Paper Info
Title
A partitioned linear minimum mean square estimator for error concealment [video decoder error concealment]
Abstract
In this paper, we proposed a partitioned linear minimum mean square error estimator (P-LMMSE) for error concealment. The proposed P-LMMSE estimator adopts the multi-hypothesis motion compensation (MHMC) technique to reconstruct the corrupted block, in which the lost blocks are predicted by a linear combination of motion compensated blocks (hypotheses). In our proposed P-LMMSE estimator, the weighting coefficients are optimal in the sense that they minimize the mean square error. In addition, our proposed estimator exploits the properties of the hypotheses to improved accuracy of prediction. Each hypothesis has its own assumption and hence works well only in a particular situation, or equivalently, the statistics in different situations are not the same. Therefore, the dataset is divided into finer partitions and the weighting coefficient set in the most appropriate partition is selected to reconstruct the corrupted block.
Year
DOI
Venue
2005
10.1109/ISCAS.2005.1465173
ISCAS (3)
Keywords
Field
DocType
dataset partitioning,video decoder error concealment,motion compensation,weighting coefficient optimization,minimum mean square estimator,p-lmmse,corrupted block reconstruction,multiple-hypothesis motion compensation technique,partitioned linear mmse estimator,least mean squares methods,video coding,signal reconstruction,mhmc,error correction,gold,redundancy,statistics,automatic repeat request,mean square error,decoding
Efficient estimator,Minimum-variance unbiased estimator,Stein's unbiased risk estimate,Mean squared error,Minimum mean square error,Bias of an estimator,Statistics,Mathematics,Estimator,Orthogonality principle
Conference
ISBN
Citations 
PageRank 
0-7803-8834-8
1
0.35
References 
Authors
3
4
Name
Order
Citations
PageRank
Tak-song Chong1132.61
Oscar C. Au21592176.54
Wing-san Chau3163.24
Tai-wai Chan4223.62