Frame-adaptive vector quantization for image sequence coding

An adaptive technique for image sequence coding that is based on vector quantization is described. Each frame in the sequence is first decomposed into a set of vectors. A codebook is generated using the vectors of the first frame as the training sequence, and a label map is created by quantizing the vectors. The vectors of the second frame are then used to generate a new codebook, starting with the first codebook as seeds. The updated codebook is then transmitted. At the same time, the label map is replenished by coding the position and the new values of the labels that have changed from one frame to the other. The process is repeated for subsequent frames. Experimental results for a test sequences demonstrate that the technique can track the changes and maintain a nearly constant distortion over the entire sequence