Search Results (150)

Accurate change detection in high-resolution remote sensing imagery is essential for urban planning, land-use monitoring, and disaster response. This study introduces CTA-Net, a Cross-Temporal Attention Network for binary change detection in bi-temporal optical imagery, designed to improve robustness against pseudo-changes caused by illumination variation, seasonal effects, and sensor noise. The proposed method employs a shared Siamese encoder with multi-scale Cross-Temporal Attention modules that derive spatial and channel attention from L2 feature differences, along with a lightweight confidence estimation head for per-pixel uncertainty modelling. A hybrid loss function combining confidence-weighted binary cross-entropy and focal loss is used to address class imbalance. Experiments on the LEVIR-CD dataset demonstrate that CTA-Net achieves an overall accuracy of 98.99%, an F1-score of 87.68%, an Intersection over Union of 78.06%, a Cohen’s kappa of 0.8715, and a Matthews Correlation Coefficient of 0.8721, with stable convergence and minimal overfitting. Qualitative and calibration analyses further indicate that the model produces interpretable attention maps and reliable probabilistic outputs. To evaluate cross-domain generalization, we conduct a transfer learning case study on multispectral Sentinel-2 agricultural imagery. The model is adapted to 11-channel input and fine-tuned on automatically generated change masks derived from NDVI-delta thresholding. Under this supervision protocol, CTA-Net achieves an F1-score of 95.18% and an IoU of 90.81% on a held-out test region, with balanced precision and recall. While these results demonstrate effective adaptation across sensor modality, spatial resolution, and semantic domain, the evaluation reflects agreement with the mask generation procedure rather than independently annotated ground truth. While CTA-Net shows strong performance and reasonable interpretability, its cross-domain evaluation is limited by the use of automatically generated labels. As a result, the reported transferability should be interpreted cautiously until validated on human-annotated datasets. Full article

The objective of white balance is to accurately estimate and subsequently eliminate the color of global illumination present in an image. Learning-based methods have gained prominence over statistical approaches due to their typically superior accuracy. However, these methods rely on high-quality, large datasets. The quality of a dataset is intrinsically tied to the volume of knowledge it encapsulates, specifically the uniformity in the distribution of labels. In this study, we expand the dataset by leveraging the camera imaging pipeline. Subsequently, we segment the image into 16 partially overlapping blocks that collectively encompass the entire image. We then propose a rudimentary neural network designed to train these blocks with consistent labels, yielding 16 predictive outcomes that serve as image features. These features are used to capture complex illumination and reflection data within the image. Utilizing these features, we employ a straightforward, fully connected neural network to calculate the color mapping function, thereby correcting the image colors. Experimental results show that the methodology proposed in this paper significantly surpasses existing state-of-the-art color constancy methods. Full article

This study proposes a vision-based framework for automated inspection and quality grading of beef steaks by integrating fat marbling distribution analysis and lean-meat color evaluation. In frozen beef products, surface frost often generates specular reflections that resemble both fat and lean regions, thereby reducing segmentation accuracy. To address this challenge, a sequential and interpretable analytical framework is developed. First, homomorphic filtering is applied to suppress frost-induced illumination artifacts, followed by curvelet transform combined with square-ring filtering to separate fat and lean regions based on their multi-scale and directional characteristics. For marbling analysis, the convex hull, skeleton, and principal axis of the steak are extracted, and a chi-square goodness-of-fit test is performed within eight predefined regions to quantitatively evaluate marbling distribution uniformity and identify localized fat accumulation. For lean-meat evaluation, RGB color features are extracted and classified using a Support Vector Machine (SVM) to determine redness levels. The resulting marbling and color information are subsequently integrated through a weighted grading strategy to estimate the final quality grade. Experimental results demonstrate a fat detection rate of 92.68%, a false-positive rate of 4.97%, and a correct classification rate of 94.09% for fat segmentation, while the SVM-based lean-meat color classifier achieves an accuracy of 96.67%. Furthermore, the proposed grading framework attains an overall grading accuracy of 90.38%, showing strong agreement with human evaluation. Full article

