Calibration method and device based on single-plane target distortion elimination, equipment and medium
By using the characteristic image marking and mapping matrix calculation method of single-plane target in the light field camera, the calibration process of the light field camera is simplified, the complex and time-consuming problem of calibration in the existing technology is solved, and the distortion of the light field camera is realized Correction and accuracy improvement.
Patent Information
- Application Number
- CN202411209543.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-30
- Publication Date
- 2024-12-27
AI Technical Summary
The calibration process of existing light field cameras is complex and time-consuming, and can only eliminate main lens distortion and lack convenience.
Using the feature image marking and mapping matrix calculation method based on single-plane targets, the plane target is characterized by feature marking through feature images, the corresponding relationship between the camera subview and the target feature points is constructed, the mapping matrix is calculated and image mapped to realize light Distortion correction for field cameras.
The light field camera calibration operation is simplified, the convenience is improved, and the distortion of the main lens and microlens array is effectively eliminated, and the measurement accuracy is improved.
Smart Images
Figure CN119205927A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of camera calibration, and in particular to a calibration method, device, equipment and medium based on single-plane target distortion elimination. Background Art
[0002] A light field camera is a device that can capture the direction of light in a scene. It maps light onto an image sensor through a microlens array to obtain depth and direction information of the scene. This device is often used in fields such as 3D reconstruction and virtual reality.
[0003] By making the central viewpoint imaging model of the light field camera equivalent to the classical camera model, the attitude parameters of the planar target can be estimated. In the prior art, the relative positions of the camera and the target are generally transformed multiple times to generate multiple intersections, and the parametric equations of the light corresponding to the pixels in the three-dimensional space are fitted through these intersections. Then, the light is uniformly resampled to eliminate the calibration error and realize the calibration of the light field camera.
[0004] However, the existing technology requires the collection of multiple sets of planar target data at different angles. The calibration process is complicated and time-consuming, and can only eliminate the distortion of the main lens.
[0005] Therefore, how to solve the low convenience of the current light field camera calibration process has become a technical problem that needs to be solved urgently. Summary of the invention
[0006] The present application provides a calibration method, apparatus, device and storage medium based on single-plane target distortion elimination, aiming to improve the convenience of the light field camera calibration process.
[0007] In a first aspect, the present application provides a calibration method based on single-plane target distortion elimination, the method comprising:
[0008] Based on the feature image, feature points on the plane target are marked to obtain target feature points;
[0009] Based on camera feature points corresponding to the target feature points in a camera subview of a light field camera, calculating a mapping matrix corresponding to the camera subview;
[0010] Based on the mapping matrix, image mapping is performed on the camera subview to obtain a distortion-corrected image of the camera subview, so as to achieve calibration of the light field camera.
[0011] In a second aspect, the present application further provides a calibration device based on single-plane target distortion elimination, the calibration device based on single-plane target distortion elimination comprising:
[0012] A target feature marking module is used to mark feature points on a plane target based on a feature image to obtain target feature points;
[0013] A mapping matrix calculation module, used to calculate a mapping matrix corresponding to the camera subview based on camera feature points corresponding to the target feature points in the camera subview of the light field camera;
[0014] The distortion correction module is used to perform image mapping on the camera subview based on the mapping matrix to obtain a distortion-corrected image of the camera subview, so as to calibrate the light field camera.
[0015] In a third aspect, the present application also provides a computer device, comprising a processor, a memory, and a computer program stored in the memory and executable by the processor, wherein when the computer program is executed by the processor, the steps of the calibration method based on single-plane target distortion elimination as described above are implemented.
[0016] In a fourth aspect, the present application also provides a computer-readable storage medium, on which a computer program is stored, wherein when the computer program is executed by a processor, the steps of the calibration method based on single-plane target distortion elimination as described above are implemented.
[0017] The present application provides a calibration method, device, computer equipment and storage medium based on distortion elimination of a single plane target. The method of the present application includes, based on a feature image, feature marking feature points on a plane target to obtain target feature points; based on camera feature points in a camera subview of a light field camera corresponding to the target feature points, calculating a mapping matrix corresponding to the camera subview; based on the mapping matrix, image mapping the camera subview to obtain a distortion-corrected image of the camera subview to achieve calibration of the light field camera. In the above manner, the present application features the plane target through a feature image, and achieves the construction of a correspondence between the camera feature points in the camera subview obtained by the light field camera acquiring the plane target and the target feature points, avoiding sampling of the plane target at multiple positions and angles, simplifying the calibration operation process of the light field camera, and improving the convenience of light field camera calibration. According to the correspondence between the feature points, the mapping matrix of the camera subview is constructed, so that the camera subview image is mapped into a distortion-free distortion-corrected image through the mapping matrix, thereby realizing the distortion correction of the main lens of the light field camera and the distortion correction of the microlens array, and improving the measurement accuracy of the light field camera. BRIEF DESCRIPTION OF THE DRAWINGS
[0018] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.
[0019] Figure 1 A schematic flow chart of a first embodiment of a calibration method based on single-plane target distortion elimination provided in an embodiment of the present application;
[0020] Figure 2 A schematic diagram of a distorted image provided in an embodiment of the present application;
[0021] Figure 3 A schematic diagram of a distortion-corrected image provided in an embodiment of the present application;
[0022] Figure 4 A schematic flow chart of a second embodiment of a calibration method based on single-plane target distortion elimination provided in an embodiment of the present application;
[0023] Figure 5 It is a structural schematic diagram of a first embodiment of a calibration device based on single-plane target distortion elimination provided by the present application;
[0024] Figure 6 It is a schematic block diagram of the structure of a computer device provided in an embodiment of the present application.
[0025] The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION
[0026] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.
[0027] The flowcharts shown in the accompanying drawings are only examples and do not necessarily include all the contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps may also be decomposed, combined or partially merged, so the actual execution order may change according to actual conditions.
[0028] In conjunction with the accompanying drawings, some embodiments of the present application are described in detail below. In the absence of conflict, the following embodiments and features in the embodiments can be combined with each other.
[0029] Please refer to Figure 1 , Figure 1 A schematic flow chart of a first embodiment of a calibration method based on single-plane target distortion elimination provided in an embodiment of the present application.
[0030] like Figure 1 As shown, the calibration method based on single-plane target distortion elimination includes steps S101 to S103.
[0031] S101, based on the feature image, feature marking the feature points on the plane target to obtain the target feature points;
[0032] In one embodiment, the feature image includes at least one of a stripe image, a Gray code image, a checkerboard image, etc. The feature image may also be other images containing rich features, as long as the feature points of the plane target can be uniquely marked to facilitate subsequent search and establishment of feature point correspondence.
[0033] In one embodiment, other encoding methods may be used to uniquely mark the feature points on the plane target. These encoding methods may be image processing technology, optical encoding technology, etc. The key is to achieve unique identification and marking of the feature points.
[0034] Furthermore, the characteristic image is acquired; based on an image mapping method, the characteristic image is mapped onto the plane target to obtain a characteristic-coded plane target; based on the characteristic-coded plane target, characteristic points on the plane target are marked to obtain the target characteristic points.
[0035] In one embodiment, a suitable stripe image, Gray code image or checkerboard image is selected as the feature image. For example, a group of black and white stripe images can be selected, and the width and spacing of the stripes can be adjusted according to requirements.
[0036] In one embodiment, the planar target should be flat, and the surface material should be able to clearly reflect or display the mapped feature image.
[0037] In one embodiment, a mapping device or other display device may be placed at an appropriate position on the planar target to ensure that the feature image can be evenly mapped on the entire planar target. The selected feature image is mapped onto the planar target by the mapping device to ensure that the image is clear and the stripes or patterns can be accurately identified.
[0038] For example, Figure 2 As shown, fringe mapping can be used to uniquely mark all points on a planar target. Specifically, a set of horizontal and vertical stripes and a Gray code image can be displayed on an electronic display screen, and the horizontal and vertical phases of each screen point can be obtained by phase resolution.
[0039] S102, calculating a mapping matrix corresponding to the camera subview based on camera feature points corresponding to the target feature points in the camera subview of the light field camera;
[0040] In one embodiment, the image mapping is a mapping of planes to points between planes.
