Learning Efficient Linear Predictors for Motion Estimation
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F06%3A00124649" target="_blank" >RIV/68407700:21230/06:00124649 - isvavai.cz</a>
Result on the web
—
DOI - Digital Object Identifier
—
Alternative languages
Result language
angličtina
Original language name
Learning Efficient Linear Predictors for Motion Estimation
Original language description
A novel object representation for tracking is proposed. The tracked object is represented as a constellation of spatially localised linear predictors which are learned on a single training image. In the learning stage, sets of pixels whose intensities allow for optimal least square predictions of the transformations are selected as a support of the linear predictor. The approach comprises three contributions: learning object specific linear predictors, explicitly dealing with the predictor precision - computational complexity trade-off and selecting a view-specific set of predictors suitable for global object motion estimate. Robustness to occlusion is achieved by RANSAC procedure. The learned tracker is very efficient, achieving frame rate generally higher than 30 frames per second despite the Matlab implementation.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
JD - Use of computers, robotics and its application
OECD FORD branch
—
Result continuities
Project
Result was created during the realization of more than one project. More information in the Projects tab.
Continuities
S - Specificky vyzkum na vysokych skolach<br>R - Projekt Ramcoveho programu EK<br>V - Vyzkumna aktivita podporovana z jinych verejnych zdroju
Others
Publication year
2006
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
Proceedings of 5th Indian Conference on Computer Vision, Graphics and Image Processing
ISBN
978-3-540-68301-8
ISSN
0302-9743
e-ISSN
—
Number of pages
12
Pages from-to
—
Publisher name
Springer
Place of publication
Berlin
Event location
Madurai
Event date
Dec 13, 2006
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
000244671700040