Defrosting and demisting area identification method for automobile windshield glass

Abstract

The invention discloses an automobile windshield glass defrosting and demisting area identification method, which comprises the following steps of: determining a defrosting and demisting area through a three-dimensional single-arm measurement scriber, and drawing the defrosting and demisting area on a drawing; setting image acquisition equipment, and putting the drawing into a preset acquisition area of the image acquisition equipment; acquiring a drawing through the image acquisition equipment; establishing an image correction model, and correcting the image; and the area of the corrected defrosting and demisting area is calculated, and a result is generated. Through the technical scheme of the invention, the defrosting and demisting area identification process of the automobile windshield glass has the advantages of high automation, intelligence, high accuracy, relatively high calculation speed and the like, and the defects of large error, low efficiency, low automation and intelligence degrees and the like in the existing data processing link are improved.

Description

Technical Field

[0001] The invention belongs to the technical field of machine vision, and in particular relates to a method for identifying the defrosting and defogging area of ​​a car windshield. Background Art

[0002] The automobile windshield defrost and defogging area detection refers to detecting whether the automobile windshield defrost and defogging area can reach the specified value within a specified time, and checking whether the automobile windshield defrost and defogging area covers the specified area on the windshield.

[0003] The existing detection method requires the use of a three-dimensional single-arm measuring and marking instrument to determine the position of the windshield AB area and the defrost and defogging area, then to depict the area, and finally to calculate the area of ​​the windshield defrost and defogging area through an area integrator.

[0004] Although the existing methods can meet the requirements for defrosting and defogging area detection, there are the following shortcomings in the detection process: there are too many manual operations in the detection process, the data obtained from the detection are prone to large errors, the test efficiency is low, and the degree of automation and intelligence is low. Summary of the invention

[0005] The present invention provides a method for identifying the defrosting and defogging area of ​​a car windshield, aiming to solve the above-mentioned problems.

[0006] The method for identifying the defrosting and defogging area of ​​a car windshield provided by the present invention comprises:

[0007] Determine the defrosting and defogging area using a three-dimensional single-arm measuring and marking instrument and draw it on the drawing;

[0008] Configure the image acquisition device and place the drawing into the preset acquisition area of ​​the image acquisition device;

[0009] The drawing is collected by the image acquisition device to obtain an image;

[0010] Establishing an image correction model to correct the image;

[0011] Calculate the area of ​​the corrected defrost and defogging area.

[0012] Further, the configuring of the image acquisition device includes:

[0013] Adjust the position and posture of the image acquisition device, and set the sensitivity, shooting mode, white balance, metering, focus, exposure compensation, image format, image style, drive mode and focal length of the image acquisition device;

[0014] The posture of the image acquisition device includes: the relative position of the image acquisition device and the drawing, and the relative angle between the lens in the image acquisition device and the drawing.

[0015] Furthermore, the capturing of the drawings by the image capturing device to obtain the image includes: adjusting the configuration of the image capturing device, photographing the drawings by the image capturing device in a preset capturing area to obtain the image; and recording the image and the adjusted configuration of the image capturing device.

[0016] Furthermore, the process of establishing the image correction model includes: calibrating the image acquisition device through the Tsai two-step calibration method, obtaining the correspondence between the drawing and the image under different configurations of the image acquisition device, and establishing the correspondence between the physical points in the drawing and the pixel points in the image under different configurations of the image acquisition device.

[0017] Furthermore, the steps of the Tsai two-step calibration method are specifically as follows:

[0018] Capture multiple calibration images at different positions and angles through an image acquisition device; perform corner point detection on multiple calibration images through the image acquisition device to obtain the two-dimensional pixel coordinates of each corner point on the image; establish a radial consistency equation between the two-dimensional pixel coordinates of the feature point and the world coordinates based on the pinhole model and the radial distortion model; solve the radial consistency equation through the least squares method to obtain the intrinsic parameters of the camera;

[0019] Select a point on the calibration image as the origin of the world coordinate system, and determine the world coordinates of other points; establish the projection equation between the image coordinates and the world coordinates of the feature point based on the intrinsic parameters and the pinhole model; solve the projection equation through the least squares method to obtain the extrinsic parameters of the camera.

[0020] Furthermore, after the image correction model is established, the pixel points in the image are restored to the physical points in the drawing according to the corresponding relationship between the physical points in the drawing and the pixel points in the image.

[0021] Further, the calculation of the area of ​​the defrost and defogging region after correction includes:

[0022] De-noising the corrected image;

[0023] Perform edge recognition on the denoised image to obtain contour lines in the defrosting and defogging area;

[0024] The number of pixels within each contour line is counted, and the area of ​​the defrost and defogging region corresponding to the image is calculated.

[0025] Furthermore, the denoising method includes: mean filtering, median filtering, Gaussian filtering, wavelet denoising, non-local mean denoising, and total variation denoising.

[0026] Furthermore, after calculating the area of ​​the corrected defrost and defogging region, the method further includes: selecting a report template, generating and saving a report according to the area of ​​the defrost and defogging region corresponding to the calculated image.

[0027] Compared with the prior art, the present invention has the following beneficial effects:

[0028] The technical solution of the present invention uses machine vision to automatically identify and detect the defrosting and defogging area of ​​automobile windshields. First, for the drawings of the defrosting and defogging area that have been drawn, the fixed camera is used to automatically collect the relevant images, and then the collected images are further processed using data processing technologies such as image preprocessing, contour recognition, image enhancement, area calculation, and size calibration, so as to calculate the area of ​​the defrosting and defogging area of ​​the windshield, and display and save the test results through a computer interface. The application of machine vision and its related technologies to detect the defrosting and defogging area of ​​automobile windshields has the advantages of high automation, intelligence, high accuracy, and fast calculation speed, which improves the shortcomings of the existing data processing links such as large errors, low efficiency, low automation and intelligence, and greatly improves the test efficiency and accuracy.

[0029] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0031] Figure 1 It is a flow chart of a method for identifying the defrosting and defogging area of ​​a car windshield provided by the present invention;

[0032] Figure 2 It is a working schematic diagram of an image acquisition device provided by the present invention. DETAILED DESCRIPTION

[0033] The present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It is to be understood that the specific embodiments described herein are only used to explain the present invention, rather than to limit the present invention. It should also be noted that, for ease of description, only parts related to the present invention, rather than all structures, are shown in the accompanying drawings.

[0034] Embodiment 1

[0035] The present invention proposes a method for identifying the defrosting and defogging area of ​​a car windshield, aiming to reduce the manual operation process in the detection process, reduce the error of the data obtained by the detection, and improve the test efficiency as well as the degree of automation and intelligence.

[0036] Figure 1 This is a flow chart of a method for identifying the defrosting and defogging area of ​​a vehicle windshield provided in the first embodiment of the present invention. Figure 1 As shown, the present embodiment provides a method for identifying the defrosting and defogging area of ​​a car windshield, which is applicable to the scenario of performance testing of the defrosting and defogging function of a car windshield, and specifically includes the following steps:

[0037] S101: Determine the defrosting and defogging area using a three-dimensional single-arm measuring and marking instrument, and draw it on the drawing.

[0038] It should be noted that the defrosting and defogging areas of the car windshield include area A and area B, etc.

[0039] Here is an explanation of some of the terms:

[0040] Area A refers to the area enclosed by the intersection of four planes extending forward from point V and the outer surface of the windshield. These four planes are: plane 1), a vertical plane passing through points V1 and V2 and forming an angle of 13° with the X-axis on the left side of the X-axis; plane 2), a plane passing through point V1 and forming an elevation angle of 3° with the X-axis and parallel to the Y-axis; plane 3), a plane passing through point V2 and forming an angle of 1° with the X-axis and parallel to the Y-axis; plane 4), a vertical plane passing through points V1 and V2 and forming an angle of 20° with the X-axis to the right side of the X-axis.

