Header

UZH-Logo

Maintenance Infos

A real-time event-based selective attention system for active vision


Sonnleithner, D; Indiveri, G (2012). A real-time event-based selective attention system for active vision. In: Rückert, Ulrich; Sitte, Joaquin; Werner, Felix. Advances in Autonomous Mini Robots. Berlin, Germany: Proceedings of the 6-th AMiRE Symposium, 205-219.

Abstract

In real world scenarios, guiding vision to focus on salient parts of the visual space is a computationally demanding tasks. Selective attention is a biologi- cally inspired strategy to cope with this problem, that can be used in engineered systems with limited resources. In active vision systems however, the stringent real- time requirements limit the space of solutions that can be achieved with conven- tional machine vision techniques and systems. We propose a hybrid approach where we combine a custom neuromorphic VLSI saliency-map based attention system with a conventional machine vision system, to implement both fast contrast-based saccadic eye movements in parallel with conventional visual attention models that use high-resolution color input images. We describe the system and characterize its response properties with experiments using both basic control visual stimuli and natural scenes.

Abstract

In real world scenarios, guiding vision to focus on salient parts of the visual space is a computationally demanding tasks. Selective attention is a biologi- cally inspired strategy to cope with this problem, that can be used in engineered systems with limited resources. In active vision systems however, the stringent real- time requirements limit the space of solutions that can be achieved with conven- tional machine vision techniques and systems. We propose a hybrid approach where we combine a custom neuromorphic VLSI saliency-map based attention system with a conventional machine vision system, to implement both fast contrast-based saccadic eye movements in parallel with conventional visual attention models that use high-resolution color input images. We describe the system and characterize its response properties with experiments using both basic control visual stimuli and natural scenes.

Statistics

Citations

Altmetrics

Additional indexing

Item Type:Book Section, not refereed, original work
Communities & Collections:07 Faculty of Science > Institute of Neuroinformatics
Dewey Decimal Classification:570 Life sciences; biology
Language:English
Date:May 2012
Deposited On:06 Mar 2013 08:24
Last Modified:05 Apr 2016 16:37
Publisher:Proceedings of the 6-th AMiRE Symposium
ISBN:978-3-642-27482-4
Free access at:Official URL. An embargo period may apply.
Publisher DOI:https://doi.org/10.1007/978-3-642-27482-4_21
Official URL:http://ncs.ethz.ch/pubs/pdf/Sonnleithner_Indiveri12.pdf

Download

Full text not available from this repository.
View at publisher