Robust Optical Flow Model Derived From Biology

Posted 11 Nov 2009 at 01:09 UTC by steve

Optical Flow image processing algorithms have been around for a while but have yet to match the motion detection capabilities of insects. In particular current models tend to fail in real-world situations which include high-dynamic range as well as rapidly changing contrast, velocity, and acceleration. Russel Brinkworth and David O'Carroll of the University of Adelaide in Australia explain:

The extraction of accurate self-motion information from the visual world is a difficult problem that has been solved very efficiently by biological organisms utilizing non-linear processing. Previous bio-inspired models for motion detection based on a correlation mechanism have been dogged by issues that arise from their sensitivity to undesired properties of the image, such as contrast, which vary widely between images.

Brinkworth and O'Carroll have come up with a new optical flow model, described in their paper, Robust Models for Optic Flow Coding in Natural Scenes Inspired by Insect Biology (PDF format). Their new system is based on the actual neural processing pathways of the fly which could prove to be a very robust velocity estimator and accurate sensor for self-motion in robots. CC-licensed image of female Tabanus Horse Fly by flickr user Thomas Shahan.