INVESTIGADORES
PASTORE Juan Ignacio
congresos y reuniones científicas
Título:
Real-Time Pupil-Tracking Embedded-System based on Neural Networks
Autor/es:
CRISTIAN ORDOÑEZ; EDUARDO BLOTTA; JUAN IGNACIO PASTORE; LUCÍA DAI PARA; LUCÍA ISABEL PASSONI
Lugar:
Mar del Plata
Reunión:
Congreso; XVII Reunión de trabajo en Procesamiento de la Información y Control - RPIC 2017; 2017
Institución organizadora:
Instituto de Investigaciones Científicas y Tecnológicas en Electrónica ICYTE-CONICET
Resumen:
This paper proposes a low-cost video-based RealTime Pupil-Tracking embedded system which will allow people with reduced mobility to control a wheelchair through their eyes.The main aspect of the method is its capacity to be implemented in a portable computing system, reduced both in computing power and in RAM memory. The Pupil-Tracking system is based on Feedforward Neural Networks -using offline training-, and in the ?dark pupil effect?. The performance of the method was validated using an own database, built under different ambient lighting conditions.