Premium
Automatic ICP‐Based Global Matching of Free‐Form Linear Features
Author(s) -
Vassilaki Dimitra I.,
Ioannidis Charalambos C.,
Stamos Athanassios A.
Publication year - 2012
Publication title -
the photogrammetric record
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.638
H-Index - 51
eISSN - 1477-9730
pISSN - 0031-868X
DOI - 10.1111/j.1477-9730.2012.00692.x
Subject(s) - iterative closest point , geospatial analysis , computer science , matching (statistics) , position (finance) , curse of dimensionality , projection (relational algebra) , point (geometry) , transformation (genetics) , artificial intelligence , linear map , algorithm , computer vision , pattern recognition (psychology) , mathematics , point cloud , geography , geometry , remote sensing , biochemistry , finance , economics , gene , pure mathematics , statistics , chemistry
The geometric exploitation of linear features has been investigated in various remote sensing and geospatial problems. This paper introduces a novel and general method based on the iterative closest point (ICP) algorithm for the global matching of heterogeneous free‐form linear features of the same (2D–2D, 3D–3D), or different, (2D–3D) dimensionality. No constraints are imposed on either the transformation, the projection type or the geometric nature of the features. The method assumes no prior knowledge of the relative position of the features, or of point correspondences, and is tested with various simulated and real‐world heterogeneous data.