Proceedings of the 30th International Conference on Computer Graphics and Machine Vision (GraphiCon 2020). Part 2最新文献_第6页

Methodological Foundations for Teaching Computer Graphics for Students in IT Areas 信息技术领域学生计算机图形学教学的方法论基础

Proceedings of the 30th International Conference on Computer Graphics and Machine Vision (GraphiCon 2020). Part 2 Pub Date : 2020-12-17 DOI: 10.51130/graphicon-2020-2-4-28

V. Karabchevsky

引用次数: 1

DL-inferencing for 3D Cephalometric Landmarks Regression task using OpenVINO 基于OpenVINO的三维头颅测量标志回归任务的dl推理

Proceedings of the 30th International Conference on Computer Graphics and Machine Vision (GraphiCon 2020). Part 2 Pub Date : 2020-12-17 DOI: 10.51130/graphicon-2020-2-3-35

E. Vasiliev, D. Lachinov, A. Getmanskaya

{"title":"DL-inferencing for 3D Cephalometric Landmarks Regression task using OpenVINO","authors":"E. Vasiliev, D. Lachinov, A. Getmanskaya","doi":"10.51130/graphicon-2020-2-3-35","DOIUrl":"https://doi.org/10.51130/graphicon-2020-2-3-35","url":null,"abstract":"In this paper, we evaluate the performance of the Intel Distribution of OpenVINO toolkit in practical solving of the problem of automatic three-dimensional Cephalometric analysis using deep learning methods. This year, the authors proposed an approach to the detection of cephalometric landmarks from CT-tomography data, which is resistant to skull deformities and use convolutional neural networks (CNN). Resistance to deformations is due to the initial detection of 4 points that are basic for the parameterization of the skull shape. The approach was explored on CNN for three architectures. A record regression accuracy in comparison with analogs was obtained. This paper evaluates the perfor- mance of decision making for the trained CNN-models at the inference stage. For a comparative study, the computing environments PyTorch and Intel Distribution of OpenVINO were selected, and 2 of 3 CNN architectures: based on VGG for regression of cephalometric landmarks and an Hourglass-based model, with the RexNext backbone for the land- marks heatmap regression. The experimental dataset was consist of 20 CT of patients with acquired craniomaxillofacial deformities and was in- clude pre- and post-operative CT scans whose format is 800x800x496 with voxel spacing of 0.2x0.2x0.2 mm. Using OpenVINO showed a great increase in performance over the PyTorch, with inference speedup from 13 to 16 times for a Direct Regression model and from 3.5 to 3.8 times for a more complex and precise Hourglass model.","PeriodicalId":344054,"journal":{"name":"Proceedings of the 30th International Conference on Computer Graphics and Machine Vision (GraphiCon 2020). Part 2","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127409313","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Virtual and Augmented Reality Technologies in Training Architecture and Civil Engineering Specialists 虚拟和增强现实技术在培训建筑和土木工程专家

Proceedings of the 30th International Conference on Computer Graphics and Machine Vision (GraphiCon 2020). Part 2 Pub Date : 2020-12-17 DOI: 10.51130/graphicon-2020-2-4-29

Iu.N. Zgoda, A. Semenov

引用次数: 1

Geometric Modeling of Stress Visualization Based on the Functional-Voxel Method 基于功能体素的应力可视化几何建模

Proceedings of the 30th International Conference on Computer Graphics and Machine Vision (GraphiCon 2020). Part 2 Pub Date : 2020-12-17 DOI: 10.51130/graphicon-2020-2-3-54

S. Pushkarev, A. Tolok

{"title":"Geometric Modeling of Stress Visualization Based on the Functional-Voxel Method","authors":"S. Pushkarev, A. Tolok","doi":"10.51130/graphicon-2020-2-3-54","DOIUrl":"https://doi.org/10.51130/graphicon-2020-2-3-54","url":null,"abstract":"The visualization of the parameters of the stress state of a solid remains one of the parameters influencing the adoption of engineering decisions. For example, methods for determining finite elements (FEM), which make it possible to determine and visualize stress in the selected regions of the model. Applying element methods to analytically constructed models to localize the search for stress to its values at a point, however, will not lead to successful results. The paper discusses the principles of visualization of local stresses based on the functional-voxel method. The concept of a volume vector as a unit of volume distribution of a force vector in a solid isotropic medium is introduced. Geometrical foundations are proposed for computer representation of the stress unit in an isomorphic body based on a raster image. Geometric models of the stress tensor are constructed for the main site, the inclined platform. The principles of applying the functional-voxel model in the tasks of constructing complex objects are proposed. The application of the functional voxel method for discrete modeling of the deformation of a geometric object is illustrated by the example of a function that describes a rectangular plate.","PeriodicalId":344054,"journal":{"name":"Proceedings of the 30th International Conference on Computer Graphics and Machine Vision (GraphiCon 2020). Part 2","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117183917","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Simulation of Quadcopter's Complex Spatial Motion in Virtual Environment Systems 虚拟环境系统中四轴飞行器复杂空间运动的仿真

