Search Results (164)

On university campuses, trees and green spaces shape how students and staff move and use outdoor spaces. To support planning, tree species information is needed at the level of individual trees. Tree species classification from UAV RGB imagery remains difficult in complex campus scenes because roads, buildings, shadows and subtle inter species differences degrade recognition. To address background interference, the loss of subtle fine-grained cues before tokenization, and insufficient local structure modeling in lightweight transformer-based classification, we propose TreeSpecViT for tree species classification. It uses a MobileViT backbone and a Background Suppression Module (BSM) to reduce clutter from non-canopy regions. A Fine-Grained Feature Guidance (FGF) module is inserted before the unfold operation to enhance canopy details and guide tokenization toward key regions. $1\times 1$ convolutional neck layers align channels, and a Global and Local Fusion (GLF) module jointly models overall crown semantics and local textures for species recognition. From the predicted masks and species labels, we build an individual tree digital archive. The archive stores per tree geometric attributes and can be linked with grids of campus activity intensity to analyze how activity patterns relate to vegetation structure. TreeSpecViT achieves an Accuracy of 87.88% (+6.06%) and an F1 score of 76.48% (+5.08%) on the SZUTreeDataset. On our self constructed NJFUDataset, it reaches 76.30% (+5.10%) in Accuracy and 70.10% (+7.20%) in F1. These results surpass mainstream models. Ablation experiments show that the modules jointly reduce background clutter and enhance canopy features. Overall, TreeSpecViT supports campus scale analyses that link human activity intensity to vegetation patterns and provides a practical basis for planning and adjusting campus green spaces. Full article

Traditional concert-hall evaluations primarily rely on ISO 3382-1 scalar parameters (e.g., C₅₀ and C₈₀), which summarize temporal energy behavior but provide limited insight into the directional composition of early reflections, particularly in geometrically shadowed seating zones. This paper presents a first-order Ambisonics (FOA)-based 3D acoustic sensing framework to diagnose under-balcony directional imbalance, with emphasis on early vertical-reflection deficiency. Scene-based FOA impulse responses (WXYZ) were measured at 11 audience positions (P1–P11) in the National Concert Hall (Taipei) and analyzed using intensity-based direction-of-arrival (DoA) proxies, axis-resolved directional energy build-up, and a distributional descriptor based on directional spatial entropy. Results are presented at three representative frequencies (125 Hz, 1 kHz, and 4 kHz) and analyzed within full (0–200 ms), early (0–80 ms), and late (80–200 ms) windows. While the magnitude proxy $\mid p^{meas}\left(f\right)\mid$ exhibits strong seat-to-seat variability and does not support a uniform attenuation assumption under the balcony, direction-resolved metrics reveal a consistent under-balcony signature. Specifically, the early–late vertical energy discrepancy $\Delta R_z={\displaystyle R_z^{early}}-{\displaystyle R_z^{late}}$ is persistently negative at under-balcony positions (P7–P11) across all three frequencies, indicating a selective reduction in early vertical contribution relative to the late field. Directional entropy analysis further shows predominantly negative $\Delta H_n={\displaystyle H_n^{early}}-{\displaystyle H_n^{late}}$, with more negative values in the under-balcony group, consistent with stronger early directional constraint in shadowed seats. Spatial trend maps are provided via Gaussian RBF interpolation within the audience domain for visualization only. The proposed FOA-based diagnostic framework provides a practical and physically interpretable approach to identify direction-specific early-reflection deficits that remain masked in conventional scalar evaluations, supporting mechanism-oriented assessment and targeted intervention in geometrically constrained listening areas. Full article

