Methods, apparatus, equipment and storage media for testing the smoothness of automotive paint surfaces

Abstract

This application relates to a method, apparatus, equipment, and storage medium for detecting the smoothness of automotive paint surfaces. The method includes: vertically aligning a strip light source with the automotive paint surface to project strip light onto the surface, forming a strip light projection; acquiring an image of the strip light projection using a camera; determining the measured width of the strip light projection based on the image; obtaining a reference width of the light projection; and quantifying the smoothness deviation of the automotive paint surface based on the measured width and the reference width. This eliminates the need for manual visual judgment, removing the subjectivity and human error inherent in traditional manual inspection, and achieving an objective and repeatable quantitative assessment of paint surface smoothness. The absence of manual intervention significantly shortens the single-test time and improves testing efficiency. Both optical projection and image acquisition are non-contact methods, avoiding the risk of damage to the paint surface during the testing process. While ensuring testing accuracy, the system is lightweight, low-cost, and easy to deploy.

Description

Technical Field

[0001] This application relates to the field of automotive testing, and more particularly to a method, apparatus, equipment, and storage medium for testing the smoothness of automotive paint surfaces. Background Technology

[0002] The smoothness of automotive paint (commonly known in the industry as "orange peel") is a significant factor affecting the overall appearance quality of a vehicle. Currently, the detection of paint orange peel primarily relies on the following two methods: (1) Manual visual inspection: The smoothness of the paint surface is mainly inspected by the naked eye of the quality inspectors. However, manual inspection has the problems of strong subjectivity and lack of unified standards. The judgment results of different inspectors often differ. At the same time, manual inspection is inefficient and difficult to meet the large-scale inspection needs of automobile production lines. Moreover, long-term visual inspection can easily lead to visual fatigue, which can easily result in missed inspections and false inspections.

[0003] (2) Traditional testing equipment testing: To solve the problem of subjectivity in manual testing, measuring equipment is used. Such equipment usually needs to be in contact with the paint surface or to measure at very close distance. During the testing process, physical damage such as scratches and indentations may be caused to the paint surface. Summary of the Invention

[0004] In order to solve the above-mentioned technical problems, or at least partially solve the above-mentioned technical problems, this application provides a method, apparatus, equipment and storage medium for testing the smoothness of automotive paint surfaces.

[0005] In a first aspect, this application provides a method for testing the smoothness of automotive paint surfaces, including: A bar light source is vertically aligned with the car paint surface to project bar light onto the car paint surface, forming a bar light projection on the car paint surface; The image of the bar light projection is captured by a camera; Based on the image, the measured width of the strip light projection is determined; Obtain the reference light band width, and quantify the smoothness deviation of the automotive paint surface based on the measured light band width and the reference light band width.

[0006] In one possible implementation, determining the measured width of the striped light projection based on the image includes: Extract a plurality of first edge pixels on the first edge and a plurality of second edge pixels on the second edge of the bar light projection from the image; wherein the first edge and the second edge are two edges of the bar light projection that are opposite each other in the width direction; Line fitting is performed on the plurality of first edge pixels and the plurality of second edge pixels respectively to obtain the first edge fitting line and the second edge fitting line; The vertical distance between the first edge fitting line and the second edge fitting line is determined as the measured width of the strip light projection.

[0007] In one possible implementation, extracting a plurality of first edge pixels on the first edge and a plurality of second edge pixels on the second edge of the bar-shaped light projection from the image includes: Convert the image to a grayscale image; In the grayscale image, pixels with grayscale values ​​greater than a preset threshold are identified as edge pixels. Based on the position of the edge pixels in the width direction of the strip light projection, the edge pixels are divided into a first edge pixel located on the first edge and a second edge pixel located on the second edge.

[0008] In one possible implementation, obtaining the reference optical band width includes: Obtain the standard light band width at a preset distance as the reference light band width; wherein, the standard light band width at the preset distance is the light band width of the strip light projection formed when the strip light source projects strip light onto the flat mirror surface at the preset distance.

[0009] In one possible implementation, quantifying the smoothness deviation of the automotive paint surface based on the measured light band width and the reference light band width includes: Obtain the measured distance between the strip light source and the car paint surface; Determine the difference between the measured optical band width and the reference optical band width; Based on the measured distance and the preset distance, the difference is corrected to obtain the width offset; wherein, the width offset is used to quantify the flatness deviation of the car paint surface.

[0010] In one possible implementation, correcting the difference based on the measured distance and the preset distance includes: The difference is corrected according to the following formula: ; in, This is the width offset. The measured optical band width is... The reference light band width is, The measured distance is... The preset distance is [the distance].

[0011] In one possible implementation, obtaining the reference optical band width includes: Obtain the measured distance between the strip light source and the car paint surface; Obtain the standard light band width at a preset distance; wherein, the standard light band width at the preset distance is the light band width of the strip light projection formed when the strip light source projects strip light onto a flat mirror surface at the preset distance; Based on the measured distance and the preset distance, the standard light band width at the preset distance is corrected to obtain the reference light band width.

[0012] In one possible implementation, quantifying the smoothness deviation of the automotive paint surface based on the measured light band width and the reference light band width includes: The difference between the measured light band width and the reference light band width is determined as the width offset; wherein, the width offset is used to quantify the flatness deviation of the automotive paint surface.

[0013] In one possible implementation, the method further includes: The width offset is compared with a preset smoothness grade model to determine the smoothness grade of the car paint surface.

[0014] In one possible implementation, the method further includes: The bar light source is moved step by step along a direction perpendicular to the length of the bar light. Each time it is moved, the steps of vertically aligning the bar light source with the car paint surface, projecting the bar light onto the car paint surface, and subsequent steps are performed.

[0015] Secondly, this application provides an automotive paint surface smoothness testing device, comprising: The projection module is used to vertically align the strip light source with the car paint surface and project strip light onto the car paint surface to form a strip light projection on the car paint surface; The image acquisition module is used to acquire images of the bar light projection via a camera; A measurement module is used to determine the measured width of the strip light projection based on the image; The reference value acquisition module is used to obtain the reference optical band width; The quantization module is used to quantify the flatness deviation of the automotive paint surface based on the measured light band width and the reference light band width.

