Search Results (391)

The fusion of LiDAR and photogrammetry point clouds is a necessary advancement in 3D-modeling, enabling more comprehensive and accurate representations of physical environments. The main contribution of this paper is the development of an innovative fusion system that combines classical algorithms, such as Structure from Motion (SfM), with advanced machine learning techniques, like Coherent Point Drift (CPD) and Feature-Metric Registration (FMR), to improve point cloud alignment and fusion. Experimental results, using a custom dataset of real-world scenes, demonstrate that the hybrid fusion method achieves an average error of less than 5% in the measurements of small reconstructed objects, with large objects showing less than 2% deviation from real sizes. The fusion process significantly improved structural continuity, reducing artifacts like edge misalignments. The k-nearest neighbors (kNN) analysis showed high reconstruction accuracy for the hybrid approach, demonstrating that the hybrid fusion system, particularly when combining machine learning-based refinement with traditional alignment methods, provides a notable advancement in both geometric accuracy and computational efficiency for real-time 3D-modeling applications. Full article

The geometric alignment of highways directly affects the fuel consumption of motor vehicles. To analyze the impact of the road gradient on fuel consumption, actual road tests were conducted in plateau and mountainous areas. Geographic Information Systems (GISs) were used to calculate road gradients, and Vehicle Specific Power (VSP) distributions were obtained through testing, serving as inputs for the motor vehicle emission simulator (MOVES) model. Finally, the simulation results were verified against the experimental results. The findings indicate a strong positive correlation between road gradients ranging from −5% to +5%, the VSP, and fuel consumption. At a constant gradient, the fuel consumption rate increases with the vehicle speed; the fuel consumption factor is lowest at 60 km/h and highest at 40 km/h. Under both constant and actual driving speeds, when the absolute values of uphill and downhill gradients are the same, the average fuel consumption for both uphill and downhill driving shows that, at gradients of 1% to 3%, the fuel savings from downhill driving can offset the additional fuel consumption on uphill driving. At gradients of 4% to 6%, the increase in fuel consumption on uphill driving surpasses the savings from downhill driving. During uphill climbs, lower speeds within the mid-to-low range result in lower fuel consumption and greater reserve power. The MOVES model demonstrates good adaptability in plateau and mountainous areas. Full article

Nowadays, with increasing concerns about the environment and energy security, efforts have intensified to develop effective energy generation technologies based on renewable sources that align with the principles of sustainable growth. In response to these demands, biomass-fueled furnaces have become essential components of modern combined heat and power generation systems. This work aims to predict the thermal performance of a helically coiled multi-tube heat exchanger designed to recover heat from waste biomass incineration flue gases. The working fluid used is thermal oil. The work focuses on determining the thermal output of a heat exchanger for prescribed design parameters, including the thermal parameters of cooling oil and the temperature difference of flue gas, and the geometrical details. A novel in-house stationary lumped multi-section model, utilizing the iterative calculation method, was developed, allowing fast predictions of the operation parameters of helically coiled multi-tube type heat exchangers. Two different configurations of the exchanger, three-pipe (case I) and four-pipe (case II), were considered. The thermal output obtained from calculations for case I showed a satisfactory convergence with the value based on the measurement data, at about 6%. Once validated, the model was used to determine the required heat exchange surface area of a four-pipe heat exchanger of larger design heat output (2.2 MW) and assumed tube dimensions and configurations. The accuracy of the heat exchanger capacity prediction was below 12%, proving the developed calculation tool to be reliable for design and optimization purposes. Full article

This study presents a method for aligning the geometric parameters of images in multi-channel imaging systems based on the application of pre-processing methods, machine learning algorithms, and a calibration setup using an array of orderly markers at the nodes of an imaginary grid. According to the proposed method, one channel of the system is used as a reference. The images from the calibration setup in each channel determine the coordinates of the markers, and the displacements of the marker centers in the system’s channels relative to the coordinates of the centers in the reference channel are then determined. Correction models are obtained as multiple polynomial regression models based on these displacements. These correction models align the geometric parameters of the images in the system channels before they are used in the calculations. The models are derived once, allowing for geometric calibration of the imaging system. The developed method is applied to align the images in the channels of a module of a multispectral imaging polarimeter. As a result, the standard image alignment error in the polarimeter channels is reduced from 4.8 to 0.5 pixels. Full article

