Mesh Segmentation Research Articles

MATCHING PERSISTENT SCATTERER CLUSTERS TO BUILDING ELEMENTS IN MESH REPRESENTATION

Abstract. The deformation time series of Persistent Scatterer points show a correlated behavior if they lay on the same rigid structure and therefore undergo the same deformation process. By clustering, such groups of Persistent Scatterer (PS) points can be identified. We use segmented mesh representations of single buildings, to find the optimal assignment of such clusters to parts of the structure. By applying a quality metric, the assignment is judged quantitatively. The proposed method is useful for the integration of PSInSAR into building information modeling (BIM) and aims at a cost-effective city-wide per-building monitoring.

SparseMeshCNN with Self-Attention for Segmentation of Large Meshes

In many clinical applications, 3D mesh models of human anatomies are important tools for visualization, diagnosis, and treatment planning. Such 3D mesh models often have a high number of vertices to capture the complex shape, and processing these large meshes on readily available graphic cards can be a challenging task. To accommodate this, we present a sparse version of MeshCNN called SparseMeshCNN, which can process meshes with more than 60 000 edges. We further show that adding non-local attention in the network can mitigate the small receptive field and improve the results. The developed methodology was applied to separate the Left Atrial Appendage (LAA) from the Left Atrium (LA) on 3D mesh models constructed from medical images, but the method is general and can be put to use in any application within mesh classification or segmentation where memory can be a concern.

THE RECOGNITION OF HERITAGE QUALITIES FROM FEATURE-BASED DIGITAL PROCEDURES IN THE ANALYSIS OF HISTORICAL URBAN CONTEXTS

Abstract. The documentation of historical architectural heritage in urban contexts involves the consideration of planning adaptations of settlements and landscape, related to the identification of formal and semantic qualities. In particular, the identification of cultural significance of Heritage building units can find correspondence in geometrical features that are documented within the urban asset. In this way, urban monitoring, in an increasingly automated way, can support the identification and characterization of semantic elements also regarding Heritage objects, observing the invariance and conservation of formal constants in urban dynamic assets.Considering the experimental case study of Solikamsk historical center, belonging to Upper Kama route (Russia), a multi-instrumental strategy of spatial survey is applied, evaluating data coverages and resolutions. This analysis defines a preliminary framework to develop further processes of 3D triangulation and reality-based meshing. The morpho-metric detail of final models constitutes the basis for the computing test of feature-based procedures, including regions recognition and mesh segmentation, which can be calibrated for shape qualities and scales, reaching a preliminary modeling classification of Heritage and urban building units.

Electromagnetic coupling modeling and accuracy verification of non-parallel cable structure

<sec>Owing to the random bundling of the cable bundle, the different conductors within the cable present non-parallel distribution structural features. Such a structural feature leads to different cross-sectional structures at different positions along the line. The variations of spacing between different conductors and the height from the ground can lead the distribution parameters to change. This requires that when solving the electromagnetic coupling of the cable bundle, the cable bundle should be divided into multiple grid segments along the line, and the distribution parameters should be calculated according to the cross-sectional geometry information at different grid segment positions.</sec><sec>On the basis of the integration of the transmission line model and the distributed parameter model, the distribution parameters of different mesh segments are calculated according to the cross-sectional structure of different mesh segments of the cable in this paper. When the parameters are brought into the transmission line model, an electromagnetic coupling model suitable for non-parallel cable structures is established. In order to verify the accuracy of the model, a unit cable structure from real cable with non-parallel distribution characteristics is designed. The calculation results from the proposed model are compared with the calculation results from the full-wave algorithm and the experimental results, showing they are in good agreement with each other.</sec><sec>In order to understand the influence of the cable non-parallel structure characteristics on the response of electromagnetic coupling to cable, the comparison of electromagnetic coupling response results between the parallel cable and non-parallel cable structures are made and analyzed, showing that the non-parallel structure characteristics of the cable have a significant effect on the electromagnetic coupling. It is confirmed that the influence of the non-parallel cable structure characteristics must be considered in the electromagnetic coupling simulation of the real cable.</sec>

A computational method for detecting aspect ratio and problematic features in additive manufacturing

