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

筛选
英文 中文
Detecting Errors in Cognitive Models Using Visualization Metaphors of Fuzzy Cognitive Maps 利用模糊认知地图的可视化隐喻检测认知模型中的错误
R. Isaev, A. Podvesovskii
{"title":"Detecting Errors in Cognitive Models Using Visualization Metaphors of Fuzzy Cognitive Maps","authors":"R. Isaev, A. Podvesovskii","doi":"10.51130/graphicon-2020-2-4-13","DOIUrl":"https://doi.org/10.51130/graphicon-2020-2-4-13","url":null,"abstract":"Verification of cognitive models is one of the most important stages in their construction, since reliability of results of subsequent modeling largely depends on the successful implementation of verification. The paper considers the problem of verifying cause-and-effect relationships in cognitive models based on the use of fuzzy cognitive maps. It is noted that increasing the effectiveness of cognitive model verification is possible by activating analyst's cognitive potential. The most natural way of such activation is to increase cognitive clarity of the model through the use of visualization capabilities. For this purpose, a number of metaphors for visualizing fuzzy cognitive maps have been proposed, aimed at increasing their cognitive clarity during verification. Each of the metaphors is focused on the visualization of a certain type of fragments of a fuzzy cognitive map potentially containing errors, redundancy or incompleteness and therefore of interest from the point of view of verification. The first considered visualization metaphor is intended to display the cycles that are part of a cognitive graph. The second metaphor focuses on the mapping of transitive paths between concepts. Finally, the third metaphor is aimed at eliminating cognitive model incompleteness, which consists in the lack of relationships between some concepts. Examples are given of applying the proposed visualization metaphors to increase cognitive clarity of the visual image of the verified fuzzy cognitive map.","PeriodicalId":344054,"journal":{"name":"Proceedings of the 30th International Conference on Computer Graphics and Machine Vision (GraphiCon 2020). Part 2","volume":"78 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":"131150294","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
Dataset Expansion by Generative Adversarial Networks for Detectors Quality Improvement 基于生成对抗网络的数据集扩展检测器质量改进
A. Kostin, V. Gorbachev
{"title":"Dataset Expansion by Generative Adversarial Networks for Detectors Quality Improvement","authors":"A. Kostin, V. Gorbachev","doi":"10.51130/graphicon-2020-2-3-29","DOIUrl":"https://doi.org/10.51130/graphicon-2020-2-3-29","url":null,"abstract":"Modern neural network algorithms for object detection tasks require a large la-belled dataset for training. In a number of practical applications creation and an-notation of large data, collections requires considerable resources which are not always available. One of the solutions to this problem is creation of artificial images containing the object of interest. In this work the use of generative adversarial networks (GAN) for generation of images of target objects is proposed. It is demonstrated experimentally that GAN’s allows to create new images on the basis of the initial collection of real images on background images (not containing objects), which simulate real images accurately enough. Due to this, it is possible to create a new training collection containing a greater variety of training examples, which allows to achieve higher precision for detection algorithm. In our setting, GAN training does not require more data than is required for direct detector training. The proposed method has been tested to teach a network for detecting unmanned aerial vehicles (UAVs).","PeriodicalId":344054,"journal":{"name":"Proceedings of the 30th International Conference on Computer Graphics and Machine Vision (GraphiCon 2020). Part 2","volume":"10 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":"133183493","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
The Application of the Model of High-Speed Pixel Clustering in Problems of Preprocessing of the Images of the Remote Sensing of the Earth 高速像元聚类模型在地球遥感图像预处理问题中的应用
I. Khanykov
