Search Results (1,454)

Single-image super-resolution refers to the reconstruction of a high-resolution image from a single low-resolution observation. Although recent deep learning-based methods have demonstrated notable success on simulated datasets—with low-resolution images obtained by degrading and downsampling high-resolution ones—they frequently fail to generalize to real-world settings, such as document scans, which are affected by complex degradations and semantic variability. In this study, we introduce a task-driven, multi-task learning framework for training a super-resolution network specifically optimized for optical character recognition tasks. We propose to incorporate auxiliary loss functions derived from high-level vision tasks, including text detection using the connectionist text proposal network (CTPN), text recognition via a convolutional recurrent neural network (CRNN), keypoints localization using Key.Net, and hue consistency. To balance these diverse objectives, we employ a dynamic weight averaging (DWA) mechanism, which adaptively adjusts the relative importance of each loss term based on its convergence behavior. Experimental evaluation demonstrates that the proposed approach improves text detection, measured with intersection over union, by 1.09% for simulated and 1.94% for real-world datasets containing scanned documents, while preserving overall image fidelity. These improvements are statistically significant as confirmed by the Kruskal–Wallis H test and the post hoc Dunn test with Benjamini–Hochberg p-value correction. Our findings highlight the value of multi-objective optimization in super-resolution models for bridging the gap between simulated training regimes and practical deployment in real-world scenarios. Full article

The efficient recognition of unpaved roads from remote sensing (RS) images holds significant value for tasks such as emergency response and route planning in outdoor environments. However, unpaved roads often face challenges such as blurred boundaries, low contrast, complex shapes, and a lack of publicly available datasets. To address these issues, this paper proposes a novel architecture, Swin-FSNet, which combines frequency analysis and spatial enhancement techniques to optimize feature extraction. The architecture consists of two core modules: the Wavelet-Based Feature Decomposer (WBFD) module and the Hybrid Dynamic Snake Block (HyDS-B) module. The WBFD module enhances boundary detection by capturing directional gradient changes at the road edges and extracting high-frequency features, effectively addressing boundary blurring and low contrast. The HyDS-B module, by adaptively adjusting the receptive field, performs spatial modeling for complex-shaped roads, significantly improving adaptability to narrow road curvatures. In this study, the southern mountainous area of Shihezi, Xinjiang, was selected as the study area, and the unpaved road dataset was constructed using high-resolution UAV images. Experimental results on the SHZ unpaved road dataset and the widely used DeepGlobe dataset show that Swin-FSNet performs well in segmentation accuracy and road structure preservation, with an IoU_road of 81.76% and 71.97%, respectively. The experiments validate the excellent performance and robustness of Swin-FSNet in extracting unpaved roads from high-resolution RS images. Full article

When a CMOS (Complementary Metal–Oxide–Semiconductor) imaging system operates at a high frame rate or a high line rate, the exposure time of the imaging system is limited, and the acquired image data will be dark, with a low signal-to-noise ratio and unsatisfactory sharpness. Therefore, in order to improve the visibility and signal-to-noise ratio of remote sensing images based on CMOS imaging systems, this paper proposes a low-light remote sensing image enhancement method and a corresponding ZYNQ (Zynq-7000 All Programmable SoC) design scheme called the BGIR (Bilateral-Guided Image Restoration) algorithm, which uses an improved multi-scale Retinex algorithm in the HSV (hue–saturation–value) color space. First, the RGB image is used to separate the original image’s H, S, and V components. Then, the V component is processed using the improved algorithm based on bilateral filtering. The image is then adjusted using the gamma correction algorithm to make preliminary adjustments to the brightness and contrast of the whole image, and the S component is processed using segmented linear enhancement to obtain the base layer. The algorithm is also deployed to ZYNQ using ARM + FPGA software synergy, reasonably allocating each algorithm module and accelerating the algorithm by using a lookup table and constructing a pipeline. The experimental results show that the proposed method improves processing speed by nearly 30 times while maintaining the recovery effect, which has the advantages of fast processing speed, miniaturization, embeddability, and portability. Following the end-to-end deployment, the processing speeds for resolutions of 640 × 480 and 1280 × 720 are shown to reach 80 fps and 30 fps, respectively, thereby satisfying the performance requirements of the imaging system. Full article

