Mesh Data Research Articles

Long-Term Fine-Grained Forecasts of Emergency Demand Using EMS Big Data and Population Estimates

In recent years, Japan has been facing a super-aging society, impacting various sectors. The issues of overcrowded emergency medical services and the increase in emergency transport cases are particularly severe, necessitating urgent responses. The research group, in collaboration with the Kobe City Fire Department, is conducting a study focusing on long-term fine-grained forecasts of emergency demand. This study aims to provide indicators for the strategic deployment of emergency teams and the scaling of medical facilities. By utilizing regional mesh data, it can capture local characteristics far more precisely than previous city or district-level forecasts, offering significant advantages for local government policy implementation. In the prediction process, there are two stages to leverage national land numerical information and improve the accuracy of the forecast model. The results reveal regional disparities in future emergency demand, enabling optimal allocation of emergency resources and strategic planning for emergency services.

3D Head Pose Estimation via Normal Maps: A Generalized Solution for Depth Image, Point Cloud, and Mesh

Head pose estimation plays a crucial role in various applications, including human–machine interaction, autonomous driving systems, and 3D reconstruction. Current methods address the problem primarily from a 2D perspective, which limits the efficient utilization of 3D information. Herein, a novel approach, called pose orientation‐aware network (POANet), which leverages normal maps for orientation information embedding, providing abundant and robust head pose information, is introduced. POANet incorporates the axial signal perception module and the rotation matrix perception module, these lightweight modules make the approach achieve state‐of‐the‐art (SOTA) performance with few computational costs. This method can directly analyze various topological 3D data without extensive preprocessing. For depth images, POANet outperforms existing methods on the Biwi Kinect head pose dataset, reducing the mean absolute error (MAE) by ≈30% compared to the SOTA methods. POANet is the first method to perform rigid head registration in a landmark‐free manner. It also incorporates few‐shot learning capabilities and achieves an MAE of about on the Headspace dataset. These features make POANet a superior alternative to traditional generalized Procrustes analysis for mesh data processing, offering enhanced convenience for human phenotype studies.

3D textured mesh scene data fusion method considering multiple scales and resolutions

ABSTRACT The fusion of 3D textured mesh scene data can effectively and seamlessly integrate multiple spatially related 3D geographical scene models into larger and more comprehensive datasets. Existing methods usually have different degrees of texture distortion and unreduced texture problems in the splicing area, and these methods do not consider the current situation of Level of Detail(LoD) data organisation in the 3D textured mesh model. We propose a 3D textured mesh scene data fusion method considering multiple scales and resolutions. First, seamless extraction of splicing areas was achieved based on spatial relationship constraints and orthogonal inverse projection principles. Second, the sparse scene structure concept was employed to generate sparse summary scene images. Finally, a dual simplification operator for both mesh and texture was proposed to construct multi-resolution 3D textured mesh models, simultaneously reconstructing triangular facets and textures within the splicing regions. We used multiple 3D textured mesh data constructed from aerial obliques to conduct data fusion experimental verification. The results indicate that our method exhibits minimal texture distortion during grid reconstruction in splicing areas and model simplification, effectively reducing the amount of simplified texture data. Additionally, our method adeptly addresses multilevel detailed 3D textured mesh models, demonstrating good feasibility and advancement.

OccFaçade: enabling precise building façade parsing in large urban scenes with occlusion

ABSTRACT Building façade parsing is to recognize the building façade image into different categories of individuals including walls, doors, windows, balconies, etc. However, obstructions such as trees present a significant challenge to conducting façade parsing. In this paper, we designed OccFaçade to achieve high-precision parsing of occluded building façades in large urban scenes. OccFaçade primarily incorporates two modules, Multi-layer Dilated Convolution Module (MD-Module) and Multi-scale Row-Column Convolution Module (MRC-Module), to capture repeated texture in local and row-column directions. This aims to leverage repetitive textures to address occlusion challenges in building façade parsing. Besides, we introduce our building façade dataset MeshFaçade from the Mesh data generated by drone imagery to study the occlusion problem of missing textures. The experimental results demonstrate that OccFaçade achieves state-of-the-art performance with mIOU of 85.01%, 84.09%, 72.95%, and 88.83% on the ENPC2014 dataset, ECP dataset, RueMonge2014 dataset, and our MeshFaçade dataset, respectively. The code and data are available at https://github.com/yueyisui/OccFacade.

