测绘学报 ›› 2018, Vol. 47 ›› Issue (1): 71-81.doi: 10.11947/j.AGCS.2018.20170368

• 摄影测量学与遥感 • 上一篇    下一篇

顾及灰度和梯度信息的多模态影像配准算法

闫利, 王紫琦, 叶志云   

  1. 武汉大学测绘学院, 湖北 武汉 430079
  • 收稿日期:2017-07-04 修回日期:2017-11-13 出版日期:2018-01-20 发布日期:2018-02-05
  • 作者简介:闫利(1966-),男,博士,教授,研究方向为摄影测量与遥感。E-mail:lyan@sgg.whu.edu.cn
  • 基金资助:
    国土资源部公益性行业科研专项经费资助项目(201511009)

Multimodal Image Registration Algorithm Considering Grayscale and Gradient Information

YAN Li, WANG Ziqi, YE Zhiyun   

  1. School of Geodesy and Geomatics, Wuhan University, Wuhan 430079, China
  • Received:2017-07-04 Revised:2017-11-13 Online:2018-01-20 Published:2018-02-05
  • Supported by:
    The Special Scientific Research Fund of Land and Resource Public Welfare Profession of China (No. 201511009)

摘要: 基于特征匹配的多模态影像配准方法无法达到像素级配准精度要求。本文研究了一种顾及灰度和梯度信息的多模态影像配准算法。基于马尔科夫随机场(MRF)的非参数化配准模型充分利用多模态影像的图像信息进行相似性测量,同时考虑了灰度及梯度统计信息,求解方法上对值空间进行离散化,提高收敛速度。通过3组多模态影像的配准试验,验证了该算法的可行性。试验表明:本文算法的配准效果优于基于人工刺点的多项式模型配准和只考虑灰度信息的多模态影像配准;与此同时,该算法对于较大形变的影像配准也具有一定的适用性。在空间精度方面,平均配准误差小于1个像素,最大配准误差小于2个像素。

关键词: 多模态影像, 梯度信息, 马尔科夫随机场, 离散优化, 非参数化配准

Abstract: Multimodal image registration method based on feature matching can't satisfy the demands of pixel level registration precision.This paper proposes a multimodal image registration algorithm considering grayscale and gradient information.The nonparametric registration model based on Markov random field (MRF) makes full use of the image information of multimodal image to measure the similarity which considers the grayscale and the gradient statistical information are considered,and the value space is discretized to improve the convergence speed.The algorithm is validated both qualitatively and quantitatively demonstrating its potentials on three groups of multimodal image registration experiments.The result indicates that the proposed algorithm is superior to the polynomial model registration based on manual selection and the multimodal image registration only with gray information only.At the same time,this algorithm has some applicability for multimodal image registration of large deformation.In terms of spatial accuracy,the average registration error is less than 1 pixel and the maximum registration error is less than 2 pixels.

Key words: multimodal image, gradient information, Markov random field, discrete optimization, non-parametric registration

中图分类号: