A context modeling algorithm and its application in video compression

A new algorithm for context modeling of binary sources with application to video compression is presented. Our proposed method is based on a tree rearrangement and tree selection process for an optimized modeling of binary context trees. We demonstrate its use for adaptive context-based coding of selected syntax elements in a video coder. For that purpose we apply our proposed technique to the H.264/AVC standard and evaluate its performance for different sources and different quantization parameters. Experimental results show that by using our proposed algorithm coding gains similar or superior to those obtained with the H.264/AVC CABAC algorithm is achieved.