基于磁感应和Kinect的混合跟踪算法研究

Research on Hybrid Tracking Algorithm Based on Magnetic and Kincct

跟踪注册技术是增强现实系统中的一个重要研究内容,其致力于将虚拟信息与真实环境精确配准和对实物的精准跟踪,从而构建高效稳定的增强现实系统。在跟踪注册过程中,单一的跟踪注册技术有其自身的局限性与不足,为提高增强现实中跟踪注册的精确性和鲁棒性,结合Kinect深度信息跟踪和磁感应跟踪自身的优缺点,提出了一种基于模糊逻辑和自适应卡尔曼滤波的混合跟踪算法,对磁感应跟踪和Kinect跟踪数据进行动态加权融合,从而实现对手部的实时、精准跟踪。实验表明:该算法能有效地提高基于磁感应和Kinect深度信息跟踪的精确性和鲁棒性。

Tracking registration technology is used to the accurate virtual information in real environment to construct stable and efficient Augmented Reality System,which plays a most important role in the Augmented Reality.Single tracking method is limited accuracy and robustness of the tracking process in Augmented Reality.This paper proposes a hybrid algorithm based on fuzzy logic and self-adaptive Kalman filter,which dynamically fuses magnetic data and Kinect depth data to complete accurate real-time hand tracking.Experimental results show this algorithm can effectively improve the robustness of the hybrid tracking and accuracy of the motion estimation.