Accurate detection and reliable grasping of small bolts are essential for intelligent manufacturing and automated assembly. However, this remains a challenge due to the small size, slender geometry, and metallic reflective surfaces of bolts. In this paper, we propose a vision-guided robotic bolt handling framework that integrates lightweight object detection, optimization-oriented grasp execution, and collision-aware trajectory planning. The lightweight YOLOv8n-BoltLite detector, improved with E-C2f, LCA, SA-PAN, and WD-IoU loss, enhances localization accuracy and feature representation for small and slender bolts. A robotic grasping framework is designed to transform detection results into executable robotic actions through 3D pose estimation, mid-shank grasp point generation, and optimization-oriented execution formulation. Additionally, a five-segment trajectory planning strategy ensures safe and efficient robot motion. Experimental results show that YOLOv8n-BoltLite achieves a five-run average mAP of 99.64 ± 0.05% with 198 FPS, and 3.02 M parameters. On an additional challenging external test set involving illumination variation, clutter, partial occlusion, reflection, and clustered bolts, the proposed detector achieves 94.62 ± 0.18%, outperforming recent lightweight detectors under the same training protocol. Robotic experiments involving 1000 controlled grasping trials and 300 multi-target grasping attempts demonstrate a controlled-condition success rate of 97.0% and improved target-selection reliability in multi-bolt scenes. These results suggest that the proposed framework offers a practical and efficient solution for automated bolt handling in intelligent manufacturing environments. Full article

The algae-based landfill leachate (LL) treatment system has been proved promising for nutrient recycling and biomass production at lab- or small-scale photobioreactors (PBRs). However, many assessment tools such as techno-economic analyses (TEAs) usually utilize parameters from small-scale experiments as input data to predict the potential performance of commercial large-scale or full-scale bioreactors. Reliability of using data from lab-scale for commercial large-scale estimation is still uncertain. This study compared the performance of three photobioreactor systems that differed simultaneously in scale, geometry, light intensity, mixing mode, and aeration: 0.125 L small-scale flask, 1 L medium-scale tubular PBR, and 15 L wall-shaped PBR for real LL treatment. The 1 L medium-scale tubular photobioreactor outperformed the other two systems in biomass growth rate and the rates of nitrogen and phosphorus removal, even though all three systems removed nearly all NH₄-N and PO₄-P (≈100%) within two weeks. Possible reasons for this better performance include stronger illumination, a bubbling aeration mode, the reactor shape (which improves mixing), and higher surface area to volume ratio × light intensity. According to these results, using relatively small-scale flask experimental data for predictive analysis of industrial-scale algal systems could be inadequate. In this study, volumetric optical radiation (VOR) serves as a promising preliminary descriptive indicator to reflect the overall performance of an algal-based treatment system. Full article

Achieving stable local focus-height measurement across different material surfaces is important for I-line-lithography-related inspection, where sub-micrometer height deviations can affect imaging quality, exposure uniformity, and subsequent autofocus performance. This study evaluates the local focus-height repeatability of a linear charge-coupled device (LCCD)-based focus metrology system under several I-line-lithography-related material-surface conditions. The prototype integrates fiber-coupled LED illumination, telecentric projection and imaging optics, reference marks, and a two-step localization procedure based on template matching and centroid estimation; the dual-wavelength source is treated as part of the fixed optical configuration. Tests were performed on silicon wafers, GaAs bright substrates, sapphire, infrared transmissive material, and SiC, covering different reflectivity levels and surface structures. The measured peak-to-valley repeatability was 35–37 nm for highly reflective samples and 40–54 nm for intermediate- or low-reflectivity and microstructured samples, all below the selected 70 nm conservative engineering criterion derived from the depth-of-focus estimate. These results indicate that the integrated LCCD measurement chain maintained stable local repeatability within the tested material-surface range, providing experimental support for further development of local focus metrology and precision optical inspection. Full article

Unmanned surface vessels (USVs) equipped with onboard vision are increasingly used in environmental monitoring, search and rescue, and autonomous navigation. However, conventional USV autonomy systems often adopt a decoupled design in which target perception and disturbance estimation are developed independently. Such systems may suffer performance degradation when visual observations become unreliable under water-surface reflections, illumination variations, or partial occlusions, while the disturbance observer still depends on manually tuned parameters under time-varying environmental disturbances. To address these issues, this paper proposes a three-stage co-optimized target perception and disturbance estimation framework for USVs. First, a lightweight hybrid convolutional neural network (CNN)–Transformer perception module is developed to extract robust vessel features under challenging water-surface visual conditions. Second, a reinforcement learning (RL)-driven mechanism is used to adaptively tune a higher-order sliding mode observer (HOSMO) for disturbance estimation. Third, a confidence-guided perception-observer co-optimization strategy is formulated, in which visual confidence is used to regulate observer adaptation and reduce estimation divergence during temporary perception degradation. Simulation and outdoor lake experiments demonstrate that the proposed framework improves visual matching accuracy, observer convergence, and estimation stability compared with conventional decoupled methods. The outdoor lake experiments provide initial real-world validation under natural illumination variations and mild water-surface disturbances, while further open-water and multi-vessel validation is planned for future work. Full article

