A multi-camera atmosphere lamp color calibration method and device based on machine vision

Abstract

The present application relates to a kind of multi-camera atmosphere lamp color calibration methods based on machine vision, comprising the following: at the bottom of optical darkroom, the LED lamp plate to be detected is installed, and the center of other side is respectively installed industrial camera;While lighting all LED lamp head arranged at the LED lamp plate, the image of the lamp plate to be measured is respectively collected by main camera and auxiliary camera;Positioning is carried out to each LED lamp head based on the image collected by main camera and auxiliary camera, and position coordinate and color coordinate parameter are obtained;Compensation calibration is carried out based on the color coordinate parameter collected by each camera, and the final color coordinate parameter is obtained;The position coordinate and color coordinate parameter associated with each LED lamp head are written into the MCU of LED lamp head.The method of the present application can accurately measure the color data of multiple LED atmosphere lamps simultaneously, greatly reduce the time required for color calibration, greatly reduce the mechanical complexity, and improve the stability of the system.

Description

Technical Field

[0001] This invention relates to the field of lighting color calibration technology, and in particular to a method and apparatus for color calibration of multi-camera ambient lights based on machine vision. Background Technology

[0002] As automobiles become increasingly intelligent, ambient lighting products are evolving from decorative components to interactive elements. Strip and panel-type ambient lighting products, due to the use of numerous LED chips, place stringent requirements on the color consistency of these chips. Currently, there is no fully mature color calibration system on the market. Some existing systems use color analyzer probes to collect data, which is inefficient, as it can only read the color parameters of one LED at a time. This represents a significant waste of human and material resources for companies without achieving high-precision calibration results.

[0003] Therefore, how to simultaneously acquire high-precision color parameters from multiple LEDs to reduce the time and power consumption costs incurred by the factory has become a crucial issue. Summary of the Invention

[0004] The purpose of this invention is to at least address one of the shortcomings of the prior art by providing a method and apparatus for color calibration of multi-camera ambient lights based on machine vision.

[0005] To achieve the above objectives, the present invention adopts the following technical solution:

[0006] Specifically, a multi-camera ambient light color calibration method based on machine vision is proposed, including the following:

[0007] An LED light board to be tested is installed at the bottom of the optical darkroom. Industrial cameras are installed at the top and the center of the other four sides of the optical darkroom. The industrial camera installed at the top is the main camera, and the cameras installed on the other four sides are auxiliary cameras. The focal points of the main camera and the auxiliary cameras coincide with the center of the bottom of the optical darkroom.

[0008] Simultaneously, all LED lamp heads installed on the LED lamp board are lit up, and images of the lamp board under test are captured by the main camera and the auxiliary camera respectively.

[0009] Based on the images captured by the main camera and the auxiliary camera, the position coordinates of each LED head are obtained, and the color coordinate parameters on the CIE chromaticity coordinate map corresponding to the image captured by each camera are obtained.

[0010] The final color coordinate parameters are obtained by compensation and calibration based on the color coordinate parameters acquired by each camera;

[0011] Write the position coordinates and color coordinates associated with each LED head into the MCU of the LED head.

[0012] Furthermore, specifically, clips for fixing the ambient lights to be calibrated are installed at equal intervals on the LED light panel. Each clip carries a flip-top detachable beam shaper. A LIN bus interface supporting hot-swapping is reserved below the clip. The LED light head is set in the beam shaper, which adjusts the beam emitted by the LED light head into a circle.

[0013] Furthermore, specifically, the position coordinates of each LED head are obtained by locating it based on the images captured by the main camera and the auxiliary camera, including:

[0014] The image captured by the main camera is used as the first image. The reference position coordinates (x, y) of each LED head are obtained by the first image processing process, where the left and right direction is defined as the X-axis and the front and back direction is defined as the Y-axis.

[0015] For the images captured by the left and right side cameras, the position coordinates (x1, y1) and (x2, y2) of each LED head are first obtained through the first image processing process. Then, the angle α between the camera and the left and right horizontal lines is calculated based on the vertical distance between the camera and the bottom of the optical darkroom and the straight-line distance between the camera and the center of the bottom of the optical darkroom. Finally, x1 and x2 are adjusted according to the angle α to obtain (x11, y1) and (x22, y2).

