Real-Time Human Pose Estimation and Tracking Using Heterogeneous Multi-Sensor Fusion
Wonjin Hong, Jin Kim
| The Graduate school of Advanced Imaging Science, Multimedia & Film(GSAIM), Chung-Ang University
We propose a real-time 3D human pose estimation system that fuses LiDAR and inertial sensors. To address drift issues from single-sensor usage, the system combines data from both sensors to estimate body parameters, position, and orientation, reconstructing them onto a virtual avatar. Experimental results demonstrate high accuracy and strong agreement with existing multi-sensor systems.
Wonjin Hong is currently pursuing a master's degree at the Graduate School of Advanced Imaging Science and Technology (GSAIM) at Chung-Ang University. His research interests include motion capture-based human motion analysis, human-computer interaction (HCI), and human motion generation.
Jin Kim is currently pursuing a master's degree at the Graduate School of Advanced Imaging Science and Technology (GSAIM) at Chung-Ang University. His research interests include motion capture-based human motion analysis, HCI, and embodied interface design.