Applications for bio-inspired visual processing algorithms

R. S.A. Brinkworth, D. C. O'Carroll

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

3 Citations (Scopus)

Abstract

The extraction of useful cues for object identification and navigation through visual scenes is technically challenging. Traditionally designed artificial systems struggle to solve this task in real time, despite utilising high-resolution cameras, sophisticated software and computers with hundreds of millions of transistors. However insects, with low-resolution eyes and small brains (less than a million neurons), are able to avoid obstacles and successfully navigate through complex surrounds during high-speed flight. By studying the underlying neuronal processes governing this remarkable ability it has been possible to reverse engineer models for biological visual processing which rival insects in image normalisation (ability to detect objects independent of environmental conditions) and fast, reliable motion detection across different scenes. These models have been implemented in both software simulations and real-world hardware.

Original languageEnglish
Title of host publication2008 23rd International Conference Image and Vision Computing New Zealand, IVCNZ
DOIs
Publication statusPublished - 2008
Externally publishedYes
Event2008 23rd International Conference Image and Vision Computing New Zealand, IVCNZ - Christchurch, New Zealand
Duration: 26 Nov 200828 Nov 2008

Publication series

Name2008 23rd International Conference Image and Vision Computing New Zealand, IVCNZ

Conference

Conference2008 23rd International Conference Image and Vision Computing New Zealand, IVCNZ
Country/TerritoryNew Zealand
CityChristchurch
Period26/11/0828/11/08

Keywords

  • Biorobotics
  • Computational models of vision
  • Computer vision
  • Image models
  • Motion estimation

Fingerprint

Dive into the research topics of 'Applications for bio-inspired visual processing algorithms'. Together they form a unique fingerprint.

Cite this