Search Results (18,128)

Smart safety helmets equipped with vision systems are emerging as powerful tools for industrial infrastructure inspection. This paper presents a comprehensive state-of-the-art review of such VSLAM-enabled (Visual Simultaneous Localization and Mapping) helmets. We surveyed the evolution from basic helmet cameras to intelligent, sensor-fused inspection platforms, highlighting how modern helmets leverage real-time visual SLAM algorithms to map environments and assist inspectors. A systematic literature search was conducted targeting high-impact journals, patents, and industry reports. We classify helmet-integrated camera systems into monocular, stereo, and omnidirectional types and compare their capabilities for infrastructure inspection. We examine core VSLAM algorithms (feature-based, direct, hybrid, and deep-learning-enhanced) and discuss their adaptation to wearable platforms. Multi-sensor fusion approaches integrating inertial, LiDAR, and GNSS data are reviewed, along with edge/cloud processing architectures enabling real-time performance. This paper compiles numerous industrial use cases, from bridges and tunnels to plants and power facilities, demonstrating significant improvements in inspection efficiency, data quality, and worker safety. Key challenges are analyzed, including technical hurdles (battery life, processing limits, and harsh environments), human factors (ergonomics, training, and cognitive load), and regulatory issues (safety certification and data privacy). We also identify emerging trends, such as semantic SLAM, AI-driven defect recognition, hardware miniaturization, and collaborative multi-helmet systems. This review finds that VSLAM-equipped smart helmets offer a transformative approach to infrastructure inspection, enabling real-time mapping, augmented awareness, and safer workflows. We conclude by highlighting current research gaps, notably in standardizing systems and integrating with asset management, and provide recommendations for industry adoption and future research directions. Full article

The application of satellite-derived sea surface temperature in coastal regions is critical for resolving the dynamics of frontal features and coastal upwelling. Here, we examine and compare sea surface temperature (SST) gradients derived from two satellite products, the Multi-Scale Ultra-High Resolution SST Product (MUR, 0.01° grid scale) and the Operational SST and Ice Analysis (OSTIA, 0.05° grid scale), available through the Group for High Resolution SST (GHRSST). Both products show similar seasonal variability, with maxima occurring in the summer time frame. Additionally, both products show an increasing trend of SST gradients near the coast. However, differences exist between the two products (maximum gradient intensities were around 0.11 and 0.06 °C/km for OSTIA and MUR, respectively). The potential contributions of both cloud cover and the collocation of the MUR SST onto the OSTIA SST grid product to these differences were examined. Spectra and coherences were examined at two specific latitudes along the coast where upwelling can occur. A major conclusion is that future work needs to focus on cloud cover and its impact on the derivation of SST in coastal regions. Future comparisons also need to apply collocation methodologies that maintain, as much as possible, the spatial variability of the high-resolution product. Full article

Computer vision techniques such as three-dimensional digital image correlation (3D-DIC) and three-dimensional point tracking (3D-PT) have demonstrated broad applicability for monitoring the conditions of large-scale engineering systems by reconstructing and tracking dynamic point clouds corresponding to the surface of a structure. Accurate stereophotogrammetry measurements require the stereo cameras to be calibrated to determine their intrinsic and extrinsic parameters by capturing multiple images of a calibration object. This image-based approach becomes cumbersome and time-consuming as the size of the tested object increases. To streamline the calibration and make it scale-insensitive, a multi-sensor system embedding inertial measurement units and a laser sensor is developed to compute the extrinsic parameters of the stereo cameras. In this research, the accuracy of the proposed sensor-based calibration method in performing stereophotogrammetry is validated experimentally and compared with traditional approaches. Tests conducted at various scales reveal that the proposed sensor-based calibration enables reconstructing both static and dynamic point clouds, measuring displacements with an accuracy higher than 95% compared to image-based traditional calibration, while being up to an order of magnitude faster and easier to deploy. The novel approach has broad applications for making static, dynamic, and deformation measurements to transform how large-scale structural health monitoring can be performed. Full article

