Calibration methods, apparatus, electronic devices and readable storage media

Abstract

This application relates to a calibration method, apparatus, electronic device, and readable storage medium. The method includes the steps of: sending a movement command to a motion mechanism to move a target reference object to a first coordinate corresponding to the movement command, wherein the first coordinate is based on a motion coordinate system corresponding to the motion mechanism; matching a target model corresponding to the target reference object in a preset model; determining a second coordinate on the target model corresponding to the first coordinate, wherein the second coordinate is based on a visual coordinate system corresponding to the vision system; and performing calibration operations on the motion mechanism and the vision system using the first and second coordinates. By matching a target model corresponding to the target reference object, the calibration parameters, namely the first and second coordinates, are automatically obtained without the need for manual positioning of the target reference object, thus improving calibration efficiency. Simultaneously, the correspondence between the target model and the target reference object ensures the accuracy of the calibration operation.

Description

Technical Field

[0001] This application relates to the field of industrial automation, and more particularly to a calibration method, apparatus, electronic device, and readable storage medium. Background Technology

[0002] The widespread application of machine vision has made industrial automation possible. Automated equipment equipped with image processing has more powerful functions, which not only greatly improves production efficiency but also reduces labor and equipment costs. In the process of vision guidance, the calibration of the vision system and motion system is indispensable. However, existing calibration methods usually use elements on the product as image features, which is highly dependent on the product. Each time the product is changed, manual recalibration is required, resulting in low calibration efficiency and accuracy. Summary of the Invention

[0003] This application provides a calibration method, apparatus, electronic device, and readable storage medium, aiming to solve the technical problems of low efficiency and low accuracy in the calibration of vision systems and motion systems in the prior art.

[0004] To solve the above-mentioned technical problems, or at least partially solve them, this application provides a calibration method, the method comprising the steps of:

[0005] A movement command is sent to the motion mechanism to move the target reference object to the first coordinate corresponding to the movement command, wherein the first coordinate is based on the motion coordinate system corresponding to the motion mechanism;

[0006] Match the target model corresponding to the target reference object in the preset model;

[0007] A second coordinate corresponding to the first coordinate is determined on the target model, wherein the second coordinate is based on the visual coordinate system corresponding to the visual system;

[0008] The motion mechanism and the vision system are calibrated using the first coordinate and the second coordinate.

[0009] Optionally, the step of matching the target model corresponding to the target reference in the preset model includes:

[0010] Receive a model generation instruction and obtain the model parameters in the model generation instruction, wherein the model parameters include shape symbols and size parameters;

[0011] Match the base model corresponding to the shape mark, wherein the base model is a reference mark shape model;

[0012] The dimensions of the basic model are adjusted according to the size parameters to obtain the preset model corresponding to the model generation instruction.

[0013] Optionally, the step of adjusting the size of the basic model according to the size parameters to obtain the preset model corresponding to the model generation instruction includes:

[0014] Obtain the background parameters from the model generation instruction, and generate the model background based on the background parameters;

[0015] The dimensions of the basic model are adjusted according to the stated dimension parameters;

[0016] The adjusted base model is drawn on the model background to obtain the preset model corresponding to the model generation instruction.

[0017] Optionally, the step of matching the target model corresponding to the target reference object in the preset model includes:

[0018] Acquire image data containing the target reference object;

[0019] The image data is used to identify the feature information of the target reference object;

[0020] Match the target model corresponding to the feature information in the preset model.

[0021] Optionally, the step of identifying the feature information of the target reference object by recognizing the image data includes:

[0022] Determine the region of interest corresponding to the target reference object in the image data;

[0023] Contour information is obtained by extracting the contour of the target reference object in the region of interest;

[0024] The contour information is used as the feature information.

[0025] Optionally, the step of matching the target model corresponding to the feature information in the preset model includes:

[0026] The similarity between the feature information and each of the preset models is calculated to obtain the similarity between each preset model.

[0027] The preset model with the highest similarity is taken as the target model.

[0028] Optionally, the step of calculating the similarity between the feature information and each of the preset models includes:

[0029] Obtain the pyramid model corresponding to the preset model. The pyramid model includes multiple levels, and the information richness of the corresponding levels increases sequentially from top to bottom.

