一种基于四叉树的分片泊松图像无缝融合算法  

A Quadtree Based Piecewise Poisson Seamless Composition Algorithm for Image Stitching

作　　者：王晓明 朱一心[2] WANG Xiao-ming;ZHU Yi-xin(School of Science,Shandong Jiaotong University,Ji'nan 250357,China;School of Mathematical Science,Capital Normal University,Beijing 100048,China)

机构地区：[1]山东交通学院理学院,山东济南250357 [2]首都师范大学数学科学学院,北京100048

出　　处：《数学的实践与认识》2023年第3期220-228,共9页Mathematics in Practice and Theory

摘　　要：基于四叉树的思想,提出了一种图像分片融合算法,通过求解若干建立在梯度域上的低维泊松方程组,实现了图像无缝融合.相比较传统的泊松算法,这种分片处理策略,一方面大大降低了大幅宽图像融合对计算机内存和计算性能的要求,为普通计算机处理大幅宽图像融合提供了新的途径,同时也能支持并行处理,从而提升大幅宽图像融合效率.算法保证了融合图像整体上分片连续,有效去除了接缝,适用于超高分辨率或航拍等大幅宽图像拼接问题.A piecewise composition algorithm is proposed for ultra wide stitching image,which solves several low-dimensional Poisson equations based on gradient domain to achieve seamless image.This piecewise processing strategy,on the one hand,greatly reduces the requirements for computer memory and computing performance,which provides a new way for ordinary computers to process large-width image composition,and also supports parallel processing to improve the efficiency of image seamless composition.The algorithm guarantees piecewise continuous of the whole composed image,effectively eliminates seams,and is suitable for ultra-wide image stitching problems such as ultra-high resolution or aerial photography.

关 键 词：图像拼接 无缝融合 分片 泊松方程 四叉树 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]