应用改进的ICP算法检测工业封头表面变形

由于工业封头变形使得采集到的两期点云重心不一致,受点云重心变化的干扰,传统ICP算法出现局部收敛的情况,本文提出了一种基于点对间欧氏距离计算点云加权重心的ICP改进算法。该方法通过给不同距离的点对赋予权值,变形区域的点对距离较大,赋予的权值相对小,有效地消除了变形区域的点云对重心位置的影响。实验结果表明,该方法大大提高了ICP算法的精准性,有效消除重心变化的影响,从而可以准确地检测出工业封头变形区域。

The Application of Impr oved ICP Algorithm to Detect Surface Deformation Ind usrt ial Equipment

For industrial equipment deformation allows the acquisition of two point clouds to the center of gravity is inconsistent , so by changing the focus point cloud interference , the traditional ICP algorithm is a partial convergence of circumstances , is proposed based on the Euclidean distance between points on the point cloud computing weighted center of gravity ICP algorithm .In this method , the distance to different points on the assigned weights , because the deformation zone distance between a point on the larger value of the rights conferred by a relatively small , thus effectively eliminating deformation region of the point cloud on the location of the center of gravity.Experimental results show that the method greatly improves the efficiency of the ICP algorithm , the effective elimination of the center of gravity changes .Which can accurately detect the deformation area of industrial equipment .