Accurate apple detection and precise three-dimensional (3D) localisation are essential for autonomous robotic harvesting in orchard environments, where occlusion, illumination variation, depth noise, and the similar colour appearance of fruits and surrounding leaves present significant challenges. This paper proposes a dual-detector vision framework combined with depth-aware back-projection to achieve robust apple detection and metric 3D localisation in real time. The method integrates the complementary strengths of YOLOv8 and Mask R-CNN through confidence-weighted fusion of bounding boxes and pixel-wise union of segmentation masks, producing stabilised two-dimensional (2D) apple representations under visually ambiguous conditions. The fusion results are converted into dense 3D representations through depth-guided projection within the camera coordinate system representing the visible fruit surface. A depth-consistency weighting strategy assigns higher influence to depth-reliable pixels during centroid computation, thereby suppressing noisy or occluded depth measurements and improving the stability of 3D fruit centre estimation, while local intensity normalisation standardises neighbourhood-level pixel intensities to reduce the impact of shadows, highlights, and uneven lighting, enabling more consistent segmentation and detection across varying illumination conditions. Experimental results demonstrate an accuracy of 98.9%, an mAP of 94.2%, an F1-score of 93.3%, and a recall of 92.8%, while achieving real-time performance at 86.42 FPS, confirming the suitability of the proposed method for robotic harvesting in challenging orchard environments. Full article

Natural hydrogen has gained attention as a low-carbon energy vector, and some reported surface expressions have been linked to subcircular patterns, or fairy circles (FC), that may be detectable in multispectral satellite imagery. The Carolina Bays region, on the eastern coast of the United States, was selected because it hosts abundant, well-mapped subcircular depressions. This study aims to comparatively evaluate machine learning algorithms for identifying subcircular structures using Landsat-8 data. We processed 105 Collection 2 Level 2 scenes, masking clouds and shadows using the Level 2 quality band. Pixel-level labels were determined using a well-curated public dataset, derived from a high-resolution LiDAR survey. Traditional models (logistic regression, random forest, and multilayer perceptron) achieved precision scores below 0.66 and enabled a variable-importance analysis, which identified Band 3 (green), Band 6 (SWIR1), and five Normalised Unit Indices as the most predictive features. Deep learning models improved detection, and a U-Net architecture allowed for pixel-level segmentation of FC-like structures, producing false positives mostly in cloudy or shadowed areas. Overall, the results suggest that FC detection from multispectral data alone remains challenging due to class overlap and cloud/shadow contamination. Future work could explore integrating additional non-spectral descriptors, such as morphometric variables, to reduce ambiguities. Full article

Magnetron sputtering serves as a key method for fabricating functional thin films used in transparent film heaters. However, as heater designs become more intricate, achieving uniform film deposition on nonrectangular areas induces localized overheating owing to current density crowding, compromising long-term reliability of the device. To address this limitation, a simulation-assisted design and fabrication strategy is presented to realize a uniform temperature profile through the precise regulation of the sheet resistance distribution of the film. Initially, an electrothermal-coupled finite element model was established using COMSOL Multiphysics to inversely determine the spatial gradient of sheet resistance required for achieving a uniform thermal distribution. Subsequently, a custom-designed mesh shadow mask was used to locally adjust the flux of indium tin oxide (ITO) sputtered particles, enabling the establishment of a relationship between the mask’s aperture geometry and the resulting particle deposition profile. The magnetic field and plasma simulations were integrated to model particle transport and design a specialized gradient aperture-based shadow mask, enabling the deposition of an ITO film with a controlled sheet resistance gradient in a single magnetron sputtering step. Experimental results demonstrated that the proposed method decreased the maximum temperature variation by 8.25 °C and reduced the standard deviation of the surface temperature by 82.1% at an average temperature of 45 °C within a defined nonrectangular heating region, demonstrating a substantial improvement in temperature uniformity relative to conventional uniform coating processes. Full article

