基于最小二乘法的点云数据拼接研究

Research of Point-clouds Registration Based on Least-square Method

点云数据拼接在逆向工程、计算机视觉、医学图像处理等方面有着十分广泛的应用。为了更快、更精确地进行点云数据拼接,根据计算机点云数据拼接处理的要求,结合空间坐标组合变换和矩阵变换的原理,提出了一种基于最小二乘法采用多个标志点计算坐标转换矩阵的点云数据拼接方法。通过实例对当前几种常用的典型的拼接方法进行分析比较的结果表明,利用该方法实现点云数据的拼接,具有速度快、精度高、稳定性好、操作简单等特点,非常适合于工程实际应用。

Point-clouds registration is widely applied in reverse-engineering, computer vision and medical imaging, etc. Based on the combined transformation theory of the space coordinates, a registration method, which extracts the transition matrix with multi-points based on least-square method to minimize the transition error, is proposed. Some typical methods are specified and analyzed with practical examples in this paper. Experimental results show that this approach can realize point-clouds registration as the features of rapid speed, high accuracy, stability and simple operation. It is powerful for practical engineering.