LED lamp bead calibration method and apparatus, and device and medium

Abstract

Provided in the present application are an LED lamp bead calibration method and apparatus, and a device and a medium. In the method, a binocular stereoscopic vision calibration system is formed by means of a first calibration camera and a second calibration camera, thereby improving the calculation precision of three-dimensional coordinates of a target lamp bead in a camera coordinate system, reducing coordinate errors of the target lamp bead during coordinate conversion, reducing three-dimensional coordinate errors of the target lamp bead in the camera coordinate system, and thus improving the calibration accuracy of the relative position between the target lamp bead and an eye-tracking camera.

Description

LED lamp bead calibration method, device, equipment and medium

[0001] This application claims priority to the Chinese patent application filed with the China Patent Office on March 19, 2024, with application number 2024103165207, and invention name “LED lamp bead calibration method, device, equipment and medium”, the entire contents of which are incorporated by reference into this application. Technical Field

[0002] The present application relates to the field of machine vision calibration technology, and in particular to a method, device, equipment and medium for calibrating LED lamp beads. Background Art

[0003] Smart wearable devices (such as AR / VR glasses) can locate the user's visual center through eye tracking technology. This involves using an eye-tracking camera to capture the reflection point of an LED light source in the eye image. Based on the relative coordinates of the LED light source and the eye-tracking camera, an eyeball model is constructed. This eyeball model is then used to calculate the coordinates of the visual center in the eye image, enabling eye tracking of the visual center. Therefore, the accuracy of visual center eye tracking depends on the accuracy of the relative position calibration between the eye-tracking camera and the LED light source.

[0004] However, the LED light source calibration method in related art cannot directly determine the relative position of the eye tracking camera and the LED light source. Instead, the LED light source and the eye tracking camera must be calibrated separately to obtain their coordinates in the world coordinate system, thereby determining their relative position. This can lead to inaccurate LED light source calibration results, thereby reducing the accuracy of eye tracking results.

[0005] Therefore, how to improve the calibration accuracy of LED lamp beads in eye tracking systems has become a technical problem that needs to be solved urgently. Summary of the Invention

[0006] The present application provides an LED lamp bead calibration method, apparatus, device and storage medium, aiming to improve the accuracy of LED lamp bead calibration in an eye tracking system.

[0007] In a first aspect, the present application provides a method for calibrating an LED lamp bead, comprising:

[0008] Obtaining a first calibration parameter corresponding to the first calibration camera and a third calibration parameter of the eye-tracking camera;

[0009] Based on the lamp bead images of the target lamp bead captured by the first calibration camera and the second calibration camera respectively, obtaining first image coordinates corresponding to the first calibration camera and second image coordinates corresponding to the second calibration camera;

[0010] Calculate the first three-dimensional coordinates of the target lamp bead in the camera coordinate system corresponding to the first calibration camera based on the first image coordinates, the second image coordinates and the first calibration parameters;

[0011] Based on the third calibration parameter and the first calibration parameter, the first three-dimensional coordinate is converted into a camera coordinate system corresponding to the eye-tracking camera to obtain the target three-dimensional coordinate of the target lamp bead relative to the eye-tracking camera.

[0012] In a second aspect, the present application further provides an LED lamp bead calibration device, comprising:

[0013] A calibration parameter acquisition module, configured to acquire a first calibration parameter corresponding to the first calibration camera and a third calibration parameter of the eye-tracking camera;

[0014] An image coordinate acquisition module, configured to obtain first image coordinates corresponding to the first calibration camera and second image coordinates corresponding to the second calibration camera based on the lamp bead images of the target lamp bead captured by the first calibration camera and the second calibration camera respectively;

[0015] a three-dimensional coordinate calculation module, configured to calculate the first three-dimensional coordinates of the target lamp bead in the camera coordinate system corresponding to the first calibration camera based on the first image coordinates, the second image coordinates, and the first calibration parameters;

[0016] A three-dimensional coordinate conversion module is used to convert the first three-dimensional coordinate into the camera coordinate system corresponding to the eye-tracking camera based on the third calibration parameter and the first calibration parameter, so as to obtain the target three-dimensional coordinate of the target lamp bead relative to the eye-tracking camera.

[0017] 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 LED lamp bead calibration method as described above are implemented.

[0018] In a fourth aspect, the present application further 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 LED lamp bead calibration method as described above are implemented.

[0019] The present application provides a method, apparatus, device, and storage medium for calibrating LED lamp beads. The method includes obtaining a first calibration parameter corresponding to a first calibration camera and a third calibration parameter of an eye-tracking camera; based on the lamp bead images of the target lamp bead captured by the first calibration camera and the second calibration camera, respectively, obtaining the first image coordinates corresponding to the first calibration camera and the second image coordinates corresponding to the second calibration camera; based on the first image coordinates, the second image coordinates, and the first calibration parameter, calculating the first three-dimensional coordinates of the target lamp bead in the camera coordinate system corresponding to the first calibration camera; based on the third calibration parameter and the first calibration parameter, converting the first three-dimensional coordinates into the camera coordinate system corresponding to the eye-tracking camera to obtain the target three-dimensional coordinates of the target lamp bead relative to the eye-tracking camera. In the above manner, the present application captures the lamp bead images of the target lamp bead through the first calibration camera and the second calibration camera, and then calculates the first three-dimensional coordinates of the target lamp bead in the camera coordinate system of the first calibration camera based on the first image coordinates and the second image coordinates of the target lamp bead in the two lamp bead images, as well as the first calibration parameter of the first calibration camera. The binocular stereo vision calibration system composed of a first calibration camera and a second calibration camera can improve the calculation accuracy of the three-dimensional coordinates of the target lamp beads in the camera coordinate system, thereby reducing the coordinate error of the target lamp beads during coordinate conversion, so that the target three-dimensional coordinate error of the target lamp beads obtained by coordinate conversion according to the first calibration parameters and the second calibration parameters in the camera coordinate system corresponding to the eye-tracking camera is smaller, thereby improving the calibration accuracy of the relative position between the target lamp beads and the eye-tracking camera. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the description of the embodiments. 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 any creative work.

