Correction method and system, storage medium, program product, electronic equipment and vehicle

Abstract

The invention relates to a correction method and system, a storage medium, a program product, electronic equipment and a vehicle, and relates to the field of image processing. The correction method is applied to a vehicle and mainly comprises the steps that distortion correction is conducted on a target projection image through a target method, and the target projection image is an image projected on an irregular curved surface related to the vehicle. Through the above technical scheme, a proper distortion correction method can be selected to correct the projection distortion of the projector, and the problem that the projection picture has linear or nonlinear distortion when the projector projects to the irregular curved surface related to the vehicle is effectively solved, so that the aesthetic degree of the projection picture relative to the visual field of a driver is improved, and the user experience is improved.

Description

Technical Field

[0001] The present application relates to the field of image processing, and in particular to a correction method, system, storage medium, program product, electronic device and vehicle. Background Art

[0002] In the related art, the projector distortion correction method usually adopts the method of identifying the imaging parameters in the projection process and the image features of the projected image on the projection surface, and determining the correction parameters for distortion correction. The existing distortion correction methods are mostly applied to the projection images of conventional planes, and the de-distortion effect is not good when projecting on irregular curved surfaces related to vehicles. Summary of the invention

[0003] The embodiments of the present application provide a calibration method, system, storage medium, program product, electronic device and vehicle to at least partially solve the above-mentioned technical problems.

[0004] In order to achieve the above-mentioned object, according to a first aspect of the present application, a correction method is provided, which is applied to a vehicle, and the method comprises: using a target method to perform distortion correction on a target projection image; The target projection image is an image projected onto an irregular curved surface associated with the vehicle.

[0005] Optionally, the irregular curved surface includes a surface of an A-pillar of the vehicle.

[0006] Optionally, the target method includes one of a perspective transformation method, a pixel matching method, a camera calibration method, a distortion model algorithm, and a multi-view geometry image algorithm.

[0007] Optionally, before using the target method to perform distortion correction on the target projection image, the method further includes: Determine the target method.

[0008] Optionally, the method for determining the target includes: Determining the target method according to the first camera image and the first projection image; Wherein, the first projection image is an image projected on the irregular curved surface; The first camera image is an image obtained by photographing the first projection image with a camera.

[0009] Optionally, the camera is a human eye measurement camera installed on a vehicle.

[0010] Optionally, the method of determining the target according to the first camera image and the first projection image includes: generating a target mapping table according to a center point in the first camera image and a calibration point in the first projection image; The target method is determined according to the target mapping table.

[0011] Optionally, generating a target mapping table according to a center point in the first camera image and a calibration point in the first projection image includes: Obtaining first coordinates of a center point in the first camera image in a camera image coordinate system; Acquire a second coordinate of the calibration point in the first projection image in the projection image coordinate system; The target mapping table between the center point and the correction point is generated based on the first coordinate and the second coordinate.

[0012] Optionally, before obtaining the first coordinates of the center point in the first camera image in the camera image coordinate system, the method further includes: Image enhancement is performed on the first camera image to identify the center point.

[0013] Optionally, obtaining a first coordinate of a center point in the first camera image in a camera image coordinate system includes: Acquire a detection point set based on the first camera image; determining the first coordinate using a clustering algorithm; wherein the detection point set is determined by identifying the dot matrix elements in the first camera image; The first coordinates are determined by performing cluster analysis on the detection point set.

[0014] Optionally, acquiring a second coordinate of the calibration point in the first projection image in a projection image coordinate system includes: Based on the spatial relationship of the calibration points in the first projection image, second coordinates of the calibration points are determined.

[0015] Optionally, generating the target mapping table between the center point and the correction point based on the first coordinate and the second coordinate includes: generating a first mapping table between the center point and the correction point based on a first mapping relationship between the first coordinate and the second coordinate; In a case where the number of the center points is less than or equal to the number of the correction points, determining repeated mapping points in the projection image coordinate system based on the first mapping table and the second coordinates; Determine, based on the repeated mapping points and the center points corresponding to the repeated mapping points, a second mapping table between the center points to be completed and the repeated mapping points; Generate the target mapping table based on the first mapping table and the second mapping table; The repeated mapping points include at least two correction points having a first mapping relationship with the same center point.

[0016] Optionally, the determining, based on the repeated mapping points and the center points corresponding to the repeated mapping points, a second mapping table between the center points to be completed and the repeated mapping points includes: Based on the first coordinates of the center point to be completed, use a convolution kernel to scan the first camera image to generate a third coordinate of the center point to be completed in the camera image coordinate system; Based on the second coordinate and the third coordinate, the second mapping table between the center point to be completed and the repeated mapping point is generated.

[0017] Optionally, the determining, based on the repeated mapping points and the center points corresponding to the repeated mapping points, a second mapping table between the center points to be completed and the repeated mapping points includes: Based on the first coordinate of the center point to be completed, shifting the first coordinate of the center point to be completed in a first direction by a predetermined pixel to generate a fourth coordinate of the center point to be completed in the camera image coordinate system; Based on the second coordinate and the fourth coordinate, the second mapping table between the center point to be completed and the repeated mapping point is generated.

[0018] Optionally, determining the target method according to the target mapping table includes: Acquire the area coordinates of the projection area in the camera image coordinate system according to the target mapping table; Processing the region coordinates by at least two distortion correction methods to obtain at least two corrected camera images; determining the target method based on at least two calibrated camera images; The projection area is an area on the irregular curved surface where the first projection image is displayed; and the target method is one of at least two distortion correction methods.

[0019] Optionally, the processing of the region coordinates by at least two distortion correction methods to obtain at least two corrected camera images includes: Based on the target mapping table and the projection area, at least two correction projection images are determined using at least two of the distortion correction methods, and at least two correction projection images are photographed using the camera to obtain at least two correction camera images.

[0020] Optionally, the method of determining the target according to at least two calibrated camera images comprises: determining a degree of overlap between at least two of the calibrated camera images; The target method is determined according to the value of the overlap degree; wherein the overlap degree is determined according to the overlap area between at least two of the calibrated camera images.

[0021] According to a second aspect of the present application, a correction system is provided, which is applied to a vehicle, and the system comprises: A vehicle-mounted projector for projecting a target projection image on an irregular curved surface associated with the vehicle; The distortion correction module is used to perform distortion correction on the target projection image using the correction method.

[0022] According to a third aspect of the present application, a non-temporary computer-readable storage medium is provided, on which a computer program is stored, and when the program is executed by a processor, the above-mentioned correction method is implemented.

[0023] According to a fourth aspect of the present application, a computer program product is also provided, comprising a computer program, wherein the computer program implements the steps of the above-mentioned correction method when executed by a processor.

[0024] According to a fifth aspect of the present application, an electronic device is provided, comprising: a memory on which a computer program is stored; and a processor for executing the computer program in the memory to implement the above-mentioned correction method.

[0025] According to a sixth aspect of the present application, a vehicle is provided, comprising the above-mentioned correction system or electronic device, or implementing the correction method described in any of the above-mentioned embodiments.

[0026] The benefits of this application are: The present application relates to a correction method, system, storage medium, program product, electronic device and vehicle, and relates to the field of image processing. Among them, the correction method mainly includes: using a target method to perform distortion correction on a target projection image, wherein the target projection image is an image projected on an irregular surface related to the vehicle. Through the above technical solution, a suitable distortion correction method can be selected to perform projector projection distortion correction, effectively solving the problem of linear or nonlinear distortion of the projection image when the projector is projected onto an irregular surface related to the vehicle, thereby improving the aesthetics of the projection image relative to the driver's field of view and enhancing the user experience.

[0027] Other features and advantages of the present application will be described in detail in the subsequent detailed description. BRIEF DESCRIPTION OF THE DRAWINGS In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present application, and those skilled in the art can obtain other drawings based on these drawings without creative work.

[0028] In order to more completely understand the present application and its beneficial effects, the following description will be given in conjunction with the accompanying drawings, wherein the same figure numbers represent the same parts in the following description.

[0029] Figure 1 is a flowchart of a calibration method provided in an embodiment of the present application; Figure 2 is a flowchart of another calibration method provided in an embodiment of the present application; Figure 3a is a top view of a schematic diagram of the arrangement of a correction device provided in an embodiment of the present application; Figure 3b is a side view of a schematic diagram of the arrangement of a correction device provided in an embodiment of the present application; Figure 4 is a flowchart of another calibration method provided in an embodiment of the present application; Figure 5 is a flowchart of another calibration method provided in an embodiment of the present application; Figure 6 It is a schematic diagram of the architecture of a correction system provided in an embodiment of the present application; Figure 7 It is a schematic diagram of the architecture of a vehicle provided in an embodiment of the present application.

[0030] Description of reference numerals: 10. Vehicle; 300. Correction system; 301. Human eye measurement camera; 302. Vehicle cockpit center console; 303. Vehicle projector; 304. A-pillar; 305. Distortion correction module. DETAILED DESCRIPTION

[0031] The technical solutions in the embodiments of the present application will be described clearly and completely below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present application.

[0032] According to the first aspect of the present application, an embodiment of the present application provides a calibration method, see Figure 1 , the correction method provided in the embodiment of the present application includes the following steps.

[0033] Step S100: Determine the target method.

[0034] Step S200: using a target method to perform distortion correction on a target projection image, wherein the target projection image is an image projected onto an irregular curved surface related to the vehicle.

[0035] In some embodiments, the irregular curved surface includes a surface of an A-pillar 304 of the vehicle 10 .

[0036] In some embodiments, the target method includes one of a perspective transformation method, a pixel matching method, a camera calibration method, a distortion model algorithm, and a multi-view geometry image algorithm.

[0037] It should be understood that the irregular curved surfaces associated with the vehicle 10 include irregular curved surfaces inside the vehicle 10 and irregular curved surfaces outside the vehicle 10. In the design of the vehicle 10, the cabin A-pillar 304 refers to the pillars located on both sides of the front windshield on the driver and front passenger sides. These pillars structurally support the roof and play an important role in the overall safety and stability of the vehicle 10. However, due to its position and shape, the A-pillar 304 may cause a certain obstruction to the driver's field of vision. The irregular curved surface associated with the vehicle 10 can be the inner surface of the A-pillar 304 facing the inside of the vehicle 10, or it can be the outer surface of the A-pillar 304 facing away from the inside of the vehicle 10, or it can be a welcome light carpet projected on an irregular ground, and this application does not limit this.

[0038] Exemplarily, the target projection image is an image projected on the irregular curved surface of the A-pillar 304 by the vehicle-mounted projector 303. Specifically, the projection information may include navigation information, warning information, or other augmented reality content. Since the curved surface of the A-pillar 304 may have a relatively complex geometric shape, the target projection image may have linear or nonlinear distortion, making the above-mentioned projection information difficult to identify in the driver's field of view. Therefore, it is necessary to select a suitable target method to be applied to the target projection image projected on the cockpit A-pillar 304, so as to effectively solve the projection distortion problem on the cockpit A-pillar 304, and ensure the accurate transmission of the projection information and the improvement of the driving experience.

[0039] Based on this, in step S100, a suitable target method is determined, and the selection of a specific target method may include at least one of the following distortion correction methods: Perspective transformation method: suitable for scenes that need to correct distortion caused by changes in viewing angle.

[0040] Pixel matching method: Corrects distortion by matching pixel points in the image, suitable for fine correction.

[0041] Camera calibration method: uses the internal and external parameters of the camera for calibration, which is suitable for scenes that require high-precision calibration.

[0042] Distortion model algorithm: Corrects distortion based on a specific mathematical model, suitable for scenarios with known distortion characteristics.

[0043] Multi-view geometry image algorithm: It uses the principle of multi-view geometry for correction, which is suitable for scenes that require comprehensive multi-angle information.

[0044] In the embodiment of the present application, a suitable target method is selected according to the characteristics of the cockpit A-pillar 304 . In step S200 , the selected target method is used to perform distortion correction on the image projected on the irregular curved surface.

[0045] Through the above technical solution, a suitable distortion correction method can be selected to correct the projector projection distortion, effectively solving the problem of linear or nonlinear distortion of the projection image when the projector is projected onto an irregular curved surface related to the vehicle, thereby improving the aesthetics of the projection image relative to the driver's field of view and enhancing the user experience.

[0046] In some embodiments, the above step S100 includes: Step S110: determining a target method according to the first camera image and the first projection image; Wherein, the first projection image is an image projected onto the irregular curved surface; The first camera image is an image obtained by photographing the first projection image with a camera.

[0047] In some embodiments, the camera is an eye measurement camera 301 mounted on a vehicle.

