测绘学报 ›› 2021, Vol. 50 ›› Issue (7): 916-929.doi: 10.11947/j.AGCS.2021.20200492

• 摄影测量学与遥感 • 上一篇    下一篇

结合张量与互信息的混合模型多模态图像配准方法

李培1, 姜刚1,2, 马千里1, 薛万峰1, 杨伟华1   

  1. 1. 长安大学地质与测绘工程学院, 陕西 西安 710054;
    2. 西部矿产资源与地质工程教育部重点实验室, 陕西 西安 710054
  • 收稿日期:2020-10-21 修回日期:2021-04-21 发布日期:2021-08-13
  • 作者简介:李培(1996-),男,硕士,研究方向为多模态图像配准。E-mail:1239608938@qq.com
  • 基金资助:
    国家自然科学基金(41977231)

A hybrid model combining tensor and mutual information for multi-modal image registration

LI Pei1, JIANG Gang1,2, MA Qianli1, XUE Wanfeng1, YANG Weihua1   

  1. 1. College of Geology Engineering and Geomatics, Chang'an University, Xi'an 710054, China;
    2. Key Laboratory of Western China's Mineral Resources and Geological Engineering, Ministry of Education, Xi'an 710054, China
  • Received:2020-10-21 Revised:2021-04-21 Published:2021-08-13
  • Supported by:
    The National Natural Science Foundation of China (No. 41977231)

摘要: 多模态图像之间存在显著的非线性强度差异,并且图像会因为噪声而退化,因此,多模态图像自动配准是一项具有挑战性的任务。为了解决这两个问题,本文提出一种多模态图像自动配准方法,该方法分为预配准和精配准两个阶段。在预配准阶段,通过改进SIFT算法来大致对齐多模态图像。在精配准阶段,首先,利用块Harris检测器在预配准后的参考图上提取均匀分布的特征点。然后,通过各向异性结构张量捕捉多模态图像中的结构信息来构建特征描述符,该特征描述符对噪声具有稳健性。更进一步,本文结合张量方向平行度和梯度互信息提出了一种相似度准则(tensor orientation and mutual information,TOMI)。最后,本文用多种模态图像(包括Optical,LiDAR,SAR和Map)来评估提出的方法。试验结果表明,本文提出的方法对非线性强度变化和噪声具有较好的稳健性,并且匹配效果优越。

关键词: 各向异性滤波, 多模态图像, 结构张量, 相似度准则, 图像配准

Abstract: There are significant nonlinear intensity differences between multi-modal images. Moreover, the noise in these images will cause image degradation. Therefore, the automatic registration of multi-modal images is a challenging task. To address the two problems, this paper proposes a multi-modal image automatic registration method, which is divided into two stages: pre-registration and fine registration. In the pre-registration stage, an improved SIFT algorithm is used to roughly align multi-modal images. In the fine registration stage, the block Harris detector is first used to extract evenly distributed feature points on the pre-registered reference image. Then, the structure information in the multi-modal images is captured by the anisotropic structure tensor to construct a feature descriptor, which is robust to noise. Furthermore, a similarity criterion named TOMI (tensor orientation and mutual information) is proposed combining the tensor orientation parallelism and gradient mutual information. Finally, Multi-modal images (including Optical, LiDAR, SAR, and Map data) are used to evaluate the proposed algorithm. The experimental results show that the method proposed in this paper is robust to nonlinear intensity differences and noise, and the matching effect is superior.

Key words: anisotropic filtering, multi-modal images, structure tensor, similarity criterion, image registration

中图分类号: