs indicate an accuracy-oriented rather than lightweight design. Full article

Unmanned aerial vehicle (UAV) visual navigation relies critically on robust image matching between UAV-acquired aerial imagery and pre-existing satellite reference maps. However, extreme cross-domain heterogeneity—encompassing temporal, radiometric, viewpoint, and sensor variations—causes severe performance degradation in existing deep learning-based matchers trained on conventional benchmarks. Furthermore, manual annotation of ground-truth correspondences is prohibitively expensive. This paper proposes a semi-supervised saliency-aware image matching framework with bi-level meta-learning. Our approach comprises two synergistic stages: (1) automated dense correspondence generation via parameterized geometric synthesis, which constructs a large-scale coarse dataset ${\mathcal{D}}_c$ (approximately 50,000 pairs) without dense manual point annotation, serving as the primary training corpus for the feature matching network; (2) expert-validated meta-data curation producing a high-quality meta-dataset ${\mathcal{D}}_m$ (500 pairs) that supervises the training of a Saliency Judgment Network through bi-level meta-optimization, enabling the network to identify and prioritize geometrically reliable correspondences. Experimental results on the proposed RS-Hetero-50K benchmark and cross-domain FuJian-Mountain dataset demonstrate substantial improvements over representative sparse and detector-free matchers, including LoFTR, SuperGlue, and LightGlue. The complete CNN-attention and saliency-aware framework achieves 95.4% matching precision, which is consistent with the best result reported in the experimental section. The plug-and-play experiments further confirm that the proposed saliency module consistently improves representative sparse and detector-free matchers, indicating that the performance gain stems from both stronger feature representation and saliency-guided correspondence selection. The largest terrain-specific gain is observed in gobi scenes, where the AUC@5 px improves by 16.8% relative to the LoFTR baseline, demonstrating improved robustness in weakly textured remote sensing environments. Full article

Methane source-rate inversion from remote-sensing plume imagery is essential for emissions monitoring, but its accuracy is often limited by uncertainty in ancillary wind information. This study examines how physical knowledge can be integrated into a deep-learning inversion model when the available wind input is imperfect. Using a controlled large-eddy-simulation (LES) benchmark designed for EnMAP/PRISMA-style imaging-spectrometer methane quantification, we compare six models that span image-only regression, flexible wind conditioning, simplified hard integrated-mass-enhancement (IME) coupling, and soft physics-guided learning under clean inputs, deterministic wind bias, stochastic Gaussian wind noise, and source-rate-stratified tests. Under clean benchmark conditions, flexible wind conditioning provides the best scalar accuracy, with FiLM reaching a mean absolute percentage error (MAPE) of 6.19% and a root mean squared error (RMSE) of 1323.36, followed closely by Concat (MAPE 6.37%, RMSE 1325.69). The simplified hard-coupling model is sensitive to wind perturbations: DIN-hard rises from MAPE 8.44% under clean inputs to 31.39% and 26.89% under deterministic wind-bias multipliers α = 0.7 and α = 1.3, respectively, and becomes unstable under stronger Gaussian wind noise in the tested protocol. By contrast, DIN-soft-v2 remains competitive under clean conditions (MAPE 6.39%, RMSE 1360.94), follows smoother degradation under biased or noisy wind, and improves plume spatial diagnostics relative to DIN-soft (center-of-mass shift 3.92 versus 4.07 pixels; plume alignment degree 2.60 versus 2.72 degrees). The calibrated IME-style physical baseline reaches a clean MAPE 24.45%, indicating that the learning-based models substantially outperform this benchmark physical proxy. Within this LES-based benchmark and the tested wind-perturbation protocols, the results suggest that IME-inspired physical knowledge is more robustly incorporated as a calibratable soft prior than as the simplified hard log-additive forward coupling considered here; however, transfer to real satellite scenes still requires validation. Full article

A remote sensing scene graph (RSSG) enables machines to interpret interactions among ground objects in remote sensing images and supports semantic reasoning and description, thus making it a fundamental technique in the field. However, most existing scene reasoning approaches cannot fully utilize multimodal information, resulting in limited performance when inferring spatial relationships among ground objects. To this end, we propose a Unified Visual-Semantic Triple Prompt Learning (UVSTPL) framework, which integrates visual features with matched geospatial object labels, leverages a prompt learning module for multimodal feature extraction, and employs a refined UVTransE model to predict spatial relationships. The core principle of UVSTPL is to enhance semantic feature extraction and improve relationship prediction performance via the collaborative fusion of visual and linguistic modalities. To strengthen the model’s ability to reason about the spatial relationships among ground objects in images, a novel Geo-RSSG dataset is constructed, which includes precise annotations of geographic entities, spatial relationships, and attributes. Extensive experiments demonstrate that the proposed UVSTPL method outperforms benchmark models on the spatial relationship prediction task. In comparison with the best baseline method, our approach improves prediction precision by 1.85%, mean precision by 8.49%, mean recall by 17.46%, and mean F1-score by 12.97%. This study offers valuable insights for advancing the understanding and cognitive capabilities of remote sensing scenes. Full article