Method and device for image rectification

1. A method for image rectification, comprising:

receiving two images captured by a first image capturing device and a second image capturing device, wherein the two images are images of a target object captured from different viewpoints;

performing an epipolar rectification on the two images;

selecting a same focal length parameter for the first image capturing device and the second image capturing device, wherein the two images captured from the different viewpoints have a same field of view after an undistortion without a scaling relationship;

rectifying the two images after the epipolar rectification based on image contents; and

splicing the two images rectified based on the image contents,

wherein rectifying the two images comprises determining positions of feature point pairs corresponding in the two images by:

determining positions of candidate feature point pairs corresponding in the two images;

removing feature point pairs having a wrong correspondence from the candidate feature point pairs using a Random Sample Consensus (RANSAC) algorithm; and

aligning the two images according to the positions of the feature point pairs and parameters of the first image capturing device and the second image capturing device,

wherein aligning the two images according to the positions of the feature point pairs and the parameters of the first image capturing device and the second image capturing device comprises:

determining an error function relative to an obtained first parameter according to the positions of the feature point pairs and the parameters of the first image capturing device and the second image capturing device;

obtaining optimized parameters of the first image capturing device and the second image capturing device according to the error function; and

adjusting the two images according to the optimized parameters of the first image capturing device and the second image capturing device,

wherein each feature point pair comprises a first point and a second point,

wherein determining the error function relative to the obtained first parameter according to the positions of the feature point pairs and the parameters of the first image capturing device and the second image capturing device comprises:

projecting the first point to an image coordinate system of an image of the second point by a three-dimensional point cloud according to the parameters of the first image capturing device and the second image capturing device to obtain a projection point; and

determining a distance between the projection point and the second point as the error function, and

wherein the error function comprises a regularization term, and

wherein the regularization term is determined by a multiplication of a coefficient and a sum of squares of a pair of predetermined rotation-related parameters from the first image capturing device and the second image capturing device.

2. The method of claim 1 , wherein feature points of the feature point pairs comprise one item listed below:

points having variations in at least one direction greater than a first threshold; and points with unchanged locations independent of whether the sizes of the images change.

3. The method of claim 1 , wherein the pair of predetermined rotation-related parameters correspond to an axis in a three-dimensional coordinate system, and wherein the regularization term is determined to ensure not excessive rotation over the axis when the error function is minimal.

4. The method of claim 3 , wherein the axis is Z-axis.

5. The method of claim 1 , wherein the optimized parameters of the first image capturing device and the second image capturing device comprise at least one item listed below:

rotation parameters, focal lengths, and coordinates of principal points.

6. The method of claim 1 , wherein

performing the epipolar rectification on the two images comprises:

undistorting the two images according to the selected focal length parameter;

determining a row alignment matrix of the two images in a no-parallax direction according to a translation matrix and a rotation matrix of the first image capturing device and the second image capturing device; and

rectifying the two images according to the row alignment matrix in the no-parallax direction.

7. The method of claim 1 , wherein before splicing the two images rectified based on image contents, the method further comprises:

cropping parts of whole images of the two images or the whole images for splicing, according to contents in the whole images, from the two images rectified based on the image contents.

8. A non-transitory computer readable storage medium storing computer programs, wherein when the computer programs are executed by a second processor, the steps of the method of claim 1 are implemented.

9. A device for image rectification, comprising a memory, a third processor, and computer programs stored in the memory and operable on the third processor, wherein when the computer programs are executed by the third processor, the steps of the method of claim 1 are implemented.