[0016] For the images captured by the front and rear side cameras, the position coordinates (x3, y3) and (x4, y4) of each LED head are first obtained through the first image processing process. Then, the angle β between the camera and the front and rear horizontal lines is calculated based on the vertical distance between the camera and the bottom of the optical dark chamber and the straight distance between the camera and the center of the bottom of the optical dark chamber. Finally, y3 and y4 are adjusted according to the angle β to obtain (x3, y33) and (x4, y44).

[0017] Calculate the distances from the reference position coordinates (x, y) in (x11, y1), (x22, y2), (x3, y33), and (x4, y44), and remove the points whose distances are greater than the first threshold as outliers to obtain the remaining points after removal.

[0018] The final position coordinates (x0, y0) are obtained by averaging the x and y coordinates of the remaining points after the removal.

[0019] Furthermore, specifically, the first image processing procedure includes,

[0020] The image to be processed is filtered to obtain a denoised second image;

[0021] The second image is converted to grayscale to obtain the third image;

[0022] Multiple image edges were obtained by performing edge detection on the third image using the Canny operator;

[0023] Each image edge is segmented using an image segmentation algorithm to obtain a segmented image corresponding to each image edge. Interference contours are removed by matching according to a pre-set contour matching template. The interference contours include the LED light panel contour. The segmented image corresponding to the remaining contour is the contour image of each LED light head.

[0024] For the outline image of each LED head, calculate the centroid coordinates and define the centroid coordinates as the reference position coordinates or position coordinates of the LED head.

[0025] Furthermore, specifically, the final color coordinate parameters are obtained by compensation and calibration based on the color coordinate parameters acquired by each camera, including:

[0026] Assume the color coordinates captured by the main camera are (X, Y), and the distance from its camera to the bottom center of the optical darkroom is h; the color coordinates captured by the left-side camera are (X1, Y1), and the distance from its camera to the bottom center of the optical darkroom is h1; the color coordinates captured by the right-side camera are (X2, Y2), and the distance from its camera to the bottom center of the optical darkroom is h2; the color coordinates captured by the front-side camera are (X3, Y3), and the distance from its camera to the bottom center of the optical darkroom is h3; and the color coordinates captured by the rear-side camera are (X4, Y4), and the distance from its camera to the bottom center of the optical darkroom is h4.

[0027] The color coordinate parameters are adjusted based on the distance from the camera to the bottom center of the optical darkroom. The adjusted color coordinate parameters are as follows:

[0028] Calculate the distance between the adjusted color coordinate parameters collected by each auxiliary camera and the adjusted color coordinate parameters collected by the main camera. Define the color coordinate parameters whose distance is greater than the second threshold as outliers and remove them to obtain the remaining color coordinate parameters after removal.

[0029] The final color coordinate parameters (X0, Y0) are obtained by averaging the remaining color coordinate parameters.

[0030] Furthermore, specifically, the position coordinates and color coordinates associated with each LED head are written into the MCU of the LED head, including...

[0031] The color coordinate parameters are mapped one-to-one with the position coordinates and connected to the LIN bus main interface of the LED light board via a USB to LIN converter. Each LIN sub-interface on the LED light board is connected to the MCU of each LED head via hot-plugging. Finally, the calibrated color parameter data is written into the MCU via LIN bus communication technology.

[0032] This invention also proposes a multi-camera ambient light color calibration device based on machine vision, comprising the following:

[0033] An optical darkroom is used to install an LED light board to be tested at the bottom of the optical darkroom. Industrial cameras are installed at the top and the center of the other four sides of the optical darkroom. The industrial camera installed at the top is the main camera, and the cameras installed on the other four sides are auxiliary cameras. The focal points of the main camera and the auxiliary cameras coincide with the center of the bottom of the optical darkroom.

