Download
PDF 1.95 MB
master's thesis
20   11
Objective video quality measure based on artifacts detected in video
Viliams Bajčinovci (2017)
Josip Juraj Strossmayer University of Osijek
Faculty of Electrical Engineering, Computer Science and Information Technology Osijek
Department of Communications
Chair of Radiocommunications and Telecommunications
Metadata
TitleObjektivna mjera kvalitete videa zasnovana na detektiranim artefaktima u videu
AuthorViliams Bajčinovci
Mentor(s)Mario Vranješ (thesis advisor)
Abstract
U ovom radu razvijena je objektivna metrika koja bez mogućnosti pristupa informacijama referentne video sekvence, na temelju detektiranih artefakata, daje ocjenu kvalitete testne video sekvence. Za potrebe razvoja i testiranja metrike kreirane su dvije nove video baze te su nad pripadnim sekvencama provedeni subjektivni testovi. Uz kreirane baze, korištene su još dvije javno dostupne video baze za testiranje rada novo-stvorene metrike. Metrika uzima u obzir vremensko i prostorno maskiranje artefakata te koristi Minkowski vremensko sažimanje povratnih vrijednosti korištenih algoritama za detekciju artefakata i nelinearnu transformaciju. Za potrebe poboljšanja predviđanja kvalitete, razvijen je model za klasifikaciju načina kompresije izvornog sadržaja.
Keywordsobjective video quality assessment no-reference processing video quality database subjective video quality assessment video artifacts
Parallel title (English)Objective video quality measure based on artifacts detected in video
Committee MembersMario Vranješ (committee chairperson)
Snježana Rimac-Drlje (committee member)
Denis Vranješ (committee member)
GranterJosip Juraj Strossmayer University of Osijek
Faculty of Electrical Engineering, Computer Science and Information Technology Osijek
Lower level organizational unitsDepartment of Communications
Chair of Radiocommunications and Telecommunications
PlaceOsijek
StateCroatia
Scientific field, discipline, subdisciplineTECHNICAL SCIENCES
Computing
Information Systems
Study programme typeuniversity
Study levelgraduate
Study programmeGraduate University Study Programme in Electrical Engineering; specializations in: Communications and Informatics, Power Engineering
Study specializationCommunications and Informatics
Academic title abbreviationmag.ing.el.
Genremaster's thesis
Language Croatian
Defense date2017-09-28
Parallel abstract (English)
In this Master Thesis an objective no-reference metric for video quality assessment based on artifact detection was developed. For requirements of metric development and testing, two new video quality databases were created and subjective quality assessment experiments conducted. Two other publicly available video quality databases were also used for the newly-created video quality metric testing. The developed metric takes spatial and temporal artifact masking effects into account, uses Minkowski temporal pooling to pool values returned by algorithms for artifact detection and nonlinear transformation. A model for compression method classification was developed resulting in increase of video quality prediction performance.
Parallel keywords (Croatian)objektivna ocjena kvalitete videa obrada bez reference video baza subjektivna ocjena kvalitete videa video artefakti
Resource typetext
Access conditionOpen access
Terms of usehttp://rightsstatements.org/vocab/InC/1.0/
URN:NBNhttps://urn.nsk.hr/urn:nbn:hr:200:156026