The integration of artificial intelligence (AI) with ultrasonic biosensing presents a transformative opportunity for enhancing diagnostic accuracy in agricultural and biomedical applications. This study develops a data-driven deep learning model to address the challenge of acoustic artifacts in B-mode ultrasound imaging, specifically for sow pregnancy diagnosis. We designed a biosensing system centered on a mechanical sector-scanning ultrasound probe (5.0 MHz) as the core biosensor for data acquisition. To overcome the limitations of traditional filtering methods, we introduced a lightweight Deep Neural Network (DNN) based on the YOLOv8 architecture, which was data-driven and trained on a purpose-built dataset of sow pregnancy ultrasound images featuring typical artifacts like reverberation and acoustic shadowing. The AI model functions as an intelligent detection layer that identifies and masks artifact regions while simultaneously detecting and annotating key anatomical features. This combined detection–masking approach enables artifact-aware visualization enhancement, where artifact regions are suppressed and diagnostic structures are highlighted for improved clinical interpretation. Experimental results demonstrate the superiority of our AI-enhanced approach, achieving a mean Intersection over Union (IOU) of 0.89, a Peak Signal-to-Noise Ratio (PSNR) of 34.2 dB, a Structural Similarity Index (SSIM) of 0.92, and clinically tested early gestation accuracy of 98.1%, significantly outperforming traditional methods (IoU: 0.65, PSNR: 28.5 dB, SSIM: 0.72, accuracy: 76.4). Crucially, the system maintains a single-image processing time of 22 ms, fulfilling the requirement for real-time clinical diagnosis. This research not only validates a robust AI-powered ultrasonic biosensing system for improving reproductive management in livestock but also establishes a reproducible, scalable framework for intelligent signal enhancement in broader biosensor applications. Full article

Semantic segmentation of high-resolution remote sensing imagery is a critical technology for the intelligent interpretation of sensor data, supporting automated environmental monitoring and urban sensing systems. However, processing data from dense urban scenarios remains challenging due to sensor signal occlusions (e.g., shadows) and the complexity of parsing multi-scale targets from optical sensors. Existing approaches often exhibit a trade-off between the accuracy of global semantic modeling and the precision of complex boundary recognition. While the Segment Anything Model (SAM) offers powerful zero-shot structural priors, its direct application to remote sensing is hindered by domain gaps and the lack of inherent semantic categorization. To address these limitations, we propose a dual-branch cooperative network, PriorSAM-DBNet. The main branch employs a Densely Connected Swin (DC-Swin) Transformer to capture cross-scale global features via a hierarchical shifted window attention mechanism. The auxiliary branch leverages SAM’s zero-shot capability to exploit structural universality, generating object-boundary masks as robust signal priors while bypassing semantic domain shifts. Crucially, we introduce a parameter-efficient Scaled Subsampling Projection (SSP) module that employs a weight-sharing mechanism to align cross-modal features, freezing the massive SAM backbone to ensure computational viability for practical sensor applications. Furthermore, a novel Attentive Cross-Modal Fusion (ACMF) module is designed to dynamically resolve semantic ambiguities by calibrating the global context with local structural priors. Extensive experiments on the ISPRS Vaihingen, Potsdam, and LoveDA-Urban datasets demonstrate that PriorSAM-DBNet outperforms state-of-the-art approaches. By fine-tuning only 0.91 million parameters in the auxiliary branch, our method achieves mIoU scores of 82.50%, 85.59%, and 53.36%, respectively. The proposed framework offers a scalable, high-precision solution for remote sensing semantic segmentation, particularly effective for disaster emergency response where rapid feature recognition from sensor streams is paramount. Full article

Background subtraction is a core preprocessing step for video analytics, enabling downstream tasks such as detection, tracking, and scene understanding in applications ranging from surveillance to transportation. However, real-time deployment remains challenging when illumination changes, shadows, and dynamic backgrounds produce heavy-tailed pixel variations that are difficult to capture with simple Gaussian assumptions. In this work, we propose a fully parallel GPU implementation of a per-pixel background model that represents temporal pixel deviations with lognormal distributions. During a short training phase, a circular buffer of n frames (as small as $n=3$) is used to estimate, for every pixel, robust log-domain parameters $(\mu ,\sigma )$. During testing, each incoming frame is compared against a robust reference (per-pixel median), and a lognormal cumulative density function yields a probabilistic foreground score that is thresholded to produce a binary mask. We evaluate the method on multiple videos under varying illumination and motion conditions and compare qualitatively with widely used mixture of Gaussians baselines (MOG and MOG2). Our method achieves, on average, 87 fps with a buffer size of 10, and reaches about 188 fps with a buffer size of 3, on an NVIDIA 3080 Ti. Finally, we discuss the accuracy–latency trade-off with larger buffers. Full article