10. A device for image rectification, comprising:

a receiver, configured to receive two images, wherein the two images are images of a target object captured from different viewpoints;

a first image capturing device having a first focal length parameter and a second image capturing device having a second focal length parameter, wherein the first focal length parameter and the second focal length parameter are the same, wherein the two images captured from the different viewpoints have a same field of view after an undistortion without a scaling relationship, and wherein the first image capturing device and the second image capturing device capture the first image and the second image;

a rectification processor configured to perform an epipolar rectification on the two images, determine positions of feature point pairs corresponding in the two images, and rectify the two images after the epipolar rectification based on image contents; and

a splicer, configured to splice the two images rectified based on the image contents,

wherein the rectification processor determines positions of feature point pairs corresponding in the two images by:

determining positions of candidate feature point pairs corresponding in the two images; and

removing feature point pairs having a wrong correspondence from the candidate feature point pairs using a Random Sample Consensus (RANSAC) algorithm,

wherein the rectification processor aligns the two images according to the positions of the feature point pairs and parameters of the first image capturing device and the second image capturing device,

wherein each feature point pair comprises a first point and a second point,

wherein the rectification processor determines an error function relative to an obtained first parameter according to the positions of the feature point pairs and the parameters of the first image capturing device and the second image capturing device by:

projecting the first point to an image coordinate system of an image of the second point by a three-dimensional point cloud according to the parameters of the first image capturing device and the second image capturing device to obtain a projection point; and

determining a distance between the projection point and the second point as the error function,

wherein the rectification processor obtains optimized parameters of the first image capturing device and the second image capturing device according to the error function,

wherein the rectification processors adjust the two images according to the optimized parameters of the first image capturing device and the second image capturing device,

wherein the error function comprises a regularization term, and

wherein the regularization term is determined by a multiplication of a coefficient and a sum of squares of a pair of predetermined rotation-related parameters from the first image capturing device and the second image capturing device.

11. The device of claim 10 , wherein the rectification processor is configured to:

determine an error function relative to an obtained first parameter according to the positions of the feature point pairs and the parameters of the first image capturing device and the second image capturing device,

obtain optimized parameters of the first image capturing device and the second image capturing device according to the error function, and

adjust the two images according to the optimized parameters of the first image capturing device and the second image capturing device.

12. The device of claim 10 wherein

the rectification processor is configured to undistort the two images according to a selected focal length parameter, determine a row alignment matrix of the two images in a no-parallax direction according to a translation matrix and the rotation matrix of the first image capturing device and the second image capturing device, and rectify the two images according to the row alignment matrix in the no-parallax direction.

13. The device of claim 10 , wherein

the splicer is further configured to crop parts of whole images of the two images or the whole images for splicing, according to contents in the whole images, from the two images rectified based on the image contents, before splicing the two images rectified based on the image contents.

14. A system for image rectification, comprising: a first image capturing device, a second image capturing device, and a first processor; wherein

the first image capturing device and the second image capturing device are configured to capture images of a target object from different viewpoints and have a same focal length parameter;

the first processor is configured to acquire the two images of the target object captured from the different viewpoints and determine positions of feature point pairs corresponding in the two images;

the two images captured from the different viewpoints have a same field of view after an undistortion without a scaling relationship; and

the first processor is further configured to perform an epipolar rectification on the two images, rectify the two images after the epipolar rectification based on image contents, and splice the two images rectified based on the image contents,

wherein the first processor determines positions of feature point pairs corresponding in the two images by:

determining positions of candidate feature point pairs corresponding in the two images; and

removing feature point pairs having a wrong correspondence from the candidate feature point pairs using a Random Sample Consensus (RANSAC) algorithm,

wherein the first processor aligns the two images according to the positions of the feature point pairs and parameters of the first image capturing device and the second image capturing device,

wherein each feature point pair comprises a first point and a second point,

wherein the first processor determines an error function relative to an obtained first parameter according to the positions of the feature point pairs and the parameters of the first image capturing device and the second image capturing device by:

projecting the first point to an image coordinate system of an image of the second point by a three-dimensional point cloud according to the parameters of the first image capturing device and the second image capturing device to obtain a projection point; and

determining a distance between the projection point and the second point as the error function,

wherein the first processor obtains optimized parameters of the first image capturing device and the second image capturing device according to the error function,

wherein the first processors adjust the two images according to the optimized parameters of the first image capturing device and the second image capturing device,

wherein the error function comprises a regularization term, and

wherein the regularization term is determined by a multiplication of a coefficient and a sum of squares of a pair of predetermined rotation-related parameters from the first image capturing device and the second image capturing device.