Optical coordinate measurement is a universal technique that aligns with the rapid development of industrial technologies and new materials. Nevertheless, can this technique be consistently effective when applied to the precise measurement of all types of materials? As shown in this article, an analysis of optical measurement systems reveals that some materials cause difficulties during the scanning process. This article details the matting process, resulting, as demonstrated, in lower measurement uncertainty values compared to the pre-matting state, and identifies materials for which applying a matting spray significantly improves the measurement quality. The authors propose a classification of materials into easy-to-scan and hard-to-scan groups, along with specific procedures to improve measurements, especially for the latter. Tests were conducted in an accredited Laboratory of Coordinate Metrology using an articulated arm with a laser probe. Measured objects included spheres made of ceramic, tungsten carbide (including a matte finish), aluminum oxide, titanium nitride-coated steel, and photopolymer resin, with reference diameters established by a high-precision Leitz PMM 12106 coordinate measuring machine. Diameters were determined from point clouds obtained via optical measurements using the best-fit method, both before and after matting. Color measurements using a spectrocolorimeter supplemented this study to assess the effect of matting on surface color. The results revealed correlations between the material type and measurement accuracy. Full article

A novel centrifuge-less cloud point extraction (CL-CPE) method was developed for the spectrophotometric determination of copper(II) using 4-nitrocatechol (4NC) as the chelating agent. The extraction system utilizes a mixed micellar phase composed of the nonionic surfactant Triton X-114 and the ionic liquid (IL) Aliquat^® 336 (A336). The extracted ternary ion-association complex, identified as (A336⁺)₂[Cu(4NC)₂], exhibits a maximum absorbance at 451 nm, with a molar absorption coefficient of 8.9 × 10⁴ M⁻¹ cm⁻¹ and a Sandell’s sensitivity of 0.71 ng cm⁻². The method demonstrates a linear response in the copper(II) concentration range of 32–763 ng mL⁻¹ and a limit of detection of 9.7 ng mL⁻¹. The logarithmic extraction constant (log K_ex) was determined to be 7.9, indicating efficient extraction. Method performance, evaluated by the Blue Applicability Grade Index (BAGI) and the Click Analytical Chemistry Index (CACI), confirmed its feasibility, practicality, simplicity, convenience, cost-effectiveness, environmental friendliness, and analytical competitiveness. The proposed IL-CL-CPE method was successfully applied to the analysis of a dietary supplement, a solution for infusion, and synthetic mixtures simulating various copper alloys. Full article

As medical technology develops and digital demands grow, personal health records (PHRs) are becoming more patient-centered than before based on cloud-based health information exchanges. While enhancing data accessibility and sharing, these systems present privacy and security issues, including data breaches and unauthorized access. We developed a post-quantum, group-oriented encryption scheme using the Crystal-Kyber Key encapsulation mechanism (KEM). Leveraging lattice-based post-quantum cryptography, this scheme ensures quantum resilience and chosen ciphertext attack security for layered cloud PHR environments. It supports four encryption modes: individual, group, subgroup-specific, and authorized subgroup decryption, meeting diverse data access needs. With efficient key management requiring only one private key per user, the developed scheme strengthens the privacy and security of PHRs in a future-proof, flexible, and scalable manner. Full article

To solve the low efficiency of traditional sheet metal measurement, this paper proposes a digital inspection method for sheet metal parts based on 3D point clouds. The 3D point cloud data of sheet metal parts are collected using a 3D laser scanner, and the topological relationship is established by using a K-dimensional tree (KD tree). The pass-through filtering method is adopted to denoise the point cloud data. To preserve the fine features of the parts, an improved voxel grid method is proposed for the downsampling of the point cloud data. Feature points are extracted via the intrinsic shape signatures (ISS) algorithm and described using the fast point feature histograms (FPFH) algorithm. After rough registration with the sample consensus initial alignment (SAC-IA) algorithm, an initial position is provided for fine registration. The improved iterative closest point (ICP) algorithm, used for fine registration, can enhance the registration accuracy and efficiency. The greedy projection triangulation algorithm optimized by moving least squares (MLS) smoothing ensures surface smoothness and geometric accuracy. The reconstructed 3D model is projected onto a 2D plane, and the actual dimensions of the parts are calculated based on the pixel values of the sheet metal parts and the conversion scale. Experimental results show that the measurement error of this inspection system for three sheet metal workpieces ranges from 0.1416 mm to 0.2684 mm, meeting the accuracy requirement of ±0.3 mm. This method provides a reliable digital inspection solution for sheet metal parts. Full article

