Ayuda
Ir al contenido

Dialnet


Nat: a robot that recognizes offices

  • Aleix Martínez [1] ; Sergio González [1] ; Jordi Vitrià [1] ; Jaime López Krahe [2]
    1. [1] Universitat Autònoma de Barcelona

      Universitat Autònoma de Barcelona

      Barcelona, España

    2. [2] Université Paris
  • Localización: CAEPIA'97: actas / coord. por Asociación Española de Inteligencia Artificial, Vicente J. Botti Navarro, 1997, ISBN 84-8498-765-5, págs. 327-336
  • Idioma: inglés
  • Texto completo no disponible (Saber más ...)
  • Resumen
    • In this paper we present a novel technique to implement a complex visual behaviour: to look for where I am. The method is based on an active vision system which allows us to build real-time applications. To define this behaviour, visual scanning is used. That is: (i) a focus of attention mechanism which selects the most important visual areas to be analysed, (ii) an iconic representation based on gaussian filters (i.e. pattern matching), (iii) a dimensionality reduction criteria that allows us to reduce the complexity of the pattern matching process, and (iv) a scanning strategy. This implementation shows how complex information processing tasks can be solved by using active visual behaviour based on simple mechanisms.


Fundación Dialnet

Dialnet Plus

  • Más información sobre Dialnet Plus

Opciones de compartir

Opciones de entorno