基于改进最佳缝合线的大视差岩心图像拼接算法  

A large parallax core image mosaic algorithm based on improved best stitching-seam

作　　者：程诗翩 何海波 卿粼波[1] 何小海[1] CHENG Shipian;HE Haibo;QING Linbo;HE Xiaohai(College of Electronics and Information Engineering,Sichuan University,Chengdu 610065,China;Chengdu Xitu Technology Co.Ltd.,Chengdu 610065,China)

机构地区：[1]四川大学电子信息学院,成都610065 [2]成都西图科技有限公司,成都610065

出　　处：《智能计算机与应用》2020年第9期21-24,共4页Intelligent Computer and Applications

摘　　要：在大视差岩心图像拼接中,传统的图像配准算法难以对齐图像,最佳缝合线算法融合的图像也不自然。针对这一问题,本文提出了一种基于改进最佳缝合线的大视差岩心图像拼接算法。首先,用贝叶斯特征模型剔除匹配异常值,再由正确的匹配点构造变形函数;其次,对重叠区域中间部分进行图像变形以对齐图像,在该区域建立最佳缝合线的能量函数,并引入视差信息到能量函数当中,以减小视差误差;最后,利用动态规划思想找到最佳缝合线并缝合图像,有效实现了大视差岩心图像拼接。通过多组实验对比,结果表明本文算法能够使大视差岩心图像拼接地更加自然,拼接结果更接近真实场景。In the large parallax core image stitching,the traditional image matching algorithm is difficult to align the image,and the image fused by the best stitching-seam is not natural.Aiming at this problem,this paper proposed an image mosaic algorithm for large parallax core images based on improved best stitching-seam.First,we use the Bayesian feature model to eliminate matching outlier,and then construct the deformation function from the correct matching points.Then,the center of the overlapping region is deformed to align the image,and the energy function of the best suture is established in the region.And parallax information is introduced into energy function to reduce parallax error.Finally,we use the idea of dynamic programming to find the best stitching-seam and merge images,and large parallax core image mosaic is realized effectively.By comparing multiple sets of experiments,the results show that the algorithm in this paper can make the stitching of large parallax core images more natural,and the stitching results are closer to the real scene.

关 键 词：大视差 图像拼接 图像变形 能量函数 最佳缝合线 

分 类 号：TP399[自动化与计算机技术—计算机应用技术]