Latest revision as of 21:24, 3 February 2021

Abstract

In artificial vision applications, such as tracking, a large amount of data captured by sensors is transferred to processors to extract information relevant for the task at hand. Smart vision sensors offer a means to reduce the computational burden of visual processing pipelines by placing more processing capabilities next to the sensor. In this work, we use a vision-chip in which a small processor with memory is located next to each photosensitive element. The architecture of this device is optimized to perform local operations. To perform a task like tracking, we implement a neuromorphic approach using a Dynamic Neural Field, which allows to segregate, memorize, and track objects. Our system, consisting of the vision-chip running the DNF, outputs only the activity that corresponds to the tracked objects. These outputs reduce the bandwidth needed to transfer information as well as further post-processing, since computation happens at the pixel level.

Original document

The different versions of the original document can be found in:

• http://dx.doi.org/10.1145/2967413.2967444

• http://dx.doi.org/10.5167/uzh-132646

• https://www.zora.uzh.ch/id/eprint/132646/1/p148-Martel.pdf

• https://core.ac.uk/display/78271216,

https://www.zora.uzh.ch/id/eprint/132646/1/p148-Martel.pdf,

https://dl.acm.org/citation.cfm?id=2967444,

https://dblp.uni-trier.de/db/conf/icdsc/icdsc2016.html#MartelS16,

https://www.zora.uzh.ch/id/eprint/132646,

https://dl.acm.org/ft_gateway.cfm?id=2967444&ftid=1785458&dwn=1,

https://academic.microsoft.com/#/detail/2513433687

• http://dl.acm.org/ft_gateway.cfm?id=2967444&ftid=1785458&dwn=1,

http://dx.doi.org/10.1145/2967413.2967444 under the license http://www.acm.org/publications/policies/copyright_policy#Background

DOIS: 10.1145/2967413.2967444 10.5167/uzh-132646