Search Results (335)

6DoF pose estimation is one of the key technologies for robotic grasping. Due to the lack of texture, most existing 6DoF pose estimation methods perform poorly on transparent objects. In this work, a hierarchical feature fusion network, HFF6DoF, is proposed for 6DoF pose estimation of transparent objects. In HFF6DoF, appearance and geometry features are extracted from RGB-D images with a dual-branch network, and are hierarchically fused for information aggregation. A decoding module is introduced for semantic segmentation and keypoint vector-field prediction. Based on the results of semantic segmentation and keypoint prediction, 6DoF poses of transparent objects are calculated by using Random Sample Consensus (RANSAC) and Least-Squares Fitting. In addition, a new transparent-object 6DoF pose estimation dataset, TDoF20, is constructed, which consists of 61,886 pairs of RGB and depth images covering 20 types of objects. The experimental results show that the proposed HFF6DoF outperforms state-of-the-art approaches on the TDoF20 dataset by a large margin, achieving an average ADD of 50.5%. Full article

Accurate measurement of plant height in leafy vegetables is challenging due to their short stature, high planting density, and severe canopy occlusion during later growth stages. These factors often limit the reliability of single-plant monitoring across the full growth cycle in open-field environments. To address this, we propose a multi-temporal point cloud alignment method for accurate plant height measurement, focusing on Choy Sum (Brassica rapa var. parachinensis). The method estimates plant height by calculating the vertical distance between the canopy and the ground. Multi-temporal point cloud maps are reconstructed using an enhanced Oriented FAST and Rotated BRIEF–Simultaneous Localization and Mapping (ORB-SLAM3) algorithm. A fixed checkerboard calibration board, leveled using a spirit level, ensures proper vertical alignment of the Z-axis and unifies coordinate systems across growth stages. Ground and plant points are separated using the Excess Green (ExG) index. During early growth stages, when the soil is minimally occluded, ground point clouds are extracted and used to construct a high-precision reference ground model through Cloth Simulation Filtering (CSF) and Kriging interpolation, compensating for canopy occlusion and noise. In later growth stages, plant point cloud data are spatially aligned with this reconstructed ground surface. Individual plants are identified using an improved Euclidean clustering algorithm, and consistent measurement regions are defined. Within each region, a ground plane is fitted using the Random Sample Consensus (RANSAC) algorithm to ensure alignment with the X–Y plane. Plant height is then determined by the elevation difference between the canopy and the interpolated ground surface. Experimental results show mean absolute errors (MAEs) of 7.19 mm and 18.45 mm for early and late growth stages, respectively, with coefficients of determination (R²) exceeding 0.85. These findings demonstrate that the proposed method provides reliable and continuous plant height monitoring across the full growth cycle, offering a robust solution for high-throughput phenotyping of leafy vegetables in field environments. Full article

Building information models (BIMs) serve as a foundational tool for digital management of existing structures. Traditional methods suffer from low automation and heavy reliance on manual intervention. This paper proposes an automated method for structural component dimension recognition and BIM modeling based on 3D point cloud data. The proposed methodology follows a three-step workflow. First, the raw point cloud is semantically segmented using the PointNet++ deep learning network, and individual structural components are effectively isolated using the Fast Euclidean Clustering (FEC) algorithm. Second, the principal axis of each component is determined through Principal Component Analysis, and the Random Sample Consensus (RANSAC) algorithm is applied to fit the boundary lines of the projected cross-sections, enabling the automated extraction of geometric dimensions. Finally, an automated script maps the extracted geometric parameters to standard IFC entities to generate the BIM model. The experimental results demonstrate that the average dimensional error for beams and columns is within 3 mm, with the exception of specific occluded components. This study realizes the efficient transformation from point cloud data to BIM models through an automated workflow, providing reliable technical support for the digital reconstruction of existing buildings. Full article

Background/Objectives: Caffeine citrate represents the standard pharmacological intervention for apnea of prematurity (AOP) and episodes of intermittent hypoxia (IH). Despite its widespread use, consensus regarding the necessity of routine serum monitoring, optimal dosing protocols, and precise clinical indications remains elusive. The primary objective of this investigation was to evaluate the longitudinal trajectory of serum caffeine concentrations in preterm infants and to analyze their correlation with the incidence of AOP and IH episodes. Furthermore, we sought to determine whether blood caffeine concentrations varied significantly across gestational ages throughout the postnatal period. Methods: This multicenter, prospective observational study enrolled preterm infants with a gestational age of ≤30 weeks. Participants were administered a standard loading dose of caffeine citrate within the first 24 h of life, followed by a standardized maintenance regimen. Serum caffeine levels were quantified on a weekly basis. The cohort was stratified into two distinct groups based on gestational age: Group 1 (23–27 weeks) and Group 2 (28–30 weeks). Results: The study yielded 588 serum caffeine measurements from a cohort of 104 preterm infants, characterized by a median gestational age of 28 weeks (range: 23–30 weeks) and a mean birth weight of 1034 ± 296 g. Statistical analysis revealed no significant disparities in serum caffeine concentrations across gestational age groups (p > 0.05). Notably, during the third week of life, infants with apneic episodes demonstrated significantly lower caffeine levels than those without apnea (p = 0.016). Furthermore, a significant negative correlation was identified between serum caffeine concentrations and the frequency of IH episodes during the third, fourth, and fifth weeks of life across multiple oxygen saturation thresholds. Conclusions: While serum caffeine concentrations in preterm infants did not vary significantly with gestational age, lower levels were associated with a higher incidence of AOP and IH episodes. These results suggest that while routine monitoring or dose adjustment based solely on gestational age may not be warranted, maintaining adequate serum levels is critical for symptom management. Future research should prioritize randomized controlled trials with expanded sample sizes, extended follow-up periods, and a rigorous analysis of adverse effects. Full article

Background/Objectives: Prolonged fasting—defined as voluntary abstinence from caloric intake for periods exceeding 24 h—is increasingly recognized not only as a metabolic intervention but also as a psycho-behavioral modulator. According to the 2024 international consensus, intermittent fasting encompasses diverse temporal patterns including time-restricted feeding, alternate-day fasting, and periodic fasting of multi-day duration. While metabolic benefits are well documented, the psychoneurobiological and psychiatric consequences remain incompletely characterized. This review critically appraises current evidence on the psychological and psychiatric effects of prolonged and intermittent fasting, including both secular and religious practices. Methods: A narrative synthesis was conducted on clinical trials, observational studies, and translational research published between January 2010 and June 2025 in PubMed, Scopus, and PsycINFO. Search terms included combinations of “prolonged fasting,” “intermittent fasting,” “psychological,” “psychiatric,” “religious fasting,” “Ramadan,” and “Orthodox Church.” Eligible studies required explicit evaluation of mood, cognition, stress physiology, or psychiatric symptoms. Data were analyzed qualitatively, with particular attention to study quality, fasting regimen characteristics, and participant vulnerability. This is a non-registered narrative synthesis drawing on clinical trials, observational studies, and preclinical evidence published between January 2010 and June 2025. Results: Eighty-seven studies met inclusion criteria (39 human; 48 preclinical). In metabolically healthy adults, short-term time-restricted eating and supervised prolonged fasting were associated with modest reductions in depressive symptoms and perceived stress, with small improvements in executive functioning—typically observed in small samples and with limited follow-up. Religious fasting during Ramadan and the Orthodox Christian fasting periods demonstrated similar neuropsychological effects, including greater perceived spiritual meaning and affective modulation, though cultural context played a moderating role. Potential adverse mental-health impacts included mood destabilization, anxiety exacerbation, and rare psychotic or manic decompensations in vulnerable individuals. Randomized trials reported few adverse events and no signal for severe psychiatric harm, whereas observational studies more often noted symptom exacerbations in at-risk groups. Patients with eating disorder phenotypes exhibited increased cognitive preoccupation with food and a heightened risk of behavioral relapse. Methodological heterogeneity across studies—including variation in fasting protocols, psychological assessments, and follow-up duration—limited cross-study comparability. Conclusions: Evidence indicates a bidirectional relationship wherein fasting may foster psychological resilience in select populations while posing significant psychiatric risks in others. Inclusion of religious fasting traditions enriches understanding of culturally mediated outcomes. To enhance rigor and safety, future studies should incorporate clinician-rated outcomes (e.g., HDRS-17, CGI-S/CGI-I), standardized adverse-event tracking using validated psychiatric terminology, and prospective safety monitoring protocols, with ≥6–12-month follow-up. Full article