[0030] Match the target model corresponding to the feature information in the hierarchy from top to bottom;

[0031] For each level, the information richness corresponding to the feature information is converted into information richness corresponding to the level, and the similarity is calculated with the matching model determined in the previous level.

[0032] The preset model whose similarity meets the preset matching conditions is used as the matching model corresponding to the current level.

[0033] To achieve the above objectives, the present invention also provides a calibration device, the calibration device comprising:

[0034] A first sending module is configured to send a movement command to a motion mechanism, so that the motion mechanism moves a target reference object to a first coordinate corresponding to the movement command, wherein the first coordinate is based on the motion coordinate system corresponding to the motion mechanism;

[0035] The first matching module is used to match the target model corresponding to the target reference object in the preset model;

[0036] The first determining module is used to determine a second coordinate on the target model corresponding to the first coordinate, wherein the second coordinate is based on the visual coordinate system corresponding to the visual system;

[0037] The first execution module is used to perform calibration operations on the motion mechanism and the vision system using the first coordinate and the second coordinate.

[0038] To achieve the above objectives, the present invention also provides an electronic device, the electronic device including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program, when executed by the processor, implements the steps of the calibration method as described above.

[0039] To achieve the above objectives, the present invention also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the calibration method described above.

[0040] This invention proposes a calibration method, apparatus, electronic device, and readable storage medium. The method involves sending a movement command to a motion mechanism, causing the motion mechanism to move a target reference object to a first coordinate corresponding to the movement command. The first coordinate is based on the motion coordinate system corresponding to the motion mechanism. A target model corresponding to the target reference object is matched within a preset model. A second coordinate corresponding to the first coordinate is determined on the target model, where the second coordinate is based on the visual coordinate system corresponding to the vision system. Calibration operations are performed on the motion mechanism and the vision system using the first and second coordinates. By matching the target model to the target reference object, the calibration parameters, namely the first and second coordinates, are automatically obtained without the need for manual positioning of the target reference object, improving calibration efficiency. Furthermore, the correspondence between the target model and the target reference object ensures the accuracy of the first and second coordinates, thereby guaranteeing the accuracy of the calibration operation. Attached Figure Description

[0041] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0042] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0043] Figure 1 This is a flowchart illustrating the first embodiment of the calibration method of the present invention;

[0044] Figure 2 This is a schematic diagram of the shape of the reference mark in the calibration method of the present invention;

[0045] Figure 3 This is a schematic diagram of the module structure of the electronic device of the present invention. Detailed Implementation

[0046] It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention. To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present application, and not all of them. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of this application.

[0047] This invention provides a calibration method, referring to Figure 1 , Figure 1 This is a flowchart illustrating the first embodiment of the calibration method of the present invention. The method includes the following steps:

[0048] Step S10: Send a movement command to the motion mechanism so that the motion mechanism moves the target reference to the first coordinate corresponding to the movement command, wherein the first coordinate is based on the motion coordinate system corresponding to the motion mechanism;

[0049] Movement commands are used to instruct the motion mechanism to perform actions; the specific type of motion mechanism can be set based on the actual application scenario, such as a robotic arm or a linear motor.

[0050] The target reference object is the source of parameters for the calibration operation. In this embodiment, calibration refers to determining the transformation relationship between the motion coordinate system of the motion mechanism and the visual coordinate system of the vision system. Therefore, when performing the calibration operation, it is necessary to determine the corresponding coordinates in the motion coordinate system and the visual coordinate system, and then determine the transformation relationship between the two coordinate systems through the coordinates. The target reference object is used to determine the coordinates for calibration.

[0051] The first coordinate is used to indicate the position of the target reference object in the motion coordinate system. It can be understood that the target reference object has a certain volume in space. Therefore, the first coordinate can indicate the position of a specific point of the target reference object that has been set in advance. The number of first coordinates can be one or more, that is, the first coordinates corresponding to multiple points on the target reference object can be obtained at the same time in the motion coordinate system.

