Shoe polishing method and system based on visual auxiliary adjustment

Abstract

The invention relates to a shoe polishing method and device based on visual auxiliary adjustment, and the method comprises the steps: firstly obtaining a shoe image, marking a flaw position on the shoe image, and obtaining a training sample; and training an identification model according to the training sample to obtain an AI visual model which can be used for identifying flaws. Acquiring a working image of the to-be-polished shoe; the working image is transmitted to an AI vision model, so that the AI vision model recognizes the flaw position of the working image, and polishing information is determined; and the polishing information is automatically packaged and distributed to the corresponding industrial robot in a set mode, so that the industrial robot is indicated to achieve the polishing process according to the polishing information and complete information sharing processing on one side of the industrial robot. On the basis, accurate polishing is conducted according to the actual flaws of the shoes, and the polishing machining mode is high in freedom degree and accurate.

Description

Technical Field

[0001] The present application relates to the field of intelligent manufacturing technology, and in particular to a shoe polishing method and system based on vision-assisted adjustment. Background Art

[0002] Shoe polishing is one of the most important links in the shoe assembly process. Its main purpose is to remove the defects on the surface of the shoe and improve its glossiness and waterproof performance. By using polishing tools and materials, you can remove the defects such as spots, scratches and stains on the surface of the shoe, making the shoe more beautiful and comfortable.

[0003] At present, the dust particles released during the shoe polishing process are harmful to the human body, so the application demand of automated processing equipment in the shoe polishing process is becoming increasingly prominent. With the application of Internet of Things technology and industrial robots, the automated processing equipment for shoe polishing has gradually matured. However, the current automated processing equipment for shoe polishing mainly operates according to set programs, and the processing procedures are relatively fixed, and the processing effect is poor in dealing with local complex polishing needs. Summary of the invention

[0004] In view of the above analysis, the embodiments of the present invention aim to provide a shoe polishing method and device based on visual assisted adjustment, so as to solve the problem that the automated processing equipment currently used for shoe polishing in the prior art mainly operates according to a set program, the processing procedures are relatively fixed, and the processing effect is poor in dealing with local complex polishing requirements.

[0005] The embodiment of the present application provides a shoe polishing method based on visual assisted adjustment, comprising the steps of:

[0006] Acquire a shoe image, and mark defect locations on the shoe image to obtain a training sample;

[0007] Training a recognition model according to the training samples to obtain an AI visual model that can be used to identify defects;

[0008] Acquire a working image of the shoe to be polished;

[0009] Transmitting the working image to the AI ​​vision model so that the AI ​​vision model can identify defect locations of the working image and determine polishing information;

[0010] The polishing information is automatically packaged and distributed to the corresponding industrial robot in a set mode to instruct the industrial robot to implement the polishing process according to the polishing information and complete information sharing processing on the industrial robot side.

[0011] The shoe polishing method based on visual-assisted adjustment in the embodiment of the present application first obtains a shoe image, and marks the defect position on the shoe image to obtain a training sample; trains a recognition model based on the training sample to obtain an AI visual model that can be used to identify defects. Obtain a working image of the shoe to be polished; transmit the working image to the AI ​​visual model so that the AI ​​visual model can recognize the defect position of the working image and determine the polishing information; automatically package the polishing information and distribute it to the corresponding industrial robot in a set mode to instruct the industrial robot to implement the polishing process according to the polishing information and complete information sharing processing on the industrial robot side. Based on this, precise polishing is performed according to the actual defects of the shoe, and the polishing processing method has a high degree of freedom and is accurate.

[0012] As one of the optional embodiments, before the process of transmitting the working image to the AI ​​vision model, the process further includes the following steps:

[0013] The outline of the target position of the shoe in the working image is identified according to an edge detection algorithm, and the outline is independently cut out to update the working image.

[0014] As one of the optional embodiments, the AI ​​visual model identifies the defect position of the working image and determines the polishing information, including the steps of:

[0015] Determine the image coordinate position of the defect position in the working image;

[0016] The actual coordinates of the image coordinate positions are converted according to the image coordinate positions to determine the grinding information.

