3.8 Proceedings Paper

A Skeleton Posture Transfer Method from Kinect Capture

出版社

IEEE
DOI: 10.1109/VRHCIAI57205.2022.00033

关键词

posture transfer; skeleton; Kinect; 3D model; virtual reality

资金

  1. Hainan Natural Science Foundation [620RC604]
  2. Science and Technology Project of Haikou [2020-014, 2020-044, 2020-053]
  3. Guilin University of Electronic Technology, Guangxi Key Laboratory of Image and Graphic Intelligent Processing (GIIP2012)
  4. National Natural Science Foundation [61502127]
  5. Key R&D Projects in Hainan Province [ZDYF201901O]
  6. Research project on education and teaching reform of Hainan Normal University [hsjg2020-20]

向作者/读者索取更多资源

This paper proposes a method to transfer user's posture to a 3D model, by capturing skeleton information using Kinect and applying a series of transformations on the skeleton. The feasibility and effectiveness of this method have been demonstrated through experiments, and it can be applied to other types of models as well.
At present, 3D models are applied to many fields, and the action control of 3D model needs be studied further. In order to control a 3D model using user-acceptable devices, this paper proposes a method to transfer the posture of the skeleton captured by Kinect to a skeleton of the Soldier model, which is a sample in Microsoft's DirectX SDK First, using the Kinect to collect the user's skeleton information, combined with the initial posture of the Soldier skeleton, through node matching, inverse mirror transformation, transformation from absolute to relative, coordinate space transformation, to generate a skeleton with the same structure as the Soldier skeleton, which can be applied to the Soldier model. And in a virtual reality scene, the corresponding actions of users can drive the Soldier model. Experiments show that the method is feasible and effective. The proposed method can also be referenced and applied to a target skeleton with other structures.

作者

我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。

评论

主要评分

3.8
评分不足

次要评分

新颖性
-
重要性
-
科学严谨性
-
评价这篇论文

推荐

暂无数据
暂无数据