Improved quality of experience of reconstructed H.264/AVC encoded video sequences through robust pixel domain error detection

The transmission of H.264/AVC encoded sequences over noisy wireless channels generally adopt the error detection capabilities of the transport protocol to identify and discard corrupted slices. All the macroblocks (MBs) within each corrupted slice are then concealed. This paper presents an algorithm that does not discard the corrupted slices but tries to detect those MBs which provide major visual artefacts and then conceal only these MBs. Results show that the proposed solution, based on a set of image-level features and two support vector machines (SVMs), manages to detect 94.6% of those artefacts. Gains in peak signal-to-noise ratios (PSNR) of up to 5.74 dB have been obtained when compared to the standard H.264/AVC decoder.

[1]  Nello Cristianini,et al.  An Introduction to Support Vector Machines and Other Kernel-based Learning Methods , 2000 .

[2]  Olivia Nemethova,et al.  Combined sequential decoding and error concealment of H.264 video , 2004, IEEE 6th Workshop on Multimedia Signal Processing, 2004..

[3]  Matti Pietikäinen,et al.  Unsupervised texture segmentation using feature distributions , 1997, Pattern Recognit..

[4]  Miska M. Hannuksela,et al.  H.264/AVC in wireless environments , 2003, IEEE Trans. Circuits Syst. Video Technol..

[5]  Miska M. Hannuksela,et al.  H.264/AVC video for wireless transmission , 2005, IEEE Wireless Communications.

[6]  Reuben A. Farrugia,et al.  ENHANCING ERROR RESILIENCE IN WIRELESS TRANSMITTED COMPRESSED VIDEO SEQUENCES THROUGH A PROBABILISTIC NEURAL NETWORK CORE , 2007 .

[7]  S. Sathiya Keerthi,et al.  Improvements to Platt's SMO Algorithm for SVM Classifier Design , 2001, Neural Computation.

[8]  Cyril Bergeron,et al.  Soft-input decoding of variable-length codes applied to the H.264 standard , 2004, IEEE 6th Workshop on Multimedia Signal Processing, 2004..

[9]  John Platt,et al.  Probabilistic Outputs for Support vector Machines and Comparisons to Regularized Likelihood Methods , 1999 .

[10]  Luca Superiori,et al.  DETECTION OF VISUAL IMPAIRMENTS IN THE PIXEL DOMAIN OF CORRUPTED H.264/AVC PACKETS , 2007 .

[11]  Markus Rupp,et al.  Robust Error Detection for H.264/AVC Using Relation Based Fragile Watermarking , 2006 .

[12]  Markus Rupp,et al.  Improved Detection for H.264 Encoded Video Sequences over Mobile Networks , 2005 .

[13]  C.J. Debono,et al.  Resilient transmission of H.264/AVC video sequences using probabilistic neural networks , 2008, 2008 3rd International Symposium on Communications, Control and Signal Processing.

[14]  Markus Rupp,et al.  Performance of a H.264/AVC Error Detection Algorithm Based on Syntax Analysis , 2007, J. Mobile Multimedia.