[0034] The data acquisition module is used to simultaneously illuminate all the LED lamp heads set at the LED lamp board, and to acquire images of the lamp board under test through the main camera and the auxiliary camera respectively;

[0035] The data conversion module is used to locate each LED head based on the images captured by the main camera and the auxiliary camera to obtain the position coordinates, and to obtain the color coordinate parameters on the CIE chromaticity coordinate diagram corresponding to the image captured by each camera.

[0036] The compensation and calibration module is used to perform compensation and calibration based on the color coordinate parameters acquired by each camera to obtain the final color coordinate parameters;

[0037] The data writing module is used to write the position coordinates and color coordinates associated with each LED head into the MCU of the LED head.

[0038] Furthermore, specifically,

[0039] Clips for securing ambient lights to be calibrated are installed at equal intervals on the LED light panel. Each clip carries a flip-top, detachable beam shaper. A hot-swappable LIN bus interface is reserved below the clip. The LED light head is located in the beam shaper, which adjusts the beam emitted by the LED light head into a circle.

[0040] Furthermore, specifically, the position coordinates and color coordinates associated with each LED head are written into the MCU of the LED head, including...

[0041] The color coordinate parameters are mapped one-to-one with the position coordinates and connected to the LIN bus main interface of the LED light board via a USB to LIN converter. Each LIN sub-interface on the LED light board is connected to the MCU of each LED head via hot-plugging. Finally, the calibrated color parameter data is written into the MCU via LIN bus communication technology.

[0042] The beneficial effects of this invention are as follows:

[0043] This invention provides a machine vision-based multi-camera ambient light color calibration method. It employs an LED light board supporting beam shaping as a calibration template, simultaneously illuminating LEDs on the board using a LIN bus. Multiple cameras collect color light data from different angles, along with the position information of the LEDs. The data from multiple angles is comprehensively analyzed to compensate for interference between LEDs. After algorithmic calculations, the calibrated data is written into the ambient light's MCU. Using this method, the color data of multiple LED ambient lights can be accurately measured simultaneously, significantly reducing the time required for color calibration, greatly minimizing mechanical complexity, and improving system stability. Attached Figure Description

[0044] The above and other features of this disclosure will become more apparent from the detailed description of the embodiments illustrated in conjunction with the accompanying drawings. In the accompanying drawings, the same reference numerals denote the same or similar output voltages. Obviously, the drawings described below are merely some embodiments of this disclosure. For those skilled in the art, other drawings can be obtained from these drawings without any inventive effort. In the drawings:

[0045] Figure 1 The diagram shows a flowchart of a multi-camera ambient light color calibration method based on machine vision according to the present invention.

[0046] Figure 2 The image shown is an LED light panel supporting beam shaping in one embodiment of a multi-camera ambient light color calibration method based on machine vision according to the present invention.

[0047] Figure 3 The diagram shown is a beam shaping schematic of one embodiment of the multi-camera ambient light color calibration method based on machine vision of the present invention.

[0048] Figure 4 The diagram shown is a schematic representation of the multi-camera arrangement in one embodiment of a machine vision-based multi-camera ambient light color calibration method of the present invention.

[0049] Figure 5The diagram shown is a schematic representation of the compensation calibration of color coordinate parameters and CIE coordinates in one embodiment of a multi-camera ambient light color calibration method based on machine vision according to the present invention.

[0050] Figure 6 The diagram shown illustrates the implementation of LIN interface hot-plugging in one embodiment of a machine vision-based multi-camera ambient light color calibration method according to the present invention. Detailed Implementation

[0051] The following will provide a clear and complete description of the concept, specific structure, and technical effects of the present invention in conjunction with embodiments and accompanying drawings, so as to fully understand the purpose, solution, and effects of the present invention. It should be noted that, unless otherwise specified, the embodiments and features described in this application can be combined with each other. The same reference numerals used throughout the accompanying drawings indicate the same or similar parts.

[0052] First, some terms appearing in this application will be explained as follows:

[0053] The full name of LED is Light Emitting Diode.

[0054] The industrial cameras include cameras made using CCD or CMOS devices and used in industrial applications.

[0055] The full name of CCD is Charge Coupled Device.

[0056] CMOS stands for Complementary Metal Oxide Semiconductor.

[0057] The full name of MCU is Microcontroller Unit.

