An intelligent assisted stereoscopic teaching method based on shape contour matching

Abstract

The present invention provides a method for assisting stereoscopic teaching based on shape contour matching, comprising: obtaining an image of an object, and extracting edges in the image using an edge detection algorithm; after processing the extracted edges, generating a smooth contour and extracting key points therein, and then constructing a similarity matrix; matching the currently extracted contour features with the reference contour features based on the similarity matrix, and recording relevant information according to the corresponding coordinates after the match is successful, to complete the teaching task; 2. High precision: For objects that require precise teaching, this method achieves high-precision matching and teaching through the steps of edge detection, contour feature extraction, and similarity matrix construction. 2. Strong effectiveness: For objects with simple shapes and obvious contour features, this method can quickly and effectively complete the teaching task.

Description

Technical Field

[0001] The invention relates to the technical field of wax inlay processing, and in particular to a method for assisting stereoscopic teaching based on shape contour matching. Background Art

[0002] Traditional wax setting process relies on a lot of manpower, and relies on manual setting of diamonds one by one. This kind of artificial wax setting has problems such as low efficiency, unevenness, and easy to cause damage. The emergence of wax setting machines is expected to solve the above problems well.

[0003] The wax setting machines currently used in the market use positioning pin teaching. This teaching method has high requirements for operators, and operators must have skilled manual setting training to adapt to the work.

[0004] To this end, a method of intelligent assisted stereoscopic teaching based on shape contour matching is proposed. This method automatically obtains the coordinates of the teaching point by collecting the image of the processed object and using a machine vision algorithm. This teaching method can greatly reduce the dependence on the technical level of the teaching staff through simple manual operation assisted by an intelligent image algorithm, and is simple and efficient. Summary of the invention

[0005] The present invention provides a method for auxiliary stereoscopic teaching based on shape contour matching, and the teaching process is as follows:

[0006] Obtain an image of the object and use an edge detection algorithm to extract edges in the image;

[0007] After processing the extracted edges, a smooth contour is generated and key points are extracted, and the similarity matrix is ​​calculated;

[0008] Based on the similarity matrix, the currently extracted contour features are matched with the reference contour features, and the relevant coordinate information of the successfully matched objects is recorded to complete the teaching task.

[0009] In some embodiments, acquiring an image of an object includes:

[0010] Use a microscope to observe the object to be processed and obtain an image of the object.

[0011] In some embodiments, when the edge detection algorithm is used to extract the edge in the image, it includes:

[0012] Use edge detection algorithms to extract edges in item images and perform filtering.

[0013] In some embodiments: when using the edge detection algorithm, operators such as Sobel are used for edge detection.

[0014] In some embodiments: when constructing the similarity matrix, it includes:

[0015] The similarity matrix is ​​constructed by comparing the similarity between the contour features captured during manual teaching of the robot and the stored reference contour features.

[0016] In some embodiments, the matching of the currently extracted contour features with the reference contour features based on the similarity matrix includes:

[0017] By running the global optimal solution and dynamic programming algorithm, the currently extracted contour features are matched with the reference contour features. After the match is successful, the corresponding coordinate information is recorded to complete the teaching task.

[0018] In some embodiments, the edge detection specifically includes:

[0019] After the image is converted to grayscale and convolution is performed, the gradient value dim is calculated, and the following steps are performed based on the calculation results:

[0020] dim>Set the threshold value to the pixel edge point;

[0021] dim≤set threshold, which means the pixel is not an edge point;

[0022] Wherein: the threshold is set manually according to different application scenarios. After calculation, the processed image data is output.

[0023] The present invention also provides a system for assisting stereoscopic teaching based on shape contour matching, comprising:

[0024] An image acquisition module, the acquisition module is used to acquire an image of an object through a microscope;

[0025] An edge detection module, wherein the edge detection module is used to extract edges in an object image by using an edge detection algorithm;

[0026] A contour feature extraction module, which is used to process the extracted edges, generate a smooth contour and extract key points on the contour;

[0027] A similarity matrix construction module, wherein the similarity matrix construction is used to construct a similarity matrix by comparing the similarity between the contour features captured during manual teaching of the robot and the stored reference contour features;

[0028] A contour recognition module is used to match the currently extracted contour features with the reference contour features.

[0029] The present invention also provides a computer device, which includes a processor and a memory coupled to the processor, wherein program instructions are stored in the memory, and when the program instructions are executed by the processor, the processor executes the steps of the method for assisted stereoscopic teaching based on shape contour matching as described above.

[0030] The present invention also provides a storage medium that can store program instructions constructed based on the above-mentioned shape contour matching-based assisted stereoscopic teaching method.

[0031] The embodiment of the present invention has the following advantages due to the adoption of the above technical solution:

[0032] 1. High precision: For objects that require precise teaching, this method achieves high-precision matching and teaching through steps such as edge detection, contour feature extraction, and similarity matrix construction.

[0033] 2. Strong effectiveness: For objects with simple shapes and obvious contour features, this method can complete the teaching task quickly and effectively.

