Search Results (243)

Optical vegetation and soil indices are widely used in Earth observation, although their estimation is strongly affected by cloud coverage and illumination variability. Synthetic-aperture radar (SAR) has therefore attracted increasing interest as an alternative source for spectral index prediction. Most existing studies focus on directly estimating a single index from SAR observations. In this work, we investigate a more flexible formulation in which Sentinel-2 multispectral bands are first reconstructed from Sentinel-1 SAR data and subsequently used to derive multiple spectral indices. Experiments are conducted on the SEN12TP dataset, exploiting near-synchronous paired Sentinel-1 and Sentinel-2 acquisitions together with auxiliary elevation and land-cover information. Three SAR-to-multispectral reconstruction strategies are compared, namely, Efficient-UNet, Pix2Pix, and a conditional flow matching model. The resulting indices are then evaluated against those obtained through dedicated index-specific reconstruction models. The results show that Efficient-UNet achieves the best overall multispectral reconstruction performance among the evaluated architectures. Moreover, indices derived from reconstructed multispectral bands achieve performance comparable to dedicated index-specific models while offering substantially greater flexibility, as multiple indices can be computed within a single framework without retraining task-specific models. At the same time, the experiments highlight important intrinsic limitations of SAR-based spectral reconstruction. Although the reconstructed products preserve the large-scale spatial organization of the scenes, they do not fully recover fine spectral and vegetation-sensitive details. Consequently, SAR-derived spectral indices should be regarded as approximate proxies of optical observations rather than direct substitutes, particularly in applications requiring accurate biophysical interpretation. Full article

Very-high-resolution (VHR) multispectral satellite imagery contains rich semantic information, yet its real-time transmission is constrained by limited satellite-to-ground bandwidth and dynamic channel impairments. Conventional communication schemes prioritize pixel-level reconstruction, resulting in large transmission overhead and poor robustness under unfavorable channel conditions. To address these challenges, an end-to-end task-oriented semantic communication framework for remote sensing downstream recognition tasks, termed Semantic Transmission Architecture for Remote Sensing (STARS), is proposed. To improve transmission efficiency for very-high-resolution remote sensing images with highly redundant background regions, a Semantic Feature Reweighting Module (SFRM) is introduced to dynamically evaluate token-level semantic importance and adaptively allocate transmission resources to task-critical features. Furthermore, vector quantization and a practical digital transmission chain are jointly integrated to achieve efficient semantic compression, while dynamic channel variations are incorporated during training to improve robustness under fading channel conditions. Experimental results on the DOTA dataset demonstrate that STARS consistently outperforms conventional schemes and existing semantic baselines under Rician fading channels, validating the effectiveness of semantic-aware feature allocation for bandwidth-efficient VHR imagery transmission. Full article

Pansharpening plays an important role in remote sensing image processing. Its purpose is to fuse a high-spatial-resolution panchromatic (PAN) image and a low-spatial-resolution multispectral (LRMS) image, thereby reconstructing a high-resolution multispectral (HRMS) image with both high spatial clarity and high spectral fidelity. In recent years, diffusion models have shown great potential in image generation. However, existing diffusion-based pansharpening methods usually adopt a fixed denoising strategy, making it difficult to adapt to the stage-wise changes in the denoising process and complex degradation distributions. Based on this, we propose PanDiM, an efficient generative framework for pansharpening. Specifically, we reformulate pansharpening as a high-frequency residual restoration process constrained by multimodal conditions. To improve the response accuracy of the model in complex regions, we design a Degradation-Posterior Guidance Module (DPGM), which extracts dual-scale physical detail priors from the PAN image, explicitly infers the degradation posterior, and converts it into dynamic control variables to adaptively regulate the state evolution of Mamba. In addition, we propose a time-aware mechanism, which allows temporal information to directly intervene in posterior estimation and state-space modeling, so as to accurately match the modeling requirements of different denoising stages. Considering the characteristics of residual reconstruction, we further propose a frequency-decoupled loss (FDL), which separates low- and high-frequency components in the frequency domain and applies targeted constraints. This significantly enhances the model’s ability to represent textures and achieves more robust spectral fidelity. Extensive experiments on three benchmark datasets, including WorldView-3, GaoFen-2, and QuickBird, show that PanDiM significantly outperforms existing mainstream methods in both reduced-resolution and full-resolution evaluations, providing a new solution for high-fidelity pansharpening in complex scenarios. Full article

