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

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.