On the Use of Disparity Maps for robust Robot Localization under Different Illumination Conditions

In this paper, we introduce the use of disparity maps to alleviate the problem of appearancebased robot localization due to changes in illumination. We describe how is it possible to use disparity maps for appearance-based localization and we compare the results obtained using disparity maps with those obtained with other techniques commonly used to reduce the effect of illumination on images: histogram equalization and gradientbased filters. The results we present show that disparity maps are sensitive enough to rotations and translations of the robot and that they are less sensitive to changes in illumination than previously used techniques. Consequently, we show that disparity maps are a valid alternative to achieve a robust appearance-based robot localization.

[1]  O. Faugeras.  Three-dimensional computer vision: a geometric viewpoint , 1993 .

[2]  Irwin Sobel,et al.  An Isotropic 3×3 image gradient operator , 1990 .

[3]  Horst Bischof,et al.  Mobile robot localization under varying illumination , 2002, Object recognition supported by user interaction for service robots.

[4]  Ben J. A. Kröse,et al.  A probabilistic model for appearance-based robot localization , 2001, Image Vis. Comput..

[5]  D Marr,et al.  Theory of edge detection , 1979, Proceedings of the Royal Society of London. Series B. Biological Sciences.

[6]  Sam T. Roweis,et al.  EM Algorithms for PCA and SPCA , 1997, NIPS.

[7]  Hiroshi Murase,et al.  Illumination Planning for Object Recognition Using Parametric Eigenspaces , 1994, IEEE Trans. Pattern Anal. Mach. Intell..

[8]  Ben J. A. Kröse,et al.  Auxiliary particle filter robot localization from high-dimensional sensor observations , 2002, Proceedings 2002 IEEE International Conference on Robotics and Automation (Cat. No.02CH37292).

[9]  Kurt Konolige,et al.  Small Vision Systems: Hardware and Implementation , 1998 .

[10]  Rafael C. González,et al.  Local Determination of a Moving Contrast Edge , 1985, IEEE Transactions on Pattern Analysis and Machine Intelligence.