Machine vision-based disassembly and assembly training and evaluation methods, systems, devices and media

Abstract

This invention discloses a machine vision-based method, system, device, and medium for disassembly and assembly training evaluation. The method includes: acquiring first image information of parts disassembled by a test subject, placing the parts on a preset workbench according to the disassembly sequence; determining the contour and position information of the parts based on the first image information; determining the part type based on the contour information and the disassembly sequence based on the position information; inputting the part type and disassembly sequence into a pre-constructed disassembly and assembly training evaluation model, and outputting the disassembly and assembly training evaluation result. This invention uses machine vision to identify the type and sequence of parts disassembled by the test subject, thereby automatically evaluating the disassembly and assembly training process without requiring one-on-one teacher evaluation. This ensures the objectivity and accuracy of the disassembly and assembly training evaluation, improves the efficiency of the evaluation, and is beneficial to improving the teaching quality of disassembly and assembly training. It can be widely applied in the field of mechanical disassembly and assembly training technology.

Description

Technical Field

[0001] This invention relates to the field of mechanical disassembly and assembly training technology, and in particular to a disassembly and assembly training evaluation method, system, device and medium based on machine vision. Background Technology

[0002] In mechanical vocational education, skills training and evaluation are frequently conducted, such as machine disassembly and assembly. To better assess students' operational details during the disassembly and assembly process, teachers typically stand beside students and score them one by one according to a prescribed evaluation scale. This evaluation method is somewhat subjective, and the entire evaluation process is inefficient. Therefore, due to limitations in teaching staff, current mechanical disassembly and assembly training can only be conducted through random sampling, which significantly impacts the teaching quality of students' disassembly and assembly training. Summary of the Invention

[0003] The purpose of this invention is to at least partially solve one of the technical problems existing in the prior art.

[0004] Therefore, one objective of this invention is to provide a machine vision-based disassembly and assembly training evaluation method. This method can identify the type and sequence of parts disassembled by the test subject through machine vision, thereby automatically evaluating the test subject's disassembly and assembly training process without the need for one-on-one evaluation by a teacher. This ensures the objectivity and accuracy of the disassembly and assembly training evaluation, improves the efficiency of the evaluation, and helps to improve the teaching quality of disassembly and assembly training.

[0005] Another objective of this invention is to provide a machine vision-based disassembly and assembly training and evaluation system.

[0006] To achieve the above-mentioned technical objectives, the technical solutions adopted in the embodiments of the present invention include:

[0007] In a first aspect, embodiments of the present invention provide a machine vision-based disassembly and assembly training and evaluation method, comprising the following steps:

[0008] Acquire first image information of the parts disassembled by the test subject, and place the parts on a preset workbench in the disassembly order;

[0009] The contour information and position information of the part are determined based on the first image information;

[0010] The part type of the part is determined based on the contour information, and the disassembly sequence of the part is determined based on the position information;

[0011] The part type and disassembly sequence are input into a pre-built disassembly and assembly training and evaluation model, and the disassembly and assembly training and evaluation results are output.

[0012] Furthermore, in one embodiment of the present invention, the step of determining the contour information and position information of the part based on the first image information specifically includes:

[0013] The foreground and background of the first image information are separated to obtain foreground image information;

[0014] The foreground image information is subjected to global threshold segmentation to obtain the second image information;

[0015] The second image information is subjected to feature selection and segmentation processing to obtain multiple feature regions, and then the contour information and position information of the part are determined based on the feature regions.

[0016] Furthermore, in one embodiment of the present invention, the step of performing global threshold segmentation processing on the foreground image information to obtain the second image information specifically includes:

[0017] Determine the first grayscale mean and first standard deviation of each pixel in the foreground image information within a preset area;

[0018] A first feature threshold is determined for each pixel based on the first grayscale mean and the first standard deviation.

[0019] The foreground image information is subjected to global threshold segmentation based on the first feature threshold to obtain the second image information.

[0020] Furthermore, in one embodiment of the present invention, the step of determining the part type of the part based on the contour information specifically includes:

[0021] The contour area of ​​the part is determined based on the contour information;

[0022] Obtain the first area of ​​the worktable, and then determine the area ratio of the part to the worktable based on the outline area and the first area;

[0023] The part type of the part is determined based on the area ratio and a first mapping relationship between the pre-constructed area ratio and the part type.

