Centroid based person detection using pixelwise prediction of the position

Simple item page
dc.contributor.authorDoležel, Petrcs
dc.contributor.authorŠkrabánek, Pavelcs
dc.contributor.authorŠtursa, Dominikcs
dc.contributor.authorBaruque Zanon, Brunocs
dc.contributor.authorCogollos Adrian, Hectorcs
dc.contributor.authorKrýda, Pavelcs
dc.coverage.issue1cs
dc.coverage.volume63cs
dc.date.accessioned2022-07-29T14:52:19Z
dc.date.available2022-07-29T14:52:19Z
dc.date.issued2022-07-06cs
dc.description.abstractImplementations of person detection in tracking and counting systems tend towards processing of orthogonally captured images on edge computing devices. The ellipse-like shape of heads in orthogonally captured images inspired us to predict head centroids to determine positions of persons in images. We predict the centroids using a fully convolutional network (FCN). We combine the FCN with simple image processing operations to ensure fast inference of the detector. We experiment with the size of the FCN output to further decrease the inference time. We compare the proposed centroid-based detector with bounding box-based detectors on head detection task in terms of the inference time and the detection performance. We propose a performance measure which allows quantitative comparison of the two detection approaches. For the training and evaluation of the detectors, we form original datasets of 8000 annotated images, which are characterized by high variability in terms of lighting conditions, background, image quality, and elevation profile of scenes. We propose an approach which allows simultaneous annotation of the images for both bounding box-based and centroid-based detection. The centroid-based detector shows the best detection performance while keeping edge computing standards.en
dc.formattextcs
dc.format.extent1-12cs
dc.format.mimetypeapplication/pdfcs
dc.identifier.citationJournal of Computational Science. 2022, vol. 63, issue 1, p. 1-12.en
dc.identifier.doi10.1016/j.jocs.2022.101760cs
dc.identifier.issn1877-7503cs
dc.identifier.other178514cs
dc.identifier.urihttp://hdl.handle.net/11012/208207
dc.language.isoencs
dc.publisherELSEVIERcs
dc.relation.ispartofJournal of Computational Sciencecs
dc.relation.urihttps://www.sciencedirect.com/science/article/pii/S1877750322001442cs
dc.rightsCreative Commons Attribution 4.0 Internationalcs
dc.rights.accessopenAccesscs
dc.rights.sherpahttp://www.sherpa.ac.uk/romeo/issn/1877-7503/cs
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/cs
dc.subjectPersondetectionen
dc.subjectFullyconvolutionalnetworksen
dc.subjectPerformancemeasureen
dc.subjectEdgecomputingen
dc.subjectComputervisionen
dc.titleCentroid based person detection using pixelwise prediction of the positionen
dc.type.driverarticleen
dc.type.statusPeer-revieweden
dc.type.versionpublishedVersionen
sync.item.dbidVAV-178514en
sync.item.dbtypeVAVen
sync.item.insts2023.02.01 08:52:44en
sync.item.modts2023.02.01 08:15:54en
thesis.grantorVysoké učení technické v Brně. Fakulta strojního inženýrství. Ústav automatizace a informatikycs
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
1s2.0S1877750322001442main.pdf
Size:
2 MB
Format:
Adobe Portable Document Format
Description:
1s2.0S1877750322001442main.pdf
Download
Collections
Ústav automatizace a informatiky