Observatorio de I+D+i UPM

Descripción
A neural behavior initiating agent (BIA) is proposed to integrate relevant compressed image information coming from others cooperating and specialized neural agents. Using this arrangement the problem of tracking and recognizing a moving icon has been solved by partitioning it into three simpler and separated tasks. Neural agents associated to those tasks proved to be easier to train and show a good general performance. The obtained neural controller can handle spurious images and solve an acute image related task in a dynamical environment. Under prolonged dead-lock conditions the controller shows traces of genuine spontaneity. The overall performance has been tested using a pan and tilt camera platform and real images taken from several objects, showing the good tracking results discussed in the paper.
Internacional	Si
Nombre congreso	IJCNN, Internacional Join Conference on Neural Networks
Tipo de participación	960
Lugar del congreso	Barcelona_SPAIN
Revisores	Si
ISBN o ISSN	978-1-4244-6917-8
DOI
Fecha inicio congreso	17/07/2010
Fecha fin congreso	23/07/2010
Desde la página	420
Hasta la página	425
Título de las actas	IJCNN, Internacional Join Conference on Neural Networks

Esta actividad pertenece a memorias de investigación

• Autor: Oscar Chang Tortolero (UPM)
• Autor: Pascual Campoy Cervera (UPM)
• Autor: Carol Viviana Martinez Luna (UPM)
• Autor: Miguel Ángel Olivares Mendez (UPM)

• Creador: Grupo de Investigación: Computer Vision
• Centro o Instituto I+D+i: Centro de Automática y Robótica (CAR). Centro Mixto UPM-CSIC
• Departamento: Automática, Ingeniería Electrónica e Informática Industrial