Open AccessQuintuple Local Coordinate Images for Local Shape Description
Author(s) -
Wuyong Tao,
Xian-Sheng Hua,
Rui-Sheng Wang,
Dianxiang Xu
Publication year - 2020
Publication title -
photogrammetric engineering and remote sensing
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.483
H-Index - 127
eISSN - 2374-8079
pISSN - 0099-1112
DOI - 10.14358/pers.86.2.121
Subject(s) - robustness (evolution) , weighting , artificial intelligence , point cloud , computation , computer vision , pattern recognition (psychology) , mathematics , computer science , algorithm , physics , biochemistry , chemistry , acoustics , gene
Owing to poor descriptiveness, weak robustness, and high computation complexity of local shape descriptors ( LSDs ), point-cloud registration in the case of partial overlap and object recognition in a cluttered environment are still challeng- ing tasks. For this purpose, an LSD is developed in this article by proposing a new local reference frame ( LRF ) method and designing a novel feature representation. In the LRF method, two weighting methods are applied to obtain robustness to noise, point-density variation, and incomplete shape. Additionally, a vector representation is calculated to disambiguate the sign of the x-axis. The feature representation encodes the local information by generating the local coordinate images from five views. Thus, more geometric and spatial information is included in the descriptor. Finally, the performance of the LRF method and the LSD is evaluated on several popular data sets. The experimental results demonstrate well that the LRF is robust to noise, point-density variation, and incomplete shape, and the LSD holds strong robustness, superior descriptiveness, and high computational efficiency.