基于计算机视觉的三维人体运动捕捉方法

A. D. Obukhov, D. L. Dedov, E. O. Surkova, I. L. Korobova
{"title":"基于计算机视觉的三维人体运动捕捉方法","authors":"A. D. Obukhov, D. L. Dedov, E. O. Surkova, I. L. Korobova","doi":"10.23947/2687-1653-2023-23-3-317-328","DOIUrl":null,"url":null,"abstract":"Introduction. The analysis of approaches to tracking the human body identified problems when capturing movements in a three-dimensional coordinate system. The prospects of motion capture systems based on computer vision are noted. In existing studies on markerless motion capture systems, positioning is considered only in two-dimensional space. Therefore, the research objective is to increase the accuracy of determining the coordinates of the human body in three-dimensional coordinates through developing a motion capture method based on computer vision and triangulation algorithms. Materials and Methods . A method of motion capture was presented, including calibration of several cameras and formalization of procedures for detecting a person in a frame using a convolutional neural network. Based on the skeletal points obtained from the neural network, a three-dimensional reconstruction of the human body model was carried out using various triangulation algorithms. Results. Experimental studies have been carried out comparing four triangulation algorithms: direct linear transfer, linear least squares method, L2 triangulation, and polynomial methods. The optimal triangulation algorithm (polynomial) was determined, providing an error of no more than 2.5 pixels or 1.67 centimeters. Discussion and Conclusion . The shortcomings of existing motion capture systems were revealed. The proposed method was aimed at improving the accuracy of motion capture in three-dimensional coordinates using computer vision. The results obtained were integrated into the human body positioning software in three-dimensional coordinates for use in virtual simulators, motion capture systems and remote monitoring.","PeriodicalId":13758,"journal":{"name":"International Journal of Advanced Engineering Research and Science","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2023-09-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"3D Human Motion Capture Method Based on Computer Vision\",\"authors\":\"A. D. Obukhov, D. L. Dedov, E. O. Surkova, I. L. Korobova\",\"doi\":\"10.23947/2687-1653-2023-23-3-317-328\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Introduction. The analysis of approaches to tracking the human body identified problems when capturing movements in a three-dimensional coordinate system. The prospects of motion capture systems based on computer vision are noted. In existing studies on markerless motion capture systems, positioning is considered only in two-dimensional space. Therefore, the research objective is to increase the accuracy of determining the coordinates of the human body in three-dimensional coordinates through developing a motion capture method based on computer vision and triangulation algorithms. Materials and Methods . A method of motion capture was presented, including calibration of several cameras and formalization of procedures for detecting a person in a frame using a convolutional neural network. Based on the skeletal points obtained from the neural network, a three-dimensional reconstruction of the human body model was carried out using various triangulation algorithms. Results. Experimental studies have been carried out comparing four triangulation algorithms: direct linear transfer, linear least squares method, L2 triangulation, and polynomial methods. The optimal triangulation algorithm (polynomial) was determined, providing an error of no more than 2.5 pixels or 1.67 centimeters. Discussion and Conclusion . The shortcomings of existing motion capture systems were revealed. The proposed method was aimed at improving the accuracy of motion capture in three-dimensional coordinates using computer vision. The results obtained were integrated into the human body positioning software in three-dimensional coordinates for use in virtual simulators, motion capture systems and remote monitoring.\",\"PeriodicalId\":13758,\"journal\":{\"name\":\"International Journal of Advanced Engineering Research and Science\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2023-09-29\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"International Journal of Advanced Engineering Research and Science\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.23947/2687-1653-2023-23-3-317-328\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"International Journal of Advanced Engineering Research and Science","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.23947/2687-1653-2023-23-3-317-328","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

摘要

介绍。对跟踪人体的方法的分析发现了在三维坐标系中捕捉运动时存在的问题。展望了基于计算机视觉的运动捕捉系统的发展前景。在现有的无标记动作捕捉系统研究中,定位只考虑二维空间。因此,研究目标是通过开发一种基于计算机视觉和三角测量算法的运动捕捉方法,提高在三维坐标中确定人体坐标的精度。材料与方法。提出了一种运动捕捉方法,包括几个摄像机的校准和使用卷积神经网络检测帧中的人的形式化程序。基于神经网络获取的骨骼点,利用各种三角剖分算法对人体模型进行三维重建。结果。实验研究比较了四种三角剖分算法:直接线性转移、线性最小二乘法、L2三角剖分和多项式方法。确定了最优三角剖分算法(多项式),误差不超过2.5像素(1.67厘米)。讨论与结论。揭示了现有动作捕捉系统的不足。该方法旨在提高计算机视觉在三维坐标下的运动捕捉精度。所获得的结果被集成到三维坐标的人体定位软件中,用于虚拟模拟器、运动捕捉系统和远程监控。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
3D Human Motion Capture Method Based on Computer Vision
Introduction. The analysis of approaches to tracking the human body identified problems when capturing movements in a three-dimensional coordinate system. The prospects of motion capture systems based on computer vision are noted. In existing studies on markerless motion capture systems, positioning is considered only in two-dimensional space. Therefore, the research objective is to increase the accuracy of determining the coordinates of the human body in three-dimensional coordinates through developing a motion capture method based on computer vision and triangulation algorithms. Materials and Methods . A method of motion capture was presented, including calibration of several cameras and formalization of procedures for detecting a person in a frame using a convolutional neural network. Based on the skeletal points obtained from the neural network, a three-dimensional reconstruction of the human body model was carried out using various triangulation algorithms. Results. Experimental studies have been carried out comparing four triangulation algorithms: direct linear transfer, linear least squares method, L2 triangulation, and polynomial methods. The optimal triangulation algorithm (polynomial) was determined, providing an error of no more than 2.5 pixels or 1.67 centimeters. Discussion and Conclusion . The shortcomings of existing motion capture systems were revealed. The proposed method was aimed at improving the accuracy of motion capture in three-dimensional coordinates using computer vision. The results obtained were integrated into the human body positioning software in three-dimensional coordinates for use in virtual simulators, motion capture systems and remote monitoring.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
自引率
0.00%
发文量
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×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
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:481959085
Book学术官方微信