Pedestrian Detection and Tracking Using HOG and Oriented-LBP Features

Abstract : During the last decade, various successful human detection methods have been developed. However, most of these methods focus on finding powerful features or classifiers to obtain high detection rate. In this work we introduce a pedestrian detection and tracking system to extract and track human objectives using an on board monocular camera. The system is composed of three stages. A pedestrian detector, which is based on the non-overlap HOG feature and an Oriented LBP feature, is applied to find possible locations of humans. Then an object validation step verifies detection results and rejects false positives by using a temporal coherence condition. Finally, Kalman filtering is used to track detected pedestrians. For a 320×240 image, the implementation of the proposed system runs at about 14 frames/second, while maintaining an human detection rate similar to existing methods.
Type de document :
Communication dans un congrès
Erik Altman; Weisong Shi. 8th Network and Parallel Computing (NPC), Oct 2011, Changsha,, China. Springer, Lecture Notes in Computer Science, LNCS-6985, pp.176-184, 2011, Network and Parallel Computing. 〈10.1007/978-3-642-24403-2_15〉
Liste complète des métadonnées

Littérature citée [22 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-01593010
Contributeur : Hal Ifip <>
Soumis le : lundi 25 septembre 2017 - 16:33:21
Dernière modification le : vendredi 1 décembre 2017 - 01:09:43
Document(s) archivé(s) le : mardi 26 décembre 2017 - 14:36:44

Fichier

978-3-642-24403-2_15_Chapter.p...
Fichiers produits par l'(les) auteur(s)

Licence


Distributed under a Creative Commons Paternité 4.0 International License

Identifiants

Citation

Yingdong Ma, Xiankai Chen, George Chen. Pedestrian Detection and Tracking Using HOG and Oriented-LBP Features. Erik Altman; Weisong Shi. 8th Network and Parallel Computing (NPC), Oct 2011, Changsha,, China. Springer, Lecture Notes in Computer Science, LNCS-6985, pp.176-184, 2011, Network and Parallel Computing. 〈10.1007/978-3-642-24403-2_15〉. 〈hal-01593010〉

Partager

Métriques

Consultations de la notice

42

Téléchargements de fichiers

29