[0058] The CIE 1931-XYZ color space refers to a color space defined mathematically by the International Commission on Illumination (CIE) in 1931.

[0059] Reference Figure 1 as well as Figure 4 Example 1: This invention proposes a multi-camera ambient light color calibration method based on machine vision, comprising the following:

[0060] Step 110: Install the LED light board to be tested at the bottom of the optical darkroom, and install industrial cameras at the top and the center of the other four sides of the optical darkroom. The industrial camera installed at the top is the main camera, and the cameras installed on the other four sides are auxiliary cameras. The focal points of the main camera and the auxiliary cameras coincide with the center of the bottom of the optical darkroom.

[0061] Step 120: Simultaneously light up all the LED lamp heads set at the LED lamp board, and capture images of the lamp board under test using the main camera and the auxiliary camera respectively;

[0062] Step 130: Based on the images captured by the main camera and the auxiliary camera, locate each LED head to obtain its position coordinates, and obtain the color coordinate parameters on the CIE chromaticity coordinate diagram corresponding to the image captured by each camera. The CIE chromaticity coordinate diagram refers to the CIE 1931-XYZ color space. Obtaining the color coordinate parameters on the CIE chromaticity coordinate diagram corresponding to the image captured by the camera is an existing technology. The image data is captured by the camera, the RGB data in the image is analyzed, and then the coordinate data in the CIE1931 chromaticity space is converted by the existing mature algorithm.

[0063] Step 140: Perform compensation calibration based on the color coordinate parameters acquired by each camera to obtain the final color coordinate parameters;

[0064] Step 150: Write the position coordinates and color coordinates associated with each LED head into the MCU of the LED head.

[0065] Reference Figure 2 In this embodiment 1, an LED light board supporting beam shaping is used as a calibration template. The LEDs on the light board are simultaneously illuminated using a LIN bus. Multiple cameras collect color light data from different angles, along with the position information of the LEDs. The data from multiple angles is comprehensively analyzed to compensate for interference between LEDs. After algorithmic calculations, the calibrated data is written into the MCU of the ambient light. Using the method of this invention, the color data of multiple LED ambient lights can be accurately measured simultaneously, significantly reducing the time required for color calibration, greatly reducing mechanical complexity, and improving system stability.

[0066] Reference Figure 3 In a preferred embodiment of the present invention, specifically, clips for fixing the ambient light to be calibrated are installed at equal intervals on the LED light plate. The clips carry a flip-type detachable beam shaper. A LIN bus interface supporting hot-swapping is reserved below the clips. The LED light head is set in the beam shaper, and the beam shaper adjusts the beam emitted by the LED light head into a circle.

[0067] In this preferred embodiment, in order to reduce the interference between the optical paths of each LED lamp head when testing multiple LED lamp heads at the source, a beam shaper is used to adjust the light emitted by the LED lamp heads. On the one hand, this makes the beam focused to facilitate data acquisition by the camera, and on the other hand, it greatly reduces the mutual interference between adjacent optical paths.

[0068] For details, see Figure 2 The ambient light to be tested is installed at the pre-drilled clips at equal intervals on the strip light panel. The gray part is the control circuit of the ambient light, including the MCU. Adjacent ambient lights are installed in opposite directions to maximize the use of the light panel space and ensure the spacing between the LEDs. The gray part and the other end of the control circuit are the LED positions. Each LED is provided with a removable beam shaping shield, and beam shaping is as follows... Figure 2 As shown, adjusting the divergent LED light into a circular beam significantly reduces light interference between LEDs.

[0069] In a preferred embodiment of the present invention, specifically, the position coordinates of each LED head are obtained by locating the images captured by the main camera and the auxiliary camera, including:

[0070] The image captured by the main camera is used as the first image. The reference position coordinates (x, y) of each LED head are obtained by the first image processing process, where the left and right direction is defined as the X-axis and the front and back direction is defined as the Y-axis.

