A photoelectric three-coordinate measurement method and measurement system

Abstract

The present invention discloses a photoelectric three-coordinate measurement method. A lamp under test is placed on a support platform, and the spatial coordinates of the light's illumination center are determined through the following steps: S1: Three position imaging units are used to capture images from different directions, obtaining first, second, and third image information, respectively; the principal optical axes of the three position imaging units are not coplanar, and the measurement fields of at least two position imaging units cover the lamp under test; S2: A data transceiver control unit calculates and analyzes the three-dimensional coordinates of the light's illumination center in a world coordinate system based on the three image information. This method is applied to vehicle lighting performance testing. By rationally designing the three position imaging units and combining image recognition with deep learning algorithms, the method effectively obtains the three-dimensional coordinates of headlights. It features a simple structure, ease of operation, low measurement cost, and high measurement accuracy.

Description

Technical Field

[0001] The present invention relates to the field of photoelectric testing, and in particular to a photoelectric three-coordinate measurement method and a measurement system. Background Art

[0002] The quality of motor vehicle headlights is crucial for safe nighttime driving. The China New Car Program (C-NCAP) currently proposes a vehicle-level static indoor evaluation method for evaluating motor vehicle headlight performance. The C-NCAP Management Rules (2024 Edition) also describe the vehicle lighting performance test method. The vehicle is parked on a platform, typically a turntable, with an optical test screen located 25 meters from the vehicle's road zero line origin. First, a three-coordinate measuring machine is used to measure the spatial position of the vehicle body and the headlight illumination center to determine the relative position between the vehicle and the platform's rotation center. Lighting performance is then measured by masking the left and right headlights, obtaining the illuminance distribution on the optical test screen at a certain distance. Combined with the spatial position of the headlight illumination center, the data is synthesized and converted to obtain the spatial light intensity distribution centered on the headlight illumination center. Accurate positioning of the headlight illumination center is crucial.

[0003] There are two ways to locate the optical center of vehicle headlights. The first is manual measurement. Due to the special irregular shapes such as curved surfaces in the design of headlights, this measurement method mainly relies on human subjective judgment, with low measurement accuracy and efficiency, and poor operability. The second is measurement using a three-dimensional coordinate measuring machine. A three-dimensional coordinate measuring machine is an instrument that measures by taking points in three dimensions. It is mainly composed of a mechanical system (X, Y, Z axes, etc.), detection sensors, a control system, and a data processing system. The measurement principle is to coordinate the motion of the detection sensor with the mechanical system's measurement space axis to obtain the spatial point position of the unit to be measured. Through a series of mathematical calculations, the spatial coordinates (x, y, z) of the measured point to be measured are obtained. This measurement method has high measurement accuracy, but the instrument is expensive. Summary of the Invention

[0004] In response to the shortcomings of the existing technology, the present invention provides a photoelectric three-coordinate measurement method and measurement system, which are applied to the whole vehicle lighting performance test. By rationally designing three position imaging units and combining image recognition and deep learning algorithms, the three-dimensional position coordinates of the headlights in the world coordinate system are effectively calculated. The method has a simple structure, easy operation, low measurement cost and high measurement accuracy.

[0005] The present invention discloses a photoelectric three-coordinate measurement method. A lamp to be measured is placed on a carrier platform. An optical test screen is provided in front of the lamp to receive a light beam emitted by the lamp. A light radiation imaging unit is used to measure the light spot image of the optical test screen. The spatial position coordinates of the brightness center of the lamp to be measured are determined by the following steps:

[0006] S1: Use a first position imaging unit, a second position imaging unit, and a third position imaging unit to respectively shoot from different directions to obtain first image information, second image information, and third image information, respectively; the principal optical axes of the three position imaging units are not coplanar, and the measurement fields of at least two of the three position imaging units cover the lamp under test, and the measurement field of the first position imaging unit generally covers the carrier platform and / or the lamp under test;

[0007] S2: The data transceiver control unit calculates and analyzes the three-dimensional position coordinates of the brightness center of the measured light in the world coordinate system based on the three image information.

[0008] The data transceiver control unit of the present invention processes the image information obtained by the three position imaging units, and obtains the three-dimensional position coordinates of the brightness center of the measured light in the world coordinate system by calculation, wherein the three-dimensional position coordinates include height, longitudinal and lateral coordinates. It should be noted that, generally, the world coordinate system takes a certain point on the support platform as the coordinate origin, the direction perpendicular to the optical test screen through this position point is the x-axis direction (i.e., the longitudinal axis of the world coordinate system), the direction perpendicular to the x-axis in the horizontal plane is the y-axis direction (i.e., the lateral axis of the world coordinate system), and the vertical direction is the z-axis direction (corresponding to height). In the light distribution test of the lamp, the light beam emitted by the measured lamp is irradiated onto the optical test screen to form a light spot, and the light spot on the optical test screen is photographed using the light radiation imaging unit, thereby obtaining the spatial light distribution information of the measured lamp.

[0009] In the above technical solution, the first position imaging unit can be specifically placed above the lamp to be measured, and the measurement field of view of the first position imaging unit covers the supporting platform. According to the first image information obtained by the first position imaging unit, the horizontal plane position information of the brightness center of the lamp to be measured relative to the supporting platform is calculated by image recognition; the second position imaging unit and the third position imaging unit are placed in front of the two sides of the lamp to be measured, and the measurement fields of the second position imaging unit and the third position imaging unit both cover the lamp to be measured. According to the second image information and the third image information obtained by the second position imaging unit and the third position imaging unit, the vertical plane position information of the brightness center of the lamp to be measured relative to the supporting platform is calculated.

[0010] Furthermore, the above technical solution can be used to measure the three-dimensional position coordinates of vehicle headlights. The lamp under test is installed on a vehicle, which is then parked on a platform. In step S1, a first position imaging unit is positioned above the platform, with its measurement field covering the platform. Second and third position imaging units are positioned on either side of the platform, with their measurement fields covering the lamp under test, capturing images of the vehicle from two sides. It should be noted that the first position imaging unit can be positioned above the platform, while the second and third position imaging units can be positioned on either side of the platform, either side, or one high and one low. The specific positions of the three position imaging units can be designed based on actual needs, such as vehicle size, the parameters of the position imaging units, and the installation location of the vehicle headlights. The position imaging units can be cameras or cameras. This positioning design, combined with an image recognition algorithm, effectively obtains the three-dimensional position coordinates of the lamp under test in the world coordinate system, providing convenient operation and high measurement accuracy. During vehicle lighting performance testing, the optical test screen is typically positioned 10m or 25m from the platform.

[0011] Furthermore, the support platform can rotate about the horizontal and / or vertical axis, and the rotation of the support platform is adjusted based on the feedback of the spot image obtained by the optical radiation imaging unit at different rotation angles, and the position of the optical center of the light under test is further determined using the above steps S1 and S2. In the above technical solution, the rotation center of the support platform is generally used as the coordinate origin of the world coordinate system. The light spot image of the optical test screen is measured using the optical radiation imaging unit arranged facing the optical measurement screen. The data transceiver control unit analyzes the spot image to obtain the spot center position, and then uses feedback to adjust the rotation of the support platform to correct the direction of the light axis of the light under test so that the light axis of the light under test is parallel to or coincides with the longitudinal axis of the world coordinate system.

[0012] In the above technical solution, a cross laser can be used to aim at the photometric center of the lamp under test, or a label can be used to mark the photometric center of the lamp under test, so as to quickly find the pixel position corresponding to the photometric center in the images captured by the first position imaging unit, the second position imaging unit, and the third position imaging unit.

[0013] Furthermore, an illumination light source may be used to illuminate the lamp under test, and image recognition may be used to extract the lamp outline information to obtain the photometric center position.

[0014] In the above technical solution, the coordinate conversion relationship between the world coordinate system with the rotation center of the support platform as the coordinate origin and the coordinate system of the measured light with the brightness center of the measured light as the coordinate origin can be calculated based on the three-dimensional coordinates of the brightness center of the measured light in the world coordinate system. Specifically, coordinate rotation transformation and translation transformation can be performed to obtain the conversion transformation matrix. Combined with the image information obtained by the light radiation imaging unit, the spatial light distribution information with the brightness center of the measured light as the origin can be further calculated.

[0015] Furthermore, the first image information captured by the first position imaging unit can be used to extract the vehicle contour information by image recognition to obtain the deflection information of the vehicle center line relative to the longitudinal axis of the world coordinate system; the distance of the vehicle feature point (such as a reflector) relative to the origin of the world coordinate system can also be obtained based on the extracted vehicle contour information, and the longitudinal coordinates of the photometric center position can be further obtained based on the known vehicle installation parameters. Specifically, the first position imaging unit is arranged above the vehicle, and the measurement field of view covers the vehicle. Preferably, the first position imaging unit is arranged directly above the rotation center of the support platform to simplify the calculation steps and facilitate the calculation.

[0016] Furthermore, the support platform can rotate around the vertical axis, and the rotation of the support platform is fed back according to the vehicle centerline angle information obtained from the first image information, so that the vehicle centerline is parallel to or coincides with the longitudinal axis of the world coordinate system, which facilitates the calculation of the spatial light distribution information of the measured lamp.

[0017] Furthermore, the three position imaging units are calibrated separately using measurement markers, including: the spatial position coordinates of the measurement markers in the world coordinate system are known, and based on the images captured by each position imaging unit, the coordinates of the measurement markers with known spatial coordinates in the world coordinate system correspond to a pixel point or pixel area with known pixel coordinates in the image captured by the first position imaging unit, / the second position imaging unit, and / or the third position imaging unit, a mapping relationship is established between the three-dimensional spatial coordinates in the world coordinate system and the pixel coordinates of the position imaging unit. When the lamp to be measured is a headlamp on a complete vehicle, the calibration step can be completed before the vehicle is parked on the support platform. When the vehicle is not in the vehicle, the position imaging unit can clearly capture the measurement markers. However, when the vehicle is parked on the support platform, the measurement markers may be obscured or removed.

[0018] The coordinates of the above measurement marks in the world coordinate system can be expressed as (x n ,y n ,z n), where n is a positive integer greater than 0. In actual vehicle lighting performance measurement, the world coordinate system is generally established with the rotation center of the carrier as the coordinate origin. The coordinates of the measurement mark with known spatial coordinates in the world coordinate system correspond to a pixel point or pixel area with known pixel coordinate position in the picture taken by the three position imaging units. In a specific embodiment, according to the coordinate data of each measurement mark in the world coordinate system, some 2D-3D matching algorithms are used to solve the mapping relationship between the pixel coordinate system and the world coordinate system to obtain the conversion relationship between the pixel coordinate systems of the three position imaging units and the world coordinate system. The 2D-3D matching algorithm includes but is not limited to the PNP (Perspective-n-Point) algorithm, the straight line linear transformation algorithm (DLT), the nonlinear optimization algorithm (BA), etc.

[0019] In the above technical solution, taking the relative positional relationship between the first position imaging unit and the supporting platform as an example, when the first position imaging unit is placed directly above the supporting platform, that is, in the specific case where the inclination angle of the first position imaging unit relative to the XY plane of the world coordinate system is 0, the mapping relationship between the three-dimensional coordinates in the world coordinate system and the pixel coordinates of the first position imaging unit is as follows:

[0020]

[0021]

[0022] Wherein, u and v are the coordinates of a pixel point in the image captured by the first position imaging unit, x and y are the coordinates of u and v mapped to the XY plane of the world coordinate system; a and b are the actual distances corresponding to a single pixel in the x and y directions, respectively, which are obtained by calibrating the measurement markers with known spatial position coordinates; c and d are the translation parameters between the receiving point A of the first position imaging unit and the origin O of the world coordinate system on the XY plane.

[0023] When the first position imaging unit is placed obliquely above the carrier, that is, the inclination angle of the first position imaging unit relative to the world coordinate system XY plane is not 0, for a certain point on the carrier (when z is not 0), take xu conversion as an example, Figure 1 As shown, O is the origin of the world coordinate system, θ is the tilt angle of the first position imaging unit relative to the XY plane of the world coordinate system, (x, 0, z) is a point on the support platform, the Y axis is perpendicular to the paper and points outward, A is the receiving point of the first position imaging unit, B is the origin of the pixel coordinate system, and (u, 0) is the corresponding point of the (x, 0, z) coordinate point in the pixel coordinate system. When the translation parameters c and d are 0, we can get:

[0024]

[0025]

[0026]

[0027]

[0028] Among them, z is the height of a certain point on the support platform. For the headlight brightness center, this parameter can be obtained by the second position imaging unit and / or the third position imaging unit; h is the height of the receiving point A of the first position imaging unit, that is, the distance of the receiving point A of the first position imaging unit in the Z-axis direction in the world coordinate system; (x2,0,0) is the intersection of the line connecting the coordinate point (x,0,z) and the receiving point A of the first position imaging unit on the XY plane of the world coordinate system, and h1 is the intersection of the coordinate point (x,0,z) and the line connecting the receiving point A of the first position imaging unit with the Z-axis.

