High-resolution remote sensing image registration method with control points distributed in adaptive manner

Abstract

The invention discloses a high-resolution remote sensing image registration method with control points distributed in an adaptive manner. By the use of the high-resolution remote sensing image registration method, a multi-scale J-image is introduced into image registration. A self-adaptive control points extracting method based on a partitioning strategy is provided to extract the control points of the multi-scale J-image image, thus the defect that the control points only sense specific directional high-frequency information is overcome. A self-adaptive control points extracting strategy is defined so as to limit control point distribution. The control points are subjected to multi-scale matching by NMI (normalized mutual information measure), allowing registration function smooth. Geometric correction is realized by adopting Delaunay triangle local transformation. In the following text, basic principle and key steps of the algorithm are introduced, and three remote-sensing image groups of different types are subjected to experiment and analysis and comparison experiments with various registration methods based on wavelet transform and NSCT (non-subsampled contourlet transform).

Description

technical field [0001] The invention relates to a high-resolution remote sensing image registration method with self-adaptive distribution of control points and belongs to the technical field of remote sensing image registration. Background technique [0002] 1 Basic framework of image registration [0003] With the wide application of high-resolution remote sensing images, image registration for high-resolution remote sensing images has become an important topic in the field of remote sensing application research. The basic framework of image registration mainly includes the following aspects: [0004] (1) Feature space refers to the image features extracted from the reference image and the image to be registered, mainly including grayscale features, point features, edge features, and moment-invariant structural features. [0005] (2) Search space refers to the range and method of image registration transformation during geometric correction. Among them, the transformati...

AI Technical Summary

Problems solved by technology

When the existing multi-scale registration algorithm constrains the distribution of control points, it usually chooses to extract a certain number of control points in a certain size window, so it is difficult to ensure a reasonable distribution of point sets with the same name

Finally, the control point matching strategy currently used in image registration based on point features usually only considers the gray statistical characteristics of local areas, while ignoring the texture, scale and other characteristics of the original image, which is easily disturbed by noise and other factors , reducing the reliability of the point set with the same name and increasing the possibility of mismatching

Images