Three-dimensional (3D) hyperspectral point clouds provide both surface geometry and spectral information, offering a promising tool for close-range surface characterization. However, reliable reflectance-related spectral measurement on complex surfaces remains challenging because camera-recorded spectral signals are strongly affected by non-uniform illumination, surface geometry, and the spectral response of the imaging system, while existing correction methods are often limited by Lambertian assumptions and narrow spectral capacity. In this work, we present a close-range 3D hyperspectral measurement framework with geometry-aware spectral correction that integrates a structured-light 3D measurement module with a hyperspectral imaging module. The system enables the acquisition of fused 3D hyperspectral data with a sphere-fitting RMS residual below 40 μm and a spectral resolution of 7 nm. To improve spectral correction on geometrically complex surfaces, we propose a physics-guided spectral correction model, termed 3D light-field spectral correction (3D-LFSC), which is inspired by the geometric dependence described by the bidirectional reflectance distribution function (BRDF) and uses measurable geometric information to model geometry-dependent spectral variation. Because the system adopts a cross-polarized illumination–detection configuration, the corrected spectra should be interpreted as diffuse-dominant apparent reflectance estimates under the fixed system configuration, rather than complete surface reflectance. Experiments on surfaces with different geometries and reflectance properties show that the proposed method improves spectral consistency by more than 10% compared with existing methods. The framework also demonstrates applicability to chromaticity-related analysis on facial surfaces, indicating its potential for close-range spectral measurement of complex biological surfaces. Full article

Understanding the variations in the bidirectional reflectance distribution function (BRDF) and albedo over snow surface under various conditions is important for interpreting the surface–atmosphere processes of the cryosphere, and the kernel-driven model is among the most popular methods to obtain this information for a comprehensive analysis. Recently, the RossThick-LiSparseReciprocal-Snow (RTLSRS) model was developed to better characterize the anisotropic reflectance of snow and shows strong potential for integration into operational remote sensing algorithms for snow BRDF/albedo retrieval. To comprehensively test the ability of the RTLSRS model to reproduce snow reflectance, the fitting accuracy to different multi-angular data derived from ground, tower, aircraft, and satellite platforms across the full optical wavelength range were demonstrated in this study. Special attention in this study was directed to analyzing the model performance under extreme illumination observation geometries, particularly with respect to the retrieval accuracy and stability under large Solar Zenith Angles (SZAs) and different Relative Azimuth Angles (RAAs). The model performance for silt-polluted snow surface with different concentrations is also assessed to provide necessary supplementation, relative to “pure” snow surface in the previous study. The main findings of this study are summarized as follows: (1) The RTLSRS model exhibits strong robustness under various SZAs; even when the SZA exceeds 80°, the model maintains high accuracy in BRDF reconstruction, with root mean square error (RMSE) values below 0.05. (2) The model also demonstrates satisfactory inversion capability when observations deviate from the principal plane (PP); the model can achieve fitting accuracy with R² approaching 0.5 and RMSE below 0.05 for MODIS data. (3) In the spectral range below 1300 nm, the RTLSRS model effectively reconstructs the scattering characteristics of snow surfaces with light impurity levels (<20 g/0.5 m²). (4) The spectral shape of snow reflectance remains consistent across different view zenith angles (VZAs) in general. However, the variations caused by different SZAs can be as high as 38.49% and such SZA-induced difference can result in WSA estimation discrepancy of up to 63.43%. This comprehensive assessment further affirms and demonstrates the applicability of the RTLSRS model for the first time in fitting observations across different platforms with various optical wavelengths and geometries, and provides an improved understanding to analyze BRDF variations for the user community. Full article

