TOWARDS THE ESTIMATION OF CONSPICUITY WITH VISUAL PRIORS

Ludovic Simon, Jean-Philippe Tarel, Roland Brémond

2008

Abstract

Traffic signs are designed to be clearly seen by drivers. However a little is known about the visual influence of the traffic sign environment on how it will be perceived. Computer estimation of the conspicuity from images using a camera mounted on a vehicle is thus of importance in order to be able to quickly make a diagnosis regarding conspicuity of traffic signs. Unfortunately, our knowledge about the human visual processing system is rather incomplete and thus conspicuity visual mechanisms remain poorly understood. A complete model for conspicuity is not known, only specific features are known to be of importance. It makes sense to assume that an important task for drivers is to search for traffic signs. We therefore propose a new paradigm for conspicuity estimation in search tasks based on statistical learning of the visual features of the object of interest.

References

  1. Bremond, R., Tarel, J.-P., Choukour, H., and Deugnier, M. (2006). La saillance visuelle des objets routiers, un indicateur de la visibilité routière. In Proceedings of Journées des Sciences de l'Ingénieur (JSI'06), Marne la Vallée, France.
  2. CIE137 (2000). The conspicuity of traffic signs in complex backgrounds. In CIE137, Technical report of the Commision Internationale de L'Eclairage (CIE).
  3. Fleuret, F. and Sahbi, H. (2003). Scale-invariance of support vector machines based on the triangular kernel. In Proceedings of IEEE International Workshop on Statistical and Computational Theories of Vision, Nice, France.
  4. Gao, D. and Vasconcelos, N. (2004). Discriminant saliency for visual recognition from cluttered scenes. In NIPS.
  5. Itti, L., Koch, C., and Niebur, E. (1998). A model of saliency-based visual attention for rapid scene analysis. IEEE Transactions on Pattern Analysis and Machine Intelligence, 20(11):1254-1259.
  6. Navalpakkam, V. and Itti, L. (2005). Modeling the influence of task on attention. Vision Research, 45(2):205-231.
  7. Schölkopf, B. and Smola, A. (2002). Learning with Kernels. MIT Press, Cambridge, MA, USA.
  8. Simon, L., Tarel, J.-P., and Bremond, R. (2007). A new paradigm for the computation of conspicuity of traffic signs in road images. In Proceedings of 26th session of Commision Internationale de L'Eclairage (CIE'07), volume II, pages 161 - 164, Beijing, China.
  9. Sundstedt, V., Debattista, K., Longhurst, P., Chalmers, A., and Troscianko, T. (2005). Visual attention for efficient high-fidelity graphics. In Spring Conference on Computer Graphics (SCCG 2005), pages 162-168.
  10. Underwood, G., Foulsham, T., van Loon, E., Humphreys, L., and Bloyce, J. (2006). Eye movements during scene inspection: A test of the saliency map hypothesis. European Journal of Cognitive Psychology, 18(3):321-342.
  11. Vapnik, V. (1999). The Nature of Statistical Learning Theory. Springer Verlag, 2nd edition, New York.
Download


Paper Citation


in Harvard Style

Simon L., Tarel J. and Brémond R. (2008). TOWARDS THE ESTIMATION OF CONSPICUITY WITH VISUAL PRIORS . In Proceedings of the Third International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2008) ISBN 978-989-8111-21-0, pages 323-328. DOI: 10.5220/0001083503230328


in Bibtex Style

@conference{visapp08,
author={Ludovic Simon and Jean-Philippe Tarel and Roland Brémond},
title={TOWARDS THE ESTIMATION OF CONSPICUITY WITH VISUAL PRIORS},
booktitle={Proceedings of the Third International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2008)},
year={2008},
pages={323-328},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0001083503230328},
isbn={978-989-8111-21-0},
}


in EndNote Style

TY - CONF
JO - Proceedings of the Third International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2008)
TI - TOWARDS THE ESTIMATION OF CONSPICUITY WITH VISUAL PRIORS
SN - 978-989-8111-21-0
AU - Simon L.
AU - Tarel J.
AU - Brémond R.
PY - 2008
SP - 323
EP - 328
DO - 10.5220/0001083503230328