A GWO-ML-based large deformation finite element variable mapping method: An example of RITSS large deformation finite element simulation

The mapping of variables between old and new elements is a crucial aspect of large deformation finite element simulation. However, traditional mapping methods suffer from limited applicability and complex operations. In this study, a novel Gray Wolf Optimization-Machine Learning (GWO-ML) based variable mapping method for large deformation finite element analysis is proposed. This method achieves accurate mapping results without requiring explicit determination of element-to-element positional relationships. Furthermore, it effectively integrates a wider range of integration point information during the mapping process and maintains high prediction accuracy near boundaries with sparse mesh data. The remeshing and interpolation technique by small strain is employed as an illustrative example, wherein a set of automated operations is proposed to control the commercial software ABAQUS through Python scripting for conducting small strain analysis and GWO-ML mapping process. For machine learning models, Multilayer Perceptrons, Random Forest, Extreme Learning Machine, and Support Vector Regression, are compared, where the RF model has excellent computational accuracy and efficiency in terms of performance. The application of this method is investigated in scenarios with various foundation types, motion modes, loading modes, and multi-physics coupling mappings. The results confirm that the method exhibits high accuracy and robustness in simulation processes.

Optimal Design of an Interior Permanent Magnet Synchronous Motor for Electric Vehicle Applications Using a Machine Learning-Based Surrogate Model

This paper presents an innovative design for an interior permanent magnet synchronous motor (IPMSM), targeting enhanced performance for electric vehicle (EV) applications. The proposed motor features a double V-shaped rotor structure with irregular ferrite magnets embedded in the slots between the permanent magnets. This design significantly enhances torque performance. Furthermore, a machine learning-based surrogate model is developed by integrating fine and coarse mesh data. Optimized using the Non-dominated Sorting Genetic Algorithm II (NSGA-II), this surrogate model effectively reduces computational time compared to traditional finite element analysis (FEA).

A method for assessing guide layout and error on implant accuracy

Functional and esthetic results require accurate implant placement. We aimed to develop a predictive method for assessing guide layout and error on implant accuracy. A mathematical model for position error analysis was constructed based on triangular mesh data. This model examines the relationship between the spatial shifts of multiple surfaces and the spatial shifts of specific points. It involves encasing these surfaces in a cuboid bounding box and expressing them in a local coordinate system. The influence of positioning surface error and layout of surgical guide were researched with a simulation test. The result shows that error in the implant site position is directly related to the error in the guide locating surface under the same layout. When the guide locating surface layout varies, as the length, width, and height of the minimum cuboid envelope increase, the maximum deviation in the implant site position decreases.

A Prediction‐Traversal Approach for Compressing Scientific Data on Unstructured Meshes with Bounded Error

AbstractWe explore an error‐bounded lossy compression approach for reducing scientific data associated with 2D/3D unstructured meshes. While existing lossy compressors offer a high compression ratio with bounded error for regular grid data, methodologies tailored for unstructured mesh data are lacking; for example, one can compress nodal data as 1D arrays, neglecting the spatial coherency of the mesh nodes. Inspired by the SZ compressor, which predicts and quantizes values in a multidimensional array, we dynamically reorganize nodal data into sequences. Each sequence starts with a seed cell; based on a predefined traversal order, the next cell is added to the sequence if the current cell can predict and quantize the nodal data in the next cell with the given error bound. As a result, one can efficiently compress the quantized nodal data in each sequence until all mesh nodes are traversed. This paper also introduces a suite of novel error metrics, namely continuous mean squared error (CMSE) and continuous peak signal‐to‐noise ratio (CPSNR), to assess compression results for unstructured mesh data. The continuous error metrics are defined by integrating the error function on all cells, providing objective statistics across nonuniformly distributed nodes/cells in the mesh. We evaluate our methods with several scientific simulations ranging from ocean‐climate models and computational fluid dynamics simulations with both traditional and continuous error metrics. We demonstrated superior compression ratios and quality than existing lossy compressors.

