Area identification method for AB area and defrosting and demisting area of automobile windshield glass

Abstract

The invention discloses an automobile windshield glass AB area identification method, which comprises the following steps of: installing an automatic V point simulation device on an internal seat of an automobile, emitting light spots by the automatic V point simulation device, and mapping 12 angular point positions of A1, A2 and B area boundaries on the automobile windshield glass; parchment paper with the same size as the automobile windshield glass is laid on the automobile windshield glass, and 12 angular points are marked on the parchment paper with different colors based on the positions of the light spots; image information on the identification plate is collected by the industrial camera, and a first electronic drawing is obtained; identifying the first electronic drawing by adopting a target identification algorithm, identifying 12 angular points from the first electronic drawing, and generating bounding boxes of the same color at the angular points of the same type; and according to the color of the bounding box, the angular points of the same type are connected to obtain areas A1, A2 and B, and the areas of the areas A1, A2 and B are calculated.

Description

Technical Field

[0001] The invention relates to the technical field of vehicle testing, in particular to a method for identifying the area of ​​an AB zone of a car windshield. Background Art

[0002] The evaluation criteria for the performance of the automobile defrosting and defogging system generally refer to whether the defrosting and defogging system can restore the windshield in the key visible area to transparency within the specified time. The performance of the automobile defrosting and defogging system has an important impact on the safe driving of the vehicle. The relevant international and domestic government departments, standardization organizations, industry associations and automobile manufacturers attach great importance to this.

[0003] The relevant national test standards have mandatory requirements for the performance of defrosting and defogger systems. Among them, GB11555-2009 requires: 20 minutes after the start of the defrosting test, 80% of the A area has been defrosted; 25 minutes after the start of the defrosting test, 80% of the A' area has been defrosted; 40 minutes after the start of the defrosting test, 95% of the B area has been defrosted; 10 minutes after the start of the defogger test, 90% of the A area has been defogged; 10 minutes after the start of the defogger test, 80% of the B area has been defogged. The calculation of the test results will determine whether the test results can meet the regulatory requirements, so the judgment of the results should be accurate.

[0004] In the prior art, there are usually the following methods for calculating the windshield AB area and the defrost and defogging area: 1. The grid counting calculation method requires dividing the defrost and defogging trajectory diagram into multiple grid graphics, and calculating the defrost and defogging area ratio in the visible area by the grid counting method. However, due to the irregularity of the defrost and defogging trajectory diagram itself, the processed graphics can only be as close to the real area as possible, so the calculation result has a certain deviation from the actual result; 2. The windshield AB area and the defrost and defogging area are depicted on the front windshield of the car, and then the area is depicted on sulfuric acid paper, and the area of ​​the AB area and the defrost and defogging area are calculated and summed by an area integrator. However, the calculation result of this method depends on the calculation result of the area integrator, and there are problems such as large error, low efficiency and low intelligence.

[0005] In addition, the existing Chinese patent "CN201611170886.X" discloses a method for testing the defrost and defog area ratio of a vehicle, which is to draw a defrost and defog trajectory diagram on the windshield obtained at a preset time on a test paper corresponding to the shape of the windshield; respectively obtain a first paper mass occupied by the visible area in the test paper and a second paper mass occupied by the defrost and defog area corresponding to the defrost and defog trajectory diagram in the visible area in the test paper; calculate the defrost and defog area ratio of the vehicle according to the first paper mass and the second paper mass. However, the inventors of this application found that the above technology has at least the following technical problems in the process of implementing the technical solution of the invention in the embodiment of this application: In the process of manually drawing and rubbing the defrost and defog trajectory diagram, there may be certain subjective judgment errors. In order to ensure the accuracy of the test, it is necessary to ensure the consistency of the quality of the test paper, such as thickness, density, etc. Otherwise, different batches of paper will cause deviations in the measurement results. Summary of the invention

[0006] In view of the above-mentioned prior art, the present invention provides a method for identifying the area of ​​the AB zone of a car windshield, mainly to solve the technical problems existing in the above-mentioned background technology.

[0007] To achieve the above object, the technical solution of the embodiment of the present invention is implemented as follows:

[0008] The first aspect of the present invention discloses a method for identifying the area of ​​the AB region of a car windshield, the method comprising the following steps:

[0009] An automated V-point simulation device is installed on the seat inside the car. The automated V-point simulation device emits light spots to map the 12 corner points of the boundaries of the A1, A2, and B zones on the car windshield.

