It is easy to fall into a local optimum for registration algorithms, such as iterative closest point (ICP) algorithm in 3-D point cloud registration. In this study, a coarse registration algorithm based on the transformation of the geometric center of gravity and the centroid is proposed. Firstly, the noise and outliers are removed by using the filters for the point clouds. Then, a preliminary model of rotational transformation of point the clouds is established through the analysis of the relation of the gravity center and centroid of two point clouds. Moreover, according to the relation between rotation angle and registration error, an iterative rotation model is established to obtain the optimal rotation angle. Finally, ICP algorithm is applied to further improve registration performance. The experimental results show that the proposed coarse registration algorithm demonstrates superior performance, compared with the registration methods relying on the overlapped center of gravity.