RGB-T object detection combines visible texture information with thermal saliency cues to improve detection under degraded illumination. Existing RGB-T fusion methods usually perform feature interaction in the spatial domain or treat spectral responses jointly, which may allow coarse background components to dominate the fusion process while weakening boundary and small-target details. In addition, the repeated upsampling and aggregation operations in the detection neck can further smooth high-frequency responses preserved during early fusion. This paper proposes F²Net, a frequency-guided RGB-T object detection framework built on a dual-stream YOLOv11s architecture. The method decomposes RGB and thermal features into low- and high-frequency components for separate cross-modal fusion, mitigates detail attenuation during neck decoding, and regularizes spatial correspondence between RGB and thermal representations during training. On M3FD, F²Net achieves 89.6% mAP@0.5 and 62.1% mAP@0.5:0.95, improving the Dual-YOLOv11s baseline by 7.7 and 6.6 percentage points, respectively, while increasing the parameter count from 13.8M to 15.4M and GFLOPs from 33.9G to 35.6G. Additional experiments on LLVIP and KAIST evaluate the method under low-light and road-scene conditions. The KAIST results show that high-IoU localization remains challenging in dense and occluded pedestrian scenes. This indicates that frequency-guided fusion mainly strengthens target response generation and moderate-IoU detection, but it does not fully solve precise boundary regression under severe occlusion and weak contour conditions. Full article

Melon (Cucumis melo L.) is a globally significant horticultural crop, characterized by high nutritional value and substantial commercial status. However, frequent outbreaks of powdery mildew severely threaten its yield and fruit quality. Current early detection methods primarily focus on detached leaf assays, which often lack sufficient model generalization. This study proposes a temporal 3D multispectral point cloud reconstruction method for melon plants by integrating multispectral imaging with 3D reconstruction technology. An Artificial Neural Network (ANN) model for 3D spatial light field distribution was developed based on a hemispherical white reference to achieve precise reflectance calibration of the multispectral point clouds. Post-calibration, the coefficient of variation (CV) for the spectral reflectance of the hemispherical reference in 3D space was reduced to less than 2.4%. On this basis, an early classification model for melon powdery mildew was constructed using Partial Least Squares Discriminant Analysis (PLS-DA) based on the mean reflectance spectra of individual plant point clouds. The results demonstrate that the average recognition accuracy reaches 85.94% from 4 days post-inoculation onwards, enabling disease early warning three days in advance. This research provides critical theoretical support and technical reference for the non-destructive early monitoring and precision smart plant protection of crops in facility agriculture. Full article

Multispectral temperature measurement technology based on blackbody radiation theory has been widely applied in the field of non-contact temperature measurement. However, its applicability is limited by the single-point measurement mode. To address this limitation, this study developed a spectral fusion temperature measurement device and proposed a new method for reconstructing the two-dimensional temperature field of deflagration fireballs by fusing spectral and imaging data. The device adopts a CCD sensor and a fiber optic spectrometer placed in parallel with parallel optical axes. To ensure the accuracy of the CCD’s response characteristics at different distances, the photo-response non-uniformity (PRNU) calculation method was used for precision validation. In this study, spectral and imaging data of deflagration fireballs were obtained through experiments. Spectral data of consecutive frames at 189 ms, 192 ms, 195 ms, and 198 ms were extracted and analyzed, confirming that the temperature range at the four time points is 1050 K to 1800 K. The proposed method generates temperature elements with equal temperature intervals and their probabilities within the temperature range, and calculates the theoretical radiation spectrum of each element. Then, least squares optimization fitting is performed on the experimentally measured spectra to obtain the optimal probabilities of the temperature elements in the temperature field. By combining these optimal probabilities with CCD grayscale images, the 2D temperature distribution of the deflagration fireball was reconstructed. Results show that: the PRNU value of the device at a distance of 9 m is less than 2.2% through experimental verification; fused images of the temperature field spectra of four consecutive frames of the deflagration fireball were obtained using the proposed method. The average temperatures reconstructed by the proposed method at 189 ms, 192 ms, 195 ms, and 198 ms were 1382 K, 1373 K, 1366 K, and 1357 K, respectively, while the corresponding temperatures obtained by conventional spectral inversion were 1430 K, 1422 K, 1414 K, and 1406 K. The relative errors were 3.2%, 3.4%, 3.3%, and 3.4%, respectively, with an average relative error of approximately 3.3%. Full article