[0041] Area B refers to the area of ​​the outer surface of the windshield surrounded by the following four planes, and at least 25 mm inward from the edge of the transparent part of the windshield. The four planes are: Plane 1), a plane passing through point V1, which is 7° in elevation with the X-axis and parallel to the Y-axis; Plane 2), a plane passing through point V2, which is 5° in depression with the X-axis and parallel to the Y-axis; Plane 3), a vertical plane passing through points V1 and V2 and forming an angle of 17° with the X-axis on the left side of the X-axis; Plane 4), a plane with the longitudinal center plane of the vehicle as the reference plane and symmetrical to the vertical plane described in Plane 3.

[0042] The V point is the point that represents the position of the driver's eyes. The V point is related to the vertical plane passing through the center line of the driver's seat position, the R point and the designed seat back angle. The V point is used to check whether the vehicle's field of vision meets the requirements. Usually, the two points V1 and V2 are used to represent the different positions of the V point. The R point is the "sitting reference point", which refers to the design H point specified by the seat manufacturer. The design back angle refers to the angle between the vertical line passing through the R point and the torso line of the two-dimensional human body model.

[0043] Defrosting is the process of removing frost or ice covering the inner and outer surfaces of the windshield using a defrosting device or windshield wipers. A defrosting device is a device used to melt frost or ice on the inner and outer surfaces of the windshield to restore a clear view. The defrosting area refers to the area of ​​the windshield that restores a clear view after defrosting.

[0044] Demisting is the process of removing the fog covering the inner surface of the windshield using a demisting device. A demisting device is a device used to remove water vapor condensation on the inner surface of the windshield to restore a clear view. The demisting area refers to the area on the inner surface of the windshield that restores a clear view after demisting.

[0045] S102: configuring an image acquisition device and placing the drawing into a preset acquisition area of ​​the image acquisition device.

[0046] The configuration of the image acquisition device includes:

[0047] Adjust the posture of the image acquisition device, and set the sensitivity, shooting mode, white balance, metering, focus, exposure compensation, image format, image style, drive mode and focal length of the image acquisition device.

[0048] The posture of the image acquisition device includes: the relative position of the image acquisition device and the drawing, and the relative angle between the lens in the image acquisition device and the drawing.

[0049] S103: Capturing the drawing by using the image acquisition device to obtain an image.

[0050] Specifically, the method includes: adjusting the configuration of the image acquisition device, photographing the drawing in a preset acquisition area through the image acquisition device to obtain an image; and recording the image and the adjusted configuration of the image acquisition device.

[0051] S104: Establish an image correction model to correct the image.

[0052] Specifically, the method includes: calibrating the image acquisition device through the Tsai two-step calibration method, obtaining the correspondence between the drawing and the image under different configurations of the image acquisition device, and establishing the correspondence between the physical points in the drawing and the pixel points in the image under different configurations of the image acquisition device.

[0053] Figure 2 This is a working schematic diagram of an image acquisition device provided in Embodiment 1 of the present invention. The image acquisition device may be a device such as a camera with a shooting function. Figure 2 In the example, the area captured by the lens of the image acquisition device is the preset acquisition area, in which a calibration plate (chessboard) is placed. Due to the camera inclination during the shooting process, different images will be obtained, such as Figure 2As shown on the right, the image needs to be corrected for image acquisition at different angles.

[0054] Among them, the steps of Tsai's two-step calibration method are as follows:

[0055] Step 1: Collect multiple calibration images at different positions and angles through an image acquisition device; perform corner point detection on multiple calibration images through the image acquisition device to obtain the two-dimensional pixel coordinates of each corner point on the image; establish a radial consistency equation between the two-dimensional pixel coordinates of the feature point and the world coordinates based on the pinhole model and the radial distortion model; solve the radial consistency equation through the least squares method to obtain the intrinsic parameters of the camera;

[0056] Step 2: Select a point on the calibration image as the origin of the world coordinate system, and determine the world coordinates of other points; establish the projection equation between the image coordinates and the world coordinates of the feature point based on the intrinsic parameters and the pinhole model; solve the projection equation by the least squares method to obtain the extrinsic parameters of the camera.

[0057] The first step of Tsai's two-step calibration method is to calibrate the camera's internal parameters. It is necessary to use a set of known three-dimensional spatial points and their two-dimensional pixel coordinates in the camera coordinate system to solve the camera's internal parameters through the least squares method. Specifically, a checkerboard calibration plate can be used to obtain these data, and then the functions in computer vision libraries such as OpenCV can be used to calibrate the internal parameters.

[0058] The second step of Tsai's two-step calibration method is to calibrate the camera's external parameters. It is necessary to use a set of known 3D space points and their 2D pixel coordinates in the camera coordinate system to solve the camera's internal parameters through the least squares method. Specifically, you can take images of the same set of 3D space points at different positions and postures, and then use functions in computer vision libraries such as OpenCV to calibrate the external parameters.

[0059] Among them, the intrinsic parameters include the parameters inherent to the image acquisition device, such as focal length, pixel plane center, etc.; the extrinsic parameters include the position and orientation information of the image acquisition device in the world coordinate system.

[0060] Tsai two-step calibration method is a commonly used method for camera calibration, which aims to improve the measurement accuracy and stability. The steps of Tsai two-step calibration method are as follows:

[0061] The first step is to obtain the intrinsic parameter matrix, including: taking multiple calibration images at different angles on an affine plane, extracting feature points (such as corner points) in these images, and calculating the pixel coordinates of the corner points in the image; solving these equations by the least squares method to obtain the intrinsic parameter matrix.

[0062] The second step is to obtain the extrinsic parameter matrix: select an estimated plane, set the world coordinate system corresponding to this plane as (X, Y, Z), and then project all points on the plane onto the calibration image to obtain the pixel coordinates P; by applying the least squares method to the coordinates of the points on the estimated plane, the equation of the plane in the camera coordinate system can be obtained; this equation and the coordinates of the points on the calibration image are solved together to obtain the rotation matrix and translation vector of the camera; repeat the above steps and use different estimated planes to obtain multiple sets of rotation matrices and translation vectors. After averaging these matrices and vectors and normalizing them in the world coordinate system, the orientation information of the camera in the world coordinate system, namely the extrinsic parameter matrix, can be obtained.

[0063] Through the Tsai two-step calibration method, the internal and external parameters of the camera can be accurately solved, thereby achieving accurate calibration of the camera, improving measurement accuracy and stability, and achieving more accurate and reliable visual measurement and control.

[0064] After the image correction model is established, the pixel points in the image are restored to the physical points in the drawing according to the correspondence between the physical points in the drawing and the pixel points in the image.

[0065] S105: Calculate the area of ​​the corrected defrost and defogging region.

[0066] Specifically include:

[0067] De-noising the corrected image;

[0068] Perform edge recognition on the denoised image to obtain contour lines in the defrosting and defogging area;

[0069] The number of pixels within each contour line is counted, and the area of ​​the defrost and defogging region corresponding to the image is calculated.

[0070] Among them, the denoising methods include: mean filtering, median filtering, Gaussian filtering, wavelet denoising, non-local mean denoising, and total variation denoising.

[0071] Mean filtering means replacing the value of each pixel with the average value of the surrounding pixels. It is suitable for mild Gaussian noise. It includes arithmetic mean filtering, geometric mean filtering, and harmonic mean filtering.

[0072] Median filtering means replacing the value of each pixel with the median value of its surrounding pixels, which is suitable for salt and pepper noise.

[0073] Gaussian filtering means using a Gaussian kernel to smooth an image, which is suitable for Gaussian noise.

[0074] Wavelet denoising means: using wavelet transform to decompose the signal into sub-bands of different frequencies, and then removing noise through threshold processing.

[0075] Non-local mean denoising refers to using the information of similar areas in the image to remove noise, which is suitable for retaining image details.

[0076] Total variation denoising means: removing noise by minimizing the total variation of the image, which is suitable for maintaining the edge of the image. Total variation denoising in Python is a common image processing technique that can be used to remove noise and smooth images. The core idea of ​​total variation denoising is to achieve denoising by minimizing the total variation of the image.

