Performance Evaluation of CNN Based Pedestrian and Cyclist Detectors On Degraded Images

Simple item page
dc.contributor.authorZemčík, Tomášcs
dc.contributor.authorKratochvíla, Lukášcs
dc.contributor.authorBilík, Šimoncs
dc.contributor.authorBoštík, Ondřejcs
dc.contributor.authorZemčík, Pavelcs
dc.contributor.authorHorák, Karelcs
dc.coverage.issue1cs
dc.coverage.volume15cs
dc.date.issued2021-02-28cs
dc.description.abstractThis paper evaluates the effects of input image degradation on performance of image object detectors. The purpose of the evaluation is to determine usability of the detectors trained on original images in adverse conditions. SSD and Faster R-CNN based pedestrian and cyclist detector performance with images degraded with motion blur, out-of-focus blur, and JPEG compression artefacts, most commonly occurring in mobile or static traffic systems. An experiment was designed to assess the effect of degradations on detection precision and cross class confusion. The paper describes the two datasets created for this evaluation, evaluation of a number of detectors on increasingly more degraded images, comparison of their performance, and assessment of their tolerance to different types of image degradation as well as a discussion of the results.en
dc.formattextcs
dc.format.extent1-13cs
dc.format.mimetypeapplication/pdfcs
dc.identifier.citationInternational Journal of Image Processing. 2021, vol. 15, issue 1, p. 1-13.en
dc.identifier.issn1985-2304cs
dc.identifier.orcid0000-0003-4363-4313cs
dc.identifier.orcid0000-0001-8425-323Xcs
dc.identifier.orcid0000-0001-8797-7700cs
dc.identifier.orcid0000-0002-7856-2084cs
dc.identifier.orcid0000-0001-7969-5877cs
dc.identifier.orcid0000-0002-2280-3029cs
dc.identifier.other170686cs
dc.identifier.researcheridJEP-7714-2023cs
dc.identifier.researcheridG-6439-2010cs
dc.identifier.scopus57222421244cs
dc.identifier.scopus6507084407cs
dc.identifier.urihttp://hdl.handle.net/11012/200992
dc.language.isoencs
dc.publisherComputer Science Journals (CSC Journals)cs
dc.relation.ispartofInternational Journal of Image Processingcs
dc.relation.urihttps://www.cscjournals.org/library/manuscriptinfo.php?mc=IJIP-1213cs
dc.rightsCreative Commons Attribution-NonCommercial 4.0 Internationalcs
dc.rights.accessopenAccesscs
dc.rights.sherpahttp://www.sherpa.ac.uk/romeo/issn/1985-2304/cs
dc.rights.urihttp://creativecommons.org/licenses/by-nc/4.0/cs
dc.subjectObject Detectionen
dc.subjectImage Degradationen
dc.subjectPedestrian Detectionen
dc.subjectCyclist Detectionen
dc.subjectSSDen
dc.subjectFaster R-CNN.en
dc.titlePerformance Evaluation of CNN Based Pedestrian and Cyclist Detectors On Degraded Imagesen
dc.type.driverarticleen
dc.type.statusPeer-revieweden
dc.type.versionpublishedVersionen
sync.item.dbidVAV-170686en
sync.item.dbtypeVAVen
sync.item.insts2025.02.03 15:39:29en
sync.item.modts2025.01.17 16:48:42en
thesis.grantorVysoké učení technické v Brně. Fakulta elektrotechniky a komunikačních technologií. Ústav automatizace a měřicí technikycs
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
IJIP1213.pdf
Size:
1.4 MB
Format:
Adobe Portable Document Format
Description:
IJIP1213.pdf
Download
Collections
Ústav automatizace a měřicí techniky