A geometry-aware deep learning framework for the reduction of atmospheric noise in SAR (Synthetic Aperture Radar) interferograms has been proposed and validated in this study. Our model has obvious advantages over existing ones in the following three aspects: (1) our objective is to reconstruct the original SAR imagery using an autoencoder and then eliminate noise by subtracting the reconstructed data from the raw data. However, our network architecture is not symmetric, and we choose to employ HRNet-w32 to preserve the details of the input dataset. (2) A deep supervision module equipped with diverse feature-unleashing mechanisms (including geometric, multispectral, and sematic features) is also developed to enhance the model’s predictive capability and interpretability. (3) We emphasize the significance of fractal geometry and variogram inference in the loss function, given that atmospheric disturbances, specifically humidity, clouds, and fogs, often exhibit statistically fractal characteristics. Compared with existing methods and ablation studies, our framework achieves relatively robust APS suppression performance across multiple quantitative metrics, including the Mean Squared Error (MSE), Nash–Sutcliffe Efficiency (NSE), Mean Absolute Error (MAE), Structural Similarity Index (SSIM), and Coefficient of Correlation (CoC), with improvements of at least 5.0% over the baselines. Full article

As the role of remote sensing continues to grow, the fusion technology of low-spatial-resolution hyperspectral images and high-spatial-resolution multispectral images has become increasingly critical. Traditional methods rely on fixed rules and exhibit poor robustness, whereas deep learning methods struggle to establish efficient interactions between local and global information due to the complexity of their underlying networks. Therefore, we propose a deep learning fusion module that combines pixel-wise adaptive wavelet transform with a spectral–spatial dual-branch extraction. Firstly, by utilizing the unique properties of the wavelet transform, it is possible to effectively preserve spectral information and extract spatial edge features, thereby achieving preliminary fusion by leveraging both low-frequency and high-frequency components. To compensate for the lack of nonlinear expression capability in the wavelet transform, a dual-branch parallel extraction of spectral and spatial features is subsequently performed in the deep learning module. The Multi-Scale Group Convolution module (MSGC) is utilized to extract spectral information, while the Spectral Compression and Spatially Guided Gating Module (SCSGM) is employed to extract spatial information, thereby enhancing the data’s adaptive capability. A bidirectional attention mechanism is interspersed within the module to capture complementary information across different scales, ultimately reconstructing a high-resolution hyperspectral image. Finally, the proposed fusion strategy demonstrates superior performance in practical image reconstruction, outperforming more than ten state-of-the-art fusion methods. Full article

Coastal urbanization is increasingly constrained by legacy land-use patterns and escalating climate risks, yet long-term morphological trajectories remain poorly quantified due to the absence of multispectral data in pre-satellite archives. This study introduces a scalable deep learning pipeline that bridges a century-scale domain gap through an attention-enhanced Pix2Pix colorization stage and a few-shot U-Net++ segmentation stage, enabling automated reconstruction of urban expansion from panchromatic historical aerial imagery (1920–1971) and digital aerial photographs (1997) to contemporary very-high-resolution satellite data (2024) in Les Sables-d’Olonne, France. The novelty of the approach lies in coupling generative colorization with epoch-specific fine-tuning to overcome radiometric and annotation bottlenecks that have historically prevented quantitative urban reconstruction from pre-satellite archives. The colorization stage achieved high spectral fidelity (PSNR 35.21 dB, SSIM 0.9762), and segmentation performed strongly on modern imagery (mIoU 0.9789). While the segmentation model performed strongly on modern imagery, direct transfer to historical data exhibited substantial domain shift due to radiometric discrepancies. Few-shot adaptation on year-specific calibration sets recovered reliable building footprints (mIoU 0.53–0.65) across the full timeline. Multi-scalar analysis of the reconstructed footprints revealed constrained anisotropic expansion: early saturation of the coastal historic core, followed by rapid inland peri-urbanization post-1971 driven by geographic barriers. This spatiotemporal shift has entrenched spatial lock-in, placing recent development in retro-littoral zones that are vulnerable to submersion and characterized by severe vegetation loss. The framework unlocks previously inaccessible historical archives for quantitative urban monitoring, providing critical insights into legacy effects of unconstrained growth and informing resilient coastal planning under climate change. Full article