{"title":"The Application of the Model of High-Speed Pixel Clustering in Problems of Preprocessing of the Images of the Remote Sensing of the Earth","authors":"I. Khanykov","doi":"10.51130/graphicon-2020-2-3-41","DOIUrl":"https://doi.org/10.51130/graphicon-2020-2-3-41","url":null,"abstract":"The purpose of the research is to use the modified Ward’s method in high-speed processing of full-HD images of the remote sensing of the Earth. The classical Ward’s method is modified by dividing the computational process into three successive stages. The first stage quickly builds a coarse hierarchy of approximations. The second stage performs a quality improvement of the specified partition for a fixed number of colors (clusters). The third stage is the clustering of the superpixels using the Ward’s method. The software-algorithmic toolkit consists of four operations on clusters of pixels and image segments: merge operation joins together two clusters; divide operation reversibly disjoins the selected cluster into two; split operation extracts the part of the cluster into individual cluster; correct operation reclassifies pixels by extracting from one cluster and inserting into another cluster. The quality is assessed by the total squared error. The quality improvement is provided by iterative execution of a combination of merge and divide operations of pixel clusters, in particular image segments. One of the clusters (segments) is divided in two and a pair of other mismatched with it is combined into one according to the criterion of the minimum increment of the total squared error. The proposed modified Ward’s method is appropriate in processing of fullHD images of the remote sensing of the Earth. The results of processing in pure segmentation and clustering modes are compared. The proposed pixel clustering model is appropriate in high-speed processing of the fullHD images. The pixel clustering in comparison with image segmentation allows to define in more detail both the contours of objects of interest and their internal structure","PeriodicalId":344054,"journal":{"name":"Proceedings of the 30th International Conference on Computer Graphics and Machine Vision (GraphiCon 2020). Part 2","volume":"318 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":"132088083","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
Modeling ArUco Markers Images for Accuracy Analysis of Their 3D Pose Estimation ArUco标记图像建模及其三维姿态估计的准确性分析
A. Poroykov, P. Kalugin, S. Shitov, I. Lapitskaya
{"title":"Modeling ArUco Markers Images for Accuracy Analysis of Their 3D Pose Estimation","authors":"A. Poroykov, P. Kalugin, S. Shitov, I. Lapitskaya","doi":"10.51130/graphicon-2020-2-4-14","DOIUrl":"https://doi.org/10.51130/graphicon-2020-2-4-14","url":null,"abstract":"Fiducial markers are used in vision systems to determine the position of objects in space, reconstruct movement and create augmented reality. Despite the abundance of work on analysis of the accuracy of the estimation of the fiducial markers spatial position, this question remains open. In this paper, we propose the computer modeling of images with ArUco markers for this purpose. The paper presents a modeling algorithm, which was implemented in the form of software based on the OpenCV library. Algorithm is based on projection of three-dimensional points of the marker corners into two-dimensional points using the camera parameters and rendering the marker image in the new two-dimensional coordinates on the modeled image with the use of the perspective transformation obtained from these points. A number of dependencies were obtained by which it is possible to evaluate the error in determining the position depending on markers size. Including the probability of detecting a marker depending on its area on an image.","PeriodicalId":344054,"journal":{"name":"Proceedings of the 30th International Conference on Computer Graphics and Machine Vision (GraphiCon 2020). Part 2","volume":"73 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":"127617021","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: 7
The Variational Iterations Method for the Three-dimensional Equations Analysis of Mathematical Physics and the Solution Visualization with its Help 数学物理三维方程分析的变分迭代法及其解的可视化
A. Tebyakin, I. Papkova, V. Krysko
{"title":"The Variational Iterations Method for the Three-dimensional Equations Analysis of Mathematical Physics and the Solution Visualization with its Help","authors":"A. Tebyakin, I. Papkova, V. Krysko","doi":"10.51130/graphicon-2020-2-4-9","DOIUrl":"https://doi.org/10.51130/graphicon-2020-2-4-9","url":null,"abstract":"The aim of the work is to use the variational iterations method to study the three-dimensional equations of mathematical physics and visualize the solutions obtained on its basis and the 3DsMAX software package. An analytical solution of the three-dimensional Poisson equations is obtained for the first time. The method is based on the Fourier idea of variables separation with the subsequent application of the Bubnov-Galerkin method for reducing partial differential equations to ordinary differential equations, which in the Western scientific literature has become known as the generalized Kantorovich method, and in the Eastern European literature has known as the variational iterations method. This solution is compared with the numerical solution of the three-dimensional Poisson equation by the finite differences method of the second accuracy order and the finite element method for two finite element types: tetrahedra and cubic elements, which is a generalized