Loading...
Loading...

Go to the content (press return)

Multiresolution co-clustering for uncalibrated multiview segmentation

Author
Ventura, C.; Varas, D.; Vilaplana, V.; Giro, X.; Marques, F.
Type of activity
Journal article
Journal
Signal processing: image communication
Date of publication
2019-05-04
Volume
76
First page
151
Last page
166
DOI
10.1016/j.image.2019.04.010
Project funding
Multimodal Signal Processing and Machine Learning on Graphs
Repository
http://hdl.handle.net/2117/133018 Open in new window
https://imatge.upc.edu/web/publications/multiresolution-co-clustering-uncalibrated-multiview-segmentation Open in new window
URL
https://www.sciencedirect.com/science/article/abs/pii/S0923596518302054 Open in new window
Abstract
We propose a technique for coherently co-clustering uncalibrated views of a scene with a contour-based representation. Our work extends the previous framework, an iterative algorithm for segmenting sequences with small variations, where the partition solution space is too restrictive for scenarios where consecutive images present larger variations. To deal with a more flexible scenario, we present three main contributions. First, motion information has been considered both for region adjacency a...
Keywords
co-clustering techniques, image segmentation, multiview segmentation, object segmentation
Group of research
GPI - Image and Video Processing Group
IDEAI-UPC - Intelligent Data Science and Artificial Intelligence Research Center

Participants