Motion Models that Only Work Sometimes - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2012

Motion Models that Only Work Sometimes

Résumé

It is too often that tracking algorithms lose track of interest points in image sequences. This persistent problem is difficult because the pixels around an interest point change in appearance or move in unpredictable ways. In this paper we explore how classifying videos into categories of camera motion improves the tracking of interest points, by selecting the right specialist motion model for each video. As a proof of concept, we enumerate a small set of simple categories of camera motion and implement their corresponding specialized motion models. We evaluate the strategy of predicting the most appropriate motion model for each test sequence. Within the framework of a standard Bayesian tracking formulation, we compare this strategy to two standard motion models. Our tests on challenging real-world sequences show a significant improvement in tracking robustness, achieved with different kinds of supervision at training time.
Fichier principal
Vignette du fichier
12_garcia-cifuentes_bmvc2012_PREVIEW.pdf (2.18 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-00806098 , version 1 (29-03-2013)

Identifiants

  • HAL Id : hal-00806098 , version 1

Citer

Cristina Garcia Cifuentes, Marc Sturzel, Frédéric Jurie, Gabriel J. Brostow. Motion Models that Only Work Sometimes. British Machive Vision Conference, Sep 2012, Guildford, United Kingdom. 12 p. ⟨hal-00806098⟩
266 Consultations
405 Téléchargements

Partager

Gmail Facebook X LinkedIn More