论文标题
强大的ICP初始化方法
An approach to robust ICP initialization
论文作者
论文摘要
在本说明中，我们提出了一种初始化迭代最接近点（ICP）算法的方法，以匹配与刚性变换相关的未标记点云。该方法基于匹配由点的协方差矩阵定义的椭圆形，然后测试各种主半轴匹配，这些匹配因有限反射组的元素而不同。我们得出了噪声方法的鲁棒性和数值实验的稳健性，这证实了我们的理论发现。
In this note, we propose an approach to initialize the Iterative Closest Point (ICP) algorithm to match unlabelled point clouds related by rigid transformations. The method is based on matching the ellipsoids defined by the points' covariance matrices and then testing the various principal half-axes matchings that differ by elements of a finite reflection group. We derive bounds on the robustness of our approach to noise and numerical experiments confirm our theoretical findings.