[0041] In one embodiment, points corresponding to feature points on the target are identified in the subview of the light field camera. Since all points on the planar target are uniquely marked, only an appropriate number of equally spaced points need to be selected as feature points. Since the phase value of the feature point after phase modulation will not change after camera imaging, the [u, v] coordinates of the feature point on the camera plane can be obtained by searching and interpolating.
[0042] In one embodiment, feature point matching may also be accomplished using image processing techniques such as feature detection and matching algorithms.
[0043] It is understandable that if a feature image such as a checkerboard is used, the camera feature point search method must be replaced with a corresponding corner point detection algorithm.
[0044] In one embodiment, the three-dimensional coordinates of the target feature points may be converted into two-dimensional coordinates on the camera subview according to known light field camera intrinsic parameters and depth information.
[0045] The camera internal parameters include focal length, principal point coordinates, distortion coefficient, etc. The depth information may include the depth distance between the light field camera and the planar target.
[0046] In one embodiment, a linear equation system is constructed by matching the target feature points with the camera feature points to obtain feature point pairs. Each feature point pair can provide two equations for solving the elements of the mapping matrix.
[0047] For example, the mapping matrix between points on a plane is a 3×4 matrix, which can be expressed as:
[0048]
[0049] Among them, h 34 Usually set to 1 to simplify calculations.
[0050] In one embodiment, the least square method or other methods may be used to solve the above linear equations to obtain the optimal solution of the image mapping matrix.
[0051] In one embodiment, the obtained mapping matrix needs to be verified to ensure that it can accurately map the camera feature points in all camera subviews to the correct positions. An iterative method may be used to improve the accuracy of the mapping matrix.
[0052] In one embodiment, the mapping matrix of all feature point pairs of each camera subview is saved, and all subsequent camera subviews will be mapped to this virtual plane.
[0053] S103: Perform image mapping on the camera subview based on the mapping matrix to obtain a distortion-corrected image of the camera subview, so as to calibrate the light field camera.
[0054] In one embodiment, the camera subview is transformed using the already calculated mapping matrix. This involves finding the sub-pixel coordinates (u, v) that map each uniform grid point (x, y) on the virtual plane to the subview.
[0055] Generally, image mapping can help correct image distortion caused by lens distortion. The goal of this step is to obtain a distortion-corrected image.
[0056] Furthermore, based on the mapping matrix, the sub-pixel coordinates of each non-feature point in the camera sub-view are calculated; based on the interpolation method, the grayscale value corresponding to each sub-pixel value is determined; based on the grayscale value, the camera sub-view is mapped to a distortion-free virtual plane to obtain a distortion-corrected image of the camera sub-view.
[0057] In one embodiment, the interpolation method includes linear interpolation, bilinear interpolation, bicubic interpolation, spline interpolation and other interpolation methods.
[0058] Among them, linear interpolation is a simple interpolation between points in one dimension. Bilinear interpolation performs linear interpolation independently in two directions. Bicubic interpolation refers to the use of cubic polynomials for interpolation in two directions, providing smoother results. Spline interpolation uses spline curves for smooth interpolation.
[0059] In one embodiment, for a non-feature point (x, y) on a non-feature uniform grid point on a virtual plane, its sub-pixel coordinates (u, v) can be calculated according to the mapping matrix of the region in which it is located. Interpolation methods including but not limited to linear interpolation, bilinear interpolation, bicubic interpolation, spline interpolation, etc. can be used to obtain the grayscale value corresponding to the sub-pixel coordinates (u, v).
[0060] The coordinates of the camera view are (u, v), and the coordinates of the virtual plane, i.e., the target plane, are (x, y). The coordinates of the camera view are actual, lens-distorted, and non-uniform. The virtual target plane is preset in the embodiment of the present application, and the virtual target plane is uniform and distortion-free. The input of the mapping matrix established between the virtual plane and the camera view is a uniform (x, y) coordinate, and the output is a non-uniform (u, v) coordinate. The purpose is to obtain the sub-pixel coordinates of each uniform grid point in the actual image, and then obtain the grayscale values of these sub-pixel coordinates according to the interpolation method, and then assign the grayscale values to the uniform grid points (x, y) on the virtual plane.
