ENGLISH
La vitrine de diffusion des publications et contributions des chercheurs de l'ÉTS
RECHERCHER

Spatio-temporal fusion for learning of regions of interests over multiple video streams

Téléchargements

Téléchargements par mois depuis la dernière année

Plus de statistiques...

Khoshrou, Samaneh et Cardoso, Jaime S. et Granger, Eric et Teixeira, Luis F.. 2015. « Spatio-temporal fusion for learning of regions of interests over multiple video streams ». In Advances in Visual Computing : 11th International Symposium, ISVC 2015, Las Vegas, NV, USA, December 14-16, 2015, Proceedings, Part II (Las Vegas, NV, USA, Dec. 14-16, 2015) Coll. « Lecture Notes in Computer Science », vol. 9475. , p. 509-520. Springer Verlag.

[img]
Prévisualisation
PDF
Spatio-temporal-fusion-for-learning-of-regions-of-interests-over-multiple-video-streams.pdf

Télécharger (921kB) | Prévisualisation

Résumé

Video surveillance systems must process and manage a growing amount of data captured over a network of cameras for various recognition tasks. In order to limit human labour and error, this paper presents a spatial-temporal fusion approach to accurately combine information from Region of Interest (RoI) batches captured in a multi-camera surveillance scenario. In this paper, feature-level and score-level approaches are proposed for spatial-temporal fusion of information to combine information over frames, in a framework based on ensembles of GMMUBM (Universal Background Models). At the feature-level, features in a batch of multiple frames are combined and fed to the ensemble, whereas at the score-level the outcome of ensemble for individual frames are combined. Results indicate that feature-level fusion provides higher level of accuracy in a very efficient way.

Type de document: Compte rendu de conférence
Professeur:
Professeur
Granger, Éric
Affiliation: Génie de la production automatisée
Date de dépôt: 28 janv. 2016 19:43
Dernière modification: 17 août 2016 19:21
URI: http://espace2.etsmtl.ca/id/eprint/12175

Actions (Authentification requise)

Dernière vérification avant le dépôt Dernière vérification avant le dépôt