[0017] As one of the optional embodiments, the process of converting the actual coordinates of the image coordinate position according to the image coordinate position to determine the polishing information is as follows:

[0018]

[0019] Wherein, X_img and Y_img represent the image coordinate positions, and X_real and Y_real represent the actual coordinates;

[0020] Where scale is the scale, as follows: scale = pixel length / actual length;

[0021] Wherein, resolution is the image resolution, as follows: resolution = pixel length / actual length (inches).

[0022] As one of the optional embodiments, the process of automatically packaging the polishing information and distributing it to the corresponding industrial robot in a set mode includes the steps of:

[0023] Deploy the operating system's packaging environment and various environment supports, and serve as a node server to schedule continuous integration tools;

[0024] Control the continuous integration tool to call the node server, and select the polishing information for continuous integration construction, packaging, uploading, and backing up according to the settings;

[0025] The polishing information is tested according to the continuous integration tool, and the polishing information is distributed to the corresponding industrial robot after the test passes.

[0026] As one of the optional embodiments, the information sharing process includes the steps of:

[0027] The polishing process of the industrial robot is transmitted back to the continuous integration tool through log information to achieve test case adjustment and human-computer interaction display.

[0028] As one of the optional embodiments, the polishing process includes the steps of:

[0029] Trigger scanning to calculate the offset value in space;

[0030] Polishing is performed according to the offset value and the position of the robot arm until the AI ​​vision model cannot identify the defect position in the working image.

[0031] The embodiment of the present application also provides a shoe polishing device based on visual auxiliary adjustment, comprising:

[0032] A sample acquisition module is used to acquire a shoe image and mark defect locations on the shoe image to obtain a training sample;

[0033] A model training module, used to train a recognition model according to the training samples to obtain an AI visual model that can be used to identify defects;

[0034] An image acquisition module, used to acquire a working image of the shoes to be polished;

[0035] An information calculation module, used for transmitting the working image to the AI ​​vision model, so that the AI ​​vision model can identify the defect position of the working image and determine the polishing information;

[0036] The processing control module is used to automatically package the polishing information and distribute it to the corresponding industrial robot in a set mode to instruct the industrial robot to implement the polishing process according to the polishing information and complete information sharing processing on the industrial robot side.

[0037] The shoe polishing device based on visual assisted adjustment in the embodiment of the present application first obtains a shoe image, and marks the defect position on the shoe image to obtain a training sample; trains a recognition model based on the training sample to obtain an AI visual model that can be used to identify defects. Obtain a working image of the shoe to be polished; transmit the working image to the AI ​​visual model so that the AI ​​visual model can recognize the defect position of the working image and determine the polishing information; automatically package the polishing information and distribute it to the corresponding industrial robot in a set mode to instruct the industrial robot to implement the polishing process according to the polishing information and complete information sharing processing on the industrial robot side. Based on this, precise polishing is performed according to the actual defects of the shoe, and the polishing processing method has a high degree of freedom and is accurate.

[0038] At least one embodiment of the present application further provides a data control device, including:

[0039] one or more memories non-transitorily storing computer-executable instructions;

[0040] One or more processors are configured to run computer executable instructions, wherein the computer executable instructions, when executed by the one or more processors, implement the shoe polishing method based on visual assisted adjustment according to any embodiment of the present application.

[0041] The above-mentioned data control device first obtains a shoe image and marks the defect position on the shoe image to obtain a training sample; trains the recognition model according to the training sample to obtain an AI visual model that can be used to identify defects. Obtain a working image of the shoe to be polished; transmit the working image to the AI ​​visual model so that the AI ​​visual model can identify the defect position of the working image and determine the polishing information; automatically package the polishing information and distribute it to the corresponding industrial robot in a set mode to instruct the industrial robot to implement the polishing process according to the polishing information and complete information sharing processing on the industrial robot side. Based on this, precise polishing is performed according to the actual defects of the shoes, and the polishing processing method has a high degree of freedom and is accurate.

[0042] At least one embodiment of the present application further provides a non-transitory computer-readable storage medium, wherein the non-transitory computer-readable storage medium stores computer-executable instructions, and when the computer-executable instructions are executed by a processor, the shoe polishing method based on visual-assisted adjustment according to any embodiment of the present application is implemented.

[0043] The above-mentioned non-transitory computer-readable storage medium first obtains a shoe image and marks the defect position on the shoe image to obtain a training sample; trains the recognition model based on the training sample to obtain an AI visual model that can be used to identify defects. Obtain a working image of the shoe to be polished; transmit the working image to the AI ​​visual model so that the AI ​​visual model can identify the defect position of the working image and determine the polishing information; automatically package the polishing information and distribute it to the corresponding industrial robot in a set mode to instruct the industrial robot to implement the polishing process according to the polishing information and complete information sharing processing on the industrial robot side. Based on this, precise polishing is performed according to the actual defects of the shoes, and the polishing processing method has a high degree of freedom and is accurate. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 It is a flow chart of a shoe polishing method based on visual assisted adjustment according to an embodiment of the application;

[0045] Figure 2 A flow chart of a shoe polishing method based on visually assisted adjustment according to a preferred embodiment;

[0046] Figure 3 This is the flow chart of the grinding process;

[0047] Figure 5 A schematic block diagram of a data control device provided by the present invention;

[0048] Figure 4 This is a module structure diagram of a shoe polishing device based on visual assisted adjustment according to an embodiment of an application;

[0049] Figure 6 A schematic diagram of a non-transitory computer-readable storage medium provided by the present invention. DETAILED DESCRIPTION

[0050] In order to make the purpose, technical scheme and advantages of the embodiments of the present application clearer, the technical scheme of the embodiments of the present application will be clearly and completely described below in conjunction with the drawings of the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all of the embodiments. Based on the described embodiments of the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0051] Unless otherwise defined, the technical terms or scientific terms used in this application should be understood by people with ordinary skills in the field to which this application belongs. "First", "second" and similar words used in this application do not indicate any order, quantity or importance, but are only used to distinguish different components. "Include" or "comprise" and similar words mean that the elements or objects appearing before the word cover the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0052] In order to keep the following description of the embodiments of the present application clear and concise, the present application omits detailed descriptions of some known functions and known components.

[0053] An embodiment of the present application provides a shoe polishing method based on visually assisted adjustment.

[0054] Figure 1 FIG. 1 is a flow chart of a shoe polishing method based on visually assisted adjustment according to an embodiment of an application. Figure 1 As shown, a shoe polishing method based on visual assisted adjustment in an embodiment of the application includes steps S100 to S104:

[0055] S100, obtaining a shoe image, and marking defect locations on the shoe image to obtain a training sample;

[0056] S101, training a recognition model according to the training samples to obtain an AI visual model that can be used to identify defects;

[0057] S102, obtaining a working image of the shoes to be polished;

[0058] S103, transmitting the working image to the AI ​​vision model, so that the AI ​​vision model can identify the defect position of the working image and determine the polishing information;

[0059] S104, automatically packaging the polishing information and distributing it to the corresponding industrial robot in a set mode, so as to instruct the industrial robot to implement the polishing process according to the polishing information and complete information sharing processing on the industrial robot side.

[0060] The shoe images include pre-prepared training samples and defect samples processed by subsequent information sharing, which are annotated according to known defect locations and used as training samples to establish a training data set.

[0061] Preferably, the AI ​​vision model is trained based on the machine vision algorithm and the training samples. Meanwhile, in the subsequent actual processing of the industrial robot, the image of the shoes in the polishing process is also used to adjust the AI ​​vision model in real time.

[0062] Among them, the AI ​​vision model of the embodiment of the present application has the following characteristics:

[0063] Feature extraction: AI vision models, especially deep learning models, are able to extract complex features from input data. When processing images of shoes, AI vision models can identify features such as edges, textures, shapes, and colors in the shoe images.

[0064] Data annotation: During the training phase, each shoe image in the training data set will be annotated with the defect location. Here, a large number of polished images will be annotated with the defect blanks (such as polishing defects-blanks), that is, each shoe object in the image is manually labeled (such as category name) and bounding box (Bounding Box). Annotation is used to indicate important features and their association with specific labels for AI visual models.

[0065] Learning process: With a large amount of labeled data, the AI ​​vision model adjusts its internal parameters (weights and biases) through the back-propagation algorithm so that it can accurately predict the object labels in the shoe images. This process involves the calculation and optimization of the loss function to reduce the prediction error.