[0061] In one embodiment, the selected interpolation method is applied to calculate the grayscale value corresponding to the sub-pixel coordinates. This is a sub-pixel level fine processing of the original image in order to map the distorted light field sub-view to the undistorted virtual plane, thereby reconstructing an undistorted image on the virtual plane.
[0062] In one embodiment, if Figure 3 As shown in FIG. 1 , by mapping all camera subviews of the light field camera to the same distortion-free virtual plane, the distortion of the main lens and the microlens array can be eliminated, thus achieving the calibration of the light field camera.
[0063] Optionally, after distortion correction and mapping are completed, the accuracy of the results can be verified. The correction effect can be evaluated by comparison with actual objects or by using known test patterns. The algorithm can be further optimized based on the evaluation results.
[0064] This embodiment provides a calibration method based on single-plane target distortion elimination, which features the plane target through a feature image, and realizes the construction of the correspondence between the camera feature points and the target feature points in the camera subview obtained by the light field camera collecting the plane target, avoiding the sampling of the plane target at multiple positions and multiple angles, simplifying the calibration operation process of the light field camera, and improving the convenience of the light field camera calibration. According to the correspondence relationship of the feature points, the mapping matrix of the camera subview is constructed, so that the camera subview image is mapped into a distortion-free distortion-corrected image through the mapping matrix, realizing the distortion correction of the main lens of the light field camera and the distortion correction of the microlens array, and improving the measurement accuracy of the light field camera.
[0065] Please refer to Figure 4 , Figure 4 A schematic flow chart of a second embodiment of a calibration method based on single-plane target distortion elimination provided in an embodiment of the present application.
[0066] like Figure 4 As shown, based on the above Figure 1 In the illustrated embodiment, step S102 specifically further includes:
[0067] S201, based on the light field camera, collecting the feature-marked planar target to obtain a camera subview;
[0068] In one embodiment, a light field camera is pointed at a planar target, and its position and angle are adjusted to ensure that the planar target is completely within the camera's field of view. The light field camera is turned on for data collection. The light field camera captures multiple sub-views of the planar target, each of which contains a portion of the planar target's information.
[0069] In one embodiment, the feature information and depth information of the planar target may be extracted through steps such as image registration, feature point matching, and three-dimensional reconstruction.
[0070] S202, searching for camera feature points corresponding to each of the target feature points in the camera subview based on the phase mark to obtain a feature point pair set;
[0071] In one embodiment, in the camera subview, the feature points on the target can be identified by phase marking technology, and their corresponding points in the camera image can be found. These point pairs (target feature points and camera feature points) constitute a feature point pair set.
[0072] In one embodiment, a light field camera is used to photograph a planar target to obtain multiple sub-views, which are the results of observing the same scene from different angles and contain depth information of the scene.
[0073] In one embodiment, phase marking is a method for accurately measuring the position of an object by adding specific phase changes to the image. In the camera subview, by analyzing these phase changes, the camera feature points corresponding to the target feature points can be found.
[0074] In one embodiment, camera feature points corresponding to target feature points in a planar target are extracted from a camera subview captured by a light field camera. Because target feature points are uniquely marked on a planar target, and their phase values do not change after being imaged by the camera. Therefore, according to the phase modulation principle, the phase values of these feature points can be converted into two-dimensional coordinates (u, v) on the camera imaging plane by searching and interpolating. Then, the mapping points of each target feature point in the camera subview are determined according to the two-dimensional coordinates, i.e., the camera feature points, thereby constructing a mapping relationship between the camera feature points and the target feature points.
[0075] Furthermore, a phase value of the preselected target feature point is obtained; the camera feature point corresponding to the phase value is searched in the camera subview; and the feature point pair set is obtained based on a mapping relationship between the camera feature point and the target feature point.
[0076] In one embodiment, some target feature points are pre-selected on a planar target. These target feature points may be prominent points on the planar target, such as corner points, edge points or other easily identifiable features. Phase marking technology is used to add phase marks to these pre-selected target feature points. For example, a specific scent pattern is added or a specific lighting mode is used. Then, the phase values of these feature points are extracted by image processing technology (such as Fourier transform). Among them, the phase value is the key information describing the position of the feature point.
