Exact Subpixel Motion Estimation in DCT Domain.

摘要

Currently existing subpixel motion estimation algorithms require interpolation of inter-pixel values which undesirably increases the overall complexity and data flow and deteriorates estimation accuracy. In this paper, we develop DCT-based techniques to estimate subpel motion at different desired subpel levels of accuracy in DCT domain without interpolation. We show that subpixel motion information is preserved in the DCT of a shifted signal under some condition in the form of pseudo phases and establish subpel sinusoidal orthogonal principles to extract this information. Though applicable to other areas as well, the resulted algorithms from these techniques for video coding are flexible and scalable in terms of estimation accuracy with very low computational complexity O(N2) compared to O(N4) for Full Search Block Matching Approach and its subpixel versions. Above all, motion estimation in DCT domain instead of spatial domain simplifies the conventional hybrid DCT-based video coder, especially the heavily loaded feedback loop in the conventional design, resulting in a fully DCT-based high-throughput video codec. In addition, the computation of pseudo phases is local and thus a highly parallel architecture is feasible for the DCT-based algorithms. Finally simulation on video sequences of different characteristics shows comparable performance of the proposed algorithms to block matching approaches.