[0016] In one possible implementation, the measurement module includes: An edge pixel extraction unit is used to extract multiple first edge pixels on the first edge and multiple second edge pixels on the second edge of the bar-shaped light projection from the image; wherein the first edge and the second edge are two edges of the bar-shaped light projection that are opposite each other in the width direction; An edge fitting unit is used to perform straight line fitting on the plurality of first edge pixels and the plurality of second edge pixels respectively to obtain a first edge fitting line and a second edge fitting line; The distance calculation unit is used to determine the vertical distance between the first edge fitting line and the second edge fitting line, which is used as the measured light band width of the strip light projection.

[0017] In one possible implementation, the edge pixel extraction unit is specifically used for: Convert the image to a grayscale image; In the grayscale image, pixels with grayscale values ​​greater than a preset threshold are identified as edge pixels. Based on the position of the edge pixels in the width direction of the strip light projection, the edge pixels are divided into a first edge pixel located on the first edge and a second edge pixel located on the second edge.

[0018] In one possible implementation, the reference value acquisition module is specifically used for: Obtain the standard light band width at a preset distance as the reference light band width; wherein, the standard light band width at the preset distance is the light band width of the strip light projection formed when the strip light source projects strip light onto the flat mirror surface at the preset distance.

[0019] In one possible implementation, the quantization module includes: A ranging unit is used to obtain the measured distance between the bar light source and the car paint surface; The difference calculation unit is used to determine the difference between the measured optical band width and the reference optical band width; The first correction unit is used to correct the difference based on the measured distance and the preset distance to obtain a width offset; wherein the width offset is used to quantify the flatness deviation of the car paint surface.

[0020] In one possible implementation, the first correction unit is specifically used for: The difference is corrected according to the following formula: ; in, This is the width offset. The measured optical band width is... The reference light band width is, The measured distance is... The preset distance is [the distance].

[0021] In one possible implementation, the reference value acquisition module includes: A ranging unit is used to obtain the measured distance between the bar light source and the car paint surface; A standard value acquisition unit is used to acquire the standard light band width at a preset distance; wherein, the standard light band width at the preset distance is the light band width of the strip light projection formed when the strip light source projects strip light onto a flat mirror surface at the preset distance; The second correction unit is used to correct the standard light band width at the preset distance based on the measured distance and the preset distance, so as to obtain the reference light band width.

[0022] In one possible implementation, the quantization module is specifically used for: The difference between the measured light band width and the reference light band width is determined as the width offset; wherein, the width offset is used to quantify the flatness deviation of the automotive paint surface.

[0023] In one possible implementation, the device further includes: The rating module is used to compare the width offset with a preset smoothness rating model to determine the smoothness rating of the car paint surface.

[0024] In one possible implementation, the device further includes: The control module is used to move the bar light source step by step along a direction perpendicular to the length of the bar light. Each time it moves, it executes the steps of vertically aligning the bar light source with the car paint surface, projecting the bar light onto the car paint surface, and so on.

[0025] Thirdly, this application provides an automotive paint surface smoothness testing device, including a strip light source, a camera, a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus; Memory, used to store computer programs; A strip light source is used to project strip light onto the paint surface of a car to form a strip light projection on the paint surface of the car; A camera is used to capture images of the bar-shaped light projection; The processor, when executing a program stored in the memory, implements the automotive paint surface smoothness testing method according to any one of claims 1 to 10.

[0026] Fourthly, this application provides a computer-readable storage medium storing a program for a method for detecting the smoothness of automotive paint surfaces, wherein when the program for detecting the smoothness of automotive paint surfaces is executed by a processor, it implements the steps of the method for detecting the smoothness of automotive paint surfaces as described in any of the first aspects.

[0027] The technical solution provided in this application has the following beneficial effects: (1) A strip light source is used to project a strip light vertically onto the car paint surface, forming a strip light projection that can be inspected on the paint surface; the image of the projection is acquired by a camera; the measured light band width is determined based on the image; finally, the flatness deviation of the paint surface is quantified by obtaining the reference light band width and comparing it with the measured light band width. Since the entire inspection process is completed automatically by the equipment, on the one hand, no manual visual judgment is required, thus eliminating the subjectivity and human error of traditional manual inspection, and realizing an objective and repeatable quantitative assessment of the flatness of the paint surface; on the other hand, no manual intervention is required, which greatly shortens the single inspection time and improves the inspection efficiency, especially suitable for the large-volume and fast-paced inspection needs on the automotive production line; furthermore, both optical projection and image acquisition are non-contact methods, avoiding the risk of damage to the paint surface during the inspection process.

[0028] (2) This scheme first converts the optical projection on the paint surface into a digital image through image acquisition, and then extracts the measurable geometric quantity of the measured light band width from it; then, by introducing a reference light band width as a comparison benchmark, the measured width is compared with the reference width, and finally the visual perception of paint surface smoothness is converted into a numerical width offset. This process transforms the originally vague subjective judgment of "orange peel severity" into a quantitative indicator with clear physical meaning, which significantly improves the precision and accuracy of the detection.

[0029] (3) This solution only requires a single linear light source and a conventional camera to achieve detection, without the need for a composite light source system or complex image fusion algorithms. At the data processing level, comparative analysis is performed by extracting the one-dimensional geometric quantity of the light band width, without the need for additional complex algorithms, which significantly reduces the complexity of image processing and the consumption of computing resources. This application achieves lightweight, low-cost and easy-to-deploy detection system while ensuring detection accuracy. Attached Figure Description

[0030] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of the invention.

[0031] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0032] Figure 1 A schematic diagram of an automotive paint surface smoothness testing device provided in an embodiment of this application; Figure 2A schematic flowchart of a method for testing the smoothness of automotive paint surfaces provided in this application embodiment; Figure 3 A schematic diagram of the striped light projection of automotive paint with different orange peel grades provided in the embodiments of this application; Figure 4 A schematic diagram of a linear light projection onto automotive paint stripes provided in an embodiment of this application; Figure 5 This is a schematic diagram illustrating the acquisition of the projection width of a linear light pattern on automotive paint strips, provided in an embodiment of this application. Figure 6 A flowchart illustrating another embodiment of the automotive paint surface smoothness testing method provided in this application; Figure 7 A flowchart illustrating another embodiment of the automotive paint surface smoothness testing method provided in this application. Figure 8 A flowchart illustrating another embodiment of the automotive paint surface smoothness testing method provided in this application. Figure 9 A block diagram illustrating an embodiment of an automotive paint surface smoothness testing device provided in this application; Figure 10 A block diagram illustrating another embodiment of an automotive paint surface smoothness testing device provided in this application. Figure 11 This is a structural diagram of an automotive paint surface smoothness testing device provided in an embodiment of this application. Detailed Implementation

[0033] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0034] For ease of understanding, the following is an exemplary description of the automotive paint surface smoothness testing equipment provided in the embodiments of this application.

[0035] See Figure 1 This is a schematic diagram of an automotive paint surface smoothness testing device provided in an embodiment of this application. Figure 1 As shown, the device includes a housing 1, a touch screen 2, a bar light source 3, a camera 4, a proximity sensor 5, a lampshade 6, a battery 7, and a chip 8 (integrating memory and a processor).

[0036] The strip light source 3 is exemplarily an LED (Light Emitting Diode) strip light source, used to project strip light onto the car paint surface. This light source emits uniform and stable light, capable of forming clear projected patterns on the car paint surface. Depending on different detection requirements, parameters such as the intensity and color of the strip light can also be adjusted.

[0037] The lampshade 6 is exemplarily made of high-transparency glass, ensuring that the light emitted by the strip light source 3 can penetrate with high fidelity and low loss, maximizing the uniformity and stability of the light, and avoiding light scattering or distortion caused by the lampshade material from affecting the clarity of the projected pattern. At the same time, the high-transparency glass material has good scratch resistance and high-temperature resistance, adapting to various environments that may be encountered during the inspection process and extending the service life of the equipment. This design makes the strip light patterns projected onto the car paint surface more precise, providing a reliable optical basis for the camera 4 to capture clear image data and for the chip 8 to perform subsequent flatness analysis.

[0038] In addition, light boxes ( Figure 1 (Not shown) It can be made of black light-absorbing plastic, which can effectively absorb stray reflected light inside the lamp box and interference light that may enter from the external environment, avoiding secondary reflection or scattering of these useless lights inside the lamp box, thereby further ensuring the purity of the light projected onto the car paint surface and the clarity of the projected texture. This design, together with the high-transparency glass lamp cover, forms a light projection system with stable optical performance, providing more reliable environmental support for the subsequent camera 4 to accurately capture the paint surface image and the chip 8 to perform flatness data processing, improving the anti-interference capability and detection accuracy of the entire detection device.

[0039] The distance sensor 5 is integrated into the strip light source box and is used to detect the distance between the detection device and the paint surface of the car being tested, providing distance data support for the subsequent paint surface smoothness quantification algorithm.

[0040] Camera 4 is used in conjunction with bar light source 3 to capture images of bar light projections on the car's paint surface. For example, camera 4 has high resolution and a high frame rate, enabling it to quickly and clearly capture image details, ensuring that the acquired image quality meets the requirements for subsequent analysis.

[0041] The touch screen 2 is used to display the operation interface, real-time images captured by the camera 4, and the results of analysis and processing (such as orange peel grade information). The touch screen 2 uses a high-definition, high-contrast screen, making it easy for operators to intuitively view the test results.

[0042] Battery 7 powers the entire testing equipment, ensuring it can operate independently in various environments. Battery 7 features low voltage, high capacity, and long battery life, and supports fast charging to improve testing efficiency.

[0043] Chip 8 is the core processing unit of the detection device, integrating a memory and a processor. The memory stores image information captured by the camera and the results calculated by the chip; the processor executes the built-in data processing software to process and analyze the images captured by the camera. This processor possesses powerful computing and image processing capabilities, enabling it to quickly and accurately identify the features of bar-shaped light projection patterns (for example, it can perform preprocessing operations such as noise reduction and enhancement on the captured images, and then extract the key features of the bar-shaped light projection patterns) and calculate the orange peel grade according to a preset algorithm, thereby quantifying the smoothness deviation of the automotive paint surface.

[0044] For example, the orange peel grade is divided into 0-10 levels, where level 0 represents a mirror effect, with the smoothest and flattest surface; the higher the grade, the more obvious the orange peel phenomenon.

[0045] based on Figure 1 The example testing equipment provided in this application embodiment offers a method for testing the smoothness of automotive paint surfaces. The general working principle is as follows: During testing, the strip light source 3 of the testing equipment is vertically aligned with the car paint surface, projecting strip light onto the paint surface to form specific projected patterns. Because the orange peel effect causes microscopic unevenness on the paint surface, these unevennesses will cause the projected patterns of the strip light to be distorted, and the more severe the orange peel effect, the more obvious the distortion of the projected patterns.

[0046] During the inspection, distance sensor 5 acquires the vertical distance between the inspection device and the car paint surface in real time, while camera 4 simultaneously captures bar-shaped light projection images with deformed textures. Built-in chip 8 acquires the distance data and bar-shaped light projection image data, processes and analyzes the images using data processing software, and calculates the orange peel grade of the car paint surface based on the degree and characteristics of the bar-shaped light projection texture, comparing it with a preset sample library. The result is then displayed on touch screen 2. Finally, the image data containing the inspection results can be stored or deleted according to the user's selection.

[0047] The technical solution provided in this application has at least the following beneficial effects: (1) High detection accuracy: By combining bar-shaped light projection texture with advanced image processing algorithms, it can accurately identify different degrees of orange peel phenomenon, accurately judge the orange peel grade, and provide a reliable basis for the quality assessment of automobile paint surface; (2) High detection efficiency: The entire detection process is highly automated, and the process from image acquisition to result display can be completed quickly, which significantly improves detection efficiency and is suitable for large-scale detection on automobile production lines; (3) The results are intuitive: the orange peel grade is directly displayed on the screen, and the operator can understand the quality of the paint surface at a glance, so as to take corresponding measures in a timely manner; (4) Portable and flexible: The device is powered by a battery, is small in size, easy to carry and move, and can be used in different detection scenarios, with high flexibility.

[0048] Figure 2 This is a flowchart illustrating an embodiment of a method for testing the smoothness of automotive paint surfaces provided in this application. Figure 2 As shown, the method includes the following steps: Step 201: Align the bar light source vertically with the car paint surface to project bar light onto the car paint surface, forming a bar light projection on the car paint surface.

[0049] This step is the initial stage of the testing process, and its purpose is to establish optical marks on the paint surface of the vehicle to be tested that can be used for analysis.

[0050] Among them, the light emitted by the strip light source is long and thin. When it shines perpendicularly onto the painted surface, it forms a clear strip of light projection on the surface. For example, Figure 3 This is a schematic diagram of the surface projection of different orange peel grades of automotive paint stripes provided in the embodiments of this application.

[0051] In step 201, the requirement to "align the strip light source perpendicularly to the car's paint surface" is to ensure that the geometry of the projection is only affected by the smoothness of the paint surface itself, without introducing additional geometric distortion due to the angle of incidence. This strip light projection will serve as the direct object for subsequent image acquisition and analysis, and its shape changes carry information about the smoothness of the car's paint surface.

[0052] Step 202: Capture the image of the bar light projection using a camera.

[0053] In this process, the bar light projection formed in step 201 is converted into digital image data that can be processed by a computer by capturing images of the bar light projection through a camera.

[0054] In practice, the camera is aimed at the stripe-shaped light projection area on the car's paint surface and captures an image containing that projection. The captured image should clearly and completely present the shape of the stripe-shaped light projection, including the outlines of its two edges. This image is the foundational data source for all subsequent quantitative analyses, and its quality directly affects the accuracy of the detection results.

[0055] Step 203: Based on the image of the bar light projection, determine the measured width of the light band of the bar light projection.

[0056] The "measured light band width" refers to the geometric width of the striped light projection in the image, perpendicular to its length. Specifically, it corresponds to the vertical distance between the two edges of the striped light projection. This width value is a measurable physical quantity that comprehensively reflects the actual shape of the striped light projection under the current detection conditions (including the current detection distance, the smoothness of the paint surface, etc.).

[0057] Step 204: Obtain the reference light band width, and quantify the flatness deviation of the automotive paint surface based on the measured light band width and the reference light band width.

[0058] This step is used to quantitatively assess the smoothness of the car's paint surface through comparison.

[0059] Among them, "reference light band width" is a benchmark value used for comparison. It represents the width that the strip light projection should have under a certain benchmark condition (such as an ideal flat paint surface, standard detection distance, etc.).

[0060] By comparing the "measured light band width" obtained in step 203 with the "reference light band width" (e.g., calculating the difference, ratio, or other mathematical relationships), a quantitative index reflecting the difference between the two can be obtained. This index is called "smoothness deviation". Its value directly corresponds to the severity of the orange peel effect on the paint surface: the larger the deviation, the worse the smoothness of the paint surface and the more obvious the orange peel phenomenon; the smaller the deviation, the closer the paint surface is to a smooth state.

[0061] The technical solution provided in this application has the following beneficial effects: (1) A strip light source is used to project a strip light vertically onto the car paint surface, forming a strip light projection that can be inspected on the paint surface; the image of the projection is acquired by a camera; the measured light band width is determined based on the image; finally, the flatness deviation of the paint surface is quantified by obtaining the reference light band width and comparing it with the measured light band width. Since the entire inspection process is completed automatically by the equipment, on the one hand, no manual visual judgment is required, thus eliminating the subjectivity and human error of traditional manual inspection, and realizing an objective and repeatable quantitative assessment of the flatness of the paint surface; on the other hand, no manual intervention is required, which greatly shortens the single inspection time and improves the inspection efficiency, especially suitable for the large-volume and fast-paced inspection needs on the automotive production line; furthermore, both optical projection and image acquisition are non-contact methods, avoiding the risk of damage to the paint surface during the inspection process.

[0062] (2) This scheme first converts the optical projection on the paint surface into a digital image through image acquisition, and then extracts the measurable geometric quantity of the measured light band width from it; then, by introducing a reference light band width as a comparison benchmark, the measured width is compared with the reference width, and finally the visual perception of paint surface smoothness is converted into a numerical width offset. This process transforms the originally vague subjective judgment of "orange peel severity" into a quantitative indicator with clear physical meaning, which significantly improves the precision and accuracy of the detection.

[0063] (3) This solution only requires a single linear light source and a conventional camera to achieve detection, without the need for a composite light source system or complex image fusion algorithms. At the data processing level, comparative analysis is performed by extracting the one-dimensional geometric quantity of the light band width, without the need for additional complex algorithms, which significantly reduces the complexity of image processing and the consumption of computing resources. This application achieves lightweight, low-cost and easy-to-deploy detection system while ensuring detection accuracy.

[0064] Figure 3 A flowchart illustrating an embodiment of another method for testing the smoothness of automotive paint surfaces provided in this application. Figure 3 The process shown is in Figure 2 Based on the illustrated process, an exemplary implementation for determining the measured light band width of a bar-shaped light projection based on an image is described. For example... Figure 3 As shown, the method includes the following steps: Step 301: Extract multiple first edge pixels on the first edge and multiple second edge pixels on the second edge of the bar light projection from the image; wherein the first edge and the second edge are two opposite edges of the bar light projection in the width direction.

[0065] The purpose of this step is to locate and extract the pixels that constitute the two edges of the strip light projection from the acquired image.

[0066] like Figure 4 As shown, in the image of the bar-shaped light projection, the projection appears as a bright band of light, with two distinct edges forming at its boundary with the surrounding dark background. These two edges are opposite each other in the width direction and are defined as the first edge and the second edge, respectively. This step uses image processing techniques (such as edge detection algorithms) to identify the pixels located on these two edges and assigns them as "first edge pixels" and "second edge pixels," respectively. The spatial distribution of these pixels reflects the actual shape of the bar-shaped light projection.

[0067] In one embodiment, extracting a plurality of first edge pixels on a first edge and a plurality of second edge pixels on a second edge of a bar-shaped light projection from an image includes: converting the image to a grayscale image; identifying pixels in the grayscale image whose grayscale values ​​are greater than a preset threshold as edge pixels; and dividing the edge pixels into first edge pixels located on the first edge and second edge pixels located on the second edge according to their positions in the width direction of the bar-shaped light projection.

[0068] In this embodiment, the original color image captured by the camera is first converted into a grayscale image. The grayscale value (0-255) of each pixel in the grayscale image represents the brightness of that pixel. The purpose of this step is to simplify the amount of data for subsequent processing and eliminate interference from color information, allowing image analysis to focus on brightness changes.

[0069] For example, the gray value Gray of each pixel in a grayscale image is calculated according to the following formula: Gray = 0.299R + 0.587G + 0.114B Where R represents the grayscale value of the pixel in the red channel, G represents the grayscale value of the pixel in the green channel, and B represents the grayscale value of the pixel in the blue channel. This formula is a standard grayscale conversion formula, which can reasonably map color information into a single brightness value based on the differences in human eye sensitivity to different colors.

[0070] See Figure 4 This is a schematic diagram illustrating the acquisition of grayscale values ​​of pixels in a linear light projection image of automotive paint stripes, provided in an embodiment of this application. Figure 4 As shown, the pixels within the bar-shaped light projection area have higher grayscale values, while the pixels in the background area have lower grayscale values, creating a sharp brightness contrast and providing favorable conditions for subsequent threshold-based edge pixel recognition.

[0071] In a grayscale image, the area of ​​the bar-shaped light projection is bright, while the background area is dim. Therefore, the edges are where the grayscale values ​​change abruptly. Accordingly, this embodiment uses a threshold method for identification: a grayscale threshold is set, and all pixels with grayscale values ​​greater than this threshold are marked as "edge pixels." This process allows for the rapid and complete capture of all high-brightness pixels associated with the bar-shaped light projection.

[0072] Then, by analyzing the coordinate positions of the identified edge pixels in the image (e.g., scanning along a direction perpendicular to the length of the stripe of light), they can be divided into two groups: pixels located on one side of the light stripe are classified as "first edge pixels," and pixels located on the other side of the light stripe are classified as "second edge pixels." Thus, two sets of edge points corresponding to the two edges of the stripe of light projection have been identified from the image.

[0073] This embodiment uses a unified threshold operation and a geometrically based division to accurately and efficiently extract the pixels of the two edges of the strip light projection. The algorithm is robust and easy to implement, laying a solid foundation for subsequent accurate fitting of the two edge lines.

[0074] Step 302: Perform line fitting on multiple first edge pixels and multiple second edge pixels respectively to obtain the first edge fitting line and the second edge fitting line.

[0075] The purpose of this step is to fit the discrete edge pixels extracted in step 301 into a straight line representation.

[0076] Due to the orange peel effect on the paint surface, the edges of the striped light projection are usually curved or irregular. To quantify this irregularity, a "baseline" is established—the ideal straight line position the edge should have if the paint surface were perfectly smooth. This step uses a straight line fitting algorithm (e.g., least squares method) to fit the pixels in the first and second edge pixel sets respectively, resulting in two straight lines, called the first edge fitting line and the second edge fitting line. These two lines represent the statistically significant "main trend" or "average position" of the first and second edges.

[0077] See Figure 5 The example shows the dashed line as the edge fitting line.

[0078] Step 303: Determine the vertical distance between the first edge fitting line and the second edge fitting line as the measured width of the strip light projection.

[0079] After obtaining the two edge-fitted straight lines, this step calculates the vertical distance between them. This distance geometrically represents the "average width" or "subject width" of the stripe projection in the image, referred to as the "measured light band width." This width value is a comprehensive geometric feature quantity that incorporates information about the paint surface smoothness at the current detection distance.

[0080] Through steps 301 to 303, the measured width of the light band of the light projection is extracted from the image of the light projection. This measured width of the light band is a key feature that can be used for subsequent quantitative comparison.

[0081] Figure 6 This is a flowchart illustrating another embodiment of a method for testing the smoothness of automotive paint surfaces provided in this application. Figure 6 As shown, the method includes the following steps: Step 601: Align the bar light source vertically with the car paint surface and project bar light onto the car paint surface to form a bar light projection on the car paint surface.

[0082] Step 602: Capture the image of the bar light projection using a camera.

[0083] Step 603: Based on the image of the bar light projection, determine the measured width of the light band of the bar light projection.

[0084] For detailed explanations of steps 601 to 603, please refer to the explanations in the above embodiments, which will not be repeated here.

[0085] Step 604: Obtain the standard light band width at the preset distance as the reference light band width.

[0086] The standard light band width at the preset distance is the light band width of the strip light projection formed when a strip light source projects strip light onto a flat mirror surface at the preset distance.

[0087] Step 605: Obtain the measured distance between the bar light source and the car paint surface.

[0088] Step 606: Determine the difference between the measured optical band width and the reference optical band width.

[0089] Step 607: Based on the measured distance and the preset distance, the above difference is corrected to obtain the width offset; wherein, the width offset is used to quantify the flatness deviation of the car paint surface.

[0090] For ease of understanding, steps 604 to 607 are explained uniformly: First, to quantify the smoothness of the car paint surface, a clear benchmark is obtained. Step 604 establishes this benchmark using a pre-defined standard condition: at a fixed preset distance (e.g., 0.5 meters), the same strip light source is projected onto an ideally smooth mirror surface, and the width of the resulting strip light projection is measured and defined as the "standard light band width." This width represents the theoretical width that should exist on an ideally smooth surface at a standard distance (i.e., a fixed preset distance, such as 0.5 meters), serving as a reference value for subsequent actual width measurements.

[0091] However, in actual testing, the distance between the testing equipment and the car paint surface (the measured distance) often differs from the preset distance, and the width of the light band itself changes with distance (larger when closer and smaller when farther away). Therefore, directly comparing the difference between the measured light band width and the reference light band width includes both the deformation caused by the smoothness of the paint surface and the geometric scaling effect caused by different distances, and cannot directly reflect the true smoothness deviation.

[0092] Therefore, step 605 obtains the measured distance at the time of detection through the distance sensor, providing a basis for subsequent calibration. Further, in step 606, the original difference between the measured light band width and the reference light band width is first calculated. This difference is an original quantity that combines "flatness information" and "distance influence".

[0093] Finally, step 607 utilizes the principle of similar triangles in optical imaging to correct the original difference based on the ratio between the measured distance and the preset distance. By converting the original difference to an equivalent value at the preset distance, the geometric scaling effect caused by different distances can be eliminated, thus obtaining a quantitative indicator that purely reflects the smoothness of the paint surface: width offset. The magnitude of this width offset directly corresponds to the severity of the orange peel effect on the paint surface: the larger the offset, the greater the difference between the paint surface and the ideal smooth mirror surface, and the worse the smoothness; conversely, the smaller the offset, the closer the paint surface is to a smooth state.

[0094] The original difference is corrected according to the following formula: ; in, This is the width offset. To measure the actual optical band width, For reference optical band width, For actual measured distance, This is the preset distance.

[0095] Figure 6 The process shown is in Figure 2 Based on the process shown, by unifying the light band width data measured at different distances to a comparable scale, a stable, accurate and physically meaningful flatness quantification index is finally output.

[0096] Figure 7 This is a flowchart illustrating another embodiment of the automotive paint surface smoothness testing method provided in this application. Figure 7 As shown, the method includes the following steps: Step 701: Align the bar light source vertically with the car paint surface to project bar light onto the car paint surface, forming a bar light projection on the car paint surface.

[0097] Step 702: Capture the image of the bar light projection using a camera.

[0098] Step 703: Based on the image of the bar light projection, determine the measured width of the light band of the bar light projection.

[0099] For detailed explanations of steps 701 to 703, please refer to the explanations in the above embodiments, which will not be repeated here.

[0100] Step 704: Obtain the standard light band width at the preset distance.

[0101] Step 705: Obtain the measured distance between the bar light source and the car paint surface.

[0102] Step 706: Based on the measured distance and the preset distance, the standard light band width at the preset distance is corrected to obtain the reference light band width.

[0103] Step 707: Determine the difference between the measured light band width and the reference light band width as the width offset; whereby the width offset is used to quantify the flatness deviation of the automotive paint surface.

[0104] For ease of understanding, steps 704 to 707 are explained uniformly: First, it should be noted that steps 704 to 707 above constitute a different... Figure 6 Another implementation approach of the illustrated embodiment is as follows: First, a benchmark is established, then the benchmark is dynamically adjusted according to the measured distance, and finally compared with the measured value to obtain a quantifiable index of flatness deviation. Specifically, step 704 first establishes a benchmark value: the standard light strip width at a preset distance. This value is obtained by projecting the same strip light source onto an ideally flat mirror surface at a fixed preset distance (e.g., 0.5 meters) and measuring the width of the resulting strip light projection.

[0105] However, in actual testing, the measured distance between the testing equipment and the car paint surface often differs from the preset distance. Because the light band width itself has a geometric characteristic of being larger when closer and smaller when farther away, directly comparing the standard light band width at the preset distance with the measured light band width introduces interference caused by distance differences. Therefore, it is necessary to "adjust" the reference value to the same distance condition as the actual measurement.

[0106] Accordingly, step 706 corrects the standard light band width at the preset distance based on the ratio between the measured distance and the preset distance, obtaining a reference light band width corresponding to the current measured distance. This correction process essentially maps the reference value from the "preset distance" to the "measured distance," making the reference light band width and the measured light band width on the same distance scale, thus achieving direct comparability.

[0107] The standard light band width at the preset distance is corrected according to the following formula: ; in, This is the reference light band width obtained after correction, corresponding to the measured distance.

[0108] Finally, step 707 compares the measured optical band width with the corrected reference optical band width, calculates the difference between the two, and determines the difference as the width offset.

[0109] Since the reference light band width has been distance-corrected and is at the same distance as the measured light band width, this difference purely reflects the difference between the paint surface smoothness and the ideal smooth surface, and no longer includes the influence of distance factors. The magnitude of this width offset directly corresponds to the severity of the paint surface orange peel effect: the larger the offset, the worse the paint surface smoothness; the smaller the offset, the closer the paint surface is to a smooth state.

[0110] Figure 7 The process shown is in Figure 2 Based on the process shown, the reference light band width and the measured light band width are dynamically adjusted according to the measured distance to make them the same distance scale, which simplifies the subsequent comparison logic. The difference obtained directly is the pure flatness deviation index.

[0111] Figure 8 This is a flowchart illustrating another embodiment of the automotive paint surface smoothness testing method provided in this application. Figure 8 As shown, the method includes the following steps: The bar light source is moved step by step along a direction perpendicular to the length of the bar light. Each time it is moved, the following steps are performed: Step 801: Align the bar light source vertically with the car paint surface and project bar light onto the car paint surface to form a bar light projection on the car paint surface.

[0112] Step 802: Capture the image of the bar light projection using a camera.

[0113] Step 803: Based on the image of the bar light projection, determine the measured width of the light band of the bar light projection.

[0114] Step 804: Obtain the reference light band width, and based on the measured light band width and the reference light band width, obtain the width offset; whereby the width offset is used to quantify the flatness deviation of the automotive paint surface.

[0115] Step 805: Compare the width offset with the preset flatness grade model to determine the flatness grade of the car paint surface.

[0116] In practical applications, automotive paint surfaces are typically panels of a certain area (such as engine hoods, doors, etc.), and a single inspection can only cover a localized area within the projection range of the strip light. To achieve a comprehensive evaluation of the entire paint surface area to be tested, this application provides a scanning inspection mode. The core idea is to move the inspection device so that the strip light sequentially covers different locations on the paint surface, and perform a complete inspection process at each location, thereby obtaining the flatness distribution information of the entire area.

[0117] The step of moving the strip light source gradually along a direction perpendicular to its length refers to the operator holding the testing device and moving the strip light source continuously or in steps along a direction perpendicular to its extension (i.e., parallel to the width of the light band). Each time it moves to a new position, the strip light projects onto an uncovered area of ​​the paint surface, forming a new strip light projection. Subsequently, for each testing position, steps 801 to 807 are executed sequentially to obtain the flatness evaluation result of that local area. In this way, full coverage testing of the entire automotive paint panel can be achieved, avoiding the limitations of single-point measurement.

[0118] For detailed descriptions of steps 801 to 806, please refer to the relevant descriptions in the above embodiments, which will not be repeated here.

[0119] The purpose of step 807 is to convert the width offset calculated in step 806 into a flatness level with clear physical meaning, making the test results more intuitive and easy to understand.

[0120] To achieve this transformation, a smoothness rating model is established beforehand. The process of establishing this model is as follows: First, during the offline phase (i.e., the model training phase), a large number of automotive paint surface samples with different orange peel levels were collected. These samples covered a variety of typical surface states, ranging from mirror finish (level 0) to severe orange peel (level 10). Using the detection method described in this application, each sample was detected at a standard distance, and its corresponding width offset was obtained.

[0121] Then, through data analysis, a correspondence between width offset and orange peel grade is established. This correspondence can be expressed in the form of a lookup table, fitted curve, classification boundary, or regression model. For example, the numerical range of width offset can be divided into several intervals, each interval corresponding to an orange peel grade; or a continuous function mapping between width offset and grade can be established. This correspondence constitutes the "smoothness grade model" described in this application.

[0122] In actual testing, after obtaining the width offset of the current detection position in step 806, step 807 inputs this offset into a pre-established flatness level model. By comparison or calculation, the flatness level corresponding to that position can be automatically determined. For example, the width offset can be compared with a preset threshold or level boundary in the model, and the corresponding level value can be directly output.

[0123] According to one embodiment of this application, the flatness level adopts a grading standard of 0 to 10, where: level 0 represents a mirror effect, the surface is the smoothest and flattest, and there is no orange peel phenomenon visible to the naked eye; as the level increases, the orange peel phenomenon gradually worsens; level 10 represents the most severe orange peel phenomenon, and the surface shows obvious orange peel texture.

[0124] This grading method aligns with standard practices in the automotive painting industry, allowing quality inspectors, production line operators, and end-users to intuitively understand test results without the need to interpret complex numerical values. Test results can be directly displayed on a touchscreen in digital form, and users can also choose to store test images with grade labels, creating a traceable quality record.

[0125] Figure 8 The illustrated embodiment is in Figure 2 In addition to the illustrated embodiments, the beneficial effects also include: (1) Full coverage inspection: By moving the scanning, the entire panel of the car paint is evaluated regionally, overcoming the limitations of single-point measuring instruments; (2) High degree of automation: Image acquisition, width extraction, deviation quantification and grade determination are automatically performed at each detection position, resulting in high detection efficiency; (3) Intuitive results: The technical width offset is converted into the industry-standard 0-10 level, which makes it easier for people in different positions to understand and apply.

[0126] Figure 9 This is a block diagram illustrating an embodiment of an automotive paint surface smoothness testing device provided in this application. Figure 9 As shown, the device includes: The projection module 91 is used to vertically align the strip light source with the car paint surface and project strip light onto the car paint surface to form a strip light projection on the car paint surface. Image acquisition module 92 is used to acquire images of the bar light projection through a camera; Measurement module 93 is used to determine the measured width of the strip light projection based on the image; Reference value acquisition module 94 is used to acquire the reference optical band width; The quantization module 95 is used to quantify the flatness deviation of the automotive paint surface based on the measured light band width and the reference light band width.

[0127] In one possible implementation, the measurement module 93 includes: An edge pixel extraction unit is used to extract multiple first edge pixels on the first edge and multiple second edge pixels on the second edge of the bar-shaped light projection from the image; wherein the first edge and the second edge are two edges of the bar-shaped light projection that are opposite each other in the width direction; An edge fitting unit is used to perform straight line fitting on the plurality of first edge pixels and the plurality of second edge pixels respectively to obtain a first edge fitting line and a second edge fitting line; The distance calculation unit is used to determine the vertical distance between the first edge fitting line and the second edge fitting line, which is used as the measured light band width of the strip light projection.

[0128] In one possible implementation, the edge pixel extraction unit is specifically used for: Convert the image to a grayscale image; In the grayscale image, pixels with grayscale values ​​greater than a preset threshold are identified as edge pixels. Based on the position of the edge pixels in the width direction of the strip light projection, the edge pixels are divided into a first edge pixel located on the first edge and a second edge pixel located on the second edge.

[0129] In one possible implementation, the reference value acquisition module 94 is specifically used for: Obtain the standard light band width at a preset distance as the reference light band width; wherein, the standard light band width at the preset distance is the light band width of the strip light projection formed when the strip light source projects strip light onto the flat mirror surface at the preset distance.

[0130] In one possible implementation, the quantization module 95 includes: A ranging unit is used to obtain the measured distance between the bar light source and the car paint surface; The difference calculation unit is used to determine the difference between the measured optical band width and the reference optical band width; The first correction unit is used to correct the difference based on the measured distance and the preset distance to obtain a width offset; wherein the width offset is used to quantify the flatness deviation of the car paint surface.

[0131] In one possible implementation, the first correction unit is specifically used for: The difference is corrected according to the following formula: ; in, This is the width offset. The measured optical band width is... The reference light band width is, The measured distance is... The preset distance is [the distance].

[0132] In one possible implementation, the reference value acquisition module 94 includes: A ranging unit is used to obtain the measured distance between the bar light source and the car paint surface; A standard value acquisition unit is used to acquire the standard light band width at a preset distance; wherein, the standard light band width at the preset distance is the light band width of the strip light projection formed when the strip light source projects strip light onto a flat mirror surface at the preset distance; The second correction unit is used to correct the standard light band width at the preset distance based on the measured distance and the preset distance, so as to obtain the reference light band width.

[0133] In one possible implementation, the quantization module 95 is specifically used for: The difference between the measured light band width and the reference light band width is determined as the width offset; wherein, the width offset is used to quantify the flatness deviation of the automotive paint surface.

[0134] In one possible implementation, see Figure 10 The apparatus provided in this application embodiment further includes: The rating module 96 is used to compare the width offset with a preset smoothness rating model to determine the smoothness rating of the car paint surface.

[0135] The control module 97 is used to move the bar light source step by step along a direction perpendicular to the length of the bar light. Each time it moves, it executes the steps of vertically aligning the bar light source with the car paint surface, projecting the bar light onto the car paint surface, and the subsequent steps.

[0136] In another embodiment of this application, an automotive paint surface smoothness testing device is also provided, including a strip light source 1150, a camera 1160, a processor 1110, a communication interface 1120, a memory 1130 and a communication bus 1140, wherein the processor 1110, the communication interface 1120 and the memory 1130 communicate with each other through the communication bus 1140. Memory 1130 is used to store computer programs; A strip light source 1150 is used to project strip light onto the paint surface of a car to form a strip light projection on the paint surface of the car; Camera 1160 is used to capture images of the bar-shaped light projection; The processor 1110 is used to execute the program stored in the memory to implement the automotive paint surface smoothness detection method described in any of the foregoing method embodiments.

[0137] The electronic device provided in this application embodiment enables the processor to perform an objective and repeatable quantitative assessment of the smoothness of the paint surface by executing the program stored in the memory. This eliminates the subjectivity and human error of traditional manual inspection, significantly shortens the single inspection time, improves inspection efficiency, and avoids the risk of damage to the paint surface during the inspection process.

[0138] The communication bus 1140 mentioned in the above electronic device can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. This communication bus 1140 can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 11 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0139] The communication interface 1120 is used for communication between the above-mentioned electronic device and other devices.

[0140] The memory 1130 may include random access memory (RAM) or non-volatile memory, such as at least one disk storage device. Optionally, the memory may also be at least one storage device located remotely from the aforementioned processor.

[0141] The processor 1110 mentioned above can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0142] In another embodiment of this application, a computer-readable storage medium is provided, on which a program for a method for detecting the smoothness of automotive paint surfaces is stored. When the program for detecting the smoothness of automotive paint surfaces is executed by a processor, it implements the steps of the method for detecting the smoothness of automotive paint surfaces described in any of the foregoing method embodiments.

[0143] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0144] The above description is merely a specific embodiment of this application, enabling those skilled in the art to understand or implement this application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features claimed herein.

Claims

1. A method for detecting the flatness of a paint surface of an automobile, characterized by, include: A bar light source is vertically aligned with the car paint surface to project bar light onto the car paint surface, forming a bar light projection on the car paint surface; The image of the bar light projection is captured by a camera; Based on the image, the measured width of the strip light projection is determined; Obtain the reference light band width, and quantify the smoothness deviation of the automotive paint surface based on the measured light band width and the reference light band width.

2. The automobile paint surface flatness detection method according to claim 1, characterized by, Determining the measured width of the striped light projection based on the image includes: Extract a plurality of first edge pixels on the first edge and a plurality of second edge pixels on the second edge of the bar-shaped light projection from the image; wherein the first edge and the second edge are two opposite edges of the bar-shaped light projection in the width direction; Line fitting is performed on the plurality of first edge pixels and the plurality of second edge pixels respectively to obtain the first edge fitting line and the second edge fitting line; The vertical distance between the first edge fitting line and the second edge fitting line is determined as the measured width of the strip light projection.

3. The automobile paint surface flatness detection method according to claim 2, characterized by, Extracting multiple first edge pixels on the first edge and multiple second edge pixels on the second edge of the bar-shaped light projection from the image includes: Convert the image to a grayscale image; In the grayscale image, pixels with grayscale values ​​greater than a preset threshold are identified as edge pixels. Based on the position of the edge pixels in the width direction of the strip light projection, the edge pixels are divided into a first edge pixel located on the first edge and a second edge pixel located on the second edge.

4. The automobile paint surface flatness detection method according to claim 1, characterized by, The process of obtaining the reference optical band width includes: Obtain the standard light band width at a preset distance as the reference light band width; wherein, the standard light band width at the preset distance is the light band width of the strip light projection formed when the strip light source projects strip light onto the flat mirror surface at the preset distance.

5. The automobile paint surface flatness detection method according to claim 4, characterized by, The method of quantifying the smoothness deviation of the automotive paint surface based on the measured light band width and the reference light band width includes: Obtain the measured distance between the strip light source and the car paint surface; Determine the difference between the measured optical band width and the reference optical band width; Based on the measured distance and the preset distance, the difference is corrected to obtain the width offset; wherein, the width offset is used to quantify the flatness deviation of the car paint surface.

6. The automobile paint surface flatness detection method according to claim 5, characterized by, The step of correcting the difference based on the measured distance and the preset distance includes: The difference is corrected according to the following formula: ； wherein, is the width offset, is the measured light band width, is the reference light band width, is the measured distance, is the preset distance.

7. The automobile paint surface flatness detection method according to claim 1, characterized by, The process of obtaining the reference optical band width includes: Obtain the measured distance between the strip light source and the car paint surface; Obtain the standard light band width at a preset distance; wherein, the standard light band width at the preset distance is the light band width of the strip light projection formed when the strip light source projects strip light onto a flat mirror surface at the preset distance; Based on the measured distance and the preset distance, the standard light band width at the preset distance is corrected to obtain the reference light band width.

8. The method of claim 7, wherein the step of detecting the flatness of the automobile paint surface is performed by using a light source and a camera. The method of quantifying the smoothness deviation of the automotive paint surface based on the measured light band width and the reference light band width includes: The difference between the measured light band width and the reference light band width is determined as the width offset; wherein, the width offset is used to quantify the flatness deviation of the automotive paint surface.

9. The method of claim 5 or 8, wherein The method further includes: The width offset is compared with a preset smoothness grade model to determine the smoothness grade of the car paint surface.

10. The method for testing the smoothness of automotive paint surfaces according to claim 1, characterized in that, The method further includes: The bar light source is moved step by step along a direction perpendicular to the length of the bar light. Each time it is moved, the steps of vertically aligning the bar light source with the car paint surface, projecting the bar light onto the car paint surface, and subsequent steps are performed.

11. A device for testing the smoothness of automotive paint surfaces, characterized in that, include: The projection module is used to vertically align the strip light source with the car paint surface and project strip light onto the car paint surface to form a strip light projection on the car paint surface; The image acquisition module is used to acquire images of the bar light projection via a camera; A measurement module is used to determine the measured width of the strip light projection based on the image; The quantization module is used to obtain the reference light band width and quantify the smoothness deviation of the automotive paint surface based on the measured light band width and the reference light band width.

12. A device for testing the smoothness of automotive paint surfaces, characterized in that, It includes a bar light source, a camera, a processor, a communication interface, a memory, and a communication bus. The processor, the communication interface, and the memory communicate with each other through the communication bus. Memory, used to store computer programs; A strip light source is used to project strip light onto the paint surface of a car to form a strip light projection on the paint surface of the car; A camera is used to capture images of the bar-shaped light projection; The processor, when executing a program stored in the memory, implements the automotive paint surface smoothness testing method according to any one of claims 1-10.

13. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a program for a method of detecting the smoothness of automotive paint surfaces, which, when executed by a processor, implements the steps of the method of detecting the smoothness of automotive paint surfaces according to any one of claims 1-10.

Images