[0024] Furthermore, in one embodiment of the present invention, the step of determining the part type of the part based on the contour information specifically includes:

[0025] The contour information is input into a pre-built part recognition model, and the part type of the part is output.

[0026] The part recognition model is obtained by training and optimizing a deep neural network model.

[0027] Furthermore, in one embodiment of the present invention, the step of determining the disassembly sequence of the parts based on the location information specifically includes:

[0028] The placement order of the parts is determined based on the location information, and then the disassembly order of the parts is determined based on the placement order.

[0029] Furthermore, in one embodiment of the present invention, the disassembly and assembly training evaluation method further includes the step of constructing a disassembly and assembly training evaluation model, which specifically includes:

[0030] Determine the sequence of part types for the standard disassembly and assembly process;

[0031] Multiple evaluation indicators are set according to the part type sequence, and the weights of the evaluation indicators are determined;

[0032] The disassembly and assembly training evaluation model is determined based on the evaluation index and the weight.

[0033] Secondly, embodiments of the present invention provide a machine vision-based disassembly and assembly training and evaluation system, comprising:

[0034] The image acquisition module is used to acquire first image information of the parts disassembled by the test subject, and the parts are placed on a preset workbench in the disassembly order.

[0035] The contour information and position information determination module is used to determine the contour information and position information of the part based on the first image information;

[0036] The part type and disassembly sequence determination module is used to determine the part type of the part based on the contour information and to determine the disassembly sequence of the part based on the position information.

[0037] The model evaluation module is used to input the part type and the disassembly sequence into a pre-built disassembly and assembly training evaluation model, and output the disassembly and assembly training evaluation results.

[0038] Thirdly, embodiments of the present invention provide a machine vision-based disassembly and assembly training and evaluation device, comprising:

[0039] At least one processor;

[0040] At least one memory for storing at least one program;

[0041] When the at least one program is executed by the at least one processor, the at least one processor implements the above-described machine vision-based disassembly and assembly training and evaluation method.

[0042] Fourthly, embodiments of the present invention also provide a computer-readable storage medium storing a processor-executable program, which, when executed by a processor, is used to perform the aforementioned machine vision-based disassembly and assembly training and evaluation method.

[0043] The advantages and beneficial effects of the present invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention:

[0044] This invention acquires first image information of parts disassembled by a test subject, determines the contour and position information of each part based on the first image information, identifies the part type based on the contour information, and determines the disassembly sequence of each part based on the position information. Then, the disassembly sequence and corresponding part type are input into a pre-constructed disassembly and assembly training evaluation model, outputting the disassembly and assembly training evaluation result. This invention, through machine vision, can identify the type and sequence of parts disassembled by the test subject, thereby automatically evaluating the subject's disassembly and assembly training process. It eliminates the need for one-on-one teacher evaluation, ensuring the objectivity and accuracy of the disassembly and assembly training evaluation, improving the efficiency of the evaluation, and ultimately enhancing the teaching quality of disassembly and assembly training. Attached Figure Description

[0045] To more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings used in the embodiments of the present invention are described below. It should be understood that the drawings described below are only for the convenience of clearly describing some embodiments of the technical solutions of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0046] Figure 1 A flowchart illustrating the steps of a machine vision-based disassembly and assembly training and evaluation method provided in an embodiment of the present invention;

[0047] Figure 2 This is a schematic diagram showing the placement of parts on a worktable according to an embodiment of the present invention;

[0048] Figure 3 A structural block diagram of a machine vision-based disassembly and assembly training and evaluation system provided in an embodiment of the present invention;

[0049] Figure 4 This is a structural block diagram of a machine vision-based disassembly and assembly training and evaluation device provided in an embodiment of the present invention. Detailed Implementation

[0050] The embodiments of the present invention are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, and should not be construed as limiting the present invention. The step numbers in the following embodiments are set only for ease of explanation, and there is no limitation on the order between the steps. The execution order of each step in the embodiments can be adaptively adjusted according to the understanding of those skilled in the art.

