Two-dimensional rigid body universal deviation correction method based on local information backtracking and terminal equipment

Abstract

The invention relates to the field of LCD panel display automatic deviation correction, and discloses a local information backtracking-based two-dimensional rigid body universal deviation correction method and terminal equipment, which can be suitable for a multi-camera automatic system needing to quickly approach a clear target in a visual field, and the deviation correction method comprises the following steps: obtaining all types of template images under the visual field of each camera; then, according to the visual calibration matrix and an information backtracking algorithm, the movement amount of the platform is rapidly calculated on the premise that the rotation center of the platform does not need to be calculated, and accurate deviation correction is achieved; the motion distance of the platform can be adjusted in real time according to the image in the visual field of the camera, proper exposure time can be kept under the condition that the contrast ratio of the selected target and the background part is large, the underexposure or overexposure phenomenon is avoided, the motion platform moves rapidly, and then the center of the target approaches the center of the template image; and the high-precision alignment efficiency and stability of the equipment are improved.

Description

Technical Field

[0001] The invention relates to the field of automatic deviation correction of LCD panel display, and in particular to a two-dimensional rigid body universal deviation correction method and terminal equipment based on local information backtracking. Background Art

[0002] To improve production efficiency, automation systems play a very important role in industrial applications and manufacturing. In addition, to promote high output, using visual servo systems to perform more precise assembly can obtain stable and high-quality results to replace manual labor.

[0003] Precision alignment provides the possibility of improving production quality during the processing or assembly of products, especially under the condition of reduced size. The mechanisms that usually realize this function include precision motion, rotation mechanism and feedback system. With the improvement of computing efficiency, vision systems also provide significant alignment, detection and quality inspection functions in many applications such as semiconductors, liquid crystal displays (LCDs), automobiles, and food industries.

[0004] Among precision mechanisms, there are two types of displacement and rotation stages commonly used in industrial applications; the XYθ and UVW or XXY types. The UVW type is compact in size and thinner than the XYθ type, but is limited in displacement and orientation range. In many applications, substrates only need to be adjusted in tiny displacements and orientations, such as printed circuit boards (PCBs), surface mount technology (SMT), integrated circuit packaging, solar cells, etc., to align the substrate parallel to the system.

[0005] For these reasons, the UVW platform is very suitable for precision alignment functions, and for this reason it is necessary to design a universal two-dimensional rigid body correction method based on local information backtracking, a terminal device, and a computer-readable storage medium. Summary of the invention

[0006] In order to overcome the above-mentioned shortcomings, the present invention provides a two-dimensional rigid body universal correction method and terminal device based on local information backtracking, so as to solve the problems in the prior art of difficulty in calculating the rotation center of the platform, unsatisfactory target recognition and grasping effect, and affecting the stability and accuracy of the correction.

[0007] The present invention provides a general two-dimensional rigid body correction method based on local information backtracking. The correction method is applicable to a multi-camera automation system that needs to quickly approach a clear target within a field of view, and includes the following correction steps: Step S1, making a ROI template image, obtaining the actual center of the template image, and then obtaining the actual deviation correction distance of the platform through a visual calibration algorithm combined with a local information backtracking algorithm; Step S2: If the center of the template image does not meet the predetermined value of the predetermined center, then step S1 is repeated while excluding other external interferences until the center of the template image meets the predetermined value of the predetermined center, thereby achieving accurate correction.

[0008] Furthermore, in step S1, the ROI template image is algorithmically processed, that is, an effective and accurate template center is obtained according to image algorithms including grayscale center method, edge contour method and manual selection method, and then visual calibration is performed based on the template center and information in the local area of ​​the platform is obtained.

[0009] Further, in step S2, the predetermined values ​​that do not meet the predetermined center include: S2.1, the center of the template image deviates far from the predetermined center; S2.2, the template image contains redundant factors; S2.3. Poor accuracy suddenly occurs during the correction process; When a situation occurs that does not meet the predetermined center value, the initial ROI template image in step S1 is processed by image algorithm, and the template image after algorithm processing is slightly adjusted. The adjustment method includes adjusting the ROI image center and eliminating any one or more of redundant factors to generate an accurate and clear template image. The real-time image of the platform is then positioned according to the center of the template image, and the actual correction distance of the platform is calculated through the matrix obtained by visual calibration and local information backtracking.

[0010] Furthermore, the multi-camera automation system includes more than two cameras. In step S1, the visual calibration algorithm is based on the image center taken by each camera, and then combined with the layout information of each camera as a reference, to construct a mathematical model of the local information backtracking algorithm, and to construct the relationship between the image center and the platform rotation center in an ideal state as a reference position. The relationship of the reference position is expressed by the following equation: ; Where x0 and y0 represent the rotation center of the motion platform, α1 and α2 represent the global coordinate angle between the camera center and the right-handed coordinate system, and rccd1 and rccd2 represent the distances from the two cameras to the rotation center.

[0011] Furthermore, a rotation angle σθ is arranged on the platform at the reference position, and the relationship between the image center and the platform after the rotation σθ in the ideal state is constructed as the new position. The relationship of the new position is expressed by the following equation: ; Where x′ccd1, y′ccd1, x′ccd2 and y′ccd2 represent the coordinates of the new position after rotation σθ, and the difference between the reference position and the new position is expressed by the following equation: ; Where σxccd1 and σxccd2 represent the offset distances of the two cameras in the X direction, Sx and Sy represent the sum and difference of the two cameras in the X and Y directions, L represents the length of the line between the center points of the two cameras, Lx represents the distance between the two cameras parallel to the X direction, and Ly represents the distance between the two cameras parallel to the Y direction.

[0012] Furthermore, the visual calibration algorithm includes the following process according to the logical relationship between the reference position and the new position: S1.1. Perform algorithm matching processing on the template image to obtain the center of the real-time image, and obtain the relationship between the center of the template and the center of the real-time image; S1.2. Treat the movement of the equipment platform as rigid body motion, including translation and rotation, and perform reverse calculation based on logical relationships.

[0013] Furthermore, the visual calibration process establishes a mathematical equation based on the changes in the camera's field of view caused by the platform movement, which is specifically represented by the following equation: .

[0014] Furthermore, in the mathematical model, the functional relationship between the rotation angles of the two cameras is expressed as follows: ; In the mathematical model, the correction distance of the device platform is obtained using the functional relationship of the camera rotation angle, which is expressed by the following equation: ; Among them, σxccd1, σxccd2, σyccd1 and σyccd2 are known values ​​obtained by image processing technology; the direction of the substrate can be interpolated by inverting fx(σθ) and fy(σθ), which are established in the calibration procedure; then σxccd1(σθ)+σxccd2(σθ) and σyccd1(σθ)+σyccd2(σθ) are calculated during the calibration process.

[0015] The terminal device includes a memory, a processor and a computer program. The computer program is stored in the memory and can be run on the processor. When the processor executes the computer program, the correction steps are implemented according to the general correction method for two-dimensional rigid bodies based on local information backtracking as described above.

[0016] A readable storage medium stores a computer program, and when the computer program is executed by a processor, the correction steps of the correction method based on local information backtracking described above are executed.

[0017] Compared with the prior art, the present invention has the following beneficial effects: 1. It can obtain all types of template images under the field of view of each camera, and then quickly calculate the platform movement amount based on the visual calibration matrix and information backtracking algorithm without calculating the platform rotation center, so as to achieve accurate correction; 2. It can adjust the platform movement distance in real time according to the image in the camera's field of view. When the contrast between the selected target and the background is large, it can maintain the appropriate exposure time to avoid underexposure or overexposure, so that the moving platform can move quickly and the target center can approach the template image center, improving the efficiency and stability of high-precision alignment of the equipment.

[0018] Additional aspects and advantages of the present invention will be given in part in the following description and in part will be obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. 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 paying creative labor.

[0020] Figure 1 Schematic diagram of the implementation of a two-dimensional rigid body universal deviation correction method based on local information backtracking provided by an embodiment of the present invention; Figure 2 It is a structural schematic diagram of a deviation correction device based on local information backtracking provided by an embodiment of the present invention; Figure 3 It is a structural diagram of another type of motion workbench; Figure 4 is a schematic diagram of the relationship between the camera real-time image and the template image provided by an embodiment of the present invention; Figure 5 It is a calibration flow chart of a two-dimensional rigid body universal deviation correction method based on local information backtracking provided by an embodiment of the present invention; Figure 6 It is a schematic diagram of image changes before and after the two-dimensional rigid body universal correction method based on local information backtracking provided by an embodiment of the present invention is applied; Figure 7 It is a schematic diagram of the structure of a terminal device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0021] The technical solution of the present invention will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments.