[0071] For the images captured by the left and right side cameras, the position coordinates (x1, y1) and (x2, y2) of each LED head are first obtained through the first image processing process. Then, the angle α between the camera and the left and right horizontal lines is calculated based on the vertical distance between the camera and the bottom of the optical darkroom and the straight-line distance between the camera and the center of the bottom of the optical darkroom. Finally, x1 and x2 are adjusted according to the angle α to obtain (x11, y1) and (x22, y2).

[0072] For the images captured by the front and rear side cameras, the position coordinates (x3, y3) and (x4, y4) of each LED head are first obtained through the first image processing process. Then, the angle β between the camera and the front and rear horizontal lines is calculated based on the vertical distance between the camera and the bottom of the optical dark chamber and the straight distance between the camera and the center of the bottom of the optical dark chamber. Finally, y3 and y4 are adjusted according to the angle β to obtain (x3, y33) and (x4, y44).

[0073] Calculate the distances from the reference position coordinates (x, y) in (x11, y1), (x22, y2), (x3, y33), and (x4, y44), and remove the points whose distances are greater than the first threshold as outliers to obtain the remaining points after removal.

[0074] The final position coordinates (x0, y0) are obtained by averaging the x and y coordinates of the remaining points after the removal.

[0075] In this preferred embodiment, considering that the side cameras have a certain angle with the horizontal plane when acquiring images, the angle will not affect the Y-axis data of the left and right side cameras, but will reduce the X-axis data by a certain ratio. Therefore, the horizontal axis coordinate of the measured position coordinates can be adjusted and corrected by using coordinate calculation combined with geometric analysis based on the angle α between the left and right side cameras and the X-axis. Similarly, the angle will not affect the X-axis data of the front and rear side cameras, but will reduce the Y-axis data by a certain ratio. Therefore, the vertical axis coordinate of the measured position coordinates can be adjusted and corrected by using coordinate calculation combined with geometric analysis based on the angle β between the front and rear side cameras and the Y-axis. The distance between the corrected point and the reference position coordinates is calculated, and obviously erroneous experimental data is removed. If more than half of the data is erroneous during the removal process, the process can be stopped and the engineer can be notified for verification. For correcting coordinates by angle, the mapping relationship between the angle and the scaling ratio can be obtained through pre-experimentation, and this mapping relationship can be called during detection.

[0076] In a preferred embodiment of the present invention, specifically, the first image processing process includes:

[0077] The image to be processed is filtered to obtain a denoised second image;

[0078] The second image is converted to grayscale to obtain the third image;

[0079] Multiple image edges were obtained by performing edge detection on the third image using the Canny operator;

[0080] Each image edge is segmented using an image segmentation algorithm to obtain a segmented image corresponding to each image edge. Interference contours are removed by matching according to a pre-set contour matching template. The interference contours include the LED light panel contour. The segmented image corresponding to the remaining contour is the contour image of each LED light head.

[0081] For the outline image of each LED head, calculate the centroid coordinates and define the centroid coordinates as the reference position coordinates or position coordinates of the LED head.

[0082] In this preferred embodiment, the outline of the LED head is obtained by extracting the outline of the image to be processed. Then, the centroid coordinates of the LED head outline are regarded as the coordinates of the LED head in the current image, which can accurately calculate the coordinates of the LED head.

[0083] Reference Figure 5 In a preferred embodiment of the present invention, specifically, the final color coordinate parameters are obtained by compensation and calibration based on the color coordinate parameters acquired by each camera, including:

[0084] Assume the color coordinates captured by the main camera are (X, Y), and the distance from its camera to the bottom center of the optical darkroom is h; the color coordinates captured by the left-side camera are (X1, Y1), and the distance from its camera to the bottom center of the optical darkroom is h1; the color coordinates captured by the right-side camera are (X2, Y2), and the distance from its camera to the bottom center of the optical darkroom is h2; the color coordinates captured by the front-side camera are (X3, Y3), and the distance from its camera to the bottom center of the optical darkroom is h3; and the color coordinates captured by the rear-side camera are (X4, Y4), and the distance from its camera to the bottom center of the optical darkroom is h4.