Significant improvements in the forest-based industrial sector are expected due to increased digitalization; however, examples of practical implementations remain limited. This study explores the use of an automated algorithm to estimate truckload volumes based on 3D point cloud data acquired using two different LiDAR scanning platforms. This research compares the performance of a professional mobile laser scanning (MLS GeoSLAM) platform and a smartphone-based iPhone LiDAR system. A total of 48 truckloads were measured using a combination of manual, factory-based, and digital approaches. Accuracy was evaluated using standard error metrics, including the mean absolute error (MAE) and root mean square error (RMSE), with manual or factory references used as benchmarks. The results showed a strong correlation and no significant differences between the algorithmic and manual measurements when using the MLS platform (MAE = 2.06 m³; RMSE = 2.46 m³). For the iPhone platform, the results showed higher deviations and significant overestimation compared to the factory reference (MAE = 3.29 m³; RMSE = 3.60 m³). Despite these differences, the iPhone platform offers real-time acquisition and low-cost deployment. These findings highlight the trade-offs between precision and operational efficiency and support the adoption of automated measurement tools in timber supply chains. Full article

This paper presents the design and implementation of a high-precision vehicle detection and classification system for toll stations on national highways in Colombia, leveraging LiDAR-based 3D point cloud processing and supervised machine learning. The system integrates a multi-sensor architecture, including a LiDAR scanner, high-resolution cameras, and Doppler radars, with an embedded computing platform for real-time processing and on-site inference. The methodology covers data preprocessing, feature extraction, descriptor encoding, and classification using Support Vector Machines. The system supports eight vehicular categories established by national regulations, which present significant challenges due to the need to differentiate categories by axle count, the presence of lifted axles, and vehicle usage. These distinctions affect toll fees and require a classification strategy beyond geometric profiling. The system achieves $89.9\%$ overall classification accuracy, including $96.2\%$ for light vehicles and $99.0\%$ for vehicles with three or more axles. It also incorporates license plate recognition for complete vehicle traceability. The system was deployed at an operational toll station and has run continuously under real traffic and environmental conditions for over eighteen months. This framework represents a robust, scalable, and strategic technological component within Intelligent Transportation Systems and contributes to data-driven decision-making for road management and toll operations. Full article

Due to the challenges in obtaining full-body point clouds and the time-consuming registration of parametric body models, we propose an end-to-end Front Point Cloud Parametric Body Regression Network (FPCR-Net). This network directly regresses the pose and shape parameters of a parametric body model from a single front point cloud of the human body. The network first predicts the label probabilities of corresponding body parts and the back point cloud from the input front point cloud. Then, it extracts equivariant features from both the front and predicted back point clouds, which are concatenated into global point cloud equivariant features. For pose prediction, part-level equivariant feature aggregation is performed using the predicted part label probabilities, and the rotations of each joint in the parametric body model are predicted via a self-attention layer. Shape prediction is achieved by applying mean pooling to part-invariant features and estimating the shape parameters using a self-attention mechanism. Experimental results, both qualitative and quantitative, demonstrate that our method achieves comparable accuracy in reconstructing body models from front point clouds when compared to implicit representation-based methods. Moreover, compared to previous regression-based methods, vertex and joint position errors are reduced by 43.2% and 45.0%, respectively, relative to the baseline. Full article

The rapid growth of electric vehicles (EVs) and new energy systems has put lithium-ion batteries at the center of the clean energy change. Nevertheless, to achieve the best battery performance, safety, and sustainability in many changing circumstances, major innovations are needed in Battery Management Systems (BMS). This review paper explores how artificial intelligence (AI) and digital twin (DT) technologies can be integrated to enable the intelligent BMS of the future. It investigates how powerful data approaches such as deep learning, ensembles, and models that rely on physics improve the accuracy of predicting state of charge (SOC), state of health (SOH), and remaining useful life (RUL). Additionally, the paper reviews progress in AI features for cooling, fast charging, fault detection, and intelligible AI models. Working together, cloud and edge computing technology with DTs means better diagnostics, predictive support, and improved management for any use of EVs, stored energy, and recycling. The review underlines recent successes in AI-driven material research, renewable battery production, and plans for used systems, along with new problems in cybersecurity, combining data and mass rollout. We spotlight important research themes, existing problems, and future drawbacks following careful analysis of different up-to-date approaches and systems. Uniting physical modeling with AI-based analytics on cloud-edge-DT platforms supports the development of tough, intelligent, and ecologically responsible batteries that line up with future mobility and wider use of renewable energy. Full article

