CN110738707A - Distortion correction method, device, equipment and storage medium for cameras - Google Patents
Distortion correction method, device, equipment and storage medium for cameras Download PDFInfo
- Publication number
- CN110738707A CN110738707A CN201910983234.5A CN201910983234A CN110738707A CN 110738707 A CN110738707 A CN 110738707A CN 201910983234 A CN201910983234 A CN 201910983234A CN 110738707 A CN110738707 A CN 110738707A
- Authority
- CN
- China
- Prior art keywords
- distortion
- orthodontic
- pixel
- pixel coordinates
- array image
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 76
- 238000012937 correction Methods 0.000 title claims description 40
- 230000008569 process Effects 0.000 claims description 33
- 238000004364 calculation method Methods 0.000 claims description 19
- 230000015654 memory Effects 0.000 claims description 14
- 238000012804 iterative process Methods 0.000 claims description 4
- 230000009466 transformation Effects 0.000 claims description 4
- 238000004590 computer program Methods 0.000 claims description 3
- 238000003702 image correction Methods 0.000 claims description 2
- 238000004891 communication Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 4
- 238000001514 detection method Methods 0.000 description 3
- 238000004422 calculation algorithm Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 238000011895 specific detection Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/80—Analysis of captured images to determine intrinsic or extrinsic camera parameters, i.e. camera calibration
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30204—Marker
- G06T2207/30208—Marker matrix
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Image Processing (AREA)
Abstract
The method obtains a plane array image acquired by a camera and an orthodontic plane array image obtained by correcting distortion of the plane array image, obtains pixel coordinates of preset characteristic points in the plane array image as distortion pixel coordinates, obtains pixel coordinates of the preset characteristic points in the orthodontic plane array image as orthodontic pixel coordinates according to the orthodontic pixel coordinates, obtains predicted pixel coordinates of the preset characteristic points according to at least the distortion pixel coordinates and the predicted pixel coordinates, calculates distortion parameters of the camera, and corrects the image acquired by the camera by using the distortion parameters.
Description
Technical Field
The present application relates to the field of electronic information, and in particular, to a distortion correction method, apparatus, device, and storage medium for cameras.
Background
Since the lens of the camera is distorted, distortion correction of the image is generally required in order to avoid the influence of the distortion on the image captured by the camera.
The existing distortion correction method is defined in an image coordinate system, so that besides distortion parameters, internal parameters of a camera, such as a focal length, a principal point and the like, and external parameters, such as a conversion matrix from a world coordinate system to the image coordinate system, and the like, need to be calibrated. Moreover, the process of image distortion removal also requires the participation of these parameters. Therefore, the conventional distortion correction method for a camera has a large calculation amount.
Disclosure of Invention
The application provides a distortion correction method, a distortion correction device, distortion correction equipment and a distortion correction storage medium for cameras, and aims to solve the problem of large calculation amount of the distortion correction method for the cameras.
In order to achieve the above object, the present application provides the following technical solutions:
A distortion correction method for a camera, comprising:
acquiring a planar array image and an orthodontic planar array image, wherein the planar array image is acquired by a camera, and the orthodontic planar array image is obtained by correcting distortion of the planar array image;
acquiring pixel coordinates of preset feature points in the planar array image as distorted pixel coordinates;
acquiring pixel coordinates of the preset characteristic points in the orthodontic plane array image as orthodontic pixel coordinates;
acquiring a predicted pixel coordinate of the preset feature point according to the orthodontic pixel coordinate;
calculating a distortion parameter of the camera based at least on the distorted pixel coordinates and the predicted pixel coordinates;
correcting the image captured by the camera using the distortion parameter.
Optionally, obtaining the predicted pixel coordinates of the preset feature point according to the orthodontic pixel coordinates includes:
acquiring a predicted line straight line, wherein the predicted line straight line corresponding to the i-th line of orthodontic pixels in the orthodontic plane array image is determined by a slope i and pixel coordinates of a reference point i, the slope i is the slope of a line fitting straight line of the i-th line of orthodontic pixels, the reference point i is an orthodontic pixel point which is closest to a preset main point in the i-th line of orthodontic pixels, or an orthodontic pixel point which is closest to a vertical line of the line fitting straight line, and the vertical line is a straight line which passes through the main point and is perpendicular to the line fitting straight line;
obtaining a predicted column straight line, wherein the predicted column straight line corresponding to a jth orthodontic pixel in the orthodontic plane array image is determined by a slope j and a pixel coordinate of a reference point j, the slope j is the slope of a column fitting straight line of the jth orthodontic pixel, the reference point j is an orthodontic pixel point closest to a preset main point in the jth orthodontic pixel, or is an orthodontic pixel point closest to a vertical line of the column fitting straight line, and the vertical line of the column fitting straight line is a straight line which passes through the main point and is perpendicular to the column fitting straight line;
and taking the intersection point of the prediction row straight line and the prediction column straight line as the prediction pixel coordinate.
Optionally, calculating a distortion parameter of the camera at least according to the distortion pixel coordinate and the prediction pixel coordinate, including:
substituting the distorted pixel coordinates and the predicted pixel coordinates into a preset distortion model to obtain distortion equation set, wherein the distortion model is used for representing the distorted pixel coordinates and the predicted pixel coordinates and generating a transformation relation according to the distortion parameters;
the distortion parameters are obtained by solving a least squares solution of a system of equations including at least the th distortion equation set.
Optionally, the system of equations further comprises:
and a second distortion equation set, wherein the second distortion equation set is obtained by substituting the predicted pixel coordinates and the distortion pixel coordinates of the preset virtual feature points into the distortion model.
Optionally, calculating a distortion parameter of the camera according to at least the distortion pixel coordinate and the prediction pixel coordinate, further comprising:
after the distortion parameter is determined, if the distortion parameter is not converged, the following procedures are executed, the distortion parameter is calculated in an iterative mode until the distortion parameter is converged, the plane array image is corrected by using the distortion parameter obtained in the previous times of iterative processes, the orthodontic plane array image is updated, the pixel coordinate of the preset characteristic point in the orthodontic plane array image is obtained and is used as the orthodontic pixel coordinate, the predicted pixel coordinate of the preset characteristic point is obtained according to the orthodontic pixel coordinate, and the distortion parameter of the camera is calculated at least according to the distorted pixel coordinate and the predicted pixel coordinate.
