Automatic ICP‐Based Global Matching of Free‐Form Linear Features
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.
Document Type: Research Article
Affiliations: ) National Technical University of Athens, Greece
Publication date: 2012-09-01