Depth-based real time head pose tracking using 3D template matching
Journal
SIGGRAPH Asia 2012
Date Issued
2012
Author(s)
Abstract
In this paper, we propose a system to estimate head poses only using depth information in real-time. An optimization method based on 3D model fitting is developed. We iteratively minimize the distance between source and target point clouds of a user's head. The method give fully real-time responses (30fps) without the GPU speedup. We adopt a commodity depth sensor named Microsoft Kinect as well as Asus Xtion, and use the depth image as the only input so that our system will not be affected by illumination variations. However, the simplicity of this acquisition device comes at the cost of frequent noises in the acquired data. We demonstrate that 6 degrees of freedom real-time head motion tracking in 3D space can be achieved with such noisy depth data.
SDGs
Type
conference paper