OBSTACLE DETECTION AND AVOIDANCE ON SIDEWALKS

D. Castells, J. M. F. Rodrigues, J. M. H. du Buf

Abstract

We present part of a vision system for blind and visually impaired people. It detects obstacles on sidewalks and provides guidance to avoid them. Obstacles are trees, light poles, trash cans, holes, branches, stones and other objects at a distance of 3 to 5 meters from the camera position. The system first detects the sidewalk borders, using edge information in combination with a tracking mask, to obtain straight lines with their slopes and the vanishing point. Once the borders are found, a rectangular window is defined within which two obstacle detection methods are applied. The first determines the variation of the maxima and minima of the gray levels of the pixels. The second uses the binary edge image and searches in the vertical and horizontal histograms for discrepancies of the number of edge points. Together, these methods allow to detect possible obstacles with their position and size, such that the user can be alerted and informed about the best way to avoid them. The system works in realtime and complements normal navigation with the cane.

References

  1. Heath, M., Sarkar, S., Sanocki, T., and Bowyer, K. (1997). A robust visual method for assessing the relative performance of edge-detection algorithms. IEEE Trans. PAMI, 19(12):1338-1359.
  2. Kayama, K., Yairi, I., and Igi, S. (2007). Detection of sidewalk border using camera on low-speed buggy. Proc. IASTED Int. Conf. on Artificial Intelligence and Applications,13-15 February, Innsbruck, Austria, pages 262-267.
  3. Kim, L., Park, S., Lee, S., and Ha, S. (2009). An electronic traveler aid for the blind using multiple range sensors. IEICE Electronics Express, 11(6):794-799.
  4. Lee, S. and Kang, S. (2008). A walking guidance system for the visually impaired. Int. J. Pattern Recogn. Artif. Intell., 22(6):1171 - 1186.
  5. Rodrigues, J. and du Buf, J. (2009). Multi-scale lines and edges in V1 and beyond: brightness, object categorization and recognition, and consciousness. BioSystems, 95:206-226.
Download


Paper Citation


in Harvard Style

Castells D., M. F. Rodrigues J. and M. H. du Buf J. (2010). OBSTACLE DETECTION AND AVOIDANCE ON SIDEWALKS . In Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2010) ISBN 978-989-674-029-0, pages 235-240. DOI: 10.5220/0002816002350240


in Bibtex Style

@conference{visapp10,
author={D. Castells and J. M. F. Rodrigues and J. M. H. du Buf},
title={OBSTACLE DETECTION AND AVOIDANCE ON SIDEWALKS},
booktitle={Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2010)},
year={2010},
pages={235-240},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0002816002350240},
isbn={978-989-674-029-0},
}


in EndNote Style

TY - CONF
JO - Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2010)
TI - OBSTACLE DETECTION AND AVOIDANCE ON SIDEWALKS
SN - 978-989-674-029-0
AU - Castells D.
AU - M. F. Rodrigues J.
AU - M. H. du Buf J.
PY - 2010
SP - 235
EP - 240
DO - 10.5220/0002816002350240