Authors:
Marc Ebner
and
Johannes Hansen
Affiliation:
Ernst-Moritz-Arndt-Universität Greifswald and Institut für Mathematik und Informatik, Germany
Keyword(s):
Color Constancy, Space Average Color, Depth Map, Color, Kinect.
Related
Ontology
Subjects/Areas/Topics:
Applications and Services
;
Biomedical Engineering
;
Biomedical Signal Processing
;
Computer Vision, Visualization and Computer Graphics
;
Medical Image Detection, Acquisition, Analysis and Processing
Abstract:
A human observer is able to judge the color of objects independent of the illuminant. In contrast, a digital sensor
(or the retinal receptors for that matter) only measure reflected light which varies with the illuminant. The
brain is somehow able to compute a color constant descriptor from the light falling onto the retina. We have
improved a well known color constancy algorithm based on local space average color. This color constancy
algorithm can be mapped to the different visual processing stages of the human brain. We have extended this
algorithm by incorporating depth information. The idea is that wherever there are depth discontinuities there
may also be a change of the illuminant in the image. Hence, depth discontinuities are used to separate different
illuminants. This allows us to better estimate the local illumination and allows us to compute an improved
color constant descriptor. We also compute local space average depth to decide locally whether to average data
from reti
nal sensors uniformly or non-uniformly. We show how our algorithm works on real world scenes.
Depth information is obtained from a standard Kinect sensor.
(More)