Search Results (215)

To meet the demand for real-time and accurate diamond particle size measurement in industrial scenarios—where traditional image processing methods lack robustness in complex environments and existing deep learning models struggle to balance accuracy and efficiency—this paper proposes an integrated framework for dynamic segmentation and morphological analysis of diamond particles based on video streams. A fully automated data acquisition system consisting of a high-precision motion stage, an industrial camera, and an optical microscope is first constructed to capture dynamic particle images. Based on YOLOv8n-seg, a lightweight SPR-YOLOv8 instance segmentation model is then developed with three key improvements: a Large Separable Kernel Attention (LSKA) mechanism is introduced into the SPPF module to enhance feature discriminability; the RepBlock module is adopted in the neck network to improve feature fusion efficiency through structural re-parameterization; and a P2 small-object detection head is introduced while large-object detection branches are removed, enabling the model to focus on tiny, densely distributed particles. Finally, a contour-based geometric analysis method is proposed for particle size estimation based on segmentation results. Experimental results show that the proposed model achieves an mAP@0.9 of 0.861 while maintaining a low parameter count (0.97 M) and a high inference speed of 500 FPS. Compared with the conventional OpenCV-based method (CADPS), the proposed DPSCA framework reduces the mean absolute percentage error in particle size measurement by over 70%, while also demonstrating strong accuracy and stability in consecutive-frame tracking. Overall, this study provides a practical and efficient automated inspection solution for online quality control in superhard material manufacturing, and supplementary cross-scale experiments further demonstrate promising robustness on diamond particles beyond the primary 180–250 μm range. Full article

Ground Control Points (GCPs) are essential for accurate georeferencing of optical imagery; however, their selection is often heuristic and affected by temporal changes in image geometry. This challenge is particularly acute for Google Earth imagery, where acquisition conditions and mosaicking processes vary over time. This paper presents a multi-epoch robust framework for the automatic design of GCP networks to precisely georeference multi-temporal Google Earth images. GCP selection is formulated within an affine optimal experimental design setting, in which candidate configurations are evaluated against the most challenging acquisition epoch to promote consistency over time. A hybrid DI-optimality criterion balances transformation stability and interior prediction accuracy without requiring interior control points. The framework also includes an automated method for determining the optimal number of GCPs using marginal-gain stopping and cost-regularized μ-sweep analysis. Experiments on two urban case studies show that compact, well-conditioned GCP networks can match the accuracy of larger heuristic networks and achieve top 10% root-mean-square error (RMSE) performance on a random feasible subset benchmark. Results demonstrate that a carefully designed GCP network can greatly reduce the number of control points needed while maintaining stable geometric performance across acquisition sessions. Full article

Traditional satellite-derived bathymetry (SDB) often suffers from systematic optical path distortions due to the neglect of seafloor slope effects, leading to significant accuracy degradation in high-gradient coastal areas. This study proposes a Slope-Aware Physics-Informed Neural Network (SA-PINN) framework that synergistically utilizes ICESat-2 bathymetric photons and Sentinel-2 multispectral imagery. The core innovation involves a slope-aware operator, integrated into the radiative transfer-based physics loss function, which explicitly rectifies directional optical path deviations induced by seafloor inclination. By fusing physical mechanisms with data-driven features, the model utilizes a seven-dimensional feature space comprising four spectral bands, two directional slope components, and prior depth. Applications at Culebra, Maui, and Molokai demonstrate that SA-PINN significantly outperforms the Stumpf model, Random Forest, and standard CNNs, achieving root mean square errors (RMSE) of 1.36 m, 2.91 m, and 1.34 m, respectively. Ablation studies confirm that SA-PINN reduces RMSE by up to 37% compared to CNN in complex regions with slopes exceeding 10°, ensuring superior physical consistency and spatial continuity. This research provides a robust, in situ-free automated solution for high-resolution bathymetric mapping in remote and steep coastal environments globally. Full article