Employing Gamified Crowdsourced Close-Range Sensing in the Pursuit of a Digital Twin of the Earth

Advances in mobile consumer technology, especially in smartphones, have given rise to numerous new crowdsourcing opportunities. With the miniaturization of sensors and the growing number of smartphone models containing a wide range of them, we are now capable of creating digital imitations of real-world objects using everyday mobile devices. In this study, we created four augmented reality (AR) applications utilizing LiDAR sensors that were designed for crowdsourcing the creation of such digital imitations, i.e., digital twins. A user study was undertaken where video recordings, audio recordings, point cloud, and mesh data were collected in forest settings. Each approach was evaluated in terms of the characteristics and quality of the crowdsourced data acquired, as well as the participants’ behavior and experience. Our findings demonstrate that through gamification approaches, we can influence not only the user experience but also the type and quality of the crowdsourced data. Our findings offer guidance on which gamification dynamics and interactions are best suited for several types of crowdsourcing tasks. We also show that the collection of meaningful data is not limited to specific interactions or experiences and suggest that there are multiple routes in gamification design for reaching the desired outcomes.

A detection method for road network interchanges with the MeshCNN based on Delaunay triangulation

ABSTRACT Due to their unstructured characteristics, mature convolutional neural network (CNN) models often have difficulty performing spatial analysis with vector data. Current studies used graph neural network (GCN) models to address this problem. However, the definition of cognition factors involves uncertainties, making it challenging to accurately and comprehensively define these factors. In this paper, the road interchange detection task is taken as an example to introduce the MeshCNN, a deep learning model based on triangular mesh data, aiming to provide a new solution for spatial analysis of vector data. A triangular edge classification model is first trained with simple input features. Then, interchanges are detected based on the classification results with an adaptive method. Experiments were conducted on real-world road network data from four cities. The results reveal that the proposed method outperformed the existing methods with precision and recall rate of 89.36% and 79.25% for interchange detection on the total datasets. Furthermore, our proposed method can also detect interchanges in other regions more easily than the GCN method.

GeoSparseNet: A Multi-Source Geometry-Aware CNN for Urban Scene Analysis

The convolutional neural networks (CNNs) functioning on geometric learning for the urban large-scale 3D meshes are indispensable because of their substantial, complex, and deformed shape constitutions. To address this issue, we proposed a novel Geometry-Aware Multi-Source Sparse-Attention CNN (GeoSparseNet) for the urban large-scale triangular mesh classification task. GeoSparseNet leverages the non-uniformity of 3D meshes to depict both broad flat areas and finely detailed features by adopting the multi-scale convolutional kernels. By operating on the mesh edges to prepare for subsequent convolutions, our method exploits the inherent geodesic connections by utilizing the Large Kernel Attention (LKA) based Pooling and Unpooling layers to maintain the shape topology for accurate classification predictions. Learning which edges in a mesh face to collapse, GeoSparseNet establishes a task-oriented process where the network highlights and enhances crucial features while eliminating unnecessary ones. Compared to previous methods, our innovative approach outperforms them significantly by directly processing extensive 3D mesh data, resulting in more discerning feature maps. We achieved an accuracy rate of 87.5% when testing on an urban large-scale model dataset of the Australian city of Adelaide.

