An automatic 3D point cloud registration method based on regional curvature maps
作者:
Highlights:
• A novel 3D shape descriptor-Regional Curvature Map (RCM) is proposed.
• An automatic 3D point cloud registration method based on RCMs is introduced.
• The RCM is discriminative and robust against normal errors and varying point cloud density.
• The RCM searching and matching strategy reduces the influence of area with missing data.
• The RCM-based registration method achieves a higher registration rate and efficiency.
摘要
•A novel 3D shape descriptor-Regional Curvature Map (RCM) is proposed.•An automatic 3D point cloud registration method based on RCMs is introduced.•The RCM is discriminative and robust against normal errors and varying point cloud density.•The RCM searching and matching strategy reduces the influence of area with missing data.•The RCM-based registration method achieves a higher registration rate and efficiency.
论文关键词:3D point cloud,Local shape descriptor,Regional curvature distribution,3D surface registration
论文评审过程:Received 14 August 2012, Revised 7 June 2016, Accepted 22 September 2016, Available online 27 October 2016, Version of Record 12 November 2016.
论文官网地址:https://doi.org/10.1016/j.imavis.2016.09.002