Manual survey data entry remains a bottleneck in large-scale research, marketing, and public policy, where survey sheets are still widely used due to accessibility and high response rates. Despite the progress in Optical Character Recognition (OCR) and Optical Mark Recognition (OMR), existing systems treat these tasks separately and are typically tailored to clean, standardized forms, making them unreliable for real-world survey sheets with diverse markings and handwritten inputs. These limitations hinder automation and introduce significant error rates in data transcription. To address this, we propose SurveyNet, a unified deep learning framework that combines OCR and OMR capabilities to automatically digitize complex survey responses within a single model. SurveyNet processes both handwritten digits and a wide variety of mark types including ticks, circles, and crosses across multiple question formats. We also introduce SurveySet, a novel dataset comprising 135 real-world survey forms annotated across four key response types. Experimental results demonstrate that SurveyNet achieves between 50% and 97% classification accuracy across tasks, with strong performance even on small and imbalanced datasets. This framework offers a scalable solution for streamlining survey digitization workflows, reducing manual errors, and enabling timely analysis in domains ranging from consumer research to public health and education. Full article

The integration of micro-nano optical structures has become an essential strategy for overcoming the performance bottlenecks of quantum well infrared photodetectors (QWIPs), specifically by addressing the inherent inability of planar devices to couple with normally incident light due to intersubband transition selection rules. A critical factor in this integration is the precise spectral overlap between an optical mode and the material’s excitation mode. Therefore, achieving precise spectral engineering is indispensable. However, conventional electromagnetic simulations act as forward solvers, calculating optical responses based on given geometric parameters. They cannot directly perform inverse design, which involves deriving optimal geometric parameters directly from a desired optical response. Consequently, structural optimization is severely constrained by time-consuming trial-and-error iterations, which often struggle to find the global optimum in a complex design space. To overcome these limitations, this paper presents a comprehensive theoretical and numerical study proposing a deep learning framework for QWIPs coupled with all-dielectric micropillar structures. By establishing a structure-absorption spectrum dataset via finite difference time domain (FDTD) simulations, we developed a dual-network setup. For the forward prediction, a multilayer perceptron (MLP) maps geometric parameters (side length a and period p) to the absorption spectrum, achieving a computational speedup of seven orders of magnitude over traditional numerical simulations. Concurrently, a convolutional neural network (CNN) is employed for the inverse design, realizing on-demand design of geometric parameters based on target spectra with high reconstruction accuracy. Furthermore, the selected all-dielectric micropillar structures are highly compatible with mainstream semiconductor fabrication processes. This research provides an efficient, automated toolkit for the development of high-performance infrared photodetectors. Full article

The relentless miniaturization of semiconductor components and Printed Circuit Boards (PCBs) has rendered Automated Optical Inspection (AOI) of micro-defects a critical bottleneck in modern manufacturing and metrology. While in-line inspection systems offer economically viable and scalable quality control solutions, they impose stringent constraints on both inference latency and detection robustness—particularly for diminutive, sparsely distributed defects (e.g., mouse bites, pinholes) amidst complex, repetitive circuit topologies. To bridge this gap, we present a semantic-enhanced FCOS framework specifically engineered for micro-defect inspection. Our approach introduces two synergistic innovations: (1) a Semantic-Guided Upsampling Unit (SGU) that adaptively reweights channel–spatial features to reconcile the semantic disparity between shallow textural details and deep contextual representations; and (2) a Sparse Center-ness Calibration (SCC) module that enforces high-confidence, spatially sparse supervision to sharpen localization precision and suppress false positives. The SGU is integrated within a Progressive Semantic-Enhanced Feature Pyramid Network (PSE-FPN) that extends multi-scale representations to stride-4 (P2) resolution, while the SCC module is embedded directly into the detection head. Comprehensive evaluations on MS COCO and the real-world DeepPCB dataset validate the efficacy of our design. On COCO, our model achieves 41.8% AP with real-time throughput of 28 FPS on a single NVIDIA 1080Ti GPU. A lightweight variant further attains 41.6% AP at 42 FPS, accommodating high-throughput production environments. For PCB defect detection, the framework delivers 98.7% mAP@0.5, substantially outperforming contemporary detectors. These results demonstrate that semantics-aware, lightweight architectures enable scalable, real-time quality assurance in semiconductor manufacturing. Full article

Objective: To develop and validate an artificial intelligence (AI) system for automated lens opacities classification system III (LOCS III)-based grading of all three major cataract subtypes using anterior segment optical coherence tomography (AS-OCT). Methods: This is a single-center cross-sectional study. AS-OCT images were collected and manually graded by ophthalmologists according to LOCS III. The dataset was randomly split into training, validation, and test sets. We propose a novel multi-granularity mask-guided network (MMNet) that jointly performs lens substructure segmentation and severity grading. The model’s performance was assessed on an independent test set for automatic grading of cortical cataract (CC), nuclear cataract (NC), and posterior subcapsular cataract (PSC) and the grading performance of the proposed method against ophthalmologists was also evaluated. The model’s interpretability was assessed via attention heatmaps and feature visualization. Results: The proposed MMNet exhibited high agreement with ground truth conducted through gold standard. The proportions of predictions with an absolute error < 1.0 for three subtypes range from 83.02% to 89.94%. The model’s grading accuracy for cataract subtypes was between 82.20 ± 1.41% and 89.76 ± 1.31% among the three subtypes, the Area Under the Curve (AUC) was between 0.954 (95% CI, 0.952–0.969; p < 0.001) and 0.973 (95% CI, 0.964–0.985; p < 0.001). The MMNet shows a satisfactory mean absolute error (MAE) of 0.14 ± 0.35 in CC, 0.10 ± 0.30 in NC, and 0.17 ± 0.38 in PSC grading. It also achieved a fast grading speed of 0.0178 s/image against manual grading. Conclusions: The proposed AI model presented advanced performance on AS-OCT images in automated LOCS III-based cataract grading for CC and NC, and also showed feasibility in PSC assessment. Full article

We propose and experimentally validate an automatic urban water leakage detection architecture that leverages dark fiber links already deployed in telecommunication networks in underground conduits in the vicinity of water pipelines. The sensing stage relies on a differential-phase coherent optical time-domain reflectometry interrogator enhanced with optical pulse compression to improve sensitivity. Building on this vibration acquisition stage, automatic leakage detection algorithms are implemented by searching for leak-induced activity in the frequency domain, which is well suited to revealing leakage-related features. After acquiring a baseline calibration to characterize normal-condition vibrations at each sensing position, leakage candidates are identified by comparing distribution-based metrics computed over multiple measurements against the corresponding baseline statistics. Two automatic leakage detection strategies are developed. First, low-complexity feature-based metrics are implemented, enabling continuous monitoring with minimal computational requirements. Second, an autoencoder-based anomaly detection technique is introduced, which also relies on location-specific normal-condition calibration but reduces the dependence on prior knowledge of the expected leakage vibration signatures. A real-world field trial on an urban network demonstrates reliable detection and localization using controlled leak events generated in the field, with measurements performed over a 17 km sensing fiber and an effective spatial resolution of 2.6 m. Benchmarking against a commercial punctual electro-acoustic leak detector yields consistent trends. Overall, the proposed system could complement existing technologies by enabling automated, continuous city-scale monitoring over already deployed dark fiber infrastructure. Full article

Calving front position is a key indicator of glacier and ice-sheet dynamics and an important variable for assessing mass loss and sea-level rise. Rapid growth in satellite data availability and image analysis techniques has driven the development of numerous automated calving front detection algorithms; however, the methodological landscape remains fragmented. This scoping review aims to map the existing literature on automated calving front detection, characterize the types of algorithms and data sources used, and identify trends, gaps, and challenges in current approaches. A systematic search of major bibliographic databases and complementary sources was conducted to identify studies describing automated or semi-automated calving front detection from satellite imagery or derived datasets. Eligible studies included peer-reviewed articles and relevant grey literature using optical, synthetic aperture radar (SAR), or multi-sensor data. Data were charted using a predefined framework that captures the algorithmic approach, input data characteristics, spatial and temporal coverage, validation strategies, and reported performance metrics. The review identifies a wide range of methods, from early threshold- and edge-based techniques to recent machine learning and deep learning approaches, with a strong shift toward convolutional neural networks over the past few years. Despite methodological progress, validation practices and evaluation metrics remain heterogeneous, and standardized benchmark datasets are scarce. This scoping review provides a structured overview of the field and highlights priorities for future methodological development and benchmarking. Full article

