Relocation using Laser and Vision
D. Ortín,
J. Neira, J.M.M. Montiel
Computer Science Dept. of the University of
Zaragoza,
María de Luna 1,
50018 Zaragoza (Spain).
We present
a method for solving the first location problem using 2D laser and vision. Our
observation is a two dimensional laser scan combined with its corresponding
image. The observation is segmented in textured vertical planes; each vertical
plane contains geometrical information about its location given by the laser
scan, plus the gray level image obtained by the camera. The rich plane texture
allows a safe plane recognition and the computer vision geometry allows to
compute the relative camera motion once two planes are recognized as
correspondent. The proposed algorithm outperforms both laser-only or vision only
algorithms. This is shown in the experimental results where a map composed of 8
observations of a 20x3 meters corridor allows to successfully locate the
robot(without any other prior) in 163 out of 192 initial robot locations.