[0010] Laying a paper having the same size as the windshield of the car on the windshield of the car, and marking 12 corner points on the paper with different colors based on the position of the light spot;

[0011] Calibrate the industrial camera, then remove the sulfuric acid paper and place it on the identification plate, and use the industrial camera to collect image information on the identification plate to obtain a first electronic drawing;

[0012] Using a target recognition algorithm to recognize the first electronic drawing, identifying 12 corner points from the first electronic drawing, and generating bounding boxes of the same color at the same type of corner points;

[0013] According to the color of the bounding box, connect the corner points of the same type to obtain the A1, A2, and B regions, and calculate the areas of the A1, A2, and B regions.

[0014] Optionally, the industrial camera is calibrated, specifically including: using Zhang Zhengyou calibration algorithm to perform in-camera parameter calibration and distortion correction on the industrial camera.

[0015] Optionally, 12 corner points of the boundaries of areas A1, A2 and B are mapped on the car windshield, specifically including: mapping four corner points about area A1, mapping four corner points about area A2, and mapping four corner points about area B on the car windshield.

[0016] Optionally, 12 corner points are marked on the paper with different colors, specifically including marking four corner points about the A1 area on the paper with red, marking four corner points about the A2 area on the paper with yellow, and marking four corner points about the B area on the paper with blue.

[0017] Optionally, the target recognition algorithm consists of a ByteTrack algorithm and a YOLOv5s detector, wherein the YOLOv5s detector is used to realize the recognition of 12 corner points, and the ByteTrack algorithm is used to add bounding boxes of different colors to the 12 corner points, wherein red bounding boxes are added to the four corner points of the A1 area, yellow bounding boxes are added to the four corner points of the A2 area, and blue bounding boxes are added to the four corner points of the B area.

[0018] Optionally, according to the color of the bounding box, the same type of corner points are connected to obtain areas A1, A2, and B, specifically including: using red lines to connect multiple red bounding boxes, and the area enclosed by them constitutes area A1; using yellow lines to connect multiple yellow bounding boxes, and the area enclosed by them constitutes area A2; using blue lines to connect multiple blue bounding boxes, and the area enclosed by them constitutes area B, and finally boxing out areas A1, A2, and B on the first electronic drawing.

[0019] Optionally, the areas of regions A1, A2, and B are calculated, specifically including: for the first electronic drawing in which regions A1, A2, and B have been framed, contour detection is performed using the contour detection function in OpenCV; for the contour detection result, the ConvexHull function is used to calculate the convex hull of the contour, and the ContourArea function is used to calculate the area of ​​the convex hull, thereby obtaining the areas of regions A1, A2, and B, and based on the areas of regions A1 and A2, the area of ​​region A is obtained.

[0020] The second aspect of the present invention discloses a method for identifying the defrosting and defogging area of ​​a car windshield, which specifically comprises the following steps:

[0021] The sulfuric acid paper with 12 corner points marked is laid again on the windshield of the car. When the air conditioner in the car is turned on the defrosting and defogging mode, an industrial camera is used to collect images to obtain a second electronic drawing.

[0022] The second electronic drawing is used as a layer, and is merged with the first electronic drawing in which the A1, A2, and B areas are framed, to obtain a third electronic drawing, wherein the third electronic drawing includes the defrosted area, the non-defrosted area, and the framed A1, A2, and B areas;

[0023] For the overlapping part of the defrosted area and areas A1, A2, and B, the contour detection function in OpenCV is used to perform contour detection. For the contour detection result, the ConvexHull function is used to calculate the convex hull of the contour, and the ContourArea function is used to calculate the area of ​​the convex hull, so as to obtain the area of ​​the defrosted area in areas A1, A2, and B.

[0024] The beneficial effects of the present invention are as follows: the corner point positions of the AB zone of the windshield are accurately mapped through an automated V-point simulation device, thereby avoiding subjective errors caused by manual operation in traditional methods; an industrial camera and a target recognition algorithm are used to automatically identify corner points and draw regional boundaries, thereby greatly reducing manual participation and improving the automation level of the overall process; compared with traditional grid counting methods or area integrator calculation methods, the method of the present invention can quickly and accurately obtain the area data of the AB zone and the defrost and defogging zone, thereby significantly improving work efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] Figure 1 This is a flow chart of the method for identifying the area of ​​the AB zone of a car windshield in an embodiment of the present application;

[0026] Figure 2 Schematic diagram of the A1 region, A2 region, and B region formed in the embodiment of the present application;