Agriculture accounts for 29% of the Gross Domestic Product of the Nusa Tenggara Islands (NTIs). However, recurring agricultural droughts pose a major threat to the sustainability of agriculture in this region. The interplay between precipitation, solar radiation, and surface temperature as meteorological factors plays a key role in affecting vegetation (Soil-Adjusted Vegetation Index) and agricultural drought (Temperature Vegetation Dryness Index) in the NTIs. Based on the analyses of interplay with temporal lag, this study investigates the effect of each factor on agricultural drought and attempts to provide early warnings regarding drought in the NTIs. We collected surface information data from Moderate-Resolution Imaging Spectroradiometer (MODIS). Meanwhile, rainfall was estimated from Himawari-8 based on the INSAT Multi-Spectral Rainfall Algorithm (IMSRA). The results showed reliable performance for 8-day and monthly scales against gauges. The drought analysis results reveal that the NTIs suffer from mild-to-moderate droughts, where cropland is the most vulnerable, causing shifts in the rice cropping season. The driving factors could also explain >60% of the vegetation and surface-dryness conditions. Furthermore, our monthly and 8-day TVDI estimation models could capture spatial drought patterns consistent with MODIS, with coefficient of determination (R²) values of more than 0.64. The low error rates and the ability to capture the spatial distribution of droughts, especially in open-land vegetation, highlight the potential of these models to provide an estimation of agricultural drought. Full article

Object detection technology enables the automatic identification of photovoltaic (PV) panel locations and conditions, significantly enhancing operational efficiency for maintenance teams while reducing the time and cost associated with manual inspections. Challenges arise due to the low resolution of remote sensing images combined with small-sized targets—PV panels intertwined with complex urban or natural backgrounds. To address this, a parallel architecture model based on YOLOv5 was designed, substituting traditional residual connections with parallel convolution structures to enhance feature extraction capabilities and information transmission efficiency. Drawing inspiration from the bottleneck design concept, a primary feature extraction module framework was constructed to optimize the model’s deep learning capacity. The improved model achieved a 4.3% increase in mAP, a 0.07 rise in F1 score, a 6.55% enhancement in recall rate, and a 6.2% improvement in precision. Additionally, the study validated the model’s performance and examined the impact of different loss functions on it, explored learning rate adjustment strategies under various scenarios, and analyzed how individual factors affect learning rate decay during its initial stages. This research notably optimizes detection accuracy and efficiency, holding promise for application in large-scale intelligent PV power station maintenance systems and providing reliable technical support for clean energy infrastructure management. Full article

Cities house more than half of the world’s population and are responsible for more than 70% of the world anthropogenic CO₂ emissions. Therefore, quantifications of emissions from major cities, which are only less than a hundred intense emitting spots across the globe, should allow us to monitor changes in global fossil fuel CO₂ emissions in an independent, objective way. The study adopted a high-spatiotemporal-resolution regional assimilation method using satellite observation data and atmospheric transport model WRF-Chem/DART to assimilate CO₂ concentration and fluxes in Lisbon, a major city in Portugal. It is based on Zhang’s assimilation method, combined OCO-2 XCO₂ retrieval data, ODIAC 1 km anthropogenic CO₂ emissions and Ensemble Adjustment Kalman Filter Assimilation. By employing three two-way nested domains in WRF-Chem, we refined the spatial resolution of the CO₂ concentrations and fluxes over Lisbon to 3 km. The spatiotemporal distribution characteristics and main driving factors of CO₂ concentrations and fluxes in Lisbon and its surrounding cities and countries were analyzed in March 2020, during the period affected by COVID-19 pandemic. The results showed that the monthly average CO₂ and XCO₂ concentrations in Lisbon were 420.66 ppm and 413.88 ppm, respectively, and the total flux was 0.50 Tg CO₂. From a wider perspective, the findings provide a scientific foundation for urban carbon emission management and policy-making. Full article