[0052] Step S20: Match the target model corresponding to the target reference object in the preset model;

[0053] The target model is a virtual model pre-generated for the reference object; it can be understood that the target model and the target reference object have the same size and shape, that is, the target model and the target reference object have the same mapping in the motion coordinate system and the visual coordinate system, that is, the corresponding points in the target model and the target reference object have the same coordinates in the motion coordinate system and the visual coordinate system.

[0054] Step S30: Determine the second coordinate corresponding to the first coordinate on the target model, wherein the second coordinate is based on the visual coordinate system corresponding to the visual system;

[0055] The second coordinate is used to indicate the position of the point in the visual coordinate system. Since the target model corresponds to the target reference, the second coordinate on the target model that corresponds to the first coordinate should be consistent with the first coordinate of the target reference mapped to the corresponding coordinate in the visual coordinate system. Therefore, the second coordinate in the visual coordinate system that corresponds to the first coordinate can be accurately determined through the target model.

[0056] Step S40: Calibrate the motion mechanism and vision system using the first coordinate and the second coordinate.

[0057] The calibration of the motion mechanism and vision system can be achieved by calculating the transformation relationship between the first coordinate and the second coordinate; the specific calibration method can be set based on the actual application scenario, and is not limited here.

[0058] Understandably, in practical applications, multiple sets of corresponding first and second coordinates can be obtained by sending multiple movement commands to the motion mechanism, and then calibration can be achieved based on these multiple sets of corresponding first and second coordinates.

[0059] This embodiment automatically obtains calibration parameters, namely the first and second coordinates, by matching the target model with the target reference object, without the need for manual positioning of the target reference object. This improves calibration efficiency. At the same time, the correspondence between the target model and the target reference object ensures the accuracy of the first and second coordinates, thereby ensuring the accuracy of the calibration operation.

[0060] Furthermore, in the second embodiment of the calibration method of the present invention based on the first embodiment of the present invention, the step before step S30 includes:

[0061] Step S50: Receive the model generation instruction and obtain the model parameters in the model generation instruction, wherein the model parameters include shape symbols and size parameters;

[0062] Step S60: Match the base model corresponding to the shape mark, wherein the base model is the reference mark shape model;

[0063] Step S70: Adjust the size of the basic model according to the size parameters to obtain the preset model corresponding to the model generation instruction.

[0064] The model generation command is used to instruct the generation of a preset model.

[0065] Model parameters are used to indicate the features of the generated preset model; specifically, the shape flag indicates the shape of the generated preset model, and the size parameter indicates the size of the generated preset model.

[0066] A benchmark mark shape model refers to a model whose shape is a benchmark mark; benchmark marks are constructed using basic geometric shapes, see [link to relevant documentation]. Figure 2 , Figure 2 The diagram illustrates optional reference mark shapes in this embodiment, including circles, rings, rectangles, crosses, rhombuses, L-shapes, triangles, and double frames. It is understood that... Figure 2 The reference mark shape shown is for illustrative purposes only. In actual applications, specific reference mark shapes can be set based on actual application needs. It is understandable that real-world reference objects correspond to the preset model; therefore, the shape of the reference object for the entity displayed is also the reference mark shape.

[0067] After determining the basic model based on the benchmark, the structure of the preset model to be generated can be determined by setting the size of the basic model. The specific size parameters can be set according to actual needs, such as by measuring the size of the real-world reference object and setting the size parameters of the basic model based on the measurement value, thereby obtaining a preset model corresponding to the real-world reference object.

[0068] It is understandable that the specific type of size parameters will be different for different basic shapes. For example, for a basic model of a circle, the size parameter can be the radius; for a basic model of a rectangle, the size parameters can be the length and width; other shapes can be set similarly, which will not be elaborated further.

[0069] In this embodiment, a preset model is generated using a simple reference marker, which reduces the computational load for matching the subsequent target model and speeds up the matching process. The preset model can be obtained by adjusting the size parameters of the basic model, eliminating the need for users to manually generate the model, reducing the complexity of model generation and improving calibration efficiency.

[0070] Further, step S70 includes the following steps:

[0071] Step S71: Obtain the background parameters from the model generation instruction, and generate the model background based on the background parameters;

[0072] Step S72: Adjust the dimensions of the basic model according to the dimension parameters;

[0073] Step S73: Draw the adjusted basic model on the model background to obtain the preset model corresponding to the model generation command.

