Method and system for remote sensing image registration based on directed line segments

Abstract

The invention relates to the technical field of image processing, and specifically discloses a remote sensing image registration method based on directed line segments. This method first uses the BRISK algorithm to extract rough matching point pairs, and then uses two sets of matching point sets to construct directed line segment sets in the reference image and the image to be registered respectively, and uses the F-norm criterion as a method of adjacent line segment matching for directed Line segment matching, and finally based on the probability and statistics model to accurately locate the matching point, solve the registration parameters, and then obtain the registration reference image and the image to be registered for registration. In addition, the invention also provides a remote sensing image registration system based on directed line segments. The present invention fully considers the texture information of the image when constructing the directed line segment features, and performs feature point matching, thereby achieving the technical effects of effectively eliminating incorrectly matching points and obviously improving the matching accuracy.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to a remote sensing image registration method and system based on directed line segments. Background technique [0002] Image registration is one of the key technologies in remote sensing image processing, target recognition, image reconstruction, robot vision and other fields, and is the basis of image stitching technology. [0003] At present, the remote sensing image registration is mainly divided into two categories: the registration method based on the region gray level and the registration method based on the feature. [0004] Among them, the commonly used image registration methods based on the area gray level include: cross-correlation method, FFT-based phase correlation method and mutual information method. [0005] The general technical means are as follows: the method based on image features first extracts features such as edges, corners, contours and area cente...

AI Technical Summary

Problems solved by technology

However, although the traditional BRISK algorithm has a speed advantage, it has poor robustness and high error matching rate, and often cannot meet the accuracy requirements of image registration.

Images