Pose Estimation of Free-Form Objects Bodo Rosenhahn 1 and Gerald Sommer 2 1 University of Auckland (CITR) Computer Science Department Tamaki Campus Private Bag 92019 Auckland New Zealand bros028@cs.auckland.ac.nz 2 Institut f¨ ur Informatik und Praktische Mathematik Christian-Albrechts-Universit¨at zu Kiel Olshausenstr. 40, 24098 Kiel, Germany gs@ks.informatik.uni-kiel.de Abstract. In this contribution we present an approach for 2D-3D pose estimation of 3D free-form surface models. In our scenario we observe a free-form object in an image of a calibrated camera. Pose estimation means to estimate the relative position and orientation of the 3D object to the reference camera system. The object itself is modeled as a two- parametric 3D surface and extended by one-parametric contour parts of the object. A twist representation, which is equivalent to a Fourier representation allows for a low-pass approximation of the object model, which is advantageously applied to regularize the pose problem. The experiments show, that our developed algorithms are fast (200ms/frame) and accurate (1 o rotational error/frame). 1 Introduction Pose estimation itself is one of the oldest computer vision problems. It is crucial for many computer and robot vision tasks. Pioneering work was done in the 80’s and 90’s by Lowe [8], Grimson [7] and others. These authors use point correspondences. More abstract entities can be found in [16,3]. In the literature we find circles, cylinders, kinematic chains or other multi-part curved objects as entities. Works concerning free-form curves can be found e.g. in [5]. Contour point sets, affine snakes, or active contours are used for visual servoing in different works. For a definition of the pose problem we want to quote Grimson [7]: By pose we mean the transformation needed to map an object model from its inherent coordinate system into agreement with the sensory data. We are estimating the relative rotation and translation of a 3D object with respect to a reference camera system in the framework of a 2D-3D pose estimation approach. In this work we deal with free-form surface and contour models for object representation. We want to quote Besl [2] for a definition: A free-form surface has a well defined surface that is continuous almost everywhere except at vertices, edges and cusps. T. Pajdla and J. Matas (Eds.): ECCV 2004, LNCS 3021, pp. 414–427, 2004. c  Springer-Verlag Berlin Heidelberg 2004