Optionally, the condition for convergence of the distortion parameter includes at least terms as follows:
calculating the iteration times of the distortion parameters to reach a preset value;
the deviation between the distortion parameter value obtained in the current iteration process and the distortion parameter value obtained in the last iterations process is smaller than a th preset threshold value;
the deviation between the current distorted pixel coordinate and the historical distorted pixel coordinate is smaller than a second preset threshold, the current distorted pixel coordinate is determined by using the distorted parameter obtained in the current iteration process and a preset real pixel coordinate, and the historical distorted pixel coordinate is determined by using the distorted parameter obtained in the last iteration processes and the real pixel coordinate;
and the deviation between the predicted pixel coordinate determined by the orthodontic parameters obtained by the current iteration process and the orthodontic pixel coordinate is smaller than a third preset threshold value.
Optionally, the distortion parameters in the distortion model include:
the radial distortion model comprises a plurality of orders, a radial distortion parameter and a tangential distortion parameter.
distortion correction device for camera, comprising:
the image acquisition unit is used for acquiring a plane array image and an orthodontic plane array image, wherein the plane array image is acquired by a camera, and the orthodontic plane array image is obtained by correcting distortion of the plane array image;
an th coordinate acquiring unit, configured to acquire pixel coordinates of a preset feature point in the planar array image as distorted pixel coordinates;
the second coordinate acquisition unit is used for acquiring the pixel coordinates of the preset characteristic points in the orthodontic plane array image as orthodontic pixel coordinates;
the third coordinate obtaining unit is used for obtaining the predicted pixel coordinate of the preset feature point according to the orthodontic pixel coordinate;
a distortion parameter calculation unit for calculating a distortion parameter of the camera at least according to the distorted pixel coordinates and the predicted pixel coordinates;
and the image correction unit is used for correcting the image acquired by the camera by using the distortion parameter.
distortion correction device for camera comprises memory and processor;
the memory is used for storing programs;
the processor is configured to execute the program to implement the steps of the distortion correction method for the camera.
readable storage medium, having stored thereon a computer program which, when being executed by a processor, carries out the steps of the method for distortion correction of a camera as described above.
According to the technical scheme, the method comprises the steps of obtaining a plane array image collected by a camera and an orthodontic plane array image obtained by correcting distortion of the plane array image, obtaining pixel coordinates of preset characteristic points in the plane array image as distortion pixel coordinates, obtaining pixel coordinates of the preset characteristic points in the orthodontic plane array image as orthodontic pixel coordinates. And acquiring the predicted pixel coordinates of the preset feature points according to the orthodontic pixel coordinates, calculating the distortion parameters of the camera at least according to the distortion pixel coordinates and the predicted pixel coordinates, and correcting the image acquired by the camera by using the distortion parameters. It can be seen from the above steps that the distortion parameter calculation process only needs to use the pixel coordinates, and therefore, the external reference of the camera and the other internal references except the distortion parameter do not need to be introduced, and therefore, the calculation amount can be reduced significantly.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative efforts.
Fig. 1 is a schematic structural diagram of a distortion correction system of a camera disclosed in an embodiment of the present application;
FIG. 2 is a flowchart of a distortion correction method for cameras disclosed in the embodiments of the present application;
FIG. 3 illustrates planar array diagrams;
fig. 4 is a flowchart illustrating a process of obtaining predicted pixel coordinates of preset feature points by using a straight line fitting manner, which is disclosed in the embodiment of the present application;
FIG. 5 is a flowchart of a method for calculating distortion parameters of cameras disclosed in the embodiments of the present application;
fig. 6 is a schematic structural diagram of a distortion correction apparatus for cameras disclosed in the embodiments of the present application;
fig. 7 is a schematic structural diagram of a distortion correction apparatus for cameras disclosed in the embodiments of the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be described clearly and completely with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only partial embodiments of the present application , rather than all embodiments.
Fig. 1 is a system for distortion correction of a camera, which includes a planar array pattern, a camera, and a computing device, according to an embodiment of the present disclosure. The camera shoots a plane array pattern to obtain a plane array image, and shoots other scenes by the camera to obtain a scene image, wherein the plane array image and the scene image are collectively called as an original image (namely, an image with distortion).
The computing device internally comprises a distortion correction unit, and the distortion correction unit runs the distortion correction method of the camera provided by the application.
Fig. 2 is a distortion correction method for cameras disclosed in the embodiment of the present application, including the following steps:
s201: acquiring a planar array image and an orthodontic planar array image.
The planar array image is an image obtained by acquiring a planar array pattern by a camera. Examples of the planar array pattern are shown in fig. 3, and may be a black and white checkerboard pattern (left in fig. 3) or a circular array pattern (right in fig. 3).
The orthodontic planar array image is an image obtained by performing distortion correction on the planar array image. Specifically, the distortion parameter is used to perform distortion correction on the planar array image, in this embodiment, the initial value of the distortion parameter is set to 0, and in this case, the initial orthodontic planar array image is the planar array image.
Of course, the initial value of the distortion parameter can be set to be other empirical values, and the plane array image is subjected to distortion correction by using other empirical values to obtain the initial orthodontic plane array image.
Of course, other methods may be used to obtain the orthodontic planar array image, and are not limited herein.
S202: and acquiring the pixel coordinates of the preset characteristic points in the planar array image as distorted pixel coordinates.
Wherein the predetermined characteristic points are selected according to the characteristics of the planar array pattern. For example, for a black-and-white checkerboard, the upper left corner of each cell is used as a preset feature point, and the pixel coordinates of the preset feature point can be detected by adopting a corner point detection method. For the circular array pattern, the center of the circle is used as the preset feature point, and the pixel coordinates of the preset feature point can be detected by adopting a circle detection and circle center calculation method.
The above specific detection algorithm can be seen in the prior art. Optionally, after the pixel coordinates of the preset feature points are detected, a sub-pixel interpolation method may be further used to obtain more accurate pixel coordinates of the preset feature points, which may be referred to in the prior art specifically and is not described herein again.
Let the planar array image beAssuming that the planar array pattern includes N rows and M columns of array units (e.g., cells of a checkerboard pattern or circles of a circular pattern), assuming that each array unit includes preset feature points (hereinafter, referred to as feature points), assuming that i is the row number of the array unit in the array, i is 1,2, …, N, j is the column number of the array unit in the array, j is 1,2, …, M, and t is i.m + j, the pixel coordinate of the feature point of the t-th array unit in the original planar array image is recorded as i.m + j
For the purpose of distinguishing the following description, a pixel in the planar array image as a preset feature point is referred to as a distorted pixel, and the pixel coordinate obtained in this step is also referred to as a distorted pixel coordinate.
S203: and acquiring pixel coordinates of preset characteristic points in the orthodontic plane array image as orthodontic pixel coordinates.
Setting an orthodontic plane array image as
The resolution is also NxM. And obtaining the pixel coordinates of the preset characteristic points in the orthodontic plane array image by using the same detection mode as the plane array image. The pixel coordinate of the t-th array unit characteristic point is expressed as
For the purpose of distinguishing the following description, a pixel in the orthodontic planar array image as a preset feature point is referred to as an orthodontic pixel, and the pixel coordinate obtained in this step is also referred to as an orthodontic pixel coordinate.
S204: and acquiring the predicted pixel coordinates of the preset feature points according to the orthodontic pixel coordinates.
Specifically, the predicted pixel coordinates of the preset feature points can be obtained by adopting a straight line fitting mode:
and acquiring a predicted line straight line, wherein the predicted line straight line corresponding to the ith orthodontic pixel in the orthodontic plane array image is determined by a slope i and a pixel coordinate of a reference point i, the slope i is the slope of the line fitting straight line of the ith orthodontic pixel, the reference point i is the orthodontic pixel point closest to a preset main point in the ith orthodontic pixel, or the orthodontic pixel point closest to the vertical line of the line fitting straight line, and the vertical line of the line fitting straight line is a straight line which passes through the main point and is perpendicular to the line fitting straight line.
And acquiring a predicted column straight line, wherein the predicted column straight line corresponding to the jth orthodontic pixel in the orthodontic plane array image is determined by a slope j and a pixel coordinate of a reference point j, the slope j is the slope of the column fitting straight line of the jth orthodontic pixel, the reference point j is an orthodontic pixel point which is closest to a preset principal point in the jth orthodontic pixel, or is closest to a vertical line of the column orthodontic fitting straight line, and the vertical line of the column fitting straight line is a straight line which passes through the principal point and is perpendicular to the column fitting straight line.
And taking the intersection point of the prediction row straight line and the prediction column straight line as the prediction pixel coordinate.
Wherein the pixel coordinates (u) of the predetermined principal point0,v0) The image parameter can be obtained by other camera internal reference calibration methods, specifically referring to the prior art, or can be approximately represented by pixel coordinates (0.5M +0.5,0.5N +0.5) in the right center of the image, where N is the resolution in the vertical direction of the image, and M is the resolution in the horizontal direction of the image.
A more detailed implementation of obtaining the predicted pixel coordinates of the preset feature points is shown in the flowchart of fig. 4.
In the following description, the predicted pixel coordinate of the t-th array unit feature point is represented as Pt＝(ut,vt)。
S205: and calculating distortion parameters of the camera at least according to the distortion pixel coordinates and the prediction pixel coordinates.
Specifically, the distortion model is used for representing the coordinates of a distorted pixel and the coordinates of a predicted pixel, and generating a transformation relation according to the distortion parameters.
Optionally, in this embodiment, the distortion model is shown in formula (1):
in the above formula, q is the radial distortion model order; k is a radical of1,k2,…,kqIs a radial distortion parameter; p is a radical of1,p2Is a tangential distortion parameter;
is a distorted pixel coordinate; u and v are ideal pixel coordinates; u. of0,v0R is a coefficient for grouping the pixel coordinates into , and is constants.
In the present embodiment, the constant R in the distortion model can be calculated using the following formula:
R＝0.5(M2+N2)0.5
where M and N are the image horizontal resolution and vertical resolution, respectively, the use of this formula means that the value of R is set to -half the diagonal length of the image.
Therefore, the distorted pixel coordinates and the predicted pixel coordinates are substituted into the distortion model to obtain an equation set, and the distortion parameters are obtained by solving the least square solution of the equation set.
The specific solving process can be seen in the prior art.
Optionally, in order to prevent overfitting and obtain an optimal solution, as shown in fig. 5, the distortion parameter may be calculated by using the virtual feature point as a calculation basis, and a specific calculation flow of the distortion parameter may be calculated.
S206: the image captured by the camera is corrected using the distortion parameters.
Let the undistorted image be I, with a resolution of N × M, N being the vertical resolution, and M being the horizontal resolution. Let l be i.m + j, and the pixel coordinate of the ith row and j column be (u)l,vl) Obviously ul＝j,vlI. The image distortion removing method comprises the following steps:
A1. using the obtained distortion parameter to remove the pixel (u) at i-th row and j-th column of distortion mapl,vl) Substituting into a common for ideal pixel coordinatesEquation (1) calculates the corresponding distorted pixel coordinates
A2. According to distorted pixel coordinatesThe neighborhood pixels of the position are taken from the original image I.
A3. Performing pixel interpolation according to the pixel value of the neighborhood pixel to obtain the pixel coordinate in the original image
New pixel value ofThe pixel interpolation can be realized by adopting methods such as nearest neighbor interpolation, bilinear interpolation or bicubic interpolation.
A4. use
Fills in the I row and j column pixels I (u) in the undistorted imagel,vl) The value of (c).
The above distortion correction method is merely an example, and an image may be corrected based on a distortion parameter by using another conventional method.
The distortion correction method of the camera shown in fig. 2 has the following effects:
1. the pixel coordinates are used for operation instead of the image coordinates, the distortion calibration process can realize independent calculation of distortion parameters, so that the dependence on other internal parameters and external parameters except the distortion parameters is removed, only the distortion parameters participate in the image distortion removal process, and the calculation amount is reduced.
2. Because the image is based on the pixel coordinates, the distortion parameter can be calibrated only by planar array images, and a plurality of planar array images shot at different angles are not needed, so the calculation efficiency is high.
3. Most of the existing camera distortion calibration methods do not consider tangential distortion, so that the tangential distortion of a camera cannot be corrected. The distortion model of the present embodiment includes a tangential distortion parameter, so that the high-order tangential distortion of the camera can be corrected.
