当我们抓握物体时,手指和手掌的多个区域通常会与物体表面接触。重建这些接触区域具有挑战性。本文介绍了一种方法,通过结合基于标记的运动捕捉与现有的基于深度学习的手部网格重建技术,来近似估计接触区域。
Chapters in this video
0:04
Introduction
1:02
Preparing the Motion Capture System
1:28
Calibrating the Cameras
2:02
Creating and Preparing Stimulus Object
3:10
Co‐Registering Real and Mesh Model Versions of the Stimulus Object
4:25
Setting up Markers on the Hands
5:08
Acquiring a Single Trial and Labeling the Markers
6:26
Reconstruct the Joint Skeletal Joint Poses
7:07
Generating Hand Mesh Reconstructions and Hand‐Object Contact Region Estimates
7:46
Results: Estimation of Contact Regions for Hand‐Object Interactions During Multi‐Digit Grasps
9:02
Conclusion
Related Videos
版权所有 © 2026 MyJoVE Corporation。保留所有权利。