Pose Estimation Without Explicit Matching

Anders Lundquist
Computational Vision and Active Perception Laboratory (CVAP)
Royal Institute of Technology, S-100 44 Stockholm, Sweden
Tech. Rep. ISRN KTH/NA/P-96/17-SE, May. 1996

Abstract

In mobile robot navigation applications it is common to have camera motion and pose (position and orientation) restricted to a plane. This allows the pose estimation problem to be solved using only the horizontal position of features. Since these applications also often require relatively high speed performance, the 2D case of pose estimation is of potentially great imnadaance. AnCVAP/ analytical solution for the 2D perspective 3-point problem is given. As opposed to the 3D case, this problem has a unique solution. In order to avoid, or at least reduce, matching problems, a generalized Hough transform method is used for determining the pose without explicit matching. Various ways of reducing combinatorial complexity and making use of a priori knowledge are investigated. The resulting pose estimation algorithm is then used in a Kalman filter based navigation system.

Anders Lundquist (andersl@bion.kth.se)