4. The radial distortion model adopted by the existing camera distortion calibration method is low in order, mostly only supports 1-3 order radial distortion, only can correct small radial distortion, and is not suitable for distortion correction of a fisheye camera. The order k of the radial distortion in the distortion model in the embodiment can be set, and 4-order or more radial distortion can be supported, so that distortion correction can be performed on the fisheye camera.
Fig. 4 is a specific process of obtaining the predicted pixel coordinates of the preset feature points by using a straight line fitting manner, which includes the following steps:
orthodontic flat array imagesThe characteristic point set of the ith row of the medium array unit is expressed as
And (3) solving a predicted line straight line of the ith row array unit feature point according to S401-S404:
s401: determining a set of points S using a line fitting methodiIs determined by assuming that the slope of the line is gammai。
S402: finding a passing principal point (u)0,v0) And the equation u of the straight line perpendicular to the best fit straight line is-gammaiv+(u0+γiv0) This line is referred to as the perpendicular line of the line-fitting straight line.
S403: finding SiThe point closest to the perpendicular of the line-fitted straight line is assumed to have a pixel coordinate of (α)i,βi)。
S404, finding a passing point (α)i,βi) And the slope is gammaiIs given by the equation v ═ γiu+(βi-γiαi) This line is referred to as a predicted line of the ith line array unit feature point.
In the case of small distortion of the camera, in the process of obtaining the predicted straight line of the ith row of the array unit feature point, S403 may be used to obtain SiMiddle distance principal point (u)0,v0) The method of the nearest point is replaced to reduce the amount of calculation.
Orthodontic flat array images
The characteristic point set of the middle j column array unit is
And (5) calculating a predicted array straight line of the j-th array unit feature point according to S405-S408:
s405: the best fit line (i.e. column fit line) of the point set is obtained by a line fitting method, and the slope of the line is assumed to be
S406: finding a passing principal point (u)0,v0) And the equation of a straight line perpendicular to the best-fit straight line
This line is referred to as the perpendicular to the column-fit line.
S407: finding TjThe point closest to the perpendicular of the column-fitted straight line is assumed to have a pixel coordinate of (ρ)j,θj)。
S408: finding a passing point (rho)j,θj) And the slope is
Equation of (2)
This line is called the predicted array line of the j-th array of unit feature points.
In the case that the distortion of the camera is small, in the process of finding the predicted straight line of the j-th column of the array unit feature points, S407 can be used to find the predicted straight lineGet SiMiddle distance principal point (u)0,v0) The method of the nearest point is replaced to reduce the amount of calculation.
S409: the intersection of the prediction row line and the prediction column line is set as the prediction pixel coordinate.
In particular, because of the predicted pixel coordinates (u) of the ith row and j column array elementt,vt) Is the intersection point of two prediction straight lines, and the coordinates of the intersection point are substituted into two straight line equations to obtain:
vt＝γiut+(βi-γiαi)
the predicted pixel coordinate (u) of the ith row and j column array elementt,vt) Is a solution to the above binary order system of equations.
In the flow shown in fig. 4, the predicted pixel coordinates can be obtained only by using a linear algorithm, so that the calculation speed is high and the hardware implementation is easy.
Fig. 5 is a flowchart of calculating a distortion parameter of a camera according to at least a distorted pixel coordinate and a predicted pixel coordinate, which includes the following steps:
s501: and setting the initial distortion parameter to be 0, namely setting the initial orthodontic plane array image to be the plane array image.
S502: and acquiring the predicted pixel coordinates and the distorted pixel coordinates of the preset virtual feature points.
In order to solve the problem, in the embodiment, edge pixel points in the planar array image are selected as virtual feature points, distorted pixel coordinates of the virtual feature points are obtained from the planar array image, and predicted pixel coordinates of the virtual feature points are obtained from predicted pixel coordinates of the orthodontic planar array image.
And S503, substituting the distorted pixel coordinates and the predicted pixel coordinates into a preset distortion model to obtain an th distortion equation set.
And the distorted pixel coordinates are the pixel coordinates of the preset feature points in the current planar array image. And predicting pixel coordinates, namely pixel coordinates of preset characteristic points in the current orthodontic plane array image.
S504: and substituting the predicted pixel coordinates and the distorted pixel coordinates of the virtual feature points into the distortion model to obtain a second distortion equation set.
And S505, obtaining distortion parameters by solving least square solutions of the th distortion equation set and the second equation distortion set.
Specifically, when w is equal to m · n, the distortion model formula (1) is substituted with the predicted pixel coordinates as ideal pixel coordinates from the predicted pixel coordinates and the distorted pixel coordinates of each unit feature point, so as to obtain the th distortion equation set:
in the above two formulae, xt＝(ut-u0)R-1,yt＝(vt-v0)R-1,
According to the predicted pixel coordinate and the distorted pixel coordinate of the virtual feature point, the predicted pixel coordinate is used as an ideal pixel coordinate, and the ideal pixel coordinate is substituted into the distortion model formula (1) to obtain a second distortion equation set
In the above two formulae, Xt＝(Ut-u0)R-1,Yt＝(Vt-v0)R-1,
The distortion equations (2) (3) (4) (5) of w feature points and c virtual feature points are combined, and in order to reduce the contribution of the virtual feature points to the distortion parameters, the equal-sign sides of the equations (4) and (5) are multiplied by smaller weights epsilonsWherein 0 is not more than epsilons1, s 1,2, c, the following system of linear equations may be constructed:
let f be [ k ]1… kqp1p2]TThe above linear equation set is given as Af ═ b, and the least squares solution of the distortion parameters can be obtained as:
f＝(ATA)-1ATb (7)
s506: and judging whether the distortion parameters are converged, if so, ending the process, and if not, executing S507.
Convergence indicates that the distortion parameters are close to the optimal solution.
Specifically, the condition for convergence of the distortion parameter includes at least items as follows:
1. and calculating the iteration times of the distortion parameters to reach a preset value.
2. The deviation between the distortion parameter value obtained in the current iteration process and the distortion parameter value obtained in the last iterations process is less than the th preset threshold value.
3. And the deviation of the current distorted pixel coordinate and the historical distorted pixel coordinate is less than a second preset threshold value.
