A Projective Framework for Scene Segmentation in the Presence of Moving Objects

David Demirdjian 1 Radu Horaud 1
1 MOVI - Modeling, localization, recognition and interpretation in computer vision
GRAVIR - IMAG - Graphisme, Vision et Robotique, Inria Grenoble - Rhône-Alpes, CNRS - Centre National de la Recherche Scientifique : FR71
Abstract : Given a sequence of pairs of images gathered with an uncalibrated stereo camera pair and given a set of point-to-point correspondences between, these image pairs, we describe a method that segments the observed scene into static and moving objects while it rejects badly matched points. Unlike many approaches which were suggested in the past, the method allows for both motion of the camera pair (egomotion) and non rigid scenes (scenes composed of static objects as well as objects undergoing various motions). First we establish the projective framework enabling us to characterize rigid motion in projective space. Second we use this characterization in conjunction with a robust estimation technique to determine egomotion. Third we describe a method based on data classification which further considers the non-static scene points anal groups them into several moving objects. Finally we show some preliminary experiments involving a moving stereo head observing both static and moving objects.
Document type :
Conference papers
Complete list of metadatas

https://hal.inria.fr/inria-00590114
Contributor : Team Perception <>
Submitted on : Tuesday, May 3, 2011 - 9:22:54 AM
Last modification on : Wednesday, April 11, 2018 - 1:56:00 AM
Long-term archiving on : Thursday, August 4, 2011 - 2:55:33 AM

Files

David-cvpr99.pdf
Files produced by the author(s)

Identifiers

Collections

IMAG | INRIA | UGA

Citation

David Demirdjian, Radu Horaud. A Projective Framework for Scene Segmentation in the Presence of Moving Objects. IEEE Conference on Computer Vision and Pattern Recognition (CVPR '99), Jun 1999, Fort Collins, United States. pp.2--8, ⟨10.1109/CVPR.1999.786909⟩. ⟨inria-00590114⟩

Share

Metrics

Record views

199

Files downloads

245