Line matching method based on affine invariant feature and homography

Abstract

The invention relates to a line matching method based on affine invariant feature and homography. As line matching is lack of an effective geometric constraint of an epipolar line in point matching. A homography constraint is introduced as the geometric constraint of line segment matching to make up the defect that the line segment matching is lack of a strong geometric constraint. The invention additionally discloses a line segment automatic matching method based on the homography constraint. Line segments are transmitted and sleeved among images through the homography constraint, so that the searching difficulty for the line segments of the same name is reduced, and the matching accuracy is improved; the line segments of the same name are backwards searched after primary matching, so that matching errors are removed, and the matching accuracy is further improved. The method achieves the line segment automatic matching for remote-sensing image pairs.

Description

technical field [0001] The invention relates to a matching method of remote sensing images, in particular to a line matching method based on affine invariant features and a homography matrix. Background technique [0002] Using line features as matching primitives has obvious advantages in some specific applications, such as in 3D reconstruction of buildings (Habib 1998[1]). This is because: the buildings on the image contain a large number of straight line segments; the straight line segments are easy to detect and mostly have clear physical meaning; line features have more descriptive geometric constraints than point features, and are more reliable. [0003] However, compared to point matching, line segment matching is technically more difficult, mainly due to (Schmid and Zisserman 1997[2]; Baillard and Zisserman 2000[3]): (1) Extracting line segments from images, most of the line segments are broken, and the line segments The topological relationship between has been los...

AI Technical Summary

Problems solved by technology

[0003] However, compared to point matching, line segment matching is technically more difficult, mainly due to (Schmid and Zisserman 1997[2]; Baillard and Zisserman 2000[3]): (1) Extracting line segments from images, most of the line segments are broken, and the line segments The topological relationship between has been lost; (2) point matching has a strong constraint relationship such as epipolar geometry, while line matching lacks such a constraint relationship

[0004] At present, most digital photogrammetry systems in the world search for points with the same name through epipolar geometric constraints, but epipolar constraints cannot provide one-to-one correspondence between feature points.

Some researchers proposed to use the image points of the same name to form a triangulation to constrain the search range of the same-name straight line. This method requires pre-triangulation, and the efficiency is not high.

Images