[0022] The components of the embodiments of the present invention generally described and shown in the drawings herein may be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the drawings is not intended to limit the scope of the claimed invention, but merely represents selected embodiments of the present invention.

[0023] Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in the field without making any creative work shall fall within the scope of protection of the present invention.

[0024] In the description of the present invention, it should be noted that the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc., indicating the orientation or positional relationship, are based on the orientation or positional relationship shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, the terms "first", "second", and "third" are used for descriptive purposes only, and cannot be understood as indicating or implying relative importance.

[0025] In the description of the present invention, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0026] In the attached Figure 1-7 In the figure, CCD1 represents the first camera 22 and CCD2 represents the second camera 25.

[0027] refer to Figure 1 The present invention provides a two-dimensional rigid body universal deviation correction method based on local information backtracking, which is applicable to a multi-camera automation system that needs to quickly approach a clear target within a field of view. The method includes: Step S1, making a ROI template image, and obtaining the actual center of the template image according to image algorithms including grayscale center method, edge contour method and manual selection method, and finally obtaining the actual deviation correction distance of the platform through visual calibration algorithm combined with local information backtracking algorithm; Step S2: If the center of the template image deviates far from the predetermined center, or the template image contains many redundant factors, or the accuracy is suddenly poor during the correction process, then, after confirming that there is no other external interference, repeat step S1 until the center of the template image is infinitely close to the predetermined center or the redundant factors are eliminated or the correction accuracy meets the specification requirements by adjusting the algorithm inside the image, thereby achieving precise correction.

[0028] refer to Figure 2 and Figure 3 The multi-camera automation system that needs to quickly approach a clear target in the field of view mainly includes: a display device 21, a first camera 22, a motion workbench 23, a second camera 25 and a carrying device 26. The product glass 24 is placed on the motion workbench 23, and the obvious marks on the product glass 24 appear in the fields of view of the first camera 22 and the second camera 25 at the same time. The first camera 22 and the second camera 25 simultaneously capture the obvious marks on the product glass 24. The software carrying the two-dimensional rigid body universal correction method based on local information backtracking in the display device 21 performs calculations to obtain the actual correction distance, and the motion workbench 23 completes the corresponding correction movement, and then refers to Figure 6 , which enables precise alignment of multi-camera automated systems that need to quickly approach clear targets within the field of view.

[0029] refer to Figure 4 , showing the relationship between the reference fiducial marker and the new fiducial marker in the camera field of view. The differences between the reference pattern and the new pattern positions at the first camera 22 are σxccd1 and σyccd1, and at the second camera 25 are σxccd2 and σyccd2.

[0030] In some embodiments, Figure 4 The relationship shown in FIG. 2 and before the deviation correction action of the moving workbench 23 is realized, the following steps are also included: accomplish Figure 1 The mathematical model shown in the figure provides a foundation for the two-dimensional rigid body general correction method based on local information backtracking. The mathematical model facilitates the processing of subsequent algorithms. The explanation of the mathematical model includes: Starting from the mathematical model, the relationship between the image center and the platform rotation center in the ideal state is constructed, and the relationship between the image center and the rotation angle is obtained as follows: ; Where x0 and y0 represent the rotation center of the motion platform, α1 and α2 represent the angle between the camera center and the global coordinate of the right-handed coordinate system, rccd1 and rccd2 represent the distances from the two cameras to the rotation center, and L represents the length of the two cameras. Here, a small rotation angle σθ is given by the motion table 23; the new position is given by the following equation: ; Among them, x′ccd1, y′ccd1, x′ccd2 and y′ccd2 represent the coordinates of the new position after rotation σθ, and the difference between the reference position and the new position can be expressed as: ; σxccd1 and σxccd2 represent the offsets of camera 1 and camera 2 in the X direction, respectively. Sx and Sy represent the sum and difference of the two cameras in the X and Y directions, respectively. After expanding their geometric relationship using Taylor's formula, we can get their obvious logical connection, that is, the sum and difference of the two cameras are polynomial functions of the direction, and their relative relationship can be constructed during the calibration process.

