Calibration board

Abstract

The embodiment of the utility model discloses a calibration board. The calibration plate comprises a central area and an edge area surrounding the outer side of the central area; first identification codes are arranged in the edge area, second identification codes are arranged in the central area, and the number of the first identification codes is larger than that of the second identification codes in unit area; calibration coordinates of the first identification code and the second identification code in a calibration plate coordinate system are arranged in the first identification code and the second identification code. Through the embodiment of the invention, the problem of how to assist in improving the calibration efficiency and the calibration accuracy is solved.

Description

Technical Field

[0001] This application relates to the field of image processing technology, and particularly to a calibration board for camera calibration. Background Art

[0002] In the field of automated high-precision processing, it is often necessary to accurately position items such as battery wafers for the next process. The currently commonly used positioning method is to obtain the image of the item through machine vision and identify the coordinate position of the item in the real space. This method first requires determining the mapping relationship between the pixel coordinate system in the camera and the coordinate system in the real space, and this determination process is also called camera calibration.

[0003] A calibration board is required for camera calibration, such as Figure 1 as described, the current calibration boards mostly use black and white checkerboard calibration boards. When calibrating the camera, feature points are marked on the black and white checkerboard calibration board, and the calibration board image with feature points is captured by the camera. The number of grids on the calibration board is counted manually to determine the calibration coordinates of the feature points, and each calibration coordinate is filled in manually to complete the calibration. This kind of calibration board results in low efficiency in determining calibration coordinates, complex operation and is prone to errors.

[0004] Therefore, there is an urgent need for a new calibration board to solve at least one problem of the existing calibration board. Summary of the Utility Model

[0005] To solve the problems of the existing technology, this application provides a calibration board.

[0006] The utility model provides a calibration board, which includes a central area and an edge area surrounding the outside of the central area;

[0007] The edge area is provided with a first identification code, and the central area is provided with a second identification code. In terms of unit area, the number of the first identification codes is greater than the number of the second identification codes in the unit area; both the first identification code and the second identification code are provided with their calibration coordinates in the calibration board coordinate system.

[0008] In an embodiment of the calibration board of this application,

[0009] The calibration board further includes a first pattern unit surrounding the first identification code and a second pattern unit surrounding the second identification code, and the size of the first pattern unit is smaller than that of the second pattern unit. More feature points are calculated based on the pattern units around the identification codes. Since the number of the first identification codes is greater than that of the second identification codes, that is, the density of the first identification codes is higher than that of the second identification codes, in order to match the corresponding identification codes for easy calculation, the size of the first pattern unit is set to be smaller than that of the second pattern unit. At the same time, the camera with a small viewing angle in the edge area can obtain at least one identification code and the corresponding surrounding pattern units.

[0010] In an embodiment of the calibration board of the present application,

[0011] Both the first pattern unit and the second pattern unit are distributed in a black-and-white alternating pattern, which is convenient for the recognition and calculation of the camera.

[0012] In an embodiment of the calibration board of the present application,

[0013] The pattern unit is a polygon pattern or a dot. The polygon pattern and the dot have feature points that are convenient for recognition and calculation, such as the intersection of sides in the polygon and the center of the dot.

[0014] In an embodiment of the calibration board of the present application,

[0015] The size of the first identification code is n times the size of the first pattern unit surrounding it, and the size of the second identification code is m times the size of the second pattern unit surrounding it, where n≥2 and m≥2. First, the identification code is larger than the surrounding pattern unit for easy highlighting and recognition. Second, the identification code is an integer multiple of the surrounding pattern unit, which is convenient for calculating the side line size or feature points of the pattern unit through the identification code and reduces the calculation difficulty.

[0016] In an embodiment of the calibration board of the present application,

[0017] Each first identification code and the first pattern unit surrounding the first identification code form a first checkerboard. A plurality of first checkerboards in the edge area are arranged in an array. The first checkerboard is square, and the first identification code is located at the center of the first checkerboard;

[0018] The second identification code and the second pattern unit surrounding the second identification code form a second checkerboard. The second checkerboard is square, and the second identification code is located at the center of the second checkerboard.

[0019] Based on the checkerboard array arrangement, and all the checkerboards are square, and the identification codes are located at the centers of the corresponding checkerboards, so that the camera can capture the pattern units on the calibration board and identify the identification codes whether from above or below the calibration board, which is convenient for the identification and calibration of the camera.

