Computation reduction for motion estimation in MPEG-4 video encoder
Chunxi Chen, Ruijia Li · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · 2004
In this paper, computation reduction algorithm of motion estimation is developed for MPEG4 video encoders. Our focus is on the computation reduction for block based integer and half pixel search. A method is proposed to reduce the search points and computation with little extra tradeoff and small quality downgrade. In MPEG4, the motion estimation is mainly composed of three major parts: 1) The Macroblock based integer pixel search. 2) The block based integer pixel search. 3) The half pixel search. The Macroblock based integer pixel search usually consumes the most computation power. Therefore many fast search algorithms are employed instead of the full search. In contrast, as to 2), 3), since the search range is quite small, usually the full search method is used. With many novel algorithms the computation requirements in 1) decrease greatly. Hence, the percentage of 2) and 3) are increasing and come to an important position for computation reduction. The method proposed in this paper jointly considered the ME, DCT and quantization. It takes advantage of the idea in both MB and block layer. The computation reduction is obvious from experiment. Because the full search algorithm is still in use, the quality downgrade is little compared to the old computation reduction algorithms.