In metal additive manufacturing, geometries with high aspect ratio (AR) features are often associated with defects caused by thermal stresses and other related build failures. Ideally, excessively high AR features would be detected and removed in the design phase to avoid unwanted failure during manufacture. However, AR is scale and orientation independent and identifying features across all scales and orientations is exceptionally challenging. Furthermore, not all high AR features are as easy to recognise as thin walls and fine needles. There is therefore a pressing need for further development in the field of problematic features detection for additive manufacturing processes. In this work, a dimensionless ratio (D1/D2) based on two distance metrics that are extracted from triangulated mesh geometries is proposed. Based on this method, geometries with different features (e.g. thin wall, helices and polyhedra) were generated and evaluated to produce metrics that are similar to AR. The prediction results are compared with known theoretical AR values of typical geometries.By combining this metric with mesh segmentation, this method was further extended to analyse the geometry with complex features. The proposed method provides a powerful, general and promising way to automatically detect high AR features and tackle the relevant defect issues prior to manufacture.

Dual-Sampling Attention Pooling for Graph Neural Networks on 3D Mesh

Mesh is an essential and effective data representation of a 3D shape. The 3D mesh segmentation is a fundamental task in computer vision and graphics. It has recently been realized through a multi-scale deep learning framework, whose sampling methods are of key significance. Rarely do the previous sampling methods consider the receptive field contour of vertex, leading to loss in scale consistency of the vertex feature. Meanwhile, uniform sampling can ensure the utmost uniformity of the vertex distribution of the sampled mesh. Consequently, to efficiently improve the scale consistency of vertex features, uniform sampling was first used in this study to construct a multi-scale mesh hierarchy. In order to address the issue on uniform sampling, namely, the smoothing effect, vertex clustering sampling was used because it can preserve the geometric structure, especially the edge information. With the merits of these two sampling methods combined, more and complete information on the 3D shape can be acquired. Moreover, we adopted the attention mechanism to better realize the cross-scale shape feature transfer. According to the attention mechanism, shape feature transfer between different scales can be realized by the construction of a novel graph structure. On this basis, we propose dual-sampling attention pooling for graph neural networks on 3D mesh. According to experiments on three datasets, the proposed methods are highly competitive.

The Segmentation of Road Scenes Based on Improved ESPNet Model

Image segmentation is an important research in image processing and machine vision in which automated driving can be seen the main application scene of image segmentation algorithms. Due to the many constraints of power supply and communication in in-vehicle systems, the vast majority of current image segmentation algorithms are implemented based on the deep learning model. Despite the ultrahigh segmentation accuracy, the problem of mesh artifacts and segmentation being too severe is obvious, and the high cost, computational, and power consumption devices required are difficult to apply in real-world scenarios. It is the focus of this paper to construct a road scene segmentation model with simple structure and no need of large computing power under the premise of certain accuracy. In this paper, the ESPNet (Efficient Spatial Pyramid of Dilated Convolutions for Semantic Segmentation) model is introduced in detail. On this basis, an improved ESPNet model is proposed based on ESPNet. Firstly, the network structure of the ESPNet model is optimized, and then, the model is optimized by using a small amount of weakly labeled and unlabeled scene sample data. Finally, the new model is applied to video image segmentation based on dash cam. It is verified on Cityscape, PASCAL VOC 2012, and other datasets that the algorithm proposed in this paper is faster, and the amount of parameters required is less than 1% of other algorithms, so it is suitable for mobile terminals.

A semi-automatic seed point-based method for separation of individual vertebrae in 3D surface meshes: a proof of principle study

PurposeThe purpose of this paper is to present and validate a new semi-automated 3D surface mesh segmentation approach that optimizes the laborious individual human vertebrae separation in the spinal virtual surgical planning workflow and make a direct accuracy and segmentation time comparison with current standard segmentation method.MethodsThe proposed semi-automatic method uses the 3D bone surface derived from CT image data for seed point-based 3D mesh partitioning. The accuracy of the proposed method was evaluated on a representative patient dataset. In addition, the influence of the number of used seed points was studied. The investigators analyzed whether there was a reduction in segmentation time when compared to manual segmentation. Surface-to-surface accuracy measurements were applied to assess the concordance with the manual segmentation.ResultsThe results demonstrated a statically significant reduction in segmentation time, while maintaining a high accuracy compared to the manual segmentation. A considerably smaller error was found when increasing the number of seed points. Anatomical regions that include articulating areas tend to show the highest errors, while the posterior laminar surface yielded an almost negligible error.ConclusionA novel seed point initiated surface based segmentation method for the laborious individual human vertebrae separation was presented. This proof-of-principle study demonstrated the accuracy of the proposed method on a clinical CT image dataset and its feasibility for spinal virtual surgical planning applications.

