Show simple item record

dc.contributor.authorErabadda, Buddhiprabha
dc.contributor.authorMallikarachchi, Thanuja
dc.contributor.authorKulupana, Gosala
dc.contributor.authorFernando, Anil
dc.date.accessioned2019-10-21T13:22:18Z
dc.date.available2019-10-21T13:22:18Z
dc.date.issued2019-09-06
dc.identifier.citationErabadda, B., Mallikarachchi, T., Kulupana, G. and Fernando, A. (2019) 'Fast CU Size Decisions for HEVC Inter-PredictionUsing Support Vector Machines', 27th European Signal Processing Conference, 2-6 September, Spain.en_US
dc.identifier.urihttp://hdl.handle.net/10369/10786
dc.descriptionPaper presented at 27th European Signal Processing Conference, 2-6 September, 2019, Spain.en_US
dc.description.abstractThe brute force rate-distortion optimisation based approach used in the High Efficiency Video Coding (HEVC) encoders to determine the best block partitioning structure fora given content demands an excessive amount of computational resources. In this context, this paper proposes a novel algorithm to reduce the computational complexity of HEVC inter-prediction using Support Vector Machines. The proposed algorithm predicts the Coding Unit (CU) split decision of a particular block enabling the encoder to directly encode the selected block, avoiding the unnecessary evaluation of the remaining CU size combinations.Experimental results demonstrate encoding time reductions of~58% and ~50% with 2.27%, and 1.89% Bjøntegaard DeltaBit Rate (BDBR) losses for Random Access and Low-Delay B configurations, respectively.en_US
dc.language.isoenen_US
dc.publisherEURASIPen_US
dc.relation.ispartofseries27th European Signal Processing Conference;
dc.titleFast CU Size Decisions for HEVC Inter-Prediction Using Support Vector Machinesen_US
dc.typeConference paperen_US
dcterms.dateAccepted2019-09-06
rioxxterms.funderCardiff Metropolitan Universityen_US
rioxxterms.identifier.projectCardiff Metropolian (Internal)en_US
rioxxterms.versionAMen_US
rioxxterms.licenseref.urihttp://www.rioxx.net/licenses/under-embargo-all-rights-reserveden_US
rioxxterms.licenseref.startdate2019-10-21
rioxxterms.freetoread.startdate2100-01-01
rioxxterms.funder.project37baf166-7129-4cd4-b6a1-507454d1372een_US


Files in this item

Thumbnail

This item appears in the following collection(s)

Show simple item record