[0074] Background parameters indicate background features in the preset model. It is understood that when identifying a target reference object, the target reference object has an environmental background. Therefore, this embodiment sets a background in the preset model so that the obtained preset model is consistent with the image of the target reference object obtained in subsequent applications, thereby further improving the accuracy of target model matching.

[0075] Background parameters can be set based on the actual application environment; background parameters include, but are not limited to, pixel precision, color, black brightness, and white brightness.

[0076] After generating the model background based on the background parameters, the preset model can be obtained by drawing the basic model with the set size on the model background.

[0077] This embodiment can further improve the accuracy of target model matching.

[0078] Furthermore, in the third embodiment of the calibration method of the present invention based on the first embodiment, step S20 includes the following steps:

[0079] Step S21: Obtain image data containing the target reference object;

[0080] Step S22: Identify the image data to obtain the feature information of the target reference object;

[0081] Step S23: Match the target model corresponding to the feature information in the preset model.

[0082] Image data is acquired through a vision system; feature information is used to indicate the characteristics of the target reference object.

[0083] After the motion mechanism moves the target reference object to the position corresponding to the movement command, it sends a completion signal to the host computer. After receiving the completion signal, the host computer uses the vision system to acquire image data containing the target reference object, and then identifies the feature information of the target reference object by recognizing the image data. The specific recognition method and the type of feature information can be set according to the actual application needs.

[0084] Before recognizing image data, data processing can be performed to make the recognition more accurate. For example, filtering can enhance the features of the target reference object and the contrast between it and the background; binarization can convert the image data into a binary image; and morphological operations such as dilation and erosion can be used to eliminate interference information in the binary image. Then, recognition operations can be performed on the binary image to obtain feature information.

[0085] Further, step S22 includes the following steps:

[0086] Step S221: Determine the region of interest corresponding to the target reference object in the image data;

[0087] Step S222: Extract the contour of the target reference object in the region of interest to obtain contour information;

[0088] Step S223: Use the contour information as feature information.

[0089] The ROI (Region of Interest) is used to indicate the region where the target reference object is located. The largest bounding rectangle containing the largest connected region in the binarized image is taken as the ROI. It can be understood that the connected region in the binarized image is the region where the target reference object is located. Therefore, the largest bounding rectangle containing the largest connected region can cover the target reference object.

[0090] Determining the region of interest can narrow down the recognition range, thereby improving recognition efficiency.

[0091] The contour information of the target reference object is extracted within the region of interest. It is understood that the contour information reflects the shape characteristics of the target reference object, and the contour information has significant uniqueness in the shape of the reference mark. Therefore, using the contour information as feature information can accurately achieve the matching between the target reference object and the target model. The specific extraction method of the contour can be set according to actual needs. For example, in this embodiment, XLD (eXtendedLine Descriptions, subpixel edges) is used to determine the subpixel edge contour of the target reference object.

[0092] Further, step S23 includes the following steps:

[0093] Step S231: Calculate the similarity between the feature information and each preset model to obtain the similarity corresponding to each preset model;

[0094] Step S232: Select the preset model with the highest similarity as the target model.

[0095] Similarity is used to indicate the degree of similarity between feature information and a pre-defined model. The higher the similarity, the greater the similarity; the lower the similarity, the smaller the similarity. The specific method for calculating similarity can be selected based on the actual application requirements.

[0096] When generating a preset model, the minimum score corresponding to the model can be set based on the different structures and complexities of the model. Only when the similarity is greater than the minimum score is it considered that it is possible to match the feature information. Therefore, the preset models that may match can be determined first by the minimum score, and then the final target model can be determined from the preset models that may match.

[0097] In practical applications, there may be situations where multiple target references exist in an image at the same time, and multiple target references overlap. When generating a preset model, the number of matches and the maximum overlap can be set so that independent target references and overlapping target references can be distinguished during matching.

[0098] Further, step S231 includes the following steps:

[0099] Step S2311: Obtain the pyramid model corresponding to the preset model. The pyramid model includes multiple levels, and the information richness of the corresponding levels increases sequentially from top to bottom.

[0100] Step S2312: Match the target model corresponding to the feature information in the hierarchy from top to bottom;

[0101] Step S2313: For each level, convert the information richness corresponding to the feature information into information richness corresponding to the level, and calculate the similarity with the matching model determined in the previous level.

[0102] Step S2314: Use the preset model whose similarity meets the preset matching conditions as the matching model corresponding to the current level.

[0103] Information richness is used to indicate the amount of data processed; information richness can be image size or resolution. Understandably, the higher the information richness, the greater the amount of data processed and the longer the processing time; conversely, the lower the information richness, the smaller the amount of data processed and the shorter the processing time.

[0104] If feature information is directly matched with a preset model, the amount of data to be processed is large. In this embodiment, a pyramid model is set up to perform a fast preliminary match first through the level with lower information richness, and then to determine the accurate target model through the level with higher information richness. Specifically, at the top level, the feature information is converted into the minimum information richness, and each preset model is also converted to the minimum information richness. By calculating the similarity with each preset model, the preset model with a similarity greater than a preset threshold is used as the matching model for the current level and moves to the next level. The information richness of the feature information and the matching model is increased to match the current level, and the similarity between the feature information and the matching model is calculated. The matching model corresponding to the current level is determined based on the similarity to further narrow down the range of matching models. This process is repeated until the last level, at which the final target model is determined.

[0105] This embodiment can achieve accurate matching of the target model.

[0106] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, as some steps may be performed in other orders or simultaneously according to this application. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions and modules involved are not necessarily essential to this application.

[0107] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods according to the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods of the various embodiments of this application.

[0108] This application also provides a calibration apparatus for implementing the above-described calibration method, the calibration apparatus comprising:

[0109] The first sending module is used to send a movement command to the motion mechanism so that the motion mechanism moves the target reference object to the first coordinate corresponding to the movement command, wherein the first coordinate is based on the motion coordinate system corresponding to the motion mechanism;

[0110] The first matching module is used to match the target model corresponding to the target reference object in the preset model;

[0111] The first determining module is used to determine the second coordinates corresponding to the first coordinates on the target model, wherein the second coordinates are based on the visual coordinate system corresponding to the visual system;

[0112] The first execution module is used to perform calibration operations on the motion mechanism and vision system using the first coordinate and the second coordinate.

[0113] This calibration device automatically obtains calibration parameters, namely the first and second coordinates, by matching the target model with the target reference object, eliminating the need for manual positioning of the target reference object. This improves calibration efficiency. At the same time, the correspondence between the target model and the target reference object ensures the accuracy of the first and second coordinates, thereby guaranteeing the accuracy of the calibration operation.

[0114] It should be noted that the first sending module in this embodiment can be used to execute step S10 in this application embodiment, the first matching module in this embodiment can be used to execute step S20 in this application embodiment, the first determining module in this embodiment can be used to execute step S30 in this application embodiment, and the first execution module in this embodiment can be used to execute step S40 in this application embodiment.

[0115] Furthermore, the device also includes:

[0116] The first receiving module is used to receive the model generation instruction and obtain the model parameters in the model generation instruction, wherein the model parameters include shape marks and size parameters;

[0117] The second matching module is used to match the base model corresponding to the shape mark, where the base model is the reference mark shape model;

[0118] The second execution module is used to adjust the size of the basic model according to the size parameters to obtain the preset model corresponding to the model generation instruction.

[0119] Furthermore, the second execution module includes:

[0120] The first acquisition submodule is used to acquire the background parameters in the model generation instruction and generate the model background based on the background parameters;

[0121] The first adjustment submodule is used to adjust the size of the basic model according to the size parameters;

[0122] The first drawing submodule is used to draw the adjusted base model on the model background to obtain the preset model corresponding to the model generation command.

[0123] Furthermore, the first matching module includes:

[0124] The second acquisition submodule is used to acquire image data containing the target reference object;

[0125] The first recognition submodule is used to identify the feature information of the target reference object by recognizing the image data;

[0126] The first matching submodule is used to match the target model corresponding to the feature information in the preset model.

