A gradient descent orthogonal search algorithm for motion estimation

Hsin Jung Wu*, Shu Jhen Fan Jiang, Chia Hung Yeh

*此作品的通信作者

研究成果: 書貢獻/報告類型會議論文篇章

摘要

A 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.

原文英語
主出版物標題ICS 2010 - International Computer Symposium
頁面799-803
頁數5
DOIs
出版狀態已發佈 - 2010
對外發佈
事件2010 International Computer Symposium, ICS 2010 - Tainan, 臺灣
持續時間: 2010 12月 162010 12月 18

出版系列

名字ICS 2010 - International Computer Symposium

其他

其他2010 International Computer Symposium, ICS 2010
國家/地區臺灣
城市Tainan
期間2010/12/162010/12/18

ASJC Scopus subject areas

  • 電腦科學(全部)

指紋

深入研究「A gradient descent orthogonal search algorithm for motion estimation」主題。共同形成了獨特的指紋。

引用此