A method to improve the registration accuracy of images taken at night

Abstract

A method for improving the registration precision of images photographed at night specifically includes the steps that images to be in registration are input; graying is performed on the images; histogram equalization is performed; characteristic points are detected; the characteristic points are matched; mistaken characteristic point matching pairs are removed through an RANSAC algorithm; whether characteristic points of images photographed under the flashlight condition are too concentrated or not is judged, if yes, characteristic point matching pair equalization is performed, and if not, an affine transformation matrix is solved directly through detected characteristic point matching pairs; the characteristic point matching pairs are equalized; equations are formulated through the characteristic point matching pairs, an equation set is solved, and an affine transformation matrix is obtained; image registration is performed. According to the method, matching pairs can be added in a self-adaptive mode according to the position information of the detected characteristic point matching pairs, the characteristic points can be distributed more evenly, the problem that because the characteristic points are too concentrated, overfitting is caused is avoided, and the registration precision of the images photographed at night is improved.

Description

technical field [0001] The invention belongs to the technical field of image processing, and further relates to a method for improving the registration accuracy of images taken at night in the technical field of image registration. The present invention is used in registration preprocessing for fusion of a single-frame flashlight image and multi-frame non-flashlight images to improve the quality of photographing at night, can effectively avoid ghosting and blurring, and greatly improve the quality of image fusion. Background technique [0002] At present, there are mainly frequency-domain-based methods and time-domain-based methods for image registration at night. The most representative method based on the time domain is the feature-based method. This method extracts feature points from the image to be registered according to the feature point extraction algorithm, and uses the feature points to perform image registration. The advantages of the feature-based method are sca...

AI Technical Summary

Problems solved by technology

This method has a good registration effect on images to be registered with little change in illumination, but there is still a disadvantage that for images to be registered with large changes in illumination intensity, there will be few feature points extracted, or the extracted The feature points are too concentrated, resulting in overfitting and reducing the registration accuracy

The disadvantage of this method is that when this method is applied to the image registration of night shooting with and without flash, it does not consider the uneven distribution of illumination, resulting in uneven distribution of detected feature points , which causes overfitting, causing the image to be registered only in a certain area

Images