An urban wide baseline image feature point matching method based on local geometric structure constraint

Abstract

The invention belongs to the technical field of image processing, and relates to an urban wide baseline image feature point matching method based on local geometric structure constraint, which comprises the following steps of S1, extracting point features and linear features, and obtaining local geometric structure information of feature points; S2, constructing a feature point supporting region;S3, acquiring a feature region and a feature descriptor; S4, performing initial matching based on the similarity of the feature descriptors, and obtaining a basic matrix between the initial matching set and the stereo image pairs; S5, carrying out secondary matching on the feature points which are not successfully matched and have at least two geometrical structure directions; S6, performing feature point matching expansion on the feature points which are not successfully matched; S7, combining all the matched matching sets, removing the wrong matching in the matching sets, and obtaining a final matching set. The method solves the problems that in the prior art, wrong matching is generated for feature points located at the discontinuous parallax position, and a reliable initial matching set is difficult to obtain, so that a final matching set is unreliable.

Description

technical field

[0001] The invention belongs to the technical field of image processing, and in particular relates to a feature point matching method of an urban wide baseline image constrained by a local geometric structure. Background technique

[0002] Image matching is one of the key scientific issues in the field of photogrammetry image processing. After decades of development, researchers have proposed many matching methods for different types of images. Existing image matching methods can be roughly divided into two categories: grayscale-based matching methods and feature-based matching methods.

[0003] For traditional downward-looking aerial images, due to the small pitch and roll angles and the relatively stable flight height of the platform, there are no obvious geometric differences such as scale, rotation, and perspective projection deformation between images. The grayscale-based matching method A higher matching accuracy can be obtained. Among grayscale-base...

Examples

Embodiment 1

[0084] Such as figure 1 As shown in , a feature point matching method of urban wide baseline image constrained by local geometric structure includes the following steps:

[0085] S1: Extract the point features and line features of the reference image and the search image, and obtain the local geometric structure information of each feature point based on it, such as figure 2 shown, including the following steps:

[0086] S1-1: Take the current feature point p i As the center, determine the local neighborhood R of size m×m i , and extract the local neighborhood R with i Intersecting non-parallel line features where N i is the number of non-parallel straight line features, l j Indicates the jth straight line feature;

[0087] S1-2: Take the current feature point p i As the origin, select the neighborhood straight line feature l extracted in step S1-1 j ,(j=1,...,N i ) parallel direction vector as the geometric structure direction of the feature point;

[0088] S1-3:...

technical field

[0001] The invention belongs to the technical field of image processing, and in particular relates to a feature point matching method of an urban wide baseline image constrained by a local geometric structure. Background technique

[0002] Image matching is one of the key scientific issues in the field of photogrammetry image processing. After decades of development, researchers have proposed many matching methods for different types of images. Existing image matching methods can be roughly divided into two categories: grayscale-based matching methods and feature-based matching methods.

[0003] For traditional downward-looking aerial images, due to the small pitch and roll angles and the relatively stable flight height of the platform, there are no obvious geometric differences such as scale, rotation, and perspective projection deformation between images. The grayscale-based matching method A higher matching accuracy can be obtained. Among grayscale-base...

Examples

Embodiment 1

[0084] Such as figure 1 As shown in , a feature point matching method of urban wide baseline image constrained by local geometric structure includes the following steps:

[0085] S1: Extract the point features and line features of the reference image and the search image, and obtain the local geometric structure information of each feature point based on it, such as figure 2 shown, including the following steps:

[0086] S1-1: Take the current feature point p i As the center, determine the local neighborhood R of size m×m i , and extract the local neighborhood R with i Intersecting non-parallel line features where N i is the number of non-parallel straight line features, l j Indicates the jth straight line feature;

[0087] S1-2: Take the current feature point p i As the origin, select the neighborhood straight line feature l extracted in step S1-1 j ,(j=1,...,N i ) parallel direction vector as the geometric structure direction of the feature point;

[0088] S1-3:...

Images