Robust Motion Segmentation from Pairwise Matches
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21730%2F19%3A00337354" target="_blank" >RIV/68407700:21730/19:00337354 - isvavai.cz</a>
Result on the web
<a href="https://arxiv.org/abs/1905.09043" target="_blank" >https://arxiv.org/abs/1905.09043</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1109/ICCV.2019.00076" target="_blank" >10.1109/ICCV.2019.00076</a>
Alternative languages
Result language
angličtina
Original language name
Robust Motion Segmentation from Pairwise Matches
Original language description
In this paper we address a classification problem that has not been considered before, namely motion segmentation given pairwise matches only. Our contribution to this unexplored task is a novel formulation of motion segmentation as a two-step process. First, motion segmentation is performed on image pairs independently. Secondly, we combine independent pairwise segmentation results in a robust way into the final globally consistent segmentation. Our approach is inspired by the success of averaging methods. We demonstrate in simulated as well as in real experiments that our method is very effective in reducing the errors in the pairwise motion segmentation and can cope with large number of mismatches.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
—
OECD FORD branch
10102 - Applied mathematics
Result continuities
Project
<a href="/en/project/EF15_003%2F0000468" target="_blank" >EF15_003/0000468: Intelligent Machine Perception</a><br>
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)
Others
Publication year
2019
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
2019 IEEE International Conference on Computer Vision (ICCV 2019)
ISBN
978-1-7281-4804-5
ISSN
1550-5499
e-ISSN
2380-7504
Number of pages
11
Pages from-to
671-681
Publisher name
IEEE Computer Society Press
Place of publication
Los Alamitos
Event location
Seoul
Event date
Oct 27, 2019
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
000531438100068