Image positioning method and system thereof

Patent metadata

Field	Value
Publication number	US-10922844-B2
Application number	US-201916698929-A
Country	US
Kind code	B2
Filing date	Nov 27, 2019
Priority date	Mar 28, 2019
Publication date	Feb 16, 2021
Grant date	Feb 16, 2021

Abstract

An image positioning method having following steps is provided. The steps include: obtaining world coordinates of two reference points and image coordinates of two projection points corresponding to the two reference points; calculating a plurality of coordinate transformation parameters relative to transformation between any image coordinates and any world coordinates corresponding to a camera according only to the world coordinates of the two reference points, the image coordinates of the two projection points, and world coordinates of the camera; obtaining an second image having an object image corresponding to an object through the camera; and positioning world coordinates of the object according to the coordinate transformation parameters.

First claim

What is claimed is:

1. An image positioning method, comprising:
obtaining, by a processor, world coordinates of two reference points and image coordinates of two projection points in a first image corresponding to the two reference points, wherein the first image is obtained through a camera;
calculating, by a processor, a plurality of coordinate transformation parameters relative to transformation between any image coordinates of two dimensions in the first image and any world coordinates of three dimensions corresponding to the camera according only to the world coordinates of the two reference points, the image coordinates of the two projection points, and world coordinates of the camera, wherein the coordinate transformation parameters comprise a focal length, a first rotation angle, a second rotation angle and a third rotation angle;
obtaining, by a processor, a second image through the camera, wherein the second image comprises an object image corresponding to an object; and
positioning, by a processor, world coordinates of the object according to the coordinate transformation parameters,
wherein the step of calculating the plurality of coordinate transformation parameters relative to the transformation between any image coordinates and any world coordinates corresponding to the camera according only to the world coordinates of the two reference points, the image coordinates of the two projection points, and the world coordinates of the camera further comprises:
determining, by a processor, a plurality of reference distances between a lens of the camera and the two reference points according to the world coordinates of the two reference points and the world coordinates of the camera, the reference distances comprising the reference distance between the lens of the camera and a first reference point, the reference distance between the lens of the camera and a second reference point, and the reference distance between the first reference point and the second reference point;
determining, by a processor, a plurality of projection distances between a first image central point and the two projection points according to image coordinates of the first image central point and the image coordinates of the two projection points, the projection distances comprising the projection distance between the first image central point and a first projection point, the projection distance between the first image central point and a second projection point, and the projection distance between the first projection point and the second projection point; and
calculating, by the processor, the focal length in the coordinate transformation parameters according to the reference distances and the projection distances.

2. The image positioning method as claimed in claim 1 , further comprising:
obtaining, by the processor, the first image from the camera; and
determining, by the processor, resolution information corresponding to the first image and calculating image coordinates of the two projection points according to the resolution information.

3. The image positioning method as claimed in claim 1 , wherein the step of calculating, by the processor, the focal length in the coordinate transformation parameters according to the reference distances and the projection distances further comprises:
determining, by the processor, correlations between the reference distances and the projection distances;
calculating by the processor, an angle of a central angle between the first image central point, the first projection point, and the second projection point; and
calculating, by the processor, the focal length according to the correlations between the reference distances and the projection distances and the angle of the central angle between the first image central point, the first projection point, and the second projection point.

4. The image positioning method as claimed in claim 3 , wherein the step of calculating the angle of the central angle between the first image central point, the first projection point, and the second projection point and the correlations between the reference distances and the projection distances further comprises:
calculating, by the processor, a cosine value of the central angle between the first image central point, the first projection point, and the second projection point according to the projection distances.

5. The image positioning method as claimed in claim 1 , wherein the step of calculating the plurality of coordinate transformation parameters relative to the transformation between any image coordinates and any world coordinates corresponding to the camera according only to the world coordinates of the two reference points, the image coordinates of the two projection points, and the world coordinates of the camera further comprises:
calculating, by the processor, the first rotation angle and the second rotation angle in the coordinate transformation parameters according to the image coordinates corresponding to the two projection points, height differences between the two reference points and the camera, and the focal length.

6. The image positioning method as claimed in claim 5 , wherein the step of calculating, by the processor, the first rotation angle and the second rotation angle in the coordinate transformation parameters according to the image coordinates corresponding to the two projection points, the height differences between the two reference points and the camera, and the focal length further comprises:
transforming, by the processor, the image coordinates of the two projection points to coordinates of the two reference points in a camera coordinate system;
determining, by the processor, coordinate values of an intermediate third coordinate axis of the two reference points in a second intermediate coordinate system; and
calculating the first rotation angle and the second rotation angle according to the coordinate values of the intermediate third coordinate axis of the two reference points and the height differences between the two reference points and the camera.

7. The image positioning method as claimed in claim 1 , wherein the step of calculating the plurality of coordinate transformation parameters relative to the transformation between any image coordinates and any world coordinates corresponding to the camera according only to the world coordinates of the two reference points, the image coordinates of the two projection points, and the world coordinates of the camera further comprises:
calculating, by the processor, a world projection vector by projecting a reference vector formed by the two reference points on a world plane perpendicular to a world third coordinate axis of a world coordinate system;
calculating, by the processor, an intermediate projection vector by projecting the reference vector formed by the two reference points on an intermediate plane perpendicular to an intermediate third coordinate axis of a second intermediate coordinate system; and
calculating, by the processor, the third rotation angle in the coordinate transformation parameters according to the world projection vector and the intermediate projection vector.

8. The image positioning method as claimed in claim 7 , wherein the step of calculating, by the processor, the third rotation angle in the coordinate transformation parameters according to the world projection vector and the intermediate projection vector further comprises:
calculating, by the processor, the third rotation angle in the coordinate transformation parameters according to an angle between the world projection vector and the intermediate projection vector.

9. The image positioning method as claimed in claim 7 , wherein the step of calculating, by

Assignees

• Ind Tech Res Inst

Inventors

• Chang Shu-Hsin
• Lu Kun-Hsien

Classifications

• G01C3/22 Primary

  using a parallactic triangle with variable angles and a base of fixed length at, near, or formed by the object · CPC title

• G06T2207/30244

  Camera pose · CPC title

• G06T2207/30184

  Infrastructure · CPC title

• G06T7/70

  Determining position or orientation of objects or cameras (camera calibration G06T7/80) · CPC title

• G06T2207/10004

  Still image; Photographic image · CPC title