Coherent mesh representation for parallel I/O of unstructured polyhedral meshes

This paper presents a new mesh data layout for parallel I/O of linear unstructured polyhedral meshes. The new mesh representation infers coherence across entities of different topological dimensions, i.e., grid cells, faces, and points. The coherence due to cell-to-face and face-to-point connectivities of the mesh is formulated as a tree data structure distributed across processors. The mesh distribution across processors creates consecutive and contiguous slices that render an optimized data access pattern for parallel I/O. A file format using the coherent mesh representation, developed and tested with OpenFOAM, enables the usability of the software at unprecedented scales. Further implications of the coherent and sliceable mesh representation arise due to simplifications in partitioning and diminished pre- and post-processing overheads.

A trade-off between lives and the economy? Subsidizing dining out under the COVID-19 pandemic in Japan

We investigate how a government subsidy for dining out to support the restaurant industry has been associated with economic and health outcomes during the COVID-19 pandemic in Japan. Using nationwide 500-meter mesh data, we demonstrate that Japan’s Go To Eat scheme, which was gradually introduced across all prefectures beginning in October 2020, mitigated the negative impact of the pandemic on population mobility in restaurant areas, while having little association with the spread of COVID-19 afterward. The influence was particularly large for population mobility within a prefecture and in restaurant areas near train stations. The scheme also had diminishing positive spillover effects around the restaurant areas. The findings imply that such a subsidy can be a balanced policy response to the pandemic once epidemiological factors are properly managed.

Data and physics-driven modeling for fluid flow with a physics-informed graph convolutional neural network

A physics-informed graph convolutional network (PINN-GCN) data-driven model was proposed to solve steady-state fluid flows with various geometries. A GCN guarantees a data-driven model that adapts to irregularly structured or unstructured mesh data. In addition, the mean squared residuals of the governing equations in partial differential forms and boundary conditions are introduced into the loss function of the network model, the Physics-Informed Neural Network (PINN) increases the knowledge of the physical rules of the model, enhances the model accuracy even with sparse training data. With nine training cases containing approximately 2000 spatial point data individually, PINN-GCN could accurately predict the physical flow field over a two-dimensional object of variable size, achieving above 98.6% for mean accuracy. With five training data cases, the model could predict flow over a cylinder with variable position, achieving above 98.2% for mean accuracy. Moreover, the PINN-GCN framework can produce high-resolution predictions, even with low-resolution field training data. Furthermore, the PINN-GCN prediction speed was approximately 1000 times faster than that of the numerical simulations. Thus, the proposed model can rapidly predict high-resolution flow fields using a physics-informed, grid- and geometry-adaptive, data-driven model.

An adaptive anisotropic bilateral filtering method for mesh data in scale space

Three-dimensional mesh data of parts, such as blades and engine bodies, have been widely used in industrial fields. Due to the different kinds of noise during mesh acquisition and the machining deficiency of parts, the mesh quality tends to be insufficient for subsequent operations. Therefore, mesh denoising is a necessary and critical procedure to improve mesh quality. Existing methods commonly apply geometry features smoothing, which may also create unexpected results, such as volume shrinkage and blurring of sharp edges. This paper proposed an adaptive anisotropic bilateral filtering method for mesh data in scale space. Firstly, the mesh is decomposed into a smooth base with low frequency and a height vector field with high frequency based on scale space theory. The denoising of the vertex spatial field is transformed into the denoising of the height vector field, aiming to only consider high-frequency information. Secondly, the bilateral filter scheme with the anisotropic Gaussian kernel is proposed to denoise the height vector field, removing noise mixed with features. The parameters in the bilateral filter scheme are chosen adaptively by maximizing the designed probability density function. The mean square angular error of the proposed method is less than 0.15 rad, which is superior to the general-purpose algorithms, for instance, Laplacian filtering, bilateral mesh filtering and bilateral normal filtering algorithm.

