Biologically Inspired Electronics for Micropower Vision Processing

Vision processing is a topic traditionally associated
with neurobiology; known to encode, process and
interpret visual data most effectively. For example,
the human retina; an exquisite sheet of
neurobiological wetware, is amongst the most powerful
and efficient vision processors known to mankind.
With improving integrated technologies, this has
generated considerable research interest in the
microelectronics community in a quest to develop
effective, efficient and robust vision processing
hardware with real-time capability. This book
describes the design of a bio-inspired hybrid
analogue/digital chip for centroiding, sizing and
counting of enclosed objects. This chip is the first
silicon retina capable of centroiding and sizing
multiple objects in true parallel fashion. Based on a
novel distributed architecture, this system achieves
ultra-fast and ultra-low power operation in
comparison to conventional techniques. The techniques
developed are applicable to vision and sensory
processing applications in general that require
processing of large numbers of parallel inputs,
normally presenting a computational bottleneck.

Autorentext

Dr Constandinou is the Research Officer in Bionics at theInstitute of Biomedical Engineering at Imperial College London.He received both his BEng and PhD degrees from Imperial inElectronic Engineering. His research is in integratedmicrotechnology, with emphasis on ultra-low power circuits &systems for bio-applied and bio-inspired applications.

Klappentext

Vision processing is a topic traditionally associatedwith neurobiology; known to encode, process andinterpret visual data most effectively. For example,the human retina; an exquisite sheet ofneurobiological wetware, is amongst the most powerfuland efficient vision processors known to mankind.With improving integrated technologies, this hasgenerated considerable research interest in themicroelectronics community in a quest to developeffective, efficient and robust vision processinghardware with real-time capability. This bookdescribes the design of a bio-inspired hybridanalogue/digital chip for centroiding, sizing andcounting of enclosed objects. This chip is the firstsilicon retina capable of centroiding and sizingmultiple objects in true parallel fashion. Based on anovel distributed architecture, this system achievesultra-fast and ultra-low power operation incomparison to conventional techniques. The techniquesdeveloped are applicable to vision and sensoryprocessing applications in general that requireprocessing of large numbers of parallel inputs,normally presenting a computational bottleneck.