A rearview mirror flatness detection method and system

Abstract

The present application relates to mirror detection technical field, especially to a rearview mirror flatness detection method and system, steps include: setting detection area, and projecting line laser to detection area;Detecting standard rearview mirror, obtaining the center line thereof through center line detection model, and recording as reference center line;Detecting the rearview mirror to be measured, obtaining the center line thereof through center line detection model, and recording as detection center line;Calculating defect degree γ;Comparing reference center line and detection center line, obtaining the inclination angle β of detection center line;Calculating the fluctuation degree ζ of detection center line;According to inclination angle β, fluctuation degree ζ and defect degree γ, calculating flatness score S, if flatness score S exceeds the set area, then determining that the flatness of rearview mirror to be measured is unqualified;The present application can effectively solve the problems of low detection efficiency and low detection precision in the prior art.

Description

Technical Field

[0001] This invention relates to the field of mirror inspection technology, and in particular to a method and system for inspecting the flatness of a rearview mirror. Background Technology

[0002] As an auxiliary tool for drivers to observe the situation behind the vehicle, the flatness of car rearview mirrors directly affects the quality of the reflected image. If the rearview mirror has problems such as deformation or tilting, the reflected image will be distorted, affecting the driver's normal observation. Therefore, the flatness of rearview mirrors needs to be inspected after production. Current inspection methods typically involve manual measurement by personnel using a ruler against the mirror surface. This method is not only inefficient, but the results are also mainly based on manual observation, making it easy to miss minor deformations or tilting issues, resulting in low inspection precision. Summary of the Invention

[0003] This invention provides a method and system for detecting the flatness of rearview mirrors, which can effectively solve the problems of low detection efficiency and low detection precision in the prior art.

[0004] The present invention provides a method for detecting the flatness of a rearview mirror, comprising the following steps:

[0005] Define the detection area and project a laser line onto the detection area;

[0006] The standard rearview mirror is inspected, and its centerline is obtained through the centerline detection model and recorded as the reference centerline.

[0007] The rearview mirror to be tested is inspected, and its centerline is obtained through the centerline detection model and recorded as the detection centerline.

[0008] Calculate the defect degree γ; compare the reference center line and the detection center line to obtain the tilt angle β of the detection center line; calculate the fluctuation degree ζ of the detection center line;

[0009] The flatness score S is calculated based on the tilt angle β, fluctuation ζ, and defect γ. If the flatness score S exceeds the set range, the flatness of the rearview mirror under test is deemed unqualified.

[0010] The centerline detection model specifically includes:

[0011] Turn off the line laser, acquire an image of the detection area, and calculate the background light intensity parameters;

[0012] Turn on the line laser and horizontally transport the rearview mirror through the detection area at a fixed speed, so that the mirror surface of the rearview mirror is facing upwards and the transport direction is perpendicular to the width direction of the line laser.

[0013] The reflection angle direction of the line laser is acquired at fixed time intervals to obtain an image of the detection area. The image is then preprocessed using the background light intensity parameter, and the position of the light intensity centroid in the image is calculated.

[0014] Remove all images whose centroid position could not be calculated for light intensity;

[0015] Using the ordinal number as the independent variable a and the position of the centroid of light intensity obtained in chronological order as the dependent variable b, starting from a = 0, the center line b(a) is obtained.

[0016] Furthermore, in the centerline detection model, the preprocessing of the detection region image using background light intensity parameters specifically includes:

[0017] The direction of the rearview mirror's movement is the x-axis, and the width direction of the line laser is the y-axis.

[0018] Let Ibg(x,y) be the light intensity of the pixel in the x-th row and y-th column of the obtained detection area image when the line laser is turned off, and calculate the mean μbg and standard deviation σbg of all pixels in the image;

[0019] Let Iraw(x,y) be the light intensity of the pixel in the x-th row and y-th column of the obtained detection area image when the line laser is turned on.

[0020] The light intensity of the pixel in the x-th row and y-th column of the image obtained after image preprocessing is:

[0021] Inorm(x,y)=(Iraw(x,y)-μbg) / σbg.

[0022] Furthermore, in the centerline detection model, the specific method for calculating the centroid position of light intensity in the image is as follows:

[0023] Let Inorm(x,y) be the light intensity of the pixel in the x-th row and y-th column of the image obtained after image preprocessing;

[0024] Calculate the segmentation threshold T = μnorm + 3σnorm;

[0025] Where μnorm is the average light intensity of all pixels in the image, and σnorm is the standard deviation of the light intensity of all pixels in the image;

[0026] Pixels with light intensity greater than T in the image are selected and recorded as laser pixels, and the centroid position b is calculated:

[0027] b=(Σy·Inorm(x,y)) / (ΣInorm(x,y));

[0028] Where Σy·Inorm(x,y) represents the sum of the light intensity of all laser pixels multiplied by their corresponding column number y; ΣInorm(x,y) represents the sum of the light intensity of all laser pixels.

[0029] Furthermore, the defect degree γ is calculated as follows:

[0030] The images remaining in the centerline detection model are numbered 0, 1, 2, ... a according to their generation time;

[0031] Let Inorm_base(a)(x,y) be the laser pixel intensity obtained in the a-th image when testing a standard rearview mirror;

[0032] Let Inorm_test(a)(x,y) be the intensity of the laser pixel obtained in the a-th image when testing the rearview mirror under test.

[0033] For all values ​​of 'a', calculate the light intensity difference ΔIa(x,y) = Inorm_base(a)(x,y) - Inorm_test(a)(x,y) for each value.

[0034] Define an allowable range, and denote the number of laser pixels whose △Ia(x,y) exceeds the allowable range as p, and the total number of laser pixels as P;

[0035] Defect degree γ = p / P.

[0036] Furthermore, it also includes a continuity detection step, specifically:

[0037] After selecting the laser pixels in each image, the x-values ​​of the laser pixels are checked for continuity. If they are continuous, the subsequent calculations continue; if they are not continuous, the missing values ​​are filled in using interpolation to ensure that the x-values ​​of the laser pixels are continuous.

[0038] Furthermore, the tilt angle β of the detection center line is specifically obtained as follows:

[0039] Let the baseline centerline be b0(a) and the detection centerline be b1(a);

[0040] When calculating each value of 'a', the offset Δb(a) = b1(a) - b0(a);

[0041] Inclination angle β = arctan(△b(a)avg / 2D);

[0042] Where △b(a)avg is the average value of all △b(a); D is the distance between the laser emission point and the mirror surface.

[0043] Furthermore, the fluctuation ζ of the detection center line is calculated as follows:

[0044] Let the center line of the test be designated as b1(a);

[0045] Find the maximum and minimum points of the detection center line, and calculate the difference of b1 value between adjacent maximum and minimum points; set the acceptance range, and record the number of differences that exceed the acceptance range as n;

[0046] Calculate the midpoint between adjacent maximum and minimum points, then calculate the slope of the straight line connecting two adjacent midpoints, and denote the standard deviation of the difference between all slopes and tanβ as m;

[0047] The volatility ζ is calculated to be 0.19·n·m.

[0048] Furthermore, the formula for calculating the flatness score S is as follows:

[0049] S=k1·|γ| / [γ]+k2·|β| / [β]+k3·|ζ| / [ζ];

[0050] Where k1, k2, and k3 are all set adjustment coefficients; [γ] is the maximum allowable value of defect degree γ; [β] is the maximum allowable value of tilt angle β; and [ζ] is the maximum allowable value of fluctuation degree ζ.

[0051] The present invention also provides a rearview mirror flatness detection system, comprising:

[0052] The testing rack is equipped with a testing area;

[0053] The laser emitter and camera are fixedly mounted above the detection area;

[0054] A conveying device for conveying rearview mirrors;

[0055] The processor is used to implement the rearview mirror flatness detection method described above.

[0056] Furthermore, in the testing area, except for the rearview mirror mirror, the top surface of the rest of the area is covered with a layer of black frosted material.

[0057] The technical solution of this invention can achieve the following technical effects:

[0058] This invention achieves rapid acquisition of the rearview mirror surface condition through line laser scanning and camera image acquisition, and analyzes the rearview mirror surface image from multiple indicators, which can significantly improve the detection efficiency and accuracy of rearview mirror flatness, and greatly reduce the technical dependence on operators, perfectly adapting to the needs of intelligent manufacturing. Attached Figure Description

[0059] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0060] Figure 1 This is a flowchart of the rearview mirror flatness detection method in this invention;

[0061] Figure 2 This is a schematic diagram of the rearview mirror flatness detection system of the present invention;

[0062] Reference numerals: 1. Detection frame; 2. Laser emitter; 3. Camera; 4. Conveying device. Detailed Implementation

[0063] The basic principles and main features of the technical solution of the present invention will be described below with reference to the accompanying drawings of the embodiments of the present invention. The following description will use one or more embodiments for a more intuitive understanding. These embodiments are merely some, not all, of the embodiments of the present invention.

[0064] In the description of this invention, the terms indicating orientation or positional relationship (such as up, down, left, right, etc.) are based on the orientation shown in the drawings or some conventional positional relationships, and are only for the convenience of describing this invention and simplifying the description, and are not intended to indicate or imply that the features referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as limiting this invention.

[0065] This invention relates to a method for detecting the flatness of a rearview mirror, such as... Figure 1 As shown, the steps include:

[0066] S00: Set the detection area and project a line laser onto the detection area. The detection area is the area that the camera can capture. After the rearview mirror enters the detection area, the line laser will shine on the rearview mirror and be reflected back to the camera. The camera can then capture an image of the shape of the line laser on the rearview mirror.

[0067] S10: Inspect the standard rearview mirror. The standard rearview mirror is the one with the highest pass rate. Therefore, the image generated when inspecting this standard rearview mirror can be used as the standard image and the benchmark for subsequent inspections. The centerline of the standard image is obtained by inspecting it using a centerline detection model and recorded as the benchmark centerline. In addition to obtaining the benchmark for subsequent inspections, this step also allows for self-checking of the system itself. If there are significant flaws in the standard image or benchmark centerline obtained after inspecting the standard rearview mirror, it indicates that there is a problem with the system itself, and the system error can be corrected in a timely manner.

[0068] S20: The rearview mirror under test is inspected, and the resulting image is the inspection image. The shape of the laser line in the inspection image corresponds to the defect on the rearview mirror under test. The center line is obtained through the center line detection model and recorded as the inspection center line.

[0069] S30: By comparing the line laser image on the detection image with the line laser image on the standard image, the defect degree γ can be calculated. The defect degree γ reflects the proportion of pixels with obviously abnormal light intensity on the line laser image of the detection image, indicating that the reflectivity of the mirror corresponding to the problem pixel is flawed.

[0070] Both the reference center line and the detection center line reflect the center of symmetry of the light intensity of the line laser on the two types of rearview mirrors. By comparing the reference center line and the detection center line, the tilt angle β of the detection center line can be obtained. The larger the value of the tilt angle β, the more likely the rearview mirror under test is to be skewed, that is, there is a big problem with the assembly accuracy of the rearview mirror under test.

[0071] Calculate the fluctuation ζ of the test center line. The fluctuation ζ can reflect the flatness of the rearview mirror surface under test. The smaller the fluctuation ζ, the flatter the surface of the rearview mirror.

[0072] S40: The tilt angle β, fluctuation ζ, and defect γ are interrelated and cannot be judged separately. Instead, the flatness score S is calculated based on the tilt angle β, fluctuation ζ, and defect γ to reflect the overall flatness of the rearview mirror surface. If the flatness score S exceeds the set range, the flatness of the rearview mirror under test is deemed unqualified.

[0073] The centerline detection model is mainly used to analyze images captured by the camera to identify the laser region and obtain the laser's centerline. Its main steps include environmental calibration, mirror detection, and centerline acquisition. The specific details of each step are as follows:

[0074] Environmental calibration: Turn off the line laser, acquire images of the detection area and calculate the background light intensity parameters. This will enable better differentiation between the laser area and the background area in the images captured by the camera in later stages. Since the illumination intensity may vary each time the detection is performed, this step needs to be performed every time the central detection model is started.

[0075] Mirror inspection: Turn on the line laser and horizontally transport the rearview mirror through the inspection area at a fixed speed, so that the mirror surface of the rearview mirror is facing upwards, and the transport direction is perpendicular to the width direction of the line laser.

[0076] The reflection angle of the line laser is collected at fixed intervals to obtain an image of the detection area. The interval is determined by the conveying speed and the image size, so that the rearview mirror in the two consecutive images can move forward by exactly one row of pixels. After the rearview mirror has completely passed through the detection area, multiple detection images are obtained.

[0077] Centerline acquisition: All images are preprocessed using background light intensity parameters to eliminate the influence of background light, and then the laser region in each detection image can be found. Then, the position of the light intensity centroid in each image is calculated, and then these positions of the light intensity centroid are connected to form a curve, which is the centerline.

[0078] To ensure that the centerlines obtained using this centerline detection model can be compared with each other, the starting point of the centerline must be fixed. By eliminating all images whose light intensity centroid position cannot be calculated, the starting points of all centerlines can be guaranteed to correspond to each other.

[0079] Using the ordinal number as the independent variable a (i.e., a takes the values ​​0, 1, 2, 3, etc.) and the position of the light intensity centroid obtained in chronological order as the dependent variable b (corresponding to the value of y when the laser width direction of the subsequent center-shifting line is the y-axis), starting from a = 0, the center line is obtained. The expression of the center line is b(a). The meaning of this expression is as follows: if b(1) = 10, it means that when a = 1 (i.e. in the second image left), the position of the light intensity centroid is 10.

[0080] In the centerline detection model, the specific steps for preprocessing the detection region image using background light intensity parameters include:

[0081] The direction of the rearview mirror's movement is the x-axis, and the width direction of the line laser is the y-axis.

[0082] Let Ibg(x,y) be the light intensity of the pixel in the x-th row and y-th column of the obtained detection area image when the line laser is turned off. The meaning of this expression is as follows: if Ibg(50,30)=5, it means that the light intensity Ibg(50,30) of the pixel in the 50th row and 30th column of the detection area image is 5; and calculate the mean μbg and standard deviation σbg of all pixels in the image.

[0083] Let Iraw(x,y) be the light intensity of the pixel in the x-th row and y-th column of the obtained detection area image when the line laser is turned on. The meaning of this expression is the same as above.

[0084] Then, the light intensity Inorm(x,y) of the pixel in the x-th row and y-th column of the image obtained after image preprocessing is:

[0085] Inorm(x,y)=(Iraw(x,y)-μbg) / σbg;

[0086] This transforms the image Iraw(x,y) into a new image Inorm(x,y). In the new image, the difference in light intensity Inorm between the laser region and the non-laser region becomes more obvious, making it easier to distinguish them later.

[0087] In the centerline detection model, the specific method for calculating the centroid position of light intensity in this image is as follows:

[0088] In the aforementioned calculation, the light intensity of the pixel in the x-th row and y-th column of the image obtained after image preprocessing has been obtained as Inorm(x,y);

[0089] Calculate the segmentation threshold T = μnorm + 3σnorm;

[0090] Where μnorm is the average light intensity of all pixels in image Inorm(x,y), and σnorm is the standard deviation of the light intensity of all pixels in image Inorm(x,y); the segmentation threshold T is used as a benchmark to distinguish between laser regions and non-laser regions in image Inorm(x,y). This benchmark is calculated directly from image Inorm(x,y). Therefore, the segmentation threshold T is calculated to be the most suitable value for the image, avoiding the influence of background light on the image and ensuring the accuracy of the distinction.

[0091] Pixels with light intensity greater than T in the image are selected and recorded as laser pixels, and the centroid position b is calculated:

[0092] b=(Σy·Inorm(x,y)) / (ΣInorm(x,y));

[0093] Where Σy·Inorm(x,y) represents the sum of the light intensity of all laser pixels multiplied by their corresponding column number y. For example, if the light intensity of a laser pixel is Inorm(x,y) and the range of laser pixels is x=10, y=1, 2, 3, 4, …20, then Σy·Inorm(x,y)=1·Inorm(10,1)+2·Inorm(10,2)+3·Inorm(10,3)+……+20·Inorm(10,20);

[0094] ΣInorm(x,y) represents the sum of the light intensities of all laser pixels. For example, ΣInorm(x,y) = Inorm(10,1) + Inorm(10,2) + Inorm(10,3) + ... + Inorm(10,20).

[0095] The specific calculation of the defect degree γ is as follows:

[0096] The images remaining in the centerline detection model are numbered 0, 1, 2, ... a according to their generation time;

[0097] Both the standard rearview mirror and the rearview mirror under test will generate many Inorm(x,y) images when tested using this method. To better distinguish them, a suffix is ​​now added:

[0098] Let Inorm_base(a)(x,y) be the light intensity of the laser pixel obtained in the a-th image when testing a standard rearview mirror. For example, Inorm_base(2)(10,20)=5 means that the light intensity of the laser pixel in the 10th row and 20th column of the third image is 5 when testing a standard rearview mirror.

[0099] Let Inorm_test(a)(x,y) be the intensity of the laser pixel obtained in the a-th image when testing the rearview mirror under test. For example, Inorm_test(2)(10,20)=5 means that when testing the standard rearview mirror, the intensity of the laser pixel in the 10th row and 20th column of the third image is 5.

[0100] Under normal circumstances, because the rearview mirror is restricted by a clamp during transportation, the position of the laser pixel in each image is consistent, that is, the range of x and y values ​​in each image is the same, the difference is the light intensity corresponding to the laser pixel.

[0101] For all values ​​of 'a', the light intensity difference ΔIa(x,y) = Inorm_base(a)(x,y) - Inorm_test(a)(x,y) is calculated for each value. For example, if 200 images are obtained when testing a standard rearview mirror, then 200 images will also be obtained for the rearview mirror under test, i.e., a = 0, 1^199.

[0102] Since the laser beams are illuminating the same locations, the laser area in each image is now x = 10, y = 1, 2, 3...20;

[0103] When a = 0, we need to calculate △I0(x,y), where x = 10, y = 1, 2, 3...20, which means we will get a total of 20 △I0(x,y); similarly, when a = 1, we will get a total of 20 △I1(x,y)... up to a = 199, which will get a total of 20 △I199(x,y);

[0104] Define an allowable range, and denote the number of laser pixels whose △Ia(x,y) exceeds the allowable range as p, and the total number of laser pixels as P;

[0105] Defect degree γ = p / P;

[0106] This step calculates the percentage of areas with light intensity defects in all mirror areas; a larger value indicates more severe damage to the mirror surface.

[0107] Of course, during the inspection, some parts of the mirror surface may not reflect light due to impurities, which will affect the correspondence in the calculation and the position of the light intensity centroid. Therefore, a continuity detection step is also required, specifically:

[0108] After selecting the laser pixels in each image, the continuity of the x-values ​​of the laser pixels is checked. If they are continuous, subsequent calculations can continue. If they are not continuous, it means that impurities may be blocking the laser in the discontinuous parts. In this case, the gaps need to be filled in by interpolation to ensure that the x-values ​​of the laser pixels are continuous. This will ensure a clear correspondence between the images and minimize the error in the position of the light intensity centroid.

[0109] The tilt angle β of the detection centerline is specifically obtained as follows:

[0110] Both the standard rearview mirror and the rearview mirror under test will generate a centerline b(a) when tested using this method. To better distinguish them, a corresponding suffix is ​​added:

[0111] Let the baseline centerline be b0(a) and the detection centerline be b1(a);

[0112] When calculating each value of 'a', the offset Δb(a) = b1(a) - b0(a);

[0113] Inclination angle β = arctan(△b(a)avg / 2D);

[0114] Where △b(a)avg is the average value of all △b(a); D is the distance between the laser emission point and the mirror surface;

[0115] The tilt angle β mainly reflects the angular rotation of the detection centerline relative to the reference centerline. This angular rotation is caused by the fact that the mirror surface of the rearview mirror under test and the mirror surface of the standard rearview mirror do not coincide on the plane, resulting in different light intensities of the laser light reflected into the camera. Therefore, the magnitude of the tilt angle β can indicate the degree of error in the assembly of the mirror surface of the rearview mirror under test.

[0116] The specific calculation of the fluctuation ζ of the detection centerline is as follows:

[0117] Let the center line of the test be designated as b1(a);

[0118] Find the maximum and minimum points of the detection center line and calculate the difference of b1 value between adjacent maximum and minimum points; set an acceptance range. If the value exceeds the acceptance range, it means that the span of the detection center line is large at this point. Record the number of differences that exceed the acceptance range as n. The larger the number of n, the more segments of the detection center line with large spans, which can indicate that the fluctuation of the detection center line is large.

[0119] Of course, judging solely by the size of the span is too simplistic. For example, if the detection center line fluctuates along a diagonal line, it is possible that although the span appears large in the coordinate system, the fluctuation of the detection center line around the diagonal line is actually very small. The large span in the coordinate system is a result of the fluctuation plus the inclination of the diagonal line.

[0120] Therefore, when calculating the volatility ζ, it is also necessary to consider the inclination of the detection center line, calculate the midpoint of adjacent maximum and minimum points, and then calculate the slope of the straight line connecting two adjacent midpoints. If this slope is close to tanβ (i.e., the slope of the straight line fitted by the detection center line as a whole), the standard deviation of the difference between all slopes and tanβ is denoted as m. The smaller m is, the more slopes are close to tanβ, that is, the more likely the detection center line is to fluctuate near the straight line fitted by the detection center line as a whole. Then the volatility ζ can be reduced accordingly.

[0121] Combining the two factors mentioned above, the volatility ζ can be calculated as 0.19·n·m;

[0122] The value of 0.19 is an adjustment factor, which can be set according to the actual situation.

[0123] Finally, the formula for calculating the flatness score S is as follows:

[0124] S=k1·|γ| / [γ]+k2·|β| / [β]+k3·|ζ| / [ζ];

[0125] Wherein, k1, k2, and k3 are all set adjustment coefficients, and k1+k2+k3=1, with the value set according to the safety priority; [γ] is the maximum allowable value of defect degree γ; [β] is the maximum allowable value of tilt angle β; and [ζ] is the maximum allowable value of volatility ζ.

[0126] When making a judgment, S should be judged first. After it is determined that S exceeds the set range, γ, β and ζ should be judged separately to determine which one has a larger deviation, and then corresponding adjustment suggestions should be made.

[0127] This invention also relates to a rearview mirror flatness detection system, such as... Figure 2 As shown, it includes:

[0128] Inspection rack 1 has an inspection area;

[0129] Laser emitter 2 and camera 3 are fixed on the inspection frame and positioned above the inspection area;

[0130] Conveying device 4 is used to convey rearview mirrors; the conveying device is equipped with clamps for fixing the rearview mirrors.

[0131] The processor is used to implement the rearview mirror flatness detection method described above.

[0132] In the inspection area, and on all components that will enter the inspection area, except for the rearview mirror, the top surfaces of the fixtures, inspection rack 1, and other parts are covered with a layer of black frosted material. The black frosted material can absorb the laser as much as possible and cause the unabsorbed laser to be diffusely reflected, so that the laser will not be reflected into the camera lens and the background environment will not interfere with the inspection.

[0133] The foregoing has shown and described the basic principles, main features, and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The embodiments and descriptions in the specification are merely illustrative of the principles of the invention. Various changes and modifications can be made to the invention without departing from its spirit and scope, and all such changes and modifications fall within the scope of the present invention as claimed. The scope of protection of the present invention is defined by the appended claims and their equivalents.

Claims

1. A method for detecting the flatness of a rearview mirror, characterized in that the steps include: include: Define the detection area and project a laser line onto the detection area; The standard rearview mirror is inspected, and its centerline is obtained through the centerline detection model and recorded as the reference centerline. The rearview mirror to be tested is inspected, and its centerline is obtained through the centerline detection model and recorded as the detection centerline. Calculate the defect degree γ; compare the reference center line and the detection center line to obtain the tilt angle β of the detection center line; calculate the fluctuation degree ζ of the detection center line; The flatness score S is calculated based on the tilt angle β, fluctuation ζ, and defect γ. If the flatness score S exceeds the set range, the flatness of the rearview mirror under test is deemed unqualified. The centerline detection model specifically includes: Turn off the line laser, acquire an image of the detection area, and calculate the background light intensity parameters; Turn on the line laser and horizontally transport the rearview mirror through the detection area at a fixed speed, so that the mirror surface of the rearview mirror is facing upwards and the transport direction is perpendicular to the width direction of the line laser. The reflection angle direction of the line laser is acquired at fixed time intervals to obtain an image of the detection area. The image is then preprocessed using the background light intensity parameter, and the position of the light intensity centroid in the image is calculated. Remove all images whose centroid position could not be calculated for light intensity; Using the ordinal number as the independent variable a and the position of the centroid of light intensity obtained in chronological order as the dependent variable b, starting from a=0, the center line b(a) is obtained; Specifically, the location of the light intensity centroid in this image is calculated as follows: Let Inorm(x,y) be the light intensity of the pixel in the x-th row and y-th column of the image obtained after image preprocessing; Calculate the segmentation threshold T = μnorm + 3σnorm; Where μnorm is the average light intensity of all pixels in the image, and σnorm is the standard deviation of the light intensity of all pixels in the image; Pixels with light intensity greater than T in the image are selected and recorded as laser pixels, and the centroid position b is calculated: b=(Σy·Inorm(x,y)) / (ΣInorm(x,y)); Where Σy·Inorm(x,y) represents the sum of the light intensity of all laser pixels multiplied by their corresponding column number y; ΣInorm(x,y) represents the sum of the light intensity of all laser pixels.

2. The rearview mirror flatness detection method according to claim 1, characterized in that, In the centerline detection model, the detection region image is preprocessed using background light intensity parameters, specifically including: The direction of the rearview mirror's movement is the x-axis, and the width direction of the line laser is the y-axis. Let Ibg(x,y) be the light intensity of the pixel in the x-th row and y-th column of the obtained detection area image when the line laser is turned off, and calculate the mean μbg and standard deviation σbg of all pixels in the image; Let Iraw(x,y) be the light intensity of the pixel in the x-th row and y-th column of the obtained detection area image when the line laser is turned on. The light intensity of the pixel in the x-th row and y-th column of the image obtained after image preprocessing is: Inorm(x,y)=(Iraw(x,y)-μbg) / σbg.

3. The rearview mirror flatness detection method according to claim 1, characterized in that, The specific calculation of the defect degree γ is as follows: The images remaining in the centerline detection model are numbered 0, 1, 2, ... a according to their generation time; Let Inorm_base(a)(x,y) be the laser pixel intensity obtained in the a-th image when testing a standard rearview mirror; Let Inorm_test(a)(x,y) be the intensity of the laser pixel obtained in the a-th image when testing the rearview mirror under test. For all values ​​of a, calculate the light intensity difference ΔIa(x,y) = Inorm_base(a)(x,y) - Inorm_test(a)(x,y) for each value. Define an allowable range, and denote the number of laser pixels whose △Ia(x,y) exceeds the allowable range as p, and the total number of laser pixels as P; Defect degree γ = p / P.

4. The rearview mirror flatness detection method according to claim 1, characterized in that, It also includes a continuity detection step, specifically: After selecting the laser pixels in each image, the x-values ​​of the laser pixels are checked for continuity. If they are continuous, the subsequent calculations continue; if they are not continuous, the missing values ​​are filled in using interpolation to ensure that the x-values ​​of the laser pixels are continuous.

5. The rearview mirror flatness detection method according to claim 1, characterized in that, The tilt angle β of the detection centerline is specifically obtained as follows: Let the baseline centerline be b0(a) and the detection centerline be b1(a); When calculating each value of 'a', the offset Δb(a) = b1(a) - b0(a); Inclination angle β = arctan(△b(a)avg / 2D); Where △b(a)avg is the average value of all △b(a); D is the distance between the laser emission point and the mirror surface.

6. The rearview mirror flatness detection method according to claim 4, characterized in that, The specific calculation of the fluctuation ζ of the detection centerline is as follows: Let the center line of the test be designated as b1(a); Find the maximum and minimum points of the detection center line, and calculate the difference of b1 value between adjacent maximum and minimum points; set the acceptance range, and record the number of differences that exceed the acceptance range as n; Calculate the midpoint between adjacent maximum and minimum points, then calculate the slope of the straight line connecting two adjacent midpoints, and denote the standard deviation of the difference between all slopes and tanβ as m; The volatility ζ is calculated to be 0.19·n·m.

7. The rearview mirror flatness detection method according to claim 1, characterized in that, The formula for calculating the flatness score S is as follows: S=k1·|γ| / [γ]+k2·|β| / [β]+k3·|ζ| / [ζ]; Where k1, k2, and k3 are all set adjustment coefficients; [γ] is the maximum allowable value of defect degree γ; [β] is the maximum allowable value of tilt angle β; and [ζ] is the maximum allowable value of fluctuation degree ζ.

8. A rearview mirror flatness detection system, characterized in that, include: The testing rack is equipped with a testing area; A laser emitter and a camera are fixedly mounted above the detection area; A conveying device for conveying rearview mirrors; A processor for implementing the rearview mirror flatness detection method as described in any one of claims 1 to 7.

9. The rearview mirror flatness detection method according to claim 8, characterized in that, In the inspection area, except for the mirror part of the rearview mirror, the top surface of the rest of the area is covered with a layer of black frosted material.

Images