In practical array signal processing applications, direction-of-arrival (DOA) estimation often suffers from degraded accuracy under low signal-to-noise ratio (SNR) and limited snapshot conditions. To address these challenges, we propose an off-grid DOA estimation method based on Fast Variational Bayesian Inference (OGFVBI). Within the variational Bayesian framework, we design a fixed-point criterion rooted in root-finding theory to accelerate the convergence of hyperparameter learning. We further introduce a grid fission and adaptive refinement strategy to dynamically adjust the sparse representation, effectively alleviating grid mismatch issues in traditional off-grid approaches. To address frequency dispersion in wideband signals, we develop an improved subspace focusing technique that transforms multi-frequency data into an equivalent narrowband model, enhancing compatibility with subspace DOA estimators. We demonstrate through simulations that OGFVBI achieves high estimation accuracy and resolution while significantly reducing computational time. Specifically, our method achieves more than 37.6% reduction in RMSE and at least 28.5% runtime improvement compared to other methods under low SNR and limited snapshot scenarios, indicating strong potential for real-time and resource-constrained applications. Full article

Introduction: Delirium is a common and debilitating clinical complication among ICU patients. Despite the prevalence of this condition, there are insufficient data to support or refute the routine use of atypical antipsychotics since the existing evidence remains sparse and inconclusive. The objective of the present study was to evaluate whether pre-ICU administration of the atypical antipsychotic olanzapine is associated with a differential time to delirium resolution relative to the control condition. Methods: In this emulated clinical trial, we utilized the MIMIC-IV v3.1 database, which contains deidentified health records from approximately 65,000 ICU patients, to derive a cohort of patients with a positive delirium screening within 24 h of ICU admission. We exluded patients who received any antipsychotic other than olanzapine prior to ICU admission. We performed propensity score matching using logistic regression and nearest-neighbor matching (1:1, caliper = 0.2) to balance covariates between the olanzapine and control groups. The primary outcome was time to delirium resolution, defined as the first negative delirium assessment. A Cox proportional hazards model, adjusted for multiple covariates and incorporating age as a time-dependent variable, was used to examine the association between olanzapine use and delirium resolution. Interaction terms were included to evaluate effect modification by age and gender. Results: A total of 5070 patients with a positive delirium screening within 24 h and no exposure to other antipsychotics met the eligibility criteria; 421 olanzapine users were matched to 421 controls using propensity score matching. Covariate balance was achieved (all standardized mean differences < 0.1), and no multicollinearity was detected (all VIFs < 2). Pre-ICU olanzapine use was associated with a 27% decrease in the likelihood of delirium resolution (HR = 0.73; 95% CI: 0.63–0.86; p < 0.001). A significant interaction with age indicated that the negative impact of olanzapine on delirium resolution increased with advancing age (HR = 1.0024 per unit of age × log(time), p = 0.023), translating to a 2.4% increase in the risk of prolonged delirium resolution for every 10-year increase in age per log(time). There was no modification of the association according to gender. Discussion: The negative effect of olanzapine on ICU delirium resolution, particularly among the elderly, presented in this study is in line with the results of our earlier study showing a negative effect (i.e., prolonged ICU stay) among patients receiving quetiapine relative to both control and haloperidol conditions. Distinctly strong anticholinergic effects of both olanzapine and quetiapine relative to the other antipsychotic agents may be driving the identified negative outcomes. Conclusions: Results of this emulated clinical trial do not support the use of olanzapine for the treatment of ICU delirium because the agent prolongs time to resolution of the condition. Full article

