完整後設資料紀錄
DC 欄位語言
dc.contributor.authorWu, Hsin-Jung Jr
dc.contributor.authorFan Jiang, Shu-JhenJr
dc.contributor.authorYeh, Chia-Hung Jr
dc.date.accessioned2011-01-26T01:28:31Z
dc.date.accessioned2020-05-18T03:10:41Z-
dc.date.available2011-01-26T01:28:31Z
dc.date.available2020-05-18T03:10:41Z-
dc.date.issued2011-01-26T01:28:31Z
dc.date.submitted2010-12-16
dc.identifier.urihttp://dspace.lib.fcu.edu.tw/handle/2377/29978-
dc.description.abstractA modified orthogonal search (OS) algorithm via gradient descent is proposed for fast motion estimation (ME). Gradient descent method, a first-order optimization algorithm in machine learning, is employed in video coding to reduce the ME time for coding performance enhancement. An improved OS algorithm is created in our proposed method. Through this method, the number of search points is reduced significantly and lower computation time can be achieved. Experimental results demonstrate that the proposed method can greatly improve the coding performance of H.264/AVC.
dc.description.sponsorshipNational Cheng Kung University,Tainan
dc.format.extent5p.
dc.relation.ispartofseries2010 ICS會議
dc.subjectmotion estimation
dc.subjectblock-matching algorithm
dc.subjectorthogonal search
dc.subjectgradient descent
dc.subject.otherPeer to Peer, Grid, and Cloud Computing
dc.titleA Gradient Descent Orthogonal Search Algorithm for Motion Estimation
分類:2010年 ICS 國際計算機會議(如需查看全文,請連結至IEEE Xplore網站)

文件中的檔案:
沒有與此文件相關的檔案。


在 DSpace 系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。