计算机科学 ›› 2017, Vol. 44 ›› Issue (12): 274-278.doi: 10.11896/j.issn.1002-137X.2017.12.049

• 图形图像与模式识别 • 上一篇    下一篇

基于改进IGG模型的全景图像拼接缝消除算法

瞿中,李秀丽   

  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
  • 出版日期:2018-12-01 发布日期:2018-12-01
  • 基金资助:
    本文受重庆市基础与前沿计划项目(cstc2014jcyjA40033,cstc2015jcyjA40034),重庆市科委基础科学与前沿技术研究重点项目(cstc2015jcyjBX0090),重庆市教委科学技术研究项目(KJ1500410)资助

Algorithm of Eliminating Image Stitching Line Based on Improved IGG Model

QU Zhong and LI Xiu-li   

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

摘要: 为了提高序列图像拼接得到的全景图的质量,通常将L-M(Levenberg-Marquardt)算法用于图像拼接中变换模型的参数优化,但L-M算法不能消除误匹配点对模型求解的影响。为了消除误匹配点的影响,提出了基于IGG(Institute of Geodesy & Geophysics)函数模型的抗差L-M算法。首先利用IGG算法的迭代过程具有良好的抗粗差能力和可靠的收敛性等特点来优化变换模型,提高图像配准的精准度。然后采用自适应区域的拉普拉斯多分辨和最优拼接缝相结合的方法对拼接结果进行融合,以消除因拼接缝及光照不均而造成的过渡不连续现象。实验结果表明,所提算法不仅有效提高了配准精度,同时还实现了无缝拼接,获得了高质量的无缝拼接全景图。

关键词: 全景拼接,L-M算法,IGG方法,参数优化,拼接缝消除

Abstract: In order to improve the quality of panorama obtained by image stitching,L-M(Levenberg-Marquardt) algorithm is usually applied to the parameter optimization for image mosaic of the transform model,but it cannot eliminate the influence of mismatching points of the model solution.To solve this problem,robust L-M algorithm based on IGG function model was proposed.Firstly,the iterative process of IGG algorithm has the characteristics of strong resistance to gross error and high convergence speed,which contribute to optimize transformation model and improve the accuracy of image registration.Secondly,the method of combining Laplacian multi-resolution fusion algorithm of the adaptive region and the optimal stitching line is used to eliminate transition discontinuity,which is caused by the seam and uneven illumination.The experimental results show that the improvesd algorithm not only effectively improves the registration accuracy,but also achieves a seamless and high quality panorama.

Key words: Panoramic image mosaic,L-M algorithm,IGG method,Parameter optimization,Seam-line elimination

[1] HUANG C M,LIN S W,CHEN J H.Efficient Image Stitching of Continuous Image Sequence With Image and Seam Selections[J].IEEE Sensors Journal,2015,5(10):5910-5918.
[2] KUPER B,NETANYAHU N S,SHIMSHONI I.An EfficientSIFT Based Mode Seeking Algorithm for Sub-Pixel Registration of Remotely Sensed Images[J].IEEE Geoscience & Remote Sensing Letters,2015,2(2):379-383.
[3] ZHANG D,YU C G.Image Mosaic Technology Based on Feature Point Match[J].Computer Systems & Applications,2016,5(3):107-112.(in Chinese) 张东,余朝刚.基于特征点的图像拼接方法[J].计算机系统应用,2016,5(3):107-112.
[4] BROWN M,LOWE D G.Automatic Panoramic Image Stitching using Invariant Features[J].International Journal of Computer Vision,2007,4(1):59-73.
[5] PAUL S,PATI U C.Remote Sensing Optical Image Registration Using Modified Uniform Robust SIFT[J].IEEE Geoscience &Remote Sensing Letters,2016,3(9):1300-1304.
[6] CHIA W C,YEONG L S,CH’NG S I,et al.The effect of rainfall on feature points extraction and image stitching[C]∥2014 International Conference on Information Science,Electronics and Electrical Engineering (ISEEE).IEEE,2014:1382-1386.
[7] SHEN J,ZHAO Y,YAN S,et al.Exposure fusion using boosting Laplacian pyramid[J].IEEE Transactions on Cybernetics,2014,4(9):1579-1590.
[8] QU Z,QIAO G Y,LIN S P.A Fast Image Stitching Algorithm Eliminates Seam line and Ghosting[J].Computer Science,2015,2(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,2015,2(3):280-283.
[9] WAINE M,ROSSA C,SLOBODA R,et al.3D shape visualization of curved needles in tissue from 2D ultrasound images using RANSAC[C]∥IEEE International Conference on Robotics and Automation.IEEE,2015:4723-4728.
[10] WANG T J,CHENG L Z.Image mosaic via improved Leven-berg-Marquardt algorithm[J].Journal of Computer Application,2009,9(10):2693-2694.(in Chinese) 王腾蛟,成礼智.基于Levenberg-Marquardt改进算法的图像拼接[J].计算机应用,2009,9(10):2693-2694.
[11] MO C K,CHEN S X,HAO W U,et al.A Robust Estimation Based 3D Passive Locating Algorithm[J].Electronics Optics & Control,2015,2(2):22-26.

No related articles found!
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!