A new motion-compensated reduced-order model Kalman filter to space-varying restoration of progressive and interlaced video

A motion-compensated reduced order model Kalman filter for restoring progressive and interlaced video is derived. The formulation is then extended to include mean-residual signal modeling and to develop a motion compensation approach to reduce artifacts resulting from fix-lag recursive linear space-varying (LSV) filtering. It is shown that the filters effectively restores images degraded by LSV blurs and additive noise.