Human Activity Recognition (HAR) is a pivotal research area for applications such as automated surveillance, smart homes, security, healthcare, and human behavior analysis. Traditional machine-learning approaches often rely on manual feature engineering, which can limit generalization. Although deep learning has improved HAR through automatic representation learning, achieving high detection performance under computational constraints remains challenging. This paper proposes an efficient HAR framework that combines deep learning with hybrid optimization. Surveillance videos are first decomposed into frames, and a keyframe selection stage identifies distinctive frames to reduce redundancy and computational cost while preserving informative content. Motion and appearance features are then extracted using Histogram of Oriented Optical Flow (HOOF) and a ResNet-101 model, respectively, and concatenated into a unified feature representation. Classification is performed using an Inception-based Long Short-Term Memory (Incept-LSTM) network, which is fine-tuned via the proposed Tricky Predator Optimization (TricP) over a restricted, low-dimensional parameter vector. TricP is inspired by predator poaching behavior and the social dynamics of Latrans to enhance exploration and exploitation during search. Experiments on the UCF-Crime dataset show that the proposed method achieves 96.84% specificity, 92.16% sensitivity, and 93.62% accuracy. Full article

Accurate estimation of river width is of great importance for hydrological analysis and water-related applications. However, existing remote sensing-based river-width extraction methods are often complex and prone to error accumulation due to their multi-step processing pipelines. To address these limitations, this study proposes an end-to-end stage-guided multi-task network for river-width estimation (E2E-SGRWNet), which directly regresses continuous river-width values from optical remote sensing imagery. The model adopts a stage-wise guidance strategy that progressively incorporates river spatial semantic information and geometric structural information to effectively guide the learning of river width. At the task-guidance level, a cascaded multi-task framework is designed according to the dependency relationships among tasks, in which river-mask segmentation and centerline extraction serve as auxiliary tasks to guide river-width regression. At the feature-guidance level, a cross-branch feature fusion mechanism is introduced to fully exploit multi-scale spatial semantic features and geometric structural features, thereby jointly guiding fine-grained river-width regression. The experimental results on the self-constructed RiverWidth-HR Dataset show that E2E-SGRWNet reduces the mean absolute error (MAE) and Root-Mean-Square error (RMSE) by $1.1\%$ and $3.8\%$, respectively, compared with DeepRivWidth, the strongest existing multi-stage river-width estimation baseline. Overall, E2E-SGRWNet provides a concise and robust solution for high-precision, automated river-width estimation and offers new insights into end-to-end geometric parameter regression from remote sensing imagery. Full article

Background/Objectives: Biopsy examination remains the gold standard for cancer diagnosis, relying on histopathological assessment of tissue samples to identify malignant changes. However, manual interpretation of histopathological slides is time-consuming, subjective, and susceptible to inter-observer variability. The digitization of histopathological images enables automated analysis and offers opportunities to support clinicians with more consistent and objective diagnostic tools. This study aims to enhance cancer diagnosis by proposing a hybrid framework that integrates deep-learning-based histopathological image analysis with Whispering Gallery Mode (WGM) optical sensing for complementary tissue characterization. Methods: The proposed framework combines automated tumor classification from histopathological images with biochemical signal analysis obtained from WGM optical sensors. Deep learning models, including EfficientNet-B0, InceptionV3, and Vision Transformer (ViT), were employed for binary and multi-class tumor classification using the BreakHis dataset. To address class imbalance, a Deep Convolutional Generative Adversarial Network (DCGAN) was utilized to generate synthetic histopathological images alongside conventional data augmentation techniques. In parallel, WGM optical sensors were incorporated to capture subtle tissue-specific signatures, with machine learning algorithms enabling automated feature extraction and classification of the acquired signals. Results: In multi-class classification, InceptionV3 combined with DCGAN-based augmentation achieved an accuracy of 94.45%, while binary classification reached 96.49%. Fine-tuned Vision Transformer models achieved a higher classification accuracy of 98% on the BreakHis dataset. The integration of WGM optical sensing provided additional biochemical information, offering complementary insights to image-based analysis and supporting more robust diagnostic decision-making. Conclusions: The proposed hybrid framework demonstrates the potential of combining deep-learning-based histopathological image analysis with WGM optical sensing to improve the accuracy and reliability of cancer classification. By integrating morphological and biochemical information, the framework offers a promising approach for enhanced, objective, and supportive cancer diagnostic systems. Full article

