不规则曲面的拼接是3维拼接中的难点，提出采用不规则曲面点与其一邻域点重心间的距离作为刚性特征对点云进行粗配准，使用迭代最邻近点算法和刚性特征进行精配准。实验结果表明，刚性特征迭代最邻近点算法的误差收敛速度显著提高。当点云为重心距离大于10的差姿态时，该算法与不进行粗配准的迭代最邻近点算法相比，收敛速度和拼接质量都有较大提高。

The irregular surface registration is a challenging issue in the three dimensional registration. This paper proposed an approach to point cloud coarse registration by using the distance between an irregular surface point and the center of mass of its one length neighboring points as the rigid feature, and to point cloud fine registration by the iteration close point algorithm and rigid feature. The experimental results show that the error convergence rate of the rigid feature iteration close point algorithm is significantly improved. And then, both the convergence rate and the registration quality of the algorithm are improved, compared with iteration close point algorithm that not have coarse registration, when point clouds which the distance between the center of gravity is bigger than 10.