本文将距离加权运算运用到卷积运算上提出了改进的图像镶嵌算法。该算法针对重叠区域图像边缘灰度之间的差异,考虑到中心像元与周围像元之间的相关关系,即临近像元效应,因而需要采用一定的方法来消除或减小这种影响效应,基于空间分析方法给出了像元权重因子的求解,确定出了周围像元对中心像元灰度的影响。之后运用此权重因子采用卷积距离加权算法实现了影像的无缝镶嵌。文中最后对算法在时间和视觉效果上做出了一定的评价。经与其他3种镶嵌算法分析对比,该算法简单易行、耗时少、效率高,达到了良好的视觉效果。

Applying distance weighted factor to the convolution method,the authors put forward an algorithm of image mosaic.Firstly,the algorithm considers the grey scale difference in the edges of image in overlapping area and the relation of neighboring points,it is necessary to use some ways to eliminate or decrease the impact of adjacent pixels,so we must calculate the weight factor,in this paper we make use of spatial in mathematics to compute pixel weighted factor.Secondly,we adopt the convolution method and distance weighted adopetd to realize the seamless mosaic of remote sensing images.Finally,we make some assessments to this algorithm in time spending and visual effect.Many experiments demonstrate that the proposed method is simple and easy,and it has less time consumption and higher efficiency.Adopting the algorithm to deal with the overlapping area can get favorite visual effect.