[0085] The color coordinate parameters are adjusted based on the distance from the camera to the bottom center of the optical darkroom. The adjusted color coordinate parameters are as follows:

[0086] Calculate the distance between the adjusted color coordinate parameters collected by each auxiliary camera and the adjusted color coordinate parameters collected by the main camera. Define the color coordinate parameters whose distance is greater than the second threshold as outliers and remove them to obtain the remaining color coordinate parameters after removal.

[0087] The final color coordinate parameters (X0, Y0) are obtained by averaging the remaining color coordinate parameters.

[0088] In this preferred embodiment, considering the problem that the light emitted by multiple LED heads will interfere with each other when collecting color coordinate parameters simultaneously, data is collected by cameras at multiple angles and corrected for each other. This can largely eliminate the interference between them and make the color coordinate parameters more accurate. In addition, since the distance of different cameras from the center of the bottom of the base plate will interfere with the converted color coordinates, the distance is normalized to obtain the adjusted color coordinate parameters in order to make the results as accurate as possible.

[0089] In a preferred embodiment of the present invention, specifically, the position coordinates and color coordinate parameters associated with each LED head are written into the MCU of the LED head, including,

[0090] The color coordinate parameters are mapped one-to-one with the position coordinates and connected to the LIN bus main interface of the LED light board via a USB to LIN converter. Each LIN sub-interface on the LED light board is connected to the MCU of each LED head via hot-plugging. Finally, the calibrated color parameter data is written into the MCU via LIN bus communication technology.

[0091] This invention also proposes a multi-camera ambient light color calibration device based on machine vision, comprising the following:

[0092] An optical darkroom is used to install an LED light board to be tested at the bottom of the optical darkroom. Industrial cameras are installed at the top and the center of the other four sides of the optical darkroom. The industrial camera installed at the top is the main camera, and the cameras installed on the other four sides are auxiliary cameras. The focal points of the main camera and the auxiliary cameras coincide with the center of the bottom of the optical darkroom.

[0093] The data acquisition module is used to simultaneously illuminate all the LED lamp heads set at the LED lamp board, and to acquire images of the lamp board under test through the main camera and the auxiliary camera respectively;

[0094] The data conversion module is used to locate each LED head based on the images captured by the main camera and the auxiliary camera to obtain the position coordinates, and to obtain the color coordinate parameters on the CIE chromaticity coordinate diagram corresponding to the image captured by each camera.

[0095] The compensation and calibration module is used to perform compensation and calibration based on the color coordinate parameters acquired by each camera to obtain the final color coordinate parameters;

[0096] The data writing module is used to write the position coordinates and color coordinates associated with each LED head into the MCU of the LED head.

[0097] As a preferred embodiment of the present invention, specifically...

[0098] Clips for securing ambient lights to be calibrated are installed at equal intervals on the LED light panel. Each clip carries a flip-top, detachable beam shaper. A hot-swappable LIN bus interface is reserved below the clip. The LED light head is located in the beam shaper, which adjusts the beam emitted by the LED light head into a circle.

[0099] Reference Figure 6 In a preferred embodiment of the present invention, specifically, the position coordinates and color coordinate parameters associated with each LED head are written into the MCU of the LED head, including,

[0100] The color coordinate parameters are mapped one-to-one with the position coordinates and connected to the LIN bus main interface of the LED light board via a USB to LIN converter. Each LIN sub-interface on the LED light board is connected to the MCU of each LED head via hot-plugging. Finally, the calibrated color parameter data is written into the MCU via LIN bus communication technology.

[0101] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical modules; that is, they may be located in one place or distributed across multiple network modules. Some or all of the modules can be selected to achieve the purpose of the solution in this embodiment, depending on actual needs.

[0102] Furthermore, the functional modules in the various embodiments of the present invention can be integrated into one processing module, or each module can exist physically separately, or two or more modules can be integrated into one module. The integrated modules described above can be implemented in hardware or as software functional modules.

[0103] If the integrated module is implemented as a software functional module and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments of the present invention can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc.

