Campus Event Calendar
Event Entry
What and Who
Invariance with optic flow
Yana Mileva
IMPRS-CS
Talk
AG 1, AG 2, AG 3, AG 4, AG 5, SWS
AG Audience
English
Note: We use this to send email in the morning.
Date, Time and Location
Monday, 2 July 2007
09:00
240 Minutes
E1 4
024
Saarbrücken
Abstract
Under optic flow in computer vision we understand the displacement field between two consecutive frames of a given image sequence. One of the most accurate techniques developed so far for the computation of this flow field are the so-called variational methods. These methods are based on imposing constancy over some of the image features and minimizing an energy functional. Most of the effort is directed towards finding better data and smoothness terms for this energy functional. Usually people are working with black-and-white image sequences. In our research we will consider only color images, as we believe that the color itself carries much more information than the gray value and can help us for the better estimation of the motion. So far most of the research done in optic flow computation does not consider the presence of realistic illumination changes in the image sequences. One of our main goals is to find new constancy assumptions for the data term, which overcome the problems of severe illumination changes. We will introduce a new variational methods framework that combines several constancy assumption into a successful optic flow computation technique.
Contact
IMPRS
225
--email hidden
passcode not visible
logged in users only
Jennifer Gerling, 06/29/2007 13:50
Lourdes Lara-Tapia, 06/27/2007 15:35
Lourdes Lara-Tapia, 06/18/2007 16:01 -- Created document.
Lourdes Lara-Tapia, 06/27/2007 15:35
Lourdes Lara-Tapia, 06/18/2007 16:01 -- Created document.