Kantorovich method, based on the solution of the three-dimensional stationary differential heat equation. As the method study, a set of numerical methods was used. For the results reliability, the convergence of the solutions by the partition step is checked. The results comparison with a change in the geometric parameters of the heat equation is made and a conclusion is drawn on the solutions reliability obtained. Solutions visualization using the 3Ds max program is also implemented.","PeriodicalId":344054,"journal":{"name":"Proceedings of the 30th International Conference on Computer Graphics and Machine Vision (GraphiCon 2020). Part 2","volume":"4 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":"121231605","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
Comparison of Two Approaches to Calculate Orthoscopic Interference Pictures 两种计算正交干涉图方法的比较
V. Debelov, R. Shelepaev
{"title":"Comparison of Two Approaches to Calculate Orthoscopic Interference Pictures","authors":"V. Debelov, R. Shelepaev","doi":"10.51130/graphicon-2020-2-4-44","DOIUrl":"https://doi.org/10.51130/graphicon-2020-2-4-44","url":null,"abstract":"In this article a computer model of the polariscope is regarded as a 3D scene. In this case, the interference pictures are the result of rendering. The light rays pass through several well-specified polariscope blocks. When developing a suitable renderer, algorithms are selected and estimated for calculating the behavior of the beams based on their physical correctness, speed, etc. A plane parallel plate of an anisotropic crystal is the main block of the scene that affects the resulting image. This article discusses the calculation of the interaction of light with this plate only. Two approaches to calculate orthoscopic interference pictures of optically anisotropic transparent crystals are considered. One is described in many well-known books and bases on definite simplifications. The other is a direct physically based modeling of a light ray path through a plane parallel plate made of a uniaxial crystal taking into account all losses of intensity while passing boundaries between media. The purpose of this paper is to estimate a difference between values obtained via different approaches","PeriodicalId":344054,"journal":{"name":"Proceedings of the 30th International Conference on Computer Graphics and Machine Vision (GraphiCon 2020). Part 2","volume":"109 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":"126673486","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
Training Beginners and Experienced Drivers using mobile-based Virtual and Augmented Reality 培训初学者和有经验的司机使用基于移动的虚拟和增强现实
T. Tomchinskaya, M. Shaposhnikova, N. Dudakov
{"title":"Training Beginners and Experienced Drivers using mobile-based Virtual and Augmented Reality","authors":"T. Tomchinskaya, M. Shaposhnikova, N. Dudakov","doi":"10.51130/graphicon-2020-2-3-69","DOIUrl":"https://doi.org/10.51130/graphicon-2020-2-3-69","url":null,"abstract":"A developed by authors application for real-time visualization of augmented and virtual reality is considered, which enables to simulate the traffic accidents on a mobile platform with the Android operating system. The application is developed on the basis of the Unity 3D and is able to visualize various types of road accidents and also link them to a terrain, different conditions of the urban environment, and map of the accident statistics. The system has an archive of videos for the accident 3D-scenes. The application interface and implementation features are considered. The subsystems of virtual and augmented reality are described in detail with examples. This application may be used to train novice drivers, learn the rules of the road, and inform experienced drivers about new road junctions. In the system environment, the distribution of the number of traffic violations depending on the driving experience for three groups (no experience, less than 3 years, more than 3 years) was investigated. The study of the usefulness of the system on the Likert scale on 80 cadets of driving schools is presented.","PeriodicalId":344054,"journal":{"name":"Proceedings of the 30th International Conference on Computer Graphics and Machine Vision (GraphiCon 2020). Part 2","volume":"85 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":"127253335","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: 4
Data Balancing Method for Training Segmentation Neural Networks 训练分割神经网络的数据平衡方法
Alexey Kochkarev, A. Khvostikov, Dmitry Korshunov, A. Krylov, M. Boguslavskiy