[0029] It should be noted that some vehicles currently on the market, to optimize performance or aesthetics, have recessed headlights. This obscures the luminous center of the vehicle's headlights, making it impossible to directly determine the luminous center's position from above. With this headlight design, the first imaging unit can be placed diagonally above the platform to capture images containing the headlight under test. Furthermore, the image information captured by the three imaging units is combined to calculate and analyze the three-dimensional coordinates of the headlight's luminous center in the world coordinate system. Alternatively, by placing the first imaging unit directly above the platform, the vehicle's contour can be extracted based on the captured first image information, determining the relative position of the vehicle and the platform. Combined with the manufacturer's headlight installation parameters, the horizontal position of the headlight's luminous center relative to the platform can be calculated. Furthermore, the vehicle's centerline can be analyzed to determine the deflection angle relative to the longitudinal axis of the world coordinate system. The platform can then be rotated so that the vehicle's centerline is parallel to or coincides with the longitudinal axis of the world coordinate system, facilitating the calculation of the headlight's light distribution information.

[0030] Furthermore, the measurement markers are structured light stripes. Specifically, this is achieved by placing a vertically positioned diffuser at a designated location on the support platform and illuminating the diffuser with a structured light generator to form structured light stripes. The spatial coordinates of the characteristic points of the structured light stripes are known. The structured light stripes, with known spatial coordinates, can be used to calibrate the position imaging unit in advance, establishing a mapping relationship between the three-dimensional spatial coordinates of the world coordinate system and the pixel coordinates of the position imaging unit. Furthermore, the known phase information of the structured light stripes can provide more accurate feature information for binocular vision matching.

[0031] Furthermore, in step S2, the height coordinate and initial lateral coordinate of the brightness center of the measured light are obtained according to the second image information and the third image information; the longitudinal coordinate of the brightness center of the measured light is further calculated according to the first image information and the lateral coordinate is corrected.

[0032] In the above technical solution, the second and third image information are used to obtain the initial values ​​of the height coordinates and lateral coordinates of the brightness center of the measured light, primarily based on the principle of binocular stereo vision measurement. Two different images of the same scene are acquired by two positional imaging units at different locations. The positional deviation between image pixels is calculated using the principle of triangulation to infer depth information in a three-dimensional world coordinate system. The main steps include imaging calibration, stereo correction, stereo matching, and depth calculation. It should be noted that when the measured light is a headlamp installed on a vehicle, the second and third position imaging units can undoubtedly be used to obtain the height information of the brightness center of the measured light, based on the positional relationship between the second and third position imaging units and the vehicle. However, the second and third position imaging units are relatively weak in recognizing the lateral coordinates of the brightness center of the measured light, with the longitudinal coordinates being the worst. Therefore, in the present invention, the first position imaging unit, positioned above the support platform, is used to correct the initial values ​​of the lateral coordinates acquired by the second and third position imaging units to further improve measurement accuracy.

[0033] In another technical solution, three position imaging units at different positions can be used to respectively obtain images of the brightness center of the measured light at different viewing angles, and an image recognition algorithm can be used to identify and extract the brightness center of the measured light, and obtain the pixel coordinates of the brightness center of the measured light. The spatial position coordinates of the three position imaging units can be combined to fit the brightness center of the measured light obtained at different shooting angles, and the data transceiver control unit can be used to convert the pixel coordinates of the brightness center of the measured light in the shooting field of view of the three position imaging units into spatial three-dimensional coordinates in the world coordinate system based on a three-dimensional reconstruction algorithm.

[0034] Furthermore, the method also includes deep learning of the photometric center positions of different types of measured lamps, facilitating the rapid and accurate identification of the photometric center positions in the first, second, and third image information captured by the first, second, and third position imaging units. Specifically, a neural network model can be constructed, including but not limited to a ResNet residual neural network; the first, second, and third image information, which have been labeled with the photometric center, are used as samples for training; and deep learning is used to train and record samples of the photometric center positions of different types of measured lamps for rapid identification of the photometric centers of similar types of measured lamps.

[0035] Furthermore, based on the image information captured by the three position imaging units, the first image information, the second image information, and the third image information are used as inputs of the neural network, and the image information is recognized using the trained deep learning neural network model to obtain the approximate position of the brightness center of the multi-lamp system. Then, the specific spatial position information of the brightness center of the measured light relative to the support platform is calculated in combination with the image recognition algorithm.

[0036] The present invention also discloses a photoelectric three-coordinate measurement system, comprising a supporting platform for placing a lamp to be measured, an optical test screen, a first position imaging unit, a second position imaging unit, a third position imaging unit, a light radiation imaging unit, and a data transceiver control unit; the optical test screen is arranged in front of the lamp to be measured, and the light beam emitted by the lamp to be measured is irradiated onto the optical test screen, and the light radiation imaging unit is aligned with the optical measurement screen; the three position imaging units are arranged in space so that their main optical axes are not coplanar, and the measurement fields of at least two of the three position imaging units cover the lamp to be measured; the three position imaging units and the light radiation imaging unit are respectively connected to the data transceiver control unit for communication. Generally, the first position imaging unit is placed above the lamp to be measured, and its measurement field of view covers the lamp to be measured and / or the supporting platform; the second position imaging unit and the third position imaging unit are respectively placed in front of the two sides of the lamp to be measured, and the measurement fields of the second position imaging unit and the third position imaging unit cover the lamp to be measured.

[0037] Furthermore, the support platform includes a rotating device that rotates the support platform horizontally and / or vertically. By mounting the lamp under test on a rotatable and controllable support platform, spatial light distribution information of the lamp under test and the three-dimensional position coordinates of the center of illumination of the lamp under test can be conveniently and quickly obtained. The optical radiation imaging unit can be used to measure the spatial light distribution information of the lamp under test, or to calibrate the optical axis direction of the lamp under test. The rotation of the support platform is adjusted based on the feedback of the light spot image information obtained by the optical radiation imaging unit, and the optical axis direction of the lamp under test is corrected so that the optical axis of the lamp under test is parallel to or coincides with the longitudinal axis of the world coordinate system.

[0038] Furthermore, the supporting platform is also provided with a number of measurement marks with known spatial coordinates, and all or part of the measurement marks are within the measurement field of view of the three position imaging units to facilitate the calibration of the mapping relationship between the pixel coordinate system of the three position imaging units and the world coordinate system.

[0039] Furthermore, the lamp under test is a headlamp installed on a vehicle, and the supporting platform is used to park the vehicle.