[0051] In the description of this invention, "multiple" means two or more. The use of "first" and "second" is for distinguishing technical features only and should not be construed as indicating or implying relative importance, or implicitly indicating the number of indicated technical features, or the order of the indicated technical features. Furthermore, unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art.

[0052] Reference Figure 1 This invention provides a machine vision-based disassembly and assembly training and evaluation method, which specifically includes the following steps:

[0053] S101. Obtain the first image information of the parts disassembled by the test subject. The parts are placed on a preset workbench in the order of disassembly.

[0054] Specifically, taking engine disassembly and assembly training as an example, the test subject disassembles engine parts such as bearings, cylinder head, spark plugs, camshaft, piston, connecting rod, and crankshaft, stacks them vertically according to the requirements of the maintenance manual, and places them on a preset workbench in the disassembly order. The camera captures the first image information of the parts, which is convenient for subsequent image analysis to determine the type of each part and the disassembly order.

[0055] like Figure 2 The diagram shows the placement of parts on a workbench according to an embodiment of the present invention. The dashed lines represent the workbench area, the dotted lines represent the part areas, and the numbers indicate the placement order of the parts. It can be understood that the parts are arranged sequentially from left to right and from top to bottom according to the disassembly order. Since mechanical parts are generally metal products, the workbench can be green to increase the color difference with the parts.

[0056] S102. Determine the contour information and position information of the part based on the first image information.

[0057] Specifically, after the camera acquires the first image information, the pixels of the first image information are divided into two parts according to color: the pixel region of interest (i.e., the foreground image) and the pixel region of no interest (i.e., the background image). Then, global threshold segmentation, feature selection, and segmentation processing are performed on the foreground image to determine the contour information and position information of multiple parts. Step S102 specifically includes the following steps:

[0058] S1021. Separate the foreground and background of the first image information to obtain foreground image information;

[0059] S1022. Perform global threshold segmentation on the foreground image information to obtain the second image information;

[0060] S1023. Perform feature selection and segmentation processing on the second image information to obtain multiple feature regions, and then determine the contour information and position information of the part based on the feature regions.

[0061] As a further optional implementation, the step S1022 of performing global threshold segmentation on the foreground image information to obtain the second image information specifically includes:

[0062] S10221. Determine the first grayscale mean and first standard deviation of each pixel in the foreground image information within a preset area;

[0063] S10222. Determine the first feature threshold for each pixel based on the first grayscale mean and the first standard deviation.

[0064] S10223. Perform global threshold segmentation on the foreground image information according to the first feature threshold to obtain the second image information.

[0065] Specifically, the first grayscale mean can be calculated using the following formula:

[0066]

[0067] Where m(x,y) represents the first gray-scale mean value of pixel (x,y) in the r neighborhood, r represents the preset neighborhood, and g(i,j) represents the gray-scale value of pixel (i,j).

[0068] The first standard deviation can be calculated using the following formula:

[0069]

[0070] Where s(x,y) represents the first standard deviation of pixel (x,y) in the r neighborhood;

[0071] The first feature threshold can be expressed as the extreme value of the following formula:

[0072]

[0073] Where T(x,y) represents the first feature threshold of pixel (x,y), R represents the dynamic range of the first standard deviation, and k represents the correction parameter.

[0074] Specifically, in this embodiment of the invention, an eight-bit grayscale image is used as an example, and the value of R is 128; in this example of the invention, the value range of k is [0,1].

[0075] In this embodiment of the invention, global threshold segmentation is performed on the foreground image information based on a first feature threshold, thereby obtaining second image information with clearly segmented pixel regions for each part. Then, feature regions for each part are obtained through feature selection and segmentation processing. The contour information of the part is determined based on the contour of the feature region, and the position information of the part on the worktable is determined based on the position of the feature region.

[0076] S103. Determine the part type based on the contour information and determine the disassembly sequence of the part based on the position information.

[0077] As a further optional implementation, the step of determining the part type based on the contour information specifically includes:

[0078] A1. Determine the contour area of ​​the part based on the contour information;

[0079] A2. Obtain the first area of ​​the worktable, and then determine the area ratio between the part and the worktable based on the outline area and the first area;

[0080] A3. Determine the part type of the part based on the area ratio and the first mapping relationship between the pre-constructed area ratio and the part type.

