Object Recognition under Various Lighting Conditions

  • Yasushi Makihara
  • Masao Takizawa
  • Yoshiaki Shirai
  • Nobutaka Shimada
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2749)


This paper describes object recognition under various lighting conditions for a robot which finds a user-specified object and brings it to the user. The system first constructs object models under a known lighting condition. Because the lighting condition in model construction is different from that in object recognition, the system needs to transform the model’s color for the current lighting condition. The system estimates color transformation by using only one observed color of a reference object. Last the system tries to recognize a user-specified object based on the estimated lighting condition. When the system fails in recognition, it tries again by using the user’s advice. Experiments using real-world refrigerator scenes are shown.


Lighting Condition Object Recognition Target Object Reference Object Service Robot 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


  1. 1.
    Y. Takahashi et al.: Development of the mobile robot system to aid the daily life for physically handicapped. Proc. of Int. Conf. on Machine Automation 2000. (2000) 549–554Google Scholar
  2. 2.
    T. Takahashi et al.: Human-Robot Interface by verbal and Nonverbal Communication. Proc. IEEE/RSJ Int. Conf. on Intelligent Robots and Systems. (1998) 924–924Google Scholar
  3. 3.
    G. Buchsbaum, “A spatial processor model for object color perception”, J. Franklin Inst. 310. (1980)Google Scholar
  4. 4.
    J. J. McCann, J. A. Hall, and E. H. Land, “Color mondrian experiments: The study of average spectral distributions”, J. Opt. Soc. Amer., Vol. 67, No. A. (1977)Google Scholar
  5. 5.
    S. Nadimi et al.: Moving Shadow Detection Using a Physics-based Approach. Proc. of 16th Int. Conf. on Pattern Recognition. Vol. 2. (2002) 701–706Google Scholar
  6. 6.
    D. H. Marimont and B. A. Wandell, “Linear models of surface and illuminant spectra”, J. Opt. Soc. Amer., Vol. 11. (1992)Google Scholar
  7. 7.
    Mark S. Drew, J. Wei, and Ze-Nian Li, “Illumination-invariant image retrieval and video segmentation”, Pattern Recognition, Vol. 32. (1999) 1369–1388CrossRefGoogle Scholar
  8. 8.
    Mark S. Drew, Ze-Nian Li, and Zinovi Tauber, “Illumination color covariant locale-based visual object retrieval”, Patter Recognition, Vol. 35, No. 8. (2002) 1687–1704zbMATHCrossRefGoogle Scholar
  9. 9.
    E. G. Miller et al.: Color Eigenflows: Statistical Modeling of Joint Color Changes. Proc. of 8th Int. Conf. on Computer Vision. Vol. 1. (2001) 607–614Google Scholar
  10. 10.
    Y. Makihara et al: A Service Robot Acting by occasional Dialog-Object Recognition Using Dialog with User and Sensor-Based Manipulation-. J. of Robotics and Mechatronics, Vol. 14, No. 2. (2002) 124–132Google Scholar
  11. 11.
    Y. Shirai: Three-Dimensional Computer Vision. Springer-Verlag. (1987) 62–68Google Scholar
  12. 12.
    Y. Makihara et al: Object Recognition Supported by User Interaction for Service Robots. Proc. of 16th Int. Conf. on Pattern Recognition. Vol. 3. (2002) 561–564Google Scholar
  13. 13.
    D. B. Judd et al.: Spectral distribution of typical daylight as a function of correlated color temperature. J. Opt. Soc. Am. Vol. 54. (1964) 1031–1040CrossRefGoogle Scholar
  14. 14.
    J. Cohen, “Dependency of the spectral reflectance curves of the Munsell color chips”, Psychonomical Science, Vol. 1. (1964) 369–370Google Scholar
  15. 15.
    Y. Makihara et al: Object Recognition Supported by User Interaction for Service Robots. Proc. of 5th Asian Conf. on Computer Vision. Vol. 2. (2002) 719–724Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2003

Authors and Affiliations

  • Yasushi Makihara
    • 1
  • Masao Takizawa
    • 2
  • Yoshiaki Shirai
    • 1
  • Nobutaka Shimada
    • 1
  1. 1.Osaka UniversitySuita, OsakaJapan
  2. 2.Minato Medical Science Inc.Sasayama, HyogoJapan

Personalised recommendations