Alignement paramétrique d'images : proposition d'un formalisme unifié et prise en compte du bruit pour le suivi d'objets

Abstract : Parametric image alignment is a fundamental task of many vision applications such as object tracking, image mosaicking, video compression and augmented reality. To recover the motion parameters, direct image alignment works by optimizing a pixel-based difference measure between a moving image and a fixed-image called template. In the last decade, many efficient algorithms have been proposed for parametric object tracking. However, those approaches have not been evaluated for aligning images of low SNR (Signal to Noise ratio) such as images captured in low-light conditions. In this thesis, we propose a new formulation of image alignment called Bidirectional Framework for unifying existing state of the art algorithms. First, this framework allows us to produce new insights on existing approaches and in particular on the ESM (Efficient Second-order Minimization) algorithm. Subsequently, we provide a theoretical analysis of image noise on the alignment process. This yields the definition of two new approaches : the ACL (Asymmetric Composition on Lie Groups) algorithm and the BCL (Bidirectional Composition on Lie Groups) algorithm, which outperform existing approaches in presence of images of different SNR. Finally, experiments on synthetic and real images captured under low-light conditions allow to evaluate the new and existing approaches under various noise conditions.
Complete list of metadatas

Cited literature [87 references]  Display  Hide  Download

https://tel.archives-ouvertes.fr/tel-00672589
Contributor : Rémi Megret <>
Submitted on : Tuesday, February 21, 2012 - 3:03:54 PM
Last modification on : Thursday, January 11, 2018 - 6:21:08 AM
Long-term archiving on : Tuesday, May 22, 2012 - 2:55:27 AM

Identifiers

  • HAL Id : tel-00672589, version 1

Citation

Jean-Baptiste Authesserre. Alignement paramétrique d'images : proposition d'un formalisme unifié et prise en compte du bruit pour le suivi d'objets. Traitement du signal et de l'image [eess.SP]. Université Sciences et Technologies - Bordeaux I, 2010. Français. ⟨tel-00672589⟩

Share

Metrics

Record views

242

Files downloads

612