{"title":"Data Balancing Method for Training Segmentation Neural Networks","authors":"Alexey Kochkarev, A. Khvostikov, Dmitry Korshunov, A. Krylov, M. Boguslavskiy","doi":"10.51130/graphicon-2020-2-4-19","DOIUrl":"https://doi.org/10.51130/graphicon-2020-2-4-19","url":null,"abstract":"Data imbalance is a common problem in machine learning and image processing. The lack of training data for the rarest classes can lead to worse learning ability and negatively affect the quality of segmentation. In this paper, we focus on the problem of data balancing for the task of image segmentation. We review major trends in handling unbalanced data and propose a new method for data balancing, based on Distance Transform. This method is designed for using in segmentation convolutional neural networks (CNNs), but it is universal and can be used with any patch-based segmentation machine learning model. The evaluation of the proposed data balancing method is performed on two datasets. The first is medical dataset LiTS, containing CT images of liver with tumor abnormalities. The second one is a geological dataset, containing of photographs of polished sections of different ores. The proposed algorithm enhances the data balance between classes and improves the overall performance of CNN model.","PeriodicalId":344054,"journal":{"name":"Proceedings of the 30th International Conference on Computer Graphics and Machine Vision (GraphiCon 2020). Part 2","volume":"68 2 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":"124101954","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: 3
Psychovisual Perception Scale Based on a Neural Network 基于神经网络的心理视觉感知量表
V. Budak, Ekaterina Ilyina
{"title":"Psychovisual Perception Scale Based on a Neural Network","authors":"V. Budak, Ekaterina Ilyina","doi":"10.51130/graphicon-2020-2-3-65","DOIUrl":"https://doi.org/10.51130/graphicon-2020-2-3-65","url":null,"abstract":"The purpose of this article is to construct a psychophysical scale of visual perception from lighting scene based on a direct propagation neural network using for assessment of real or synthesized images with spatial brightness distribution. Visual perception assessments of different scenes were obtained for 10 observers at the experimental installation of the Department of lighting engineering of the MPEI (NRU). These results were checked and found out agreed with the numerical scale of visual perception proposed by Lekish and Holladay. Neural network was trained to predict a sensation at the level of 40-70%, depending on the scale category. For more careful prediction level in each of 5 categories of scale a new experiment should be done with new calibration and with tested instructions and with more observers involved. The novelty consists in using a neural network as an expert to assess the degree of comfort of the lighting scene.","PeriodicalId":344054,"journal":{"name":"Proceedings of the 30th International Conference on Computer Graphics and Machine Vision (GraphiCon 2020). Part 2","volume":"231 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":"122702969","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
Analysis of the Influence of Vegetation Index Choice on the Classification of Satellite Images for Monitoring Forest Pathology 植被指数选择对森林病理监测卫星影像分类的影响分析
E. Trubakov, Olga Trubakova
{"title":"Analysis of the Influence of Vegetation Index Choice on the Classification of Satellite Images for Monitoring Forest Pathology","authors":"E. Trubakov, Olga Trubakova","doi":"10.51130/graphicon-2020-2-3-49","DOIUrl":"https://doi.org/10.51130/graphicon-2020-2-3-49","url":null,"abstract":"Rational use of natural resources and control over their recovery, as well as over destruction due to natural and technogenic causes, is currently one of the most urgent problems of the humanity. Forests are no exception. Multispectral images from Earth’s satellites are most often used for monitoring changes in forest planting. This is due to the fact that merging images taken in certain spectra makes it possible to recognize vegetation containing chlorophyll quite well. It also allows to detect changes in the level of chlorophyll, which shows the differences between healthy and damaged plants. Large areas of planted forests create the need to process huge amounts of data, which is difficult to do manually. One of the most important stages of image processing is the classification of objects in these images. This paper deals with various classification methods used to solve the problem of classifying images of remote sensing of the Earth. As a result, it was decided to evaluate the accuracy of classification methods on various vegetation indices. In the course of the study, the evaluation algorithm was determined, as well as one of the options for analyzing the results obtained. Conclusions were made about the work of classification methods on different vegetation indices.","PeriodicalId":344054,"journal":{"name":"Proceedings of the 30th International Conference on Computer Graphics and Machine Vision (GraphiCon 2020). Part 2","volume":"9 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":"128315739","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
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信