Advanced

Color-Based Detection Robust to Varying Illumination Spectrum

Linderoth, Magnus LU ; Robertsson, Anders LU and Johansson, Rolf LU (2013) IEEE Workshop on Robot Vision (WoRV) 2013 In [Host publication title missing] p.120-125
Abstract
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... (More)
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. (Less)
Please use this url to cite or link to this publication:
author
organization
publishing date
type
Chapter in Book/Report/Conference proceeding
publication status
published
subject
keywords
Color-based detection, Color constancy, Robust classifier, Robot vision, Ball catcher
in
[Host publication title missing]
editor
Sun, Yu
pages
6 pages
publisher
IEEE--Institute of Electrical and Electronics Engineers Inc.
conference name
IEEE Workshop on Robot Vision (WoRV) 2013
external identifiers
  • WOS:000325279400019
  • Scopus:84880299828
project
ROSETTA
language
English
LU publication?
yes
id
a19dde80-bca9-4ccb-b14f-0ae0402baae5 (old id 3349448)
date added to LUP
2013-03-27 11:05:49
date last changed
2016-10-13 04:42:57
@misc{a19dde80-bca9-4ccb-b14f-0ae0402baae5,
  abstract     = {In color-based detection methods, varying illumination<br/><br>
often causes problems, since an object may be perceived<br/><br>
to have different colors under different lighting conditions.<br/><br>
In the field of color constancy this is usually handled by<br/><br>
estimating the illumination spectrum and accounting for its<br/><br>
effect on the perceived color.<br/><br>
<br/><br>
In this paper a method for designing a robust classifier<br/><br>
is presented, i.e., instead of estimating and adapting to<br/><br>
different lighting conditions, the classifier is made wider<br/><br>
to detect a colored object for a given range of lighting<br/><br>
conditions. This strategy also naturally handles the case<br/><br>
where different parts of an object are illuminated by<br/><br>
different light sources at the same time. Only one set of<br/><br>
training data per light source has to be collected, and<br/><br>
then the detector can handle any combination of the light<br/><br>
sources for a large range of illumination intensities.},
  author       = {Linderoth, Magnus and Robertsson, Anders and Johansson, Rolf},
  editor       = {Sun, Yu},
  keyword      = {Color-based detection,Color constancy,Robust classifier,Robot vision,Ball catcher},
  language     = {eng},
  pages        = {120--125},
  publisher    = {ARRAY(0x8350250)},
  series       = {[Host publication title missing]},
  title        = {Color-Based Detection Robust to Varying Illumination Spectrum},
  year         = {2013},
}