[0048] The human eye measurement camera 301 is a specially designed device used to simulate the position and view of the human eye. In the vehicle 10 design, the camera is installed in a place that simulates the position of the human eye, usually near the head position of the driver's seat, to ensure that the captured image is similar to the view seen by the human eye in the actual scene. At the same time, the camera's viewing angle is designed to match the field of view of the human eye, specifically, including the horizontal and vertical viewing angles, so as to capture an image similar to the natural field of view of the human eye.

[0049] Using the human eye measurement camera 301 can more accurately capture the image distortion that the driver may see during actual driving, which helps to select a more appropriate target method for distortion correction and ensure that the corrected image is clearly visible in the driver's field of view.

[0050] In the above step S110, the vehicle-mounted projector 303 is used to project onto an irregular curved surface such as the A-pillar 304 to obtain a first projection image, the human eye measurement camera 301 is used to shoot the first projection image to obtain a first camera image, the first projection image and the second camera image are processed and analyzed, and the most appropriate target method is selected to perform distortion correction, thereby effectively solving the problem of linear or nonlinear distortion of the projection image when the projector is projected onto an irregular curved surface, thereby ensuring accurate communication of information.

[0051] In some embodiments, the above step S110 specifically includes the following steps: Step S111: generating a target mapping table according to the center point in the first camera image and the calibration point in the first projection image; Step S112: Determine the target method according to the target mapping table.

[0052] In some embodiments, the above step S111 includes the following steps, referring to Figure 2 As shown: Step S1111: obtaining a first coordinate of a center point in a first camera image in a camera image coordinate system; Step S1112: obtaining the second coordinates of the calibration point in the first projection image in the projection image coordinate system; Step S1113: Generate a target mapping table between the center point and the calibration point based on the first coordinate and the second coordinate.

[0053] The embodiment of the present application can be based on the fixed cockpit layout of the vehicle 10, specifically, the fixed position of the vehicle projector 303, the fixed position of the camera (specifically, the human eye measurement camera 301) and the fixed installation position of the A-pillar 304, wherein the vehicle projector 303 can be installed in the center console 302 of the vehicle cockpit, for example, refer to Figures 3a to 3b It should be understood that the cockpit layout varies according to different vehicle models.

[0054] Each point in the image projected by the vehicle-mounted projector 303 is a calibration point, and the image formed by these calibration points is the first projection image. A projection image coordinate system is established based on the first projection image. Specifically, the upper left corner of the first projection image is taken as the origin, the upper left corner to the upper right corner is the positive direction of the x-axis, and the upper left corner to the lower left corner is the positive direction of the y-axis. The first projection image is a dot matrix image set covering all pixel points, and the constituent units of these dot matrices are small graphics with a certain regular set shape, including but not limited to circles, rhombuses and squares.

[0055] It should be understood that since the first projection image is an image projected on an irregular curved surface such as the cockpit A-pillar 304, the calibration points in the first projection image will be distorted. The distorted calibration points are photographed with a camera to obtain a first camera image, with each point in the first camera image as a center point, and a camera image coordinate system is established based on the first camera image. Specifically, the upper left corner of the first camera image is taken as the origin, the upper left corner to the upper right corner is the positive direction of the x-axis, and the upper left corner to the lower left corner is the positive direction of the y-axis.

[0056] As a specific example, taking the first projection image with a resolution of 640×400 as an example, there are a total of 640×400 pixels. The first projection image is split into multiple dot matrix images, each of which contains a X × Y dot matrix, where X is the number of columns, Y is the number of rows, the column spacing between each point in the dot matrix is ​​c, and the row spacing is r, so each row in the first projection image contains calibration points, each column contains A correction point, it should be understood that when X or Y When is 1, c or r are 0 respectively.

[0057] Different dot matrix images can be created by translating the dot matrix, and finally all the dot matrix images are integrated to include all the pixels in the first projection image.

[0058] Exemplarily, the translation distance of the dot matrix is ​​1 pixel. Since the movement distance between the dot matrix images is not large, in order to clearly separate different dot matrix images, a serial number map can be created between adjacent dot matrix images, and the map is used to indicate the serial number of the next frame of the projector projection image. At the same time, each dot matrix image is named, and the naming format includes but is not limited to: naming based on the coordinate serial number of the first point, so that the coordinates of other points can be determined by the spatial relationship between the dot matrix elements.

[0059] As a specific example, setting X , Y is a number greater than 1, that is, multiple rows and columns are collected simultaneously. This method can reduce the number of dot matrix images, thereby reducing the time for collecting data and optimizing the correction process. However, it has certain requirements for the subsequent algorithm for identifying correction points. As another specific example, set X is 1 or Y is 1, that is, the dot matrix is ​​a single column or a single row. In this case, the coordinates of each correction point can be easily identified when the correction point is subsequently identified. However, this method will result in an excessive number of dot matrix images and increase the cost of data acquisition.

[0060] It should be understood that the above-mentioned resolution graphics are only used as a specific example, and images with other resolutions are still within the protection scope of this application, and this application does not make specific limitations on this.

[0061] In step S1112, the second coordinates of the calibration points in the projection image coordinate system are obtained. The set of the second coordinates of all calibration points is: ,in, x is the coordinate value corresponding to the X-axis in the projection image coordinate system, y The coordinate value corresponding to the Y axis in the projection image coordinate system, P is the set of calibration points.

[0062] The schematic diagram of the arrangement of the calibration equipment used in the calibration method provided in the embodiment of the present application is shown in FIG. Figures 3a to 3b As shown, it is obvious that the camera's field of view is larger than the projection range. The camera uses a human eye measurement camera 301 to simulate the driver's eye position and view, that is, the camera is close to the A-pillar 304, exemplarily, the distance is several tens of centimeters. Therefore, if the dot matrix unit in the first projection image is a single pixel, the corresponding pixel in the first camera image that is projected and captured will be very small, resulting in difficulty in identifying the subsequent center point. Based on the above problems, a circle with a radius of 1, that is, a diameter of 2, is used in the embodiment of the present application, and the center of each small circle is a calibration point of the dot matrix. By shooting a set of dot matrix images, a first camera image containing all pixels of the first projection image can be obtained.

[0063] In step S1111, the first coordinate of the center point in the camera image coordinate system is obtained. The set of the first coordinates of all center points is ,in, X is the coordinate value corresponding to the X axis in the camera image coordinate system, Y The coordinate value corresponding to the Y axis in the camera image coordinate system, C is the set of identified center points.

[0064] In step S1113, based on the first coordinates of the correction points acquired in step S1111 and the second coordinates of the center point acquired in step S1112, a target mapping table between the center point and the correction points may be generated.

