A Fast Point Clouds Registration Algorithm for Laser Scanners

Point clouds registration is an important step for laser scanner data processing, and there have been numerous methods. However, the existing methods often suffer from low accuracy speed when registering large point clouds. To meet this challenge, improved iterative closest (ICP) algorithm combining random sample consensus (RANSAC) algorithm, intrinsic shape signatures (ISS), 3D context (3DSC) proposed. The proposed method firstly uses voxel grid filter down-sampling. Next, feature points are extracted by ISS described 3DSC. Afterwards, ISS-3DSC features used rough with RANSAC algorithm. Finally, ICP accurate registration. experimental results show that has faster than compared algorithms, while maintaining high accuracy.