HMM-based gait modeling and recognition under different walking scenarios

Abstract : This paper addresses gait recognition, the problem of identifying people by the way of their walk. The proposed system consists of a model-free approach which extracts features directly from the human silhouette. The dynamics of the gait are modeled using Hidden Markov Models. Experiments have been carried out on the CASIA dataset C consisting of 153 people under four walking scenarios: normal walking, slow walking, fast walking and walking while carrying a bag. The results obtained are promising and compare favorably with existing approaches
Type de document :
Communication dans un congrès
ICMCS 2011 : 2nd International Conference on Multimedia Computing and Systems, Apr 2011, Ouarzazate Morocco. IEEE, Proceedings ICMCS 2011 : 2nd International Conference on Multimedia Computing and Systems, pp.1 - 5, 2011, 〈10.1109/ICMCS.2011.5945573〉
Liste complète des métadonnées

https://hal.archives-ouvertes.fr/hal-01302472
Contributeur : Médiathèque Télécom Sudparis & Institut Mines-Télécom Business School <>
Soumis le : jeudi 14 avril 2016 - 13:53:02
Dernière modification le : lundi 12 novembre 2018 - 10:54:27

Identifiants

Citation

Mounim El Yacoubi, Ayet Shaiek, Bernadette Dorizzi. HMM-based gait modeling and recognition under different walking scenarios. ICMCS 2011 : 2nd International Conference on Multimedia Computing and Systems, Apr 2011, Ouarzazate Morocco. IEEE, Proceedings ICMCS 2011 : 2nd International Conference on Multimedia Computing and Systems, pp.1 - 5, 2011, 〈10.1109/ICMCS.2011.5945573〉. 〈hal-01302472〉

Partager

Métriques

Consultations de la notice

117