DRIVABLE FLOOR DETECTION WITH MONOCULAR VISUAL PERCEPTION

Abstract

In this study, vision-based scene analysis techniques are studied for the purpose of improved navigation abilities for the mobile robots with a single camera. In this approach, first the camera searches the scenery in order to detect major vertices. In the next step, using geometrical properties of the drivable floor regions in which the mobile robot can without collusion, are defined. Experimental works are implemented on a differential drive robot with monocular camera and the success of the approach is demonstrated

Keywords

• robot vision, scene analysis, drivable floor regions detection, autonomous mobile robots, monocular vision perception

References

1. S. Borthwick and H. Durrant-Whyte, “Simultaneous localization and map building for autonomous guided vehicles.”, IROS, pp. 761–768, 1994.
2. J.-S. Gutmann and C. Schlegel, “AMOS: comparison of scan matching approaches for self-localization in indoor env.,” Proc. of Euromicro Workshop, pp. 61-67, 1996.
3. J. J. Bardyn et al., “Une architecture VLSI pour un operateur de filtrage median,” Congres reconnaissance des formes et intelligence artificielle, vol.1, pp. 557–566, Paris, 25–27 January 1984.
4. C. Tomasi and R. Manduchi, “Bilateral filtering for gray and color images,” In Proceedings of the Sixth Internatinal Conference on Computer Vision, pp. 839–846, 1998.
5. D. Comaniciu and P. Meer, “Mean shift analysis and applications,” IEEE International Conference on Computer Vision, vol. 2, p. 1197, 1999.
6. I. Sobel and G. Feldman, “A 3 × 3 Isotropic Gradient Operator for Image Processing,” In Pattern Classification and Scene Analysis, pp. 271–272, Wiley, 1973.
7. R. O. Duda and P. E. Hart, “Use of the Hough transformation to detect lines and curves in pictures, Communications of the Association for Computing Machinery 15,”(pp. 11– 15, 1972.
8. J. Matas, C. Galambos, and J. Kittler, “Robust detection of lines using the progressive probabilistic Hough transform,” Computer Vision Image Understanding 78, pp. 119–137, 2000.

9. H. Kalviainen et al., “Probabilistic and non-probabilistic Hough Transforms: overview and comparisons,” Image and Vision Computing 13, pp. 239-252, 1995.
10. Wikipedia article: “One Point perspective on Perspective (Graphical)”,web site: http://en.wikipedia.org/wiki/One-point_perspective#One-point_perspective, visited:06/07/2009. last
11. Wikipedia article: “Two Point perspective on Perspective (Graphical)”,web site: http://en.wikipedia.org/wiki/Two-point_perspective#Two-point_perspective, visited:06/07/2009. last
12. P. Heckbert, A Seed Fill Algorithm, Academic Press, New York, 1990.