Bayesian color constancy for outdoor object recognition

Yanghai Tsin, R.T. Collins, V. Ramesh, T. Kanade
Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001  
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, the 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
more » ... or 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.
doi:10.1109/cvpr.2001.990658 dblp:conf/cvpr/TsinCRK01 fatcat:jxcu42swabayplubjqyyg6ik2q