Answers are grounded in this paper and cite their sources.
We present a vision sensor chip designed to detect multiple transient objects - objects that either move or change in light intensity - and output their locations using address-event representation. The sensor uses a novel onset detector to detect transient objects and a dynamically-wired winner-takes-all circuit to group pixels and select the brightest pixel in each object. This paper describes the circuits and also presents measurements that characterize the performance of the sensor chip.
No takes yet. Share an insight, caveat, or question.
Chan et al. (2007) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: