Spatial motion patterns: action models from semi-dense trajectories
| Autor: | Ngoc-Son Vu, Thanh Phuong Nguyen, Antoine Manzanera, Matthieu Garrigues |
|---|---|
| Přispěvatelé: | Robotique et Vision (RV), Unité d'Informatique et d'Ingénierie des Systèmes (U2IS), École Nationale Supérieure de Techniques Avancées (ENSTA Paris)-École Nationale Supérieure de Techniques Avancées (ENSTA Paris), Equipes Traitement de l'Information et Systèmes (ETIS - UMR 8051), Ecole Nationale Supérieure de l'Electronique et de ses Applications (ENSEA)-Centre National de la Recherche Scientifique (CNRS)-CY Cergy Paris Université (CY) |
| Jazyk: | angličtina |
| Rok vydání: | 2014 |
| Předmět: |
Local binary patterns
Computation ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION 02 engineering and technology Geometric shape [INFO.INFO-DM]Computer Science [cs]/Discrete Mathematics [cs.DM] [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI] Artificial Intelligence Robustness (computer science) 020204 information systems 0202 electrical engineering electronic engineering information engineering Computer vision Block (data storage) Mathematics semi dense trajectory beam local binary pattern dynamic texture action recognition business.industry Binary pattern High-definition video [INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV] Trajectory 020201 artificial intelligence & image processing Computer Vision and Pattern Recognition Artificial intelligence business Software |
| Zdroj: | International Journal of Pattern Recognition and Artificial Intelligence International Journal of Pattern Recognition and Artificial Intelligence, World Scientific Publishing, 2014, 28 (07), pp.1460011. ⟨10.1142/S0218001414600118⟩ |
| ISSN: | 0218-0014 |
| DOI: | 10.1142/S0218001414600118⟩ |
| Popis: | International audience; 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. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|