Loading...
Loading...

Go to the content (press return)

Region based foreground segmentation combining color and depth sensors via logarithmic opinion pool decision

Author
Gallego, J.; Pardas, M.
Type of activity
Journal article
Journal
Journal of visual communication and image representation
Date of publication
2013-04-01
Volume
25
Number
1
First page
184
Last page
194
DOI
https://doi.org/10.1016/j.jvcir.2013.03.019 Open in new window
Repository
http://hdl.handle.net/2117/21045 Open in new window
URL
http://www.sciencedirect.com/science/article/pii/S104732031300059X# Open in new window
Abstract
In this paper we present a novel foreground segmentation system that combines color and depth sensors information to perform a more complete Bayesian segmentation between foreground and background classes. The system shows a combination of spatial-color and spatial-depth region-based models for the foreground as well as color and depth pixel-wise models for the background in a Logarithmic Opinion Pool decision framework used to correctly combine the likelihoods of each model. A posterior enhance...
Citation
Gallego, J.; Pardas, M. Region based foreground segmentation combining color and depth sensors via logarithmic opinion pool decision. "Journal of visual communication and image representation", 01 Abril 2013, vol. 25, núm. 1, p. 184-194.
Keywords
Color and depth combination, Foreground segmentation, GMM, Hellinger distance, Kinect camera, Logarithmic Opinion Pool, Space-color models, Space-depth models
Group of research
GPI - Image and Video Processing Group
IDEAI-UPC - Intelligent Data Science and Artificial Intelligence Research Center

Participants