Accurate, non-destructive estimation of crop biomass is essential for automated high-frequency monitoring and optimization in controlled-environment agriculture, yet standardized approaches remain limited for short-cycle hydroponic systems. This study introduces a reproducible and fully automated method for estimating the biomass of hydroponically grown wheat sprouts (HWSs) using high-frequency RGB imaging. The workflow integrates image preprocessing, tray segmentation, and canopy feature extraction with synchronized load-cell measurements to enable continuous, non-invasive growth tracking. To account for irrigation events and associated weight fluctuations, raw mass signals were processed using a second-order low-pass Bessel filter, preserving underlying biomass trends while removing short-term oscillations. Across 3024 paired image–mass observations collected under commercial cultivation conditions, several canopy coverage, color-based indices (AGI, Proxy NDVI), and texture features exhibited strong predictive relationships with biomass. Features reflecting greenness, canopy density, and color uniformity were positively associated with plant mass, whereas brightness- and red-channel features showed consistent negative relationships. Feature selection using an elastic-net approach identified a compact subset of informative predictors, improving model stability and interpretability. Under a nested cross-validation framework based on contiguous interval splits within sprout-growth cohorts, support vector regression (SVR) achieved the best predictive performance, with an sMAPE of 3.64% and an RMSE of 0.16 kg. Additional experiments under altered illumination conditions showed that including light intensity as an explicit covariate improved model robustness across lighting regimes. These results demonstrate that combining elastic-net feature selection with environmental covariates provides a robust and transferable framework for visual biomass estimation in hydroponic HWS. More broadly, the proposed pipeline enables non-destructive crop monitoring and supports the development of intelligent, feedback-driven control strategies for hydroponic production systems. Full article

Because of high visible and near-infrared (VNIR) reflectance, and deep shortwave infrared (SWIR) absorption, snow and ice are unique among terrestrial land cover. As such, both are well-suited to mapping and monitoring using optical remote sensing. However, to date, almost all studies of snow and ice spectroscopy have been limited to single or small numbers of specific cryospheric environments. These studies serve a diversity of objectives, but together also suggest the importance of the global continuum of snow and ice composition and spectroscopy. The continuum of snow and ice composition gives rise to the characteristics that allow different types of snow and ice to be distinguished optically. Particularly with imaging spectrometers. Characterization of this continuum of reflectance can facilitate development of physical models to quantify snow and ice composition and abundance, particularly in the presence of other types of land cover. In this study, a collection of ~140,000,000 visible through SWIR (VSWIR) reflectance spectra, collected by NASA’s EMIT imaging spectrometer from 56 diverse cryospheric environments, is used to characterize the continuum of snow and ice reflectance. This continuum is characterized using linear dimensionality reduction to quantify the dimensionality and topology of the spectral feature space of snow and ice. The resulting spectral feature space is effectively two-dimensional with a planar spectral feature continuum bounded by dry and wet snow, ice and dark targets (e.g., shadow, water). Because of the near collinearity of snow and ice endmember reflectances, linear spectral mixture models based only on these endmembers are ill-posed and unstable to inversion. However, in landscapes where sufficiently homogeneous seasonal snow is present with other land cover types, the standardized spectroscopic mixture model based on the Substrate, Vegetation and Dark (SVD) continuum can be extended with an instance-specific snow endmember (SVD + snow) to yield plausible areal fraction estimates with small misfits to observed spectra. More generally, the snow–ice-dark continuum can also be represented accurately with an optimal normalized difference index exploiting compositionally distinct differential absorptions at ~650 and ~1230 nm to distinguish dry from wet snow from white and blue ice. This optimized index, referred to as the Continuous Cryosphere Index (CCI), minimizes BRDF effects of topographic slope and aspect relative to illumination, while avoiding the saturation that causes the Normalized Difference Snow Index (NDSI) to conflate wet snow with white and blue ice reflectance. In addition to imaging spectrometers like EMIT, operational sensors like MODIS, VIIRS and WorldView-3 have spectral bands near 650 nm and 1230 nm, so they could also be used for CCI mapping. Full article

Standard fringe-based structured-light processing estimates wrapped phase from phase-shifted sinusoidal images and commonly relies on phase unwrapping to obtain a globally consistent phase representation. In practical measurements, this approach may become unstable on reflective objects and under low or non-uniform illumination, where the recorded fringe signal is distorted and the recovered phase becomes unreliable. To address these limitations, we propose a correspondence extraction method based on subpixel peak localization performed directly on phase-domain images. The wrapped phase is transformed into absolute value phase profiles, $\mathsf{\Phi }=\left|{\varphi }_w\right|$, whose local structure follows the projected fringe pattern and is less affected by object-dependent intensity variations. The proposed method reformulates correspondence extraction as a local signal-based estimation problem in the phase-domain, thereby reducing reliance on global phase-consistency constraints at the correspondence stage. A practical advantage observed in the evaluated examples is that the method remained usable in some regions where the phase became locally flat because of low modulation, saturation, or reflective surface effects. In such regions, conventional processing relies on sufficiently reliable phase gradients and subsequent unwrapping, whereas the proposed method uses local peak geometry in the transformed phase representation. In the implementation used here, Gray-code information is employed only for pixel-wise phase extension and reference indexing, not as a spatial phase-unwrapping mechanism. The method does not require machine learning models or training data and can be integrated as a correspondence analysis stage in practical structured-light systems. Full article

