Spatio-Temporal Adaptive Super-Resolution Reconstruction Model Based on Zemike Moment for Spatial Video Sequences

Video Super-Resolution(SR) reconstruction produces video sequences with High Resolution(HR) via the fusion of several Low-Resolution(LR) video frames.Traditional methods rely on the accurate estimation of subpixel motion,which constrains their applicability to video sequences with relatively simple motions such as global translation.We propose an efficient iterative spatio-temporal adaptive SR reconstruction model based on Zernike Moment(ZM),which is effective for spatial video sequences with arbitrary motion.The model uses region correlation judgment and self-adaptive threshold strategies to improve the effect and time efficiency of the ZM-based SR method.This leads to better mining of non-local selfsimilarity and local structural regularity,and is robust to noise and rotation.An efficient iterative curvature-based interpolation scheme is introduced to obtain the initial HR estimation of each LR video frame.Experimental results both on spatial and standard video sequences demonstrate that the proposed method outperforms existing methods in terms of both subjective visual and objective quantitative evaluations,and greatly improves the time efficiency.

Video Super-Resolution （SR） reconstruction produces video sequences with High Resolution （HR） via the fusion of several Low-Resolution （LR） video frames. Traditional methods rely on the accurate estimation of subpixel motion, which constrains their applicability to video sequences with relatively simple motions such as global translation. We propose an efficient iterative spatio-temporal adaptive SR reconstruction model based on Zemike Moment （ZM）, which is effective for spatial video sequences with arbitrary motion. The model uses region correlation judgment and self-adaptive threshold strategies to improve the effect and time efficiency of the ZM-based SR method. This leads to better mining of non-local self-similarity and local structural regularity, and is robust to noise and rotation. An efficient iterative curvature-based interpolation scheme is introduced to obtain the initial HR estimation of each LR video frame. Experimental results both on spatial and standard video sequences demonstrate that the proposed method outperforms existing methods in terms of both subjective visual and objective quantitative evaluations, and greatly improves the time efficiency.