[0081] Specifically, for simple mechanical assembly and disassembly training with a limited number of part types, the part type can be determined by the ratio of the part's outline to the area of ​​the worktable. The area ratios of various part types to a preset worktable surface are obtained in advance, establishing a primary mapping relationship between these ratios and the corresponding part types.

[0082] Optionally, a certain fluctuation range can be set for the area ratio of different types of parts. When the area ratio of a detected part to the worktable is within the corresponding fluctuation range, the part type of the part can be determined.

[0083] In this embodiment of the invention, the type of part is identified by the area ratio, which is fast and requires little calculation, further improving the efficiency of disassembly and assembly training and evaluation.

[0084] As a further optional implementation, the step of determining the part type based on the contour information specifically includes:

[0085] The contour information is input into a pre-built part recognition model, and the part type of the part is output.

[0086] The part recognition model is obtained by training and optimizing a deep neural network model.

[0087] Specifically, for mechanical disassembly and assembly training with many types of parts and high similarity between different types of parts, the type of part can be determined by training a part recognition model using collected part samples.

[0088] The accuracy of part type identification results can be measured by a loss function. A loss function is defined on a single training data point and measures the prediction error of that data point. Specifically, the loss value is determined by the label of a single training data point and the model's prediction result for that data. However, in actual training, a training dataset contains many data points. Therefore, a cost function is generally used to measure the overall error of the training dataset. The cost function is defined on the entire training dataset and calculates the average prediction error of all training data points, providing a better measure of the model's prediction performance. For general machine learning models, the aforementioned cost function, plus a regularization term to measure model complexity, can serve as the training objective function. Based on this objective function, the loss value of the entire training dataset can be calculated. Many types of loss functions are commonly used, such as 0-1 loss, squared loss, absolute loss, logarithmic loss, and cross-entropy loss, which can all be used as loss functions for machine learning models. These will not be elaborated upon here. In this embodiment of the invention, any one of these loss functions can be selected to determine the training loss value. Based on the training loss value, the backpropagation algorithm is used to update the model parameters. After several iterations, a well-trained part recognition model can be obtained. The specific number of iterations can be preset, or training can be considered complete when the accuracy requirement is met on the test set.

[0089] In this embodiment of the invention, the identification of part types is achieved through a neural network model, which improves the accuracy of identification and further enhances the accuracy of disassembly and assembly training and evaluation.

[0090] As a further optional implementation, the step of determining the disassembly sequence of parts based on location information specifically includes:

[0091] The placement order of the parts is determined based on the location information, and then the disassembly order of the parts is determined based on the placement order.

[0092] Specifically, such as Figure 2 As shown, the parts are placed from left to right and from top to bottom according to the disassembly sequence. Once the position information of each part is determined, the placement order of each part can be determined, and thus the disassembly sequence of the parts can be determined.

[0093] S104. Input the part type and disassembly sequence into the pre-built disassembly and assembly training evaluation model, and output the disassembly and assembly training evaluation results.

[0094] As an optional implementation, the disassembly and assembly training and evaluation method further includes the step of constructing a disassembly and assembly training and evaluation model, which specifically includes:

[0095] B1. Determine the sequence of part types for the standard disassembly and assembly process;

[0096] B2. Set multiple evaluation indicators according to the part type sequence, and determine the weights of the evaluation indicators;

[0097] B3. Determine the disassembly and assembly training evaluation model based on the evaluation indicators and weights.

[0098] Specifically, the disassembly sequence and the types of each part in the standard disassembly and assembly process are determined to obtain a part type sequence. Based on this part type sequence, multiple evaluation indicators are determined, such as incorrect disassembly sequence, number of incorrect operations, and multiple or missing parts. Corresponding weights are set, and then a fuzzy operator is used to perform a comprehensive fuzzy evaluation of each evaluation indicator. Based on the principle of maximum membership, the final disassembly and assembly training evaluation model is obtained.

