Both picture quality and coder's outputting bit-rate are important in the video coding process. An adaptive video coding algorithm is proposed in this paper. The algorithm takes into account both picture quality and coder' s outputting bit-rate. It gives out a reasonable Bayes-cost function and introduces Bayes decision method into the video coding process. The algorithm uses Bayes decision method to choose coding strategy in order to agree with the statistical sort of image macroblock. The algorithm chooses the coding strategy whose Bayes-cost is the minimum and the subjective assessment of the coding strategy is the best. At the same time

the algorithm\ngives out the trade-off parameterλbetween picture quality and coder' s outputting bit-rate. The trade-off parameterλis updated according the state of the buffer and the coder's outputting bit-rate is smoothed in order to make the best use of the channel. This method can get better quality of reconstructed picture and higher average PSNR.