A Visual Inspection Method for Defects of Automobile Interior Parts

Abstract

The present invention discloses a visual inspection method for defects of automotive interior parts, which relates to the technical field of visual inspection, and includes a visual inspection module, a light interference correction module, and a brightness analysis module. The visual inspection module is used to scan and photograph the inner contour surface of the entire starry sky ceiling. The light interference correction module is used to correct the interference of the light between adjacent LED lights on the detection result of brightness defects. The brightness analysis module is used to analyze the obtained LED light brightness data, determine whether there are defects and make improvements. The visual inspection module includes an image acquisition unit, an image processing module, and a position recognition module. The image acquisition unit is electrically connected to the image processing module, and the image processing module is electrically connected to the position recognition module. The image acquisition unit uses a camera to capture the inner contour image of the starry sky ceiling, and the image processing module is used to process the acquired image. The present invention has the characteristics of accurate detection.

Description

Technical Field

[0001] The present invention relates to the technical field of visual detection, and specifically to a method for visual detection of defects in automotive interior parts. Background Art

[0002] The starry sky roof interior of a car is a special automotive interior design. Usually, through LED lights or fiber optic technology, the effect of a starry sky is simulated on the car roof. This design is commonly used in luxury models to enhance the atmosphere and aesthetics inside the vehicle. During the actual use of the starry sky roof for lighting defect testing, in order to verify the lighting effect, an image scanning method is used to analyze the brightness of each LED light on the starry sky roof, so as to determine whether there are brightness defects.

[0003] In order to more realistically simulate the natural state of the starry sky, the brightness changes of the LED lights are usually random, and the position distribution of the LED lights will be adjusted according to the personalized needs of customers. During the existing lighting tests, a very small part of the light of the LED lights shines on adjacent LED lights, resulting in a higher test result of the brightness of the adjacent LED lights. The degree of deviation is related to the number and distance of the surrounding lit lights, and the detection result is inaccurate. Therefore, it is necessary to design an accurate visual detection method for defects in automotive interior parts. Summary of the Invention

[0004] The purpose of the present invention is to provide a method for visual detection of defects in automotive interior parts to solve the problems raised in the above background art.

[0005] To solve the above technical problems, the present invention provides the following technical solution: A method for visual detection of defects in automotive interior parts. This method works using a detection system. The detection system includes a visual detection module, a lighting interference correction module, and a brightness analysis module. The visual detection module is used to scan and photograph the inner contour surface of the entire starry sky roof. The lighting interference correction module is used to correct the interference of the light between adjacent LED lights on the detection result of brightness defects. The brightness analysis module is used to analyze the obtained LED light brightness data, determine whether there are defects and make improvements.

[0006] According to the above technical solution, the visual detection module includes an image acquisition unit, an image processing module, and a position recognition module. The image acquisition unit is electrically connected to the image processing module, and the image processing module is electrically connected to the position recognition module. The image acquisition unit uses a camera to capture the inner contour image of the starry sky roof. The image processing module is used to process the acquired image, including image denoising and identifying LED lights. The position recognition module is used to mark the positions of each LED light in a plane rectangular coordinate system;

[0007] The light interference correction module includes an interference calculation module, a correction algorithm module, and a feedback mechanism module. The interference calculation module is electrically connected to the image processing module and the position recognition module. The correction algorithm module is electrically connected to the interference calculation module and the feedback mechanism module. The interference calculation module is used to calculate the interference degree between each LED based on the brightness and position of adjacent LED lights, and realize the modeling of interference factors. The correction algorithm module is used to correct the appropriate brightness of each LED light according to the interference calculation result. The feedback mechanism module is used to adjust the brightness by controlling the current of the LED light and provide real-time feedback on the adjustment result;

[0008] The brightness analysis module includes a data acquisition module, a statistical analysis module, and an anomaly marking module. The data acquisition module is electrically connected to the image processing module. The data acquisition module is electrically connected to the statistical analysis module. The statistical analysis module is electrically connected to the anomaly marking module. The anomaly marking module is electrically connected to the correction algorithm module. The data acquisition module is used to collect the brightness and position data of each LED light to form a database. The statistical analysis module is used to perform statistical analysis on the collected data and calculate the uniformity of the brightness of all LED lights. The anomaly marking module is used to set a brightness threshold to mark the potentially defective LED lights.

