计算机科学 ›› 2016, Vol. 43 ›› Issue (5): 279-282.doi: 10.11896/j.issn.1002-137X.2016.05.053

• 图形图像与模式识别 • 上一篇    下一篇

一种改进的降低扭曲误差的快速图像拼接算法

瞿中,林嗣鹏,鞠芳蓉   

  1. 重庆邮电大学计算机科学与技术学院 重庆400065,重庆邮电大学计算机科学与技术学院 重庆400065,重庆邮电大学软件工程学院 重庆400065
  • 出版日期:2018-12-01 发布日期:2018-12-01
  • 基金资助:
    本文受重庆市教委科学技术研究项目(KJ1402001),重庆市科委基础与前沿项目(cstc2014jcyjA1347),重庆市高校优秀成果转化资助

Improved Algorithm of Fast Image Stitching by Reducing Panoramic Distortion

QU Zhong, LIN Si-peng and JU Fang-rong   

  • Online:2018-12-01 Published:2018-12-01

摘要: 通过提取SIFT特征进行图像拼接得到的全景图存在一定程度的扭曲误差,尤其当序列图像集合很大时,全景图扭曲现象更为严重。为提高全景图拼接质量,对Song Fuhua等人提出的图像拼接算法进行改进,首先改变参考图像的选取方式,提出图像序列中任意图像映射到与参考图像相同坐标系下的变换模型计算方法,并且在拼接过程中根据匹配特征点数目动态选取下次待拼接图像。与Song Fuhua等人提出的拼接算法相比,改进的图像拼接算法增加了图像重叠区域中SIFT特征点匹配对数,减小了参考图像SIFT特征检测区域。实验表明,提出的改进拼接算法提高了全景图拼接的时间效率,同时全景图扭曲现象也得到极大改善。

关键词: SIFT特征,图像配准,图像拼接,全景扭曲

Abstract: The traditional image stitching based on the SIFT feature points extraction,to a certain extent,has distortion errors.Especially,the panorama will get more seriously distorted when a panoramic result is composited by using a long image sequence.In order to create a high-quality panorama,the improved algorithm was proposed in this paper,including altering the way of selecting the reference image,and we put forward a method that can compute the transformation matrix for any image of the sequence to align with the reference image in the same coordinate space.Additionally,the improved stitching method dynamically selects the next input image based on the number of SIFT matching points.Compared with Song Fuhua’s stitching process,the improved methodincreases the number of matching feature points,and reduces SIFT feature detection area of the reference image.The experimental results show that the improved method can not only improve the efficiency of image stitching processing,but also reduce the panoramic distortion errors.

Key words: SIFT feature,Image registration,Image stitching,Panoramic distortion

[1] Kim H K,Lee K W,Jung J Y.A content-aware image stitching algorithm for mobile multimedia devices[J].IEEE Transactions on Consumer Electronics 2011,57(4):1875-1882
[2] Qu Zhong,Qiao Gao-yuan,Lin Si-peng.Fast Image Stitching Algorithm Eliminates Seam Line and Ghosting[J].Computer Scie-nce,2015,42(3):280-283(in Chinese) 瞿中,乔高元,林嗣鹏.一种消除图像拼接缝和鬼影的快速拼接算法[J].计算机科学,2015,42(3):280-283
[3] Chang R F,Chang-Chien K C,Takada,et al.Rapid image sti-tching and computer-aided detection for multipass automated breast ultrasound[J].Medical Physics,2010,37(5):2063-2073
[4] Qiu Xue-na,Liu Shi-rong,Liu Fei.An adaptive kernel-based target tracking method based on multiple features fusion[J].IEEE Transactions on Electrical and Electronic Engineering,2012,7(1):91-97
[5] Lowe D G.Distinctive image features from scale-invariant key-points[J].International Journal of Computer Vision,2004,60(2):91-110
[6] Brown M,Lowe D G.Automatic panoramic image stitchingusing invariant features[J].International Journal of Computer Vision,2007,74(1):59-73
[7] Song Fu-hua,Bin Lu.An automatic video image mosaic algo-rithm based on SIFT feature matching[C]∥International Conference on Communication,Electronics and Automation Engineering.2013:879-886
[8] Koo H I I,Kim B S,Cho N I.A new method to find an optimal warping function in image stitching[C]∥IEEE International Conference on Acoustics Speech and Signal Processing.2009:1289-1292
[9] Fu Qian-wen,He Ming-yi,Xu Chen-yu.A RANSAC image mosaic algorithm with preprocessing[J].Electronic Design Engineering,2013,21(15):183-186(in Chinese) 付倩文,何明一,徐晨宇.一种带预处理的RANSAC图像拼接算法[J].电子设计工程,2013,21(15):183-186
[10] Fu Yan-jun,Yang Kun-tao,Zou Wen-dong,et al.Image mosaic based on Levenberg-Marquardt algorithm[J].Laser Journal,2007,28(5):46-48(in Chinese) 伏燕军,杨坤涛,邹文栋,等.基于Levenberg-Marquardt算法的图像拼接[J].激光杂志,2007,28(5):46-48
[11] Zhou Xiao-jian,Ma Yi-zhong,Zhu Jia-gang,et al.Sequential-minimal-optimization algorithm for Solving Huber suppor-vector-regression with non-positive semi-definite kernels[J].Control Theory & Applications,2010,27(9):1178-1184(in Chinese) 周晓剑,马义中,朱嘉钢,等.求解非半正定核Huber-支持向量回归机问题的序列最小最优化算法[J].控制理论与应用,2010,27(9):1178-1184

No related articles found!
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!