[0099] The method steps of the embodiments of the present invention have been described above. It can be understood that the embodiments of the present invention can identify the type and sequence of the parts disassembled by the test subject through machine vision, thereby automatically evaluating the disassembly and assembly training process of the test subject without the need for one-on-one evaluation by the teacher, ensuring the objectivity and accuracy of the disassembly and assembly training evaluation, improving the efficiency of the disassembly and assembly training evaluation, and helping to improve the teaching quality of disassembly and assembly training.

[0100] Reference Figure 3 This invention provides a machine vision-based disassembly and assembly training and evaluation system, comprising:

[0101] The image acquisition module is used to acquire the first image information of the parts disassembled by the test subject. The parts are placed on a preset workbench in the disassembly order.

[0102] The contour information and position information determination module is used to determine the contour information and position information of the part based on the first image information;

[0103] The part type and disassembly sequence determination module is used to determine the part type based on the contour information and the disassembly sequence based on the position information.

[0104] The model evaluation module is used to input the part type and disassembly sequence into a pre-built disassembly and assembly training evaluation model, and output the disassembly and assembly training evaluation results.

[0105] The content of the above method embodiments is applicable to this system embodiment. The specific functions implemented in this system embodiment are the same as those in the above method embodiments, and the beneficial effects achieved are also the same as those achieved in the above method embodiments.

[0106] Reference Figure 4 This invention provides a machine vision-based disassembly and assembly training and evaluation device, comprising:

[0107] At least one processor;

[0108] At least one memory for storing at least one program;

[0109] When the above-mentioned at least one program is executed by the above-mentioned at least one processor, the above-mentioned at least one processor implements the above-mentioned machine vision-based disassembly and assembly training and evaluation method.

[0110] The content of the above method embodiments is applicable to the device embodiments. The specific functions implemented by the device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0111] This invention also provides a computer-readable storage medium storing a processor-executable program that, when executed by a processor, performs the aforementioned machine vision-based disassembly and assembly training and evaluation method.

[0112] This invention provides a computer-readable storage medium that can execute a machine vision-based disassembly and assembly training and evaluation method provided in the method embodiments of this invention. It can execute any combination of the implementation steps of the method embodiments and has the corresponding functions and beneficial effects of the method.

[0113] This invention also discloses a computer program product or computer program, which includes computer instructions stored in a computer-readable storage medium. A processor of a computer device can read the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, causing the computer device to perform... Figure 1 The method shown.

[0114] In some alternative embodiments, the functions / operations mentioned in the block diagrams may not occur in the order shown in the operation diagrams. For example, depending on the functions / operations involved, two consecutively shown blocks may actually be executed substantially simultaneously, or the aforementioned blocks may sometimes be executed in reverse order. Furthermore, the embodiments presented and described in the flowcharts of this invention are provided by way of example to provide a more comprehensive understanding of the technology. The disclosed methods are not limited to the operations and logic flows presented herein. Alternative embodiments are contemplated in which the order of various operations is changed and sub-operations described as part of a larger operation are executed independently.

[0115] Furthermore, although the invention has been described in the context of functional modules, it should be understood that, unless otherwise stated, one or more of the aforementioned functions and / or features may be integrated into a single physical device and / or software module, or one or more functions and / or features may be implemented in a separate physical device or software module. It is also understood that a detailed discussion of the actual implementation of each module is unnecessary for understanding the invention. Rather, given the properties, functions, and internal relationships of the various functional modules in the apparatus disclosed herein, the actual implementation of the module will be understood within the scope of conventional skill of an engineer. Therefore, those skilled in the art can implement the invention as set forth in the claims using ordinary techniques without excessive experimentation. It is also understood that the specific concepts disclosed are merely illustrative and not intended to limit the scope of the invention, which is determined by the full scope of the appended claims and their equivalents.

[0116] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0117] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device.

[0118] More specific examples of computer-readable media (a non-exhaustive list) include: electrical connections (electronic devices) having one or more wires, portable computer disk drives (magnetic devices), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Furthermore, computer-readable media can even be paper or other suitable media on which the aforementioned program can be printed, because the aforementioned program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or, if necessary, processing in other suitable ways, and then stored in computer memory.

[0119] It should be understood that various parts of the present invention can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0120] In the foregoing description of this specification, references to terms such as "one embodiment," "another embodiment," or "some embodiments" indicate that a specific feature, structure, material, or characteristic described in connection with an embodiment or example is included in at least one embodiment or example of the present invention. In this specification, 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.