The current distortion pixel coordinate is determined by using the distortion parameter obtained in the current iteration process and the preset real pixel coordinate, and the historical distortion pixel coordinate is determined by using the distortion parameter obtained in the previous iteration processes and the real pixel coordinate.
The real pixel coordinates being known real coordinatesThe coordinates of pixels, e.g., pixels of 4 vertices of the planar array image: (U)1,V1)＝(1,1)，(U2,V2)＝(M,1)，(U3,V3)＝(M,N)，(U4,V4)＝(1,N)。
4. And the deviation between the predicted pixel coordinate determined by the orthodontic parameters obtained by the current iteration process and the orthodontic pixel coordinate is smaller than a third preset threshold value.
I.e., the deviation of the orthodontic pixel coordinates of the orthodontic planar array image used by the current iterative process and the corresponding predicted pixel coordinates calculated therefrom.
And S507, correcting the plane array image by using the calculated distortion parameters to obtain a new orthodontic plane array image, and replacing the orthodontic plane array image used in the previous iterations with the new orthodontic plane array image to update the orthodontic plane array image, and returning to the step S502.
It should be noted that the weight ε of c virtual feature pointssMay not be -fold and its value may change accordingly with each iteration.
For example, with 4 virtual feature points, the 4 virtual feature point weights are set to a fixed value of 0.003, i.e., εs0.003 ≡ 0.003, s ≡ 1, 2. Or, 2 virtual feature points are adopted, and the initial value of the weight of the 2 virtual feature points is set as epsilon1＝0.004，ε20.005, after each iteration, the distortion parameter is calculated1And ε2All increased by 0.001.
Optionally, in order to ensure that the means for preventing the over-fitting has a good effect, in this embodiment, the pixels of the 4 vertices of the distorted planar array image may be used as the virtual feature points, in this case, the actual pixel coordinates of the pixels of the 4 vertices may be used as the predicted pixel coordinates of the virtual feature points: that is, the predicted pixel coordinates of the virtual feature points are always (U)1,V1)＝(1,1)，(U2,V2)＝(M,1)，(U3,V3)＝(M,N)，(U4,V4)＝(1,N)。
In each iteration process, after the distortion parameters are calculated, the predicted pixel coordinates of 4 virtual feature points are used as ideal pixel coordinates and are respectively substituted into the formula (1), 4 distorted pixel coordinates are obtained, and the distorted pixel coordinates of the 4 virtual feature points are updated to be used as the distorted pixel coordinates of the virtual feature points in the next iteration process.
The flow shown in fig. 5 has the following beneficial effects:
1. in order to avoid the problem of serious distortion deformation of a position, which is far away from the main point, in the undistorted image due to an over-simulation phenomenon in the distortion parameter calculation, in this embodiment, an additional constraint condition (i.e., a virtual feature point) other than the preset feature point is used to prevent the over-fitting from occurring in the optimized distortion parameter solving process, so that the distortion deformation of a position, which is far away from the main point, in the undistorted image is avoided.
2. And after the least square solution is obtained, updating the orthodontic plane array image to iteratively calculate the distortion parameter until convergence, thereby obtaining the optimal distortion parameter.
Fig. 6 is a distortion correction device for cameras disclosed in the embodiment of the present application, including:
an image obtaining unit 601, configured to obtain a planar array image and an orthodontic planar array image, where the planar array image is acquired by a camera, and the orthodontic planar array image is obtained by correcting distortion of the planar array image;
an th coordinate acquiring unit 602, configured to acquire pixel coordinates of a preset feature point in the planar array image as distorted pixel coordinates;
a second coordinate obtaining unit 603, configured to obtain pixel coordinates of the preset feature point in the orthodontic plane array image as orthodontic pixel coordinates;
a third coordinate obtaining unit 604, configured to obtain a predicted pixel coordinate of the preset feature point according to the orthodontic pixel coordinate;
a distortion parameter calculation unit 605 for calculating a distortion parameter of the camera at least based on the distorted pixel coordinates and the predicted pixel coordinates;
an image rectification unit 606, configured to correct the image captured by the camera using the distortion parameter.
Optionally, the third coordinate obtaining unit is configured to obtain the predicted pixel coordinate of the preset feature point according to the orthodontic pixel coordinate, and includes:
the third coordinate acquiring unit is specifically configured to:
acquiring a predicted line straight line, wherein the predicted line straight line corresponding to the i-th line of orthodontic pixels in the orthodontic plane array image is determined by a slope i and pixel coordinates of a reference point i, the slope i is the slope of a line fitting straight line of the i-th line of orthodontic pixels, the reference point i is an orthodontic pixel point which is closest to a preset main point in the i-th line of orthodontic pixels, or an orthodontic pixel point which is closest to a vertical line of the line fitting straight line, and the vertical line is a straight line which passes through the main point and is perpendicular to the line fitting straight line;
obtaining a predicted column straight line, wherein the predicted column straight line corresponding to a jth orthodontic pixel in the orthodontic plane array image is determined by a slope j and a pixel coordinate of a reference point j, the slope j is the slope of a column fitting straight line of the jth orthodontic pixel, the reference point j is an orthodontic pixel point closest to a preset main point in the jth orthodontic pixel, or is an orthodontic pixel point closest to a vertical line of the column fitting straight line, and the vertical line of the column fitting straight line is a straight line which passes through the main point and is perpendicular to the column fitting straight line;
and taking the intersection point of the prediction row straight line and the prediction column straight line as the prediction pixel coordinate.
Optionally, the distortion parameter calculating unit is configured to calculate a distortion parameter of the camera according to at least the distorted pixel coordinate and the predicted pixel coordinate, and includes:
the distortion parameter calculation unit is specifically configured to:
substituting the distorted pixel coordinates and the predicted pixel coordinates into a preset distortion model to obtain distortion equation set, wherein the distortion model is used for representing the distorted pixel coordinates and the predicted pixel coordinates and generating a transformation relation according to the distortion parameters;
the distortion parameters are obtained by solving a least squares solution of a system of equations including at least the th distortion equation set.
Optionally, the system of equations further comprises:
and a second distortion equation set, wherein the second distortion equation set is obtained by substituting the predicted pixel coordinates and the distortion pixel coordinates of the preset virtual feature points into the distortion model.