Advanced Synthetic Aperture Radar (SAR) has become an essential modality in remote sensing, offering all-weather capabilities and sensitivity to vegetation biophysical parameters and surface conditions, while effectively complementing optical sensor data. This study evaluates the impact of precipitation on the Normalized Polarimetric Radar Vegetation Index (NPRVI) using dual-polarization Sentinel-1 C-band SAR data from agricultural fields at the Beltsville Agricultural Research Center (BARC). Field-measured precipitation and Global Precipitation Measurement (GPM) precipitation datasets were temporally aligned with Sentinel-1 acquisition times to assess the sensitivity of radar signals to precipitation events. NPRVI exhibited a strong sensitivity to precipitation, particularly within the 1 to 7 h prior to the satellite overpass, even for small amounts of precipitation. A quality assessment (QA) framework was developed to flag and correct precipitation-affected radar observations through interpolation. The adjusted NPRVI values, based on the QA framework using precipitation within a 6 h window, showed strong agreement between field- and GPM-derived data, with an RMSE of 0.09 and a relative RMSE of 19.8%, demonstrating that GPM data can serve as a viable alternative for quality adjustment despite its coarse spatial resolution. The adjusted NPRVI for both soybean and corn fields significantly improved the temporal consistency of the time series and closely followed NDVI trends, while also capturing crop-specific seasonal variations, especially during periods of NDVI saturation or limited variability. These findings underscore the value of the proposed radar-based QA framework in enhancing the interpretability of vegetation dynamics. NPRVI, when adjusted for precipitation effects, can serve as a reliable and complementary tool to optical vegetation indices in agricultural and environmental monitoring. Full article

The trade-off between resolution and contrast is a transcendental problem in optical imaging, spanning from artistic photography to technoscientific applications. To the latter, Fourier-optics-based filters, such as the 4f system, are well-known for their image-enhancement properties, removing high spatial frequencies from an optically Fourier-transformed light signal through simple aperture adjustment. Nonetheless, assessing the contrast–resolution balance in optical imaging remains a challenging task, often requiring complex mathematical treatment and controlled laboratory conditions to match theoretical predictions. With that in mind, we propose a simple yet robust analytical technique to determine the optimal aperture in a 4f imaging system for static and quasi-static objects. Our technique employs the mathematical formalism of the H-theorem, enabling us to directly access the information of an imaged object. By varying the aperture at the Fourier plane of the 4f system, we have empirically found an optimal aperture region where the imaging entropy is maximum, given that the object is fitted to the imaged area. At that region, the image is lit and well-resolved, and no further aperture decrease improves that, as information of the whole assembly (object plus imaging system) is maximum. With that analysis, we have also been able to investigate how the imperfections in an object affect the entropy during its imaging. Despite its simplicity, our technique is generally applicable and passable for automation, making it interesting for many imaging-based optical devices. Full article

Metasurface display, a kind of unique imaging technique with subwavelength scale, plays a key role in data storage, information processing, and optical imaging due to the superior performance of high resolution, miniaturization, and integration. Recent works about grayscale imaging as a typical metasurface display have showcased an excellent performance for optical integrated devices in the near field. However, chiral grayscale imaging has been rarely elucidated, especially using a single structure. Here, a novel method is proposed to display a continuously chiral grayscale imaging that is adjusted by a metasurface consisting of a single chiral structure with optimized geometric parameters. The simulation results show that the incident light can be nearly converted into its cross-polarized reflection when the chiral structural variable parameters are α = 80° and β = 45°. The versatile metasurface can arbitrarily and independently realize the spin-selective manipulation of wavelength and amplitude of circularly polarized light. Due to the excellent manipulation ability of the versatile metasurface, a kind of circularly polarized light detection and a two-channel encoded display with different operating wavelengths are presented. More importantly, this versatile metasurface can also be used to show high-resolution chiral grayscale imaging, which distinguishes it from the results of previous grayscale imaging studies about linearly polarized incident illumination. The proposed versatile metasurface of spin-selective manipulation, with the advantages of high resolution, large capacity, and monolithic integration, provides a novel way for polarization detection, optical display, information storage, and other relevant fields. Full article

Aiming at the issues that the field mill type electric field sensor lacks an accurate and complete mathematical model, and its signal is weak and contains a large amount of harmonic noise, on the basis of establishing the mathematical model of the sensor’s induction electrode, the finite element method was adopted to analyze the influence laws of parameters such as the thickness of the shielding electrode and the distance between the induction electrode and the shielding electrode on the sensor sensitivity. On this basis, the above parameters were optimized. A signal processing circuit incorporating a pre-integral transformation circuit, a differential amplification circuit, and a bias circuit was investigated, and a completed mathematical model of the input and output of the field mill type electric field sensor was established. An improved harmonic detection method combining fast Fourier transform and back propagation neural network (FFT-BP) was proposed, the learning rate, momentum factor, and excitation function jointly participated in the adjustment of the network, and the iterative search range of the algorithm was limited by the threshold interval, further improving the accuracy and rapidity of the sensor measurement. Experimental results indicate that within the simulated electric field intensity range of 0–20 kV/m in the laboratory, the measurement resolution of this system can reach 18.7 V/m, and the measurement linearity is more than 99%. The designed system is capable of measuring the atmospheric electric field intensity in real time, providing necessary data support for lightning monitoring and early warning. Full article