High-resolution NICFI-Planet image collection on Google Earth Engine (GEE) promises fine-scale tropical forest monitoring, but persistent cloud covers, shadows, and haze undermine its value. Here, we present two simple, fully reproducible cloud-masking algorithms. We introduce (A) a Blue and Near-Infrared threshold and (B) a Sentinel-2-derived statistical thresholding approach that sets per-band cutoffs. Both are implemented end-to-end in GEE for operational use. The algorithms were first developed, tuned, and evaluated in the Sundarbans (Bangladesh) using strongly contrasting dry- and monsoon-season scenes. To assess their broader utility, we additionally tested them in two independent deltaic mangrove systems, namely, the Bidyadhari Delta in West Bengal, India, and the Ayeyarwady Delta in Myanmar. Across all sites, Algorithm B consistently removes the largest share of cloud and bright-water pixels but tends to over-mask haze and low-contrast features. Algorithm A retains more usable pixels; however, its aggressiveness is region-dependent. It appears more conservative in the Sundarbans but noticeably more over-inclusive in the India and Myanmar scenes. A Random Forest classifier provided map offers a useful reference but the model is dependent on the quantity and quality of labeled samples. The novelty of the algorithms lies in their design specifically for NICFI-Planet basemaps and their ability to operate without labeled samples. Because they rely on simple, fully shareable GEE code, they can be readily applied in regions in a consistent manner. These two algorithms offer a pragmatic operational pathway: apply them as a first-pass filter keeping in mind that its behavior may vary across environments. Full article

Wildfires are a recurring dry-season hazard in northern Thailand, contributing to severe air pollution and trans-boundary haze. However, the region lacks the ground-based measurements necessary for monitoring Live Fuel Moisture Content (LFMC), a key variable influencing vegetation flammability. This study presents a preliminary framework for near-real-time (NRT) LFMC estimation using Sentinel-2 multispectral imagery. The system integrates normalized vegetation and moisture-related indices, including the Normalized Difference Vegetation Index (NDVI), the Normalized Difference Infrared Index (NDII), and the Moisture Stress Index (MSI) with an NDVI-derived evapotranspiration fraction (ETf) within a heuristic modeling approach. The workflow includes cloud and shadow masking, weekly to biweekly compositing, and pixel-wise normalization to address the persistent cloud cover and heterogeneous land surfaces. Although currently unvalidated, the LFMC estimates capture the relative spatial and temporal variations in vegetation moisture across northern Thailand during the 2024 dry season (January–April). Evergreen forests maintained higher moisture levels, whereas deciduous forests and agricultural landscapes exhibited pronounced drying from January to March. Short-lag responses to rainfall suggest modest moisture recovery following precipitation, although the relationship is influenced by additional climatic and ecological factors not represented in the heuristic model. LFMC-derived moisture classes reflect broad seasonal dryness patterns but should not be interpreted as direct fire danger indicators. This study demonstrates the feasibility of generating regional LFMC indicators in a data-scarce tropical environment and outlines a clear pathway for future calibration and validation, including field sampling, statistical optimization, and benchmarking against global LFMC products. Until validated, the proposed NRT LFMC estimation product should be used to assess relative vegetation dryness and to support the refinement and development of future operational fire management tools, including early warnings, burn-permit regulation, and resource allocation. Full article

