Iterative algorithm for improving the resolution of video sequences
Brian C. Tom, Aggelos K. Katsaggelos · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · 1996
This paper introduces an iterative and temporally recursive technique to improve the spatial resolution of a video sequence. Such iterative techniques have a number of advantages, among which are the ability to incorporate prior information into the restoration and the removal of the need for taking inverses of matrices. At each iteration, a residual (error) term is added to the current estimate of the high resolution frame. This residual term is based on a model which mathematically describes the relationship between the low resolution images and their corresponding high resolution images. This model incorporates the motion between the frames, and in the most general case, takes into account occlusions and newly uncovered areas. Experimental results are presented which demonstrate the capabilities of the proposed approach. Keywords: video enhancement , interpolation, motion compensation , subsampling