[0065] In step S112, a target method is determined according to the target mapping table to dedistort the target projection image.

[0066] Through the above steps, a mapping relationship between the center point and the correction point can be established, and a target mapping relationship between the center point and the correction point can be generated, so as to select a suitable target method for distortion removal and solve the problem of linear or nonlinear distortion of the projection image when the projector is projected onto an irregular surface.

[0067] Reference Figure 2As shown, in some embodiments, before the above step S1111, the calibration method further includes: Step S1110: performing image enhancement on the first camera image to identify a center point.

[0068] It should be understood that the first camera image is the above-mentioned image taken by the camera. X × Y A collection of dot matrix images, each dot matrix element is a geometric image. Due to various objective factors such as inconsistent clocks between the camera and the projector, too dark an image, etc., the dot matrix image in the first projection image projected by the projector may not be clear enough, which in turn may cause the first camera image taken by the camera to be not clear enough, making it difficult to identify the subsequent center point.

[0069] Based on this, before identifying the center point in the first camera image, it is necessary to perform image enhancement on the first camera image to increase the accuracy of subsequent center point identification.

[0070] Specifically, the first camera image obtained by shooting the first projection image with the camera is subjected to steps such as gamma transformation, image expansion, binarization, and image erosion, so as to convert the first camera image with complex colors into a simple black and white dot matrix and eliminate noise, thereby reducing the difficulty of subsequent center point recognition.

[0071] In some embodiments, the above step S1111 includes the following steps: Step S301: acquiring a detection point set based on a first camera image; Step S302: using a clustering algorithm to determine the first coordinate; wherein the detection point set is determined by identifying the dot matrix elements in the first camera image; The first coordinate is determined by performing cluster analysis on the set of detection points.

[0072] Center point detection is based on the idea that the lattice elements are regular symmetrical geometric figures. The edge points of each lattice element figure in the first camera image are obtained through edge detection, and then the contour is searched and the center of mass is calculated to form a detection point set.

[0073] Exemplarily, edge detection can use the Canny operator, which is a multi-stage edge detection algorithm. Specifically, the image is first Gaussian filtered to reduce the influence of noise; then the gradient strength and direction of the image are calculated, and the Sobel operator is usually used to calculate the gradient; next, the edge is refined by suppressing non-maxima, that is, checking whether the pixel is a local maximum in the gradient direction, and if not, it is suppressed to zero; then high and low double thresholds are used to detect strong edges and weak edges, and strong edges are directly retained, and weak edges are retained if they are connected to strong edges, otherwise they are suppressed; finally, the final edge map is formed by connecting weak edges and strong edges. Through the above method, the interference of non-edge points can be reduced. This method is suitable for scenes that require accurate edge detection, and can effectively reduce the influence of noise and provide refined edges.

[0074] Exemplarily, edge detection may also use the Sobel operator, which is a simple edge detection method mainly used to calculate the gradient of an image. Since the Sobel operator does not use non-maximum suppression and a double threshold method, the edge may be rough and is suitable for fast detection.

[0075] The embodiments of the present application do not limit the specific edge detection method used, and in actual use, a method can be selected based on specific application requirements and computing resources.

[0076] After obtaining the detection point set, a clustering algorithm is used to obtain the points of different element graphics, including but not limited to DBSCAN, K-means, etc., which is not limited in this application. Exemplarily, the DBSCAN algorithm is used, the minimum number of points is set to 2, and the neighborhood value is determined according to different experimental environments. Finally, the points of each cluster are averaged to obtain the first coordinate of the center point in the camera image coordinate system. It should be noted that since the projected first projection image is a light spot, and the center point is finally identified, the center point set is sparse in the camera image coordinate system.

[0077] The embodiment of the present application can accurately identify the center point in the first camera image and obtain its corresponding first coordinates through precise edge detection and cluster analysis, thereby ensuring the accuracy and flexibility of center point recognition.

[0078] In some embodiments, the above step S1112 includes the following steps: Step S311: determining second coordinates of the calibration points based on the spatial relationship of the calibration points in the first projection image.

[0079] The first projection image is a collection of multiple dot matrix images. To determine the second coordinates of each calibration point in each dot matrix image, the second coordinates of the first point in a dot matrix image in the projection image coordinate system can be obtained. The second coordinates of all calibration points in the first projection image in the projection image coordinate system are determined based on the spatial relationship between each dot matrix element (i.e., calibration point) in the dot matrix image. Specifically, the above spatial relationship is that the column spacing between each point in the dot matrix image is c , the row spacing is r .

[0080] As a specific example, suppose m The first point in the bitmap is , then the first i List j The row points can be represented as .

[0081] Based on the above spatial relationship, the second coordinates of all the correction points can be determined, which are used to subsequently determine the mapping relationship between the correction points and the center point.

[0082] Reference Figure 4 As shown: In some embodiments, the above step S1113 includes the following steps: Step S321: generating a first mapping table between the center point and the calibration point based on a first mapping relationship between the first coordinate and the second coordinate; Step S322: when the number of center points is less than or equal to the number of calibration points, determining repeated mapping points in the projection image coordinate system based on the first mapping table and the second coordinates; Step S323: determining a second mapping table between the center point to be completed and the repeated mapping point based on the repeated mapping point and the center point corresponding to the repeated mapping point; Step S324: generating a target mapping table based on the first mapping table and the second mapping table; The repeated mapping points include at least two correction points having a first mapping relationship with the same center point.

[0083] Exemplarily, the first i List j The second coordinate of the point in the row can be expressed as , based on the first camera image and the identified center point set , it can be determined that the first coordinate of the center point corresponding to the point in the first camera image can be expressed as , the first mapping relationship between the first coordinate and the second coordinate can be expressed as In step S321, based on the first mapping relationship, a first mapping table between the center point and the correction point may be generated.

[0084] It should be understood that since the projection area of ​​the A-pillar 304 is an irregular curved surface with discontinuous and inconsistent curvature, and the projector device may be affected by objective factors such as temperature during projection, the first mapping relationships between the center point and the calibration point may be different from each other. All first mapping tables between the center point and the calibration point can be represented as a set .

[0085] Affected by the error of the image taken by the camera and the error of the center point recognition, the center point set The number of elements in will be less than or equal to the first projection image point set In step S322, based on the first mapping table, the number of elements in the first projection image dot matrix set is that a plurality of calibration points in the first projection image dot matrix set correspond to the same center point in the first camera image, and there is a first mapping table relationship between them. A set of second coordinates corresponding to the set of points of the first projection image , the set of repeated correction points in the projection image coordinate system can be determined ,in R is the set of all repeated calibration points (i.e., repeated mapping points).

[0086] Due to the existence of repeated mapping points, there is no one-to-one correspondence between the center point and the correction point, so these repeated mapping points need to be supplemented. In step S323, based on the repeated mapping points and the center points corresponding to the repeated mapping points, a second mapping table between the center point to be supplemented and the repeated mapping points can be determined. ,in, F 2 is a set of second mapping tables.

[0087] In step S324, by merging the first mapping table With the second mapping table Get the target mapping table ,in, F Is a collection of target mapping tables.

[0088] Through the above steps, the target mapping relationship between all center points and calibration points can be obtained.

[0089] In some embodiments, the above step S323 includes the following steps: Step S331: based on the first coordinates of the center point to be completed, use the convolution kernel to scan the first camera image to generate the third coordinates of the center point to be completed in the camera image coordinate system; Step S332: generating a second mapping table between the center point to be completed and the repeated mapping points based on the second coordinate and the third coordinate.

[0090] In the process of completing the center point of repeated mapping points, a position-based convolution interpolation method can be used. It should be understood that the position-based convolution interpolation is to create a new mapping relationship based on the field of the center point corresponding to the repeated mapping point, so as to obtain the center point to be completed.

[0091] Specifically, taking the center point corresponding to the repeated mapping point as the center, based on k × k The first coordinate of the center point within the sphere of size, using a size k × k The convolution kernel scans and calculates the new camera image coordinate system coordinates. The number of repeated points in the neighborhood is r , the convolution kernel weight is: ;in, w n is the weight corresponding to each neighborhood point, ( x n , y n ) is the coordinate of the neighborhood point, so the third coordinate of the center point to be completed can be obtained by the following formula: .

[0092] It should be noted that when the convolution kernel scans the first camera image, the set R of repeated mapping points needs to be updated to prevent the third coordinate of the center point to be completed from being repeated after the convolution calculation.

[0093] After completion, in step S332, a second mapping table between the center point to be completed and the repeated mapping points is generated. , there is a one-to-one correspondence between the center point to be completed and the repeated mapping point.

[0094] In some embodiments, the above step S323 includes the following steps: Step S341: based on the first coordinate of the center point to be completed, shifting the first coordinate of the center point to be completed by a predetermined pixel in a first direction to generate a fourth coordinate of the center point to be completed in the camera image coordinate system; Step S342: generating a second mapping table between the center point to be completed and the repeated mapping points based on the second coordinate and the fourth coordinate.

[0095] In the process of completing the center point of the repeated mapping point, the pixel offset method can also be used. Specifically, the pixel offset method recursively offsets the center point corresponding to the repeated mapping point by one pixel to the right until the first left side of the center point corresponding to the repeated mapping point no longer overlaps, so as to form a one-to-one mapping relationship between the center point and the correction point.

[0096] It should be understood that the first direction can be rightward or leftward, and the predetermined pixel can be 1 pixel, 2 pixels or even more pixels. It can be adjusted according to actual usage requirements during use, and this application does not limit this.

[0097] After completion, in step S342, a second mapping table between the center point to be completed and the repeated mapping points is generated. , there is a one-to-one correspondence between the center point to be completed and the repeated mapping point.

[0098] The pixel offset method mentioned above is used for center point completion. The algorithm is simple and the calculation time is short. It has certain advantages in processing efficiency and is suitable for fast processing scenarios. The convolution interpolation method mentioned above is more complex in algorithm than the pixel offset method. However, the convolution interpolation method takes into account the spatial relationship between the center points corresponding to the repeated mapping points and the re-read mapping points, and provides a more accurate mapping relationship, which is suitable for scenarios requiring high precision.

[0099] Reference Figure 5 As shown, in some embodiments, the above step S112 includes the following steps: Step S1121: obtaining the area coordinates of the projection area in the camera image coordinate system according to the target mapping table; Step S1122: Processing the region coordinates by at least two distortion correction methods to obtain at least two corrected camera images; Step S1123: determining a target method based on at least two calibrated camera images; The projection area is an area on the irregular curved surface where the first projection image is displayed; and the target method is one of at least two distortion correction methods.

[0100] After obtaining the complete target mapping table, a one-to-one mapping relationship is formed between the correction point and the center point. Next, the target method can be determined according to the target mapping table to perform image distortion correction.

[0101] In step S1121, illustratively, referring to Figures 3a to 3b As shown, based on the vehicle 10 cockpit environment, driver position, sight line and other environmental configurations, a suitable A-pillar 304 projection area is selected, and the coordinates of the projection area in the camera image coordinate system are obtained according to the target mapping table. The shape of the projection area is a straight line that fits the left and right sides of the A-pillar 304, and can be, but not limited to, a rectangle, a parallelogram, etc. The specific shape is selected when the vehicle model is adapted. The projection area can be selected using the four vertex coordinates (i.e., regional coordinates) of the regional geometric figure in the camera image coordinate system: ; Among them, ul ,ll , ur and lr They represent the positions of the four vertices: upper left, lower left, upper right, and lower right.

[0102] In step S1122, at least two of the distortion correction methods such as perspective transformation method, pixel matching method, camera calibration method, distortion model algorithm, multi-view geometry image algorithm, etc. are used to perform dedistortion processing on the above-mentioned region coordinates, so as to obtain at least two corresponding corrected camera images respectively.

[0103] In step S1123, the preferred target method is determined based on the obtained at least two calibrated camera images. Exemplarily, the dedistortion effects of the calibrated camera images can be compared to select the distortion correction method corresponding to the calibrated camera image with the best dedistortion effect as the preferred target method.

[0104] The embodiment of the present application determines a target method after performing distortion correction using a plurality of distortion correction methods, and can select the optimal target method for distortion correction in the case of a projection area on an irregular curved surface.

[0105] In some embodiments, the above step S1122 includes the following steps: Step S401: Based on the target mapping table and the projection area, at least two distortion correction methods are used to determine at least two corrected projection images, and at least two corrected camera images are obtained by shooting the at least two corrected projection images with a camera.

[0106] As a specific example, the embodiment of the present application selects two distortion correction methods, namely, a perspective transformation method and a pixel matching method, to perform distortion correction on the first projection image to obtain two corrected projection images.

[0107] For ease of understanding, in the following description, the projection image that uses the perspective transformation method to perform distortion correction is the second projection image, and the second projection image captured by the camera is the second camera image; the projection image that uses the pixel matching method to perform distortion correction is the third projection image, and the third projection image captured by the camera is the third camera image. Both the second projection image and the third projection image are corrected projection images; and both the second camera image and the third camera image are corrected camera images.

[0108] In step S1121, the coordinates of the projection area in the camera image coordinate system are obtained, and the coordinates of the points in the projection area are determined, that is, which points are included in the projection area. Specifically, the four vertices can be used to determine the coordinates of the points in the projection area. ul , ll , urand lr Get the boundary line of the projection area, and then get all the points that fall within the projection area. The set of all points that fall within the projection area is ,in,( X 1, Y 1) is the coordinates of the points in the projection area in the camera image coordinates. The points in this set can be used for pixel matching methods. Specifically, the pixel matching method directly uses the pixel set in the corresponding projection area geometry. Projection is performed, and other pixels outside the set are set to black, that is, not displayed. The third projection image is projected using the pixel matching method. The third camera image obtained by the camera is distortion-free in the camera image coordinate system and can be used as an alignment object.

[0109] Furthermore, it is assumed that there is a line-to-line correspondence between the first projection image and the projection geometric figure area, that is, the four edges of the first projection image maintain a row-column correspondence with the edges of the projection area. It should be noted that, unlike the conventional perspective transformation that only uses four vertices for calibration, the nonlinear characteristics of the surface in the A-pillar 304 area require the use of more matching point pairs for fitting to ensure the accuracy of the perspective transformation. Since the center points in the first camera image are sparse in the camera image coordinate system space, in order to obtain the above-mentioned line-to-line correspondence, a suitable center point fitting method is required to determine the geometry of the projection area. The Euclidean distance fitting method is used in the embodiment of the present application, and each row in the geometry is sampled at equal intervals. N p points, equally spaced sampling M p Row, get the set of sampling points For each sampling point ( X p , Y p ), select the center point with the smallest Euclidean distance to ensure the accuracy of the fitting. The calculation formula of Euclidean distance is as follows: ; in,( X i , Y i ) is the center point in the first camera image.

[0110] In this way, the fitted camera image coordinate system point set can be obtained , and then obtain the geometric point set of the projection area required for perspective transformation. In this embodiment, the number of sampling points in each row is N p The value is 5 to ensure sufficient accuracy and coverage, which is not limited in this application.

[0111] Perspective Transformation is a geometric transformation that projects an image from one perspective to another, which can simulate the projection effect in three-dimensional space. Its core is to map the coordinates of each pixel in the image through a 3×3 transformation matrix, so that the originally tilted and distorted image area is "straightened" or adjusted to a specific perspective.

[0112] Perspective transformation preserves the straight line shape of the image, but changes the parallelism of the straight lines of the image compared to affine transformation. The transformation formula of homogeneous coordinates of perspective transformation is: ; Among them, the left side of the equation is the transformed coordinates, and the right side of the equation is the transformation matrix T and the coordinates before transformation; a 11 , a 12 , a 21 , a 22 Control rotation, scaling, and shearing (affine transformation part); a 13 , a 23 Control translation; a 31 , a 32 Controlling the perspective effect is the core of perspective transformation.

[0113] The transformed coordinates are rewritten as: ; Then the perspective transformation formula becomes: .

[0114] Among them, the transformation matrix a 33 The term can be rewritten as 1 to obtain the new transformation matrix: .

[0115] Therefore, the number of unknowns in the transformation matrix changes from 9 to 8. Since one set of matching point pairs provides two equations, the perspective transformation in the traditional projection correction requires four sets of matching point pairs, i.e., four vertices of the correction area. However, in order to better eliminate the influence of the irregular curved surface of the A-pillar 304, the embodiment of the present application uses more point pairs, i.e., the above N p × M p To obtain the fitting point set The corresponding point pairs in the projection image coordinate system are similarly sampled in equally spaced rows and columns in the first projection image. N p × M p points, and finally we can get the transformation matrix T p Based on the transformation matrix T p The second projection image can be calculated from the first projection image, that is, the target projection image pre-distorted by the perspective transformation method. The projected image is a corrected image, and the distortion has been mostly removed.

[0116] The second projection image is photographed by a camera to obtain a second camera image. Due to the irregular curved surface feature of the A-pillar 304 , the second camera image is a distorted image.

[0117] The advantage of the pixel matching method is that it can present the projected image without distortion, maximizing the quality of the image visualized on the A-pillar 304. However, the area that can be projected is limited, which is a pixel set in a fixed area. .

[0118] The perspective transformation method can project images of any area or range and retain the blind spot information to the maximum extent. However, its visualization effect is related to the camera position and the design of the A-pillar 304, and the projected image still has some distortion.

[0119] Therefore, for example, when matching the vehicle models of functions, it is necessary to decide which method to use based on the effects of the two. Through the above-mentioned perspective transformation method and pixel matching method, two corrected projection images can be obtained: the second projection image and the third projection image, and two corrected camera images: the second camera image and the third camera image. These corrected camera images will be used later to determine the target method for distortion correction.

[0120] In some embodiments, the above step S1123 includes the following steps: Step S411: determining the degree of overlap of at least two calibrated camera images; Step S412: determining a target method according to the value of the overlap; The degree of overlap is determined based on an overlap area between at least two calibrated camera images.

[0121] RMSE (Root Mean Square Error) is used to measure the difference between two images. It evaluates the degradation of image quality by calculating the square root of the average of the squares of the difference between the corresponding pixels of the two images. The smaller the RMSE value, the more similar the two images are. This is widely used in image quality assessment, for example, to quantify the accuracy of image reconstruction, image compression, or prediction models.

[0122] However, in the specific scenario involved in the embodiment of the present application, due to the difference in the projected images, the traditional RMSE method is not suitable for evaluating the effect of the two calibrated camera images. Therefore, illustratively, a comparison method is used in the embodiment of the present application to evaluate the quality of the second camera image obtained by the perspective transformation method.

[0123] Specifically, the method comprises the following steps: The second camera image and the third camera image are binarized respectively. Binarization is an image processing technique that converts the pixel values ​​in an image into a simple form of 0 or 1 (or black and white) to facilitate subsequent comparison and analysis.

[0124] Compare the binarized second camera image and the third camera image and calculate the overlap degree (coincidence degree) of their valid pixels (i.e., non-zero pixels). This step evaluates their similarity by comparing the matching of valid pixels at the same position in the two images.