[0020] In an embodiment of the calibration board of the present application,

[0021] The size of the first identification code is smaller than the size of the second identification code, so that the small-field-of-view camera for obtaining the edge region image can obtain at least one identification code. The camera in the central region has a large field of view, and appropriately increasing the size of the identification code can reduce the complexity of calculation and identification;

[0022] And / or;

[0023] The edge region includes a plurality of sub-edge regions, and the sizes of the first identification codes in the plurality of sub-edge regions are the same, so that a plurality of cameras can be arranged in the edge region to identify the identification codes with the same standard, which is convenient for calculation;

[0024] In an embodiment of the calibration board of the present application,

[0025] The first identification codes are arranged in an array on the calibration board, which is convenient for identification and calculation;

[0026] And / or;

[0027] The second identification codes are arranged in an array on the calibration code, which is convenient for identification and calculation;

[0028] And / or;

[0029] The identification code is at least one of a two-dimensional code, a bar code or a digital code, where it is convenient to identify the corresponding position information. Preferably, it is a two-dimensional code. Even if part of the pattern of the two-dimensional code is lost, it does not affect the identification of its information.

[0030] In an embodiment of the calibration board of the present application,

[0031] The calibration board is provided with an anti-fooling mark, which can help the operator distinguish the front and back and the up and down directions of the calibration board.

[0032] In an embodiment of the calibration board of the present application,

[0033] The calibration board further includes a blank area arranged outside the edge area, and the anti-fooling mark is arranged in the blank area, which does not affect the normal use of other areas of the calibration board.

[0034] In an embodiment of the calibration board of the present application,

[0035] The calibration board includes a transparent substrate and the first identification code and the second identification code formed on the transparent substrate. The transparent substrate can transmit light, facilitating the camera shooting and the identification of the identification codes.

[0036] According to the specific embodiments provided in the present application, the following technical effects are disclosed in the present application:

[0037] In the calibration board of the present application, an identification code with calibration coordinate information is set. In this way, by reading the image of the calibration board captured by the camera, the calibration coordinates corresponding to the identification code in the image can be automatically obtained. Furthermore, based on this, the mapping relationship between the calibration board coordinate system and the pixel coordinate can be determined. It can be seen that the calibration board of the present application can improve the calibration efficiency and accuracy compared with the prior art. Moreover, in the calibration board, the identification code density in the edge area is greater than that in the central area, so that the small-field-of-view camera for obtaining the edge area image can obtain at least one identification code, avoiding the problem that no identification code can be obtained due to the small image area obtained. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required to be used in the embodiments. Obviously, the following described drawings are only some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0039] Figure 1 is a schematic structural diagram of a calibration board in the prior art;

[0040] Figure 2 is a schematic structural diagram of a calibration board according to an embodiment of the present invention;

[0041] Figure 3 is a schematic diagram of a partial edge area structure of a calibration board according to an embodiment of the present invention;

[0042] Figure 4 is a schematic diagram of the central area of a calibration board according to an embodiment of the present invention;

[0043] Figure 5 is a schematic diagram of camera arrangement on the edge area according to an embodiment of the present invention;

[0044] Figure 6 is a schematic diagram of camera arrangement on the central area according to an embodiment of the present invention;

[0045] Figure 7 is a schematic diagram of battery cell placement according to an embodiment of the present invention;

[0046] Figure 8Schematic diagram of the camera arrangement in the edge area of a battery cell according to an embodiment of the present utility model;

[0047] Figure 9 Schematic diagram of the camera arrangement in the central area of a battery cell according to an embodiment of the present utility model. Detailed implementation manners

[0048] To make the objectives, technical solutions and advantages of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application. Apparently, the described embodiments are only a part rather than all of the embodiments of the present application. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present application without creative efforts shall fall within the protection scope of the present application.

[0049] As described in the background art, during the existing camera calibration, feature points are marked on a black-and-white checkerboard calibration board, and the number of grids on the calibration board is counted manually to determine the calibration coordinates of the feature points, and each calibration coordinate is filled in manually to complete the calibration. This calibration board results in low efficiency, complex operation and easy error in determining the calibration coordinates. In the case of increasing accuracy requirements, the number of grids on the checkerboard is also continuously increasing, resulting in easy error in this method and seriously affecting the production efficiency. Based on this, the present application creatively proposes a calibration board to solve the technical problem of how to improve the calibration efficiency and accuracy.

