Tracking the Invisible: Learning Where the Object Might be

Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F10%3A00175500" target="_blank" >RIV/68407700:21230/10:00175500 - isvavai.cz</a>
Result on the web
—
DOI - Digital Object Identifier
—

Result language
angličtina
Original language name
Tracking the Invisible: Learning Where the Object Might be
Original language description
Objects are usually embedded into context. Visual context has been successfully used in object detection tasks, however, it is often ignored in object tracking. We propose a method to learn supporters which are, be it only temporally, useful for determining the position of the object of interest. Our approach exploits the General Hough Transform strategy. It couples the supporters with the target and naturally distinguishes between strongly and weakly coupled motions. By this, the position of an objectcan be estimated even when it is not seen directly (e.g., fully occluded or outside of the image region) or when it changes its appearance quickly and significantly. Experiments show substantial improvements in model-free tracking as well as in the tracking of virtual points, e.g., in medical applications.
Czech name
—
Czech description
—

Project
<a href="/en/project/7E10045" target="_blank" >7E10045: Massive Sets of Heuristics for Machine Learning</a><br>
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)<br>R - Projekt Ramcoveho programu EK

Publication year
2010
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection
CVPR 2010: Proceedings of the 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition
ISBN
978-1-4244-6984-0
ISSN
1063-6919
e-ISSN
—
Number of pages
8
Pages from-to
—
Publisher name
Omnipress
Place of publication
Madison
Event location
San Francisco
Event date
Jun 13, 2010
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
000287417501042

Similar results(10)