This paper introduces a novel geometry-based synchrosqueezing S-transform (GSSST) for advanced gearbox fault diagnosis, designed to enhance diagnostic precision in both planetary and parallel gearboxes. Traditional time-frequency analysis (TFA) methods, such as the Synchrosqueezing S-transform (SSST), often face challenges in accurately representing fault-related features when significant mode closely spaced components are present. The proposed GSSST method overcomes these limitations by implementing an intuitive geometric reassignment framework, which reassigns time-frequency (TF) coefficients to maximize energy concentration, thereby allowing fault components to be distinctly isolated even under challenging conditions. The GSSST algorithm calculates a new instantaneous frequency (IF) estimator that aligns closely with the ideal IF, thus concentrating TF coefficients more effectively than existing methods. Experimental validation, including tests on simulated signals and real-world gearbox fault data, demonstrates that GSSST achieves high robustness and diagnostic accuracy across various types of gearbox faults even in the presence of noise. Moreover, unlike conventional reassignment method, GSSST supports partial signal reconstruction, a key advantage for applications requiring accurate signal recovery. This research highlights GSSST as a promising and versatile tool for diagnosing complex mechanical faults and provides new insights for the future development of TFA methods in mechanical fault analysis. Full article

Crowd panic emergencies can pose serious risks to public safety, and effective detection and mapping of such events are crucial for rapid response and mitigation. In this paper, we propose a real-time system for detecting and mapping crowd panic emergencies based on machine learning and georeferenced biometric data from wearable devices and smartphones. The system uses a Gaussian SVM machine learning classifier to predict whether a person is stressed or not and then performs real-time spatial analysis to monitor the movement of stressed individuals. To further enhance emergency detection and response, we introduce the concept of CLOT (Classifier Confidence Level Over Time) as a parameter that influences the system’s noise filtering and detection speed. Concurrently, we introduce a newly developed metric called DEI (Domino Effect Index). The DEI is designed to assess the severity of panic-induced crowd behavior by considering factors such as the rate of panic transmission, density of panicked people, and alignment with the road network. This metric offers immeasurable benefits by assessing the magnitude of the cascading impact, enabling emergency responders to quickly determine the severity of the event and take necessary actions to prevent its escalation. Based on individuals’ trajectories and adjacency, the system produces dynamic areas that represent the development of the phenomenon’s spatial extent in real time. The results show that the proposed system is effective in detecting and mapping crowd panic emergencies in real time. The system generates three types of dynamic areas: a dynamic Crowd Panic Area based on the initial stressed locations of the persons, a dynamic Crowd Panic Area based on the current stressed locations of the persons, and the dynamic geometric difference between these two. These areas provide emergency responders with a real-time understanding of the extent and development of the crowd panic emergency, allowing for a more targeted and effective response. By incorporating the CLOT and the DEI, emergency responders can better understand crowd behavior and develop more effective response strategies to mitigate the risks associated with panic-induced crowd movements. In conclusion, our proposed system, enhanced by the incorporation of these two new metrics, proves to be a dependable and efficient tool for detecting, mapping, and assessing the severity of crowd panic emergencies, leading to a more efficient response and ultimately safeguarding public safety. Full article

