Video Compressed Sensing with Multihypothesis

被引：78

作者：

Tramel, Eric W. ^{[1
]}

Fowler, James E. ^{[1
]}

机构：

[1] Mississippi State Univ, Geosyst Res Inst GRI, Dept Elect & Comp Engn, Starkville, MS 39760 USA

来源：

2011 DATA COMPRESSION CONFERENCE (DCC) | 2011年

关键词：

JOHNSON;

D O I：

10.1109/DCC.2011.26

中图分类号：

TP301 [理论、方法];

学科分类号：

081202 ;

摘要：

The compressed-sensing recovery of video sequences driven by multihypot hesis predictions is considered. Specifically, multihypothesis predictions of the current frame are used to generate a residual in the domain of the compressed-sensing random projections. This residual being typically more compressible than the original frame leads to improved reconstruction quality. To appropriately weight the hypothesis predictions, a Tikhonov regularization to an ill-posed least-squares optimization is proposed. This method is shown to outperform both recovery of the frame independently of the others as well as recovery based on single-hypothesis prediction.

引用

页码：193 / 202

页数：10

共 18 条

[1] Database-friendly random projections: Johnson-Lindenstrauss with binary coins [J].