[0021] FIG1 is a flow chart of a first embodiment of a method for calibrating an LED lamp bead provided in an embodiment of the present application;

[0022] FIG2 is a flow chart of a second embodiment of a method for calibrating an LED lamp bead provided in an embodiment of the present application;

[0023] FIG3 is a flow chart of a third embodiment of a method for calibrating an LED lamp bead provided in an embodiment of the present application;

[0024] FIG4 is a structural diagram of a first embodiment of an LED lamp bead calibration device provided by the present application;

[0025] FIG5 is a schematic block diagram of the structure of a computer device provided in an embodiment of the present application.

[0026] The purpose, features and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0027] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0028] The flowcharts shown in the accompanying drawings are for illustrative purposes only and do not necessarily include all contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps may be decomposed, combined, or partially merged, so the actual execution order may vary depending on the actual situation.

[0029] The following describes some embodiments of the present application in detail with reference to the accompanying drawings. In the absence of conflict, the following embodiments and features therein may be combined with each other.

[0030] Please refer to Figure 1, which is a flow chart of a first embodiment of a method for calibrating an LED lamp bead provided in an embodiment of the present application.

[0031] As shown in FIG1 , the LED lamp bead calibration method includes steps S101 to S104 .

[0032] S101, obtaining a first calibration parameter corresponding to a first calibration camera and a third calibration parameter corresponding to an eye-tracking camera;

[0033] In one embodiment, a binocular stereo vision calibration system is composed of two identical cameras. The LED lamp beads embedded in the smart wearable device are calibrated by the binocular stereo vision calibration system. An eye-tracking camera is installed on each side of the smart wearable device, and a number of LED lamp beads are distributed around the eye-tracking camera. The shooting directions of the first calibration camera and the second calibration camera are both toward the smart wearable device, and the left and / or right eye-tracking cameras in the smart wearable device and the several LED lamp beads distributed around the eye-tracking cameras need to be located in the shooting field of view of the first calibration camera and the shooting field of view of the second calibration camera at the same time. The first calibration camera and the second calibration camera synchronously capture the lamp bead images of the LED lamp beads on the smart wearable device to ensure that the eye-tracking camera and the LED lamp beads are within the field of view of the stereo vision system formed by the first calibration camera and the second calibration camera.

[0034] In one embodiment, the camera has four coordinate systems, including a world coordinate system, a camera coordinate system, an image coordinate system, and a pixel coordinate system. The world coordinate system is converted to the camera coordinate system through a rigid body transformation (e.g., rotation or translation), the camera coordinate system is converted to the image coordinate system through perspective projection, and the image coordinate system is converted to the pixel coordinate system through an affine transformation.

[0035] It can be understood that most image transformations can use matrix multiplication and matrix addition to represent the mapping relationship between pixels before and after the transformation. Therefore, it is necessary to obtain camera calibration parameters when performing image transformation. The camera calibration parameters (first calibration parameters, second calibration parameters, and third calibration parameters) include camera internal parameters and camera external parameters.

[0036] The camera's internal parameters can include the physical dimensions dX and dY of a pixel, the focal length f, the distortion factor r of the image's physical coordinates, the vertical and horizontal offsets u and v (in pixels) of the image origin relative to the optical center imaging point, and the distortion coefficients. The distortion coefficients can include the camera's radial distortion coefficients K (K1, K2, K3) and tangential distortion coefficients P (P1, P2). The camera's external parameters can include the rotation matrix R and translation matrix T that transform the world coordinate system to the camera coordinate system.

[0037] Among them, the camera internal parameters include internal parameter matrix and distortion coefficient, etc., and the camera external parameters include rotation matrix and translation matrix, etc.

[0038] In one embodiment, the internal parameter matrix can be expressed as:

[0039] Where f is the focal length, dX and dY represent the physical lengths of a pixel on the camera plate in the X and Y directions, respectively, that is, the actual length and width of a pixel on the plate, u0 and v0 represent the X-axis and Y-axis coordinates of the center of the camera plate in the pixel coordinate system, and θ represents the angle between the horizontal and vertical edges of the camera plate (90° indicates no error).

[0040] In one embodiment, the external parameter matrix can be expressed as:

[0041] Where R represents the rotation matrix and T represents the translation matrix.

[0042] In one embodiment, the first calibration parameter corresponding to the first calibration camera, the second calibration parameter corresponding to the second calibration camera, and the third calibration parameter of the eye-tracking camera can be calibrated using a single-camera calibration method.

[0043] Furthermore, based on a single-camera calibration method, parameter calibration is performed on the first calibration camera, the second calibration camera, and the eye-tracking camera respectively to obtain the first calibration parameters, the second calibration parameters, and the third calibration parameters.

[0044] In one embodiment, single-camera calibration can obtain the camera's intrinsic parameter matrix and distortion coefficients. Single-camera calibration methods typically involve photographing a calibration plate of known size and calculating these parameters using algorithms such as the Zhang Zhengyou calibration method.

[0045] The calibration plate can be a checkerboard or a dot grid. The checkerboard is composed of alternating black and white squares and is suitable for focus detection; the dot grid is composed of a series of dots and is suitable for more accurate feature point positioning.

[0046] In one embodiment, when performing single-camera calibration, the camera to be calibrated (the first calibration camera, the second calibration camera, or the eye-tracking camera) is first used to photograph a calibration plate from different angles and positions to obtain several images of the calibration plate. Then, a computer algorithm or software (such as OpenCV, etc.) is used to identify and extract corner points or feature points on the calibration plate. Based on the corner points or feature points and known parameters in the calibration plate, the camera's internal parameter matrix and distortion coefficients are calculated. The internal parameter matrix may include parameter information such as focal length and principal point coordinates, while the distortion coefficients describe the distortion characteristics of the lens.

[0047] In one embodiment, the camera calibration process involves determining the camera's intrinsic and extrinsic parameters through the transformation of four coordinate systems. The world coordinate system describes the actual position of an object; the camera coordinate system describes the center of the camera lens; the image coordinate system describes the image sensor imaging center, the image center, and the center of the canvas, typically in millimeters; and the pixel coordinate system describes the position of pixels, measured in rows and columns.