[0031] In some embodiments, it is necessary to solve the algorithmic relationship between the parallel movement and rotational movement of the motion table 23 and the actual correction, and the relationship between the reference mark and the real-time mark in the camera field of view, including: establishing a mathematical equation based on the changes generated by the motion table 23 in the camera field of view, specifically expressed as: .

[0032] After a reasonable arrangement of the mathematical model, the relationship between the rotation angle and the function can be obtained: ; In addition, the correction distance of the device platform is obtained through the rotation angle and function relationship: ; Among them, σxccd1, σxccd2, σyccd1 and σyccd2 are known values ​​obtained by image processing technology, and the direction of the substrate can be interpolated by inverting fx(σθ) and fy(σθ), which are established in the calibration procedure, and then σxccd1(σθ)+σxccd2(σθ) and σyccd1(σθ)+σyccd2(σθ) can be calculated through the calibration process.

[0033] Depend on Figure 5 It can be seen that the two-dimensional rigid body general correction method based on local information backtracking provided by the embodiment of the present invention requires camera calibration, which facilitates the subsequent conversion of information data collected by the first camera 22 and the second camera 25 into the actual movement of the motion platform 23, thereby improving the accuracy of equipment correction.

[0034] Camera calibration is an important process to correspond the corresponding pixel size to the physical size. During the calibration process, the relationship between the two cameras is also constructed, which is expressed as: ; Figure 5The calibration process is shown. After calibration, the pixel size and orientation of the camera can be obtained. Through calculation, σyccd2(σθ)-σyccd1(σθ) and σxccd2(σθ)-σxccd1(σθ) are linearly related to the rotation angle in the experimental setting because the two cameras are located on both sides of the rotation center.

[0035] The two-dimensional rigid body universal correction method based on local information backtracking provided by the embodiment of the present invention requires parallel movement and rotational movement of the motion platform 23 when performing camera calibration. At the same time, the first camera 22 and the second camera 25 need to obtain pixel coordinates at the points after the movement. The calibration flow chart is as follows: Figure 5 As shown, it includes a parallel movement mode 41 of the motion platform 23 and a rotational movement mode 42 of the motion platform 23 .

[0036] It should be understood that the order of execution of the steps in the above embodiment does not necessarily mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present invention.

[0037] Corresponding to the two-dimensional rigid body universal correction method based on local information backtracking in the above embodiment, refer to Figure 6 , the imaging effect of the first camera 22 and the second camera 25 in the field of view before and after the correction can be visually viewed.

[0038] refer to Figure 2 , Figure 3 and Figure 7 The two-dimensional rigid body universal deviation correction method device based on local information backtracking includes: an implementation module 20 of the two-dimensional rigid body universal deviation correction method based on local information backtracking and a control module 60 for motion control and algorithm processing.

[0039] In some embodiments, the correction device based on local information backtracking is also provided, and the imaging effect display in the field of view of the first camera 22 and the second camera 25 before and after the correction is provided: refer to Figure 6 Before the correction device based on local information backtracking provided by the embodiment of the present invention is used for correction, the effects are as follows: a template reference image 51 in the field of view of the first camera 22, a real-time reference image 52 in the field of view of the first camera 22; a template reference image 53 in the field of view of the second camera 25, a real-time reference image 54 in the field of view of the second camera 25; After the correction is performed using the correction device based on local information backtracking provided in the embodiment of the present invention, the effect is: the template reference image and the real-time reference image 55 in the field of view of the first camera 22 are aligned with each other; the template reference image and the real-time reference image 56 in the field of view of the second camera 25 can also be aligned with each other.

[0040] like Figure 7 As shown, the terminal device of the embodiment of the present invention includes: a motion control card 61, a processor 62, a memory 63, and a computer program 64 stored in the memory 63 and can be run on the processor 62 through the motion control card 61. The computer program 64 is a program for implementing the two-dimensional rigid body universal deviation correction method based on local information backtracking. When the processor 62 executes the computer program 64, the steps in the embodiment of the two-dimensional rigid body universal deviation correction method based on local information backtracking can be implemented to obtain Figure 1 The algorithm model shown in the figure, when the processor 62 executes the computer program 64, the functions of each module in the above-mentioned device embodiments are realized, for example Figure 5 The functions of the parallel movement mode 41 and the rotational movement mode 42 of the modules shown, when the processor 62 executes the computer program 64, realizes the functions of each module in the above-mentioned device embodiments, for example Figure 6 The alignment function between the template reference image and the real-time reference image is shown.