[0034] 3. High flexibility: This method is applicable to objects of various shapes and can flexibly handle situations such as incomplete contours or those containing noise.

[0035] The above summary is for illustrative purposes only and is not intended to be limiting in any way. In addition to the illustrative aspects, embodiments and features described above, further aspects, embodiments and features of the present invention will be readily apparent by reference to the accompanying drawings and the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0037] Figure 1 is a flow chart of the method of the present invention;

[0038] Figure 2 Flow chart of the edge computing method of the present invention. DETAILED DESCRIPTION

[0039] In the following, only some exemplary embodiments are briefly described. As those skilled in the art will appreciate, the described embodiments may be modified in various ways without departing from the spirit or scope of the present invention. Therefore, the drawings and descriptions are considered to be exemplary and non-restrictive in nature.

[0040] It should be noted that the terms "first", "second", "symmetrical", "array", etc. are only used to distinguish between description and position description purposes, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the definition of "first", "symmetrical", etc. can explicitly or implicitly include one or more of these features; similarly, when the quantity of certain features is not limited in the form of words such as "two" or "three", it should be noted that this feature also explicitly or implicitly includes one or more feature quantities;

[0041] In the present invention, unless otherwise clearly specified and limited, the terms such as "installation", "connection", "fixation" and the like should be understood in a broad sense; for example, it can be a fixed connection, a detachable connection, or an integral molding; it can be a mechanical connection, a direct connection, welding, or an indirect connection through an intermediate medium, or it can be the internal connection of two elements or the interaction relationship between two elements. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood based on the description and drawings combined with specific circumstances.

[0042] The embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0043] like Figure 1-2 As shown, an embodiment of the present invention provides a method for assisting stereoscopic teaching based on shape contour matching, comprising:

[0044] Obtain an image of the object and use an edge detection algorithm to extract edges in the image;

[0045] After processing the extracted edges, a smooth contour is generated and key points are extracted to construct a similarity matrix;

[0046] Based on the similarity matrix, the currently extracted contour features are matched with the reference contour features, and after the match is successful, the relevant information is recorded according to the corresponding coordinates to complete the teaching task.

[0047] Specifically: When acquiring an image of an object, it includes:

[0048] Use a microscope to observe the object to be processed and obtain an image of the object;

[0049] More specifically, to obtain an image through a microscope, it is first necessary to use the microscope to observe the object to be processed and obtain an image of the object. During this process, the object and the microscope should be kept as still as possible to avoid a reduction in clarity.

[0050] Specifically: When edge detection algorithm is used to extract edges in an image, it includes:

[0051] Use edge detection algorithms to extract edges from item images and perform filtering.

[0052] More specifically, an edge detection algorithm is used to extract the edges in the object image. This method uses operators such as Sobel for edge detection. Different operators can be selected for edge detection in different application scenarios. To avoid interference, the edges can be filtered;

[0053] On the basis of the above scheme, Figure 2 As shown, edge detection specifically includes:

[0054] After the image is converted to grayscale and convolution is performed, the gradient value dim is calculated, and the following steps are performed based on the calculation results:

[0055] dim>Set the threshold value, which is the pixel edge point;

[0056] dim≤set threshold, which means the pixel is not an edge point;

[0057] The threshold can be set manually according to different application scenarios, and the processed image data is output after calculation.

[0058] In this embodiment, specifically: constructing a similarity matrix includes:

[0059] The similarity matrix is ​​constructed by comparing the similarity between the contour features captured during manual teaching of the robot and the stored reference contour features.

[0060] In this embodiment, specifically: when matching the currently extracted contour feature with the reference contour feature based on the similarity matrix, it includes:

[0061] By running the global optimal solution and dynamic programming algorithm, the currently extracted contour features are matched with the reference contour features. After the match is successful, the relevant information is recorded according to the corresponding coordinates to complete the teaching task.

[0062] The present invention also provides a system for assisting stereoscopic teaching based on shape contour matching, comprising:

[0063] An acquisition module, the acquisition module is used to acquire an image of an object through a microscope;

[0064] The edge detection module is used to extract the edge of the object image by using an edge detection algorithm;

[0065] The contour feature extraction module is used to process the extracted edges, generate a smooth contour and extract key points on the contour;

[0066] A similarity matrix construction module, the similarity matrix construction is used to construct a similarity matrix by comparing the similarity between the contour features captured during manual teaching of the robot and the stored reference contour features;

[0067] Contour recognition module,The contour recognition module is used to match the currently extracted contour features with the reference contour features.

[0068] The present invention also provides a computer device, which includes a processor and a memory coupled to the processor, wherein program instructions are stored in the memory, and when the program instructions are executed by the processor, the processor executes the steps of the method for assisted stereoscopic teaching based on shape contour matching as described above.

[0069] A processor can also be called a CPU (Central Processing Unit). A processor may be an integrated circuit chip that has the ability to process signals. A processor can also be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic device, a discrete gate or transistor logic device, or a discrete hardware component. A general-purpose processor can be a microprocessor or any conventional processor, etc.