[0066] Hierarchical feature representation: Deep learning models, such as convolutional neural networks (CNNs), gradually build feature representations from low-level to high-level through multiple layers of structure. For example, the first layer may only recognize simple edges and colors, while higher layers can recognize more complex shapes and structures.

[0067] Recognize patterns: After training, AI vision models are able to recognize patterns in data. In image recognition tasks, this means that the model is able to recognize visual patterns associated with specific labels.

[0068] Generalization capability: After training, the AI ​​vision model should be able to generalize to unseen data, that is, for new, unlabeled images, the AI ​​vision model should be able to accurately identify the learned labels.

[0069] After marking a large number of image defects, training the AI ​​vision model, and then calling the AI ​​vision model file, the AI ​​program can automatically identify the defects in the working image and obtain the coordinates of the label center in the working image, that is, the defect location.

[0070] As one of the preferred embodiments, Figure 2FIG. 1 is a flow chart of a shoe polishing method based on visually assisted adjustment according to a preferred embodiment. Figure 2 As shown, before the process of transmitting the working image to the AI ​​vision model in step S103, step S200 is also included:

[0071] S200, identifying the outline of the target position of the shoe in the working image according to an edge detection algorithm, and independently cutting out the outline to update the working image.

[0072] By capturing the camera, the working image of the shoes to be polished is sent to the vehicle in real time, and the outline of the target position is identified through the edge detection algorithm. Then each picture is cropped to keep the length and width consistent, and it can be ensured that each picture has a complete working image of the target position, so as to unify the input data standard of the AI ​​vision model.

[0073] The target position includes a shoe upper, a shoe surface, a shoe heel or a shoe sole.

[0074] As one of the preferred embodiments, Figure 2 As shown, in step S103, the AI ​​visual model identifies the defect position of the working image and determines the polishing information, including step S201 and step S202:

[0075] S201, determining the image coordinate position of the defect position in the working image;

[0076] S202: converting the actual coordinates of the image coordinate positions according to the image coordinate positions to determine polishing information.

[0077] Among them, there is a conversion relationship between the position of the defect in the working image and the actual coordinates, which are determined by the unified standard after edge detection algorithm processing, as follows:

[0078]

[0079] Wherein, X_img and Y_img represent the image coordinate positions, and X_real and Y_real represent the actual coordinates;

[0080] Where scale is the scale, as follows: scale = pixel length / actual length;

[0081] Wherein, resolution is the image resolution, as follows: resolution = pixel length / actual length (inches).

[0082] For example: scale = 5000 / 28 = 178.5; resolution = 5000 / (28 cm × 0.393701 inch / cm) = 453.6; this means that the image coordinate position is (2530, 300), and the converted actual coordinate is (14.2, 1.68).

[0083] Preferably, if Figure 2 As shown, the process of automatically packaging the polishing information in step S104 and distributing it to the corresponding industrial robot in a set mode includes steps S203 to S205:

[0084] S203, deploying the packaging environment and various environment supports of the operating system, and scheduling the continuous integration tool as a node server;

[0085] S204, controlling the continuous integration tool to call the node server, and performing continuous integration construction, packaging, uploading, and backing up of the polishing information according to the setting selection;

[0086] S205: Testing the polishing information according to the continuous integration tool, and distributing the polishing information to the corresponding industrial robot after the test passes.

[0087] In the embodiment of the present application, the same basic operating system is deployed for industrial robots and AI vision models to facilitate the precise control of multiple types of polishing with multiple details. After the system is deployed, the continuous integration tool is used in conjunction with the operating system to schedule and realize the automatic deployment, testing and application of polishing information.

[0088] Take the Windows operating system as an example and package it into an EXE program, as follows:

[0089]

[0090]

[0091]

[0092]

[0093] Based on this, the informatization of industrial robot control is realized, such as Figure 2 As shown, the information sharing process in step S104 includes step S206:

[0094] S206, transmitting the polishing process of the industrial robot back to the continuous integration tool through log information to achieve test case adjustment and human-computer interaction display.

[0095] Through the pre-test case adjustment, the matching degree between the AI ​​vision model and the industrial robot is improved, and the processing accuracy of shoe polishing is improved. At the same time, through the human-computer interaction display, it is convenient for relevant personnel to quickly identify and troubleshoot problems, ensuring the stability of the polishing process.

