利用共面圆特征实现增强现实图像注册

Registration in Augmented Reality from Coplanar Circles

本文提出以对象上的共面圆为基础估算对象位姿,实施增强现实图像注册的方法。假设相机内参数已标定,文章从绝对二次曲线与平面圆有公共虚交点出发,通过计算消隐线方程、确定圆心位置、获取坐标轴方向等步骤分别估算对象位姿的旋转分量和平移分量,从而最终估算出对象位姿。该算法所需预知的条件少、计算代价小,因而在工业环境中更易实现。综合数据仿真与真实对象测量验证了本文算法的正确性以及在噪声和遮挡情形下的鲁棒性。

An approach for estimating object pose from coplanar circles and implementation 3D registration is proposed in augmented reality.Provided that intrinsic parameters of camera has been calibrated,according to common virtual intersecting points between absolute conic and coplanar circles,rotation component of pose is estimated through calculating the equation of vanishing line,determining the centers of circles as well as axes direction of frame.Furthermore,translation component is finally calculated so that object pose is determined completely.The algorithm requires fewer preconditions with low computational cost,which is more readily satisfied in industrial scenario.Experiments on synthetic datum and real object show that the algorithm is correct and robust to noise and occlusion.