MOTION SEGMENTATION THROUGH FACTORIZATION - APPLICATION TO NIGHT DRIVING ASSISTANCE

Carme Julià, Joan Serrat, Antonio López, Felipe Lumbreras, Dani Ponsa, Thorsten Graf

Abstract

Intelligent vehicles are those equipped with sensors and information control systems that can assist human driving. In this context, we address the problem of detecting vehicles at night. The aim is to distinguish vehicles from lamp posts and traffic sign reflections by grouping the blob trajectories according to their apparent motion. We have adapted two factorization techniques, originally designed to estimate the scene structure from motion: the Costeira–Kanade and the Han–Kanade, named after their authors. Results on both vehicle existence in the field of view and motion segmentation are reported.

References

  1. Costeira, J. and Kanade, T. (1998). A multibody factorization method for independently moving objects. International Journal of Computer Vision, 29(3).
  2. Han, M. and Kanade, T. (2004). Reconstruction of a scene with multiple linearly moving objects. International Journal of Computer Vision, 59(3):285-300.
  3. Hu, U. (1999). Moving objects detection from time-varied background: an application on camera 3d motion analysis. Second International conference of 3-D digital imaging and modeling.
  4. Kanatani, K. and Sugaya, Y. (2004). Factorization without factorization : complete recipe. Memoirs of the Faculty of Engineering, Okayama University, 38(2):61- 72.
  5. Megret, R. and DeMenthon, D. (2002). A survey of spatio-temporal grouping techniques. Technical Report LAMP-094, Language and Media Processing, University of Maryland.
  6. Tomasi, C. and Kanade, T. (1992). Shape from motion from image streams under orthography : a factorization approach. International Journal of Computer Vision, 2(9).
  7. Woelk, Gehrig, K. (2004). A monocular image based intersection assistant. IEEE Intelligent Vehicles Symposium.
Download


Paper Citation


in Harvard Style

Julià C., Serrat J., López A., Lumbreras F., Ponsa D. and Graf T. (2006). MOTION SEGMENTATION THROUGH FACTORIZATION - APPLICATION TO NIGHT DRIVING ASSISTANCE . In Proceedings of the First International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, ISBN 972-8865-40-6, pages 270-277. DOI: 10.5220/0001362802700277


in Bibtex Style

@conference{visapp06,
author={Carme Julià and Joan Serrat and Antonio López and Felipe Lumbreras and Dani Ponsa and Thorsten Graf},
title={MOTION SEGMENTATION THROUGH FACTORIZATION - APPLICATION TO NIGHT DRIVING ASSISTANCE},
booktitle={Proceedings of the First International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP,},
year={2006},
pages={270-277},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0001362802700277},
isbn={972-8865-40-6},
}


in EndNote Style

TY - CONF
JO - Proceedings of the First International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP,
TI - MOTION SEGMENTATION THROUGH FACTORIZATION - APPLICATION TO NIGHT DRIVING ASSISTANCE
SN - 972-8865-40-6
AU - Julià C.
AU - Serrat J.
AU - López A.
AU - Lumbreras F.
AU - Ponsa D.
AU - Graf T.
PY - 2006
SP - 270
EP - 277
DO - 10.5220/0001362802700277