Repositorio de producción científica de la Universidad de Sevilla

Neuromorphic Real-Time Objects Tracking Using Address Event Representation and Silicon Retina

Opened Access Neuromorphic Real-Time Objects Tracking Using Address Event Representation and Silicon Retina

Citas

buscar en

Estadísticas
Icon
Exportar a
Autor: Gómez Rodríguez, Francisco de Asís
Miró Amarante, María Lourdes
Rivas Pérez, Manuel
Jiménez Moreno, Gabriel
Díaz del Río, Fernando
Departamento: Universidad de Sevilla. Departamento de Arquitectura y Tecnología de Computadores
Fecha: 2011
Publicado en: IWANN 2011: 11th International Work-Conference on Artificial Neural Networks (2011), p 133-140
ISBN/ISSN: 978-3-642-21500-1
Tipo de documento: Ponencia
Resumen: This paper presents a hierarchical neuromorphic system for tracking objects. We use AER (Address Event Representation) for transmitting and processing visual information provided by an asynchronous temporal contrast silicon retina. Two AER processing layers work in cascade for firstly detecting different objects, and secondly tracking them even with crossing trajectories. The output of the system offers not only the position of the tracked object but also the speed in pixels per second. The system is fully hardware implemented on FPGA (Spartan II 200), which is part of the USB-AER platform developed in part by authors. A 97.2% of the Spartan II is used for 128x128 pixels input resolution and 6 maximum objects recognition and tracking.
Cita: Gómez Rodríguez, F.d.A., Miró Amarante, M.L., Rivas Pérez, M., Jiménez Moreno, G. y Díaz del Río, F. (2011). Neuromorphic Real-Time Objects Tracking Using Address Event Representation and Silicon Retina. En IWANN 2011: 11th International Work-Conference on Artificial Neural Networks (133-140), Torremolinos, Málaga, España: Springer.
Tamaño: 582.0Kb
Formato: PDF

URI: https://hdl.handle.net/11441/70398

DOI: 10.1007/978-3-642-21501-8_17

Ver versión del editor

Mostrar el registro completo del ítem


Esta obra está bajo una Licencia Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 Internacional

Este registro aparece en las siguientes colecciones