[0041] Exemplarily, the computer program 64 can be divided into one or more program modules, one or more program modules are stored in the memory 63 and executed by the processor 62 to complete the embodiment. The one or more program modules can be a series of computer program instruction segments that can complete specific functions. The instruction segments are used to describe the execution process of the computer program 64 in the two-dimensional rigid body general correction method based on local information backtracking or the terminal device 60. For example, the computer program 64 can be divided into an implementation method of the two-dimensional rigid body general correction method based on local information backtracking implementation module 20 and an algorithm processing control module 60. Each module adopts a module known in the prior art, and the present invention does not protect the module itself, so the specific functions of each module will not be repeated here one by one.

[0042] The terminal device 60 may be a computing device such as a desktop computer, a notebook, a PDA, or a cloud server. The terminal device 60 may include but is not limited to: a processor 62 and a memory 63. Those skilled in the art will appreciate that Figure 7 This is only one example of the terminal device 60 and does not constitute a limitation on the terminal device 60. The terminal device 60 may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the terminal device may also include input and output devices, network access devices, buses, etc.

[0043] The processor 62 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may be any conventional processor.

[0044] The memory 63 may be an internal storage unit of the terminal device 60, such as a hard disk or memory of the terminal device 60, or the memory 63 may be an external storage device of the terminal device 60, such as a plug-in hard disk, a smart media card (SMC), a secure digital card (SD), a flash card (FlashCard), etc. equipped on the terminal device 60.

[0045] Furthermore, the memory 63 may also include both an internal storage unit of the terminal device 60 and an external storage device. The memory 63 is used to store computer programs and other programs and data required by the terminal device 60. The memory 63 may also be used to temporarily store data that has been output or is to be output.

[0046] The terminal device 60 of the present invention is only used as a carrier for running the above-mentioned two-dimensional rigid body universal correction method based on local information backtracking. It is not necessary to use a completely identical terminal device. It can be understood that when the two-dimensional rigid body universal correction method based on local information backtracking of the present invention is run on any program, it will fall within the protection scope of the present invention.

[0047] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In actual applications, the above-mentioned functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device is divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated in one processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0048] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0049] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0050] In the embodiments provided by the present invention, it should be understood that the disclosed devices / terminal equipment and methods can be implemented in other ways; for example, the device / terminal equipment embodiments described above are merely schematic, for example, the division of modules or units is only a logical function division, and there may be other division methods in actual implementation, for example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, and the indirect coupling or communication connection of devices or units can be electrical, mechanical or other forms.

[0051] 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 on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0052] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0053] If the integrated module / unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, the steps of the above-mentioned various method embodiments can be implemented, wherein the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, the computer-readable medium does not include electric carrier signals and telecommunication signals.

[0054] The embodiments described above are only used to illustrate the technical solutions of the present invention, and are not intended to impose any formal restrictions on the shape, material, structure, etc. of the present invention. Any simple modifications, equivalent changes and modifications made to the above embodiments based on the technical essence of the present invention shall fall within the protection scope of the technical solutions of the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions recorded in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the ideas and scope of the technical solutions of the embodiments of the present invention, and shall all be included in the protection scope of the present invention.

Claims

1. A two-dimensional rigid body general correction method based on local information backtracking, which is applicable to a multi-camera automation system that needs to quickly approach a clear target within the field of view, and is characterized by: The following correction steps are included: Step S1, making a ROI template image, obtaining the actual center of the template image, and then obtaining the actual deviation correction distance of the platform through a visual calibration algorithm combined with a local information backtracking algorithm; Step S2: If the center of the template image does not meet the predetermined value of the predetermined center, then step S1 is repeated while excluding other external interferences until the center of the template image meets the predetermined value of the predetermined center, thereby achieving accurate correction.

2. The two-dimensional rigid body universal deviation correction method based on local information backtracking according to claim 1 is characterized in that: In step S1, the ROI template image is algorithmically processed, that is, an effective and accurate template center is obtained according to image algorithms including grayscale center method, edge contour method and manual selection method, and then visual calibration is performed based on the template center and information in the local area of ​​the platform is obtained.