CUS3D: A New Comprehensive Urban-Scale Semantic-Segmentation 3D Benchmark Dataset

With the continuous advancement of the construction of smart cities, the availability of large-scale and semantically enriched datasets is essential for enhancing the machine’s ability to understand urban scenes. Mesh data have a distinct advantage over point cloud data for large-scale scenes, as they can provide inherent geometric topology information and consume less memory space. However, existing publicly available large-scale scene mesh datasets are limited in scale and semantic richness and do not cover a wide range of urban semantic information. The development of 3D semantic segmentation algorithms depends on the availability of datasets. Moreover, existing large-scale 3D datasets lack various types of official annotation data, which hinders the widespread applicability of benchmark applications and may cause label errors during data conversion. To address these issues, we present a comprehensive urban-scale semantic segmentation benchmark dataset. It is suitable for various research pursuits on semantic segmentation methodologies. This dataset contains finely annotated point cloud and mesh data types for 3D, as well as high-resolution original 2D images with detailed 2D semantic annotations. It is constructed from a 3D reconstruction of 10,840 UVA aerial images and spans a vast area of approximately 2.85 square kilometers that covers both urban and rural scenes. The dataset is composed of 152,298,756 3D points and 289,404,088 triangles. Each 3D point, triangular mesh, and the original 2D image in the dataset are carefully labeled with one of the ten semantic categories. Six typical 3D semantic segmentation methods were compared on the CUS3D dataset, with KPConv demonstrating the highest overall performance. The mIoU is 59.72%, OA is 89.42%, and mAcc is 97.88%. Furthermore, the experimental results on the impact of color information on semantic segmentation suggest that incorporating both coordinate and color features can enhance the performance of semantic segmentation. The current limitations of the CUS3D dataset, particularly in class imbalance, will be the primary target for future dataset enhancements.

Estimation of possible locations for green roofs and bioswales and analysis of the effect of their implementation on stormwater runoff control

IntroductionThe objectives of this study are twofold. The first is to identify potential green infrastructure construction sites by building rooftops and sidewalks. The second is to analyze internal flooding for a wide range of drainage areas and to quantitatively evaluate the effectiveness of stormwater runoff control.MethodsThe target area has approximately 600 ha with a runoff coefficient of 0.71. Using Arc GIS Desktop 10.8.1, this study has identified green roofs and bioswales that would be highly beneficial in capturing large amounts of rainfall. In addition, Info Works ICM was used for the inundation analysis, which can simultaneously calculate the flow in sewer pipelines and above-ground inundation flow. Runoff coefficients were calculated for each land use using the urban land use subdivision mesh data with 100 m unit. This study targeted a 10-year probability rainfall (total rainfall: 86.3 mm, maximum hourly rainfall: 52.3 mm/h, duration: 3 h) with a middle concentrated rainfall waveform obtained from past experiments in the d4PDF database of ensemble climate prediction contributing to global warming.ResultsThe amount of land availability for green roofs and bioswales was about 1 and 0.1% of the drainage area, respectively. The runoff coefficients for green roofs only, bioswales only, with and without introduction of both green roofs and bioswales were 70.34, 70.87, 70.28, and 70.93%, respectively. The difference in runoff coefficients was about 0.65 percentage points even when both were constructed. As a result of inundation analysis, the reduction was 2.5% for the maximum waterlogged area, 1.5% for the flooded area, and 0.7% for the average depth of waterlogging divided by the maximum waterlogged area. The construction of green roofs and bioswales in the same area or downstream of the area shows little mitigation effect when flooding occurs in an area near the downstream end of the sewer network.DiscussionAlthough this study has mainly discussed the stormwater runoff control aspect, the most important feature of green infrastructure is its multifunctionality. In terms of utilizing and promoting green infrastructure, it is important to visualize its multifaceted effects and share them with many stakeholders.

