Spatial motion patterns: action models from semi-dense trajectories

Abstract : A new action model is proposed, by revisiting local binary patterns for dynamic texture models, applied on trajectory beams calculated on the video. The use of semi dense trajectory field allows to dramatically reduce the computation support to essential mo-tion information, while maintaining a large amount of data to ensure robustness of statistical bag of features action models. A new binary pattern, called Spatial Motion Pattern (SMP) is proposed, which captures self similarity of velocity around each tracked point(particle), along its trajectory. This operator highlights the geometric shape of rigid parts of moving objects in a video sequence. SMPs are combined with basic velocity in-formation to form the local action primitives. Then, a global representation of a space × time video block is provided by using hierarchical blockwise histograms, which allows to efficiently represent the action as a whole, while preserving a certain level of spa-tiotemporal relation between the action primitives. Inheriting from the efficiency and the invariance properties of both the semi dense tracker Video extruder and the LBP based representations, the method is designed for the fast computation of action descrip-tors in unconstrained videos. For improving both robustness and computation time in the case of high definition video, we also present an enhanced version of the semi dense tracker based on the so called super particles, which reduces the number of trajectories while improving their length, reliability and spatial distribution.
Type de document :
Article dans une revue
International Journal of Pattern Recognition and Artificial Intelligence, World Scientific Publishing, 2014, 28 (07), pp.1460011. 〈10.1142/S0218001414600118〉
Liste complète des métadonnées

Littérature citée [38 références]  Voir  Masquer  Télécharger

https://hal.archives-ouvertes.fr/hal-01118257
Contributeur : Thanh Phuong Nguyen <>
Soumis le : mardi 24 février 2015 - 16:20:46
Dernière modification le : mercredi 16 janvier 2019 - 01:27:38
Document(s) archivé(s) le : mardi 26 mai 2015 - 17:31:19

Fichier

IJPRAI.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

Citation

Thanh Phuong Nguyen, Antoine Manzanera, Matthieu Garrigues, Ngoc-Son Vu. Spatial motion patterns: action models from semi-dense trajectories. International Journal of Pattern Recognition and Artificial Intelligence, World Scientific Publishing, 2014, 28 (07), pp.1460011. 〈10.1142/S0218001414600118〉. 〈hal-01118257〉

Partager

Métriques

Consultations de la notice

293

Téléchargements de fichiers

180