[0077] After calculating the area of ​​the corrected defrost and defogging area, it also includes: selecting a report template, generating a report and saving it.

[0078] The embodiment of the present invention provides a method for identifying the defrosting and defogging area of ​​a car windshield. The drawing is converted into an image by an image acquisition device, and then the image is mapped in the world coordinate by establishing an image correction model. The acquired image is further processed by using image preprocessing, contour recognition, image enhancement, area calculation, size calibration and other data processing technologies, so as to calculate the area of ​​the defrosting and defogging area of ​​the windshield. The shortcomings of the existing data processing link, such as large error, low efficiency, low automation and intelligence, are improved, and the test efficiency and accuracy are greatly improved.

[0079] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0080] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for identifying the defrosting and defogging area of ​​a car windshield, characterized in that: include: Determine the defrosting and defogging area using a three-dimensional single-arm measuring and marking instrument and draw it on the drawing; Configure the image acquisition device and place the drawing into the preset acquisition area of ​​the image acquisition device; The drawing is collected by the image acquisition device to obtain an image; Establishing an image correction model to correct the image; Calculate the area of ​​the corrected defrost and defogging area.

2. The method according to claim 1, characterized in that: The configuration of the image acquisition device comprises: Adjust the position and posture of the image acquisition device, and set the sensitivity, shooting mode, white balance, metering, focus, exposure compensation, image format, image style, drive mode and focal length of the image acquisition device; The posture of the image acquisition device includes: the relative position of the image acquisition device and the drawing, and the relative angle between the lens in the image acquisition device and the drawing.

3. The method according to claim 1, characterized in that: The method of acquiring an image by acquiring the drawing through the image acquisition device includes: adjusting the configuration of the image acquisition device, photographing the drawing through the image acquisition device in a preset acquisition area to obtain an image; and recording the image and the adjusted configuration of the image acquisition device.

4. The method according to claim 3, characterized in that The process of establishing the image correction model includes: calibrating the image acquisition device through the Tsai two-step calibration method to obtain the corresponding relationship between the drawing and the image under different configurations of the image acquisition device, and establishing the corresponding relationship between the physical points in the drawing and the pixel points in the image under different configurations of the image acquisition device.

5. The method according to claim 4, characterized in that The steps of the Tsai two-step calibration method are specifically as follows: Capture multiple calibration images at different positions and angles through an image acquisition device; perform corner point detection on multiple calibration images through the image acquisition device to obtain the two-dimensional pixel coordinates of each corner point on the image; establish a radial consistency equation between the two-dimensional pixel coordinates of the feature point and the world coordinates based on the pinhole model and the radial distortion model; solve the radial consistency equation through the least squares method to obtain the intrinsic parameters of the camera; Select a point on the calibration image as the origin of the world coordinate system, and determine the world coordinates of other points; establish the projection equation between the image coordinates and the world coordinates of the feature point based on the intrinsic parameters and the pinhole model; solve the projection equation through the least squares method to obtain the extrinsic parameters of the camera.

6. The method according to claim 5, characterized in that After the image correction model is established, the pixel points in the image are restored to the physical points in the drawing according to the correspondence between the physical points in the drawing and the pixel points in the image.

7. The method according to claim 6, characterized in that The calculating the area of ​​the defrost and defogging region after correction includes: De-noising the corrected image; Perform edge recognition on the denoised image to obtain contour lines in the defrosting and defogging area; The number of pixels within each contour line is counted, and the area of ​​the defrost and defogging region corresponding to the image is calculated.

8. The method according to claim 7, characterized in that The denoising methods include: mean filtering, median filtering, Gaussian filtering, wavelet denoising, non-local mean denoising, and total variation denoising.

9. The method according to claim 1, characterized in that: After calculating the area of ​​the corrected defrost and defogging region, the method further includes: selecting a report template, generating and saving a report according to the area of ​​the defrost and defogging region corresponding to the calculated image.

Images