[0077] In one embodiment, a camera feature point matching the phase value of a pre-selected target feature point is searched in the camera subview. Once a matching camera feature point is found, a mapping relationship between the target feature point and the camera feature point can be established. These mapping relationships can constitute a feature point pair set, which is the basis for subsequent image processing and analysis.
[0078] S203: Calculate a mapping matrix corresponding to each camera subview based on the feature point pair set.
[0079] In one embodiment, a mapping matrix P between points on a plane is used to transform each pixel point (u, v, 1) of the camera subview to find its coordinates (x, y, 1) on the new virtual plane. Since the mapping matrix has eight degrees of freedom, at least four pairs of feature points are required.
[0080] In one embodiment, each pair of feature points includes a point (u i , v i ) and the corresponding point (x i ,y i ). For each pair of feature points, a system of linear equations is constructed to solve the parameters of the mapping matrix between points on the plane:
[0081]
[0082] Among them, z i is a point on the virtual plane (x i ,y i , z i ) depth value. Generally, we can assume that z i =1.
[0083] In one embodiment, the least square method or other numerical methods (such as singular value decomposition) are used to solve the linear equations to obtain the mapping matrix P.
[0084] In this embodiment, image mapping helps to integrate data from different sensors or viewing angles, and promotes multimodal data processing and analysis. By using image mapping, images in different subviews can be aligned more accurately, reducing alignment errors.
[0085] See also Figure 5 , Figure 5 It is a structural schematic diagram of a first embodiment of a calibration device based on single-plane target distortion elimination provided in the present application. The calibration device based on single-plane target distortion elimination is used to execute the aforementioned calibration method based on single-plane target distortion elimination.
[0086] like Figure 5As shown, the calibration device 300 based on single-plane target distortion elimination includes: a target feature marking module 301 , a transformation matrix calculation module 302 and a distortion correction module 303 .
[0087] The target feature marking module 301 is used to perform feature marking on feature points on the plane target based on the feature image to obtain target feature points;
[0088] A mapping matrix calculation module 302 is used to calculate a mapping matrix corresponding to the camera subview based on camera feature points corresponding to the target feature points in the camera subview of the light field camera;
[0089] The distortion correction module 303 is used to perform image mapping on the camera subview based on the mapping matrix to obtain a distortion-corrected image of the camera subview, so as to calibrate the light field camera.
[0090] In one embodiment, the transformation matrix calculation module 302 includes:
[0091] A camera subview obtaining unit, configured to acquire the feature-marked planar target based on the light field camera to obtain a camera subview;
[0092] A feature point search unit, configured to search for camera feature points corresponding to each of the target feature points in the camera subview based on the phase mark, and obtain a feature point pair set;
[0093] The image mapping matrix calculation unit is used to calculate the mapping matrix corresponding to each camera subview based on the feature point pair set.
[0094] In one embodiment, the feature point search unit includes:
[0095] A phase value acquisition subunit, used to acquire the phase value of the pre-selected target feature point;
[0096] A feature point search subunit, used for searching the camera feature point corresponding to the phase value in the camera subview;
[0097] The feature point pair set obtaining subunit is used to obtain the feature point pair set based on the mapping relationship between the camera feature points and the target feature points.
[0098] In one embodiment, the target feature marking module 301 includes:
[0099] A feature image acquisition unit, used to acquire the feature image;
[0100] A feature image mapping unit, used to map the feature image onto the plane target based on an image mapping method to obtain a feature coded plane target;
[0101] The feature marking unit is used to mark the feature points on the plane target based on the feature coding plane target to obtain the target feature points.
[0102] In one embodiment, the distortion correction module 303 includes:
[0103] A sub-pixel coordinate calculation unit, used to calculate the sub-pixel coordinates of each non-feature point in the camera sub-view based on the mapping matrix;
[0104] A gray value calculation unit, used to determine the gray value corresponding to each sub-pixel value based on an interpolation method;
[0105] A distortion correction unit is used to map the camera subview to a distortion-free virtual plane based on the grayscale value to obtain a distortion-corrected image of the camera subview.
[0106] In one embodiment, the interpolation method includes linear interpolation, bilinear interpolation, bicubic interpolation and spline interpolation.
[0107] In one embodiment, the characteristic image includes at least one of a stripe image, a Gray code image, and a checkerboard image.
[0108] It should be noted that technicians in the relevant field can clearly understand that for the convenience and simplicity of description, the specific working process of the above-described device and each module can refer to the corresponding process in the aforementioned calibration method embodiment based on single-plane target distortion elimination, and will not be repeated here.
[0109] The apparatus provided in the above embodiment may be implemented in the form of a computer program. The computer program may be Figure 6 Runs on the computer device shown.
[0110] See also Figure 6 , Figure 6 1 is a schematic block diagram of a computer device provided in an embodiment of the present application. The computer device may be a server.
[0111] See also Figure 6 The computer device includes a processor, a memory and a network interface connected through a system bus, wherein the memory may include a non-volatile storage medium and an internal memory.
[0112] The non-volatile storage medium can store an operating system and a computer program. The computer program includes program instructions, and when the program instructions are executed, the processor can execute any calibration method based on single-plane target distortion elimination.
[0113] The processor is used to provide computing and control capabilities and support the operation of the entire computer equipment.
[0114] The internal memory provides an environment for the operation of the computer program in the non-volatile storage medium. When the computer program is executed by the processor, the processor can execute any calibration method based on single-plane target distortion elimination.
[0115] The network interface is used for network communication, such as sending assigned tasks, etc. Those skilled in the art will understand that Figure 6 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.
[0116] It should be understood that the processor may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Among them, the general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.
[0117] In one embodiment, the processor is used to run a computer program stored in the memory to implement the following steps:
[0118] Based on the feature image, feature points on the plane target are marked to obtain target feature points;
[0119] Based on camera feature points corresponding to the target feature points in a camera subview of a light field camera, calculating a mapping matrix corresponding to the camera subview;
[0120] Based on the mapping matrix, image mapping is performed on the camera subview to obtain a distortion-corrected image of the camera subview, so as to achieve calibration of the light field camera.
[0121] In one embodiment, the processor, when realizing the camera feature points corresponding to the target feature points in the camera subview based on the light field camera and calculating the mapping matrix corresponding to the camera subview, is used to implement:
[0122] Based on the light field camera, the planar target marked with features is collected to obtain a camera subview;
[0123] Based on the phase mark, searching for camera feature points corresponding to each of the target feature points in the camera subview to obtain a feature point pair set;
[0124] Based on the feature point pair set, a mapping matrix corresponding to each camera subview is calculated.
[0125] In one embodiment, when the processor searches for camera feature points corresponding to each of the target feature points in the camera subview based on the phase mark to obtain a feature point pair set, the processor is used to implement:
[0126] Obtaining a phase value of a preselected target feature point;
[0127] Searching for the camera feature point corresponding to the phase value in the camera subview;
[0128] The feature point pair set is obtained based on the mapping relationship between the camera feature points and the target feature points.
[0129] In one embodiment, when the processor performs feature marking on feature points on a planar target based on a feature image to obtain target feature points, the processor is used to implement:
[0130] Acquire the feature image;
[0131] Based on the image mapping method, the characteristic image is mapped onto the plane target to obtain a characteristic coded plane target;
[0132] Based on the feature-coded plane target, feature points on the plane target are marked to obtain the target feature points.
[0133] In one embodiment, when the processor performs image mapping on the camera subview based on the mapping matrix to obtain the distortion-corrected image of the camera subview, the processor is used to implement:
[0134] Based on the mapping matrix, calculating the sub-pixel coordinates of each non-feature point in the camera subview;
[0135] Determine the grayscale value corresponding to each sub-pixel value based on an interpolation method;
[0136] Based on the grayscale value, the camera subview is mapped to a distortion-free virtual plane to obtain a distortion-corrected image of the camera subview.
[0137] In one embodiment, the interpolation method includes linear interpolation, bilinear interpolation, bicubic interpolation and spline interpolation.
[0138] In one embodiment, the characteristic image includes at least one of a stripe image, a Gray code image, and a checkerboard image.