[0125] Whether to use the perspective transformation method as the final correction method is determined based on the comparison result of the overlap value and the preset threshold. In this embodiment, the preset threshold is set to 3% of the total pixels of the camera. If the overlap value of the effective pixels is lower than the preset threshold, it means that the quality of the second camera image is acceptable and the perspective transformation method can be used as the final correction method; on the contrary, if the overlap value is higher than the preset threshold, it means that the perspective transformation method may not be suitable and the pixel matching method should be used for correction.

[0126] This method can more accurately reflect the quality of the image after perspective transformation by directly comparing the overlap of effective pixels, thus providing a basis for selecting an appropriate correction method.

[0127] Compared with the existing projector distortion correction method, the correction method provided in the embodiment of the present application focuses on the visualization scene of the cockpit A-pillar 304, uses a camera to simulate the position and field of view of the human eye, and saves the relevant parameters after the correction is completed. The camera can be removed, that is, it is used when the function development is matched with the vehicle model, and no additional hardware equipment is required for mass production. Compared with the built-in camera, TOF (Time of Flight), gyroscope and other methods of the existing methods, the cost is lower and the cost is reduced to the extreme. At the same time, the embodiment of the present application takes into account that the traditional trapezoidal correction or projector correction method mostly uses affine transformation, perspective transformation, plane fitting, posture estimation and other methods, and the effect is reduced when processing the projection surface with irregular curvature. Under different vehicle models and different cockpit designs, the effect of the perspective transformation method is reduced to different degrees, so the pixel matching method is additionally used for comparison and verification and selection.

[0128] Through the above technical solution, a suitable distortion correction method can be selected to correct the projector projection distortion, effectively solving the problem of linear or nonlinear distortion of the projection image when the projector is projected onto an irregular curved surface related to the vehicle, thereby improving the aesthetics of the projection image relative to the driver's field of view and enhancing the user experience.

[0129] According to the second aspect of the present application, the embodiment of the present application further provides a correction system 300, which is applied to a vehicle 10, such as Figure 6 As shown, the system includes: The vehicle-mounted projector 303 is used to project a target projection image on an irregular curved surface associated with the vehicle 10; The distortion correction module 305 is used to perform distortion correction on the target projection image using the correction method described in any of the above embodiments.

[0130] As a specific example, the vehicle model selected in the embodiment of the present application is a fixed model Song PLUS, the camera is installed at the driver's common seat position, the camera height is 1.2m, which is the average height of the driver's sitting position, and the camera has a sufficient field of view to capture all projection images. Therefore, the camera capture view is consistent with the human eye view. Figure 1 At the same time, the camera has a high resolution, and the first camera image taken is clear enough, which is more convenient for center point identification. Exemplarily, the camera in this embodiment includes but is not limited to the use of Hikvision industrial cameras, and the lens includes but is not limited to HF0628M-6MPE; the projector is installed in the center console, and the projection lens is partially hollowed out and exposed. Exemplarily, the projector can be a MEMS (Micro-Electro-Mechanical Systems) projector, which is cheap and has low hardware cost; Exemplarily, the projector can also be a DLP (Digital Light Processing) projector. Under the current industry technology, this type of projector has a slightly higher clarity, but the price is more expensive, and most of this type of projector belongs to the supplier Texas Instruments, which is not suitable for independent research and development; Exemplarily, the projector can also be an LCOS (Liquid Crystal on Silicon) projector, which is more expensive. This application does not limit the choice of projector, and a reasonable choice can be made according to application requirements.

[0131] It should be noted that the projection area of ​​the projector needs to be larger than or equal to the area of ​​the A-pillar 304 , so as to ensure that the calibrated image can cover the area of ​​the A-pillar 304 .

[0132] It should be understood that the correction system 300 has all the beneficial effects of the above correction method, which will not be described in detail in this application.

[0133] According to the third aspect of the present application, an embodiment of the present application further provides a non-transitory computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, the steps of the above-mentioned correction method are implemented. The non-transitory computer-readable storage medium has all the beneficial effects of the above-mentioned correction method, and the present application will not repeat them here.

[0134] According to the fourth aspect of the present application, an embodiment of the present application further provides a computer program product, including a computer program. When the computer program is executed by a processor, the above correction method is implemented and has all the beneficial effects of the above correction method. The present application will not go into details here.

[0135] According to the fifth aspect of the present application, an embodiment of the present application further provides an electronic device, comprising: a memory and a processor, wherein a computer program is stored in the memory; and the processor is used to execute the computer program in the memory to implement the steps of the above correction method. The electronic device has all the beneficial effects of the above correction method, which will not be described in detail in this application.

[0136] The computer-readable storage medium may be, for example, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or component, or any combination thereof, which is not specifically limited in the present application. More specific examples of computer-readable storage media may include, but are not limited to, an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof.

[0137] In some embodiments of the present application, computer-readable storage media may be any tangible media that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0138] The computer-readable storage medium may be included in the electronic device or may exist independently without being installed in the electronic device. The computer-readable storage medium carries one or more programs. When the one or more programs are executed by the electronic device, the electronic device: Using a target method to perform distortion correction on the target projection image; The target projection image is an image projected onto an irregular curved surface related to the vehicle.

[0139] Computer program code for performing the operations of some embodiments of the present application may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer via any type of network (including a local area network (LAN) or a wide area network (WAN)), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0140] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present application. In this regard, each box in the flowchart or block diagram may represent a module, a program segment, or a portion of a code, which contains one or more executable instructions for implementing a specified logical function.

[0141] It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures.

[0142] For example, two boxes shown in succession may actually be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of boxes in the block diagram and / or flow chart, can be implemented by a dedicated hardware-based system that performs the specified function or operation, or can be implemented by a combination of dedicated hardware and computer instructions.

[0143] The units described in some embodiments of the present application may be implemented by software or hardware, and the units described may also be arranged in a processor.

[0144] The functions described above in this article may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: Field Programmable Gate Array (FPGA), Application Specific Integrated Circuit (ASIC), Application Specific Standard Parts (ASSP), System on Chip (SOC), Complex Programmable Logic Device (CPLD), etc.

[0145] According to the sixth aspect of the present application, Figure 7 As shown, the embodiment of the present application further provides a vehicle 10, including the above-mentioned correction system 300 or electronic device or implementing the correction method described in any of the above-mentioned embodiments, and the electronic device can be used to perform the above-mentioned correction method. The vehicle 10 has all the beneficial effects of the above-mentioned electronic device, and the present application will not repeat them here.

