Kernel-Based MMSE Multimedia Signal Reconstruction and Its Application to Spatial Error Concealment

This paper proposes a novel approach for multimedia signal reconstruction based on kernel density estimation (KDE). We make use of a vector formalism in which vectors consist of a first subvector containing a set of missing samples and a second one containing a set of available context samples. The missing subvector is reconstructed by a minimum mean square error estimator which employs a probability density function (pdf) obtained by KDE. As in any kernel-based method, the main issue to deal with is the estimation of an appropriate kernel bandwidth. We propose an adaptive procedure for bandwidth estimation (BE) especially conceived for signal reconstruction. Thus, unlike general KDE or kernel-based regression, which try to obtain a general fit, the focus of this BE procedure is on the specific missing subvector. Also, in order to exploit local signal correlations, our BE proposal adopts a scaling approach in which the bandwidth is computed as the local covariance matrix scaled by two factors. These two scale factors are obtained by minimization of two different approximations to the reconstruction error. The resulting reconstruction methodology is tested on a spatial error concealment (EC) application in which intracoded images have been transmitted through an error prone channel. The experimental results show the superiority of the proposed approach over a wide range of existing EC techniques.

[1]  Antonio M. Peinado,et al.  Spatial Error Concealment Based on Edge Visual Clearness for Image/Video Communication , 2013, Circuits Syst. Signal Process..

[2]  Antonio M. Peinado,et al.  On the application of multivariate kernel density estimation to image error concealment , 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

[3]  André Kaup,et al.  Fast orthogonality deficiency compensation for improved frequency selective image extrapolation , 2008, 2008 IEEE International Conference on Acoustics, Speech and Signal Processing.

[4]  Yan Zhao,et al.  Spatial Error Concealment Using Directional Extrapolation , 2005, Digital Image Computing: Techniques and Applications (DICTA'05).

[5]  Steven Kay,et al.  Fundamentals Of Statistical Signal Processing , 2001 .

[6]  Danijel Skocaj,et al.  Multivariate online kernel density estimation with Gaussian kernels , 2011, Pattern Recognit..

[7]  David W. Scott,et al.  Multivariate Density Estimation: Theory, Practice, and Visualization , 1992, Wiley Series in Probability and Statistics.

[8]  Xuelong Li,et al.  Single Image Super-Resolution With Non-Local Means and Steering Kernel Regression , 2012, IEEE Transactions on Image Processing.

[9]  Hamid Gharavi,et al.  Spatial interpolation algorithm for error concealment , 2008, 2008 IEEE International Conference on Acoustics, Speech and Signal Processing.

[10]  Jianfei Cai,et al.  Image error-concealment via Block-based Bilateral Filtering , 2008, 2008 IEEE International Conference on Multimedia and Expo.

[11]  Rabab Kreidieh Ward,et al.  An adaptive Markov random field based error concealment method for video communication in an error prone environment , 1999, 1999 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings. ICASSP99 (Cat. No.99CH36258).

[12]  M. C. Jones,et al.  Comparison of Smoothing Parameterizations in Bivariate Kernel Density Estimation , 1993 .

[13]  Michael T. Orchard,et al.  Novel sequential error-concealment techniques using orientation adaptive interpolation , 2001, IEEE Trans. Circuits Syst. Video Technol..

[14]  Søren Holdt Jensen,et al.  Sequential Error Concealment for Video/Images by Sparse Linear Prediction , 2013, IEEE Transactions on Multimedia.

[15]  D. W. Scott,et al.  Multivariate Density Estimation, Theory, Practice and Visualization , 1992 .

[16]  Zhang Rongfu,et al.  Content-adaptive spatial error concealment for video communication , 2004 .

[17]  I. Haritaoglu,et al.  Background and foreground modeling using nonparametric kernel density estimation for visual surveillance , 2002 .

[18]  James W. Wisnowski,et al.  Smoothing and Regression: Approaches, Computation, and Application , 2002 .

[19]  Huifang Sun,et al.  Concealment of damaged block transform coded images using projections onto convex sets , 1995, IEEE Trans. Image Process..

[20]  Kimmo Kansanen,et al.  On MMSE Estimation: A Linear Model Under Gaussian Mixture Statistics , 2012, IEEE Transactions on Signal Processing.

[21]  Vladimir Katkovnik,et al.  A new method for varying adaptive bandwidth selection , 1999, IEEE Trans. Signal Process..

[22]  Hamid R. Rabiee,et al.  Multi-directional spatial error concealment using adaptive edge thresholding , 2012, IEEE Transactions on Consumer Electronics.

[23]  Weisi Lin,et al.  Bayesian Error Concealment With DCT Pyramid for Images , 2010, IEEE Transactions on Circuits and Systems for Video Technology.

[24]  Peyman Milanfar,et al.  Kernel Regression for Image Processing and Reconstruction , 2007, IEEE Transactions on Image Processing.

[25]  James Stephen Marron,et al.  Visual Error Criteria for Qualitative Smoothing , 1995 .

[26]  Thomas Eriksson,et al.  Packet Video Error Concealment With Gaussian Mixture Models , 2008, IEEE Transactions on Image Processing.

[27]  Dorin Comaniciu,et al.  An Algorithm for Data-Driven Bandwidth Selection , 2003, IEEE Trans. Pattern Anal. Mach. Intell..

[28]  C. D. Kemp,et al.  Density Estimation for Statistics and Data Analysis , 1987 .

[29]  S. Sheather Density Estimation , 2004 .

[30]  Adrian G. Bors,et al.  Kernel Bandwidth Estimation for Nonparametric Modeling , 2009, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[31]  Lijian Yang,et al.  Multivariate bandwidth selection for local linear regression , 1999 .