Accurate extrinsic calibration between radar and camera sensors is essential for reliable multi-modal perception in robotics and autonomous navigation. Traditional calibration methods often rely on artificial targets such as checkerboards or corner reflectors, which can be impractical in dynamic or large-scale environments. This study presents a fully targetless calibration framework that estimates the rigid spatial transformation between radar and camera coordinate frames by aligning their observed trajectories of a moving object. The proposed method integrates You Only Look Once version 5 (YOLOv5)-based 3D object localization for the camera stream with Density-Based Spatial Clustering of Applications with Noise (DBSCAN) and Random Sample Consensus (RANSAC) filtering for sparse and noisy radar measurements. A passive temporal synchronization technique, based on Root Mean Square Error (RMSE) minimization, corrects timestamp offsets without requiring hardware triggers. Rigid transformation parameters are computed using Kabsch and Umeyama algorithms, ensuring robust alignment even under millimeter-wave (mmWave) radar sparsity and measurement bias. The framework is experimentally validated in an indoor OptiTrack-equipped laboratory using a Skydio 2 drone as the dynamic target. Results demonstrate sub-degree rotational accuracy and decimeter-level translational error (approximately 0.12–0.27 m depending on the metric), with successful generalization to unseen motion trajectories. The findings highlight the method’s applicability for real-world autonomous systems requiring practical, markerless multi-sensor calibration. Full article

In ocean bottom node (OBN) seismic exploration, the precise positioning of OBNs directly affects seismic data quality. However, complex marine environments often introduce intricate outliers into collected acoustic positioning data, which severely restricts the positioning accuracy and stability of OBNs. To address issues such as poor threshold adaptability and low continuous outlier detection capability in existing outlier detection methods when processing OBN acoustic observation data, this paper proposes a quality control method for seabed acoustic positioning based on an improved Random Sample Consensus (RANSAC) method. This method employs a dynamic threshold that adapts to the observation fitting value and inlier rate, and introduces time-series uniform grouping sampling, thereby optimizing threshold setting and sampling strategy to enhance outlier detection performance and computational efficiency. Simulation results demonstrate that compared to the conventional RANSAC, the improved method exhibits superior outlier detection performance and computational efficiency, while achieving optimal positioning accuracy. Field experiment results demonstrate that the improved method can effectively detect and eliminate both large and small outliers, as well as continuous outliers. Compared to the fixed-threshold method, the improved RANSAC method improves positioning accuracy by 28.8% and 42.2% in the Direction Alongline (DA) and Direction Crossline (DC), respectively. Additionally, it achieves a 13.3% improvement in DA positioning accuracy and a 49.0% increase in computational efficiency over the conventional RANSAC method. The research findings demonstrate that the improved RANSAC method effectively enhances the accuracy and efficiency of OBN positioning, providing technical support for high-precision positioning in complex marine seismic exploration. Full article

UAV-mounted multispectral sensors are widely used to study crop health. Utilising the same cameras to capture close-up images of crops can significantly improve crop health evaluations through multispectral technology. Unlike RGB cameras that only detect visible light, these sensors can identify additional spectral bands in the red-edge and near-infrared (NIR) ranges. This enables early detection of diseases, pests, and deficiencies through the calculation of various spectral indices. In this work, the ability to use UAV-multispectral sensors for close-proximity imaging of crops was studied. Images of plants were taken with a Micasense Rededge-MX from top and side views at a distance of 1 m. The camera has five sensors that independently capture blue, green, red, red-edge, and NIR light. The slight misalignment of these sensors results in a shift in the swath. This shift needs to be corrected to create a proper layer stack that could allow for further processing. This research utilised the Oriented FAST and Rotated BRIEF (ORB) method to detect features in each image. Random sample consensus (RANSAC) was used for feature matching to find similar features in the slave images compared to the master image (indicated by the green band). Utilising homography to warp the slave images ensures their perfect alignment with the master image. After alignment, the images were stacked, and the alignment accuracy was visually checked using true colour composites. The side-view images of the plants were perfectly aligned, while the top-view images showed errors, particularly in the pixels far from the centre. This study demonstrates that UAV-mounted multispectral sensors can capture images of plants effectively, provided the plant is centred in the frame and occupies a smaller area within the image. Full article

