Image registration method of sparse feature matching on the basis of local linear constraint

Abstract

The invention provides an image registration method of sparse feature matching on the basis of local linear constraint. The image registration method comprises the following steps: firstly, inferring an assumed matching set; then, utilizing a displacement function to define transformation Z, utilizing a diagonal matrix to point out a matching confidence level, solving a weight matrix, and obtaining an energy function; and finally, adopting a deterministic annealing technique to optimize and solve the energy function to obtain the transformation Z, and combining the transformation Z with bilinear interpolation to execute image registration. The image registration method of sparse feature matching on the basis of local linear constraint carries out global linear constraint on point matching by aiming at the problem of non-rigidity deformation since a remote sensing image is subjected to topographic relief, the point matching is subjected to the local linear constraint, and a local structure in a feature set can be protected after an image is transformed so as to improve image registration accuracy.

Description

technical field [0001] The invention relates to an image registration method for sparse feature matching based on local linear constraints, and belongs to the technical field of image processing. Background technique [0002] Image registration is a fundamental and challenging problem in the field of remote sensing and a prerequisite in many wide-ranging applications including terrain reconstruction, environmental monitoring, change detection, image mosaicing, image fusion, and map updating, etc. [0003] Image registration aims to establish the correspondence between pixels between two images of the same scene acquired at different times and from different perspectives or by different detectors. Registration problems can be classified as rigid or nonrigid, depending on the application and data format. Rigid registration (involving only a small number of parameters) is relatively easy and has been extensively studied. In contrast, non-rigid registration is more difficult, ...

AI Technical Summary

Problems solved by technology

[0006] In order to solve the deficiencies of the prior art, the present invention provides an image registration method based on sparse feature matching based on local linear constraints. Aiming at the problem of non-rigid deformation caused by terrain fluctuations in remote sensing images, local linear constraints are applied to point matching, which can Improving image registration accuracy by preserving local structure in feature sets after image transformation

Images