CN-121981881-A - Image displacement determination method and image pickup apparatus position determination method

Abstract

The application relates to the technical field of equipment control, and discloses an image displacement determining method and an image pickup equipment position determining method, wherein the method comprises the following steps: the method comprises the steps of obtaining a first image and a second image, respectively extracting characteristic points on the first image and the second image, matching the characteristic points, generating a plurality of translation vectors, determining first distances among the plurality of translation vectors, determining inner point sets corresponding to the translation vectors according to the first distances, calculating lengths of the translation vectors corresponding to the inner point sets with the largest number of the inner points, and determining the lengths of the translation vectors as image displacement. By the method, the control device can accurately determine the displacement between the first image and the second image, and the image displacement is calculated in a simple step with small calculation amount.

Inventors

• ZHOU YONGCHENG
• YAO PEIYONG

Assignees

• 深圳市睿联技术有限公司

Dates

Publication Date

20260505

Application Date

20251229

Claims (11)

1. 1. A method of image displacement determination, the method comprising: acquiring a first image and a second image; Extracting characteristic points on the first image and the second image respectively, and matching the characteristic points to generate a plurality of translation vectors; determining a first distance between the plurality of translation vectors, and determining an inner point set corresponding to each translation vector according to the first distance; calculating the length of the translation vector corresponding to the inner point set with the largest number of inner points; The length of the translation vector is determined as the image displacement.
2. 2. The image displacement determination method according to claim 1, wherein the extracting feature points on the first image and the second image, respectively, specifically comprises: Identifying the first image and the second image, and determining a static area of the first image and a static area of the second image; and respectively extracting the characteristic points of the static area on the first image and the characteristic points of the static area on the second image.
3. 3. The image displacement determination method according to claim 1, wherein the extracting feature points on the first image and the second image, respectively, specifically comprises: Extracting feature points of the first image to obtain a plurality of first feature points and first feature vectors corresponding to the first feature points; And extracting the feature points of the second image to obtain a plurality of second feature points and second feature vectors corresponding to the second feature points.
4. 4. The method of determining image displacement according to claim 2, wherein the matching the feature points generates a plurality of translation vectors, specifically comprising: matching a plurality of first feature points and a plurality of second feature points according to the first feature vector and the second feature vector to generate a plurality of feature point pairs; and generating the translation vector according to the characteristic point pairs.
5. 5. The method according to claim 4, wherein the matching the plurality of first feature points and the plurality of second feature points according to the first feature vector and the second feature vector generates a plurality of feature point pairs, and the method specifically includes: for the plurality of first feature points, performing the steps of: Respectively calculating a second distance between a first feature vector corresponding to the first feature point and each second feature vector; and if the minimum second distance is smaller than a preset matching threshold value, determining the second feature point corresponding to the second feature vector with the minimum second distance and the first feature point as a feature point pair.
6. 6. The method for determining image displacement according to claim 1, wherein determining a first distance between the plurality of translation vectors, and determining the set of interior points corresponding to each of the translation vectors according to the first distance, specifically comprises: For the plurality of translation vectors, performing the steps of: Determining the translation vector as a target translation vector; Respectively calculating first distances between the target translation vector and the rest translation vectors; and storing the rest translation vectors, of which the first distance is smaller than a preset interior point threshold value, into an interior point set corresponding to the target translation vector.
7. 7. The image displacement determination method according to claim 1, wherein before extracting feature points on the first image and the second image, respectively, and matching the feature points, the method further comprises: reducing the resolution of the first image to a preset resolution, and/or, And reducing the resolution of the second image to a preset resolution.
8. 8. The image displacement determination method according to claim 7, characterized in that the method further comprises: if the number of the inner points of the plurality of inner point sets is smaller than the preset number, the resolution of the first image and/or the second image is improved according to the preset proportion, the characteristic points on the first image and the second image are respectively extracted, the characteristic points are matched, and a plurality of translation vectors are generated; And if the number of the interior points in the plurality of interior point sets is greater than or equal to the preset number of the interior point sets, executing the step of calculating the length of the translation vector corresponding to the interior point set with the largest number of the interior points.
9. 9. A method of determining a position of an image pickup apparatus, the method comprising: Acquiring a first image acquired at a first moment and a second image acquired at a second moment in the rotation process of the image pickup equipment; Extracting characteristic points on the first image and the second image respectively, and matching the characteristic points to generate a plurality of translation vectors; Determining the distance between the translation vectors, and determining an inner point set corresponding to each translation vector according to the distance; calculating the length of the translation vector corresponding to the inner point set with the largest number of inner points; and if the length is smaller than a preset length threshold value, determining that the image pickup equipment reaches a preset position.
10. 10. A control apparatus comprising a memory, a processor, and a computer program stored on the memory, characterized in that the processor executes the computer program to implement the image displacement determination method according to any one of claims 1 to 8, or the processor executes the computer program to implement the image pickup apparatus position determination method according to claim 9.
11. 11. A computer-readable storage medium having stored thereon a computer program, characterized in that the computer program when executed by a processor implements the image displacement determination method according to any one of claims 1 to 8, or the computer program when executed by a processor implements the image pickup apparatus position determination method according to claim 9.

