基于混合现实交互的指挥棒位姿跟踪

为解决目前混合现实系统交互的自然性、直观性与准确性不高的问题，提出一种基于指挥棒的交互方式，其实现的关键是能够实时、准确地对指挥棒位姿进行测算与跟踪.为此，重点探讨一种基于双色标的视觉跟踪方法对指挥棒位姿进行测算.具体思路是先对颜色标进行快速轮廓提取，然后采用最小面积矩形法修补轮廓，从而得到颜色标在平面投影的位姿.最后利用双目视觉定位原理计算出颜色标在三维空间上的位姿即为所求的指挥棒的三维位姿.为验证所提方法的有效性，采用实验对该算法的实时性、准确性进行了分析.结果表明，该方法的实时性与准确性均能满足交互需求.

Baton-like Attitude Tracking Based on Mixed Reality Interaction

In order to solve the problem of the low level of the nature, intuition and accuracy of current mixed reality system interaction, a new method based on baton-like interaction is proposed. The key to its implementation is to measure and track the baton's attitude in real time and accurately. Therefore, the focus is on a two-color vision-based visual tracking method to measure the attitude of the baton. The specific idea is to perform fast contour extraction on the color mark, and then patch the contour by the minimum area rectangle method to get the posture of the color mark projection in the plane. Finally, the principle of binocular vision is used to calculate the three-dimensional pose of the baton. In order to verify the validity of the proposed method, experiments are carried out to analyze the real-time and accuracy of the proposed algorithm. The results show that both the real-time and accuracy of the proposed method can meet the interaction requirements.