Optionally, the distortion parameter calculating unit is configured to calculate a distortion parameter of the camera according to at least the distorted pixel coordinate and the predicted pixel coordinate, and further includes:
the distortion parameter calculation unit is specifically configured to:
after the distortion parameter is determined, if the distortion parameter is not converged, the following procedures are executed, the distortion parameter is calculated in an iterative mode until the distortion parameter is converged, the plane array image is corrected by using the distortion parameter obtained in the previous times of iterative processes, the orthodontic plane array image is updated, the pixel coordinate of the preset characteristic point in the orthodontic plane array image is obtained and is used as the orthodontic pixel coordinate, the predicted pixel coordinate of the preset characteristic point is obtained according to the orthodontic pixel coordinate, and the distortion parameter of the camera is calculated at least according to the distorted pixel coordinate and the predicted pixel coordinate.
Optionally, the condition for convergence of the distortion parameter includes at least terms as follows:
calculating the iteration times of the distortion parameters to reach a preset value;
the deviation between the distortion parameter value obtained in the current iteration process and the distortion parameter value obtained in the last iterations process is smaller than a th preset threshold value;
the deviation between the current distorted pixel coordinate and the historical distorted pixel coordinate is smaller than a second preset threshold, the current distorted pixel coordinate is determined by using the distorted parameter obtained in the current iteration process and a preset real pixel coordinate, and the historical distorted pixel coordinate is determined by using the distorted parameter obtained in the last iteration processes and the real pixel coordinate;
and the deviation between the predicted pixel coordinate determined by the orthodontic parameters obtained by the current iteration process and the orthodontic pixel coordinate is smaller than a third preset threshold value.
Optionally, the distortion parameters in the distortion model include:
the radial distortion model comprises a plurality of orders, a radial distortion parameter and a tangential distortion parameter.
The embodiment of the present application further discloses distortion correction equipment of cameras, please refer to fig. 7, which shows a schematic structural diagram of the distortion correction equipment of the camera, and the equipment may include at least processors 701, at least communication interfaces 702, at least memories 703 and at least communication buses 704;
in the embodiment of the present application, the number of the processor 701, the communication interface 702, the memory 703 and the communication bus 704 is at least , and the processor 701, the communication interface 702 and the memory 703 complete mutual communication through the communication bus 704;
the processor 701 may be central processing units, CPUs, or an ASIC specific integrated circuit
(Application Specific Integrated Circuit), or or more Integrated circuits or the like configured to implement embodiments of the invention;
the memory 703 may comprise high-speed RAM memory, and may also include non-volatile memory (non-volatile memory), etc., such as at least disk memories;
wherein the memory stores a program and the processor can call the program stored in the memory, the program for:
acquiring a planar array image and an orthodontic planar array image, wherein the planar array image is acquired by a camera, and the orthodontic planar array image is obtained by correcting distortion of the planar array image;
acquiring pixel coordinates of preset feature points in the planar array image as distorted pixel coordinates;
acquiring pixel coordinates of the preset characteristic points in the orthodontic plane array image as orthodontic pixel coordinates;
acquiring a predicted pixel coordinate of the preset feature point according to the orthodontic pixel coordinate;
calculating a distortion parameter of the camera based at least on the distorted pixel coordinates and the predicted pixel coordinates;
correcting the image captured by the camera using the distortion parameter.
Alternatively, the detailed function and the extended function of the program may be as described above.
The embodiment of the application also discloses readable storage media, which can store programs suitable for being executed by a processor, wherein the programs are used for:
acquiring a planar array image and an orthodontic planar array image, wherein the planar array image is acquired by a camera, and the orthodontic planar array image is obtained by correcting distortion of the planar array image;
acquiring pixel coordinates of preset feature points in the planar array image as distorted pixel coordinates;
acquiring pixel coordinates of the preset characteristic points in the orthodontic plane array image as orthodontic pixel coordinates;
acquiring a predicted pixel coordinate of the preset feature point according to the orthodontic pixel coordinate;
calculating a distortion parameter of the camera based at least on the distorted pixel coordinates and the predicted pixel coordinates;
correcting the image captured by the camera using the distortion parameter.
Alternatively, the detailed function and the extended function of the program may be as described above.
Based on the understanding, a part of the method or a part of the technical solution contributing to the prior art in the present application may be embodied in the form of a software product stored in storage media, which includes several instructions for causing computing devices (which may be personal computers, servers, mobile computing devices, network devices, etc.) to execute all or part of the steps of the method described in the embodiments of the present application.
The embodiments are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same or similar parts among the embodiments are referred to each other.
Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application.
Claims (10)
1, A distortion correction method for a camera, comprising:
acquiring a planar array image and an orthodontic planar array image, wherein the planar array image is acquired by a camera, and the orthodontic planar array image is obtained by correcting distortion of the planar array image;
acquiring pixel coordinates of preset feature points in the planar array image as distorted pixel coordinates;
acquiring pixel coordinates of the preset characteristic points in the orthodontic plane array image as orthodontic pixel coordinates;
acquiring a predicted pixel coordinate of the preset feature point according to the orthodontic pixel coordinate;
calculating a distortion parameter of the camera based at least on the distorted pixel coordinates and the predicted pixel coordinates;
correcting the image captured by the camera using the distortion parameter.
2. The method according to claim 1, wherein the obtaining the predicted pixel coordinates of the preset feature point according to the orthodontic pixel coordinates comprises:
acquiring a predicted line straight line, wherein the predicted line straight line corresponding to the i-th line of orthodontic pixels in the orthodontic plane array image is determined by a slope i and pixel coordinates of a reference point i, the slope i is the slope of a line fitting straight line of the i-th line of orthodontic pixels, the reference point i is an orthodontic pixel point which is closest to a preset main point in the i-th line of orthodontic pixels, or an orthodontic pixel point which is closest to a vertical line of the line fitting straight line, and the vertical line is a straight line which passes through the main point and is perpendicular to the line fitting straight line;
obtaining a predicted column straight line, wherein the predicted column straight line corresponding to a jth orthodontic pixel in the orthodontic plane array image is determined by a slope j and a pixel coordinate of a reference point j, the slope j is the slope of a column fitting straight line of the jth orthodontic pixel, the reference point j is an orthodontic pixel point closest to a preset main point in the jth orthodontic pixel, or is an orthodontic pixel point closest to a vertical line of the column fitting straight line, and the vertical line of the column fitting straight line is a straight line which passes through the main point and is perpendicular to the column fitting straight line;
and taking the intersection point of the prediction row straight line and the prediction column straight line as the prediction pixel coordinate.