[0127] Furthermore, the first identification submodule includes:

[0128] The first determining unit is used to determine the region of interest corresponding to the target reference object in the image data;

[0129] The first extraction unit is used to extract the contour of the target reference object in the region of interest to obtain contour information;

[0130] The first execution unit is used to treat contour information as feature information.

[0131] Furthermore, the first matching submodule includes:

[0132] The first calculation unit is used to calculate the similarity between the feature information and each preset model to obtain the similarity corresponding to each preset model.

[0133] The second execution unit is used to select the preset model with the highest similarity as the target model.

[0134] Furthermore, the second execution unit includes:

[0135] The first acquisition subunit is used to acquire the pyramid model corresponding to the preset model. The pyramid model includes multiple levels, and the information richness of the corresponding levels increases sequentially from top to bottom.

[0136] The first matching subunit is used to match the target model corresponding to the feature information in the hierarchy from top to bottom;

[0137] The first transformation subunit is used to convert the information richness corresponding to the feature information into information richness corresponding to the level for each level, and calculate the similarity with the matching model determined in the previous level.

[0138] The first execution subunit is used to use the preset model whose similarity meets the preset matching conditions as the matching model corresponding to the current level.

[0139] It should be noted that the examples and application scenarios implemented by the above modules and corresponding steps are the same, but are not limited to the content disclosed in the above embodiments. It should also be noted that the above modules, as part of the device, can be implemented in software or hardware, wherein the hardware environment includes a network environment.

[0140] Reference Figure 3 In terms of hardware structure, the electronic device may include components such as a communication module 10, a memory 20, and a processor 30. In the electronic device, the processor 30 is connected to both the memory 20 and the communication module 10. The memory 20 stores a computer program, which is executed by the processor 30. When the computer program is executed, it implements the steps of the above-described method embodiments.

[0141] The communication module 10 can connect to external communication devices via a network. The communication module 10 can receive requests from external communication devices and can also send requests, instructions, and information to external communication devices. External communication devices can be other electronic devices, servers, or IoT devices, such as televisions, etc.

[0142] The memory 20 can be used to store software programs and various data. The memory 20 may primarily include a program storage area and a data storage area. The program storage area may store the operating system, at least one application program required for a function (such as sending movement commands to a motion mechanism), etc.; the data storage area may include a database, and may store data or information created based on system usage. Furthermore, the memory 20 may include high-speed random access memory, and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other volatile solid-state storage device.

[0143] The processor 30 is the control center of the electronic device. It connects various parts of the electronic device via various interfaces and lines. By running or executing software programs and / or modules stored in the memory 20, and by calling data stored in the memory 20, it performs various functions and processes data, thereby providing overall monitoring of the electronic device. The processor 30 may include one or more processing units; optionally, the processor 30 may integrate an application processor and a modem processor. The application processor mainly handles the operating system, user interface, and applications, while the modem processor mainly handles wireless communication. It is understood that the modem processor may not be integrated into the processor 30.

[0144] although Figure 3Not shown, but the above electronic device may also include a circuit control module for connecting to a power supply to ensure the normal operation of other components. Those skilled in the art will understand that... Figure 3 The electronic device structure shown does not constitute a limitation on the electronic device and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0145] The present invention also proposes a computer-readable storage medium having a computer program stored thereon. The computer-readable storage medium may be... Figure 3 The memory 20 in the electronic device may be at least one of ROM (Read-Only Memory) / RAM (Random Access Memory), magnetic disk, optical disk, etc. The computer-readable storage medium includes several instructions to cause a terminal device with a processor (which may be a television, automobile, mobile phone, computer, server, terminal, or network device, etc.) to execute the methods of the various embodiments of the present invention.

[0146] In this invention, the terms "first," "second," "third," "fourth," and "fifth" are used for descriptive purposes only and should not be construed as indicating or implying relative importance. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances.

