What is it about?

Target tracking against complex backgrounds and in the presence of distracters is a highly challenging task for both artificial and natural visual systems. Yet despite low resolution compound eyes and a tiny brain, many flying insects have evolved superb abilities to track objects in visual clutter. Directly inspired by recent physiological breakthroughs in understanding the insect brain, we developed an algorithm to detect, select and pursue small prey. By testing this algorithm in a virtual world against a variety of natural scenes, we demonstrate robust performance rivaling real insects and elaborate machine vision systems, yet with relatively low complexity.

Featured Image

Read the Original

This page is a summary of: Properties of neuronal facilitation that improve target tracking in natural pursuit simulations, Journal of The Royal Society Interface, June 2015, Royal Society Publishing,
DOI: 10.1098/rsif.2015.0083.
You can read the full text:

Read

Resources

Contributors

The following have contributed to this page