A DIFFERENTIAL GEOMETRIC APPROACH FOR VISUAL NAVIGATION IN INDOOR SCENES

L. Fuentes, M. Gonzalo-Tasis, G. Bermudez, J. Finat

Abstract

Visual perception of the environment provides a detailed scene representation which contributes to improve motion planning and obstacle avoidance navigation for wheelchairs in non-structured indoor scenes. In this work we develop a mobile representation of the scene based on perspective maps for the automatic navigation in absence of previous information about the scene. Images are captured with a passive low-cost video camera. The main feature for visual navigation in this work is a map of quadrilaterals with apparent motion. From this mobile map, perspective maps are updated following hierarchical grouping in quadrilaterals maps given by pencils of perspective lines through vanishing points. Egomotion is interpreted in terms of maps of mobile quadrilaterals. The main contributions of this paper are the introduction of Lie expansion/contraction operators for quadrilateral/cuboid and the adaptation of Kalman filtering for moving quadrilaterals to estimate and predict the egomotion of a mobile platform. Our approach is enough modular and flexible for adapting to indoor and outdoor scenes provided at least four homologue cuboids be present in the scene between each pair of sampled views of a video sequence.

References

  1. A. Pruski, M. E. and Morre, Y. (2002). Vahm: A user adapted intelligent wheelchair. In IEEE Intl Conf on Control Application (Glasgow, Scotland, UK). IEEE.
  2. Cortés, U., Annicchiarico, R., Vázquez-Salceda, J., Urdiales, C., namero, L. C., López-Sánchez, M., Sànchez-Marrè, M., and Caltagirone, C. (2003). etools: The use of assistive technologies to enhance disabled and senior citizens' autonomy. In EU-LAT Workshop on e-Health, pages 117-133.
  3. Faugeras, O. (1993). Three-dimensional Computer Vision. A Geometric Viewpoint. The MIT Press, Cambridge, Mass.
  4. J. Minguez, L. M. and Montano, L. (2004). An architecture for snsor-based navigation in realistic dynamic and troublesome scenarios. In Proc. IROS). IEEE.
  5. Jelinek, D. and Taylor, C. (2001). Reconstruction of linearly parametrized models from single images with camera of unknown focal length. IEEE Trans. on Pattern Analysis and Machine Intelligence, 23(7):767-773.
  6. Levine, S. P., Bell, D. A., Jaros, L. A., Simpson, R. C., and Koren, Y. (1999). The navchair assistive wheelchair navigation system. IEEE Trans on Rehabilitation Engineering, 7 (4):443-451.
  7. M. Gonzalo, J. Finat, M. A. and Aguilar, S. (2002). Dynamical trapezoidal maps for coarse perspective model in indoor scenes. In ISPRS'02, 1st International Conference on Enterprise Information Systems. ISPRS.
  8. M. Rous, H. L. and Kraiss, K. F. (2001). Vision-based landmark extraction using indoor scene analysis for mobile robot navigation. In IEEE/RSJ International Conference. IEEE.
  9. Marion, G. (2002). Estimacin y Prediccin del Movimiento Propio en Escenas de Interior mediante Filtros Kalman. Master's thesis, Valladolid.
  10. Mazo, M. and et al (2002). Experiences in assisted mobility: The siamo project. In Proc. IEEE Intl Conf on Control Applications (Anchorage, Alaska), pages 766-771. IEEE.
  11. P. Trahanias, M. Lourakis, A. A. and Orphanoudakis, S. C. (1997). Navigational support for robotic wheelchair platforms. In Proc. ICRA-IEEE. IEEE.
  12. R. Simpson, E. LoPresti, S. H. and Nourbakhsh, I. (2004). The smart wheelchair component system. J. of Rehabilitation Research and Development, 41:429-442.
  13. Toedemé, M. Nuttin, N. T. and Gool, K. V. (2004). Vision based intelligent wheelchair control: the role of vision and inertial sensing in topological navigation. J. of Robotic Systems, 21(2):85-94.
  14. Yanco, H. A. (1998). Integrating robotic research: a survey of robotic wheelchair development. In AAAI Spring Symp. on Integrating Robotic Research (Stanford, CA). IEEE.
  15. Yuki, O. (2000). Corridor Navigation of a Mobile Robot using a camera and sensors-multiagent approach. Thesis, UCLA University, Los Angeles, CA.
Download


Paper Citation


in Harvard Style

Fuentes L., Gonzalo-Tasis M., Bermudez G. and Finat J. (2006). A DIFFERENTIAL GEOMETRIC APPROACH FOR VISUAL NAVIGATION IN INDOOR SCENES . In Proceedings of the First International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, ISBN 972-8865-40-6, pages 468-476. DOI: 10.5220/0001378104680476


in Bibtex Style

@conference{visapp06,
author={L. Fuentes and M. Gonzalo-Tasis and G. Bermudez and J. Finat},
title={A DIFFERENTIAL GEOMETRIC APPROACH FOR VISUAL NAVIGATION IN INDOOR SCENES},
booktitle={Proceedings of the First International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP,},
year={2006},
pages={468-476},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0001378104680476},
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 - A DIFFERENTIAL GEOMETRIC APPROACH FOR VISUAL NAVIGATION IN INDOOR SCENES
SN - 972-8865-40-6
AU - Fuentes L.
AU - Gonzalo-Tasis M.
AU - Bermudez G.
AU - Finat J.
PY - 2006
SP - 468
EP - 476
DO - 10.5220/0001378104680476