全部 标题 作者
关键词 摘要

OALib Journal期刊
ISSN: 2333-9721
费用:99美元

查看量下载量

相关文章

更多...

应用递归最短生成树算法实现H.264压缩域运动对象分割方法

DOI: 10.11834/jig.20091041

Keywords: H.264,压缩域,运动对象分割,递归最短生成树

Full-Text   Cite this paper   Add to My Lib

Abstract:

提出了一种基于递归最短生成树算法的H.264压缩域实时分割运动对象的算法。首先将从H.264编码端提取的运动矢量进行归一化、空间内插,得到稠密运动矢量场,再采用全局运动补偿技术抵消全局运动的影响,最后采用改进的“递归最短生成树”(RSST)算法对稠密运动矢量进行聚类,实现对运动对象的分割。实验结果表明,该算法对视频序列能实现较准确的分割。

References

[1]  Venkatesh Babu R,Ramakrishnan K R,Srinivasan S H.Video object segmentation:A compressed domain approach[J].IEEE Transactions on Circuits System and Video Technology,2004,14(4):462-474.
[2]  Zeng W,Du J,Gao W,et al.Robust moving object segmentation on H.264/AVC compressed video using the block-based MRF model[J].Real-time Imaging,2005,11(4):290-299.
[3]  Su Y P,Sun M T,Hsu V.Global motion estimation from coarsely sampled motion vector field and the applications[J].IEEE Transactions on Circuits System and Video Technology,2005,15(2):232-241.
[4]  Heitou Z E N,Tameharu HASEGA W A,Shinji OZA WA.Moving object detection from MPEG coded picture[A].In:Proceedings of IEEE International Conference on Image Processing,1999[C],Kobe,Japan,1999,4:25-29.
[5]  Eng H L,Ma K K.Spatiotemporal segmentation of moving video objects over MPEG compressed domain[A].In:Proceedings of IEEE International Conference on Multimedia and Expo,2000[C],New York,NY,USA,2000,3:1531-1534.
[6]  Liu Zhi,Lu Yu,Zhang Zhao-yang.Real-time spatiotemporal segmentation of video objects in the H.264 compressed domain[J].Journal of Visual Communication and Image Representation,2007,18 (3):275-290.
[7]  Morris O J,Lee M J,Constantinides A G.A unified method for segmentation and edge detection using graph theory[A].In:Proceedings of IEEE International Conference on Acoustics,Speech and Signal Processing,1986[C],Tokyo,Japan,1986,11:2051-2054.
[8]  Morris O J,Lee J M,Constantinides A G.Graph theory for image analysis:An approach based on the shortest spanning tree[J].IEEE Proceedings F:Communication,Radar and Signal Processing,1986,133(2):146-152.

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133