[0027] Figure 3 This is a flow chart of a method for identifying the defrosting and defogging area of ​​a car windshield in an embodiment of the present application;

[0028] Figure 4 Schematic diagram of dividing the defrosted area and the non-defrosted area in the embodiment of the present application

[0029] Description of Figure Numbers:

[0030] 1. Windshield; 2. A1 area; 3. A2 area; 4. B area; 5. Defrost and defogger dividing line. DETAILED DESCRIPTION

[0031] The technical solution of the present invention is further elaborated in detail below in conjunction with the drawings and specific embodiments of the specification. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by technicians in the technical field of the present invention. The terms used in the specification of the present invention herein are only for the purpose of describing specific embodiments and are not intended to limit the present invention. In the following description, the expression "some embodiments" is related to a subset of all possible embodiments, but it should be understood that "some embodiments" can be the same subset or different subsets of all possible embodiments, and can be combined with each other without conflict.

[0032] In the following description, a large number of specific details are provided to provide a more thorough understanding of the present invention. However, it is apparent to those skilled in the art that the present invention can be implemented without one or more of these details. In other examples, in order to avoid confusion with the present invention, some technical features well known in the art are not described.

[0033] It should be understood that the present invention can be implemented in different forms and should not be interpreted as being limited to the embodiments proposed herein. On the contrary, providing these embodiments will make the disclosure thorough and complete, and the scope of the present invention will be fully conveyed to those skilled in the art. And the purpose of the terms used herein is only to describe specific embodiments and is not intended to be a limitation of the present invention. When used herein, the singular forms of "one", "one" and "said / the" are also intended to include plural forms, unless the context clearly indicates another way. It should also be understood that the terms "compose" and / or "include" when used in this specification determine the presence of the features, integers, steps, operations, elements and / or parts, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, parts and / or groups. When used herein, the term "and / or" includes any and all combinations of the relevant listed items.

[0034] It should also be noted that when an element is referred to as being "fixed to" another element, it may be directly on the other element or there may be a central element. When an element is considered to be "connected to" another element, it may be directly connected to the other element or there may be a central element at the same time. The terms "vertical", "horizontal", "inside", "outside", "left", "right" and similar expressions used herein are for illustrative purposes only and are not intended to be the only implementation method.

[0035] In order to fully understand the present invention, a detailed structure will be proposed in the following description to illustrate the technical solution proposed by the present invention. The optional embodiments of the present invention are described in detail as follows, but in addition to these detailed descriptions, the present invention may also have other implementations.

[0036] Please refer to the attached Figure 1 The first aspect of the present invention discloses a method for identifying the area of ​​the AB zone of a car windshield, the method comprising the following steps:

[0037] S1. Install an automated V-point simulation device on the seat inside the car. The automated V-point simulation device emits light spots to map the 12 corner points of the boundaries of the A1, A2, and B zones on the car windshield.

[0038] S2, laying a piece of sulfuric acid paper of the same size as the automobile windshield on the automobile windshield, and marking 12 corner points on the sulfuric acid paper with different colors based on the position of the light spot;

[0039] S3, calibrating the industrial camera, then removing the sulfuric acid paper and placing it on an identification plate, wherein the color of the identification plate is black, and collecting image information on the identification plate by the industrial camera to obtain a first electronic drawing;

[0040] S4, using a target recognition algorithm to recognize the first electronic drawing, identifying 12 corner points from the first electronic drawing, and generating bounding boxes of the same color at the same type of corner points;

[0041] S5. Connect the corner points of the same type according to the color of the bounding box to obtain regions A1, A2, and B, and calculate the areas of regions A1, A2, and B.

[0042] Specifically, the A area and the B area on the windshield are used to define the standard of clear sight area. For example, some safety standards stipulate that the driver must be able to clearly see the external environment through these areas. The shape of these areas may vary according to different vehicle designs. The A area is composed of the A1 area and the A2 area. When in use, the automatic V-point simulation device is installed on the main driving seat of the vehicle. The automatic V-point simulation device is an existing component in the field. The automatic V-point simulation device automatically calculates and emits light spots. When emitting light spots, four light spots about the A1 area are emitted first. After a period of time, four light spots about the A2 area are generated. And so on, four light spots about the B area are generated, and a total of 12 light spots are generated. The above 12 light spots are projected on the windshield three times. The A1 area refers to the visible area near the main driving seat, and the A2 area refers to the visible area near the co-pilot seat.

[0043] Furthermore, the industrial camera is calibrated, specifically including: using Zhang Zhengyou calibration algorithm to calibrate the industrial camera's internal parameters and perform distortion correction.

[0044] Furthermore, 12 corner points of the boundaries of the A1, A2 and B areas are mapped on the car windshield, specifically including: mapping four corner points about the A1 area, mapping four corner points about the A2 area, and mapping four corner points about the B area on the car windshield.

[0045] Further, 12 corner points are marked on the paper with different colors, specifically, four corner points about the A1 area are marked on the paper with red, four corner points about the A2 area are marked on the paper with yellow, and four corner points about the B area are marked on the paper with blue. The final shape drawn is as follows: Figure 2 shown.

[0046] Furthermore, the target recognition algorithm is composed of a ByteTrack algorithm and a YOLOv5s detector, wherein the YOLOv5s detector is used to realize the recognition of 12 corner points, and the ByteTrack algorithm is used to add bounding boxes of different colors to the 12 corner points, wherein red bounding boxes are added to the four corner points of the A1 area, yellow bounding boxes are added to the four corner points of the A2 area, and blue bounding boxes are added to the four corner points of the B area.

[0047] Furthermore, according to the color of the bounding box, the corner points of the same type are connected to obtain the A1, A2, and B areas, specifically including: using red lines to connect multiple red bounding boxes, and the area enclosed by them constitutes the A1 area; using yellow lines to connect multiple yellow bounding boxes, and the area enclosed by them constitutes the A2 area; using blue lines to connect multiple blue bounding boxes, and the area enclosed by them constitutes the B area, and finally the A1, A2, and B areas are framed on the first electronic drawing.

[0048] Furthermore, the areas of regions A1, A2, and B are calculated, specifically including: for the first electronic drawing in which regions A1, A2, and B have been framed, contour detection is performed using the contour detection function in OpenCV; for the contour detection result, the ConvexHull function is used to calculate the convex hull of the contour, and the ContourArea function is used to calculate the area of ​​the convex hull, thereby obtaining the areas of regions A1, A2, and B, and based on the areas of regions A1 and A2, the area of ​​region A is obtained, that is, the areas of regions A1 and A2 are added together to obtain the area of ​​region A.

[0049] See also Figure 3 as well as Figure 4 The second aspect of the present invention discloses a method for identifying the defrosting and defogging area of ​​a car windshield, which specifically includes the following steps:

[0050] A1. When the windshield of a car is covered with frost / fog, sulfuric acid paper with 12 corner points marked is laid on the windshield of the car again. When the air conditioner in the vehicle is turned on the defrosting and defogging mode, the frost / fog in some areas of the windshield of the car is cleared. At this time, an industrial camera is used to collect images of the windshield of the car to obtain a second electronic drawing, which includes an un-defrosted area and a defrosted area.

[0051] A2, taking the second electronic drawing as a layer, and merging it with the first electronic drawing in which the A1, A2, and B areas are framed, to obtain a third electronic drawing, wherein the third electronic drawing includes the defrosted area, the non-defrosted area, and the framed A1, A2, and B areas;

[0052] A3. For the overlapping part of the defrosted area with areas A1, A2, and B, the contour detection function in OpenCV is used to perform contour detection. For the contour detection result, the ConvexHull function is used to calculate the convex hull of the contour, and the ContourArea function is used to calculate the area of ​​the convex hull, so as to obtain the area of ​​the defrosted area in areas A1, A2, and B.

[0053] The second electronic drawing is used as a layer and the first electronic drawing is used as a background color for fusion. Since the first electronic drawing is obtained based on the black identification plate, the color of the entire first electronic drawing is black. When the third electronic drawing is obtained, the undefrosted area on the third electronic drawing is grayish white as a whole, the defrosted area is black, and the A1 area is surrounded by red lines, the A2 area is surrounded by yellow lines, and the B area is surrounded by blue lines. Therefore, the defrosted area and the undefrosted area can be segmented on the third electronic drawing by segmentation algorithms such as the Otsu method. For example, Figure 4 The defrost and defogger dividing line 5 is shown in the figure, wherein the upper part of the defrost and defogger dividing line 5 is the non-defrosted area, and the lower part is the defrosted area. Based on the segmentation algorithm, the overlapping part of the defrosted area and the A1, A2, and B areas are segmented. The contour detection function in OpenCV is used to perform contour detection on the overlapping part. For the contour detection result, the ConvexHul l function is used to calculate the convex hull of the contour, and the ContourArea function is used to calculate the area of ​​the convex hull, so as to obtain the area of ​​the defrosted area in the A1, A2, and B areas.