MeshCL: Towards robust 3D mesh analysis via contrastive learning

Recent years have witnessed the success of deep learning in 3D mesh analysis, including classification and segmentation. Previous works mainly rely on supervised learning, which trains models on the labeled 3D mesh data with the cross-entropy loss. However, in the supervised training, the very limited amount of 3D mesh data restricts the feature’s discriminative power and the model’s robustness. To address or at least alleviate this issue, we propose to regularize the learned representations by associating the data points in feature space via contrastive learning. To achieve this, we first explore mesh samples with diverse geometric structures, and then apply contrastive regularization into the positive and negative pairs sampled from the feature space. In this way, our method, MeshCL, can learn robust feature representations invariant to the geometric deformation for 3D manifold mesh. In detail, to augment the geometric diversity, we examine different data augmentation techniques for mesh data. Furthermore, considering the geometric characteristics of 3D mesh, we develop more efficient positive/negative pair sampling strategies for the dense prediction task. To verify the effectiveness of MeshCL, we study two typical mesh analysis tasks, classification and segmentation. Experimental results demonstrate that MeshCL not only achieves state-of-the-art performance on the two tasks mentioned above but also significantly improves the model’s robustness.

SpATr: MoCap 3D human action recognition based on spiral auto-encoder and transformer network

Recent technological advancements have significantly expanded the potential of human action recognition through harnessing the power of 3D data. This data provides a richer understanding of actions, including depth information that enables more accurate analysis of spatial and temporal characteristics. In this context, We study the challenge of 3D human action recognition. Unlike prior methods, that rely on sampling 2D depth images, skeleton points, or point clouds, often leading to substantial memory requirements and the ability to handle only short sequences, we introduce a novel approach for 3D human action recognition, denoted as SpATr (Spiral Auto-encoder and Transformer Network), specifically designed for fixed-topology mesh sequences. The SpATr model disentangles space and time in the mesh sequences. A lightweight auto-encoder, based on spiral convolutions, is employed to extract spatial geometrical features from each 3D mesh. These convolutions are lightweight and specifically designed for fix-topology mesh data. Subsequently, a temporal transformer, based on self-attention, captures the temporal context within the feature sequence. The self-attention mechanism enables long-range dependencies capturing and parallel processing, enabling scalability for long sequences. The proposed method is evaluated on three prominent 3D human action datasets: Babel, MoVi, and BMLrub, from the Archive of Motion Capture As Surface Shapes (AMASS). Our results analysis demonstrates the competitive performance of our SpATr model in 3D human action recognition while maintaining efficient memory usage. The code and the training results are publicly available at https://github.com/h-bouzid/spatr.

Indoor Mapping with Entertainment Devices: Evaluating the Impact of Different Mapping Strategies for Microsoft HoloLens 2 and Apple iPhone 14 Pro.

Due to their low cost and portability, using entertainment devices for indoor mapping applications has become a hot research topic. However, the impact of user behavior on indoor mapping evaluation with entertainment devices is often overlooked in previous studies. This article aims to assess the indoor mapping performance of entertainment devices under different mapping strategies. We chose two entertainment devices, the HoloLens 2 and iPhone 14 Pro, for our evaluation work. Based on our previous mapping experience and user habits, we defined four simplified indoor mapping strategies: straight-forward mapping (SFM), left-right alternating mapping (LRAM), round-trip straight-forward mapping (RT-SFM), and round-trip left-right alternating mapping (RT-LRAM). First, we acquired triangle mesh data under each strategy with the HoloLens 2 and iPhone 14 Pro. Then, we compared the changes in data completeness and accuracy between the different devices and indoor mapping applications. Our findings show that compared to the iPhone 14 Pro, the triangle mesh accuracy acquired by the HoloLens 2 has more stable performance under different strategies. Notably, the triangle mesh data acquired by the HoloLens 2 under the RT-LRAM strategy can effectively compensate for missing wall and floor surfaces, mainly caused by furniture occlusion and the low frame rate of the depth-sensing camera. However, the iPhone 14 Pro is more efficient in terms of mapping completeness and can acquire a complete triangle mesh more quickly than the HoloLens 2. In summary, choosing an entertainment device for indoor mapping requires a combination of specific needs and scenes. If accuracy and stability are important, the HoloLens 2 is more suitable; if efficiency and completeness are important, the iPhone 14 Pro is better.