{"title":"使用Kinect确定运动捕捉的工作空间","authors":"Liza Egorova, A. Lavrov","doi":"10.1109/RTUCON.2015.7343155","DOIUrl":null,"url":null,"abstract":"This paper describes the method of determining the workspace for shooting motion capture in real time. Sensor Kinect for Windows v1 and v2 were selected for motion capture, Kinect2BVH program for recording data in the format of BioVision Hierarchy and mathematical processor MATLAB for computation and data visualization. In order to identify the zone in which Kinect successfully reconstructs skeleton, we conducted an experiment in which a person moves smoothly in the captured space. Reconstruction errors are defined as sudden unnatural acceleration of movement of the limbs. The result is a distribution map of the skeletal reconstruction accuracy in the area of Kinect v1 vision. Also, calculations were made to determine the limits of angular accelerations bending joints, and as a result more accurate maps were obtained for the capture with Kinect v1 and v2. These developments are used to construct virtual reality scenes.","PeriodicalId":389419,"journal":{"name":"2015 56th International Scientific Conference on Power and Electrical Engineering of Riga Technical University (RTUCON)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2015-12-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"2","resultStr":"{\"title\":\"Determination of workspace for motion capture using Kinect\",\"authors\":\"Liza Egorova, A. Lavrov\",\"doi\":\"10.1109/RTUCON.2015.7343155\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"This paper describes the method of determining the workspace for shooting motion capture in real time. Sensor Kinect for Windows v1 and v2 were selected for motion capture, Kinect2BVH program for recording data in the format of BioVision Hierarchy and mathematical processor MATLAB for computation and data visualization. In order to identify the zone in which Kinect successfully reconstructs skeleton, we conducted an experiment in which a person moves smoothly in the captured space. Reconstruction errors are defined as sudden unnatural acceleration of movement of the limbs. The result is a distribution map of the skeletal reconstruction accuracy in the area of Kinect v1 vision. Also, calculations were made to determine the limits of angular accelerations bending joints, and as a result more accurate maps were obtained for the capture with Kinect v1 and v2. These developments are used to construct virtual reality scenes.\",\"PeriodicalId\":389419,\"journal\":{\"name\":\"2015 56th International Scientific Conference on Power and Electrical Engineering of Riga Technical University (RTUCON)\",\"volume\":\"15 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2015-12-03\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"2\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2015 56th International Scientific Conference on Power and Electrical Engineering of Riga Technical University (RTUCON)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/RTUCON.2015.7343155\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2015 56th International Scientific Conference on Power and Electrical Engineering of Riga Technical University (RTUCON)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/RTUCON.2015.7343155","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 2
摘要
本文介绍了实时运动捕捉拍摄工作空间的确定方法。传感器选择Kinect for Windows v1和v2进行动作捕捉,Kinect2BVH程序以BioVision Hierarchy格式记录数据,数学处理器MATLAB进行计算和数据可视化。为了确定Kinect成功重建骨骼的区域,我们进行了一个实验,在这个实验中,一个人在捕获的空间中平稳地移动。重建错误被定义为肢体运动的突然非自然加速。结果是Kinect v1视觉区域的骨骼重建精度分布图。此外,还进行了计算,以确定角加速度弯曲关节的极限,从而获得了使用Kinect v1和v2进行捕获的更精确的地图。这些发展被用来构建虚拟现实场景。
Determination of workspace for motion capture using Kinect
This paper describes the method of determining the workspace for shooting motion capture in real time. Sensor Kinect for Windows v1 and v2 were selected for motion capture, Kinect2BVH program for recording data in the format of BioVision Hierarchy and mathematical processor MATLAB for computation and data visualization. In order to identify the zone in which Kinect successfully reconstructs skeleton, we conducted an experiment in which a person moves smoothly in the captured space. Reconstruction errors are defined as sudden unnatural acceleration of movement of the limbs. The result is a distribution map of the skeletal reconstruction accuracy in the area of Kinect v1 vision. Also, calculations were made to determine the limits of angular accelerations bending joints, and as a result more accurate maps were obtained for the capture with Kinect v1 and v2. These developments are used to construct virtual reality scenes.