Point Cloud Registration Algorithm Fusing of Super4PCS and ICP Based on the Key Points

A point cloud registration algorithm fusing of Super 4PCS and ICP based on the key point is proposed to solve the problem that the traditional Super 4PCS algorithm is time consuming and has poor registration accuracy for point clouds with low-overlap region. Firstly, by using the voxel grid method, point cloud is down-sampled to reduce the amount of the computation data. In order to reduce the search range of consistent four-point sets, key points are extracted by using ISS(Intrinsic Shape Signature) method. Then the optimal consistency four-point sets is obtained by Super4PCS based on extracted key points. We use each point in this four-point sets as the center to establish a neighborhood ball, and the overlapping regions is obtained by calculating the intersection of the neighborhood balls. Finally, registration is performed by using ICP within obtained overlapping regions. The experimental results show that the proposed method can improve the registration speed while improve the registration accuracy.