Advanced

Performance of an insect-inspired target tracker in natural conditions

Bagheri, Zahra M; Wiederman, Steven D; Cazzolato, Benjamin S; Grainger, Steven and O'Carroll, David C. LU (2017) In Bioinspiration and Biomimetics 12(2).
Abstract

Robust and efficient target-tracking algorithms embedded on moving platforms, are a requirement for many computer vision and robotic applications. However, deployment of a real-time system is challenging, even with the computational power of modern hardware. As inspiration, we look to biological lightweight solutions-lightweight and low-powered flying insects. For example, dragonflies pursue prey and mates within cluttered, natural environments, deftly selecting their target amidst swarms. In our laboratory, we study the physiology and morphology of dragonfly 'small target motion detector' neurons likely to underlie this pursuit behaviour. Here we describe our insect-inspired tracking model derived from these data and compare its... (More)

Robust and efficient target-tracking algorithms embedded on moving platforms, are a requirement for many computer vision and robotic applications. However, deployment of a real-time system is challenging, even with the computational power of modern hardware. As inspiration, we look to biological lightweight solutions-lightweight and low-powered flying insects. For example, dragonflies pursue prey and mates within cluttered, natural environments, deftly selecting their target amidst swarms. In our laboratory, we study the physiology and morphology of dragonfly 'small target motion detector' neurons likely to underlie this pursuit behaviour. Here we describe our insect-inspired tracking model derived from these data and compare its efficacy and efficiency with state-of-the-art engineering models. For model inputs, we use both publicly available video sequences, as well as our own task-specific dataset (small targets embedded within natural scenes). In the context of the tracking problem, we describe differences in object statistics within the video sequences. For the general dataset, our model often locks on to small components of larger objects, tracking these moving features. When input imagery includes small moving targets, for which our highly nonlinear filtering is matched, the robustness outperforms state-of-the-art trackers. In all scenarios, our insect-inspired tracker runs at least twice the speed of the comparison algorithms.

(Less)
Please use this url to cite or link to this publication:
author
organization
publishing date
type
Contribution to journal
publication status
published
subject
keywords
bio-inspired vision, real-time, visual target tracking
in
Bioinspiration and Biomimetics
volume
12
issue
2
publisher
IOP Publishing
external identifiers
  • scopus:85017111224
  • wos:000395902300001
ISSN
1748-3182
DOI
10.1088/1748-3190/aa5b48
language
English
LU publication?
yes
id
8cf982a5-7b63-4b40-a8e0-329cba588430
date added to LUP
2017-05-04 08:57:22
date last changed
2017-09-18 13:34:00
@article{8cf982a5-7b63-4b40-a8e0-329cba588430,
  abstract     = {<p>Robust and efficient target-tracking algorithms embedded on moving platforms, are a requirement for many computer vision and robotic applications. However, deployment of a real-time system is challenging, even with the computational power of modern hardware. As inspiration, we look to biological lightweight solutions-lightweight and low-powered flying insects. For example, dragonflies pursue prey and mates within cluttered, natural environments, deftly selecting their target amidst swarms. In our laboratory, we study the physiology and morphology of dragonfly 'small target motion detector' neurons likely to underlie this pursuit behaviour. Here we describe our insect-inspired tracking model derived from these data and compare its efficacy and efficiency with state-of-the-art engineering models. For model inputs, we use both publicly available video sequences, as well as our own task-specific dataset (small targets embedded within natural scenes). In the context of the tracking problem, we describe differences in object statistics within the video sequences. For the general dataset, our model often locks on to small components of larger objects, tracking these moving features. When input imagery includes small moving targets, for which our highly nonlinear filtering is matched, the robustness outperforms state-of-the-art trackers. In all scenarios, our insect-inspired tracker runs at least twice the speed of the comparison algorithms.</p>},
  articleno    = {025006},
  author       = {Bagheri, Zahra M and Wiederman, Steven D and Cazzolato, Benjamin S and Grainger, Steven and O'Carroll, David C.},
  issn         = {1748-3182},
  keyword      = {bio-inspired vision,real-time,visual target tracking},
  language     = {eng},
  month        = {02},
  number       = {2},
  publisher    = {IOP Publishing},
  series       = {Bioinspiration and Biomimetics},
  title        = {Performance of an insect-inspired target tracker in natural conditions},
  url          = {http://dx.doi.org/10.1088/1748-3190/aa5b48},
  volume       = {12},
  year         = {2017},
}