From Video Sequences to Motion Panoramas

Adrien Bartoli 1 Navneet Dalal 1 Biswajit Bose 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 : We address the problem of constructing mosaics from video sequences taken by rotating cameras. In particular we investigate the widespread case where the scene is not only static but may also contain large dynamic areas, induced by moving or deforming objects. Most of the existing techniques fail to produce reliable results on such video sequences. For such alignment purposes, two classes of techniques may be used: feature-based and direct methods. We derive both of them in a unified statistical manner and propose an integrated framework to construct what we call motion panoramas, based on a mixed feature-based and direct approach. Experimental results are provided on large image sequences. In particular we consider sport videos where the moving and deforming athlete is visible in every frame of the sequence, thereby making the alignment task tricky.
Document type :
Conference papers
Liste complète des métadonnées

Cited literature [15 references]  Display  Hide  Download
Contributor : Adrien Bartoli <>
Submitted on : Thursday, May 26, 2011 - 2:06:20 PM
Last modification on : Thursday, February 21, 2019 - 3:02:52 PM
Document(s) archivé(s) le : Saturday, August 27, 2011 - 2:20:16 AM


Files produced by the author(s)





Adrien Bartoli, Navneet Dalal, Biswajit Bose, Radu Horaud. From Video Sequences to Motion Panoramas. Workshop on Motion and Video Computing (MOTION '02), Dec 2002, Orlando, United States. pp.201 - 207, ⟨10.1109/MOTION.2002.1182237⟩. ⟨hal-00094772⟩



Record views


Files downloads