Current studentsExisting staffContact us
 

Ball Detection for a Lightweight Mobile Platform

Simple item page
dc.contributor.authorPratt, H.C.
dc.contributor.authorEvans, B.J.E.
dc.contributor.authorReid, I.D.
dc.contributor.authorWiederman, S.D.
dc.contributor.conferenceInternational Conference on Digital Image Computing: Techniques and Applications (DICTA) (28 Nov 2023 - 1 Dec 2023 : Port Macquarie, Australia)
dc.date.issued2023
dc.description.abstractWhile convolutional neural networks have excelled in recent years in the domain of object detection, many of the benchmark datasets focus on large objects in static frames and neglect the importance of small moving object detection. Furthermore, most state-of-the-art detectors are comprised of many millions of parameters, making them too large to be efficiently deployed onto a computationally constrained mobile platform. To address the challenge of detecting small moving targets from a robotic platform, we introduce a lightweight temporally-aware ball tracker, with a reduced computational footprint and enhanced motion understanding. To better understand how different model variants utilise motion, we analyse the detection performance of different architectures under varying forms of motion information and find that multiple-input-multiple-output models learn to favour motion information in sequences more strongly than multiple-input-single-output models.
dc.description.statementofresponsibilityHamish C. Pratt, Bernard J.E. Evans, Ian D. Reid and Steven D. Wiederman
dc.identifier.citationProceedings of the International Conference on Digital Image Computing: Techniques and Applications (DICTA 2023), 2023, pp.89-96
dc.identifier.doi10.1109/DICTA60407.2023.00021
dc.identifier.isbn9798350382204
dc.identifier.orcidEvans, B.J.E. [0000-0002-3517-3775]
dc.identifier.orcidReid, I.D. [0000-0001-7790-6423]
dc.identifier.orcidWiederman, S.D. [0000-0002-0902-803X]
dc.identifier.urihttps://hdl.handle.net/2440/148357
dc.language.isoen
dc.publisherInstitute of Electrical and Electronics Engineers (IEEE)
dc.publisher.placeOnline
dc.relation.granthttp://purl.org/au-research/grants/arc/FT180100466
dc.rights©2023 IEEE
dc.source.urihttps://ieeexplore.ieee.org/xpl/conhome/10410651/proceeding
dc.titleBall Detection for a Lightweight Mobile Platform
dc.typeConference paper
pubs.publication-statusPublished

Files

Collections

Research Outputs