High-resolution imagery is essential for monitoring heterogeneous grassland ecosystems, yet the performance of generative adversarial network (GAN) super-resolution under varying landscape heterogeneity and operational application scenarios remains unclear. This study presents a landscape-aware evaluation of super-resolution methods in semi-arid savanna grasslands of the Edwards Plateau (Texas, USA) using paired multispectral imagery from PlanetScope (3 m) and unmanned aerial vehicle (UAV) platforms (0.03 m). Two GAN models, SRGAN and ESRGAN, were compared with a bicubic interpolation baseline. Image tiles were systematically stratified along ecologically relevant gradients of vegetation condition (NDVI quartiles), spatial structure (woody patch-based clusters), and textural complexity (GLCM entropy quartiles). Model performance was evaluated across three operational frameworks: intra-sensor downscaling, cross-sensor downscaling, and intra-to-cross generalization. Reconstruction fidelity was quantified using peak signal-to-noise ratio (PSNR) and structural similarity index (SSIM), complemented by variability analysis to assess performance stability. Landscape heterogeneity strongly influenced downscaling outcomes. SRGAN performance declined in areas with dense vegetation, aggregated woody structure, and high-entropy textures, with large variability under cross-sensor and generalization scenarios. In contrast, ESRGAN demonstrated consistently robust performance across landscape gradients, whereas bicubic interpolation performed well only under intra-sensor conditions and drastically degraded under sensor transfer. These results demonstrate that vegetation condition, structural heterogeneity, and sensor-transfer scenarios jointly constrain super-resolution performance. Rather than serving as a model comparison exercise, this study emphasizes a landscape-aware framework for understanding how ecological heterogeneity and operational domain shifts jointly shape super-resolution behavior in grassland ecosystems, providing guidance for more reliable applications of deep learning-based remote sensing methods. Full article

Weed interference during early growth stages is a major constraint on sugarcane productivity, yet effective tools for species-specific detection remain limited in tropical agricultural systems. This study evaluated the spectral separability between Sugarcane (Saccharum officinarum) and a dominant weed species, Rottboellia cochinchinensis, to develop an accessible framework for early-stage weed mapping. Multispectral data acquired from an Unmanned Aerial Vehicle (UAV) and hyperspectral data obtained from a field spectrometer were utilized. Hyperspectral data were synthesized to reconstruct multispectral bands (UAV image bands) using a regularized linear synthesis model, thereby generating spectral signatures. Spectral separability between sugarcane and Rottboellia cochinchinensis was assessed visually and statistically (Jeffries–Matusita distance). Blue and Green bands provided the strongest differentiation between species, while RedEdge enhanced separability when paired with pigment-sensitive wavelengths. When using vegetation indices based on the near-infrared (NIR) band, the visual appearance of class separation was poor due to the NIR band’s sensitivity to variation in leaf internal structure, canopy architecture, water content, and spectral mixing with the soil background at the early stage of sugarcane. These results were used to differentiate weed coverage from sugarcane. Object-based image analysis (OBIA) outperformed the pixel-based method, achieving higher overall accuracy (0.9038) and a more spatially coherent weed delineation (Kappa = 0.8499). These findings suggest that synthesized spectral signatures of Rottboellia cochinchinensis and sugarcane, combined with targeted spectral indices and OBIA techniques, offer a practical and transferable approach for early detection of Rottboellia cochinchinensis at the farm level. Full article

For studies utilizing methods such as water color parameter inversion and algal bloom classification, abundant spectral bands and high spectral resolution are of great significance. However, for multispectral satellite sensors that are not designed for water color studies (e.g., Sentinel-2 MSI), the number of bands in the visible–near-infrared range is limited, and lacks specific spectral bands with rich spectral information. Hyperspectral reconstruction of multispectral data based on hyperspectral remote sensing reflectance ($R_{rs}$) databases and machine learning algorithms have been proven to be a feasible solution. Based on the in situ measured $R_{rs}$ data, this study constructed a large-sample hyperspectral $R_{rs}$ database covering various optical water types using two Chinese hyperspectral satellites, and compared the spectral reconstruction accuracy of six machine learning algorithms. The results show that expanding the $R_{rs}$ database for model training by integrating hyperspectral satellite data can effectively improve the reconstruction accuracy in waters of different optical types. Comparisons with in situ measured hyperspectral $R_{rs}$ indicate that the reconstructed Sentinel-2 hyperspectral data achieve high accuracy, with the Spectral Angle Mapper (SAM) less than 5° and the correlation coefficient ($r$) higher than 0.7. Furthermore, the reconstructed data can effectively restore spectral information not captured by the original multispectral data, such as the suspended sediment $R_{rs}$ peak at 580 nm and the chlorophyll $R_{rs}$ valley at 680 nm. Through spectral reconstruction, the spectral resolution of Sentinel-2 can be maximized while retaining its advantages of fast revisit capability and high spatial resolution, thereby expanding its application potential in water color remote sensing. Full article

