LOCAL ADAPTIVE LEARNING AND FUSION FOR SIDE INFORMATION INTERPOLATION IN DISTRIBUTED VIDEO CODING

Motivated by theoretical analysis Of the Curve fitting problem based on equivalent kernel, in this paper we propose a local adaptive learning and fusion model for side information interpolation in distributed video coding. In the proposed model, each pixel in the interpolated frame is approximated as the linear combination of samples within a local spatio-temporal window using kernel parameters as weight. The size of training window can be adaptive to the motion characteristic of video, from samples in which the kernel parameters can be locally learned. In order to further improve the quality of interpolated frames, we introduce a belief-projection based fusion strategy with adaptive weights for multiple interpolated results which are with the same time index. Experimental results demonstrate that the proposed learning and fusion model is effective in performance for side information interpolation in distributed video coding.