Description

Image displacement determination method and image pickup apparatus position determination method Technical Field The embodiment of the application relates to the technical field of equipment control, in particular to an image displacement determining method, an image pickup equipment position determining method, control equipment and a computer readable storage medium. Background Currently, the determination of image displacement generally depends on the calculation of the correlation of the overall content of two images, and the relative displacement relationship is judged by comprehensively analyzing the image data. The method often needs to execute a complex operation process on a large amount of image data, has the advantages of more calculation steps, large calculation amount and higher requirements on calculation resources and processing efficiency, and is easy to cause larger system burden in practical application. Disclosure of Invention In view of the above problems, embodiments of the present application provide an image displacement determining method, an image capturing apparatus position determining method, a control apparatus, and a computer readable storage medium, which are used for solving the problems in the prior art that image displacement calculation steps are more, calculation amount is large, and requirements on calculation resources and processing efficiency are high. According to one aspect of the embodiment of the application, an image displacement determining method is provided, and the method comprises the steps of obtaining a first image and a second image, respectively extracting characteristic points on the first image and the second image, matching the characteristic points to generate a plurality of translation vectors, determining first distances among the plurality of translation vectors, determining inner point sets corresponding to the translation vectors according to the first distances, calculating lengths of the translation vectors corresponding to the inner point sets with the largest number of the inner points, and determining the lengths of the translation vectors as image displacement. In an alternative mode, feature points on the first image and the second image are respectively extracted, and the method specifically comprises the steps of identifying the first image and the second image, determining a static area of the first image and a static area of the second image, and respectively extracting the feature points of the static area on the first image and the feature points of the static area on the second image. In an optional mode, feature points on the first image and the second image are respectively extracted, specifically comprising the steps of extracting the feature points of the first image to obtain a plurality of first feature points and first feature vectors corresponding to the first feature points, and extracting the feature points of the second image to obtain a plurality of second feature points and second feature vectors corresponding to the second feature points. In an optional mode, the feature points are matched to generate a plurality of translation vectors, and the method specifically comprises the steps of matching a plurality of first feature points with a plurality of second feature points according to the first feature vectors and the second feature vectors to generate a plurality of feature point pairs, and generating the translation vectors according to the feature point pairs. In an optional mode, a plurality of first feature points and a plurality of second feature points are matched according to the first feature vectors and the second feature vectors to generate a plurality of feature point pairs, and the method specifically comprises the following steps of respectively calculating second distances between the first feature vectors corresponding to the first feature points and the second feature vectors, and determining the second feature points corresponding to the second feature vectors with the minimum second distances and the first feature points as a feature point pair if the minimum second distances are smaller than a preset matching threshold. In an alternative mode, a first distance between a plurality of translation vectors is determined, and an inner point set corresponding to each translation vector is determined according to the first distance; and storing the translation vectors of which the first distances are smaller than a preset interior point threshold value in the rest translation vectors into an interior point set corresponding to the target translation vectors. In an alternative manner, before extracting the feature points on the first image and the second image respectively and matching the feature points to generate a plurality of translation vectors, the method further comprises reducing the resolution of the first image to a preset resolution and/or reducing the resolution of the second image to a preset