Analytical and numerical investigations on the accuracy and robustness of geometric features extracted from 3D point cloud data

• Published in: ISPRS journal of photogrammetry and remote sensing Vol. 126; pp. 195 - 208
• Main Authors: Dittrich, André, Weinmann, Martin, Hinz, Stefan
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 01.04.2017
• Subjects: computer vision; Covariance features; Eigenvalues; Feature extraction; geometry; photogrammetry; Point cloud; remote sensing; robots; Shape primitives; Variance propagation; 3D; Point cloud; Covariance features; Eigenvalues; Feature extraction; Variance propagation; Shape primitives
• ISSN: 0924-2716; 1872-8235
• DOI: 10.1016/j.isprsjprs.2017.02.012

In photogrammetry, remote sensing, computer vision and robotics, a topic of major interest is represented by the automatic analysis of 3D point cloud data. This task often relies on the use of geometric features amongst which particularly the ones derived from the eigenvalues of the 3D structure ten...