[0104] Although the description of the invention has been quite detailed and particularly of several described embodiments, it is not intended to limit it to any of these details or embodiments or any particular embodiment, but should be considered as providing a broad possible interpretation of the claims by referring to the appended claims and taking into account the prior art, thereby effectively covering the intended scope of the invention. Furthermore, the invention has been described above with respect to embodiments foreseeable by the inventors in order to provide a useful description, and non-substantial modifications to the invention that have not yet been foreseen may still represent equivalent modifications.

[0105] The above description is merely a preferred embodiment of the present invention. The present invention is not limited to the above-described embodiments. Any embodiment that achieves the technical effects of the present invention using the same means should fall within the protection scope of the present invention. Within the protection scope of the present invention, various modifications and variations can be made to the technical solutions and / or implementation methods.

Claims

1. A multi-camera ambient light color calibration method based on machine vision, characterized in that, Including the following: An LED light board to be tested is installed at the bottom of the optical darkroom. Industrial cameras are installed at the top and the center of the other four sides of the optical darkroom. The industrial camera installed at the top is the main camera, and the cameras installed on the other four sides are auxiliary cameras. The focal points of the main camera and the auxiliary cameras coincide with the center of the bottom of the optical darkroom. Simultaneously, all LED lamp heads installed on the LED lamp board are lit up, and images of the lamp board under test are captured by the main camera and the auxiliary camera respectively. Based on the images captured by the main camera and the auxiliary camera, the position coordinates of each LED head are obtained, and the color coordinate parameters on the CIE chromaticity coordinate map corresponding to the image captured by each camera are obtained. The final color coordinate parameters are obtained by compensation and calibration based on the color coordinate parameters acquired by each camera; Write the position coordinates and color coordinates associated with each LED head into the MCU of the LED head; Specifically, the final color coordinate parameters are obtained by compensation and calibration based on the color coordinate parameters acquired by each camera, including: Assume the color coordinates captured by the main camera are (X, Y), and the distance from its camera to the bottom center of the optical darkroom is h; the color coordinates captured by the left-side camera are (X1, Y1), and the distance from its camera to the bottom center of the optical darkroom is h1; the color coordinates captured by the right-side camera are (X2, Y2), and the distance from its camera to the bottom center of the optical darkroom is h2; the color coordinates captured by the front-side camera are (X3, Y3), and the distance from its camera to the bottom center of the optical darkroom is h3; and the color coordinates captured by the rear-side camera are (X4, Y4), and the distance from its camera to the bottom center of the optical darkroom is h4. The color coordinate parameters are adjusted based on the distance from the camera to the bottom center of the optical darkroom. The adjusted color coordinate parameters are as follows: , , , , ; Calculate the distance between the adjusted color coordinate parameters collected by each auxiliary camera and the adjusted color coordinate parameters collected by the main camera. Define the color coordinate parameters whose distance is greater than the second threshold as outliers and remove them to obtain the remaining color coordinate parameters after removal. The final color coordinate parameters (X0, Y0) are obtained by averaging the remaining color coordinate parameters.

2. The method for color calibration of multi-camera ambient lights based on machine vision according to claim 1, characterized in that, Specifically, clips for fixing the ambient lights to be calibrated are installed at equal intervals on the LED light panel. Each clip carries a flip-top detachable beam shaper. A LIN bus interface supporting hot-swapping is reserved below the clip. The LED light head is set in the beam shaper, which adjusts the beam emitted by the LED light head into a circle.

3. The method for color calibration of ambient lights based on machine vision using multiple cameras according to claim 1, characterized in that, Specifically, the position coordinates of each LED head are obtained by locating it based on the images captured by the main camera and the auxiliary camera, including: The image captured by the main camera is used as the first image. The reference position coordinates (x, y) of each LED head are obtained by the first image processing process, where the left and right direction is defined as the X-axis and the front and back direction is defined as the Y-axis. For the images captured by the left and right side cameras, the position coordinates (x1, y1) and (x2, y2) of each LED head are first obtained through the first image processing process. Then, the angle α between the camera and the left and right horizontal lines is calculated based on the vertical distance between the camera and the bottom of the optical dark chamber and the straight-line distance between the camera and the center of the bottom of the optical dark chamber. Finally, x1 and x2 are adjusted according to the angle α to obtain (x11, y1) and (x22, y2). For the images captured by the front and rear side cameras, the position coordinates (x3, y3) and (x4, y4) of each LED head are first obtained through the first image processing process. Then, the angle β between the camera and the front and rear horizontal lines is calculated based on the vertical distance between the camera and the bottom of the optical dark chamber and the straight-line distance between the camera and the center of the bottom of the optical dark chamber. Finally, y3 and y4 are adjusted according to the angle β to obtain (x3, y33) and (x4, y44). Calculate the distances from the reference position coordinates (x, y) in (x11, y1), (x22, y2), (x3, y33), and (x4, y44), and remove the points whose distances are greater than the first threshold as outliers to obtain the remaining points after removal. The final position coordinates (x0, y0) are obtained by averaging the x and y coordinates of the remaining points after the removal.

