A Novel Two-Step Approach for the Super-resolution Reconstruction of Video Sequences

In this paper, we propose a two-step approach for the super-resolution reconstruction of video sequences based on the degraded model. Firstly we use the sparse principal component analysis and the linear minimum mean square-error estimation method to remove the noises from the degraded video sequences. Secondly we adopt the Newton-Thiele's vector valued rational interpolation which is one of the nonlinear interpolation methods to magnify the results of the previous step. Our method is effective not only for gray video sequences, but also for color video sequences. Experimental results on a series of video sequences demonstrate that our method achieves better visual effects than those presented in [11] and [16], especially in details.