基于遗传算法和最近点迭代法的多视角数据配准

Registration of Measuring Data under Different Viewpoints Based on GA and ICP

针对复杂零件多视角下测量的数据,最近点迭代法(ICP)对两个点云相对初始位置不能相差太远的要求,提出了一种初始对齐和精配准相结合的方法来进行测量数据的配准,通过简单易行的各视角点群形心的坐标变换进行初始对齐,以提高遗传算法(GA)二次配准的寻优速度,再利用ICP实现快速的精确配准,具有更高的可靠性和稳定性.

The iterative closest point （ICP） algorithm requires a good initial position in the registration of measuring data under different viewpoints, a registration method which combined the initial matching and accuracy registration is proposed The centroid of measuring data under different viewpoints is firstly matched by coordinate transformation to improve iterative speed, then real-coded genetic algorithm （GA） is taken to achieve further matching, finally the accuracy registration can be fast realized by ICP algorithm and has better stability.