3. The two-dimensional rigid body universal deviation correction method based on local information backtracking according to claim 1 is characterized in that: In step S2, the predetermined values ​​that do not meet the predetermined center include: S2.1, the center of the template image deviates far from the predetermined center; S2.2, the template image contains redundant factors; S2.

3. Poor accuracy suddenly occurs during the correction process; When a situation occurs that does not meet the predetermined center value, the initial ROI template image in step S1 is processed by image algorithm, and the template image after algorithm processing is slightly adjusted. The adjustment method includes adjusting the ROI image center and eliminating any one or more of redundant factors to generate an accurate and clear template image. The real-time image of the platform is then positioned according to the center of the template image, and the actual correction distance of the platform is calculated through the matrix obtained by visual calibration and local information backtracking.

4. The two-dimensional rigid body universal correction method based on local information backtracking according to any one of claims 1 to 3, characterized in that: The multi-camera automation system includes more than two cameras. In step S1, the visual calibration algorithm is based on the image center taken by each camera, and then combined with the layout information of each camera as a reference to build a mathematical model of the local information backtracking algorithm, and build the relationship between the image center and the platform rotation center under the ideal state as the reference position. The relationship of the reference position is expressed by the following equation: ； Where x0 and y0 represent the rotation center of the motion platform, α1 and α2 represent the global coordinate angle between the camera center and the right-handed coordinate system, and rccd1 and rccd2 represent the distances from the two cameras to the rotation center.

5. The two-dimensional rigid body universal deviation correction method based on local information backtracking according to claim 4 is characterized in that: Arrange a rotation angle σθ on the platform at the reference position, and construct the relationship between the image center and the platform after rotation σθ in the ideal state as the new position. The relationship of the new position is expressed by the following equation: ； Where x′ccd1, y′ccd1, x′ccd2 and y′ccd2 represent the new position coordinates after rotation σθ respectively.

6. The two-dimensional rigid body universal deviation correction method based on local information backtracking according to claim 5 is characterized in that: The difference between the reference position and the new position is expressed by the following equation: ； Where σxccd1 and σxccd2 represent the offset distances of the two cameras in the X direction, Sx and Sy represent the sum and difference of the two cameras in the X and Y directions, L represents the length of the line between the center points of the two cameras, Lx represents the distance between the two cameras parallel to the X direction, and Ly represents the distance between the two cameras parallel to the Y direction.

7. The two-dimensional rigid body universal deviation correction method based on local information backtracking according to claim 6 is characterized in that: The visual calibration algorithm includes the following processes according to the logical relationship between the reference position and the new position: S1.

1. Perform algorithm matching processing on the template image to obtain the center of the real-time image, and obtain the relationship between the center of the template and the center of the real-time image; S1.

2. Treat the movement of the equipment platform as rigid body motion, including translation and rotation, and perform reverse calculation based on logical relationships.

8. The two-dimensional rigid body universal deviation correction method based on local information backtracking as claimed in claim 7, characterized in that: The process of visual calibration establishes a mathematical equation based on the changes in the camera's field of view caused by platform movement, which is specifically expressed by the following equation: 。 9. The two-dimensional rigid body universal deviation correction method based on local information backtracking as claimed in claim 8, characterized in that: In the mathematical model, the functional relationship between the rotation angles of the two cameras is expressed as follows: ； In the mathematical model, the correction distance of the device platform is obtained using the functional relationship of the camera rotation angle, which is expressed by the following equation: ； Among them, σxccd1, σxccd2, σyccd1 and σyccd2 are known values ​​obtained by image processing technology; the direction of the substrate can be interpolated by inverting fx(σθ) and fy(σθ), which are established in the calibration procedure; then σxccd1(σθ)+σxccd2(σθ) and σyccd1(σθ)+σyccd2(σθ) are calculated during the calibration process.

10. A terminal device comprising a memory, a processor and a computer program, wherein the computer program is stored in the memory and can be run on the processor, characterized in that: When the processor executes the computer program, the correction step is implemented according to the general correction method for two-dimensional rigid body based on local information backtracking as described in any one of claims 1 or 2 or 3 or 5 or 6 or 7 or 8 or 9.

Images