Digitalization of railway traffic dispatching systems is a key step in the modernization of railway telecommunication infrastructure. This paper presents a case study of the migration from legacy analog technology to a software-centric dispatching platform that integrates digital signal processing, optical fiber transmission, and Internet Protocol (IP)-based network architectures, as implemented in the Serbian railway system. The modernization is performed through an iterative, incremental process: existing analog dispatcher equipment and established operating procedures are preserved, while digital dispatching centers, trackside communication nodes, and radio-dispatching services are introduced gradually. This staged evolution enables high-capacity, noise-resilient communication and seamless interconnection between the old and the new subsystems without disrupting railway operations. The adoption of software-based control and integrated digital signal processing provides modular scalability, real-time system supervision, automated diagnostics, and improved maintainability. One of critical services within the new architecture, the Centralized Call Record- and Message-Archiving System (CCRMAS), provides a centralized platform that captures, secures, and retrieves operational railway communication in real time for monitoring, post-incident analysis, and regulatory compliance. The resulting architecture, deployed within Serbian Railways, establishes a scalable and resilient foundation for future automation, interoperability, and integration within intelligent railway traffic-management environments. Thus, the paper extracts a generalizable hybrid migration architecture model and transferable design principles, supported by deployment artifacts and illustrated through migration scenarios, that can be applied to the modernization of other legacy-intensive railway networks. Full article

With the growing global emphasis on space resources, the significance of space detection and surveillance technologies has escalated. Currently, space-based optical surveillance stands as the primary means for acquiring information on space objects. However, constrained by the diffraction limits of space telescopes, distant space objects are typically imaged as point sources. The resulting lack of sufficient spatial resolution renders traditional image-based recognition algorithms ineffective. In contrast, the Bidirectional Reflectance Distribution Function (BRDF) fully characterizes surface light scattering properties through four-dimensional features, significantly outperforming traditional two-dimensional spectral techniques in material identification. Consequently, leveraging BRDF signatures at varying phase angles has emerged as an effective approach for Space Object Identification. In this study, we developed an automated BRDF measurement system to characterize various typical aerospace materials and investigated the BRDF properties of mixed-material surfaces. A material composition ratio prediction model was constructed based on a One-Dimensional Convolutional Neural Network (1D-CNN). This model effectively extracts key features, including local slope variations and global waveform characteristics, from the BRDF curves. Experimental results demonstrate that the model achieves a maximum relative percentage error of 6.21%, implying a prediction accuracy for mixed-material composition ratios consistently exceeding 93.79%. Compared to image classification methods based on remote sensing imagery, the proposed approach offers higher computational efficiency, significantly reduced model complexity and computational cost, and enhanced robustness. This work provides essential data support for material identification by space-based telescopes and establishes an algorithmic and experimental foundation for intelligent space situational awareness systems. Full article

Human activity recognition (HAR) is essential in many applications, such as smart homes, assisted living, healthcare monitoring, rehabilitation, physiotherapy, and geriatric care. Conventional methods of HAR use wearable sensors, e.g., acceleration sensors and gyroscopes. However, they are limited by issues such as sensitivity to position, user inconvenience, and potential health risks with long-term use. Optical camera systems that are vision-based provide an alternative that is not intrusive; however, they are susceptible to variations in lighting, intrusions, and privacy issues. The paper uses an optical method of recognizing human domestic activities based on pose estimation and deep learning ensemble models. The skeletal keypoint features proposed in the current methodology are extracted from video data using PoseNet to generate a privacy-preserving representation that captures key motion dynamics without being sensitive to changes in appearance. A total of 30 subjects (15 male and 15 female) were sampled across 2734 activity samples, including nine daily domestic activities. There were six deep learning architectures, namely, the Transformer (Transformer), Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), Multilayer Perceptron (MLP), One-Dimensional Convolutional Neural Network (1D CNN), and a hybrid Convolutional Neural Network–Long Short-Term Memory (CNN–LSTM) architecture. The results on the hold-out test set show that the CNN–LSTM architecture achieves an accuracy of 98.78% within our experimental setting. Leave-One-Subject-Out cross-validation further confirms robust generalization across unseen individuals, with CNN–LSTM achieving a mean accuracy of 97.21% ± 1.84% across 30 subjects. The results demonstrate that vision-based pose estimation with deep learning is a useful, precise, and non-intrusive approach to HAR in smart healthcare and home automation systems. Full article