Light detection and ranging (LiDAR) provides three-dimensional environmental information that is critical for maintaining the safety and reliability of autonomous driving systems. However, dust accumulation on the LiDAR window can cause detection errors and degrade performance. This study determined the optimal spray conditions for accumulating dust to evaluate LiDAR sensor cleaning performance. A primary optimization experiment using spray pressure, spray speed, spray distance, and the number of sprays as variables showed that spray pressure and number of sprays had the most significant influence on the kinetic energy and distribution of dust particles. Notably, the interaction between spray distance and number of sprays—related to curvature effects—was identified as a key variable increasing process sensitivity. A supplementary experiment, which added spray angle as a variable, indicated that while spray pressure remained the most significant factor, spray angle and number of sprays had an indirect influence through interaction terms. Both experiments used the same response variable (point cloud data) interactions to stepwise analyze particle transfer and spatial diffusion. The resulting optimal conditions offer a standard basis for evaluating LiDAR cleaning performance and may help improve cleaning efficiency and maintenance strategies. Full article

Modernizing irrigation systems (ISs) from traditional gravity methods to sprinkler and drip technologies has significantly improved water use efficiency. However, it has simultaneously increased electricity demand and operational costs. Integrating photovoltaic generators into ISs represents a promising solution, as solar energy availability typically aligns with peak irrigation periods. Despite this potential, photovoltaic pumping systems (PVPSs) often face reliability issues due to fluctuations in solar irradiance, resulting in frequent start/stop cycles and premature equipment wear. The IEC 62253 standard establishes procedures for evaluating PVPS performance but primarily addresses steady-state conditions, neglecting transient regimes. As the main contribution, the current paper proposes a non-intrusive, high-resolution monitoring system and a methodology to assess the performance of an isolated, high-power PVPS, considering also transient regimes. The system records critical electrical, hydraulic and environmental parameters every second, enabling in-depth analysis under various weather conditions. Two performance indicators, pumped volume efficiency and equivalent operating time, were used to evaluate the system’s performance. The results indicate that near-optimal performance is only achievable under clear sky conditions. Under the appearance of clouds, control strategies designed to protect the system reduce overall efficiency. The proposed methodology enables detailed performance diagnostics and supports the development of more robust PVPSs. Full article

To address the issues in existing 3D point cloud facet generation networks, specifically, the tendency to produce a large number of empty facets and the uncertainty in facet count, this paper proposes a novel deep learning framework for robust facet segmentation. Based on the generated facet set, two exploratory applications are further developed. First, to overcome the bottleneck where inaccurate empty-facet detection impairs the downsampling performance, a facet-abstracted downsampling method is introduced. By using a learned facet classifier to filter out and discard empty facets, retaining only non-empty surface facets, and fusing point coordinates and local features within each facet, the method achieves significant compression of point cloud data while preserving essential geometric information. Second, to solve the insufficient precision in organ segmentation within crop point clouds, a facet growth-based segmentation algorithm is designed. The network first predicts the edge scores for the facets to determine the seed facets. The facets are then iteratively expanded according to adjacent-facet similarity until a complete organ region is enclosed, thereby enhancing the accuracy of segmentation across semantic boundaries. Finally, the proposed facet segmentation network is trained and validated using a synthetic dataset. Experiments show that, compared with traditional methods, the proposed approach significantly outperforms both downsampling accuracy and instance segmentation performance. In various crop scenarios, it demonstrates excellent geometric fidelity and semantic consistency, as well as strong generalization ability and practical application potential, providing new ideas for in-depth applications of facet-level features in 3D point cloud analysis. Full article

Rock bolts are crucial components in the subterranean support systems in underground mines that provide adequate structural reinforcement to the rock mass to prevent unforeseen hazards like rockfalls. This makes frequent assessments of such bolts critical for maintaining rock mass stability and minimising risks in underground mining operations. Where manual surveying of rock bolts is challenging due to the low-light conditions in the underground mines and the time-intensive nature of the process, automated detection of rock bolts serves as a plausible solution. To that end, this study focuses on the automatic identification of rock bolts within medium- to large-scale 3D point clouds obtained from underground mines using mobile laser scanners. Existing techniques for automated rock bolt identification primarily rely on feature engineering and traditional machine learning approaches. However, such techniques lack robustness as these point clouds present several challenges due to data noise, varying environments, and complex surrounding structures. Moreover, the target rock bolts are extremely small objects within large-scale point clouds and are often partially obscured due to the application of reinforcement shotcrete. Addressing these challenges, this paper proposes an approach termed DeepBolt, which employs a novel two-stage deep learning architecture specifically designed for handling severe class imbalance for the automatic and efficient identification of rock bolts in complex 3D point clouds. The proposed method surpasses state-of-the-art semantic segmentation models by up to 42.5% in Intersection over Union (IoU) for rock bolt points. Additionally, it outperforms existing rock bolt identification techniques, achieving a 96.41% precision and 96.96% recall in classifying rock bolts, demonstrating its robustness and effectiveness in complex underground environments. Full article