[0146] The vehicle 10 may be a fuel vehicle, a plug-in hybrid vehicle, a new energy vehicle, etc., and this application does not make any specific limitation on this.

[0147] In the description of this application, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more features. In the description of this application, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0148] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0149] The embodiments, implementation methods and related technical features of the present application can be combined and replaced with each other without conflict.

[0150] The above are only preferred embodiments of the present application and do not constitute any form of limitation to the present application. However, any simple modifications, equivalent changes and modifications made to the above embodiments based on the technical essence of the present application without departing from the content of the technical solution of the present application are still within the scope of the technical solution of the present application.

Claims

1. A calibration method, characterized in that: Applied to a vehicle, the method comprises: Using a target method to perform distortion correction on the target projection image; The target projection image is an image projected onto an irregular curved surface associated with the vehicle.

2. The method according to claim 1, characterized in that The irregular curved surface includes the surface of the A-pillar of the vehicle.

3. The method according to claim 1 or 2, characterized in that: The target method includes one of a perspective transformation method, a pixel matching method, a camera calibration method, a distortion model algorithm, and a multi-view geometric image algorithm.

4. The method according to claim 1, characterized in that: Before using the target method to perform distortion correction on the target projection image, the method further includes: Determine the target method.

5. The method according to claim 4, characterized in that The method for determining the target comprises: Determining the target method according to the first camera image and the first projection image; Wherein, the first projection image is an image projected on the irregular curved surface; The first camera image is an image obtained by photographing the first projection image with a camera.

6. The method according to claim 5, characterized in that The camera is a human eye measurement camera installed on a vehicle.

7. The method according to claim 5, characterized in that The method of determining the target according to the first camera image and the first projection image includes: generating a target mapping table according to a center point in the first camera image and a calibration point in the first projection image; The target method is determined according to the target mapping table.

8. The method according to claim 7, characterized in that The generating a target mapping table according to the center point in the first camera image and the calibration point in the first projection image comprises: Obtaining first coordinates of a center point in the first camera image in a camera image coordinate system; Acquire a second coordinate of the calibration point in the first projection image in the projection image coordinate system; The target mapping table between the center point and the correction point is generated based on the first coordinate and the second coordinate.

9. The method according to claim 8, characterized in that Before obtaining the first coordinates of the center point in the first camera image in the camera image coordinate system, the method further includes: Image enhancement is performed on the first camera image to identify the center point.

10. The method according to claim 8, characterized in that The obtaining of the first coordinates of the center point in the first camera image in the camera image coordinate system includes: Acquire a detection point set based on the first camera image; determining the first coordinate using a clustering algorithm; wherein the detection point set is determined by identifying the dot matrix elements in the first camera image; The first coordinates are determined by performing cluster analysis on the detection point set.

11. The method according to claim 8, characterized in that The obtaining of the second coordinates of the calibration point in the first projection image in the projection image coordinate system includes: Based on the spatial relationship of the calibration points in the first projection image, second coordinates of the calibration points are determined.

12. The method according to any one of claims 8 to 11, characterized in that The generating the target mapping table between the center point and the correction point based on the first coordinate and the second coordinate includes: generating a first mapping table between the center point and the correction point based on a first mapping relationship between the first coordinate and the second coordinate; In a case where the number of the center points is less than or equal to the number of the correction points, determining repeated mapping points in the projection image coordinate system based on the first mapping table and the second coordinates; Determine, based on the repeated mapping points and the center points corresponding to the repeated mapping points, a second mapping table between the center points to be completed and the repeated mapping points; Generate the target mapping table based on the first mapping table and the second mapping table; The repeated mapping points include at least two correction points having a first mapping relationship with the same center point.

13. The method according to claim 12, characterized in that The determining, based on the repeated mapping points and the center points corresponding to the repeated mapping points, a second mapping table between the center points to be completed and the repeated mapping points comprises: Based on the first coordinates of the center point to be completed, use a convolution kernel to scan the first camera image to generate a third coordinate of the center point to be completed in the camera image coordinate system; Based on the second coordinate and the third coordinate, the second mapping table between the center point to be completed and the repeated mapping point is generated.

14. The method according to claim 12, characterized in that The determining, based on the repeated mapping points and the center points corresponding to the repeated mapping points, a second mapping table between the center points to be completed and the repeated mapping points comprises: Based on the first coordinate of the center point to be completed, shifting the first coordinate of the center point to be completed in a first direction by a predetermined pixel to generate a fourth coordinate of the center point to be completed in the camera image coordinate system; Based on the second coordinate and the fourth coordinate, the second mapping table between the center point to be completed and the repeated mapping point is generated.

15. The method according to claim 7, characterized in that The determining the target method according to the target mapping table comprises: Acquire the area coordinates of the projection area in the camera image coordinate system according to the target mapping table; Processing the region coordinates by at least two distortion correction methods to obtain at least two corrected camera images; Determining the target method based on at least two calibrated camera images; The projection area is an area on the irregular curved surface where the first projection image is displayed; and the target method is one of at least two distortion correction methods.

16. The method according to claim 15, characterized in that The step of processing the region coordinates by at least two distortion correction methods to obtain at least two corrected camera images includes: Based on the target mapping table and the projection area, at least two correction projection images are determined using at least two of the distortion correction methods, and at least two correction projection images are photographed using the camera to obtain at least two correction camera images.

17. The method according to claim 15, characterized in that The method of determining the target according to at least two calibrated camera images comprises: determining a degree of overlap between at least two of the calibrated camera images; The target method is determined according to the value of the overlap degree; wherein the overlap degree is determined according to the overlap area between at least two of the calibrated camera images.

18. A calibration system, applied to a vehicle, characterized in that: The system comprises: A vehicle-mounted projector for projecting a target projection image on an irregular curved surface associated with the vehicle; A distortion correction module, configured to perform distortion correction on the target projection image using the correction method according to any one of claims 1 to 17.

19. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the correction method according to any one of claims 1 to 17 is implemented.

20. A computer program product comprising a computer program or instructions, characterized in that When the computer program or instruction is executed by a processor, the correction method according to any one of claims 1 to 17 is implemented.

21. An electronic device, characterized in that: include: a memory having a computer program stored thereon; A processor, configured to execute the computer program in the memory to implement the correction method as claimed in any one of claims 1 to 17.

22. A vehicle, characterized in that: It comprises the correction system as claimed in claim 18, or comprises the electronic device as claimed in claim 21, or implements the correction method as claimed in any one of claims 1 to 17.

Images