Markerless Camera Pose Estimation - An Overview

Tobias Nöll; Alain Pagani; Didier Stricker

In: Ariane Middel; Inga Scheler; Hans Hagen (Hrsg.). Visualization of Large and Unstructured Data Sets - Applications in Geospatial Planning, Modeling and Engineering. International Research Training Group Workshop (IRTG-1131), March 19-21, Bodega Bay, CA, USA, Pages 45-54, OpenAccess Series in Informatics (OASIcs), Vol. 19, ISBN 978-3-939897-29-3, Schloss Dagstuhl--Leibniz-Zentrum fuer Informatik, Dagstuhl, Germany, 4/2011.


As shown by the human perception, a correct interpretation of a 3D scene on the basis of a 2D image is possible without markers. Solely by identifying natural features of different objects, their locations and orientations on the image can be identified. This allows a three dimensional interpretation of a two dimensional pictured scene. The key aspect for this interpretation is the correct estimation of the camera pose, i.e. the knowledge of the orientation and location a picture was recorded. This paper is intended to provide an overview of the usual camera pose estimation pipeline as well as to present and discuss the several classes of pose estimation algorithms.

Noell2010_IRTG.pdf (pdf, 3 MB )

Deutsches Forschungszentrum für Künstliche Intelligenz
German Research Center for Artificial Intelligence