Current studentsExisting staffContact us
 

Performance of an insect-inspired target tracker in natural conditions

Simple item page
dc.contributor.authorBagheri, Z.
dc.contributor.authorWiederman, S.
dc.contributor.authorCazzolato, B.
dc.contributor.authorGrainger, S.
dc.contributor.authorO'Carroll, D.
dc.date.issued2017
dc.description.abstractRobust 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.
dc.description.statementofresponsibilityZahra M Bagheri, Steven D Wiederman, Benjamin S Cazzolato, Steven Grainger and David C O’Carroll
dc.identifier.citationBioinspiration and Biomimetics, 2017; 12(2):025006-1-025006-16
dc.identifier.doi10.1088/1748-3190/aa5b48
dc.identifier.issn1748-3182
dc.identifier.issn1748-3190
dc.identifier.orcidBagheri, Z. [0000-0002-1749-3441]
dc.identifier.orcidWiederman, S. [0000-0002-0902-803X]
dc.identifier.orcidCazzolato, B. [0000-0003-2308-799X]
dc.identifier.orcidGrainger, S. [0000-0003-4664-7320]
dc.identifier.orcidO'Carroll, D. [0000-0002-2352-4320]
dc.identifier.urihttp://hdl.handle.net/2440/105622
dc.language.isoen
dc.publisherIOP Publishing
dc.relation.granthttp://purl.org/au-research/grants/arc/DP130104572
dc.relation.granthttp://purl.org/au-research/grants/arc/DE150100548
dc.rights© 2017 IOP Publishing Ltd.
dc.source.urihttps://doi.org/10.1088/1748-3190/aa5b48
dc.subjectVisual target tracking; bio-inspired vision; real-time
dc.titlePerformance of an insect-inspired target tracker in natural conditions
dc.typeJournal article
pubs.publication-statusPublished

Files

Collections

Mechanical Engineering publications