[0050] Refer to the attached Figure 2 , Figure 2 A calibration board according to an embodiment of the present utility model, the calibration board 100 includes a central area 300 and an edge area 200 surrounding the outside of the central area 300; part of the edge area 200 refers to Figure 3 , the central area 300 refers to Figure 4, a first identification code 201 is provided within the edge region 200, and a second identification code 301 is provided within the central region 300; within a unit area, the number of the first identification codes 201 is greater than the number of the second identification codes 301 per unit area; both the first identification code 201 and the second identification code 301 are provided with their calibration coordinates in the calibration plate coordinate system. The purpose of the present utility model is to set identification codes with calibration coordinate information in the calibration plate, so that by reading the image of the calibration plate captured by the camera, the calibration coordinates corresponding to the identification codes in the image can be automatically obtained. Furthermore, based on this, the mapping relationship between the calibration plate coordinate system and the pixel coordinate is determined. It can be seen that the calibration plate of the present application can improve the calibration efficiency and accuracy compared with the prior art. Moreover, in the calibration plate 100, the identification code density of the edge region 200 is greater than that of the central region 300, so that a small-field-of-view camera for acquiring the image of the edge region can obtain at least one identification code, avoiding the problem that no identification code can be obtained due to the small image region obtained.

[0051] In one embodiment, the calibration plate 100 further includes a first pattern unit 202 surrounding the first identification code 201 and a second pattern unit 302 surrounding the second identification code 301. The size of the first pattern unit 202 is smaller than the size of the second pattern unit 302, that is, the pattern unit size of the central region 300 is larger than the pattern unit size of the edge region 200, so as to simplify the processing complexity of calculating the pattern-related coordinates according to the corresponding identification codes. In this example, both the first pattern unit 202 and the second pattern unit 302 are distributed in a black-and-white alternating pattern, which is convenient for the camera to identify and calculate. Further, the pattern unit is a polygon pattern or a dot, which is convenient for the camera to identify its edge or feature points.

[0052] In a possible embodiment, the size of the first identification code 201 is n times the size of the first pattern unit 202 surrounding it, and the size of the second identification code 301 is m times the size of the second pattern unit 302 surrounding it, where n≥2 and m≥2, which is convenient for the identification of the identification codes, and the multiple relationship is convenient for calculating the coordinates and feature points of the pattern unit according to the identification code coordinates.

[0053] In a possible embodiment, refer to Figures 2 - 4, each first identification code 201 and the first pattern units 202 surrounding the first identification code 201 form a first checkerboard. A plurality of first checkerboards in the edge area 200 are arranged in an array. The first checkerboard is square, and the first identification code 201 is located at the center of the first checkerboard. In this example, the size of the edge area 200 is 328mm * 280mm. The first checkerboard includes small black and white squares (or transparent ones), where the side length of each small square is 2mm, and the first identification codes 201 (also square, covering a square area composed of 4 squares) are also arranged in an array at the same spacing in the small checkerboards. There are 27 first identification codes 201 vertically and 32 first identification codes 201 horizontally in the edge area 200, so that in the fields of view of multiple cameras as shown in Figure 5 , there is at least one first identification code 201, and each first identification code 201 corresponds to a certain coordinate in the system;

[0054] The second identification code 301 and the second pattern units 302 surrounding the second identification code 301 form a second checkerboard. The second checkerboard is square, and the second identification code 301 is located at the center of the second checkerboard. The size of the central area 300 is 80mm * 80mm and includes the second checkerboard. The second checkerboard includes large black and white squares (transparent), and the side length of each large square is 10mm. One second identification code 301 (square, side length 16mm) is set at the center of the central area 300. The second identification code 301 covers a square area composed of 4 large squares, so that the central camera as shown in Figure 6 will capture the second identification code 301. Whether the camera is above or below the checkerboard, it can capture the squares on the checkerboard and identify the identification code for calibration. This facilitates subsequent position calculation and the calculation of the mapping relationship with pixel points.

[0055] In one implementation, the size of the first identification code 201 is smaller than that of the second identification code 301. For the cameras with a large field of view in the central area 300, the setting of the second identification code 301 is reduced, thereby simplifying the setting of the calibration board 100 and the complexity of processing the images related to the second identification code 201.

[0056] In one implementation, the edge area 200 includes a plurality of sub-edge areas, and the sizes of the first identification codes 201 in the plurality of sub-edge areas are the same, so that the small-field cameras on the edge area 200 can obtain at least one identification code.

[0057] In a possible implementation, the first identification codes 201 are arranged in an array on the calibration board 100; or the second identification codes 301 are arranged in an array on the calibration board 100 for easy capture and calculation.