Ports pose distinctive monitoring challenges due to harsh marine conditions, mixed construction typologies, and heterogeneous ground conditions. These factors complicate the routine use of satellite InSAR, especially when medium-resolution scatterers must be reliably attributed to specific assets for risk and asset management decisions. In current practice, persistent and distributed scatterer (PS/DS) points are often interpreted in map view without an explicit positional uncertainty model or systematic linkage to three-dimensional infrastructure geometry. We present an end-to-end Differential InSAR framework tailored to large ports that fuses medium-resolution Sentinel-1 Level 2 Co-registered Single-Look Complex (L2-CSLC) stacks with high-resolution airborne LiDAR at the post-processing stage. For the Port of Bahía de Algeciras (Spain), we process 123 Sentinel-1A/B images (2020–2022) in ascending and descending geometry using PS/DS time-series analysis with ETAD-like timing corrections and RAiDER tropospheric/ionospheric mitigation. LiDAR is then used to (i) derive look-specific shadow/layover masks and (ii) perform a whitening-transformed nearest-neighbor association that assigns PS/DS points to LiDAR points under an explicit range–azimuth–cross-range (RAC) uncertainty ellipsoid. The RAC standard deviations $({\sigma }_r,{\sigma }_a,{\sigma }_c)$ are derived from the effective CSLC range/azimuth resolution and from empirical height correction statistics, providing a geometry- and data-informed prior on positional uncertainty. Finally, we render dual-geometry red–green composites (ascending to R, descending to G; shared normalization) on the LiDAR point cloud, enabling consistent inspection in plan and elevation. Across asset types, rigid steel/concrete elements (trestles, quay faces, and dolphins) sustain high coherence, small whitened offsets, and stable backscatter in both looks; cylindrical storage tanks are bright but exhibit look-dependent visibility and larger cross-range residuals due to height and curvature; and container yards and vessels show high amplitude dispersion and lower temporal coherence driven by operations. Overall, LiDAR-assisted whitening-based linking reduces effective positional ambiguity and improves structure-specific attribution for most scatterers across the port. The fusion products, geometry-aware linking plus three-dimensional dual-geometry RGB, enhance the interpretability of medium-resolution SAR and provide a transferable, port-oriented basis for integrating deformation evidence into risk and asset management workflows. Full article

This study develops a satellite-based, machine-learning-based prediction algorithm to predict optimal irrigation scheduling for cotton cultivation within Rahim Yar Khan, Pakistan. The framework leverages multispectral satellite imagery (Landsat 8 and Sentinel-2), GIS-derived climatic, land surface data and real-time weather information obtained from a freely accessible weather API, eliminating the need for ground-based IoT sensors. The proposed algorithm integrates FAO-56 evapotranspiration principles and water stress indices to accurately forecast irrigation requirements across the four critical growth stages of cotton. Supervised learning algorithms, including Gradient Boosting, Random Forest, and Logistic Regression, were evaluated, with Random Forest indicating better predictive accuracy with a coefficient of determination (R²) exceeding 0.92 and a root mean square error (RMSE) of approximately 415 kg/ha, owed its capacity to handle complex, non-linear relations, and feature interactions. The model was trained on data collected during 2023 and 2024, and its predictions for 2025 were validated against observed irrigation requirements. The proposed model enabled an average 12–18% reduction in total water application between 2023 and 2025, optimizing water use deprived of compromising crop yield. By merging satellite imagery, GIS data, and weather API information, this approach provides a cost-effective, scalable solution that enables precise, stage-specific irrigation scheduling. Cloud masking was executed by applying the built-in QA bands with the Fmask algorithm to eliminate cloud and cloud-shadow pixels in satellite imagery statistics. Time series were generated by compositing monthly median values to ensure consistency across images. The novelty of our study primarily focuses on its end-to-end integration framework, its application within semi-arid agronomic conditions, and its empirical validation and accuracy calculation over direct association of multi-source statistics with FAO-guided irrigation scheduling to support sustainable cotton cultivation. The quantification of irrigation capacity, determining how much water to apply, is identified as a focus for future research. Full article