[0139] A computer-readable storage medium is also provided in an embodiment of the present application, wherein the computer-readable storage medium stores a computer program, wherein the computer program includes program instructions, and the processor executes the program instructions to implement any calibration method based on single-plane target distortion elimination provided in the embodiments of the present application.
[0140] The computer-readable storage medium may be an internal storage unit of the computer device described in the foregoing embodiment, such as a hard disk or memory of the computer device. The computer-readable storage medium may also be an external storage device of the computer device, such as a plug-in hard disk, a smart memory card (SmartMedia Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc., equipped on the computer device.
[0141] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed in the present application, and these modifications or replacements should be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be based on the protection scope of the claims.
Claims
1. A calibration method based on single-plane target distortion elimination, characterized in that: The method comprises: Based on the feature image, feature points on the plane target are marked to obtain target feature points; Based on camera feature points corresponding to the target feature points in a camera subview of a light field camera, calculating a mapping matrix corresponding to the camera subview; Based on the mapping matrix, image mapping is performed on the camera subview to obtain a distortion-corrected image of the camera subview, so as to achieve calibration of the light field camera.
2. The calibration method based on single-plane target distortion elimination according to claim 1, characterized in that: The step of calculating a mapping matrix corresponding to the camera subview based on the camera feature points corresponding to the target feature points in the camera subview of the light field camera comprises: Based on the light field camera, the planar target marked with features is collected to obtain a camera subview; Based on the phase mark, searching for camera feature points corresponding to each of the target feature points in the camera subview to obtain a feature point pair set; Based on the feature point pair set, a mapping matrix corresponding to each camera subview is calculated.
3. The calibration method based on single-plane target distortion elimination according to claim 2, characterized in that: The step of searching for camera feature points corresponding to each of the target feature points in the camera subview based on the phase mark to obtain a feature point pair set includes: Obtaining a phase value of a preselected target feature point; Searching for the camera feature point corresponding to the phase value in the camera subview; The feature point pair set is obtained based on the mapping relationship between the camera feature points and the target feature points.
4. The calibration method based on single-plane target distortion elimination according to claim 1, characterized in that: The method of marking the feature points on the plane target based on the feature image to obtain the target feature points includes: Acquire the feature image; Based on the image mapping method, the characteristic image is mapped onto the plane target to obtain a characteristic coded plane target; Based on the feature-coded plane target, feature points on the plane target are marked to obtain the target feature points.
5. The calibration method based on single-plane target distortion elimination according to claim 1, characterized in that: The performing image mapping on the camera subview based on the mapping matrix to obtain a distortion-corrected image of the camera subview includes: Based on the mapping matrix, calculating the sub-pixel coordinates of each non-feature point in the camera subview; Determine the grayscale value corresponding to each sub-pixel value based on an interpolation method; Based on the grayscale value, the camera subview is mapped to a distortion-free virtual plane to obtain a distortion-corrected image of the camera subview.
6. The calibration method based on single-plane target distortion elimination according to claim 5, characterized in that: The interpolation methods include linear interpolation, bilinear interpolation, bicubic interpolation and spline interpolation.
7. The calibration method based on single-plane target distortion elimination according to claim 1, characterized in that: The characteristic image includes at least one of a stripe image, a Gray code image, and a checkerboard image.
8. A calibration device based on single-plane target distortion elimination, characterized in that: The calibration device based on single-plane target distortion elimination comprises: A target feature marking module is used to mark feature points on a plane target based on a feature image to obtain target feature points; A mapping matrix calculation module, used to calculate a mapping matrix corresponding to the camera subview based on camera feature points corresponding to the target feature points in the camera subview of the light field camera; The distortion correction module is used to perform image mapping on the camera subview based on the mapping matrix to obtain a distortion-corrected image of the camera subview, so as to calibrate the light field camera.
9. A computer device, characterized in that: The computer device includes a processor, a memory, and a computer program stored in the memory and executable by the processor, wherein when the computer program is executed by the processor, the steps of the calibration method based on single-plane target distortion elimination as described in any one of claims 1 to 7 are implemented.
10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, wherein when the computer program is executed by a processor, the steps of the calibration method based on single-plane target distortion elimination as claimed in any one of claims 1 to 7 are implemented.