Real Time Semi-dense Point Tracking - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2012

Real Time Semi-dense Point Tracking

Matthieu Garrigues
Antoine Manzanera

Résumé

This paper presents a new algorithm to track a high number of points in a video sequence in real-time. We propose a fast keypoint detector, used to create new particles, and an associated multiscale de-scriptor (feature) used to match the particles from one frame to the next. The tracking algorithm updates for each particle a series of appearance and kinematic states, that are temporally filtered. It is robust to hand held camera accelerations thanks to a coarse-to-fine dominant movement estimation. Each step is designed to reach the maximal level of data par-allelism, to target the most common parallel platforms. Using graphics processing unit, our current implementation handles 10 000 points per frame at 55 frames-per-second on 640 × 480 videos.
Fichier principal
Vignette du fichier
parallel_tracking_iciar_submitted.pdf (1.86 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01118324 , version 1 (18-02-2015)

Identifiants

Citer

Matthieu Garrigues, Antoine Manzanera. Real Time Semi-dense Point Tracking. ICIAR, 2012, Aveiro, Portugal. pp.245 - 252, ⟨10.1007/978-3-642-31295-3_29⟩. ⟨hal-01118324⟩

Collections

ENSTA ENSTA_U2IS
48 Consultations
219 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More