Bayesian color constancy for outdoor object recognition

Yanghai Tsin, Robert Collins, Visvanathan Ramesh, Takeo Kanade

Research output: Contribution to journalConference articlepeer-review

35 Scopus citations

Abstract

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 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.

Original languageEnglish (US)
JournalProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Volume1
StatePublished - Dec 1 2001
Event2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Kauai, HI, United States
Duration: Dec 8 2001Dec 14 2001

All Science Journal Classification (ASJC) codes

  • Software
  • Computer Vision and Pattern Recognition

Fingerprint Dive into the research topics of 'Bayesian color constancy for outdoor object recognition'. Together they form a unique fingerprint.

Cite this