Open AccessKeypoint domain triangular features for fast initial alignment of 3D point clouds
Author(s) -
Quan Siwen,
Ma Jie
Publication year - 2019
Publication title -
electronics letters
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.375
H-Index - 146
ISSN - 1350-911X
DOI - 10.1049/el.2019.0802
Subject(s) - point cloud , domain (mathematical analysis) , feature (linguistics) , point (geometry) , algorithm , artificial intelligence , transformation (genetics) , computer science , computer vision , mathematics , pattern recognition (psychology) , geometry , mathematical analysis , linguistics , philosophy , biochemistry , chemistry , gene
The authors propose a keypoint domain triangular feature‐based initial alignment (KDT‐IA) method to achieve fast and automatic registration of three‐dimensional (3D) point clouds. KDT‐IA has two main contributions: a KDT feature and a transformation estimation technique called one point‐based sample consensus (1P‐SAC). KDT is ultrafast because it encodes the spatial geometry of 3D keypoints over sparse keypoints, as opposed to conventional point cloud domain features. The alignment is additionally accelerated by the 1P‐SAC algorithm due to its linear computational complexity. Experiments on real‐world scanned point cloud data confirm that KDT‐IA achieves competitive accuracy performance with classical methods yet being at least one order of magnitude faster.