[0070] The present invention also provides a storage medium that can store program instructions constructed based on the above-mentioned shape contour matching-based assisted stereoscopic teaching method.

[0071] The program instructions can be stored in the above-mentioned storage medium in the form of a software product, including several instructions for a computer device (which can be a personal computer, server, or network device, etc.) or a processor to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks or optical disks, or computer devices such as computers, servers, mobile phones, and tablets. The server can be an independent server, or it can be a cloud server that provides cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (Content Delivery Network, CDN), and basic cloud computing services such as big data and artificial intelligence platforms.

[0072] The working principle of visual assisted teaching is to first obtain a positional relationship between the needle and the visual camera, and then determine the position deviation. When using visual assisted teaching, when adding teaching points, the deviation is compensated by software.

[0073] When the visual assisted teaching mode is selected, when you click on the position of the added point to observe whether the added point teaching is correct, the observed point will be projected directly to the software operation interface through the camera. The image projected by the camera will be matched with the correct sample. If the match is the same, press OK to successfully teach, instead of the traditional teaching mode, which requires observing the processed product itself.

[0074] The characteristics of this method are as follows:

[0075] 1. High precision: For objects that require precise teaching, this method achieves high-precision matching and teaching through steps such as edge detection, contour feature extraction, and similarity matrix construction.

[0076] 2. Strong effectiveness: For objects with simple shapes and obvious contour features, this method can complete the teaching task quickly and effectively.

[0077] 3. High flexibility: This method is applicable to objects of various shapes and can flexibly handle situations such as incomplete contours or those containing noise.

[0078] This method uses operators such as Sobel, corner detection algorithms, and adopts global optimal solutions and dynamic programming algorithms. Its advantages include high accuracy, strong effectiveness, and high flexibility.

[0079] In the several embodiments provided in the present application, it should be understood that the disclosed terminals, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of units is only a logical function division, and there may be other division methods in actual implementation, such as 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 an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0080] In addition, each functional unit in each embodiment of the present application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The above integrated unit can be implemented in the form of hardware or in the form of software functional units. The above is only an implementation method of the present application, and does not limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made by using the description and drawings of this application, or directly or indirectly used in other related technical fields, is also included in the patent protection scope of the present application.

Claims

1. A method for assisting stereoscopic teaching based on shape contour matching, characterized in that: include: The object to be processed is observed using a microscope to obtain an image of the object, an edge detection algorithm is used to extract the edge in the image, and filtering is performed. When the edge detection algorithm is used, the Sobel operator is used for edge detection, which specifically includes: After the image is converted to grayscale and convolution is performed, the gradient value dim is calculated, and the following steps are performed based on the calculation results: dim>Set the threshold value, which is the pixel edge point; dim≤set threshold, which means the pixel is not an edge point; Among them, the threshold is set manually according to different application scenarios, and the processed image data is output after calculation; After processing the extracted edges, a smooth contour is generated and key points therein are extracted, and then a similarity matrix is ​​constructed, wherein the similarity matrix is ​​constructed by comparing the similarity between the contour features captured during manual teaching of the robot and the stored reference contour features; Based on the similarity matrix, the currently extracted contour features are matched with the reference contour features. Through the global optimal solution and dynamic programming algorithm, the currently extracted contour features are matched with the reference contour features. After the match is successful, the relevant information is recorded according to the corresponding coordinates to complete the teaching task.

2. A system for assisting stereoscopic teaching based on shape contour matching, characterized in that: include: An acquisition module, the acquisition module is used to acquire an image of an object through a microscope; The edge detection module is used to extract the edge in the object image by using an edge detection algorithm and perform filtering processing. When using the edge detection algorithm, the Sobel operator is used for edge detection, which specifically includes: After the image is converted to grayscale and convolution is performed, the gradient value dim is calculated, and the following steps are performed based on the calculation results: dim>Set the threshold value to the pixel edge point; dim≤set threshold, which means the pixel is not an edge point; Among them, the threshold is set manually according to different application scenarios, and the processed image data is output after calculation; A contour feature extraction module, which is used to process the extracted edges, generate a smooth contour and extract key points on the contour; A similarity matrix construction module, wherein the similarity matrix construction is used to construct a similarity matrix by comparing the similarity between the contour features captured during manual teaching of the robot and the stored reference contour features; The contour recognition module is used to match the currently extracted contour features with the reference contour features, wherein the currently extracted contour features and the reference contour features are matched through a global optimal solution and a dynamic programming algorithm, and after the match is successful, relevant information is recorded according to the corresponding coordinates to complete the teaching task.

3. A computer device, characterized in that: The computer device includes a processor and a memory coupled to the processor, wherein program instructions are stored in the memory, and when the program instructions are executed by the processor, the processor executes the steps of the method for assisted stereoscopic teaching based on shape contour matching as described in claim 1.

4. A storage medium, characterized in that: Program instructions capable of implementing the method for assisting stereoscopic teaching based on shape contour matching as claimed in claim 1 are stored.

Images