With the development of extreme ultraviolet (EUV) lithography technology to higher numerical aperture (NA), it provides higher resolution imaging quality, which may be more sensitive to the phase defect in EUV mask. Therefore, it is necessary to comprehensively understand the effect of phase defect on the imaging quality depending on the NA. We simulated aerial images of patterned EUV masks for the EUV lithography exposure tool of NA = 0.55 and NA = 0.33 using the rigorous coupled-wave analysis (RCWA) method. The results shows that higher NA enhances the contrast of aerial images, which, in turn, provides greater tolerance for phase defect. This indicates that high NA can mitigate the negative impact of phase defect on imaging quality to some extent. Furthermore, it is found that both the defect signal and the intensity loss ratio of the aerial image first increase and then decrease as the width of the phase defect increases, due to the height/width ratio of the phase defect. Meanwhile, the defect width corresponding to the maximum phase defect signal tends to become smaller as the NA becomes larger. It is also worth noting that when NA = 0.33, variations in the position of the phase defect led to fluctuations in the CD error due to the shadow effect of the absorber, while it diminishes at NA = 0.55. This is because a higher NA of 0.55 provides a stronger background field, which suppresses the shadow effect of the absorber more effectively than it does at NA = 0.33. Full article

Ensuring the structural continuity and completeness of road networks in high-resolution remote sensing imagery remains a major challenge for current deep learning methods, especially under conditions of occlusion caused by vegetation, buildings, or shadows. To address this, we propose a novel post-processing enhancement framework that improves the connectivity and accuracy of initial road extraction results produced by any segmentation model. The method employs a dual-stream encoder architecture, which jointly processes RGB images and preliminary road masks to obtain complementary spatial and semantic information. A core component is the MAF (Multi-Modal Attention Fusion) module, designed to capture fine-grained, long-range, and cross-scale dependencies between image and mask features. This fusion leads to the restoration of fragmented road segments, the suppression of noise, and overall improvement in road completeness. Experiments on benchmark datasets (DeepGlobe and Massachusetts) demonstrate substantial gains in precision, recall, F1-score, and mIoU, confirming the framework’s effectiveness and generalization ability in real-world scenarios. Full article

The Central Yunnan Water Diversion Project (CYWDP) is currently under construction and represents China’s most extensive and geologically challenging water transfer infrastructure, facing significant geohazard risks induced by intensive engineering activities, posing severe threats to its entire lifecycle safety. Therefore, monitoring and spatiotemporal evolution analysis of surface deformation along the CYWDP is critically important. This study presents the first integrated analysis of geometric distortions and multi-dimensional spatiotemporal deformation characteristics along the CYWDP, utilizing both ascending and descending orbit data from Sentinel-1. First, by integrating the Layover-Shadow Mask (LSM) model and R-Index method, we identified geometric distortion types in SAR imagery and evaluated their suitability for deformation monitoring. Subsequently, SBAS-InSAR technology was employed to derive line-of-sight (LOS) deformation information from 124 images (ascending) and 90 images (descending) acquisitions (2022–2024), enabling the identification of significant deformation zones and analyzing their spatial distribution characteristics. Finally, two-dimensional (2D) deformation fields were obtained through the joint inversion of ascending and descending orbit data in typical deformation zones. The results reveal that geometric distortions in Sentinel-1 imagery along the CYWDP are dominated by foreshortening effects, accounting for 35.3% of the study area in the ascending-orbit data and 37.9% in the descending-orbit data. A total of 10 significant deformation-prone areas were detected, and the most pronounced subsidence, amounting to −164 mm/y, was observed in the northern Jinning District (Luoci-Qujiang section), showing expansion trends toward water conveyance infrastructure. This study reveals surface deformation’s multi-dimensional spatiotemporal evolution patterns along the CYWDP. The findings support geohazard mitigation and provide a methodological reference for safety monitoring of major water conservancy projects in complex geological environments. Full article