Automatic Spectral Method of Mesh Segmentation Based on Fiedler Residual

In this paper, we propose a fully automatic mesh segmentation method, which divides meshes into sub-meshes recursively through spectral analysis. A common problem in the spectral analysis of geometric processing is how to choose the specific eigenvectors and the number of these vectors for analysis and processing. This method tackles this problem with only one eigenvector, i.e. Fiedler vector. In addition, using only one eigenvector drastically reduces the cost of computing. Different from the Fiedler vector commonly used in the bipartition of graphs and meshes, this method finds multiple parts in only one iteration, vastly reducing the number of iterations and thus the time of operation, because each iteration produces as many correct boundaries as possible, instead of only one. We have tested this method on many 3D models, the results of which suggest the proposed method performs better than many advanced methods of recent years.

Multispectral aerial imagery-based 3D digitisation, segmentation and annotation of large scale urban areas of significant cultural value

• Urban areas 3D digitisation using multispectral aerial imagery • Experimental low-cost multispectral camera for drone development • Supervised machine learning methods for 3D mesh segmentation using multispectral data • Performance evaluation of the proposed methods on a large scale case study • Web-based visualisation and annotation tool for segmentation fine-tuning Disaster risk management of movable and immovable cultural heritage is a highly significant research topic. In this work, we present a pipeline for 3D digitisation, segmentation and annotation of large scale urban areas in order to produce data that can be exploited in disaster management simulators (e.g fire spreading, crowd movement, firefighting training, evacuation planning, etc.). We have selected the old town of Xanthi (Greece) as a challenging case study. We developed a custom multispectral camera to be carried by a commercial drone. Using the structure from motion / multiview stereo (SFM/MVS) approach, we produced a 3D model of the urban area covering 0.5 k m 2 that is followed by a multilayer texture map which carries information from visible and near-infrared regions of the electromagnetic spectrum. We developed a set of machine learning approaches based on logistic regression, support vector machines and artificial neural networks that allow 3D model segmentation by exploiting not only morphological and structural features but also the multispectral behaviour of different material surfaces. We objectively evaluate the performance of the proposed segmentation approaches on six significant material-based classes (cobbled-roads granite kilns, building walls, ceramic roof-tiles, low-vegetation, high-vegetation and metal surfaces) that are used in simulating fire propagation and crowd movement. The experiments revealed that the segmentation accuracy can be enhanced by taking into consideration surface material multispectral properties as well as morphological features. A Web-based multi-user annotation tool complements our proposed pipeline by enabling further 3D model segmentation, fine tuning and semantics annotation (e.g. usage-based building classification and evacuation priorities, escape paths and gathering points).

Soft body impact on composites: Delamination experiments and advanced numerical modelling

Cohesive interface elements have become commonly used for modelling composites delamination. However, a limitation of this technique is the fine mesh size required. Here, a novel cohesive element formulation is proposed and demonstrated for modelling the numerical cohesive zone with equal fidelity but fewer elements in comparison to a linear cohesive element formulation. The newly proposed formulation has additional degrees of freedom in the form of nodal rotations which when combined with the use of multiple integration points per cohesive element, allows for delamination propagation to be modelled with increased stability. This element formulation is introduced with an adaptive modelling method, termed Adaptive Mesh Segmentation (AMS). To demonstrate its effectiveness under impact loading the new model is applied to a soft body beam bending test. This test, containing a delamination pre-crack, uses inertial constraints and results in a dynamic stress state when impacted by a gelatin cylinder.