Optical image sequences of spacecraft acquired by space-based monocular cameras are typically imaged through exposure bracketing. The spacecraft feature deformable alignment network for multi-exposure image fusion (SFDA-MEF) aims to synthesize a High Dynamic Range (HDR) spacecraft image from a set of Low Dynamic Range (LDR) images with varying exposures. The HDR image contains details of the observed target in LDR images captured within a specific luminance range. The relative attitude of the spacecraft in the camera coordinate system undergoes continuous changes during the orbital rendezvous, which leads to a large proportion of moving pixels between adjacent frames. Concurrently, subsequent tasks of the In-Orbit Servicing (IOS) system, such as attitude estimation, are highly sensitive to variations in multi-view geometric relationships, which means that the fusion result should preserve the shape of the spacecraft with minimal distortion. However, traditional methods and unsupervised deep-learning methods always exhibit inherent limitations in dealing with complex overlapping regions. In addition, supervised methods are not suitable when ground truth data are scarce. Therefore, we propose an unsupervised learning framework for the multi-exposure fusion of optical spacecraft image sequences. We introduce a deformable convolution in the feature deformable alignment module and construct an alignment loss function to preserve its shape with minimal distortion. We also design a feature point extraction loss function to render our output more conducive to subsequent IOS tasks. Finally, we present a multi-exposure spacecraft image dataset. Subjective and objective experimental results validate the effectiveness of SFDA-MEF, especially in retaining the shape of the spacecraft. Full article

To effectively decarbonize Europe’s building stock, it is crucial to monitor the progress of energy consumption and the associated emissions. This study addresses the challenge by developing a national-scale urban building energy model (nUBEM) using artificial intelligence to predict non-renewable primary energy consumption and associated GHG emissions for residential buildings. Applied to the case study of Spain, the nUBEM leverages open data from energy performance certificates (EPCs), cadastral records, INSPIRE cadastre data, digital terrain models (DTM), and national statistics, all aligned with European directives, ensuring adaptability across EU member states with similar open data frameworks. Using the XGBoost machine learning algorithm, the model analyzes the physical and geometrical characteristics of residential buildings in Spain. Our findings indicate that the XGBoost algorithm outperforms other techniques estimating building-level energy consumption and emissions. The nUBEM offers granular information on energy performance building-by-building related to their physical and geometrical characteristics. The results achieved surpass those of previous studies, demonstrating the model’s accuracy and potential impact. The nUBEM is a powerful tool for analyzing residential building stock and supporting data-driven decarbonization strategies. By providing reliable progress indicators for renovation policies, the methodology enhances compliance with EU directives and offers a scalable framework for monitoring decarbonization progress across Europe. Full article

The present research focuses on the mechanical properties and stress evolution of gas-bearing soft coal seams during drilling, which are affected by a multitude of complex factors such as high ground stress, gas pressure, and pre-existing fractures. In this study, a combination of PFC2D (Particle Flow Code in 2 Dimensions) numerical simulation and theoretical analysis is employed to investigate the borehole mechanics and fracture evolution characteristics under diverse complex conditions and to determine the factors influencing different forms of borehole failure in soft coal seams. The principal outcomes are as follows: (1) At a horizontal displacement of 0.1 m from the borehole orifice of the soft coal seam, a stress peak value of 13.9 MPa is attained; the peak value of the coal body contact force is 15.8 MPa; the peak value of the displacement is 0.008 m; and the porosity of the coal body around the borehole ranges from 0.14 to 0.35. (2) With an increase in the number of pre-existing fractures, the inclination progressively aligns with that of the pre-existing fractures. Maximum values of contact force (5.13–51.9 MPa), stress (3.19–37.2 MPa), shape dimension, and fracture angle (140–150°) are achieved under the highest lateral pressure coefficient and gas pressure (1.5 MPa). (3) The borehole energy is directly proportional to the number of pre-existing fractures, the lateral pressure coefficient, and gas pressure. The number of pre-existing fractures has the most significant impact on the damage degree, followed by the lateral pressure coefficient and then the gas pressure. (4) Two types of failure are identified: fracture-dominated failure, which is controlled by the geometric distribution of pre-existing fractures, and stress-dominated failure, wherein the failure zone gradually extends both upward and downward with an increasing lateral pressure coefficient. Full article