[0040] Furthermore, the first position imaging unit is positioned above the lamp under test; the second and third position imaging units are positioned on either side of the optical test screen, respectively, without obstructing the measurement area on the optical test screen. In one specific embodiment, when the lamp under test is a vehicle headlamp, the first position imaging unit is positioned diagonally above the vehicle's front, and its measurement field of view can cover part or all of the support platform and the vehicle's headlamp; the second and third position imaging units are positioned on either side of the optical test screen, respectively, without obstructing the measurement area on the optical test screen, and their measurement fields of view can cover the front of the vehicle and the vehicle's headlamp. Alternatively, the first position imaging unit can be positioned diagonally below the vehicle's front, with its measurement field of view covering the vehicle's headlamp; the second and third position imaging units are positioned on either side of the optical test screen, respectively, without obstructing the measurement area on the optical test screen, and their measurement fields of view covering the front of the vehicle and the vehicle's headlamp. Through the above position design, combined with an image recognition algorithm, the three-dimensional position coordinates of the headlamp in the world coordinate system can be effectively obtained, with convenient operation and high measurement accuracy.

[0041] Furthermore, the system further includes one or more illumination light sources, which serve as illumination in the above-mentioned system. In a specific embodiment, when the lamp under test is a vehicle headlamp, the test is generally conducted in a darkroom environment, and an illumination light source is required to illuminate the headlamp. The illumination light source can be set diagonally below the headlamp, with the illumination direction covering the headlamp under test. Preferably, the setting position of the illumination light source does not block the shooting field of view of the first position imaging unit, the second position imaging unit, and the third position imaging unit for the lamp under test.

[0042] Furthermore, it also includes a cross laser for locating the photometric center of the lamp under test. In one specific embodiment, when the lamp under test is a vehicle headlamp, two cross lasers are provided, each emitting a cross laser line aimed at the left and right headlamps to locate the photometric center of the headlamp, thereby facilitating rapid identification of corresponding pixel locations in the images captured by the first, second, and third position imaging units. Furthermore, the cross laser and illumination light source can be designed side by side, with the illumination light source used to illuminate the lamp under test and the cross laser used to locate the photometric center of the lamp under test.

[0043] Beneficial effects of the invention: The patent of the present invention provides a three-coordinate measurement method and measurement system. By rationally designing three position imaging units and combining image recognition algorithms to analyze image information, the three-dimensional position coordinates of the headlamp brightness center in the world coordinate system are obtained, replacing the mechanical three-coordinate measuring instrument. It is easy to operate, low cost and accurate in measurement. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1This is a diagram showing the mapping principle between the world coordinate system and the pixel coordinate system of the present invention;

[0045] Figure 2 A schematic structural diagram of an optical electronic three-coordinate measurement system provided in Example 1 of the present invention;

[0046] Figure 3 and Figure 4 Schematic diagram of the positional relationship between the world coordinate system and the pixel coordinate system in the first embodiment of the present invention;

[0047] Figure 5 This is a schematic diagram of structured light stripe calibration provided in Example 1 of the present invention;

[0048] Figure 6 A schematic diagram of the structure of an optical electronic three-coordinate measurement system provided in the second embodiment of the present invention;

[0049] Figure 7 A schematic diagram of the structure of an optical electronic three-coordinate measurement system provided in the third embodiment of the present invention;

[0050] Figure 8 and Figure 9 Schematic diagram of the positional relationship between the world coordinate system and the pixel coordinate system in the third embodiment of the present invention;

[0051] Figure 10 Schematic diagram of the binocular camera imaging model in Example 3 of the present invention;

[0052] In the figure: 1-carrying platform, 2-first position imaging unit, 3-optical test screen, 4-second position imaging unit, 5-third position imaging unit, 6-measurement mark, 7-illumination light source, 8-cross laser, 9-diffuser plate, 10-structured light generator, 11-light radiation imaging unit. DETAILED DESCRIPTION

[0053] Example 1:

[0054] This embodiment provides a photoelectric three-coordinate measurement system, such as Figure 2As shown, the system includes a platform 1 for parking a vehicle, an optical test screen 3, a first position imaging unit 2, a second position imaging unit 4, a third position imaging unit 5, a cross laser 8, a light radiation imaging unit 11, and a data transceiver control unit. The platform 1 includes a rotating device that allows the platform 1 to rotate horizontally and / or vertically. Several measurement marks 6 with known spatial coordinates are provided on the platform 1. The optical test screen 3 is positioned in front of the vehicle's headlights, with the headlights emitting a light beam that strikes the optical test screen 3. The light radiation imaging unit 11 is aligned with the optical test screen 3. The first position imaging unit 2, the second position imaging unit 4, and the third position imaging unit 5 are spatially arranged so that their principal optical axes are not coplanar, and the measurement fields of all three imaging units cover the lamp under test. The first position imaging unit 2, the second position imaging unit 4, the third position imaging unit 5, and the light radiation imaging unit 11 are each communicatively connected to the data transceiver control unit.

[0055] Specifically, the first position imaging unit 2 is positioned diagonally above the front of the vehicle, with its measurement field of view covering the support platform 1 and the vehicle's headlights. The second position imaging unit 4 and the third position imaging unit 5 are positioned on the left and right sides of the optical test screen 3, respectively, without obstructing the measurement area on the optical test screen. Their measurement fields cover the front of the vehicle and the headlights. Two cross lasers 8 are positioned below the second position imaging unit 4 and the third position imaging unit 5, respectively, and are used to project cross laser lines onto the vehicle's headlights to calibrate the headlight intensity center. During measurement, the optical test screen is generally positioned 25 meters from the support platform. The world coordinate system is established with the support platform's rotation center as the coordinate origin. The direction perpendicular to the optical test screen through the rotation center is the x-axis direction, the direction perpendicular to the x-axis in the horizontal plane is the y-axis direction, and the vertical direction is the z-axis direction.

[0056] In one specific embodiment, the measurement markers 6 are several circular target disks, whose coordinates in the world coordinate system correspond to a pixel point or pixel area with a known pixel coordinate position in the image captured by the first position imaging unit, / the second position imaging unit, and / or the third position imaging unit. In this specific embodiment, based on the coordinate data of each measurement marker in the world coordinate system, a mapping relationship between the pixel coordinate system and the world coordinate system is solved using a 2D-3D matching algorithm to obtain the conversion relationship between the pixel coordinate systems of the three position imaging units and the world coordinate system. Subsequently, the first position imaging unit 2, the second position imaging unit 4, and the third position imaging unit 5 each capture and acquire vehicle images, and the data transceiver control unit analyzes the vehicle image information to obtain the three-dimensional position coordinates of the vehicle headlight illumination center in the world coordinate system.

[0057] This embodiment also provides a photoelectric three-coordinate measurement method, using the above-mentioned photoelectric three-coordinate measurement system, such as Figure 3 and Figure 4 As shown, a vehicle is parked on a supporting platform 1 that can rotate about a horizontal axis and / or a vertical axis. An optical test screen 3 for receiving headlamp light is set in front of the vehicle. A light radiation imaging unit 11 is used to measure the light spot image of the optical test screen 3. The spatial three-dimensional position coordinates of the headlamp illumination center are determined by the following steps:

[0058] A1: Use the first position imaging unit 2, which is located diagonally above the platform 1 and has a field of view covering the headlight, to photograph the vehicle from above to obtain first image information. Use the second position imaging unit 4 and the third position imaging unit 5, which are located in front of the platform 1 and have a field of view covering the headlight, to photograph the vehicle from the side from two directions to obtain second image information and third image information, respectively.

[0059] A2: The data transceiver control unit calculates and analyzes the three-dimensional position coordinates of the vehicle headlight illumination center in the world coordinate system based on the first image information, the second image information and the third image information, wherein the three-dimensional position coordinates include height, longitudinal and lateral coordinates.

[0060] It should be noted that, in this embodiment, the optical test screen 3 is set at a position 25m away from the supporting platform. The world coordinate system takes a certain point on the supporting platform 1 as the coordinate origin. The direction perpendicular to the optical test screen 3 through this position point is the x-axis direction, the direction perpendicular to the x-axis in the horizontal plane is the y-axis direction, and the vertical direction is the z-axis direction.

[0061] In the above technical solution, the horizontal position information of the brightness center of the light being measured relative to the supporting platform can be calculated based on the first image information obtained by the first position imaging unit 2 through image recognition. The vertical position information of the brightness center of the light being measured relative to the supporting platform can be calculated based on the second and third image information obtained by the second and third position imaging units 4 and 5. The three-dimensional position coordinates of the brightness center of the headlamp can then be obtained.

[0062] Preferably, the support platform 1 can rotate around a vertical axis, and the vehicle centerline angle information obtained according to the first image information is used to feed back the rotation of the support platform 1 so that the vehicle centerline coincides with or is parallel to the longitudinal axis of the world coordinate system.

[0063] Furthermore, based on the three-dimensional coordinates of the headlamp's luminosity center in a world coordinate system with the rotation center as the coordinate origin, combined with the actual vehicle body orientation (i.e., the vehicle's length), the headlamp illumination direction corresponding to the coordinates of each point on the optical test screen (expressed in a world coordinate system with the rotation center as the coordinate origin) is calculated. This illumination direction is expressed in the headlamp coordinate system. The headlamp coordinate system takes the headlamp's luminosity center as the origin, the direction of the headlamp's optical axis as the x-axis, the direction perpendicular to the x-axis in the horizontal plane as the y-axis, and the vertical direction as the z-axis. Generally speaking, the principal axis of a headlamp installed on a vehicle is the direction passing through the luminosity center and parallel to the vehicle body orientation. Subsequent calculations are performed to obtain the spatial light intensity distribution with the headlamp's luminosity center as the origin.

[0064] Preferably, the three position imaging units are calibrated separately using the measurement markers 6. Specifically, the spatial coordinates of the measurement markers in the world coordinate system are known, and a mapping relationship is established between the three-dimensional spatial coordinates in the world coordinate system and the pixel coordinates of each position imaging unit using the images captured by each position imaging unit. This calibration step can be completed before the vehicle is parked on the platform. When the vehicle is not parked, the position imaging unit can clearly capture the measurement markers. However, when the vehicle is parked on the platform, the measurement markers may be obscured or removed.

[0065] Taking the mapping between the three-dimensional coordinates in the world coordinate system and the pixel coordinates of the imaging unit at the first position as an example, when the imaging unit at the first position is placed directly above the carrier, that is, when the inclination angle of the imaging unit at the first position relative to the XY plane of the world coordinate system is 0, the mapping relationship between the three-dimensional coordinates in the world coordinate system and the pixel coordinates of the imaging unit at the first position is as follows:

[0066]

[0067]

[0068] Wherein, u and v are the coordinates of a pixel point in the image captured by the first position imaging unit, x and y are the coordinates of u and v mapped to the XY plane of the world coordinate system; a and b are the actual distances corresponding to a single pixel in the x and y directions, respectively, which are obtained by calibration of measurement markers with known spatial position coordinates, and a and b are nonlinear parameters; c and d are the translation parameters between the receiving point A of the first position imaging unit and the origin O of the world coordinate system on the XY plane.

[0069] When the first position imaging unit is placed obliquely above the carrier, that is, the inclination angle of the first position imaging unit relative to the world coordinate system XY plane is not 0, for a certain point on the carrier (when z is not 0), take xu conversion as an example, Figure 1As shown, O is the origin of the world coordinate system, θ is the tilt angle of the first position imaging unit relative to the XY plane of the world coordinate system, (x, 0, z) is a point on the support platform, the Y axis is perpendicular to the paper and points outward, A is the receiving point of the first position imaging unit, B is the origin of the pixel coordinate system, and (u, 0) is the corresponding point of the (x, 0, z) coordinate point in the pixel coordinate system. When the translation parameters c and d are 0, we can get:

[0070]

[0071]

[0072]

[0073]

[0074] Among them, z is the height of a certain point on the supporting platform 1. For the headlight brightness center, this parameter can be obtained by the second position imaging unit 4 and / or the third position imaging unit 5; h is the height of the receiving point A of the first position imaging unit 2, that is, the distance of the receiving point A of the first position imaging unit in the Z-axis direction in the world coordinate system; (x2,0,0) is the intersection of the line connecting the coordinate point (x,0,z) and the receiving point A of the first position imaging unit on the XY plane of the world coordinate system, and h1 is the intersection of the coordinate point (x,0,z) and the line connecting the receiving point A of the first position imaging unit 2 on the Z-axis.

[0075] In another specific embodiment, the measurement mark 6 is a structured light stripe, such as Figure 5 As shown, the specific implementation method is to place a vertical diffuser plate 9 at a designated position on the carrier platform 1. A structured light generator 10 is used to illuminate the diffuser plate 9 to form structured light stripes. The spatial coordinates of the characteristic points of the structured light stripes are known, and the three position imaging units can clearly capture all or part of the measurement marks. The position imaging units can first be calibrated using the structured light stripes with known spatial coordinates to establish a mapping relationship between the three-dimensional spatial coordinates of the world coordinate system and the pixel coordinates of the position imaging units. The diffuser plate 9 is then removed and the vehicle is parked on the carrier platform 1 for three-coordinate position measurement.

[0076] In one specific embodiment, a cross laser 8 positioned in front of the vehicle is aligned with the headlamp's luminosity center; or the headlamp's luminosity center is marked using a label to locate the headlamp's luminosity center, facilitating rapid identification of corresponding pixel locations in images captured by the first, second, and third position imaging units. Two cross lasers 8 are provided, one each positioned near the second and third position imaging units 4 and 5, and emitting cross laser lines aimed at the left and right headlamps.

[0077] In a specific embodiment, step A2 further includes: obtaining the height coordinate and initial lateral coordinate of the headlight illumination center based on the second image information and the third image information; further calculating the longitudinal coordinate of the headlight illumination center based on the first image information and correcting the lateral coordinate.

[0078] In another specific embodiment, the optical radiation imaging unit 11 measures the light spot image projected by the headlamp on the optical test screen 3 to obtain the light distribution information of the headlamp, or the light spot image feedback obtained by the optical radiation imaging unit 11 at different rotation angles can be used to adjust the rotation of the supporting platform to correct the direction of the main optical axis of the headlamp.

[0079] Example 2:

[0080] This embodiment discloses a photoelectric three-coordinate measurement system. Figure 6 As shown, the system includes a platform 1 for parking a vehicle, an optical test screen 3, a first position imaging unit 2, a second position imaging unit 4, a third position imaging unit 5, an illumination light source 7, a light radiation imaging unit 11, and a data transceiver control unit. The platform 1 includes a rotating device that allows the platform 1 to rotate horizontally and / or vertically. The platform 1 is provided with several measurement marks 6 with known spatial coordinates. The optical test screen 3 is positioned in front of the vehicle's headlights, with the headlights emitting a light beam that illuminates the optical test screen 3. The light radiation imaging unit 11 is aligned with the optical test screen 3. The first position imaging unit 2, the second position imaging unit 4, and the third position imaging unit 5 are spatially arranged so that their principal optical axes are not coplanar, and the measurement fields of all three imaging units cover the lamp under test. The first position imaging unit 2, the second position imaging unit 4, the third position imaging unit 5, and the light radiation imaging unit 11 are each communicatively connected to the data transceiver control unit.

[0081] Specifically, the test is conducted in a darkroom environment. The first-position imaging unit 2 is positioned diagonally above the front of the vehicle, with the measurement field of view covering the support platform 1 and the vehicle's headlights. The second-position imaging unit 4 and the third-position imaging unit 5 are respectively positioned on the front side of the vehicle and do not block the light beams emitted by the vehicle's headlights. The measurement field of view covers the front side of the vehicle and the headlights. Two illumination light sources 7 are positioned diagonally below the headlights to provide illumination. Image recognition is used to extract the contour information of the headlights and obtain the photometric center position. The optical test screen 3 is positioned 25 meters from the support platform. The world coordinate system uses the rotation center on the support platform 3 as the coordinate origin. The direction perpendicular to the optical test screen through this position is the x-axis direction, the direction perpendicular to the x-axis in the horizontal plane is the y-axis direction, and the vertical direction is the z-axis direction. In actual measurements, in addition to using the data transceiver control unit to calculate the three-dimensional position coordinates of the headlight in the world coordinate system, the actual vehicle body orientation (i.e., the length of the vehicle) can also be used to calculate the headlight illumination direction corresponding to the coordinates of each point on the optical test screen (expressed in the world coordinate system with the rotation center as the coordinate origin). This illumination direction is expressed in the headlight coordinate system. The headlight coordinate system takes the headlight luminous center as the origin, the headlight optical axis as the x-axis, the direction perpendicular to the x-axis in the horizontal plane as the y-axis, and the vertical direction as the z-axis. Generally speaking, the principal axis of a headlight installed on a vehicle is the direction passing through the luminous center and parallel to the vehicle body orientation. Subsequent calculations are used to determine the spatial light intensity distribution with the headlight luminous center as the origin.

[0082] Preferably, the method further includes measuring the light spot image of the optical test screen 3 using a light radiation imaging unit 11 arranged facing the optical measurement screen 3, and the data transceiver control unit analyzes the light spot image to obtain the center position of the light spot and corrects the light axis direction of the headlight.

[0083] Preferably, two cross lasers (not shown in the figure) are further included. The cross lasers are arranged side by side with the lighting source in front of the vehicle. The cross lasers are used to emit cross laser lines to the headlights to further accurately locate the brightness center of the headlights.

[0084] Example 3:

[0085] This embodiment provides a photoelectric three-coordinate measurement system, such as Figure 7As shown, the system includes a platform 1 for parking a vehicle, an optical test screen 3, a first position imaging unit 2, a second position imaging unit 4, a third position imaging unit 5, a cross laser 8, a light radiation imaging unit 11, and a data transceiver control unit. The platform 1 includes a rotation device that allows the platform 1 to rotate horizontally and / or vertically. Several measurement marks 6 with known spatial coordinates are provided on the platform 1. The optical test screen 3 is positioned in front of the vehicle's headlights, with the headlights emitting a light beam that strikes the optical test screen 3. The light radiation imaging unit 11 is aligned with the optical test screen 3. The first position imaging unit 2, the second position imaging unit 4, and the third position imaging unit 5 are spatially arranged so that their principal optical axes are not coplanar. The measurement field of view of the first position imaging unit 2 covers the platform 1, while the measurement fields of the second and third position imaging units 4 and 5 cover the lamp being tested. The first position imaging unit 2, the second position imaging unit 4, the third position imaging unit 5, and the light radiation imaging unit 11 are each communicatively connected to the data transceiver control unit.

[0086] Specifically, the first position imaging unit 2 is arranged directly above the rotation center of the support platform 1, and the measurement field of view covers the support platform 1; the second position imaging unit 4 and the third position imaging unit 5 are respectively arranged at the front side of the vehicle head and do not block the measurement area on the optical test screen, and the measurement field of view covers the front side of the vehicle and the headlights. Two cross lasers 8 are respectively arranged below the second position imaging unit 4 and the third position imaging unit 5, and are used to project cross laser lines to the vehicle headlights to calibrate the headlight brightness center. During measurement, the optical test screen is generally set at a distance of 25m from the support platform. The world coordinate system is established with the rotation center of the support platform as the coordinate origin. The direction perpendicular to the optical test screen through the rotation center is the x-axis direction, the direction perpendicular to the x-axis in the horizontal plane is the y-axis direction, and the vertical direction is the z-axis direction.

[0087] This embodiment also provides a photoelectric three-coordinate measurement method, using the above-mentioned photoelectric three-coordinate measurement system, such as Figure 8 and Figure 9 As shown, a vehicle is parked on a supporting platform 1 that can rotate about a horizontal axis and / or a vertical axis. An optical test screen 3 for receiving headlamp light is set in front of the vehicle. A light radiation imaging unit 11 is used to measure the light spot image of the optical test screen 3. The spatial three-dimensional position coordinates of the headlamp illumination center are determined by the following steps:

[0088] B1: Use the first position imaging unit 2, which is located directly above the rotation center of the platform 1 and whose field of view covers the platform 1, to photograph the vehicle to obtain first image information; use the second position imaging unit 4 and the third position imaging unit 5, which are located in front of the side of the platform and whose measurement field of view covers the headlight, to photograph the side of the vehicle from two directions to obtain second image information and third image information respectively;

[0089] B2: The data transceiver control unit calculates and analyzes the three-dimensional position coordinates of the vehicle headlight illumination center in the world coordinate system based on the first image information, the second image information and the third image information, wherein the three-dimensional position coordinates include height, longitudinal and lateral coordinates.

[0090] It should be noted that, in this embodiment, the optical test screen 3 is set at a position 25m away from the supporting platform. The world coordinate system takes a certain point on the supporting platform as the coordinate origin. The direction perpendicular to the optical test screen through this position point is the x-axis direction, the direction perpendicular to the x-axis in the horizontal plane is the y-axis direction, and the vertical direction is the z-axis direction.

[0091] For general vehicles, in the above technical solution, the horizontal position information of the brightness center of the light being measured relative to the platform 1 can be calculated based on the first image information obtained by the first position imaging unit 2 through image recognition. The vertical position information of the brightness center of the light being measured relative to the platform 1 can be calculated based on the second and third image information obtained by the second and third position imaging units 4 and 5. The three-dimensional position coordinates of the brightness center of the headlight can then be obtained.

[0092] Preferably, the support platform 1 can rotate around a vertical axis, and the vehicle centerline deflection information obtained according to the first image information is used to feed back the rotation of the support platform 1 so that the vehicle centerline coincides with the longitudinal axis of the world coordinate system.

[0093] Furthermore, based on the three-dimensional coordinates of the headlamp's luminosity center in a world coordinate system with the rotation center as the coordinate origin, combined with the actual vehicle body orientation (i.e., the vehicle's length), the headlamp illumination direction corresponding to the coordinates of each point on the optical test screen (expressed in a world coordinate system with the rotation center as the coordinate origin) is calculated. This illumination direction is expressed in the headlamp coordinate system. The headlamp coordinate system takes the headlamp's luminosity center as the origin, the direction of the headlamp's optical axis as the x-axis, the direction perpendicular to the x-axis in the horizontal plane as the y-axis, and the vertical direction as the z-axis. Generally speaking, the principal axis of a headlamp installed on a vehicle is the direction passing through the luminosity center and parallel to the vehicle body orientation. Subsequent calculations are performed to obtain the spatial light intensity distribution with the headlamp's luminosity center as the origin.

[0094] Preferably, the three position imaging units are calibrated separately using the measurement marker 6. Specifically, the spatial position coordinates of the measurement marker 6 in the world coordinate system are known, and a mapping relationship between the three-dimensional spatial coordinates in the world coordinate system and the pixel coordinates of each position imaging unit is established using the images captured by each position imaging unit. The calibration step can be completed before the vehicle is parked on the platform. When the vehicle is not parked, the position imaging unit can clearly capture the measurement marker. However, when the vehicle is parked on the platform, the measurement marker may be obscured or removed.

[0095] Among them, taking the mapping between the three-dimensional coordinates in the world coordinate system and the pixel coordinates of the first position imaging unit 2 as an example, in this embodiment, the inclination angle of the first position imaging unit relative to the XY plane of the world coordinate system is 0, and the translation parameters c and d between the receiving point A of the first position imaging unit and the coordinate origin O of the world coordinate system on the XY plane are 0, then the mapping relationship between the three-dimensional coordinates in the world coordinate system and the pixel coordinates of the first position imaging unit is as follows:

[0096]

[0097]

[0098] Wherein, u and v are the coordinates of a pixel point in the image captured by the first position imaging unit, x and y are the coordinates of u and v mapped to the XY plane of the world coordinate system; a and b are the actual distances corresponding to a single pixel in the x and y directions, respectively, which are obtained by calibration of measurement markers with known spatial position coordinates.

[0099] In one specific embodiment, a cross laser 8 positioned at the front of the vehicle is aligned with the luminous center of the headlights to locate the luminous center of the headlights, facilitating rapid identification of corresponding pixel locations in images captured by the first position imaging unit 2, the second position imaging unit 4, and the third position imaging unit 5. Two cross lasers 8 are provided, one each positioned near the second position imaging unit 4 and the other near the third position imaging unit 5, and aiming at the left and right headlights to emit cross laser lines.

[0100] In a specific embodiment, the first position imaging unit, the second position imaging unit, and the third position imaging unit are cameras, wherein the second image information and the third image information obtain the initial values ​​of the height coordinates and lateral coordinates of the headlight illumination center mainly based on the binocular stereo vision measurement principle, and obtain two different images of the same scene through two cameras at different positions, calculate the position deviation between the image pixels through the triangulation principle, and infer the depth information of the position point in the three-dimensional world coordinate system. The main steps include camera calibration, stereo correction, stereo matching and depth calculation. Furthermore, the lateral coordinates of the headlight are inferred based on the depth information of the vehicle headlight. Taking the ideal binocular camera imaging model as an example, Figure 10 As shown in the figure, C1 and C2 are the left and right cameras, with focal lengths fL and fR, respectively. Ideally, fL and fR are equal, denoted by f. The distance between the camera entrance pupils is b, which can be obtained from prior information or camera calibration. P is the target position captured by the two cameras, with its coordinate position denoted by P(x, y). The horizontal distance of the target is X, and the vertical distance from the camera to the target is Z, which is the depth information we want to obtain. According to the trigonometric relationship, the parameters in the figure should satisfy:

[0101]

[0102] Arranged:

[0103]

[0104] It should be noted that in the above embodiment, based on the positional relationship between the second position imaging unit, the third position imaging unit and the vehicle, the second position imaging unit and the third position imaging unit can be used to obtain the height information of the headlight brightness center. When, in order to obtain a more complete vehicle image, the second position imaging unit and the third position imaging unit are set farther away from the supporting platform, there is no doubt that the second position imaging unit and the third position imaging unit are relatively weak in recognizing the lateral coordinates of the headlight brightness center, and the recognition of the longitudinal coordinates is relatively the worst. Therefore, in this embodiment, the first position imaging unit set on the front side of the vehicle can be used to correct the initial values ​​of the lateral coordinates obtained by the second position imaging unit and the third position imaging unit to further improve the measurement accuracy.

[0105] In one specific embodiment, deep learning is also performed on the location of the headlight brightness center of different vehicle models to facilitate the rapid and accurate identification of the brightness center location in the first, second, and third image information captured by the first, second, and third position imaging units. Specifically, a neural network model can be constructed, including but not limited to a ResNet residual neural network, using the first, second, and third image information labeled with the high and low beam brightness centers as samples for training. Deep learning is used to train and record samples of the headlight brightness center location of different vehicle models for rapid identification of the brightness centers of headlights of similar vehicle models.

[0106] In one specific embodiment, the first image information is used to extract vehicle outline information through image recognition to obtain the deflection angle of the vehicle centerline relative to the longitudinal axis of the world coordinate system. Based on the three-dimensional coordinates of the headlamp in the world coordinate system, a coordinate transformation relationship is calculated between the world coordinate system with the rotation center of the support platform as the coordinate origin and the headlamp coordinate system with the headlamp illumination center as the coordinate origin. Specifically, a coordinate rotation transformation and a translation transformation are performed to obtain a transformation matrix. Subsequently, the spatial light intensity distribution with the headlamp illumination center as the coordinate origin is further calculated.

[0107] In a specific implementation scheme, for vehicles with recessed headlights, the first position imaging unit placed directly above the supporting platform cannot capture the light under test. The vehicle contour line can be extracted based on the first image information obtained, and the relative position relationship between the vehicle and the supporting platform can be obtained. Combined with the headlight installation parameters provided by the manufacturer, the horizontal plane position information of the brightness center of the light under test relative to the supporting platform can be calculated. Furthermore, the angular deviation information of the vehicle center line relative to the longitudinal axis of the world coordinate system can be analyzed and obtained, and the supporting platform can be rotated so that the vehicle center line is parallel to or coincides with the longitudinal axis of the world coordinate system, so as to facilitate the calculation of the headlight distribution information.

[0108] While the specific embodiments of the present invention have been described above with reference to the accompanying drawings, it should be understood by those skilled in the art that the above embodiments are for illustrative purposes only and are not intended to limit the scope of the present invention. It should be understood by those skilled in the art that modifications may be made to the above embodiments without departing from the scope and spirit of the present invention. The scope of protection of the present invention is defined by the appended claims.

Claims

1. A photoelectric three-coordinate measurement method, characterized in that: The lamp to be tested is mounted on a vehicle, the vehicle is parked on a carrier platform (1), an optical test screen (3) for receiving a light beam emitted by the lamp to be tested is arranged in front of the lamp to be tested, and a light radiation imaging unit (11) is used to measure a light spot image of the optical test screen (3); Determine the spatial coordinates of the measured light intensity center through the following steps: S1: Using a first position imaging unit (2), a second position imaging unit (4), and a third position imaging unit (5) to respectively shoot from different directions, and respectively obtaining first image information, second image information, and third image information; the main optical axes of the three position imaging units (2, 4, 5) are not coplanar, and the measurement fields of at least two of the three position imaging units cover the lamp to be measured; The first position imaging unit (2) is arranged above the carrier platform (1) and has a measurement field covering the carrier platform (1); the second position imaging unit (4) and the third position imaging unit (5) are arranged at the two side fronts of the carrier platform (1) and have a measurement field covering the lamp to be measured, so as to photograph the side of the vehicle from two directions; the three position imaging units (2, 4, 5) have established a mapping relationship between the spatial coordinates in the world coordinate system and the pixel coordinates of the position imaging unit; S2: The data transceiver control unit calculates and analyzes the three-dimensional position coordinates of the brightness center of the measured light in the world coordinate system based on the three image information; The carrier platform (1) can rotate around a horizontal axis and / or a vertical axis, and the rotation of the carrier platform (1) is adjusted based on the feedback of the light spot image obtained by the light radiation imaging unit (11) at different rotation angles, and the position of the light intensity center of the measured light is further determined using the steps S1 and S2.

2. The photoelectric three-coordinate measurement method according to claim 1, characterized in that: The first image information is used to extract the vehicle contour information by image recognition to obtain the deflection angle information of the vehicle center line relative to the longitudinal axis of the world coordinate system.

3. According to the photoelectric three-coordinate measurement method described in claim 2, the support platform (1) can rotate around the vertical axis, and the rotation of the support platform (1) is fed back based on the vehicle centerline deflection information obtained according to the first image information, so that the vehicle centerline is parallel to or coincides with the longitudinal axis of the world coordinate system.

4. A photoelectric three-coordinate measurement method according to claim 1 or 2, characterized in that: The three position imaging units (2, 4, 5) are calibrated respectively using a measurement marker (6), specifically: the spatial position coordinates of the measurement marker (6) in the world coordinate system are known, and a mapping relationship between the spatial coordinates in the world coordinate system and the pixel coordinates of each position imaging unit is established through the image captured by each position imaging unit.

5. The photoelectric three-coordinate measurement method according to claim 1, characterized in that: In step S2, the height coordinate and the initial lateral coordinate of the brightness center of the measured light are obtained according to the second image information and the third image information; the longitudinal coordinate of the brightness center of the measured light is further calculated according to the first image information and the lateral coordinate is corrected.

6. The photoelectric three-coordinate measurement method according to claim 1, characterized in that: The method also includes constructing a neural network model, inputting the first image information, the second image information, and the third image information of the light intensity center of the light to be measured, which are marked, into a data transceiver control unit and used as samples for training, obtaining the approximate position of the light intensity center of the light to be measured in a multi-lamp system, and combining image recognition calculation to obtain the specific position information of the light intensity center of the light to be measured relative to the carrier (1).

7. A photoelectric three-coordinate measurement system based on the photoelectric three-coordinate measurement method according to any one of claims 1 to 6, characterized in that: The invention comprises a carrier platform (1) for placing a lamp to be tested, an optical test screen (3), a first position imaging unit (2), a second position imaging unit (4), a third position imaging unit (5), a light radiation imaging unit (11), and a data transceiver control unit; the optical test screen (3) is arranged in front of the lamp to be tested, a light beam emitted by the lamp to be tested irradiates the optical test screen (3), and the light radiation imaging unit (11) is aligned with the optical test screen (3); the three position imaging units are arranged in space so that their main optical axes are not coplanar, and the measurement fields of at least two of the three position imaging units cover the lamp to be tested; the three position imaging units and the light radiation imaging unit (11) are respectively connected to the data transceiver control unit for communication.

8. The photoelectric three-coordinate measuring system according to claim 7, characterized in that: The carrier platform (1) is also provided with a plurality of measurement marks (6) with known spatial coordinates, and the measurement marks (6) are located within the measurement field of view of the first position imaging unit (2).

9. The photoelectric three-coordinate measuring system according to claim 7, characterized in that: The first position imaging unit (2) is arranged above the lamp to be tested; the second position imaging unit (4) and the third position imaging unit (5) are respectively arranged on both sides of the optical test screen (3) without blocking the measuring area on the optical test screen (3).

10. The photoelectric three-coordinate measuring system according to claim 7, characterized in that: The lamp to be tested is a headlamp installed on a vehicle, and the supporting platform (1) is used for parking the vehicle.

11. The photoelectric three-coordinate measuring system according to claim 7, characterized in that: The supporting platform comprises a rotating device for rotating the supporting platform (1) in the horizontal and / or vertical direction.

Images