Color-Based Detection Robust to Varying Illumination Spectrum
Författare
Redaktör
- Yu Sun
Summary, in English
In color-based detection methods, varying illumination
often causes problems, since an object may be perceived
to have different colors under different lighting conditions.
In the field of color constancy this is usually handled by
estimating the illumination spectrum and accounting for its
effect on the perceived color.
In this paper a method for designing a robust classifier
is presented, i.e., instead of estimating and adapting to
different lighting conditions, the classifier is made wider
to detect a colored object for a given range of lighting
conditions. This strategy also naturally handles the case
where different parts of an object are illuminated by
different light sources at the same time. Only one set of
training data per light source has to be collected, and
then the detector can handle any combination of the light
sources for a large range of illumination intensities.
often causes problems, since an object may be perceived
to have different colors under different lighting conditions.
In the field of color constancy this is usually handled by
estimating the illumination spectrum and accounting for its
effect on the perceived color.
In this paper a method for designing a robust classifier
is presented, i.e., instead of estimating and adapting to
different lighting conditions, the classifier is made wider
to detect a colored object for a given range of lighting
conditions. This strategy also naturally handles the case
where different parts of an object are illuminated by
different light sources at the same time. Only one set of
training data per light source has to be collected, and
then the detector can handle any combination of the light
sources for a large range of illumination intensities.
Avdelning/ar
Publiceringsår
2013
Språk
Engelska
Sidor
120-125
Publikation/Tidskrift/Serie
Proc. IEEE Workshop on Robot Vision (WoRV2013), January 16-17, 2013, Clearwater, FL, USA
Fulltext
Dokumenttyp
Konferensbidrag
Förlag
IEEE - Institute of Electrical and Electronics Engineers Inc.
Ämne
- Control Engineering
Nyckelord
- Color-based detection
- Color constancy
- Robust classifier
- Robot vision
- Ball catcher
Conference name
IEEE Workshop on Robot Vision (WoRV) 2013
Conference date
2013-01-17
Conference place
Clearwater Beach, Florida, United States
Status
Published
Projekt
- LU Robotics Laboratory
- ROSETTA
Forskningsgrupp
- LCCC