Background/Objectives: The optimal duration of antibiotic therapy for bacterial prosthetic joint infections (PJI) remains a topic of considerable debate. Current recommendations are often based on limited evidence and expert consensus. Emerging data suggest that shorter antibiotic courses may be as effective as prolonged treatments in select cases. Shortening the duration of therapy offers several advantages, including a reduced risk of bacterial resistance, fewer adverse events, and cost savings. However, this approach must be carefully balanced with the individual patient’s risk of treatment failure. This narrative review aims to synthesize current evidence regarding the duration of antibiotic therapy in PJIs, according to surgical strategies—DAIR (debridement, antibiotics, and implant retention), one-stage exchange, two-stage exchange, and resection without reimplantation—and to identify parameters that may guide individualized and potentially shortened regimens. Methods: We conducted a comprehensive search of PubMed, Embase, and Cochrane Library databases through January 2025, including observational studies, randomized controlled trials, and international guidelines. Reference lists of key articles were also screened. Results: Studies on DAIR suggest that longer regimens (e.g., 8–12 weeks) are necessary, especially in staphylococcal infections, as confirmed by the DATIPO trial, which showed higher failure rates with 6 weeks compared to 12 weeks. Evidence on one-stage exchange is limited but increasingly suggests that 6 weeks may be sufficient in selected patients; however, no dedicated trial has confirmed this. In two-stage exchange, small retrospective series report successful outcomes with short antibiotic therapy combined with local antibiotics, but randomized trials show trends favoring longer regimens. For patients treated with permanent resection arthroplasty, arthrodesis, or amputation, antibiotic durations are highly variable, with few robust data. Across all strategies, most studies are limited by methodological weaknesses, including small sample sizes, retrospective design, lack of microbiological stratification, and heterogeneous outcome definitions. Conclusions: Despite growing interest in shortening antibiotic durations in PJIs, high-quality evidence remains limited. Until additional randomized trials are available—particularly in one- and two-stage exchange settings—12 weeks remains the safest reference duration for most patients, especially those with retained hardware. Future studies should incorporate stratification by infection type, causative organism, and host factors to define tailored and evidence-based antibiotic strategies. Full article

We investigate a variation of the classical voter model where the set of influencing agents depends on an individual’s current opinion. The initial population is made up of a random sample of equally sized sub-populations for each state, and two types of interactions are considered: (i) direct neighbors and (ii) second neighbors (friends of direct neighbors, excluding the direct neighbors themselves). The neighborhood size, reflecting regular network connectivity, remains constant across all agents. Our findings show that varying the interaction range introduces asymmetries that affect the probability of consensus and convergence time. At low connectivity, direct neighbor interactions dominate, leading to consensus. As connectivity increases, the probability of either state reaching consensus becomes equal, reflecting symmetric dynamics. This asymmetric effect on the probability of consensus is shown to be independent of network topology in small-world and scale-free networks. Asymmetry also influences convergence time: while symmetric cases display decreasing times with increased connectivity, asymmetric cases show an almost linear increase. Unlike the probability of reaching consensus, the impact of asymmetry on convergence time depends on the network topology. The introduction of stubborn agents further magnifies these effects, especially when they favor the less dominant state, significantly lengthening the time to consensus. We conclude by discussing the implications of these findings for decision-making processes and political campaigns in human populations. Full article

Rutting is a critical form of pavement distress that compromises driving safety and long-term structural integrity. Traditional detection methods predominantly rely on cross-sectional measurements and high-cost inertial navigation-assisted laser scanning, which limits their applicability for large-scale, full-section evaluation. To address these limitations, this study proposes a framework for full-section rutting detection leveraging an area-array structured light camera for efficient 3D data acquisition. A multi-scale texture enhancement strategy based on 2D wavelet transform is introduced to extract latent surface features, enabling robust and accurate point-cloud registration without the need for artificial markers. Additionally, an improved Random Sample Consensus—Density-Based Spatial Clustering of Applications with Noise (RANSAC-DBSCAN) algorithm is designed to enhance the precision and robustness of rutting region segmentation under real-world pavement conditions. The proposed method is experimentally validated using 102 multi-frame pavement point clouds. Compared to Fast Point Feature Histograms (FPFH) and Deep Closest Point (DCP), the registration approach achieves a 71.31% and 80.64% reduction in point-to-plane error, respectively. For rutting segmentation, the enhanced clustering method attains an average F1-score of 90.5%, outperforming baseline methods by over 15%. The proposed workflow can be seamlessly integrated into vehicle-mounted structured-light inspection systems, offering a low-cost and scalable solution for near real-time, full-lane rutting detection in routine pavement monitoring. Full article

