IPMI 2013 - LNCS 7917

Active Testing Search for Point Cloud Matching

Miguel Amável Pinheiro¹, Raphael Sznitman², Eduard Serradell³, Jan Kybic¹, Francesc Moreno-Noguer³, and Pascal Fua²

¹Center for Machine Perception, Faculty of Electrical Engineering, Czech Technical University in Prague, Czech Republic
amavemig@cmp.felk.cvut.cz
http://cmp.felk.cvut.cz/~amavemig

²Computer Vision Laboratory, École Polytechnique Fédérale de Lausanne (EPFL), Lausanne, Switzerland

³Institut de Robòtica i Informàtica Industrial (CSIC-UPC), Barcelona, Spain

Abstract. We present a general approach for solving the point-cloud matching problem for the case of mildly nonlinear transformations. Our method quickly finds a coarse approximation of the solution by exploring a reduced set of partial matches using an approach to which we refer to as Active Testing Search (ATS). We apply the method to registration of graph structures by branching point matching. It is based solely on the geometric position of the points, no additional information is used nor the knowledge of an initial alignment. In the second stage, we use dynamic programming to refine the solution. We tested our algorithm on angiography, retinal fundus, and neuronal data gathered using electron and light microscopy. We show that our method solves cases not solved by most approaches, and is faster than the remaining ones.

Keywords: point cloud matching, graph matching, image registration, active search, dendrites

LNCS 7917, p. 572 ff.

Full article in PDF | BibTeX