A Robust Segmentation Algorithmfor for 3D Complex Meshes

Segmenting 3D mesh is a difficult topic in computer graphics. This paper proposes a new mesh segmentation algorithm. First, we over-segment the input mesh to generate a series of superfacets. Second, we introduce a novel region fusion algorithm to obtain the segmentation result. Various experiments show that our algorithm is able to handle 3D meshes with complex shape and rich details. Even though the input mesh has noises or holes our algorithm can still achieve satisfactory results.

Automated Pipeline to Generate Anatomically Accurate Patient-Specific Biomechanical Models of Healthy and Pathological FSUs.

State-of-the-art preoperative biomechanical analysis for the planning of spinal surgery not only requires the generation of three-dimensional patient-specific models but also the accurate biomechanical representation of vertebral joints. The benefits offered by computational models suitable for such purposes are still outweighed by the time and effort required for their generation, thus compromising their applicability in a clinical environment. In this work, we aim to ease the integration of computerized methods into patient-specific planning of spinal surgery. We present the first pipeline combining deep learning and finite element methods that allows a completely automated model generation of functional spine units (FSUs) of the lumbar spine for patient-specific FE simulations (FEBio). The pipeline consists of three steps: (a) multiclass segmentation of cropped 3D CT images containing lumbar vertebrae using the DenseVNet network, (b) automatic landmark-based mesh fitting of statistical shape models onto 3D semantic segmented meshes of the vertebral models, and (c) automatic generation of patient-specific FE models of lumbar segments for the simulation of flexion-extension, lateral bending, and axial rotation movements. The automatic segmentation of FSUs was evaluated against the gold standard (manual segmentation) using 10-fold cross-validation. The obtained Dice coefficient was 93.7% on average, with a mean surface distance of 0.88 mm and a mean Hausdorff distance of 11.16 mm (N = 150). Automatic generation of finite element models to simulate the range of motion (ROM) was successfully performed for five healthy and five pathological FSUs. The results of the simulations were evaluated against the literature and showed comparable ROMs in both healthy and pathological cases, including the alteration of ROM typically observed in severely degenerated FSUs. The major intent of this work is to automate the creation of anatomically accurate patient-specific models by a single pipeline allowing functional modeling of spinal motion in healthy and pathological FSUs. Our approach reduces manual efforts to a minimum and the execution of the entire pipeline including simulations takes approximately 2 h. The automation, time-efficiency and robustness level of the pipeline represents a first step toward its clinical integration.

Modelling delaminations using adaptive cohesive segments with rotations in dynamic explicit analysis

Multiple delamination planes can form when a composite structure is subjected to out-of-plane stresses during static over-loading or impact loading. Numerical modelling of such events is often prohibitively expensive because large numbers of cracks can co-exist and interact, and fracture models usually affect the time step size in explicit solutions. Here a new method called Adaptive Mesh Segmentation is proposed, which introduces segmentation ‘on-the-fly’ in meshes of quadratic finite elements with six degrees of freedom per node, without any intervention from the user and without any reductions in time step size for solution stability. A novel cohesive formulation with rotational degrees of freedom is introduced which increases the resolution of the numerical cohesive zone and allows the use of relatively coarse meshes. Once a critical stress criterion is met, new degrees of freedom are added at element boundaries to model strong discontinuities. A new moment–damage relationship is proposed to link the discontinuity in rotational degrees of freedom with the cohesive zone law which is translational by definition. A method for initiating cohesive tractions and moments with minimal disturbances to the surrounding stress field is also presented. Finally, the model is applied in the analysis of composite delamination benchmarks using relatively coarse meshes and modest model sizes. Considerable improvements in accuracy are observed when compared to conventional methods.

Optimization design method for noise barrier tunnel junction on merging lanes using quad meshes

ABSTRACT Noise barrier tunnels (NBTs) are road facilities installed to reduce road traffic noise. Although building information modeling (BIM) has been widely used in civil engineering, alignment problems must first be addressed for BIM to be applied in transportation infrastructure; this is because unlike buildings, roads are linear. The array of tunnel frames based on the centerlines of individual roads cause the discontinuity of components at junctions of two NBTs. This leads to structural instabilities and poor airtightness, which in turn cause vulnerabilities such as noise and water leakage. To address these issues, this study proposes an optimization design method for NBT junctions using quad meshes. We created a Y-branch topology of NBTs using quad meshes, performed data arrangement using mesh segmentation and mesh reorder, and used the results to optimize the design via performance analysis. During mesh segmentation and mesh reorder, an interface in which the user directly enters curves to improve the efficiency of the algorithm was also developed. In addition, a case study of a main road with eight lanes that merged with a sub road with one lane was conducted, data arrangement was performed successfully, and a BIM-compliant model that used various geometric data was generated through optimization.