[0048] In one embodiment, by converting from the world coordinate system to the camera coordinate system, the camera external parameters, i.e., the rotation matrix and the translation matrix, can be solved; by converting from the camera coordinate system to the image coordinate system, the camera internal parameters, i.e., the internal parameter matrix and the distortion coefficient, can be solved; by converting from the image coordinate system to the pixel coordinate system, the pixel conversion matrix can be solved, i.e., the origin is from the center of the picture to the upper left corner, and the unit is changed from millimeters to rows and columns.

[0049] S102: Based on the lamp bead images of the target lamp bead captured by the first calibration camera and the second calibration camera respectively, obtain first image coordinates corresponding to the first calibration camera and second image coordinates corresponding to the second calibration camera;

[0050] In one embodiment, the target lamp bead must appear in the capture images of both the first calibration camera and the second calibration camera. The first calibration camera and the second calibration camera each capture images of the target lamp bead. The first image coordinates are then obtained based on the coordinate position of the lamp bead image captured by the first calibration camera in the first image coordinate system corresponding to the first calibration camera. The second image coordinates are obtained based on the coordinate position of the lamp bead image captured by the second calibration camera in the second image coordinate system corresponding to the second calibration camera.

[0051] Furthermore, second calibration parameters corresponding to the second calibration camera are obtained; based on the first calibration parameters and the second calibration parameters, a first image coordinate system corresponding to the first calibration camera and a second image coordinate system corresponding to the second calibration camera are created respectively; based on the first lamp bead image of the target lamp bead captured by the first calibration camera, the first image coordinates of the target lamp bead in the first image coordinate system are determined; based on the second lamp bead image of the target lamp bead captured by the second calibration camera, the second image coordinates of the target lamp bead in the second image coordinate system are determined.

[0052] In one embodiment, a first image coordinate system is established, with the horizontal and vertical pixels of the image captured by the first calibration camera as the X-axis and Y-axis, respectively, and the origin being the first pixel in the upper left corner of the captured image. The image coordinates of the target lamp bead in the lamp bead image in the first image coordinate system, i.e., the first image coordinates, are then determined based on the lamp bead image captured by the first calibration camera.

[0053] Similarly, establish a second image coordinate system using the horizontal and vertical pixels of the image captured by the second calibration camera as the X-axis and Y-axis, respectively, with the origin being the first pixel in the upper left corner of the captured image. Then, based on the lamp bead image captured by the second calibration camera, determine the image coordinates of the target lamp bead in the lamp bead image in the second image coordinate system, i.e., the second image coordinates.

[0054] The first image coordinates and the second image coordinates are both pixel coordinates.

[0055] S103: Calculate the first three-dimensional coordinates of the target lamp bead in the camera coordinate system corresponding to the first calibration camera based on the first image coordinates, the second image coordinates, and the first calibration parameters;

[0056] In one embodiment, based on the first image coordinates and the second image coordinates, the image parallax of the target lamp bead in the two lamp bead images captured by the first calibration camera and the second calibration camera respectively can be calculated, that is, the X-axis coordinate difference between the first image coordinates and the second image coordinates.

[0057] In one embodiment, the depth distance between the target lamp bead and the first calibration camera can be further calculated based on the image parallax and camera calibration parameters, wherein the depth distance calculation formula of the target lamp bead can be expressed as: Z = f·B / d

[0058] Where Z represents the depth distance, f represents the focal length of the first calibration camera, B represents the baseline distance between the first calibration camera and the second calibration camera, that is, the actual straight-line distance between the first calibration camera and the second calibration camera, and d represents the image disparity. The focal lengths of the first calibration camera and the second calibration camera are equal.

[0059] S104. Based on the third calibration parameter and the first calibration parameter, convert the first three-dimensional coordinate into a camera coordinate system corresponding to the eye-tracking camera to obtain the target three-dimensional coordinate of the target lamp bead relative to the eye-tracking camera.

[0060] In one embodiment, the camera calibration parameters include camera intrinsic parameters and camera extrinsic parameters. According to the camera intrinsic parameters and camera extrinsic parameters, the conversion of various camera-related coordinate systems can be realized, that is, the mutual conversion between the world coordinate system, the camera coordinate system, the image coordinate system and the pixel coordinate system.

[0061] The world coordinate system is the absolute coordinate system of the objective three-dimensional world. Because the first calibration camera, the second calibration camera, and the eye-tracking camera are placed in three-dimensional space, a world coordinate system is required to describe the positions of these three cameras. This world coordinate system is also used to describe the position of any other objects placed in this three-dimensional environment, with their coordinate values ​​expressed as (X, Y, Z).

[0062] The camera coordinate system takes the optical center of the camera as the coordinate origin, the X axis and Y axis are parallel to the X axis and Y axis of the image coordinate system respectively, and the optical axis of the camera is the Z axis. c , Y c , Z c ) represents its coordinate value.

[0063] The image coordinate system uses the center of the image plane of the camera image sensor as its origin. The X-axis and Y-axis are parallel to the two perpendicular sides of the image plane, and their coordinate values ​​are represented by (x, y). The image coordinate system uses physical units (such as millimeters) to represent the position of pixels in the image.

[0064] The pixel coordinate system is based on the top-left corner of the camera image sensor's image plane as its origin. The x-axis and y-axis are parallel to the x-axis and y-axis of the image coordinate system, respectively. Its coordinate values ​​are represented by (u, v). The pixel coordinate system is measured in pixels (rows × columns).

[0065] In one embodiment, the conversion relationship between the pixel coordinate system and the image coordinate system is:

[0066] Using a homogeneous coordinate system, the above formula can be expressed in matrix form as follows:

[0067] Among them, u represents the X-axis coordinate in the pixel coordinate system, v represents the Y-axis coordinate in the pixel coordinate system, x represents the X-axis coordinate in the image coordinate system, y represents the Y-axis coordinate in the image coordinate system, dx represents the physical size of each pixel of the camera in the X-axis direction of the image plane, dy represents the physical size of each pixel of the camera in the Y-axis direction of the image plane, and (u0, v0) represents the coordinates of the origin of the image coordinate system in the pixel coordinate system.

[0068] In one embodiment, homogeneous coordinates represent an n-dimensional vector using an n+1-dimensional vector, and refer to a coordinate system used in projective geometry.

[0069] In one embodiment, the conversion relationship between the image coordinate system and the camera coordinate system is as follows:

[0070] Using a homogeneous coordinate system, the above formula can be expressed in matrix form as follows:

[0071] Among them, f is the focal length of the camera, (x, y) represents the two-dimensional coordinates of the point in the image coordinate system, (X c , Y c , Z c ) represents the three-dimensional point coordinates in the camera coordinate system.

[0072] In one embodiment, the conversion relationship between the camera coordinate system and the world coordinate system is as follows:

[0073] Among them, R is a 3×3 rotation matrix, t is a three-dimensional translation vector, T is a translation matrix, (X c , Y c , Z c ) represents the three-dimensional coordinates of the point in the camera coordinate system, and (X, Y, Z) represents the three-dimensional coordinates of the point in the world coordinate system.

[0074] In one embodiment, the first three-dimensional coordinates are the three-dimensional coordinates of a point in the camera coordinate system corresponding to the first calibration camera or the second calibration camera. Therefore, the first three-dimensional coordinates must first be converted to three-dimensional coordinates in the world coordinate system according to the coordinate conversion formula between the camera coordinate system and the world coordinate system, thereby obtaining the three-dimensional coordinates of the target lamp bead in the world coordinate system. Then, according to the coordinate conversion formula between the camera coordinate system and the world coordinate system, the three-dimensional coordinates of the target lamp bead in the world coordinate system are reversely converted to the camera coordinate system corresponding to the eye-tracking camera, thereby obtaining the target three-dimensional coordinates of the target lamp bead in the camera coordinate system corresponding to the eye-tracking camera, thereby completing the calibration of the relative position relationship between the target lamp bead and the eye-tracking camera.

[0075] The origin of the coordinate system of the camera corresponding to the eye-tracking camera is the location of the eye-tracking camera.

[0076] This embodiment provides an LED lamp bead calibration method. The method uses a first calibration camera and a second calibration camera to capture lamp bead images of a target lamp bead. The method then calculates the first three-dimensional coordinates of the target lamp bead in the camera coordinate system of the calibration cameras based on the first and second image coordinates of the target lamp bead in the two lamp bead images, as well as the camera calibration parameters of the two calibration cameras. The binocular stereo vision calibration system composed of the first and second calibration cameras can improve the accuracy of calculating the three-dimensional coordinates of the target lamp bead in the camera coordinate system, thereby reducing the coordinate error of the target lamp bead during coordinate conversion. This results in a smaller error in the target three-dimensional coordinates of the target lamp bead obtained through coordinate conversion in the camera coordinate system corresponding to the eye-tracking camera, thereby improving the calibration accuracy of the relative position between the target lamp bead and the eye-tracking camera.

[0077] Please refer to FIG. 2 , which is a flow chart of a second embodiment of a method for calibrating an LED lamp bead provided in an embodiment of the present application.

[0078] As shown in FIG2 , based on the embodiment shown in FIG1 , step S102 specifically includes:

[0079] S201, calculating the depth distance of the target lamp bead in the camera coordinate system corresponding to the first calibration camera based on the first image coordinates, the second image coordinates and the first calibration parameters;

[0080] In one embodiment, the image parallax of the target lamp bead in the two lamp bead images captured by the first calibration camera and the second calibration camera can be calculated based on the first image coordinates and the second image coordinates. Furthermore, based on the image parallax, the focal lengths of the first calibration camera and the second calibration camera, and the baseline distance, the depth distance of the target lamp bead in the camera coordinate system corresponding to the first calibration camera (or the second calibration camera) can be calculated, that is, the Z-axis coordinate of the target lamp bead in the camera coordinate system corresponding to the first calibration camera (or the second calibration camera).

[0081] Furthermore, based on the first image coordinates and the second image coordinates, the image parallax of the target lamp bead in the first lamp bead image and the second lamp bead image is calculated; the baseline distance between the first calibration camera and the second calibration camera is obtained; and based on the first calibration parameter, the image parallax and the baseline distance, the depth distance is calculated.

[0082] In one embodiment, a feature point matching algorithm within image processing technology is used to identify and match the feature points of the target lamp bead in the lamp bead images captured by the first calibration camera and the second calibration camera. The pixel coordinates of these feature points in the two lamp bead images captured by the first calibration camera and the second calibration camera generally differ, which is known as image parallax.

[0083] Image parallax refers to the horizontal position difference of the same object in the images captured by the left and right cameras.

[0084] For example, it is assumed that the image coordinates of the target lamp bead in the lamp bead image captured by the first calibration camera are p L , the image coordinates of the target lamp bead in the lamp bead image captured by the second calibration camera are p R Then, the calculation formula of image disparity can be expressed as: d=p L ·xp R ·x

[0085] Among them, p L x represents the X-axis coordinate of the target lamp bead in the lamp bead image captured by the first calibration camera, p R x represents the X-axis coordinate of the target lamp bead in the lamp bead image captured by the second calibration camera.

[0086] In one embodiment, after the image parallax is calculated, the depth coordinate of the target lamp bead, that is, the depth distance of the target lamp bead from the first calibration camera or the second calibration camera, can be calculated based on the camera calibration parameters of the first calibration camera and the second calibration camera.

[0087] The calculation formula of the depth distance of the target lamp bead can be expressed as: Z = f·B / d

[0088] Where Z represents the depth distance, f represents the focal length of the first calibration camera or the second calibration camera, B represents the baseline distance between the first calibration camera and the second calibration camera, that is, the actual straight-line distance between the first calibration camera and the second calibration camera, and d represents the image disparity.

[0089] S202: Determine the first three-dimensional coordinates of the target lamp bead in a first camera coordinate system corresponding to the first calibration camera based on the first image coordinates and the depth distance.

[0090] In one embodiment, according to the above-mentioned conversion relationship between the image coordinate system and the camera coordinate system, the first image coordinate of the target lamp bead in the image coordinate system corresponding to the first calibration camera can be converted to the camera coordinate system corresponding to the first calibration camera, thereby obtaining the X-axis and Y-axis coordinates of the target lamp bead in the camera coordinate system corresponding to the first calibration camera, and the depth distance is the Z-axis coordinate of the target lamp bead in the camera coordinate system corresponding to the first calibration camera. Thus, the first three-dimensional coordinate of the target lamp bead in the first camera coordinate system corresponding to the first calibration camera can be obtained.

[0091] Furthermore, based on the first calibration parameters, an internal parameter matrix corresponding to the first calibration camera is obtained; based on the internal parameter matrix, the first image coordinates are converted into a normalized coordinate system corresponding to the first calibration camera to obtain the normalized coordinates corresponding to the target lamp bead; based on the normalized coordinates and the depth distance, the first three-dimensional coordinates of the target lamp bead in the first camera coordinate system are calculated.

[0092] In one embodiment, the first calibration parameters include camera intrinsic parameters and camera extrinsic parameters of the first calibration camera, wherein the camera intrinsic parameters include a camera intrinsic parameter matrix and distortion coefficients. Therefore, the intrinsic parameter matrix corresponding to the first calibration camera can be obtained based on the first calibration parameters.

[0093] In one embodiment, a dedistortion algorithm and the inverse of the internal parameter matrix K may be used to convert the first image coordinates of the target lamp bead in the first image coordinate system into normalized coordinates of the camera coordinate system.

[0094] The normalized coordinate system refers to the conversion of points in the camera coordinate system into points in the normalized plane.

[0095] For example, it is assumed that the pixel coordinates of the target lamp bead in the lamp bead image captured by the first calibration camera are (x1, y1), the depth of the target lamp bead in the camera coordinate system of the first calibration camera is Z, and the intrinsic parameter matrix of the first camera is K1.

[0096] Among them, (f x ,f y ) is the focal length in the X-axis and Y-axis directions expressed in pixels, (c x ,c y ) are the X-axis and Y-axis coordinates of the center of the camera plate in the pixel coordinate system.

[0097] Convert the pixel coordinates to the coordinates in the normalized camera coordinate system:

[0098] Then, using the depth Z, the three-dimensional coordinates (X B ,Y B ,Z B ), where: X B =x′×DY B =y′×DZ B =D

[0099] In one embodiment, the first image coordinates and the second image coordinates are pixel coordinates in the lamp bead image. Therefore, the normalized coordinate system can be an image coordinate system, and the normalized coordinates of the target lamp bead can be obtained by converting the pixel coordinates of the target lamp bead into image coordinates, i.e., converting the pixel coordinates of the target lamp bead into image coordinates using the conversion formula between the pixel coordinate system and the image coordinate system to obtain the normalized coordinates. Then, according to the conversion formula between the image coordinate system and the camera coordinate system, the normalized coordinates are converted into the first camera coordinate system to obtain the X-axis and Y-axis coordinates of the target lamp bead in the first camera coordinate system. The depth distance is then used as the Z-axis coordinate to obtain the first three-dimensional coordinates of the target lamp bead in the first camera coordinate system.

[0100] In one embodiment, image distortion is caused by variations in lens manufacturing precision and assembly processes, which can introduce distortion and distort the original image. Lens distortion is categorized into two types: radial distortion and tangential distortion. The original image captured by the lens exhibits both of the two types of distortion described in the first section. To enable better subsequent image manipulation, a dedistortion process is required.

[0101] It can be understood that image dedistortion can adopt the dedistortion algorithm in the prior art, and its main process includes: converting the pixel coordinates into the camera coordinate system to obtain the camera coordinates, and then calculating the distortion amounts in the X-axis and Y-axis directions according to the distortion coefficients (K1, K2, K3, P1, P2), correcting the camera coordinates according to the distortion amounts, and converting the corrected camera coordinates into the pixel coordinate system to obtain the corrected pixel coordinates.

[0102] It can be understood that the first calibration camera and the second calibration camera form a binocular vision system to locate the target lamp bead. Therefore, the second calibration camera can also be used to calculate the three-dimensional coordinates of the target lamp bead.

[0103] Furthermore, based on the first image coordinates, the second image coordinates and the second calibration parameters, the first three-dimensional coordinates of the target lamp bead in the camera coordinate system corresponding to the second calibration camera are calculated; based on the third calibration parameters and the second calibration parameters, the first three-dimensional coordinates are converted into the camera coordinate system corresponding to the eye-tracking camera to obtain the target three-dimensional coordinates of the target lamp bead relative to the eye-tracking camera.

[0104] In one embodiment, because the first calibration camera and the second calibration camera constitute a binocular stereo vision system, the process of calculating the first three-dimensional coordinates of the target lamp bead in the first camera coordinate system through the first image coordinates and the depth distance is the same as the process of calculating the first three-dimensional coordinates of the target lamp bead in the second camera coordinate system through the second image coordinates and the depth distance. The only difference is the camera coordinate system used.

[0105] In one embodiment, according to the above-mentioned conversion relationship between the image coordinate system and the camera coordinate system, the second image coordinates of the target lamp bead in the image coordinate system corresponding to the second calibration camera can be converted to the camera coordinate system corresponding to the second calibration camera, thereby obtaining the X-axis and Y-axis coordinates of the target lamp bead in the camera coordinate system corresponding to the second calibration camera, and the depth distance is the Z-axis coordinate of the target lamp bead in the camera coordinate system corresponding to the second calibration camera. Thus, the first three-dimensional coordinates of the target lamp bead in the second camera coordinate system corresponding to the second calibration camera can be obtained.

[0106] In this embodiment, based on the first image coordinates and the second image coordinates, the image parallax of the target lamp bead in the two lamp bead images captured by the first calibration camera and the second calibration camera is calculated, and then the depth distance between the target lamp bead and the two calibration cameras is calculated based on the image parallax, the camera calibration parameters and the baseline distance between the two calibration cameras. The depth information of the target lamp bead is calculated through binocular vision, thereby improving the accuracy of the three-dimensional coordinate calculation of the target lamp bead.

[0107] Please refer to FIG3 , which is a flow chart of a third embodiment of a method for calibrating an LED lamp bead provided in an embodiment of the present application.

[0108] As shown in FIG3 , based on the embodiment shown in FIG2 , step S104 specifically includes:

[0109] S301, calculating a second rotation matrix and a second translation vector between the first calibration camera and the eye-tracking camera based on the first calibration parameter and the third calibration parameter;

[0110] In one embodiment, three-dimensional coordinates are converted into two-dimensional coordinates of the camera through rotation and translation transformations, where the rotation matrix and translation matrix are called the external calibration parameters of the camera, which describe the process of converting the world coordinate system into the camera coordinate system.

[0111] In one embodiment, the spatial relationship between the two cameras, ie, the relative position and relative posture, may be determined by binocular vision calibration.

[0112] For example, a binocular vision system is composed of a first calibration camera and an eye-tracking camera. The two cameras simultaneously capture multiple sets of images of the same scene (such as a checkerboard) from different angles, and use feature extraction and matching algorithms (such as SIFT, SURF, or ORB) to find corresponding points between the images. Based on these corresponding points, the second rotation matrix R between the first calibration camera and the eye-tracking camera is calculated. 13 and the second translation vector T 13 .

[0113] S302: Based on the second rotation matrix and the second translation vector, transform the first three-dimensional coordinates into a camera coordinate system corresponding to the eye-tracking camera to obtain the target three-dimensional coordinates.

[0114] In one embodiment, the three-dimensional coordinates of the target lamp bead in the camera coordinate system corresponding to the first calibration camera are converted to the camera coordinate system corresponding to the eye-tracking camera. The second rotation matrix R between the first calibration camera and the eye-tracking camera is required. 13 The inverse matrix of

[0115] Among them, the target three-dimensional coordinates of the target lamp bead in the eye-tracking camera = Point 1 is the first three-dimensional coordinate (X B ,Y B ,Z B ).

[0116] In one embodiment, three-dimensional coordinate transformation can also be performed through the world coordinate system, that is, the rotation matrix and translation matrix between the camera coordinate system of the first calibration camera and the world coordinate system, as well as the rotation matrix and translation matrix between the camera coordinate system of the eye-tracking camera and the world coordinate system, are determined through the first calibration parameters and the third calibration parameters, that is, the external calibration parameters of the first calibration camera and the external calibration parameters of the eye-tracking camera.

[0117] Furthermore, based on the third calibration parameter, a coordinate transformation matrix between the camera coordinate system corresponding to the eye-tracking camera and the world coordinate system is obtained; based on the coordinate transformation matrix, the global three-dimensional coordinates are transformed into the camera coordinate system corresponding to the eye-tracking camera to obtain the target three-dimensional coordinates.

[0118] In one embodiment, based on the external calibration parameters (rotation matrix and translation matrix), the first three-dimensional coordinates in the first camera coordinate system are converted to the world coordinate system through the above-mentioned conversion relationship between the camera coordinate system and the world coordinate system to obtain the global three-dimensional coordinates of the target lamp bead in the world coordinate system. Among them, the conversion relationship between the camera coordinate system and the world coordinate system is as follows:

[0119] Among them, R is a 3×3 rotation matrix, t is a three-dimensional translation vector, T is a translation matrix, (X c , Y c , Z c ) represents the three-dimensional coordinates of the point in the camera coordinate system, and (X, Y, Z) represents the three-dimensional coordinates of the point in the world coordinate system.

[0120] In one embodiment, the extrinsic calibration parameters of the eye-tracking camera are obtained based on the third calibration parameters, namely, the rotation matrix and translation matrix between the camera coordinate system and the world coordinate system of the eye-tracking camera. Furthermore, the coordinate transformation matrix between the camera coordinate system and the world coordinate system is obtained, namely, the transformation relationship between the camera coordinate system and the world coordinate system.

[0121] In one embodiment, the global three-dimensional coordinates of the target lamp bead in the world coordinate system are obtained, and the coordinate transformation matrix between the camera coordinate system of the eye-tracking camera and the world coordinate system is obtained. Then, the target three-dimensional coordinates of the target lamp bead in the camera coordinate system of the eye-tracking camera can be calculated based on the global three-dimensional coordinates and the coordinate transformation matrix.

[0122] In one embodiment, because the camera coordinate system of the eye-tracking camera uses the center of the optical axis of the eye-tracking camera as the coordinate origin, the target three-dimensional coordinates can be used to represent the relative position of the target lamp bead relative to the eye-tracking camera.

[0123] In this embodiment, the three-dimensional coordinates of the target lamp bead in the first calibration coordinate system are converted to the world coordinate system based on the first calibration parameters and the coordinate transformation matrix to obtain global three-dimensional coordinates. The coordinate transformation matrix between the eye-tracking camera's camera coordinate system and the world coordinate system is calculated using the eye-tracking camera's third calibration parameters. Subsequently, based on the coordinate transformation matrix, the global three-dimensional coordinates of the target lamp bead in the world coordinate system are converted to the eye-tracking camera's camera coordinate system. This allows the relative positional relationship between the target lamp bead and the eye-tracking camera to be calibrated in the eye-tracking camera's camera coordinate system. This avoids errors associated with solving the eye-tracking camera's point coordinates in the world coordinate system, thereby improving the calibration accuracy of the relative position between the eye-tracking camera and the target lamp bead.

[0124] Please refer to FIG4 , which is a structural diagram of a first embodiment of an LED lamp bead calibration device provided in the present application. The LED lamp bead calibration device is used to execute the aforementioned LED lamp bead calibration method.

[0125] As shown in FIG4 , the LED lamp bead calibration device 400 includes: a calibration parameter acquisition module 401 , an image coordinate acquisition module 402 , a three-dimensional coordinate calculation module 403 and a three-dimensional coordinate conversion module 404 .

[0126] The calibration parameter acquisition module 401 is used to acquire a first calibration parameter corresponding to the first calibration camera and a third calibration parameter of the eye-tracking camera;

[0127] An image coordinate obtaining module 402 is configured to obtain first image coordinates corresponding to the first calibration camera and second image coordinates corresponding to the second calibration camera based on the lamp bead images of the target lamp bead captured by the first calibration camera and the second calibration camera respectively;

[0128] A three-dimensional coordinate calculation module 403 is used to calculate the first three-dimensional coordinates of the target lamp bead in the camera coordinate system corresponding to the first calibration camera based on the first image coordinates, the second image coordinates and the first calibration parameters;

[0129] The three-dimensional coordinate conversion module 404 is used to convert the first three-dimensional coordinate into the camera coordinate system corresponding to the eye-tracking camera based on the third calibration parameter and the first calibration parameter, and obtain the target three-dimensional coordinate of the target lamp bead relative to the eye-tracking camera.

[0130] It should be noted that, those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described devices and modules can refer to the corresponding processes in the aforementioned LED lamp bead calibration method embodiment, and will not be repeated here.

[0131] The apparatus provided in the above embodiment may be implemented in the form of a computer program, and the computer program may be run on a computer device as shown in FIG5 .

[0132] Please refer to Figure 5, which is a schematic block diagram of the structure of a computer device provided in an embodiment of the present application. The computer device may be a server.

[0133] 5 , the computer device includes a processor, a memory, and a network interface connected via a system bus, wherein the memory may include a non-volatile storage medium and an internal memory.

[0134] The non-volatile storage medium can store an operating system and a computer program. The computer program includes program instructions that, when executed, enable the processor to perform any of the LED lamp bead calibration methods.

[0135] The processor is used to provide computing and control capabilities and support the operation of the entire computer equipment.

[0136] 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 LED lamp bead calibration method.

[0137] The network interface is used for network communication, such as sending assigned tasks, etc. Those skilled in the art will understand that the structure shown in FIG5 is merely a block diagram of a portion 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. A specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different arrangement of components.

[0138] It should be understood that the processor may be a central processing unit (CPU), or 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. The general-purpose processor may be a microprocessor or any conventional processor, etc.

[0139] A computer-readable storage medium is also provided in an embodiment of the present application. The computer-readable storage medium stores a computer program. The computer program includes program instructions. The processor executes the program instructions to implement any LED lamp bead calibration method provided in the embodiment of the present application.

[0140] The computer-readable storage medium may be an internal storage unit of the computer device described in the aforementioned 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 Media Card (SMC), a Secure Digital (SD) card, a Flash Card, etc., equipped on the computer device.

[0141] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in the present application, and such modifications or substitutions should be included in the scope of protection of the present application. Therefore, the scope of protection of the present application should be based on the scope of protection of the claims.

Claims

1. A method for calibrating an LED lamp bead, the method comprising: Obtaining a first calibration parameter corresponding to the first calibration camera and a third calibration parameter of the eye-tracking camera; Based on the lamp bead images of the target lamp bead captured by the first calibration camera and the second calibration camera respectively, obtaining first image coordinates corresponding to the first calibration camera and second image coordinates corresponding to the second calibration camera; Calculate the first three-dimensional coordinates of the target lamp bead in the camera coordinate system corresponding to the first calibration camera based on the first image coordinates, the second image coordinates and the first calibration parameters; Based on the third calibration parameter and the first calibration parameter, the first three-dimensional coordinate is converted into a camera coordinate system corresponding to the eye-tracking camera to obtain the target three-dimensional coordinate of the target lamp bead relative to the eye-tracking camera.

2. The LED lamp bead calibration method according to claim 1, wherein: The obtaining, based on the lamp bead images of the target lamp bead captured by the first calibration camera and the second calibration camera respectively, first image coordinates corresponding to the first calibration camera and second image coordinates corresponding to the second calibration camera includes: Obtaining second calibration parameters corresponding to the second calibration camera; Based on the first calibration parameters and the second calibration parameters, respectively create a first image coordinate system corresponding to the first calibration camera and a second image coordinate system corresponding to the second calibration camera; Determine, based on the first lamp bead image of the target lamp bead captured by the first calibration camera, the first image coordinates of the target lamp bead in the first image coordinate system; Based on the second lamp bead image of the target lamp bead captured by the second calibration camera, the second image coordinates of the target lamp bead in the second image coordinate system are determined.

3. The LED lamp bead calibration method according to claim 2, wherein: The creating, based on the first calibration parameters and the second calibration parameters, a first image coordinate system corresponding to the first calibration camera and a second image coordinate system corresponding to the second calibration camera, respectively, includes: Establishing the first image coordinate system with the horizontal and vertical pixels of the image captured by the first calibration camera as the X-axis and Y-axis respectively, and the origin being the position of the first pixel in the upper left corner of the captured image; The second image coordinate system is established with the horizontal pixel points and vertical pixel points of the image captured by the second calibration camera as the X-axis and Y-axis respectively, and the origin being the position of the first pixel point in the upper left corner of the captured image.

4. The LED lamp bead calibration method according to claim 2, wherein: Before obtaining the first calibration parameter corresponding to the first calibration camera and the third calibration parameter of the eye-tracking camera, the method further includes: Based on a single-camera calibration method, parameter calibration is performed on the first calibration camera, the second calibration camera, and the eye-tracking camera respectively to obtain the first calibration parameters, the second calibration parameters, and the third calibration parameters.

5. The LED lamp bead calibration method according to claim 1, wherein: The step of calculating the first three-dimensional coordinates of the target lamp bead in the camera coordinate system corresponding to the first calibration camera based on the first image coordinates, the second image coordinates, and the first calibration parameters includes: Calculating the depth distance of the target lamp bead in the camera coordinate system corresponding to the first calibration camera based on the first image coordinates, the second image coordinates and the first calibration parameters; Based on the first image coordinates and the depth distance, the first three-dimensional coordinates of the target lamp bead in the first camera coordinate system corresponding to the first calibration camera are determined.

6. The LED lamp bead calibration method according to claim 5, wherein: The calculating, based on the first image coordinates, the second image coordinates, and the first calibration parameters, the depth distance of the target lamp bead in the camera coordinate system corresponding to the first calibration camera includes: Calculating the image disparity of the target lamp bead in the first lamp bead image and the second lamp bead image based on the first image coordinates and the second image coordinates; Obtaining a baseline distance between the first calibration camera and the second calibration camera; The depth distance is calculated based on the first calibration parameter, the image disparity, and the baseline distance.

7. The LED lamp bead calibration method according to claim 6, wherein: The calculating, based on the first image coordinates and the second image coordinates, the image disparity of the target lamp bead in the first lamp bead image and the second lamp bead image includes: Based on the X-axis coordinate difference between the first image coordinate and the second image coordinate, the image parallax of the target lamp bead in the first lamp bead image and the second lamp bead image is obtained.

8. The LED lamp bead calibration method according to claim 6, wherein: The calculating the depth distance based on the first calibration parameter, the image disparity and the baseline distance includes: The depth distance calculation formula of the target lamp bead is expressed as: Z=f·B / d Where Z represents the depth distance, f represents the focal length of the first calibration camera or the second calibration camera, B represents the baseline distance between the first calibration camera and the second calibration camera, that is, the actual straight-line distance between the first calibration camera and the second calibration camera, and d represents the image disparity.

9. The LED lamp bead calibration method according to claim 5, wherein: The determining, based on the first image coordinates and the depth distance, the first three-dimensional coordinates of the target lamp bead in the first camera coordinate system corresponding to the first calibration camera includes: Based on the first calibration parameters, obtaining an internal parameter matrix corresponding to the first calibration camera; Based on the internal parameter matrix, the first image coordinates are converted into a normalized coordinate system corresponding to the first calibration camera to obtain the normalized coordinates corresponding to the target lamp bead; Based on the normalized coordinates and the depth distance, the first three-dimensional coordinates of the target lamp bead in the first camera coordinate system are calculated.

10. The LED lamp bead calibration method according to claim 9, wherein: The first image coordinates are converted into a normalized coordinate system corresponding to the first calibration camera based on the internal parameter matrix to obtain the normalized coordinates corresponding to the target lamp bead, including: Based on the dedistortion algorithm and the inverse of the internal parameter matrix K, the first image coordinates of the target lamp bead in the first image coordinate system are converted into normalized coordinates of the normalized camera coordinate system of the first calibration camera.

11. The LED lamp bead calibration method according to claim 9, wherein: The calculating, based on the normalized coordinates and the depth distance, the first three-dimensional coordinates of the target lamp bead in the first camera coordinate system includes: According to the conversion formula between the image coordinate system and the camera coordinate system, the normalized coordinates are converted to the first camera coordinate system to obtain the X-axis coordinate and Y-axis coordinate of the target lamp bead in the first camera coordinate system; The depth distance is used as the Z-axis coordinate of the target lamp bead in the first camera coordinate system; Based on the X-axis coordinate, Y-axis coordinate, and Z-axis coordinate of the target lamp bead in the first camera coordinate system, a first three-dimensional coordinate of the target lamp bead in the first camera coordinate system is obtained.

12. The LED lamp bead calibration method according to claim 1, wherein: The converting the first three-dimensional coordinates into a camera coordinate system corresponding to the eye-tracking camera based on the third calibration parameter and the first calibration parameter to obtain the target three-dimensional coordinates of the target lamp bead relative to the eye-tracking camera includes: Calculating a second rotation matrix and a second translation vector between the first calibration camera and the eye-tracking camera based on the first calibration parameter and the third calibration parameter; Based on the second rotation matrix and the second translation vector, the first three-dimensional coordinates are transformed into a camera coordinate system corresponding to the eye-tracking camera to obtain the target three-dimensional coordinates.

13. The LED lamp bead calibration method according to claim 1, wherein: The method further includes: converting the first three-dimensional coordinates into a camera coordinate system corresponding to an eye-tracking camera based on the third calibration parameter and the first calibration parameter to obtain the target three-dimensional coordinates of the target lamp bead relative to the eye-tracking camera. Based on the first calibration parameters, obtaining a rotation matrix and a translation matrix between a camera coordinate system and a world coordinate system corresponding to the first calibration camera; Based on the rotation matrix and translation matrix between the camera coordinate system corresponding to the first calibration camera and the world coordinate system, the first three-dimensional coordinates are converted to the world coordinate system to obtain the global three-dimensional coordinates of the target lamp bead in the world coordinate system; Based on the third calibration parameter, a coordinate transformation matrix between a camera coordinate system corresponding to the eye-tracking camera and a world coordinate system is obtained; Based on the coordinate conversion matrix between the camera coordinate system corresponding to the eye-tracking camera and the world coordinate system, the global three-dimensional coordinates are converted into the camera coordinate system corresponding to the eye-tracking camera to obtain the target three-dimensional coordinates.

14. The LED lamp bead calibration method according to claim 1, wherein: After obtaining the first image coordinates corresponding to the first calibration camera and the second image coordinates corresponding to the second calibration camera based on the lamp bead images of the target lamp bead respectively captured by the first calibration camera and the second calibration camera, the method further includes: Obtaining second calibration parameters corresponding to the second calibration camera; Calculate the first three-dimensional coordinates of the target lamp bead in the camera coordinate system corresponding to the second calibration camera based on the first image coordinates, the second image coordinates and the second calibration parameters; Based on the third calibration parameter and the second calibration parameter, the first three-dimensional coordinate is converted into a camera coordinate system corresponding to the eye-tracking camera to obtain the target three-dimensional coordinate of the target lamp bead relative to the eye-tracking camera.

15. The LED lamp bead calibration method according to claim 1, wherein: The first calibration parameters include camera intrinsic parameters and camera extrinsic parameters of the first calibration camera, and the camera intrinsic parameters include a camera intrinsic parameter matrix and a distortion coefficient.

16. The LED lamp bead calibration method according to claim 1, wherein: The focal lengths of the first calibration camera and the second calibration camera are equal.

17. The LED lamp bead calibration method according to claim 1, wherein: The first image coordinates and the second image coordinates are both pixel coordinates.

18. An LED lamp bead calibration device, comprising: A calibration parameter acquisition module, configured to acquire a first calibration parameter corresponding to the first calibration camera and a third calibration parameter of the eye-tracking camera; An image coordinate acquisition module, configured to obtain first image coordinates corresponding to the first calibration camera and second image coordinates corresponding to the second calibration camera based on the lamp bead images of the target lamp bead captured by the first calibration camera and the second calibration camera respectively; a three-dimensional coordinate calculation module, configured to calculate the first three-dimensional coordinates of the target lamp bead in the camera coordinate system corresponding to the first calibration camera based on the first image coordinates, the second image coordinates, and the first calibration parameters; A three-dimensional coordinate conversion module is used to convert the first three-dimensional coordinate into the camera coordinate system corresponding to the eye-tracking camera based on the third calibration parameter and the first calibration parameter, so as to obtain the target three-dimensional coordinate of the target lamp bead relative to the eye-tracking camera.

19. 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 LED lamp bead calibration method as described in any one of claims 1 to 7 are implemented.

20. A computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the steps of the LED lamp bead calibration method according to any one of claims 1 to 7 are implemented.

Images