Agrivoltaic systems co-locate photovoltaic (PV) arrays and crops, offering land-use efficiency and potential microclimate benefits, yet they introduce new challenges for computer-vision-based crop monitoring. PV structures produce strong, spatially varying shadows, specular reflections, and periodic occlusions that confound visual cues for diagnosing crop diseases and abiotic stresses. Meanwhile, agrivoltaic deployments are often distributed across farms and operators, making centralized data collection impractical due to privacy, ownership, and regulatory concerns. This paper proposes PrivAgriVolt, a novel privacy-preserving learning framework for agrivoltaic crop issue recognition that explicitly models PV-induced illumination and enables collaborative training without sharing raw images. The core algorithm integrates (i) a PV-geometry-conditioned shadow normalization module that fuses estimated array layout and sun-angle priors into a shadow-aware appearance canonization network, reducing illumination-induced domain shift across times and sites; (ii) a federated contrastive stress learner that aligns stress semantics across farms via prototype-based contrastive objectives while remaining robust to heterogeneous sensors and crop stages; and (iii) an adaptive privacy layer that combines secure aggregation with budget-aware gradient perturbation and client-level clipping to provide formal privacy guarantees while preserving fine-grained diagnostic performance. Extensive experiments on real agricultural vision benchmarks and agrivoltaic shadow variants demonstrate that PrivAgriVolt improves stress recognition and segmentation under PV shading while maintaining strong privacy–utility trade-offs. Full article

We present a reproducible pipeline that converts color images into quantitative fluorescence maps by combining spectral measurement with a linear mixture model. The method is designed specifically for quantitative comparisons of Glo Germ™ on images of hands taken under different experimental conditions with controlled illumination. The emission spectrum of Glo Germ is measured using a spectral photometer and normalized to obtain its spectral power density function. This spectrum is projected into CIE XYZ coordinates and incorporated into a linear mixture model in which each pixel contains contributions from white light, UV-illuminated skin reflectance, and fluorophore emission. Component magnitudes are estimated with non-negative least squares, yielding a grayscale image whose intensity is a monotonic proxy for local fluorophore density. Spatial integration provides an image-level summary proportional to total detected material. Compared with single-channel proxies, the observer suppresses background structure, improves contrast, and remains radiometrically interpretable. Because the method depends only on measurable spectra and linear transforms, it can be reproduced across cameras and extended to other fluorophores. Full article

Eye-tracking is a key enabling technology for smart eyewear, supporting hands-free interaction, accessibility, and context-aware human–machine interfaces under strict constraints on size, power consumption, and computational complexity. While camera-based solutions provide high accuracy, their integration into lightweight and low-power wearable platforms remains challenging. This paper is a feasibility study for the design, simulation, and experimental evaluation of a photosensor oculography (PSOG) eye-tracking system that is fully integrated into an eyewear frame, based on near-infrared (NIR) emitters and photodiodes. The proposed approach combines simulation-driven optimization of the optical constellation, a multi-frequency modulation and demodulation scheme enabling parallel source discrimination and robust ambient-light rejection, and a resource-efficient signal acquisition pipeline suitable for embedded implementation. Eye rotations in azimuth and elevation are inferred from differential reflectance patterns of ocular regions (sclera, iris, and pupil) using lightweight regression techniques, including shallow neural networks and Gaussian process regression, selected to balance estimation accuracy with computational and power constraints. System performance is evaluated using a controllable artificial-eye platform under defined geometric and illumination conditions, enabling repeatable assessment of gaze-estimation accuracy and algorithmic behavior. Sub-degree errors are achieved in this controlled setting, demonstrating the feasibility and potential effectiveness of the proposed architecture. Practical considerations for translation to real-world smart eyewear, including human-subject validation, anatomical variability, calibration strategies, and embedded deployment, are discussed and identified as directions for future work. By detailing the optical design methodology, modulation strategy, and algorithmic trade-offs, this work clarifies the distinct contributions of the proposed PSOG system relative to existing frame-integrated and camera-free eye-tracking approaches, and provides a foundation for further development toward wearable and augmented-reality applications. Full article