Vehicle Categorization: Parts for Speed and Accuracy

Eric Nowak 1, 2 Frédéric Jurie 1
1 LEAR - Learning and recognition in vision
GRAVIR - IMAG - Graphisme, Vision et Robotique, Inria Grenoble - Rhône-Alpes, CNRS - Centre National de la Recherche Scientifique : FR71
Abstract : In this paper we propose a framework for categorization of different types of vehicles. The difficulty comes from the high inter-class similarity and the high intra-class variability. We address this problem using a part-based recognition system. We particularly focus on the trade-off between the number of parts included in the vehicle models and the recognition rate, i.e. the trade-off between fast computation and high accuracy. We propose a high-level data transformation algorithm and a feature selection scheme adapted to hierarchical SVM classifiers to improve the performance of part-based vehicle models. We have tested the proposed framework on real data acquired by infrared surveillance cameras, and on visible images too. On the infrared dataset, with the same speedup factor of 100, our accuracy is 12% better than the standard one-versus-one SVM.
Type de document :
Communication dans un congrès
IEEE International Workshop on Visual Surveillance and Performance Evaluation of Tracking and Surveillance (VS-PETS '05), Oct 2005, Beijing, China. IEEE, pp.277--283, 2005, 〈http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=1570926〉. 〈10.1109/VSPETS.2005.1570926〉
Liste complète des métadonnées

Littérature citée [16 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/inria-00548506
Contributeur : Thoth Team <>
Soumis le : lundi 20 décembre 2010 - 09:07:28
Dernière modification le : mercredi 11 avril 2018 - 01:55:13
Document(s) archivé(s) le : lundi 21 mars 2011 - 03:05:44

Fichier

NJ05.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

Collections

Citation

Eric Nowak, Frédéric Jurie. Vehicle Categorization: Parts for Speed and Accuracy. IEEE International Workshop on Visual Surveillance and Performance Evaluation of Tracking and Surveillance (VS-PETS '05), Oct 2005, Beijing, China. IEEE, pp.277--283, 2005, 〈http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=1570926〉. 〈10.1109/VSPETS.2005.1570926〉. 〈inria-00548506〉

Partager

Métriques

Consultations de la notice

217

Téléchargements de fichiers

264