[0147] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the present invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0148] Although embodiments of the present invention have been shown and described above, the scope of protection of the present invention is not limited thereto. It is understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those skilled in the art can make changes, modifications, and substitutions to the above embodiments within the scope of the present invention, and such changes, modifications, and substitutions should all be covered within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A calibration method, characterized in that, The calibration method includes: A movement command is sent to the motion mechanism to move the target reference object to the first coordinate corresponding to the movement command, wherein the first coordinate is based on the motion coordinate system corresponding to the motion mechanism; In the preset model, a target model corresponding to the target reference object is matched. The target model is a virtual model generated in advance for the target reference object. The target model and the target reference object have the same size and shape. The corresponding points in the target model and the target reference object have the same coordinates in the motion coordinate system and the visual coordinate system. A second coordinate corresponding to the first coordinate is determined on the target model, wherein the second coordinate is based on the visual coordinate system corresponding to the visual system; The motion mechanism and the vision system are calibrated using the first coordinate and the second coordinate. Prior to the step of matching the target model corresponding to the target reference in the preset model, the following steps are included: Receive a model generation instruction and obtain the model parameters in the model generation instruction, wherein the model parameters include shape symbols and size parameters; Match the base model corresponding to the shape mark, wherein the base model is a reference mark shape model, which is constructed from basic geometric shapes; The dimensions of the basic model are adjusted according to the size parameters to obtain the preset model corresponding to the model generation instruction.

2. The calibration method as described in claim 1, characterized in that, The step of adjusting the size of the basic model according to the size parameters to obtain the preset model corresponding to the model generation instruction includes: Obtain the background parameters from the model generation instruction, and generate the model background based on the background parameters; The dimensions of the basic model are adjusted according to the stated dimension parameters; The adjusted base model is drawn on the model background to obtain the preset model corresponding to the model generation instruction.

3. The calibration method as described in claim 1, characterized in that, The step of matching the target model corresponding to the target reference object in the preset model includes: Acquire image data containing the target reference object; The image data is used to identify the feature information of the target reference object; Match the target model corresponding to the feature information in the preset model.

4. The calibration method as described in claim 3, characterized in that, The step of identifying the feature information of the target reference object from the image data includes: Determine the region of interest corresponding to the target reference object in the image data; Contour information is obtained by extracting the contour of the target reference object in the region of interest; The contour information is used as the feature information.

5. The calibration method as described in claim 3, characterized in that, The step of matching the target model corresponding to the feature information in the preset model includes: The similarity between the feature information and each of the preset models is calculated to obtain the similarity between each preset model. The preset model with the highest similarity is taken as the target model.

6. The calibration method as described in claim 5, characterized in that, The step of calculating the similarity between the feature information and each of the preset models includes: Obtain the pyramid model corresponding to the preset model. The pyramid model includes multiple levels, and the information richness of the corresponding levels increases sequentially from top to bottom. Match the target model corresponding to the feature information in the hierarchy from top to bottom; For each level, the information richness corresponding to the feature information is converted into information richness corresponding to the level, and the similarity is calculated with the matching model determined in the previous level. The preset model whose similarity meets the preset matching conditions is used as the matching model corresponding to the current level.

7. A calibration device, characterized in that, The calibration device includes: A first sending module is configured to send a movement command to a motion mechanism, so that the motion mechanism moves a target reference object to a first coordinate corresponding to the movement command, wherein the first coordinate is based on the motion coordinate system corresponding to the motion mechanism; The first matching module is used to match a target model corresponding to the target reference object in a preset model. The target model is a virtual model generated in advance for the target reference object. The target model and the target reference object have the same size and shape. The corresponding points in the target model and the target reference object have the same coordinates in the motion coordinate system and the visual coordinate system. The first determining module is used to determine a second coordinate on the target model corresponding to the first coordinate, wherein the second coordinate is based on the visual coordinate system corresponding to the visual system; The first execution module is used to perform calibration operations on the motion mechanism and the vision system using the first coordinate and the second coordinate. The device also includes: The first receiving module is used to receive the model generation instruction and obtain the model parameters in the model generation instruction, wherein the model parameters include shape marks and size parameters; The second matching module is used to match the base model corresponding to the shape mark, wherein the base model is the reference mark shape model, which is constructed from basic geometric shapes; The second execution module is used to adjust the size of the basic model according to the size parameters to obtain the preset model corresponding to the model generation instruction.

8. An electronic device, characterized in that, The electronic device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program, when executed by the processor, implements the steps of the calibration method as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the steps of the calibration method as described in any one of claims 1 to 6.

Images