Full metadata record
DC FieldValueLanguage
dc.contributor.authorReithmeier, Lukas
dc.contributor.authorKrauss, Oliver
dc.contributor.authorZwettler, Adam Gerald
dc.contributor.editorSkala, Václav
dc.date.accessioned2021-09-01T07:24:17Z
dc.date.available2021-09-01T07:24:17Z
dc.date.issued2021
dc.identifier.citationWSCG 2021: full papers proceedings: 29. International Conference in Central Europe on Computer Graphics, Visualization and Computer Vision, p. 273-282.en
dc.identifier.isbn978-80-86943-34-3
dc.identifier.issn2464-4617
dc.identifier.issn2464–4625(CD/DVD)
dc.identifier.urihttp://hdl.handle.net/11025/45033
dc.format10 s.cs
dc.format.mimetypeapplication/pdf
dc.language.isoenen
dc.publisherVáclav Skala - UNION Agencycs
dc.rights© Václav Skala - UNION Agencycs
dc.subjectsegmentace instancecs
dc.subjectRGB-D datacs
dc.subjectpřenosové učenícs
dc.subjectreflexní prostředícs
dc.titleTransfer Learning and Hyperparameter Optimization for Instance Segmentation with RGB-D Images in Reflective Elevator Environmentsen
dc.typeconferenceObjecten
dc.typekonferenční příspěvekcs
dc.rights.accessopenAccessen
dc.type.versionpublishedVersionen
dc.description.abstract-translatedElevators, a vital means for urban transportation, are generally lacking proper emergency call systems besidesan emergency button. In the case of unconscious or otherwise incapacitated passengers this can lead to lethalsituations. A camera-based surveillance system with AI-based alerts utilizing an elevator state machine can helppassengers unable to initiate an emergency call. In this research work, the applicability of RGB-D images asinput for instance segmentation in the highly reflective environment of an elevator cabin is evaluated. For objectsegmentation, a Region-based Convolution Neural Network (R-CNN) deep learning model is adapted to use depthinput data besides RGB by applying transfer learning, hyperparameter optimization and re-training on a newlyprepared elevator image dataset. Evaluations prove that with the chosen strategy, the accuracy of R-CNN instancesegmentation is applicable on RGB-D data, thereby resolving lack of image quality in the noise affected andreflective elevator cabins. The mean average precision (mAP) of 0.753 is increased to 0.768 after the incorporationof additional depth data and with additional FuseNet-FPN backbone on RGB-D the mAP is further increased to0.794. With the proposed instance segmentation model, reliable elevator surveillance becomes feasible as firstprototypes and on-road tests proof.en
dc.subject.translatedinstance segmentationen
dc.subject.translatedRGB-D dataen
dc.subject.translatedtransfer learningen
dc.subject.translatedreflective environmentsen
dc.identifier.doihttps://doi.org/10.24132/CSRN.2021.3101.30
dc.type.statusPeer-revieweden
Appears in Collections:WSCG 2021: Full Papers Proceedings

Files in This Item:
File Description SizeFormat 
J71.pdfPlný text4,43 MBAdobe PDFView/Open


Please use this identifier to cite or link to this item: http://hdl.handle.net/11025/45033

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.