A combined probabilistic framework for learning gestures and actions


Autoria(s): Escolano Ruiz, Francisco; Cazorla, Miguel; Gallardo López, Domingo; Llorens Largo, Faraón; Satorre Cuerda, Rosana; Rizo Aldeguer, Ramón
Contribuinte(s)

Universidad de Alicante. Departamento de Ciencia de la Computación e Inteligencia Artificial

Robótica y Visión Tridimensional (RoViT)

Laboratorio de Investigación en Visión Móvil (MVRLab)

Informática Industrial e Inteligencia Artificial

Data(s)

13/07/2012

13/07/2012

1998

Resumo

In this paper we introduce a probabilistic approach to support visual supervision and gesture recognition. Task knowledge is both of geometric and visual nature and it is encoded in parametric eigenspaces. Learning processes for compute modal subspaces (eigenspaces) are the core of tracking and recognition of gestures and tasks. We describe the overall architecture of the system and detail learning processes and gesture design. Finally we show experimental results of tracking and recognition in block-world like assembling tasks and in general human gestures.

Identificador

ESCOLANO, Francisco, et al. "A combined probabilistic framework for learning gestures and actions". En: Tasks and Methods in Applied Artificial Intelligence : 11th International Conference on Industrial and Engineering Applications of Artificial Intelligence and Expert Systems IEA-98-AIE Benicàssim, Castellón, Spain, June 1–4, 1998 Proceedings, Volume II / Angel Pasqual del Pobil, José Mira, Moonis Ali (Eds.). Berlin : Springer, 1998. (Lecture Notes in Computer Science; 1416). ISBN 3-540-64574-8, pp. 658-667

3-540-64574-8

0302-9743 (Print)

1611-3349 (Online)

http://hdl.handle.net/10045/23397

10.1007/3-540-64574-8_452

Idioma(s)

eng

Publicador

Springer Berlin / Heidelberg

Relação

http://dx.doi.org/10.1007/3-540-64574-8_452

Direitos

The original publication is available at www.springerlink.com

info:eu-repo/semantics/restrictedAccess

Palavras-Chave #Visual inspection #Gesture recognition #Learning #Probabilistic constraints #Eigenmethods #Ciencia de la Computación e Inteligencia Artificial
Tipo

info:eu-repo/semantics/conferenceObject