TU Darmstadt / ULB / TUbiblio

Verification of Single-Person Access in a Mantrap Portal Using RGB-D Images

Siegmund, Dirk ; Wainakh, Aidmar ; Braun, Andreas (2016)
Verification of Single-Person Access in a Mantrap Portal Using RGB-D Images.
XII Workshop de Visão Computacional. Proceedings. Campo Grande, Mato Grosso Do Sul, Brazil (November 9-11 2016​)
Konferenzveröffentlichung, Bibliographie

Kurzbeschreibung (Abstract)

Automatic entrance systems are increasingly gaining importance to guarantee security in e.g. critical infrastructure. A pipeline is presented which verifies that only a single, authorized subject can enter a secured area. Verification scenarios are carried out by using a set of RGB-D images. Features, invariant to rotation and pose are used and classified by different metrics to be applied in real-time. The performance was evaluated by using scenarios in which the system was attacked by a second subject. The results show that the presented approach outerperforms competitive methods. It concludes with a summary of strengths and weaknesses and gives an outlook for future work.

Typ des Eintrags: Konferenzveröffentlichung
Erschienen: 2016
Autor(en): Siegmund, Dirk ; Wainakh, Aidmar ; Braun, Andreas
Art des Eintrags: Bibliographie
Titel: Verification of Single-Person Access in a Mantrap Portal Using RGB-D Images
Sprache: Englisch
Publikationsjahr: November 2016
Veranstaltungstitel: XII Workshop de Visão Computacional. Proceedings
Veranstaltungsort: Campo Grande, Mato Grosso Do Sul, Brazil
Veranstaltungsdatum: November 9-11 2016​
Kurzbeschreibung (Abstract):

Automatic entrance systems are increasingly gaining importance to guarantee security in e.g. critical infrastructure. A pipeline is presented which verifies that only a single, authorized subject can enter a secured area. Verification scenarios are carried out by using a set of RGB-D images. Features, invariant to rotation and pose are used and classified by different metrics to be applied in real-time. The performance was evaluated by using scenarios in which the system was attacked by a second subject. The results show that the presented approach outerperforms competitive methods. It concludes with a summary of strengths and weaknesses and gives an outlook for future work.

Freie Schlagworte: Guiding Theme: Smart City, Guiding Theme: Visual Computing as a Service, Research Area: Computer vision (CV), Research Area: Human computer interaction (HCI), People detection, Scene analysis, Optical flow, 3D Computer vision, CRISP
Fachbereich(e)/-gebiet(e): 20 Fachbereich Informatik
20 Fachbereich Informatik > Mathematisches und angewandtes Visual Computing
Hinterlegungsdatum: 07 Mai 2019 08:45
Letzte Änderung: 07 Mai 2019 08:45
PPN:
Export:
Suche nach Titel in: TUfind oder in Google
Frage zum Eintrag Frage zum Eintrag

Optionen (nur für Redakteure)
Redaktionelle Details anzeigen Redaktionelle Details anzeigen