image registration——————图像配准

Posted 2022-09-22 ezreal-

（1）background：   

 Image registration：  the process of overlaying two or more images of the same scene taken at different times  from different viewpoints, and/or by different sensors. It geometrically aligns two images—the reference and sensed images

中文释义：图像配准是使用某种方法，基于某种评估标准，将一副或多副图片（局部）最优映射到目标图片上的方法。

 

附录———相近概念类比 

Dense image correspondence:  correspondence estimation is a task of matching pixels of one image with those of others; when referring to dense correspondence estimation,the emphasis is on finding suitable matches(correspondences) for every one those pixels; 

 （是图像配准的一个具体子目录？应用场景不同？）

 

（2）Method：

基于特征的图像配准方法

Feature detection：

Salient and distinctive objects(closed-boundary regions, edges, contours, line intersections, corners, etc.) are manually or, preferably, automatically detected. For further processing, these features can be represented by their point representatives (centers
of gravity, line endings, distinctive points), which are called control points (CPs) in the literature.

Feature matching：

In this step, the correspondence between the features detected in the sensed image and those detected in the reference image is established.
Various feature descriptors and similarity measures along with spatial relationships among the features are used for that purpose

Transform model estimation. 

The type and parameters of the so-called mapping functions, aligning the sensed image with the reference image, are estimated. The parameters of the mapping functions are computed by means of the established feature correspondence.

 Image resampling and transformation

the sensed image is transformed by means of the mapping functions.image values in non-integer coordinates are computed by the appropriate interpolation technique.

 

 

 

 

 

 

参考文献： 

【1】Armin M A, Barnes N, Khan S, et al. Unsupervised Learning of Endoscopy Video Frames’ Correspondences from Global and Local Transformation[M]//OR 2.0 Context-Aware Operating Theaters, Computer Assisted Robotic Endoscopy, Clinical Image-Based Procedures, and Skin Image Analysis. Springer, Cham, 2018: 108-117.

【2】知乎专栏 https://zhuanlan.zhihu.com/p/62210477

【3】Image registration methods: a survey