Abstract: This paper proposes a Super-resolution(SR) algorithm with adaptive regularization based on weight. In case of existence of local motion and/or occlusion, regions that have local motion and/or occlusion have different noise level. To cope with this problem, it proposes to adaptively weight each region according to its reliability and the regularization parameter is simultaneously estimated for each region. The regions are generated by segmenting the reference frame using watershed segmentation. Experimental results show the effectiveness of the algorithm.

Key words: Super-resolution(SR) algorithm, image registration, local weighting, adaptive regularization, fusion

摘要： 不精确的配准参数会使图像重建结果不理想。为此，提出一种基于权值的自适应正则化超分辨率算法。自适应局部区域权值根据该区域的可靠性进行自适应运算，利用分水岭分割将参考图像分成不同区域，由此提升重建质量。对真实视频序列的实验结果证明该算法有效。

关键词: 超分辨率算法, 图像配准, 局部加权, 自适应正则化, 融合

CLC Number: 

• TP391