Near-net-shaped metal products manufactured by high-pressure diecasting (HPD) encountered more or less critical failure during operation, owing to the development of micro-defects and structural inhomogeneity attributed to the complexity of geometrical die design. Because the associated work primarily relies on technical experience, it is necessary to perform the structural analysis of the HPDed component in comparison with simulation-based findings that forecast flow behavior, hence reducing trial and error for optimization. This study validated the fluidity and solidification behaviors of a commercial-grade Al-Si-Cu-Mg alloy (ALDC12) that is widely used in electric vehicle housing parts using the ProCAST tool. Both experimental and simulation results exhibited that defects at the interface of a compact mold filling were barely detected. However, internal micro-pores were seen in the bolt region, resulting in a 17.27% drop in micro-hardness compared to other parts, for which the average values from distinguished observation areas were 111.24 HV, 92.03 HV, and 103.87 HV. The simulation aligns with structural observations on defect formation due to insufficient fluidity in local geometry. However, it may underestimate the cooling rate under isothermal conditions. Thus, the simulation used in this work provides reliable predictions for optimizing HPD processing of the present alloy. Full article

During the harvesting process of Cerasus humilis, the fruits are susceptible to compression and impacts from the combing teeth, leading to internal damage to the pulp and rupture of the peel. This compromises the quality of the harvested fruits and subsequent processing, resulting in significant economic losses. To investigate the mechanical behavior of Cerasus humilis fruit, this study measured the geometric parameters as well as the mechanical properties (failure load, elastic modulus, compressive strength, and fracture energy) of the peel, pulp, and core in both the axial and radial directions. A geometric model of Cerasus humilis fruit was constructed using three-dimensional reverse engineering technology. The rupture process of the fruit under compressive loading was simulated and analyzed using Abaqus software (Version 2023). The damage mechanisms were investigated, and the accuracy and reliability of the finite element model were validated through compression experiments. The experimental results indicated that the mechanical properties of the peel of Cerasus humilis fruit exhibited no significant differences between the axial and radial directions, allowing it to be regarded as an isotropic material. In contrast, the mechanical properties of the pulp and core showed significant differences in both directions, demonstrating anisotropic characteristics. Additionally, the axial compressive strength of the Cerasus humilis fruit was higher than its radial compressive strength. The simulation results revealed that during axial compression, when the surface stress of the peel reached 0.08 MPa, the fruit completely fractured. The location and morphology of the cracks in the simulation were consistent with those observed in the experimental results. Furthermore, under different compression directions, the force–displacement curves obtained from actual compression tests closely aligned with those from the finite element simulations. The finite element model established in this study effectively simulates and predicts the cracking and internal damage behavior of Cerasus humilis fruit under compressive loads. This research provides a theoretical foundation and technical guidance for reducing mechanical damage during the harvesting process of Cerasus humilis. Full article

Semantic segmentation tasks encompass various applications, such as autonomous driving, medical imaging, and robotics. Achieving accurate semantic information retrieval under conditions of high dynamic range and rapid scene changes remains a significant challenge for image-based algorithms. This challenge is primarily attributable to the limitations of conventional image sensors, which can experience motion blur or exposure artifacts. In contrast, event-based vision sensors, which asynchronously report changes in pixel intensity, offer a compelling solution by acquiring visual information at the same rate as the scene dynamics, thereby mitigating these limitations. However, we encounter a significant challenge in event-based semantic segmentation tasks: the need to expend time on converting event data into frame images to align with existing image-based semantic segmentation techniques. This approach squanders the inherently high temporal resolution of event data, compromising the accuracy and real-time performance of semantic segmentation tasks. To address these issues, this work explores a sparse semantic segmentation approach that directly addresses event data. We propose a network named EventSegNet that improves the ability to extract geometric features from event data by combining geometric feature enhancement operations and attention mechanisms. Based on this, we propose a large-scale event-based semantic segmentation dataset that provides labels for each event. Our approach achieved a new F1 score of 84.2% on the dataset. In addition, a lightweight and edge-oriented AI inference deployment technique was implemented for the network model. Compared to the baseline model, the optimized network model reduces the F1 score by 1.1% but is more than twice as fast computationally, enabling real-time inference on the NVIDIA AGX Xavier. Full article

