An MPEG 2 To H 264 Transcoder In Baseline Profile HARDEEPSINH JADEJA UTA ID 1000721847 What is Transcoding The operation of converting video in one format to another format It is the ability to take existing video content and change the bitrate and or resolution in order to view it on another video playback device Need for Transcoding MPEG 2 4 has been a widely accepted video coding standard for various applications ranging from DVD to digital tv broadcast The most important goal of MPEG 2 was to make the storage and transmission of digital AV material more efficient However new H 264 AVC standard 13 has an even broader perspective to support high and low bit rate multimedia applications on existing and future networks Need for TranscodingContd H 264 requires half of the space to store video content when compared to MPEG 2 1 Hence there is need to find compatibility between MPEG2 and H 264 devices MPEG 2 Encoder Decoder Fig 1 MPEG 2 encoder decoder 1 H 264 Encoder Fig 2 H 264 Encoder 9 Different MacroBlock sizes of H 264 for Motion Estimation Fig 3 Different macroblocks in H 264 8 Normal Method of motion estimation In H 264 inter frame motion estimation is performed using different MB sizes from 16 16 to 4 4 8 For each MB all different sizes are evaluated and the one leading to the minimum rate distortion RD cost is then selected This guarantees the optimal block size for the final encoding but at the expense of a high computational cost How is this transcoder Different Machine learning tools are used to exploit the correlation between the macroblock MB 1 decision of the H 264 video format and the distribution of the motion compensated residual in MPEG 2 Dynamic motion window technique is also proposed to further speed up the decision process The Algorithm for motion estimation for proposed trancoder The proposed MPEG 2 to H 264 transcoder consists of two parts an MPEG 2 decoder followed by an H 264 encoder First the transcoder fully decodes the MPEG 2 sequence and the information required by the decision trees and the dynamic motion window mechanism is gathered during this stage The information is given as input to decision tree The H 264MB mode decision is replaced by a simple mode assignment FAST MB MODE DECISION USING MACHINE LEARNING Creating the Training Files Fig 4 Training algorithm for decision tree 2 Decision Trees Fig 5 Decision tree for deciding the macro block mode of H 264 encoder 1 Dynamic motion window Adapting the search range based on the motion vector of the incoming MB could reduce the motion estimation 1 Dynamic motion window is combination of two methods Dynamic search range based on the length of the motion vectors in the MPEG 2 video 2 Orientation of the Motion vectors 2 Conclusions Computational complexity of Inter prediction Motion estimation of H 264 encoder of transcoder can be reduced by 90 1 Machine learning tool is Weka J4 8 3 Software used is JM reference software version 17 2 8 MPEG 2V12 reference software for MPEG 2 6 References 1 H Kalva et al An MPEG 2 to H 264 video transcoder in the baseline profile IEEE 2 3 4 5 6 7 8 9 Transactions on circuits and systems for video technology vol 20 no 5 pp 763 768 May 2010 G Fern ndez Escribano et al Reducing motion estimation complexity in MPEG 2 to H 264 transcoding in Proc IEEE International Conference Multimedia Expo ICME Beijing China pp 440 443 Jul 2 5 2007 I E G Richardson H 264 MPEG 4 part 10 in H 264 and MPEG 4Video Compression Hoboken NJ Wiley pp 159 223 2003 G Fern ndez Escribano et al A fast MB mode decision algorithm for MPEG 2 toH 264 Pframe transcoding IEEE Transactions on circuits and systems for video technology vol 18 no 2 pp 172 185 Feb 2008 JM software http iphome hhi de suehring tml MPEG 2 software http www mpeg org MPEG video mssg free mpeg software html M Isnardi MPEG 2 video compression Sarnoff corporation Nov 29 1999 W W Cohen and Y Singer A simple fast and effective rule learner in Proc 16th Natl Conf Artificial Intelligence Orlando FL pp 335 342 Jul 18 22 1999 T Wiegand and Gary J Sullivan Overview of H 264 AVC video coding standards IEEE Transactions on circuits and systems for video technology vol 13 no 7 pp 560 576 July 2003
View Full Document