Blockchain technology has rapidly evolved beyond cryptocurrencies, underpinning diverse applications such as supply chains, healthcare, and finances, yet its security vulnerabilities remain a critical barrier to safe adoption. However, attackers increasingly exploit weaknesses in consensus protocols, smart contracts, and network layers with threats such as Denial-of-Chain (DoC) and Black Bird attacks, posing serious challenges to blockchain ecosystems. We conducted anomaly detection using two independent datasets (A and B) generated from simulation attack scenarios including hash rate, Sybil, Eclipse, Finney, and Denial-of-Chain (DoC) attacks. Key blockchain metrics such as hash rate, transaction authorization status, and recorded attack consequences were collected for analysis. We compared both class-balanced and imbalanced datasets, applying Synthetic Minority Oversampling Technique (SMOTE) to improve representation of minority-class samples and enhance performance metrics. Supervised models such as Random Forest, Gradient Boosting, and Logistic Regression consistently outperformed unsupervised models, achieving high F1-scores (0.90), while balancing the training data had only a modest effect. The results are based on simulated environment and should be considered as preliminary until the experiment is performed in a real blockchain environment. Based on identified gaps, we recommend the exploration and development of multifaceted defense approaches that combine prevention, detection, and response to strengthen blockchain resilience. Full article

As drone-based Light Detection and Ranging (LiDAR) becomes more accessible, it presents new opportunities for automated, geometry-driven classification. This study investigates the use of LiDAR point cloud data and Machine Learning (ML) to classify rooftop solar panels from building surfaces. While rooftop solar detection has been explored using satellite and aerial imagery, LiDAR offers geometric and reflectance-based attributes for classification. Two datasets were used: the University of Southern Queensland (UniSQ) campus, with commercial-sized panels, both elevated and flat, and a suburban area in Newcastle, Australia, with residential-sized panels sitting flush with the roof surface. UniSQ was classified using RANSAC (Random Sample Consensus), while Newcastle’s dataset was processed based on reflectance values. Geometric features were selected based on histogram overlap and Kullback–Leibler (KL) divergence, and models were trained using a Multilayer Perceptron (MLP) classifier implemented in both PyTorch and Scikit-learn libraries. Classification achieved F1 scores of 99% for UniSQ and 95–96% for the Newcastle dataset. These findings support the potential for ML-based classification to be applied to unlabelled datasets for rooftop solar analysis. Future work could expand the model to detect additional rooftop features and estimate panel counts across urban areas. Full article

To address the high-precision navigation requirements of urban low-altitude electric vertical take-off and landing (eVTOL) aircraft in environments where global navigation satellite systems (GNSSs) are denied and under complex urban terrain conditions, a terrain-matching optimization algorithm based on light detection and ranging (LiDAR) is proposed. Given the issues of GNSS signal susceptibility to occlusion and interference in urban low-altitude environments, as well as the error accumulation in inertial navigation systems (INSs), this algorithm leverages LiDAR point cloud data to assist in constructing a digital elevation model (DEM). A terrain-matching optimization algorithm is then designed, incorporating enhanced feature description for key regions and an adaptive random sample consensus (RANSAC)-based misalignment detection mechanism. This approach enables efficient and robust terrain feature matching and dynamic correction of INS positioning errors. The simulation results demonstrate that the proposed algorithm achieves a positioning accuracy better than 2 m in complex scenarios such as typical urban canyons, representing a significant improvement of 25.0% and 31.4% compared to the traditional SIFT-RANSAC and SURF-RANSAC methods, respectively. It also elevates the feature matching accuracy rate to 90.4%; meanwhile, at a 95% confidence level, the proposed method significantly increases the localization success rate to 96.8%, substantially enhancing the navigation and localization accuracy and robustness of eVTOLs in complex low-altitude environments. Full article

To detect damage in underwater pile foundations, we propose a new method based on the diffusion probability model and improved PointMLP. First, PCA-ICP registration is carried out for the point cloud data from different stations using a sonar system. A variety of filtering algorithms and the Random Sample Consensus (RANSAC) method are employed to obtain a complete point cloud of the pile foundation. The pile foundation defect point cloud is generated and enhanced based on the diffusion probability model. The feature attention mechanism is added to the PointMLP, and then the improved PointMLP is trained to identify the defect of the pile foundation. In our study, the point cloud of a wharf pile foundation was collected, and the experimental results effectively identified the damage to the pile foundation. Up to 95% accuracy was achieved for the calculated volume. The volume error of the damage was 0.0756 m³, with an accuracy of 95.238%. Thus, this method can provide technical support for detecting underwater pile foundation defects and avoiding the occurrence of major accidents. Full article