Selecting and designing grippers for an assembly task in a structured approach

ABSTRACT In this paper, we present a structured approach to selecting and designing a set of grippers for an assembly task. Compared to current experience-based gripper design method, our approach accelerates the design process by automatically generating a set of initial design options for gripper types and parameters according to the CAD models of assembly components. We use mesh segmentation techniques to segment the assembly components and fit the segmented parts with shape primitives, according to the predefined correspondence between shape primitive and gripper type, suitable gripper types and parameters can be selected and extracted from the fitted shape primitives. Moreover, we incorporate the assembly constraints in the further evaluation of the initially obtained gripper types and parameters. Considering the affordance of the segmented parts and the collision avoidance between the gripper and the subassemblies, applicable gripper types and parameters can be filtered from the initial options. Among the applicable gripper configurations, we further optimize the number of grippers for performing the assembly task, by exploring the gripper that is able to handle multiple assembly components during the assembly. Finally, the feasibility of the designed grippers is experimentally verified by assembling a part of an industrial product.

3D Mesh Segmentation Based on Energy Optimization

3D Mesh Segmentation Based on Energy Optimization

An Efficient Data Retrieval Parallel Reeb Graph Algorithm

The Reeb graph of a scalar function that is defined on a domain gives a topologically meaningful summary of that domain. Reeb graphs have been shown in the past decade to be of great importance in geometric processing, image processing, computer graphics, and computational topology. The demand for analyzing large data sets has increased in the last decade. Hence, the parallelization of topological computations needs to be more fully considered. We propose a parallel augmented Reeb graph algorithm on triangulated meshes with and without a boundary. That is, in addition to our parallel algorithm for computing a Reeb graph, we describe a method for extracting the original manifold data from the Reeb graph structure. We demonstrate the running time of our algorithm on standard datasets. As an application, we show how our algorithm can be utilized in mesh segmentation algorithms.

Planning Grasps With Suction Cups and Parallel Grippers Using Superimposed Segmentation of Object Meshes

This article develops model-based grasp planning algorithms. It focuses on industrial end-effectors like grippers and suction cups, and plans grasp configurations considering computer aided design (CAD) models of target objects. The developed algorithms can stably find many high-quality grasps, with satisfying precision and little dependency on the quality of CAD models. The undergoing core technique is superimposed segmentation, which preprocesses a mesh model by peeling it into superimposed facets. The algorithms use the facets to locate contacts and synthesize grasp poses for popular industrial end-effectors. Several tunable parameters are prepared to adapt the algorithms to meet various requirements. The experimental section studies the influence of the tunable parameters and analyzes the cost, precision, and robustness of the proposed algorithms and their planned grasps, with both simulations and real-world systems. Besides, the proposed algorithms are applicable to mesh models reconstructed from point clouds obtained by depth sensors. Some experiments and analysis are also carried out to study and demonstrate the ability.

An improved 3D shape visibility graph with application to mesh segmentation

While most existing 3D shape representation features exploit either surface or volumetric information to describe the mesh, in this paper we propose a method that efficiently combines this dual information. Using both representations, convex as well as concave regions are captured, a property which is necessary for effective shape segmentation. The method extends the well-known volumetric visibility descriptor to a novel geodesic variant that can represent the surface and thus provides complementary information. Specifically, for a pair of mesh nodes, this novel surface representation is constructed by computing the joint visibility among all nodes of the geodesic path connecting them and are at a certain absolute distance each other. By considering different such distances, multiple joint visibility values are computed, organized in a sequence. Although the proposed mesh descriptor can be used in many different ways, in this work two elements of the produced visibility sequence are used. All the above information is appropriately organized in a graph that enhances the connectedness between mesh points and reflects the geometric properties of the mesh, a fact which is supported by the provided experimental results on 3D mesh segmentation.