This study assesses the use of Quantile-Mapping methods for bias correction and downscaling in climate change studies. A “Perfect Model Experiment” is conducted using high-resolution climate simulations as pseudo-references and coarser versions as biased data. The focus is on European daily temperature and precipitation under the RCP 8.5 scenario. Six methods are tested: an empirical Quantile-Mapping approach, the “Cumulative Distribution Function—transform” (CDF-t) method, and four CDF-t variants with different parameters. Their performance is evaluated based on univariate and multivariate properties over the calibration period (1981–2010) and a future period (2071–2100). The results show that while Quantile Mapping and CDF-t perform similarly during calibration, significant differences arise in future projections. Quantile Mapping exhibits biases in the means, standard deviations, and extremes, failing to capture the climate change signal. CDF-t and its variants show smaller biases, with one variant proving particularly robust. The choice of discretization parameter in CDF-t is crucial, as the low number of bins increases the biases. This study concludes that Quantile Mapping is not appropriate for adjustments in a climate change context, whereas CDF-t, especially a variant that stabilizes extremes, offers a more reliable alternative. Full article

Climate variations impact the preservation of heritage buildings, necessitating a strategic understanding of potential effects to effectively guide preservation efforts. This study analyzes temperature- and precipitation-dependent climate-heritage indices in Trentino–South Tyrol using EURO-CORDEX regional climate models for the period 1971–2100 under RCP 4.5 and RCP 8.5 scenarios. The selected indices were calculated with climdex-kit and relied on bias-adjusted temperature and precipitation data with a 1 km spatial resolution. The obtained results indicate a geographically punctuated increase in biomass accumulation on horizontal surfaces, a slight decreasing trend in freeze–thaw events, an increase in growing degree days indicating a small, heightened insect activity, and a rise in heavy precipitation days. The Scheffer Index shows a significantly increased potential for wood degradation, particularly under the RCP 8.5 scenario, while the Wet-Frost Index remains consistently low. Finally, according to each identified hazard, adaptive solutions are suggested. These findings provide critical insights into future climate impacts on heritage buildings in the region, aiding stakeholders in planning targeted interventions. The study emphasizes the crucial role of integrating detailed climate data into heritage preservation strategies, advocating for the inclusion of future risk analysis in the “knowledge path” in order to enhance the resilience of buildings. Full article

Hyperspectral imaging (HSI) is a powerful tool for precision imaging tasks such as vegetation analysis, but its widespread use remains limited due to the high cost of equipment and challenges in data acquisition. To explore a more accessible alternative, we propose a Green Normalized Difference Vegetation Index (GNDVI)-guided green channel adjustment method, termed G-RGB, which enables the estimation of near-infrared (NIR) reflectance from standard RGB image inputs. The G-RGB method enhances the green channel to encode NIR-like information, generating a spectrally enriched representation. Building on this, we introduce FUSE-Net, a novel deep learning model that combines multi-scale convolutional layers and MLP-Mixer-based channel learning to effectively model spatial and spectral dependencies. For evaluation, we constructed a high-resolution RGB-HSI paired dataset by capturing basil leaves under controlled conditions. Through ablation studies and band combination analysis, we assessed the model’s ability to recover spectral information. The experimental results showed that the G-RGB input consistently outperformed unmodified RGB across multiple metrics, including mean squared error (MSE), peak signal-to-noise ratio (PSNR), spectral correlation coefficient (SCC), and structural similarity (SSIM), with the best performance observed when paired with FUSE-Net. While our method does not replace true NIR data, it offers a viable approximation during inference when only RGB images are available, supporting cost-effective analysis in scenarios where HSI systems are inaccessible. Full article