Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Image based 6-DOF camera pose estimation with weighted RANSAC 3D

: Wetzel, Johannes

Postprint urn:nbn:de:0011-n-2793540 (1.7 MByte PDF)
MD5 Fingerprint: c1a561effd6c65efb2cc31436ac53f98
The original publication is available at
Erstellt am: 25.2.2014

Weickert, J. (Ed.):
Pattern recognition. 35th German conference, GCPR 2013 : Saarbrücken, Germany, September 3-6, 2013; Proceedings
Berlin: Springer, 2013 (Lecture Notes in Computer Science 8142)
ISBN: 978-3-642-40601-0 (Print)
ISBN: 978-3-642-40602-7 (Online)
ISBN: 3-642-40601-7
German Conference on Pattern Recognition (GCPR) <35, 2013, Saarbrücken>
Konferenzbeitrag, Elektronische Publikation
Fraunhofer IOSB ()
camera pose estimation; tracking; RANSAC; PnP

In this work an approach for image based 6-DOF pose estimation, with respect to a given 3D point cloud model, is presented. We use 3D annotated training views of the model from which we extract natural 2D features, which can be matched to the query image 2D features. In the next step typically the Perspective-N-Point Problem in combination with the popular RANSAC algorithm on the given 2D-3D point correspondences is used, to estimate the 6-D pose of the camera in respect to the model. We propose a novel extension of the RANSAC algorithm, named w-RANSAC 3D, which uses known 3D information to weight each match individually. The evaluation shows that w-RANSAC 3D leads to a more robust pose estimation while needing significantly less iterations.