Due to the inherent limitations of both hyperspectral and multispectral imagery, balancing high spatial resolution with high spectral fidelity has become one of the fundamental challenges in remote sensing image processing. A prevailing strategy is to fuse these two types of data to reconstruct images that jointly preserve their respective advantages. However, existing reconstruction approaches still suffer from complex coupling between spatial and spectral information, and limited feature extraction capabilities. To address these issues, this study proposes PMSwinNet (Pyramid Multi-scale Swin Transformer Network), a novel architecture that integrates pyramid-based feature enhancement with Transformer mechanisms. The PMSwinNet incorporates multi-scale pyramid feature fusion and window-based self-attention. Through a progressive multi-stage design and three complementary components—feature extraction and reconstruction modules—the Transformer branch leverages window partitioning and shifting operations to capture long-range spatial dependencies and local contextual cues, while the pyramid features extract both global and local information across multiple spatial scales. In addition, a high-frequency branch is introduced, which employs lightweight convolutions to enhance edges, textures, and other high-frequency details, effectively suppressing blurring and artifacts during reconstruction. Experimental evaluations on multiple public hyperspectral datasets demonstrate that the PMSwinNet outperforms state-of-the-art methods, particularly in terms of detail preservation, spectral distortion suppression, and robustness. Full article

Conventional multispectral photodetectors typically rely on multiple electrical terminals to discriminate different wavelengths, which inevitably increases structural complexity. Here, we break this paradigm by demonstrating a dual-color visible–infrared photodetector based on a simple two-terminal Au/MoS₂/Te heterostructure. The device operates through a bias-switching mechanism: reversing the voltage polarity selectively activates either the MoS₂/Au Schottky junction for visible-light detection (520 nm) or the Te/MoS₂ heterojunction for infrared detection (1550 nm). This bias-controlled wavelength selectivity is unambiguously verified by scanning photocurrent mapping. Beyond dual-color discrimination, an adaptive convolutional neural network is employed to decode the nonlinear current–voltage characteristics and enable precise spectral identification, achieving a reconstruction error of approximately 4.5%. Furthermore, high-fidelity dual-color imaging is demonstrated at room temperature. These results establish a hardware–algorithm co-design strategy based on a minimalist two-terminal architecture, providing a viable route toward compact and intelligent spectral-sensing systems. Full article

Surface defects in high-temperature continuous cast billets are critical factors affecting the quality of steel products. Owing to high-temperature radiation, heavy dust contamination, varying billet specifications, and background interference from oxide scales and water stains, existing online surface defect detection technologies for high-temperature continuous cast billets still suffer from limitations including high false-positive rates, inefficient identification of pseudo-defects, and the inability to simultaneously detect three-dimensional (3D) depth information alongside two-dimensional (2D) features. To solve these problems, this paper proposes a multi-dimensional online detection technology for surface defects in high-temperature continuous cast billets based on multi-information fusion. A four-channel multispectral image sensor and a corresponding three-light-source imaging system were developed. Furthermore, a defect sample augmentation method, a deep learning-based 2D recognition method, and a photometric stereo-based 3D reconstruction method were designed to mitigate problems of low detection accuracy and poor robustness caused by sample imbalance among different defect types. Finally, industrial applications were conducted on large-section continuous cast billets, beam blanks, and billets during the grinding process. According to the surface defect detection requirements of different continuous cast billets, multispectral multi-information fusion and traditional 2D defect imaging methods were adopted respectively. The results demonstrate high-precision online detection of surface defects in continuous cast billets, with favorable practical application effects. Full article