[0054] The above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. The protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A method for identifying the area of ​​the AB region of a car windshield, characterized in that: The method comprises the following steps: An automated V-point simulation device is installed on the seat inside the car. The automated V-point simulation device emits light spots to map the 12 corner points of the boundaries of the A1, A2, and B zones on the car windshield. Laying a paper having the same size as the windshield of the car on the windshield of the car, and marking 12 corner points on the paper with different colors based on the position of the light spot; Calibrate the industrial camera, then remove the sulfuric acid paper and place it on the identification plate, and use the industrial camera to collect image information on the identification plate to obtain a first electronic drawing; Using a target recognition algorithm to recognize the first electronic drawing, identifying 12 corner points from the first electronic drawing, and generating bounding boxes of the same color at the same type of corner points; According to the color of the bounding box, connect the corner points of the same type to obtain the A1, A2, and B regions, and calculate the areas of the A1, A2, and B regions.

2. The method for identifying the area of ​​the AB region of a car windshield according to claim 1, characterized in that: Calibrate the industrial camera, specifically including: use Zhang Zhengyou calibration algorithm to calibrate the industrial camera's internal parameters and correct distortion.

3. The method for identifying the area of ​​the AB region of a car windshield according to claim 1, characterized in that: The 12 corner points of the boundaries of the A1, A2 and B areas are mapped on the car windshield, specifically including: mapping four corner points about the A1 area, mapping four corner points about the A2 area, and mapping four corner points about the B area on the car windshield.

4. The method for identifying the area of ​​the AB region of a car windshield according to claim 3, characterized in that: 12 corner points are marked on the paper with different colors, specifically, four corner points about the A1 area are marked on the paper with red, four corner points about the A2 area are marked on the paper with yellow, and four corner points about the B area are marked on the paper with blue.

5. The method for identifying the area of ​​the AB region of a car windshield according to claim 4, characterized in that: The target recognition algorithm consists of a ByteTrack algorithm and a YOLOv5s detector, wherein the YOLOv5s detector is used to realize the recognition of 12 corner points, and the ByteTrack algorithm is used to add bounding boxes of different colors to the 12 corner points, wherein red bounding boxes are added to the four corner points of the A1 area, yellow bounding boxes are added to the four corner points of the A2 area, and blue bounding boxes are added to the four corner points of the B area.

6. The method for identifying the area of ​​the AB region of a car windshield according to claim 5, characterized in that: According to the colors of the bounding boxes, the same type of corner points are connected to obtain areas A1, A2, and B, specifically including: using red lines to connect multiple red bounding boxes, the area enclosed by them constitutes area A1, using yellow lines to connect multiple yellow bounding boxes, the area enclosed by them constitutes area A2, and using blue lines to connect multiple blue bounding boxes, the area enclosed by them constitutes area B, and finally the A1, A2, and B areas are framed on the first electronic drawing.

7. The method for identifying the area of ​​the AB region of a car windshield according to claim 5, characterized in that: The areas of regions A1, A2, and B are calculated, specifically including: for the first electronic drawing in which regions A1, A2, and B have been framed, contour detection is performed using the contour detection function in OpenCV; for the contour detection result, the ConvexHull function is used to calculate the convex hull of the contour, and the ContourArea function is used to calculate the area of ​​the convex hull, thereby obtaining the areas of regions A1, A2, and B, and based on the areas of regions A1 and A2, the area of ​​region A is obtained.

8. A method for identifying the defrosting and defogging area of ​​a car windshield, characterized in that: It specifically includes the following steps: The sulfuric acid paper with 12 corner points marked is laid again on the windshield of the car. When the air conditioner in the car is turned on the defrosting and defogging mode, an industrial camera is used to collect images to obtain a second electronic drawing. The second electronic drawing is used as a layer, and is merged with the first electronic drawing in which the A1, A2, and B areas are framed, to obtain a third electronic drawing, wherein the third electronic drawing includes the defrosted area, the non-defrosted area, and the framed A1, A2, and B areas; For the overlapping part of the defrosted area and areas A1, A2, and B, the contour detection function in OpenCV is used to perform contour detection. For the contour detection result, the ConvexHul l function is used to calculate the convex hull of the contour, and the ContourArea function is used to calculate the area of ​​the convex hull, so as to obtain the area of ​​the defrosted area in areas A1, A2, and B.

Images