Loading...
Loading...

Go to the content (press return)

MSClique: Multiple structure discovery through the maximum weighted clique problem

Author
Sanromà, G.; Peñate, A.; Alquezar, R.; Serratosa, F.; Moreno-Noguer, F.; Andrade-Cetto, J.; González Ballester, Miguel A.
Type of activity
Journal article
Journal
PloS one
Date of publication
2016-01-01
Volume
11
Number
1
DOI
https://doi.org/10.1371/journal.pone.0145846 Open in new window
Project funding
Aerial robotic system integrating multiple arms and advanced manipulation capabilities for inspection and maintenance
Perception and Action in Robotics Problems with Large State Spaces DPI2011-27510 National Project
RobInstruct: Instructing robots using natural communication skills - TIN2014-58178-R
Robot-Human interaction, learning and cooperation in urban areas
Visual Sense, Tagging visual data with semantic descriptions PCIN-2013-047
Repository
http://hdl.handle.net/2117/84927 Open in new window
URL
http://journals.plos.org/plosone/article?id=10.1371/journal.pone.0145846 Open in new window
Abstract
We present a novel approach for feature correspondence and multiple structure discovery in computer vision. In contrast to existing methods, we exploit the fact that point-sets on the same structure usually lie close to each other, thus forming clusters in the image. Given a pair of input images, we initially extract points of interest and extract hierarchical representations by agglomerative clustering. We use the maximum weighted clique problem to find the set of corresponding clusters with ma...
Citation
Sanromà, G., Peñate, A., Alquézar, R., Serratosa, F., Moreno-Noguer, F., Andrade-Cetto, J., González-Ballester, M.A. MSClique: Multiple structure discovery through the maximum weighted clique problem. "PLoS one", 01 Gener 2016, vol. 11, núm. 1.
Group of research
ROBiri - IRI Robotics Group
VIS - Artificial Vision and Intelligent Systems

Participants

Attachments