Fusing spatial and temporal components for real-time depth data enhancement of dynamic scenes Islam, Abm Tariqul , 1982- (VerfasserIn) Staadt, Oliver , 1968- (AkademischeR BetreuerIn) Pajarola, Renato , 1969- (AkademischeR BetreuerIn) Universität Rostock (Grad-verleihende Institution) Universität Rostock Fakultät für Informatik und Elektrotechnik (Grad-verleihende Institution) Text theses Text Hochschulschrift 2019 2019 eng electronic resourceremoteComputermedienOnline-Ressource1 Online-Ressource The depth images from consumer depth cameras (e.g., structured-light/ToF devices) exhibit a substantial amount of artifacts (e.g., holes, flickering, ghosting) that needs to be removed for real-world applications. Existing methods cannot entirely remove them and perform slow. This thesis proposes a new real-time spatio-temporal depth image enhancement filter that completely removes flickering and ghosting, and significantly reduces holes. This thesis also presents a novel depth-data capture setup and two data reduction methods to optimize the performance of the proposed enhancement method.<eng> vorgelegt von ABM Tariqul Islam GutachterInnen: Oliver Staadt (University of Rostock, Institute for Visual and Analytic Computing) ; Renato Pajarola (University of Zurich, Department of Informatics) Dissertation Universität Rostock 2019 004 620 006.37 004 ST 330 54.74 http://purl.uni-rostock.de/rosdok/id00002542 https://doi.org/10.18453/rosdok_id00002542 https://nbn-resolving.org/urn:nbn:de:gbv:28-rosdok_id00002542-3 https://d-nb.info/1293657840/34 Fusing spatial and temporal components for real-time depth data enhancement of dynamic scenes--(DE-627)1682358240 urn:nbn:de:gbv:28-rosdok_id00002542-3 doi: 10.18453/rosdok_id00002542 oclc: 1136856325 ppn: (DE-627)1681397668