基于AKAZE算法的图像拼接研究
作者:
作者单位:

湘潭大学信息工程学院湘潭411105

中图分类号:

TN911.73; TP391.41

基金项目:

国家自然科学基金(61175075)、湖南省教育厅重点项目(14A137)资助


Research of image stitching based on AKAZE algorithm
Author:
Affiliation:

College of Information Engineering, Xiangtan University, Xiangtan 411105, China

  • 摘要
  • | |
  • 访问统计
  • |
  • 参考文献 [16]
  • |
  • 相似文献 [20]
  • | | |
  • 文章评论
    摘要:

    针对基于KAZE特征检测的图像拼接算法实时性问题,提出一种简单有效的AKAZE拼接算法。该算法首先通过AKAZE算法提取图像特征点,接着计算MLDB描述符从而生成特征向量。随后计算特征向量之间的汉明距离,提取出匹配的特征点对,然后利用RANSC算法估算全局单应性矩阵,根据动态线性变换算法求取重叠区域局部投影关系,结合两者统一投影平面,最后利用加权融合实现两幅图像的拼接。对KAZE、SIFT、SURF、ORB、BRISK进行性能实验比较,所用算法不仅对于高斯模糊、角度旋转、尺度变换和亮度变化等情况下保持良好的性能,而且处理时间大大缩短,实现了有效的图像拼接。

    Abstract:

    To solve the timeconsuming problem of image stitching algorithm based on KAZE, a simple and effective image stitching algorithm based on AKAZE is proposed. Firstly, AKAZE feature points are extracted. Secondly, feature vectors are constructed using the MLDB descriptor and matched by computing the Hamming distance. Thirdly, wrong matches are eliminated by RANSAC and the global homography transform, and then a local projection transform is estimated using moving direct linear transformation in the overlapping regions. The image registration is achieved by combining the two transforms. Finally, the weighted fusion method fuses the images. A performance comparison test can be conducted aiming at KAZE, SIFT, SURF, ORB, BRISK. The experimental results show that the proposed algorithm has better robustness for the various transform, and the processing time is greatly reduced.

    参考文献
    [1]郭晓冉,崔少辉.基于局部特征点配准的图像拼接算法[J].半导体光电, 2014, 35(1): 8994. GUO X R,CUI SH H.Image mosaic approach using local feature points registration[J].Semiconductor Optoelectronics, 2014, 35(1): 8994.
    [2]周美丽, 白宗文, 延小进. 基于相位相关法的图像拼接系统设计[J]. 国外电子测量技术, 2015,34 (5): 3133. ZHOU M L,BAI Z W,YAN X J.Design of the image mosaic system based on phase correlation method[J].Foreign Electronic Measurement Technology,2015, 34(5): 3133.
    [3]陈凌颖, 杨世武. 铁路视频监控中基于多算法结合的图像拼接[J]. 电子测量与仪器学报, 2012,26(3): 229235. CHEN L Y,YANG SH W. Image mosaic method based on combination of some algorithms in railway video monitoring[J]. Journal of Electronic Measurement and Instrument,2012, 26(3): 229235.
    [4]LEUTENEGGER S, CHLI M, SIEGWART R Y. BRISK: Binary robust invariant scalable keypoints [C]. 2011 IEEE International Conference on Computer Vision (ICCV), 2011: 25482555.
    [5]RUBLEE E, RABAUD V, KONOLIGE K, et al. ORB: An efficient alternative to SIFT or SURF[C]. 2011 IEEE International Conference on Computer Vision (ICCV), 2011: 25642571.
    [6]ALCANTARILLA P F, BARTOLI A, DAVISON A J. KAZE features[C].Computer VisionECCV 2012. Berlin Heidelberg: Springer, 2012: 214227.
    [7]ALCANTARILLA P, NUEVO J, BARTOLI A. Fast explicit diffusion for accelerated features in nonlinear scale spaces[C]. Proceedings of British Machine Vision Conference 2013:13.1131.1
    [8]GREWENIG S, WEICKERT J, BRUHN A. From box filtering to fast explicit diffusion[C].Pattern Recognition. Berlin Heidelberg: Springer, 2010: 533542.
    [9]LU F, WU ZH ZH, XIANG L. Fast image diffusion for feature detection and description [J]. International Journal of Computer Theory and Engineering, 2016, 8(1): 5862.
    [10]CALONDER M, LEPETIT V, STRECHA C, et al. Brief: Binary robust independent elementary features[C]. Computer Vision–ECCV 2010. Berlin Heidelberg: Springer, 2010: 778792.
    [11]YANG X, CHENG K T. LDB: An ultrafast feature for scalable augmented reality on mobile devices[C]. 2012 IEEE International Symposium on Mixed and Augmented Reality (ISMAR), 2012: 4957.
    [12]PILCHER C D, WONG J K, PILLAI S K. Inferring HIV transmission dynamics from phylogenetic sequence relationships [J]. Plos Med, 2008, 5(3):350352.
    [13]ZARAGOZA J, CHIN T J, BROWN M, et al. Asprojectiveaspossible image stitching with moving DLT[C].Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2013: 23392346.
    [14]王灿进, 孙涛, 陈娟. 基于FREAK特征的快速景象匹配[J]. 电子测量与仪器学报,2015, 29(2): 204212. WANG C J,SUN T,CHEN J.Rapid scene matching based on FREAK descriptor[J].Journal of Electronic Measurement and Instrumentation,2015,29(2): 204212.
    [15]郑永斌, 黄新生, 丰松江. SIFT 和旋转不变 LBP 相结合的图像匹配算法[J]. 计算机辅助设计与图形学学报, 2010, 22(2): 286292. ZHENG Y B, HUANG X SH, FENG S J. An image matching algorithm based on combination of SIFT and the rotation invariant LBP[J].Journal of ComputerAided Design & Computer Graphics,2010, 22(2): 286292.
    [16]衷伟岚,周力,袁臻.一种KAZE算法在人脸图像匹配中的应用[J].计算机系统应用, 2014, 23(4): 144148. ZHONG W L, ZHOU L, YUAN ZH.Application of KAZE algorithm in human face image matching[J].Computer Systems and Applications, 2014, 23(4): 144148.
    引证文献
    网友评论
    网友评论
    分享到微博
    发 布
引用本文

闫璠,张莹,高赢,涂勇涛,张东波.基于AKAZE算法的图像拼接研究[J].电子测量与仪器学报,2017,31(1):36-44

复制
分享
文章指标
  • 点击次数:11444
  • 下载次数: 47059
  • HTML阅读次数: 0
  • 引用次数: 0
历史
  • 在线发布日期: 2017-07-20
文章二维码