4. The method for color calibration of multi-camera ambient lights based on machine vision according to claim 3, characterized in that, Specifically, the first image processing step includes: The image to be processed is filtered to obtain a denoised second image; The second image is converted to grayscale to obtain the third image; Multiple image edges were obtained by performing edge detection on the third image using the Canny operator; Each image edge is segmented using an image segmentation algorithm to obtain a segmented image corresponding to each image edge. Interference contours are removed by matching according to a pre-set contour matching template. The interference contours include the LED light panel contour. The segmented image corresponding to the remaining contour is the contour image of each LED light head. For the outline image of each LED head, calculate the centroid coordinates and define the centroid coordinates as the reference position coordinates or position coordinates of the LED head.

5. The method for color calibration of multi-camera ambient lights based on machine vision according to claim 1, characterized in that, Specifically, the position coordinates and color coordinates associated with each LED head are written into the MCU of the LED head, including... The color coordinate parameters are mapped one-to-one with the position coordinates and connected to the LIN bus main interface of the LED light board via a USB to LIN converter. Each LIN sub-interface on the LED light board is connected to the MCU of each LED head via hot-plugging. Finally, the calibrated color parameter data is written into the MCU via LIN bus communication technology.

6. A multi-camera ambient light color calibration device based on machine vision, characterized in that, The apparatus comprising the steps of the method according to any one of claims 1-5, wherein the method is applied, the apparatus includes the following: An optical darkroom is used to install an LED light board to be tested at the bottom of the optical darkroom. Industrial cameras are installed at the top and the center of the other four sides of the optical darkroom. The industrial camera installed at the top is the main camera, and the cameras installed on the other four sides are auxiliary cameras. The focal points of the main camera and the auxiliary cameras coincide with the center of the bottom of the optical darkroom. The data acquisition module is used to simultaneously illuminate all the LED lamp heads set at the LED lamp board, and to acquire images of the lamp board under test through the main camera and the auxiliary camera respectively; The data conversion module is used to locate each LED head based on the images captured by the main camera and the auxiliary camera to obtain the position coordinates, and to obtain the color coordinate parameters on the CIE chromaticity coordinate diagram corresponding to the image captured by each camera. The compensation and calibration module is used to perform compensation and calibration based on the color coordinate parameters acquired by each camera to obtain the final color coordinate parameters; The data writing module is used to write the position coordinates and color coordinates associated with each LED head into the MCU of the LED head.

7. The multi-camera ambient light color calibration device based on machine vision according to claim 6, characterized in that, Specifically, Clips for securing ambient lights to be calibrated are installed at equal intervals on the LED light panel. Each clip carries a flip-top, detachable beam shaper. A hot-swappable LIN bus interface is reserved below the clip. The LED light head is located in the beam shaper, which adjusts the beam emitted by the LED light head into a circle.

8. The multi-camera ambient light color calibration device based on machine vision according to claim 6, characterized in that, Specifically, the position coordinates and color coordinates associated with each LED head are written into the MCU of the LED head, including... The color coordinate parameters are mapped one-to-one with the position coordinates and connected to the LIN bus main interface of the LED light board via a USB to LIN converter. Each LIN sub-interface on the LED light board is connected to the MCU of each LED head via hot-plugging. Finally, the calibrated color parameter data is written into the MCU via LIN bus communication technology.

Images