Background: Accurate determination of the natural head position (NHP) is essential in orthognathic surgery for optimal surgical planning and improved patient outcomes. However, traditional methods encounter reproducibility issues and rely on external devices or patient cooperation, potentially leading to inaccuracies in the surgical plan. Methods: To address these limitations, we developed a geometric deep learning network (NHP-Net) to automatically reproduce NHP from CT scans. A dataset of 150 orthognathic surgery patients was utilized. Three-dimensional skull meshes were converted into point clouds and normalized to fit within a unit sphere. NHP-Net was trained to predict a 3 × 3 rotation matrix to align the CT-acquired posture with the NHP. Experiments were conducted to determine optimal point cloud sizes and loss functions. Performance was evaluated using mean absolute error (MAE) for roll, pitch, and yaw angles, as well as a rotation error (RE) metric. Results: NHP-Net achieved the lowest RE of 1.918° ± 1.099° and demonstrated significantly lower MAEs in roll and pitch angles compared to other deep learning models (p < 0.05). These findings indicate that NHP-Net can accurately align CT-acquired postures to the NHP, enhancing the precision of surgical planning. Conclusions: By effectively improving the accuracy and efficiency of NHP reproduction, NHP-Net reduces the workload of surgeons, supports more precise orthognathic surgical interventions, and ultimately contributes to better patient outcomes. Full article

In light of the challenges posed by intricate algorithms, subpar recognition accuracy, and prolonged recognition duration in current machine vision for bridge structure monitoring, this paper presents an innovative method for recognizing and extracting structural edges based on the Gaussian difference method. Initially, grayscale processing enhances the image’s information content. Subsequently, a Region of Interest (ROI) is identified to streamline further processing steps. Following this, Gaussian check images at different scales are processed, capitalizing on the observation that edges show reduced correspondence to the Gaussian kernel. Then, the structure image’s edges are derived using the difference algorithm. Lastly, employing the scale factor, the algorithm translates the detected edge displacement within the image into the precise physical displacement of the structure. This method enables continuous monitoring of the structure and facilitates the assessment of its safety status. The experimental results affirm that the proposed algorithm adeptly identifies and extracts the structural edge’s geometric characteristics with precision. Furthermore, the displacement information derived from the scale factor closely aligns with the actual displacement, validating the algorithm’s effectiveness. Full article

The cost of indoor mapping methods based on three-dimensional (3D) LiDAR can be relatively high, and they lack environmental color information, thereby limiting their application scenarios. This study presents an innovative, low-cost, omnidirectional 3D color LiDAR mapping system for indoor environments. The system consists of two two-dimensional (2D) LiDARs, six monocular cameras, and a servo motor. The point clouds are fused with imagery using a pixel-spatial dual-constrained depth gradient adaptive regularization (PS-DGAR) algorithm to produce dense 3D color point clouds. During fusion, the point cloud is reconstructed inversely based on the predicted pixel depth values, compensating for areas of sparse spatial features. For indoor scene reconstruction, a globally consistent alignment algorithm based on particle filter and iterative closest point (PF-ICP) is proposed, which incorporates adjacent frame registration and global pose optimization to reduce mapping errors. Experimental results demonstrate that the proposed density enhancement method achieves an average error of 1.5 cm, significantly improving the density and geometric integrity of sparse point clouds. The registration algorithm achieves a root mean square error (RMSE) of 0.0217 and a runtime of less than 4 s, both of which outperform traditional iterative closest point (ICP) variants. Furthermore, the proposed low-cost omnidirectional 3D color LiDAR mapping system demonstrates superior measurement accuracy in indoor environments. Full article