| 摘要 |
<p>A computer-based method for encoding and decoding quantized sequences in Wyner-Ziv coding of video. The method takes as input to an encoder a sequence of quantized data from a finite alphabet, the sequence comprising a video frame. Another sequence of data, decoded from the prior video frame, is input to a decoder. A statistical model describing the statistical relationship between the quantized input sequence to the encoder and the input sequence to the decoder is input to both the encoder and the decoder. A minimum field size is estimated from the statistical model at the encoder and the decoder separately. A bi-partite graph is provided, having variable nodes and check nodes, in which the alphabet of each check node is the minimum field size. At the output of the check nodes of the bi-partite graph there is generated a syndrome sequence of data in response to the quantized sequence fed into the variable nodes. Then the same bi-partite graph is used in an iterative process at the decoder to reconstruct the quantized sequence by repeatedly seeking to generate an output at the check nodes equal to the syndrome sequence.</p> |