[0121] Although embodiments of the invention have been shown and described, those skilled in the art will understand that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the claims and their equivalents.

[0122] The above is a detailed description of the preferred embodiments of the present invention. However, the present invention is not limited to the above embodiments. Those skilled in the art can make various equivalent modifications or substitutions without departing from the spirit of the present invention. All such equivalent modifications or substitutions are included within the scope defined by the claims of this application.

Claims

1. A machine vision-based disassembly and assembly training and evaluation method, characterized in that, Includes the following steps: Acquire first image information of the parts disassembled by the test subject, and place the parts on a preset workbench in the disassembly order; The contour information and position information of the part are determined based on the first image information; The part type of the part is determined based on the contour information, and the disassembly sequence of the part is determined based on the position information; The part type and the disassembly sequence are input into a pre-built disassembly and assembly training and evaluation model, and the disassembly and assembly training and evaluation results are output. The step of determining the part type based on the contour information specifically includes: For mechanical assembly and disassembly training with a limited number of part types, the contour area of ​​the part is determined based on the contour information; the first area of ​​the worktable is obtained, and then the area ratio of the part to the worktable is determined based on the contour area and the first area; the part type of the part is determined based on the area ratio and a pre-built mapping relationship between the area ratio and the part type; or, For mechanical disassembly and assembly training with many types of parts and high similarity between different types of parts, the contour information is input into a pre-built part recognition model, and the part type of the part is output. The part recognition model is obtained through training and optimization of a deep neural network model. The step of determining the disassembly sequence of the parts based on the location information specifically includes: The placement order of the parts is determined based on the location information, and then the disassembly order of the parts is determined based on the placement order.

2. The machine vision-based disassembly and assembly training and evaluation method according to claim 1, characterized in that, The step of determining the contour information and position information of the part based on the first image information specifically includes: The foreground and background of the first image information are separated to obtain foreground image information; The foreground image information is subjected to global threshold segmentation to obtain the second image information; The second image information is subjected to feature selection and segmentation processing to obtain multiple feature regions, and then the contour information and position information of the part are determined based on the feature regions.

3. The machine vision-based disassembly and assembly training and evaluation method according to claim 2, characterized in that, The step of performing global threshold segmentation on the foreground image information to obtain the second image information specifically includes: Determine the first grayscale mean and first standard deviation of each pixel in the foreground image information within a preset area; A first feature threshold is determined for each pixel based on the first grayscale mean and the first standard deviation. The foreground image information is subjected to global threshold segmentation based on the first feature threshold to obtain the second image information.

4. A machine vision-based disassembly and assembly training and evaluation method according to any one of claims 1 to 3, characterized in that, The disassembly and assembly training and evaluation method also includes the step of constructing a disassembly and assembly training and evaluation model, which specifically includes: Determine the sequence of part types for the standard disassembly and assembly process; Multiple evaluation indicators are set according to the part type sequence, and the weights of the evaluation indicators are determined; The disassembly and assembly training evaluation model is determined based on the evaluation index and the weight.

5. A machine vision-based disassembly and assembly training and evaluation system, characterized in that, include: The image acquisition module is used to acquire first image information of the parts disassembled by the test subject, and the parts are placed on a preset workbench in the disassembly order. The contour information and position information determination module is used to determine the contour information and position information of the part based on the first image information; The part type and disassembly sequence determination module is used to determine the part type of the part based on the contour information and to determine the disassembly sequence of the part based on the position information. The model evaluation module is used to input the part type and the disassembly sequence into a pre-built disassembly and assembly training evaluation model, and output the disassembly and assembly training evaluation results.

6. A machine vision-based disassembly and assembly training and evaluation device, characterized in that, include: At least one processor; At least one memory for storing at least one program; When the at least one program is executed by the at least one processor, the at least one processor implements a machine vision-based disassembly and assembly training and evaluation method as described in any one of claims 1 to 4.

7. A computer-readable storage medium storing a processor-executable program, characterized in that, The processor-executable program, when executed by the processor, is used to perform a machine vision-based disassembly and assembly training and evaluation method as described in any one of claims 1 to 4.

Images