Improved global motion estimation via motion vector clustering for video stabilization

NCUIR > College of Electrical Engineering & Computer Science > Department of Electrical Engineering > journal & Dissertation > Item 987654321/107499

Please use this identifier to cite or link to this item: https://ir.lib.ncu.edu.tw/handle/987654321/107499

Title:	Improved global motion estimation via motion vector clustering for video stabilization
Authors:	龔存雄;Chen, Bo-Hao;Kopylov, Andrey;Huang, Shih-Chia;Seredin, Oleg;Karpov, Roman;Kuo, Sy-Yen;Robert Lai, K.;Tan, Tan-Hsu;Gochoo, Munkhjargal;Bayanduuren, Damdinsuren;Gong, Cihun-Siyong;Hung, Patrick C.K.
Contributors:	資訊電機學院電機工程學系
Keywords:	Artificial intelligence;Clustering;Expert systems;Mathematical analysis;Motion vector clustering;Multimedia;Shortest spanning path;Stabilization;State of the art;Vectors (mathematics);Video stabilization
Date:	2016-09-01
Issue Date:	2026-04-23 14:15:41 (UTC+8)
Publisher:	Elsevier Ltd.;Elsevier Ltd
Abstract:	摘要： Video stabilization technique is often used in handheld multimedia devices, whereas the difficulties in the accurate extraction aspect of global motion vectors restrict its development. This paper proposes a novel video stabilization approach that is based on the shortest spanning path clustering algorithm for effective and reliable estimation of the global motion vectors. As demonstrated in our experimental results, the proposed approach achieves superior stabilized effectiveness compared with the other state-of-the-art approaches based on both qualitative and quantitative measurements. 出版者： Elsevier Ltd 出版日期： 2016-09-01 出處： Engineering applications of artificial intelligence, 2016-09, Vol.54, p.39-48 版權： 2016 Elsevier Ltd 識別號： ISSN: 0952-1976 識別號： EISSN: 1873-6769 識別號： DOI: 10.1016/j.engappai.2016.05.004
Appears in Collections:	[Department of Electrical Engineering] journal & Dissertation

Files in This Item:

File	Description	Size	Format
index.html		0Kb	HTML	13	View/Open

社群 sharing

Loading...