Proceedings of the 30th International Conference on Computer Graphics and Machine Vision (GraphiCon 2020). Part 2 Pub Date : 2020-12-17 DOI: 10.51130/graphicon-2020-2-4-4

E. Strashnov, M. Mikhaylyuk

引用次数: 0

Development of a Neural Network for the Synthesis of Freeform Optical Elements with a Flat Wavefront 平面波前自由曲面光学元件合成的神经网络研究

Proceedings of the 30th International Conference on Computer Graphics and Machine Vision (GraphiCon 2020). Part 2 Pub Date : 2020-12-17 DOI: 10.51130/graphicon-2020-2-4-45

I. Mazur, A. Voznesenskaya, A. Trifanov, M. Svintsov

引用次数: 0

Spherical Visualization Database Prototype for Education and Scientific Research: Designing and Managing 面向教育科研的球形可视化数据库原型:设计与管理

Proceedings of the 30th International Conference on Computer Graphics and Machine Vision (GraphiCon 2020). Part 2 Pub Date : 2020-12-17 DOI: 10.51130/graphicon-2020-2-3-12

S. Presnyakov, Grigory Boyarshinov, A. Odintsova, A. Rybkina

{"title":"Spherical Visualization Database Prototype for Education and Scientific Research: Designing and Managing","authors":"S. Presnyakov, Grigory Boyarshinov, A. Odintsova, A. Rybkina","doi":"10.51130/graphicon-2020-2-3-12","DOIUrl":"https://doi.org/10.51130/graphicon-2020-2-3-12","url":null,"abstract":"The article describes methods for spherical visualizing of data as global geophysical, environmental, atmospheric processes on the surface of planets and different kinds of processes on the surface of spherical bodies. Such data can be demonstrated through virtual globes and spherical screens. Volumetric visualization significantly increases the degree of visibility, comprehension and assimilation of the demonstrated content and may be used in the scientific and educational process. The main goal of this research is to develop database requirements for spherical visualization. The requirements are based on the modern educational and science research representation approaches. The following tasks have been formed and accomplished: a strict classification of data; a convenient way to interact at the stage of adding data to the database and analyzing; their representativeness; introduction of additional data classifications; the possibility of individual user navigation and a high degree of inter-activity. For the proposed model, the basic functions of the database management system are described. Requirements to a basic hierarchical data model were substantiated. The main object of hierarchical data model is a spherical Slide representing a separate topic of particular discipline. The superstructure is used above the hierarchical model in the form of an individual route map representing a directory with links to the main database.","PeriodicalId":344054,"journal":{"name":"Proceedings of the 30th International Conference on Computer Graphics and Machine Vision (GraphiCon 2020). Part 2","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130632495","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

Description Models, Methods, Algorithms, and Technology for Processing Poorly tructured Raster Graphic Documents 描述模型、方法、算法和处理结构不良的光栅图形文档的技术

Proceedings of the 30th International Conference on Computer Graphics and Machine Vision (GraphiCon 2020). Part 2 Pub Date : 2020-12-17 DOI: 10.51130/graphicon-2020-2-3-61

D. Vasin

引用次数: 1

Application Map in the Noise Suppression Filter for Video Compression 噪声抑制滤波器在视频压缩中的应用

Proceedings of the 30th International Conference on Computer Graphics and Machine Vision (GraphiCon 2020). Part 2 Pub Date : 2020-12-17 DOI: 10.51130/graphicon-2020-2-3-76

R. Chernyak, R. Meshcheryakov

引用次数: 0

Surface Modeling in the Course of Engineering Graphics 工程图学课程中的曲面建模

Proceedings of the 30th International Conference on Computer Graphics and Machine Vision (GraphiCon 2020). Part 2 Pub Date : 2020-12-17 DOI: 10.51130/graphicon-2020-2-3-55

T. Markova, A. Bochkov, M. Kokorin, T. Nikitina

引用次数: 0