[0009] According to the above technical solution, the working method of the system is as follows:

[0010] S1. Use the camera in the image acquisition unit to capture the inner contour image of the starry sky ceiling, generate the original image data, and prepare for subsequent processing;

[0011] S2. Denoise the acquired image and identify the LED lights in the image processing module, and extract the clear LED light features through the image processing algorithm;

[0012] S3. Based on the processed image, mark the positions of all LED lights on the plane rectangular coordinate system to form the light position information, and calculate the brightness of each LED light;

[0013] S4. Collect the brightness of each LED light combined with the position information, calculate the interference degree between adjacent LED lights, and construct an interference factor model;

[0014] S5. Calculate the brightness uniformity of all LED lights and mark the defective LED lights;

[0015] S6. Determine the appropriate brightness of each LED light according to the interference calculation result and the defective LED lights, and adjust the current of the LED light in real time through the feedback mechanism module to achieve the preset brightness.

[0016] According to the above technical solution, in S3, the specific method for forming the light position information is as follows: Mark the positions of each LED lamp using coordinates to form a set of position coordinates \(\{(x1,y1), (x2,y2), \ldots, (x n , y n )\}, where \(x\) is the abscissa of the LED lamp, \(y\) is the ordinate of the LED lamp, and \(n\) is the number of LED lamps;

[0017] The specific method for calculating the brightness of each LED lamp is as follows: Continuously collect several inner contour images of the starry sky ceiling with a certain LED lamp on, and average the color values of the images. Divide the brightness \(l\) according to the average color value of a certain LED in the collected images. The brighter the image color value, the greater \(l\) increases proportionally, forming a set of brightness \(\{l1, l2, \ldots, l n \}.

[0018] According to the above technical solution, in S4, the specific method for constructing the interference factor model is as follows:

[0019] S4-1. In the image where a certain LED lamp is on, determine the influence range of the LED lamp according to the brightness of the LED lamp. The greater the brightness of the LED lamp, the greater the influence range increases proportionally. The influence range is specifically \(\alpha l i , where \(\alpha\) is the influence range coefficient of brightness and \(i\) is the serial number of a certain LED lamp;

[0020] S4-2. Calculate the straight-line distance \(H\) between the position coordinates of each LED lamp. Among them, the straight-line distance between two LED lamps with serial numbers \(i\) and \(k\)

[0021] S4-3. When calculating the interference degree of a certain LED lamp, only the situation where the position coordinates of this LED lamp are within the respective influence ranges of other LED lamps needs to be considered. If it exceeds the respective influence ranges of other LED lamps, no interference consideration is required. That is, only when \(H ik \lt \alpha l i , the interference degree between the LED lamps with serial numbers \(i\) and \(k\) needs to be considered;

[0022] S4-4. Correct the brightness \(l i of a certain LED lamp with serial number \(i\). Since the brightness of the light usually follows the inverse square law as the distance increases, the corrected brightness where \(\beta\) is the attenuation coefficient of distance with respect to brightness, is the influence of the brightness of the LED lamp with serial number \(k\) on \(l i , and \(m\) is the number of LED lamps that affect the LED lamp with serial number \(i\).

[0023] According to the above technical solution, in S5, the specific method for marking the defective LED lamps is as follows: Let the appropriate light brightness range be \([lmin to l max , among [l min to l max , some LED lights with a corrected brightness l it will be marked as defective, while others have normal brightness. Only the brightness of the marked defective LED lights needs to be adjusted.

[0024] According to the above technical solution, in step S6, the method for determining the appropriate brightness of each LED light is as follows: when the corrected brightness l it > l max , the brightness of the LED light with serial number i needs to be lowered to within [l min to l max , and the specific brightness reduction When the corrected brightness l it < l min , the specific brightness increase

[0025] According to the above technical solution, in step S6, the specific method for adjusting the current of the LED lights in real time through the feedback mechanism module is as follows: by changing the current I i of the LED light with serial number i to adjust the brightness, and the current change value ΔI i = I i ±μΔl i , where μ is the conversion coefficient between current and brightness, positive for brightness increase and negative for brightness decrease;

[0026] After the adjustment is completed, the brightness of each LED light is detected again. If it is within [l min to l max , no adjustment is required. If the adjusted brightness change is too large, the brightness is changed back from the adjusted brightness to the original brightness and adjusted according to the dichotomy method, that is, the brightness change is positive for brightness increase and negative for brightness decrease.

[0027] Compared with the prior art, the beneficial effects achieved by the present invention are as follows: during the process of testing the lighting defects of the star ceiling, the present invention records the position coordinates and preset brightness of each LED light, calculates the interference degree of adjacent LED lights, and thus makes targeted corrections to the actual test results, with accurate detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] The drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation to the present invention. In the drawings:

[0029] Figure 1It is a schematic diagram of the overall module structure of the present invention. Specific embodiments

[0030] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0031] Please refer to Figure 1 , the present invention provides a technical solution: a method for visual inspection of defects in automotive interior parts. This method uses a detection system for operation. The detection system includes a visual detection module, a light interference correction module, and a brightness analysis module. The visual detection module is used to scan and photograph the inner contour surface of the entire starry sky roof. The light interference correction module is used to correct the interference of the light between adjacent LED lights on the detection result of brightness defects. The brightness analysis module is used to analyze the obtained LED light brightness data, determine whether there are defects and make improvements;

[0032] The visual detection module includes an image acquisition unit, an image processing module, and a position recognition module. The image acquisition unit is electrically connected to the image processing module, and the image processing module is electrically connected to the position recognition module. The image acquisition unit uses a camera to capture the inner contour image of the starry sky roof. The image processing module is used to process the acquired image, including image denoising and identifying LED lights. The position recognition module is used to mark the positions of each LED light in the plane rectangular coordinate system;

[0033] The light interference correction module includes an interference calculation module, a correction algorithm module, and a feedback mechanism module. The interference calculation module is electrically connected to the image processing module and the position recognition module. The correction algorithm module is electrically connected to the interference calculation module and the feedback mechanism module. The interference calculation module is used to calculate the interference degree between each LED according to the brightness and position of adjacent LED lights, and realize the modeling of interference factors. The correction algorithm module is used to correct the appropriate brightness of each LED light according to the interference calculation result. The feedback mechanism module is used to adjust the brightness by controlling the current of the LED light and provide real-time feedback on the adjustment result;

[0034] The brightness analysis module includes a data acquisition module, a statistical analysis module, and an anomaly marking module. The data acquisition module is electrically connected to the image processing module, the data acquisition module is electrically connected to the statistical analysis module, the statistical analysis module is electrically connected to the anomaly marking module, and the anomaly marking module is electrically connected to the correction algorithm module. The data acquisition module is used to collect the brightness and position data of each LED lamp to form a database. The statistical analysis module is used to perform statistical analysis on the collected data and calculate the uniformity of the brightness of all LED lamps. The anomaly marking module is used to set a brightness threshold to mark potentially defective LED lamps;

[0035] The working method of this system is as follows:

[0036] S1. Use the camera in the image acquisition unit to capture the inner contour image of the starry sky ceiling, generate the original image data for subsequent processing;

[0037] S2. Denoise the acquired image and identify the LED lamps in the image processing module, and extract clear LED lamp features through image processing algorithms;

[0038] S3. Based on the processed image, mark the positions of all LED lamps on the plane rectangular coordinate system to form the lighting position information, and calculate the brightness of each LED lamp;

[0039] S4. Collect the brightness of each LED lamp combined with the position information, calculate the interference degree between adjacent LED lamps, and construct an interference factor model;

[0040] S5. Calculate the brightness uniformity of all LED lamps and mark the defective LED lamps;

[0041] S6. According to the results of the interference calculation and the defective LED lamps, determine the appropriate brightness of each LED lamp, and adjust the current of the LED lamp in real time through the feedback mechanism module to reach the preset brightness;

[0042] In S3, the specific method for forming the lighting position information is as follows: Mark the position of each LED lamp using coordinates to form a position coordinate set {(x1, y1), (x2, y2), …, (x n , y n )}, where x is the abscissa of the LED lamp, y is the ordinate of the LED lamp, and n is the number of LED lamps;

[0043] The specific method for calculating the brightness of each LED lamp is as follows: Continuously collect the inner contour images of the starry sky ceiling with a certain LED lamp lit several times, and average the color values of the images. Divide the brightness l according to the average color value of a certain LED in the collected images. The brighter the image color value, the larger l increases proportionally, forming a brightness set {l1, l2, …, l n};

[0044] In S4, the specific method for constructing the interference factor model is as follows:

[0045] S4-1. In the image where a certain LED light is on, determine the influence range of the LED light according to the brightness of the LED light. The greater the brightness of the LED light, the influence range increases proportionally. The specific influence range is αl i , where α is the influence range coefficient of brightness and i is the serial number of a certain LED light;

[0046] S4-2. Calculate the straight-line distance H between the position coordinates of each LED light. The straight-line distance between two LED lights with serial numbers i and k is

[0047] S4-3. When calculating the interference degree of a certain LED light, only consider the situation where the position coordinates of this LED light are within the respective influence ranges of other LED lights. If it exceeds the respective influence ranges of other LED lights, there is no need to consider interference. That is, only when H ik <αl i , it is necessary to consider the interference degree between the LED lights with serial numbers i and k;

[0048] S4-4. Correct the brightness l i of a certain LED light with serial number i. Since the brightness of the light usually follows the inverse square law as the distance increases, the corrected brightness where β is the attenuation coefficient of distance with respect to brightness, is the influence of the brightness of the LED light with serial number k on l i , and m is the number of LED lights that affect the LED light with serial number i;

[0049] In S5, the specific method for marking defective LED lights is as follows: Let the appropriate light brightness range be [l min ~l max . An LED light with a corrected brightness l min ~l max outside this range will be marked as defective, and the others are of normal brightness. Only the brightness of the marked defective LED lights needs to be adjusted; it

[0050] In S6, the method for determining the appropriate brightness of each LED light is as follows: When the corrected brightness l it >l max , it is necessary to lower the brightness of the LED light with serial number i to within [l min ~l max . Specifically, lower the brightness When the corrected brightness l it <l min , specifically increase the brightness

[0051] In S6, the specific method for adjusting the current of the LED lamp in real time through the feedback mechanism module is as follows: by changing the current I of the LED lamp with the serial number i i to adjust the brightness, and the current change value ΔI i = I i ±μΔl i , where μ is the conversion coefficient between current and brightness, positive when the brightness is increased and negative when the brightness is decreased;

[0052] After the adjustment is completed, the brightness of each LED lamp is detected again. If it is within [l min ~l max , no adjustment is required. If the adjusted brightness change is too large, the brightness is changed back from the adjusted brightness to the original brightness and adjusted according to the dichotomy method, that is, the brightness is changed again positive when the brightness is increased and negative when the brightness is decreased.

[0053] It should be noted that in this article, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements not only includes those elements, but also includes other elements not expressly listed, or elements inherent to such process, method, article or device.

[0054] Finally, it should be noted that the above are only the preferred embodiments of the present invention and are not used to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some of the technical features. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A method for visually inspecting defects of automobile interior parts, characterized in that: The method uses a detection system to work, and the detection system includes a visual detection module, a light interference correction module, and a brightness analysis module. The visual detection module is used to scan and shoot the inner contour surface of the entire starry sky top, the light interference correction module is used to correct the interference of lights between adjacent LED lights on the brightness defect detection result, and the brightness analysis module is used to analyze the obtained LED light brightness data to determine whether there are defects and make improvements; The visual detection module includes an image acquisition unit, an image processing module, and a position recognition module. The image acquisition unit is electrically connected to the image processing module, and the image processing module is electrically connected to the position recognition module. The image acquisition unit uses a camera to capture the inner contour image of the starry sky top. The image processing module is used to process the acquired image, including image denoising and identifying LED lights. The position recognition module is used to mark the position of each LED light on a plane rectangular coordinate system; The light interference correction module includes an interference calculation module, a correction algorithm module, and a feedback mechanism module. The interference calculation module is electrically connected to the image processing module and the position recognition module. The correction algorithm module is electrically connected to the interference calculation module and the feedback mechanism module. The interference calculation module is used to calculate the interference degree between each LED according to the brightness and position of adjacent LED lights to achieve modeling of interference factors. The correction algorithm module is used to correct the appropriate brightness of each LED light according to the interference calculation result. The feedback mechanism module is used to adjust the brightness by controlling the current of the LED light and provide real-time feedback of the adjustment result. The brightness analysis module includes a data acquisition module, a statistical analysis module, and an abnormal marking module. The data acquisition module is electrically connected to the image processing module, the data acquisition module is electrically connected to the statistical analysis module, the statistical analysis module is electrically connected to the abnormal marking module, and the abnormal marking module is electrically connected to the correction algorithm module. The data acquisition module is used to collect the brightness and position data of each LED lamp to form a database. The statistical analysis module is used to perform statistical analysis on the collected data and calculate the uniformity of the brightness of all LED lamps. The abnormal marking module is used to set a brightness threshold and mark LED lamps with potential defects; The system works as follows: S1, using the camera in the image acquisition unit to capture the inner contour image of the starry sky top, generating raw image data, and preparing for subsequent processing; S2, denoising the collected images and identifying the LED lights in the image processing module, and extracting clear LED light features through image processing algorithms; S3. Based on the processed image, mark the positions of all LED lights on a plane rectangular coordinate system to form light position information, and calculate the brightness of each LED light; S4, collecting the brightness and position information of each LED lamp, calculating the interference degree between adjacent LED lamps, and constructing an interference factor model; S5. Calculate the brightness uniformity of all LED lamps and mark defective LED lamps; S6. Determine the appropriate brightness of each LED lamp according to the result of the interference calculation and the defective LED lamp, and adjust the current of the LED lamp in real time through the feedback mechanism module to achieve the preset brightness; In S3, the specific method of forming the light position information is: marking the position of each LED light with coordinates to form a position coordinate set {(x1, y1), (x2, y2), ..., (x n ,y n )}, where x is the horizontal coordinate of the LED light, y is the vertical coordinate of the LED light, and n is the number of LED lights; The specific method for calculating the brightness of each LED lamp is as follows: continuously collect several images of the inner contour of the starry sky with a certain LED lamp on, and average the color values ​​of the images. The brightness l is divided according to the average color value of a certain LED in the collected image. The brighter the image color value, the greater the l is proportional to form a brightness set {l1, l2, ..., l n }; In S4, the specific method of constructing the interference factor model is: S4-1. In the image captured when a certain LED light is on, determine the influence range of the LED light according to the brightness of the LED light. The greater the brightness of the LED light, the greater the influence range. The specific influence range is αl i , where α is the influence range coefficient of brightness, and i is the serial number of a certain LED lamp; S4-2, calculate the straight-line distance H of the position coordinates of each LED light, where the straight-line distance between two LED lights with serial numbers i and k is S4-3. When calculating the interference degree of a certain LED light, it is only necessary to consider the situation where the position coordinates of this LED light are within the influence range of other LED lights. If the position coordinates of this LED light are beyond the influence range of other LED lights, there is no need to consider the interference. That is, only when H ik <αl i Only when the LED lights with serial numbers i and k are connected, the degree of interference between them needs to be considered; S4-4, the brightness l of a LED lamp with serial number i i Correction: Since the brightness of light usually follows the inverse square as the distance increases, correct the brightness Where β is the attenuation coefficient of distance with brightness, is the brightness of the LED light with serial number k i The impact of, m is the number of LED lamps that affect the LED lamp with serial number i; In S5, the specific method of marking the defective LED lamp is: let the appropriate light brightness range be [l min ~l max ], in [l min ~l max ] other than a corrected brightness l it The LED lights with defects will be marked as defective, while the brightness of the others is normal. Only the brightness of the LED lights with defects needs to be adjusted. In S6, the method for determining the appropriate brightness of each LED lamp is: when the corrected brightness is l it >l max When the LED light with serial number i is turned down to [l min ~l max ], specifically adjust the brightness When the corrected brightness l it <l min When the brightness is adjusted up 2. The method for visually inspecting defects of automotive interior parts according to claim 1, characterized in that: In S6, the specific method of adjusting the current of the LED lamp in real time through the feedback mechanism module is: by changing the current I of the LED lamp with sequence number i i To adjust the brightness, the current changes by ΔI i =I i ±μΔl i , where μ is the conversion factor between current and brightness, which is positive when the brightness is adjusted up and negative when the brightness is adjusted down; After adjustment, check the brightness of each LED again. min ~l max ], no adjustment is required. If the brightness change is too large, change the brightness from the adjusted brightness to the original brightness. Adjust according to the binary method, that is, change the brightness again. It is positive when the brightness is adjusted up, and negative when the brightness is adjusted down.

Images