Outdoor scene classification is challenging due to irregular geometry, uncontrolled illumination, and noisy reflectance distributions. This paper discusses a Bayesian approach to classifying a color image of an outdoor scene. A likelihood model factors in the physics of the image formation process, sensor noise distribution, and prior distributions over geometry, material types, and illuminant spectrum parameters. These prior distributions are learned through a training process that uses color observations of planar scene patches over time. An iterative linear algorithm estimates the maximum likelihood reflectance, spectrum, geometry, and object class labels for a new image. Experiments on images taken by outdoor surveillance cameras classify known material types and shadow regions correctly, and flag as outliers material types that were not seen previously.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Bayesian color constancy for outdoor object recognition


    Contributors:
    Yanghai Tsin, (author) / Collins, R.T. (author) / Ramesh, V. (author) / Kanade, T. (author)


    Publication date :

    2001-01-01


    Size :

    864748 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Bayesian Color Constancy for Outdoor Object Recognition

    Tsin, Y. / Collins, R. T. / Ramesh, V. et al. | British Library Conference Proceedings | 2001


    Color constancy for landmark detection in outdoor environments

    Todt, Eduardo / Torras, Carme | BASE | 2001

    Free access

    Bootstrapping color constancy

    Funt, B. V. / Cardei, V. C. / SPIE et al. | British Library Conference Proceedings | 1999



    Bayesian Decision Theory, the Maximum Local Mass Estimate, and Color Constancy

    Freeman, W. / Brainard, D. / IEEE Computer Society et al. | British Library Conference Proceedings | 1995