A neural network based transcoder for MPEG2 video compression

Abstract

In this paper, we proposed a neural network method for the high efficiency requatization in the design of a transcoder In our design, there are two types of video bitrate control in the proposed transcoder. One is the global adjusting of quantizer scales in which the adjusting is based on the complication of the whole frame, the other is the adaptive adjusting of quantizer scales, that the adjusting is the complication of the current macroblock. From our experimental results, the prototype transcoder can achieve desirable bitrate (1.5 Mbps) with an acceptable image quality. In additional, we constructed a video multiplexer for PPV or NVOD applications on the proposed transcoder.