[0096] Preferably, Figure 3 For the grinding process flow chart, Figure 3 As shown, the grinding process includes step S300 and step S301:

[0097] S300, triggering scanning to calculate a spatial offset value;

[0098] S301, grinding is performed according to the offset value and the position of the robot arm until the AI ​​vision model cannot identify the defect position in the working image.

[0099] Among them, the industrial robot includes a robotic arm, a pneumatic rack, a 3D camera and a PLC controller. The position information in the polishing information is sent to the robotic arm, and the robotic arm repairs the polishing defects according to the coordinates. When the pneumatic clamp clamps the last upper, the 3D camera above triggers scanning, and the lead screw pulls the clamp to the polishing position at the scanning position. After the 3D camera completes the scanning action, it sends the point map to the 3D visual correction software. After calculation, the offset value in space is obtained, and the data is sent to the PLC. The PLC then combines the feedback signal of the current position of the robotic arm and the clamp status signal to notify the robotic arm to move. The robotic arm grinding head starts the first polishing along the path of the corresponding template. After the first polishing signal ends, the program corresponding to the AI ​​visual model recognizes the current shoe and calculates the defect coordinate position, and sends the instruction and corresponding point coordinates of the robotic arm for secondary polishing again. The robotic arm performs secondary polishing. When the secondary polishing is completed, the program corresponding to the AI ​​visual model recognizes again. If the polishing quality is normal, the process ends.

[0100] The shoe polishing method based on visual-assisted adjustment in any embodiment of the present application first obtains a shoe image, and marks the defect position on the shoe image to obtain a training sample; trains a recognition model based on the training sample to obtain an AI visual model that can be used to identify defects. Obtain a working image of the shoe to be polished; transmit the working image to the AI ​​visual model so that the AI ​​visual model can recognize the defect position of the working image and determine the polishing information; automatically package the polishing information and distribute it to the corresponding industrial robot in a set mode to instruct the industrial robot to implement the polishing process according to the polishing information and complete information sharing processing on the industrial robot side. Based on this, precise polishing is performed according to the actual defects of the shoe, and the polishing processing method has a high degree of freedom and is accurate.

[0101] The embodiment of the present application also provides a shoe polishing device based on visual assisted adjustment.

[0102] Figure 4 This is a module structure diagram of a shoe polishing device based on visual assisted adjustment according to an embodiment of the application, such as Figure 4 As shown, a shoe polishing device based on visually assisted adjustment according to an embodiment of the application includes:

[0103] The sample acquisition module 100 is used to acquire a shoe image and mark defect locations on the shoe image to obtain a training sample;

[0104] A model training module 101 is used to train a recognition model according to the training samples to obtain an AI visual model that can be used to identify defects;

[0105] An image acquisition module 102 is used to acquire a working image of the shoe to be polished;

[0106] An information calculation module 103 is used to transmit the working image to the AI ​​vision model so that the AI ​​vision model can identify the defect position of the working image and determine the polishing information;

[0107] The processing control module 104 is used to automatically package the polishing information and distribute it to the corresponding industrial robot in a set mode to instruct the industrial robot to implement the polishing process according to the polishing information and complete information sharing processing on the industrial robot side.

[0108] The shoe polishing device based on visual assisted adjustment in the embodiment of the present application first obtains a shoe image, and marks the defect position on the shoe image to obtain a training sample; trains a recognition model based on the training sample to obtain an AI visual model that can be used to identify defects. Obtain a working image of the shoe to be polished; transmit the working image to the AI ​​visual model so that the AI ​​visual model can recognize the defect position of the working image and determine the polishing information; automatically package the polishing information and distribute it to the corresponding industrial robot in a set mode to instruct the industrial robot to implement the polishing process according to the polishing information and complete information sharing processing on the industrial robot side. Based on this, precise polishing is performed according to the actual defects of the shoe, and the polishing processing method has a high degree of freedom and is accurate.

[0109] At least one embodiment of the present application also provides a data control device. Figure 5 A schematic block diagram of a data control device provided in at least one embodiment of the present application. Figure 5 As shown, the data control device 20 may include one or more memories 200 and one or more processors 201. The memory 200 is used to store computer executable instructions non-transiently; the processor 201 is used to run the computer executable instructions, and when the computer executable instructions are run by the processor 201, the processor 201 may execute one or more steps in the shoe polishing method based on visual assisted adjustment according to any embodiment of the present application.

[0110] The specific implementation and related explanation of each step of the shoe polishing method based on visual auxiliary adjustment can be found in the above-mentioned embodiment of the shoe polishing method based on visual auxiliary adjustment, which will not be elaborated here. Figure 5 The components of the data control device 20 shown are merely exemplary and non-limiting. The data control device 20 may also have other components according to actual application requirements.

[0111] In one embodiment, the processor 201 and the memory 200 can communicate with each other directly or indirectly. For example, the processor 201 and the memory 200 can communicate via a network connection. The network may include a wireless network, a wired network, and / or any combination of a wireless network and a wired network, and the present application does not limit the type and function of the network. For another example, the processor 201 and the memory 200 can also communicate via a bus connection. The bus may be a peripheral component interconnect standard (PCI) bus or an extended industrial standard architecture (EISA) bus, etc. For example, the processor 201 and the memory 200 may be arranged at a remote data server end (cloud) or a distributed energy system end (local end), or may be arranged at a client end (e.g., a mobile device such as a mobile phone). For example, the processor 201 may be a device having data processing capability and / or instruction execution capability such as a central processing unit (CPU), a tensor processor (TPU), or a graphics processor GPU, and may control other components in the data prediction device 20 to perform desired functions. The central processing unit (CPU) may be an X86 or ARM architecture, etc.

[0112] In one embodiment, the memory 200 may include any combination of one or more computer program products, and the computer program product may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. Volatile memory may include, for example, random access memory (RAM) and / or cache memory (cache), etc. Non-volatile memory may include, for example, read-only memory (ROM), hard disk, erasable programmable read-only memory (EPROM), portable compact disk read-only memory (CD-ROM), USB memory, flash memory, etc. One or more computer executable instructions may be stored on the computer-readable storage medium, and the processor 201 may execute the computer executable instructions to implement various functions of the data prediction device 20. Various applications and various data, as well as various data used and / or generated by the application, etc. may also be stored in the memory 200.

[0113] It should be noted that the data control device 20 can achieve technical effects similar to the aforementioned shoe polishing method based on visual assisted adjustment, and the repeated parts will not be repeated.

[0114] At least one embodiment of the present application also provides a non-transitory computer-readable storage medium. Figure 6 A schematic diagram of a non-transitory computer-readable storage medium provided for at least one embodiment of the present application. Figure 6 As shown, one or more computer executable instructions 301 may be non-transitory stored on a non-transitory computer readable storage medium 30. For example, when the computer executable instructions 301 are executed by a computer, the computer may execute one or more steps in the shoe polishing method based on visual assistance adjustment according to any embodiment of the present application.

[0115] In one embodiment, the non-transitory computer-readable storage medium 30 may be applied to the above-mentioned data control device 20 , for example, it may be the memory 200 in the data control device 20 .

[0116] In one of the embodiments, the description of the non-transitory computer-readable storage medium 30 may refer to the description of the memory 200 in the embodiment of the data control device 20 , and the repeated parts will not be repeated.

[0117] It should be noted that the memory 200 stores different non-transiently stored computer executable instructions, and the data control device 20 corresponds to a firmware upgrade device. When the computer executable instructions are executed by the processor 201, the processor 201 can execute one or more steps in the shoe polishing method based on visual assisted adjustment according to any embodiment of the present application.

[0118] There are a few points to note about this application:

[0119] (1) The drawings of the embodiments of the present application only relate to the structures related to the embodiments of the present application, and other structures may refer to the general design.

[0120] (2) For the sake of clarity, the thickness and size of layers or structures are exaggerated in the drawings used to describe the embodiments of the present invention. It is understood that when an element such as a layer, film, region, or substrate is referred to as being "on" or "under" another element, the element may be "directly" "on" or "under" the other element, or there may be intervening elements.

[0121] (3) In the absence of conflict, the embodiments of the present application and the features in the embodiments may be combined with each other to obtain new embodiments. The above are only specific implementation methods of the present application, but the protection scope of the present application is not limited thereto. The protection scope of the present application shall be based on the protection scope of the claims.

[0122] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0123] The above embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the patent application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent application shall be subject to the attached claims.

Claims

1. A shoe polishing method based on visual assisted adjustment, characterized in that: Includes steps: Acquire a shoe image, and mark defect locations on the shoe image to obtain a training sample; Training a recognition model according to the training samples to obtain an AI visual model that can be used to identify defects; Acquire a working image of the shoe to be polished; Transmitting the working image to the AI ​​vision model so that the AI ​​vision model can identify defect locations of the working image and determine polishing information; The polishing information is automatically packaged and distributed to the corresponding industrial robot in a set mode to instruct the industrial robot to implement the polishing process according to the polishing information and complete information sharing processing on the industrial robot side.

2. The shoe polishing method based on visual assisted adjustment according to claim 1, characterized in that: Before the process of transmitting the working image to the AI ​​vision model, the process further includes the following steps: The outline of the target position of the shoe in the working image is identified according to an edge detection algorithm, and the outline is independently cut out to update the working image.

3. The shoe polishing method based on visual assisted adjustment according to claim 1, characterized in that: The AI ​​visual model identifies the defect position of the working image and determines the polishing information, including the steps of: Determine the image coordinate position of the defect position in the working image; The actual coordinates of the image coordinate positions are converted according to the image coordinate positions to determine the grinding information.

4. The shoe polishing method based on visual assisted adjustment according to claim 3, characterized in that: The process of converting the actual coordinates of the image coordinate position according to the image coordinate position to determine the polishing information is as follows: Wherein, X_img and Y_img represent the image coordinate positions, and X_real and Y_real represent the actual coordinates; Where scale is the scale, as follows: scale = pixel length / actual length; Wherein, resolution is the image resolution, as follows: resolution = pixel length / actual length (inches).

5. The shoe polishing method based on visual assisted adjustment according to claim 1, characterized in that: The process of automatically packaging the polishing information and distributing it to the corresponding industrial robot in a set mode includes the steps of: Deploy the operating system's packaging environment and various environment supports, and serve as a node server to schedule continuous integration tools; Control the continuous integration tool to call the node server, and select the polishing information for continuous integration construction, packaging, uploading, and backing up according to the settings; The polishing information is tested according to the continuous integration tool, and the polishing information is distributed to the corresponding industrial robot after the test passes.

6. The shoe polishing method based on visual assisted adjustment according to claim 5, characterized in that: The information sharing process includes the following steps: The polishing process of the industrial robot is transmitted back to the continuous integration tool through log information to achieve test case adjustment and human-computer interaction display.

7. The shoe polishing method based on visual assisted adjustment according to claim 1, characterized in that: The polishing process comprises the steps of: Trigger scanning to calculate the offset value in space; Polishing is performed according to the offset value and the position of the robot arm until the AI ​​vision model cannot identify the defect position in the working image.

8. A shoe polishing device based on visual assisted adjustment, characterized in that: include: A sample acquisition module is used to acquire a shoe image and mark defect locations on the shoe image to obtain a training sample; A model training module, used to train a recognition model according to the training samples to obtain an AI visual model that can be used to identify defects; An image acquisition module, used to acquire a working image of the shoes to be polished; An information calculation module, used for transmitting the working image to the AI ​​vision model, so that the AI ​​vision model can identify the defect position of the working image and determine the polishing information; The processing control module is used to automatically package the polishing information and distribute it to the corresponding industrial robot in a set mode to instruct the industrial robot to implement the polishing process according to the polishing information and complete information sharing processing on the industrial robot side.

9. A non-transitory computer-readable storage medium, characterized in that: The non-transitory computer-readable storage medium stores computer-executable instructions, and when the computer-executable instructions are executed by a processor, the shoe polishing method based on visual-assisted adjustment as described in any one of claims 1 to 7 is implemented.

10. A data control device, characterized in that: include: one or more memories non-transitorily storing computer-executable instructions; One or more processors are configured to run computer executable instructions, wherein the computer executable instructions, when executed by the one or more processors, implement the shoe polishing method based on visual assisted adjustment as described in any one of claims 1 to 7.

Images