An HDTV-to-SDTV spatial transcoder

Both high-definition television (HDTV) and, standard-definition television (SDTV) use the MPEG-2 video coding standard, but they have different spatial resolutions. In order to support the interlaced video coding, MPEG-2 incorporates various macroblock prediction modes. Thus, the HDTV-to-SDTV transcoding needs to handle spatial resolution downscaling and various MEPG-2 macroblock prediction modes. We investigate schemes to exploit the correlations between the input and output video in the design of an HDTV-to-SDTV transcoder so that the computation can be greatly saved while the quality of video is preserved as much as possible. First, by utilizing the motion vectors and macroblock coding modes of the input video, efficient motion reestimation and macroblock mode decision algorithms are proposed. Then a novel picture target bit allocation algorithm taking advantage of the coding statistics of the input video is presented. Simulation results showing the effectiveness of the proposed approaches are also presented.