3. The method of claim 1, wherein said calculating a distortion parameter for a camera based at least on said distorted pixel coordinates and said predicted pixel coordinates comprises:
substituting the distorted pixel coordinates and the predicted pixel coordinates into a preset distortion model to obtain distortion equation set, wherein the distortion model is used for representing the distorted pixel coordinates and the predicted pixel coordinates and generating a transformation relation according to the distortion parameters;
the distortion parameters are obtained by solving a least squares solution of a system of equations including at least the th distortion equation set.
4. The method of claim 3, wherein the system of equations further comprises:
and a second distortion equation set, wherein the second distortion equation set is obtained by substituting the predicted pixel coordinates and the distortion pixel coordinates of the preset virtual feature points into the distortion model.
5. The method of claim 3, wherein said calculating a distortion parameter for the camera based at least on the distorted pixel coordinates and the predicted pixel coordinates further comprises:
after the distortion parameter is determined, if the distortion parameter is not converged, the following procedures are executed, the distortion parameter is calculated in an iterative mode until the distortion parameter is converged, the plane array image is corrected by using the distortion parameter obtained in the previous times of iterative processes, the orthodontic plane array image is updated, the pixel coordinate of the preset characteristic point in the orthodontic plane array image is obtained and is used as the orthodontic pixel coordinate, the predicted pixel coordinate of the preset characteristic point is obtained according to the orthodontic pixel coordinate, and the distortion parameter of the camera is calculated at least according to the distorted pixel coordinate and the predicted pixel coordinate.
6. The method of claim 5, wherein the condition for convergence of distortion parameters comprises at least terms as follows:
calculating the iteration times of the distortion parameters to reach a preset value;
the deviation between the distortion parameter value obtained in the current iteration process and the distortion parameter value obtained in the last iterations process is smaller than a th preset threshold value;
the deviation between the current distorted pixel coordinate and the historical distorted pixel coordinate is smaller than a second preset threshold, the current distorted pixel coordinate is determined by using the distorted parameter obtained in the current iteration process and a preset real pixel coordinate, and the historical distorted pixel coordinate is determined by using the distorted parameter obtained in the last iteration processes and the real pixel coordinate;
and the deviation between the predicted pixel coordinate determined by the orthodontic parameters obtained by the current iteration process and the orthodontic pixel coordinate is smaller than a third preset threshold value.
7. The method of claim 3, wherein the distortion parameters in a distortion model comprise:
the radial distortion model comprises a plurality of orders, a radial distortion parameter and a tangential distortion parameter.
A distortion correction apparatus for camera, comprising:
the image acquisition unit is used for acquiring a plane array image and an orthodontic plane array image, wherein the plane array image is acquired by a camera, and the orthodontic plane array image is obtained by correcting distortion of the plane array image;
an th coordinate acquiring unit, configured to acquire pixel coordinates of a preset feature point in the planar array image as distorted pixel coordinates;
the second coordinate acquisition unit is used for acquiring the pixel coordinates of the preset characteristic points in the orthodontic plane array image as orthodontic pixel coordinates;
the third coordinate obtaining unit is used for obtaining the predicted pixel coordinate of the preset feature point according to the orthodontic pixel coordinate;
a distortion parameter calculation unit for calculating a distortion parameter of the camera at least according to the distorted pixel coordinates and the predicted pixel coordinates;
and the image correction unit is used for correcting the image acquired by the camera by using the distortion parameter.
A distortion correction apparatus for a camera of the kind 9, , comprising a memory and a processor;
the memory is used for storing programs;
the processor, for executing the program, implementing the steps of the distortion correction method of the camera as claimed in any of claims 1-7.
10, readable storage medium, having stored thereon a computer program, characterized in that the computer program, when being executed by a processor, carries out the steps of the method for distortion correction of a camera according to any of the claims , as set forth in claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910983234.5A CN110738707B (en) | 2019-10-16 | 2019-10-16 | Distortion correction method and device for camera, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910983234.5A CN110738707B (en) | 2019-10-16 | 2019-10-16 | Distortion correction method and device for camera, equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110738707A true CN110738707A (en) | 2020-01-31 |
| CN110738707B CN110738707B (en) | 2023-05-26 |
Family
ID=69269060
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910983234.5A Active CN110738707B (en) | 2019-10-16 | 2019-10-16 | Distortion correction method and device for camera, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110738707B (en) |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111387987A (en) * | 2020-03-26 | 2020-07-10 | 苏州沃柯雷克智能系统有限公司 | Height measuring method, device, equipment and storage medium based on image recognition |
| CN111415314A (en) * | 2020-04-14 | 2020-07-14 | 北京神工科技有限公司 | Resolution correction method and device based on sub-pixel level visual positioning technology |
| CN112947885A (en) * | 2021-05-14 | 2021-06-11 | 深圳精智达技术股份有限公司 | Method and device for generating curved surface screen flattening image |
| CN113115017A (en) * | 2021-03-05 | 2021-07-13 | 上海炬佑智能科技有限公司 | 3D imaging module parameter inspection method and 3D imaging device |
| CN113284189A (en) * | 2021-05-12 | 2021-08-20 | 深圳市格灵精睿视觉有限公司 | Distortion parameter calibration method, device, equipment and storage medium |
| CN113298699A (en) * | 2021-05-27 | 2021-08-24 | 上海电机学院 | Fisheye image correction method |
| CN113689413A (en) * | 2021-08-30 | 2021-11-23 | 深圳市睿达科技有限公司 | Alignment correction method and device and computer readable storage medium |