[0058] In the above embodiment, the identification code is at least one of a two-dimensional code, a bar code, and a digital code, preferably a two-dimensional code. Even if part of the pattern of the two-dimensional code is missing, it does not affect the recognition by the camera.

[0059] In one embodiment, referring to Figures 2 - 4 , the calibration board 100 sequentially includes a blank area 101, an edge area 200, and a central area 300 along the direction from the edge to the center. An anti-fooling mark 1011 is provided on the blank area 101, such as Figure 1 , printed with the words "upper left", indicating that after the calibration board 100 is horizontally placed, the calibration board 100 is in front of the operator, and the "upper left" corner is in the operator's left front. At the same time, it can help the operator distinguish the front and back of the checkerboard.

[0060] In a possible embodiment, referring to Figures 2 - 4 , the calibration board 100 includes a transparent substrate and a first pattern unit 202, a second pattern unit 302, a first identification code 201, and a second identification code 301 formed on the transparent substrate. Preferably, the whole calibration board is a transparent glass with a thickness of 3 mm, and the generated pattern is directly written onto the glass plate using photolithography technology, and the photolithography accuracy is <1um.

[0061] Based on the above embodiment, through the calibration board 100 in the present application, rapid and automatic calibration of the camera can be achieved. Specifically, the process of achieving calibration is as follows: receiving an image of the calibration board acquired by the camera; wherein, the image includes at least one identification code and regularly arranged pattern units surrounding the identification code; the camera corresponds to a pixel coordinate system; reading the identification code in the image to obtain its calibration coordinates in the calibration board coordinate system; performing feature point detection on the pattern units in the image and determining the pixel coordinates of the feature points in the pixel coordinate system; determining the calibration coordinates of the feature points according to the size of the pattern units on the calibration board and the calibration coordinates of the identification code; determining the mapping relationship between the pixel coordinate system and the calibration board coordinate system according to the calibration coordinates and pixel coordinates of the feature points. Through the identification code, such as a two-dimensional code, the calibration coordinates of its specific mark can be obtained without manual marking, saving a lot of time. Almost all of the entire calibration process is automatically achieved with little human participation. Compared with the prior art where the calibration board is manually calibrated, the calibration efficiency and accuracy are improved. Further, in this embodiment, corresponding to the field of view size of the camera, the number of first identification codes per unit area on the edge area of the calibration board is greater than the number of second identification codes per unit area in the central area, so as to avoid the problem that the camera corresponding to the small field of view in the edge area cannot obtain the identification code because the obtained area is small. At the same time, for the camera with a large field of view in the central area, the setting of the second identification code is reduced, thereby simplifying the setting of the calibration board and the processing complexity of the image related to the second identification code.

[0062] Further, based on the above embodiments, with the calibration board 100 in the present application, object positioning can be achieved. Specifically: receiving the object image of the object to be positioned acquired by the camera; determining the pixel coordinates of the object to be positioned in the pixel coordinate system of the camera according to the object image; determining the calibration coordinates of the object to be positioned according to the mapping relationship between the pixel coordinate system and the calibration board coordinate system, where the mapping relationship is determined by the calibration method of the camera as described above; and positioning the object according to the calibration coordinates of the object to be positioned.

[0063] In one embodiment, taking a battery cell as an example of the object to be positioned, as Figure 7 shown, using a calibration tooling, place the battery cell 600 in the center of the printing table 700. The periphery of the calibration tooling can be aligned with the edge of the printing table 700, and there is a hollowed-out area in the middle to place the battery cell 600, to assist in positioning the battery cell 600 on the printing table 700, as Figure 8 shown, adjust the camera to a suitable position. In this example, set four cameras to respectively capture the four corner mark points 601 of the battery cell 600, or as Figure 9 shown, set the middle camera to capture the entire battery cell 600; then place the calibration board 100 on the printing table 700 and take an image. The position fluctuation of the calibration board 100 on the printing table 700 is less than 50 mm. Start to determine the mapping relationship between the pixel coordinate system and the calibration board coordinate system through the calibration board 100 to achieve the positioning of the battery cell.

[0064] In the calibration board of the embodiment of the present application, identification codes with calibration coordinate information are set. By reading the calibration board image captured by the camera, the calibration coordinates corresponding to the identification codes in the image can be automatically obtained, and the feature points of the pattern units in the calibration board are determined through image recognition. And according to the size of the pattern units and the calibration coordinates of the identification codes, the calibration coordinates of each feature point are automatically determined, thereby determining the calibration coordinate set, so that even based on the calibration coordinate set and the pixel coordinate set, the mapping relationship between the calibration board coordinate system and the pixel coordinate system can be determined, thereby realizing the positioning of the specific object to be positioned. Almost the entire positioning process is automatically realized, with less manual participation, saving time. The operator does not need to draw and count the feature points, shortening the positioning time, avoiding errors, with a simple process, reducing the training and learning costs, and novices can easily get started.

[0065] Further, the present utility model provides a calibration system for a camera, including:

[0066] including the calibration board as described above;

[0067] at least one camera, configured to acquire an image of the calibration board, and the image at least includes one identification code;

[0068] a controller, configured to perform camera calibration according to the calibration board image acquired by the camera.

[0069] Among them, the implementation manner of the calibration plate may refer to the above-mentioned implementation manner, and the repeated parts will not be described again.

[0070] In one implementation manner, there are at least two cameras. The cameras can acquire images of different regions of the calibration plate and receive the images of different regions of the calibration plate acquired by each camera. At least one identification code is included in any one of the images, and the identification code contains its corresponding position information, so that at least one position information can be obtained for subsequent determination of the mapping relationship. It should be understood that the number of cameras can be one or more. More identification codes are acquired by multiple cameras, and more position information is obtained, which is more accurate in calculating the feature coordinates and the mapping relationship.

[0071] Each embodiment in this specification is described in a progressive manner. The same or similar parts among the embodiments can be referred to each other, and the key point of each embodiment is to illustrate the differences from other embodiments. In particular, for the system or system embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can refer to the partial description of the method embodiments. The systems and system embodiments described above are only illustrative. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art can understand and implement it without creative work.

[0072] The technical solutions provided in this application have been introduced in detail above. Specific examples are used in this article to elaborate on the principle and implementation manner of this application. The description of the above embodiments is only used to help understand the method and its core idea of this application; at the same time, for those of ordinary skill in the art, according to the idea of this application, there will be changes in the specific implementation manner and application scope. In summary, the content of this specification should not be construed as a limitation to this application.

Claims

1. A calibration plate, characterized in that: The calibration plate includes a central area and an edge area surrounding the central area; A first identification code is provided in the edge area, and a second identification code is provided in the central area. The number of the first identification codes per unit area is greater than the number of the second identification codes per unit area. The first identification code and the second identification code are both provided with their calibration coordinates in the calibration plate coordinate system.

2. The calibration plate according to claim 1, characterized in that: The calibration plate further includes a first pattern unit arranged around the first identification code, and a second pattern unit arranged around the second identification code, and the size of the first pattern unit is smaller than the size of the second pattern unit.

3. The calibration plate according to claim 2, characterized in that: The first pattern units and the second pattern units are both distributed in black and white at intervals.

4. The calibration plate according to claim 2, characterized in that: The pattern unit is a polygonal pattern or a dot.

5. The calibration plate according to claim 2, characterized in that: The size of the first identification code is n times the size of the first pattern unit surrounding the first identification code, and the size of the second identification code is m times the size of the second pattern unit surrounding the first identification code, where n≥2 and m≥2.

6. The calibration plate according to claim 5, characterized in that: Each first identification code and the first pattern units surrounding the first identification code form a first chessboard, a plurality of first chessboards in the edge region are arranged in an array, the first chessboard is a square, and the first identification code is located at the center of the first chessboard; The second identification code and the second pattern units surrounding the second identification code form a second chessboard, the second chessboard is a square, and the second identification code is located at the center of the second chessboard.

7. The calibration plate according to claim 1, characterized in that: The size of the first identification code is smaller than the size of the second identification code; and / or; The edge region includes a plurality of sub-edge regions, and the first identification codes in the plurality of sub-edge regions have the same size.

8. The calibration plate according to claim 1, characterized in that: The first identification codes are arranged in an array on the calibration plate; and / or; The second identification codes are arranged in an array on the calibration code; and / or; The identification code is at least one of a two-dimensional code, a bar code or a digital code.

9. The calibration plate according to any one of claims 1 to 8, characterized in that: The calibration plate is provided with fool-proof marks.

10. The calibration plate according to claim 9, characterized in that: The calibration plate further includes a blank area arranged outside the edge area, and the fool-proof mark is arranged in the blank area.

11. The calibration plate according to any one of claims 1 to 8, characterized in that: The calibration plate includes a transparent substrate and the first identification code and the second identification code formed on the transparent substrate.

Images