Faculty of Mathematics and Computer Science

Vision and Robotics Seminar

Moshe Machline

will speak on

Multi-body Segmentation: Revisiting Motion Consistency

Abstract:

Dynamic analysis of video sequences often relies on the segmentation
of the sequence into regions of consistent motions. Approaching this problem
requires a definition of which motions are regarded as consistent. Common
approaches to motion segmentation usually group together points or image
regions that have the same motion between successive frames (where the
same motion can be 2D, 3D, or non-rigid). We define a new type of
motion consistency, which is based on temporal consistency of behaviors
across multiple frames in the video sequence. Our definition of consistent
``temporal behavior" is expressed in terms of multi-frame linear subspace
constraints. This definition applies to 2D, 3D, and some non-rigid motions
without requiring prior model selection. We further present a multi-frame
multi-body segmentation algorithm which applies the new motion consistency
constraint directly to image brightness measurements, without requiring
prior correspondence estimation nor feature tracking.

This is joint work with Lihi Zelnik-Manor and Michal Irani.

The lecture will take place in the

Lecture Hall, Room 1, Ziskind Building

on Thursday, May 2, 2002

at noon