| CN113822937A (en) * | 2020-06-18 | 2021-12-21 | 中移(苏州)软件技术有限公司 | Image correction method, device, equipment and storage medium |
| CN113838138A (en) * | 2021-08-06 | 2021-12-24 | 杭州灵西机器人智能科技有限公司 | System calibration method, system, device and medium for optimizing feature extraction |
| CN114331814A (en) * | 2021-12-24 | 2022-04-12 | 合肥视涯技术有限公司 | Distorted picture correction method and display device |
| CN114648449A (en) * | 2020-12-18 | 2022-06-21 | 华为技术有限公司 | Image remapping method and image processing device |
| CN119295358A (en) * | 2024-12-12 | 2025-01-10 | 苏州镁伽科技有限公司 | Image distortion correction method, device, electronic device and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105701776A (en) * | 2016-01-07 | 2016-06-22 | 武汉精测电子技术股份有限公司 | Lens distortion correcting method and system used for automatic optical detection |
| CN105957041A (en) * | 2016-05-27 | 2016-09-21 | 上海航天控制技术研究所 | Wide-angle lens infrared image distortion correction method |
| CN108245788A (en) * | 2017-12-27 | 2018-07-06 | 苏州雷泰医疗科技有限公司 | A kind of binocular range unit and method, the accelerator radiotherapy system including the device |
| CN108986172A (en) * | 2018-07-25 | 2018-12-11 | 西北工业大学 | A kind of single-view linear camera scaling method towards small depth of field system |
-
2019
- 2019-10-16 CN CN201910983234.5A patent/CN110738707B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105701776A (en) * | 2016-01-07 | 2016-06-22 | 武汉精测电子技术股份有限公司 | Lens distortion correcting method and system used for automatic optical detection |
| CN105957041A (en) * | 2016-05-27 | 2016-09-21 | 上海航天控制技术研究所 | Wide-angle lens infrared image distortion correction method |
| CN108245788A (en) * | 2017-12-27 | 2018-07-06 | 苏州雷泰医疗科技有限公司 | A kind of binocular range unit and method, the accelerator radiotherapy system including the device |
| CN108986172A (en) * | 2018-07-25 | 2018-12-11 | 西北工业大学 | A kind of single-view linear camera scaling method towards small depth of field system |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111387987A (en) * | 2020-03-26 | 2020-07-10 | 苏州沃柯雷克智能系统有限公司 | Height measuring method, device, equipment and storage medium based on image recognition |
| CN111415314A (en) * | 2020-04-14 | 2020-07-14 | 北京神工科技有限公司 | Resolution correction method and device based on sub-pixel level visual positioning technology |
| CN113822937B (en) * | 2020-06-18 | 2024-01-26 | 中移(苏州)软件技术有限公司 | Image correction method, device, equipment and storage medium |
| CN113822937A (en) * | 2020-06-18 | 2021-12-21 | 中移(苏州)软件技术有限公司 | Image correction method, device, equipment and storage medium |
| CN114648449A (en) * | 2020-12-18 | 2022-06-21 | 华为技术有限公司 | Image remapping method and image processing device |
| CN113115017B (en) * | 2021-03-05 | 2022-03-18 | 上海炬佑智能科技有限公司 | 3D imaging module parameter inspection method and 3D imaging device |
| CN113115017A (en) * | 2021-03-05 | 2021-07-13 | 上海炬佑智能科技有限公司 | 3D imaging module parameter inspection method and 3D imaging device |
| CN113284189A (en) * | 2021-05-12 | 2021-08-20 | 深圳市格灵精睿视觉有限公司 | Distortion parameter calibration method, device, equipment and storage medium |
| CN112947885A (en) * | 2021-05-14 | 2021-06-11 | 深圳精智达技术股份有限公司 | Method and device for generating curved surface screen flattening image |
| CN112947885B (en) * | 2021-05-14 | 2021-08-06 | 深圳精智达技术股份有限公司 | Method and device for generating curved surface screen flattening image |
| CN113298699A (en) * | 2021-05-27 | 2021-08-24 | 上海电机学院 | Fisheye image correction method |
| CN113838138A (en) * | 2021-08-06 | 2021-12-24 | 杭州灵西机器人智能科技有限公司 | System calibration method, system, device and medium for optimizing feature extraction |
| CN113689413A (en) * | 2021-08-30 | 2021-11-23 | 深圳市睿达科技有限公司 | Alignment correction method and device and computer readable storage medium |
| CN114331814A (en) * | 2021-12-24 | 2022-04-12 | 合肥视涯技术有限公司 | Distorted picture correction method and display device |
| CN119295358A (en) * | 2024-12-12 | 2025-01-10 | 苏州镁伽科技有限公司 | Image distortion correction method, device, electronic device and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110738707B (en) | 2023-05-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110738707A (en) | Distortion correction method, device, equipment and storage medium for cameras | |
| CN107633536B (en) | Camera calibration method and system based on two-dimensional plane template | |
| US9153014B2 (en) | Image correction method and related image correction system thereof | |
| JP5075757B2 (en) | Image processing apparatus, image processing program, image processing method, and electronic apparatus | |
| CN109544643B (en) | Video camera image correction method and device | |
| CN112258418A (en) | Image distortion correction method, device, electronic equipment and storage medium | |
| CN112862895B (en) | A fisheye camera calibration method, device and system | |
| US20090141148A1 (en) | Distortion-corrected image generation unit and distortion-corrected image generation method | |
| CN113962892B (en) | Method, device and photographic equipment for correcting wide-angle lens image distortion | |
| CN111353963B (en) | Temperature compensation method and device for depth camera | |
| CN109887002A (en) | Image feature point matching method and device, computer equipment and storage medium | |
| CN111179184B (en) | Extraction method of effective area of fisheye image based on random sampling consistency | |
| CN105160632A (en) | Distortion correction method and mobile terminal | |
| CN116012241A (en) | Image distortion correction method, apparatus, computer device, and storage medium | |
| CN109547692B (en) | Image posture correction method, equipment and terminal | |
| CN111598777A (en) | Sky cloud image processing method, computer device and readable storage medium | |
| JP2013187822A (en) | Correction formula calculation method, correction method, correction apparatus, and imaging apparatus | |
| CN111028296B (en) | Method, device, equipment and storage device for estimating focal length value of spherical camera | |
| CN116012242A (en) | Camera distortion correction effect evaluation method, device, medium and equipment | |
| CN116051634A (en) | Visual positioning method, terminal and storage medium | |
| JP4020093B2 (en) | Edge detection method and apparatus, program, storage medium, and frame detection method, apparatus, program, and storage medium | |
| CN113724141B (en) | Image correction method and device and electronic equipment | |
| CN111539964B (en) | Plant canopy surface area acquisition method and device based on depth image, computer equipment and storage medium | |
| CN112927276A (en) | Image registration method and device, electronic equipment and storage medium | |
| CN113902644A (en) | Image processing method, device, equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |