Machine vision-based auxiliary material intelligent identification, splitting and warehousing method and device

Abstract

The application relates to a machine vision-based intelligent identification and splitting and warehousing method and device for auxiliary materials. The method comprises the following steps: based on a multi-view vision imaging three-dimensional model rapid generation algorithm, image acquisition and laser scanning of palletized auxiliary materials are carried out through machine vision to generate a three-dimensional model of the palletized auxiliary materials; based on a multi-dimensional feature point extraction algorithm, multi-dimensional feature extraction is carried out on the three-dimensional model of the palletized auxiliary materials through peripheral video scanning to generate auxiliary material feature points, and based on this, a multi-dimensional model is generated by assigning a digital label to a single material; based on a reverse engineering artificial intelligence algorithm, a single material model is generated by splitting the single material based on the multi-dimensional model; and based on the single material model, the single material is grabbed and sorted through a logistics sorting module to complete the intelligent identification, splitting and warehousing of the auxiliary materials. Through accurate identification and recognition of the palletized auxiliary materials, the application realizes single material splitting and analysis of the palletized auxiliary materials, and based on this, accurate grabbing, sorting and intelligent identification and warehousing of the auxiliary materials are completed.

Description

Technical Field

[0001] This disclosure relates to the field of intelligent identification and sorting, and more specifically, to a method and apparatus for intelligent identification, splitting and warehousing of auxiliary materials based on machine vision. Background Technology

[0002] In the cigarette production process, intelligent warehousing of auxiliary materials is the technological foundation of modern production enterprises. Intelligent warehousing of auxiliary materials involves packaging, weighing, and then conveying them to the formula storage via an inbound conveyor system. This intelligent warehousing system leverages the characteristics of cigarette raw materials—such as their single variety and batch storage—to achieve automatic classification and warehousing through barcodes, QR codes, and RFID identification technologies. However, existing auxiliary material warehousing methods often rely on manual sorting and handling due to factors such as the large variety and quantity of materials, significant differences in packaging and size between different manufacturers and batches of the same material, irregular stacking, and frequent material changes. Manual sorting suffers from low efficiency, high labor intensity, high sorting error rates, and difficulties in automatic statistical analysis. Furthermore, the production process, in order to meet the requirements of homogenization, humanization, and precision, further increases the workload of manual sorting.

[0003] Therefore, one or more methods are needed to solve the above problems.

[0004] It should be noted that the information disclosed in the background section above is only used to enhance the understanding of the background of this disclosure, and therefore may include information that does not constitute prior art known to those skilled in the art. Summary of the Invention

[0005] The purpose of this disclosure is to provide a machine vision-based intelligent identification, splitting, and warehousing method, apparatus, electronic device, and computer-readable storage medium for auxiliary materials, thereby overcoming, to at least some extent, one or more problems caused by the limitations and defects of related technologies.

[0006] According to one aspect of this disclosure, a machine vision-based intelligent identification, splitting, and warehousing method for auxiliary materials is provided, comprising:

[0007] A rapid 3D model generation algorithm based on multi-view vision imaging is used to acquire images of palletizing materials and perform laser scanning to generate 3D models of the palletizing materials.

[0008] Based on a multi-dimensional feature point extraction algorithm, multi-dimensional features are extracted from the three-dimensional model of the palletized auxiliary materials by scanning the surrounding video to generate auxiliary material feature points. Based on the auxiliary material feature points, a multi-dimensional model is generated by assigning digital labels to individual materials.

[0009] Based on the reverse engineering artificial intelligence algorithm, a single-material model is generated by splitting the multi-dimensional model into single materials.

[0010] Based on the single material model, the logistics sorting module grabs and sorts the single material to complete the intelligent identification, splitting, and warehousing of auxiliary materials.

[0011] In one exemplary embodiment of this disclosure, a rapid 3D model generation algorithm based on multi-view vision imaging acquires images of the palletized auxiliary materials through auxiliary material vision to generate auxiliary material image information.

[0012] Based on the information of the auxiliary materials, the palletizing auxiliary materials are modeled using a 3D laser scanning module to generate a 3D model of the palletizing machine.

[0013] In one exemplary embodiment of this disclosure, based on the manual-assisted guidance mode, images of palletizing auxiliary materials are acquired through human vision to generate training screen information.

[0014] Based on the training image information, the palletizing auxiliary materials are modeled using a 3D laser scanning module to generate a 3D model for palletizing training.

[0015] A three-dimensional model of palletizing auxiliary materials is generated by combining the three-dimensional model of the palletizing machine and the three-dimensional model of the palletizing training.

[0016] In one exemplary embodiment of this disclosure, based on a multi-dimensional feature point extraction algorithm, multi-dimensional features are extracted from the three-dimensional outline of the palletized auxiliary materials, the color of the palletized auxiliary materials, the label of the palletized auxiliary materials, the barcode of the palletized auxiliary materials, the QR code of the palletized auxiliary materials, and the production batch number of the palletized auxiliary materials through surrounding video scanning, thereby generating auxiliary material feature points.

[0017] Based on an AI-based self-learning excipient verification algorithm, multi-dimensional feature values ​​are generated by correcting the feature points of the excipients.

[0018] Based on the multi-dimensional feature values, a multi-dimensional model is generated by assigning single-material digital labels to the three-dimensional model of the palletizing auxiliary materials.

[0019] In one exemplary embodiment of this disclosure, a training set is generated by calibrating the information of the palletizing training 3D model based on an artificial intelligence self-learning algorithm.

[0020] Based on an artificial intelligence self-learning algorithm, a test set is generated by recognizing preset obstacle scenarios on the training set.

[0021] In one exemplary embodiment of this disclosure, an automatic splitting algorithm for palletized material models is generated by developing a model assignment algorithm based on artificial intelligence algorithms and reverse engineering algorithms using the test set.

[0022] Based on the automatic splitting algorithm of the palletizing material model, a single material model is generated by splitting the multi-dimensional model.

[0023] In one exemplary embodiment of this disclosure, palletizing material information is generated based on the single material model by identifying the type of palletizing auxiliary material, the manufacturer of the palletizing auxiliary material, and the production batch of the palletizing auxiliary material.

[0024] Based on the preset inbound task, the logistics sorting module locks the preset single material location through the palletized material information and generates single material location information.

[0025] Based on the location information of the single material, the servo module uses a robotic arm to grab and sort the single material, completing the intelligent identification, splitting, and warehousing of palletizing auxiliary materials.

[0026] In one aspect of this disclosure, a machine vision-based intelligent identification, splitting, and warehousing device for auxiliary materials is provided, comprising:

[0027] The image acquisition module is used to acquire images of palletizing materials through multi-view machine vision and generate a 3D model of the palletizing materials.

[0028] The feature extraction module is used to assign multi-dimensional features to the three-dimensional model of the palletizing auxiliary materials through surrounding video scanning, and generate a multi-dimensional model.

[0029] The material splitting module is used to generate a single-material model by splitting the multi-dimensional model into single materials.

[0030] The grabbing and sorting module is used to grab and sort single materials, and complete the intelligent identification, splitting and warehousing of auxiliary materials.

[0031] In one aspect of this disclosure, an electronic device is provided, comprising:

[0032] Processor; and

[0033] A memory storing computer-readable instructions that, when executed by the processor, implement the method according to any one of the preceding claims.

[0034] In one aspect of this disclosure, a computer-readable storage medium is provided having a computer program stored thereon that, when executed by a processor, implements the method according to any one of the preceding claims.

[0035] This disclosure discloses an exemplary embodiment of a machine vision-based intelligent identification, splitting, and warehousing method and apparatus for auxiliary materials. The method includes: a rapid 3D model generation algorithm based on multi-view vision imaging, using multi-view machine vision to acquire images of palletized auxiliary materials and perform laser scanning to generate a 3D model of the palletized auxiliary materials; a multi-dimensional feature point extraction algorithm, using surrounding video scanning to extract multi-dimensional features from the 3D model of the palletized auxiliary materials to generate auxiliary material feature points; based on the auxiliary material feature points, assigning digital labels to individual materials to generate a multi-dimensional model; a reverse engineering artificial intelligence algorithm, using a single-material splitting method to generate a single-material model; and based on the single-material model, using a logistics sorting module to grasp and sort the single materials, completing the intelligent identification, splitting, and warehousing of the auxiliary materials. On one hand, this disclosure achieves individual splitting and analysis of palletized auxiliary materials through accurate identification and recognition; on the other hand, based on the individual splitting and analysis of auxiliary materials, this disclosure completes accurate grasping, sorting, and intelligent identification and warehousing of auxiliary materials through a logistics sorting module.

[0036] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description

[0037] The above and other features and advantages of this disclosure will become more apparent from the detailed description of exemplary embodiments thereof with reference to the accompanying drawings.

[0038] Figure 1 A flowchart is shown for a machine vision-based intelligent identification, splitting, and warehousing method for auxiliary materials according to an exemplary embodiment of the present disclosure;

[0039] Figure 2 The illustration shows an application scenario of a machine vision-based intelligent identification, splitting, and warehousing method for auxiliary materials according to an exemplary embodiment of the present disclosure.

[0040] Figure 3 A schematic block diagram of a machine vision-based intelligent identification, splitting, and warehousing device for auxiliary materials is shown according to an exemplary embodiment of the present disclosure.

[0041] Figure 4 The diagram shows a front view of a model of a machine vision-based intelligent identification, splitting, and warehousing device for auxiliary materials according to an exemplary embodiment of the present disclosure.

[0042] Figure 5 A top view of a model of a machine vision-based intelligent identification, splitting, and warehousing device for auxiliary materials is shown according to an exemplary embodiment of the present disclosure. Detailed Implementation

[0043] Exemplary embodiments will now be described more fully with reference to the accompanying drawings. However, these exemplary embodiments can be implemented in many forms and should not be construed as limited to the embodiments set forth herein; rather, they are provided so that this disclosure will be thorough and complete, and will fully convey the concept of the exemplary embodiments to those skilled in the art. The same reference numerals in the drawings denote the same or similar parts, and therefore repeated descriptions of them will be omitted.

[0044] Furthermore, the described features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. Numerous specific details are provided in the following description to give a thorough understanding of embodiments of this disclosure. However, those skilled in the art will recognize that the technical solutions of this disclosure can be practiced without one or more of the specific details described, or other methods, components, materials, apparatuses, steps, etc., can be employed. In other instances, well-known structures, methods, apparatuses, implementations, materials, or operations are not shown or described in detail to avoid obscuring various aspects of this disclosure.

[0045] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities can be implemented in software, or in one or more software-hardened modules, or in different network and / or processor devices and / or microcontroller devices.

[0046] In this example embodiment, a machine vision-based intelligent identification, splitting, and warehousing method for auxiliary materials is first provided; see reference Figure 1 As shown, this machine vision-based intelligent identification, splitting, and warehousing method for auxiliary materials may include the following steps:

[0047] Step S110: Based on the multi-view vision imaging-based 3D model rapid generation algorithm, the 3D model of the palletizing auxiliary material is generated by image acquisition and laser scanning of the palletizing auxiliary material through multi-view machine vision.

[0048] Step S120: Based on the multi-dimensional feature point extraction algorithm, multi-dimensional features are extracted from the three-dimensional model of the palletized auxiliary material by scanning the surrounding video to generate auxiliary material feature points. Based on the auxiliary material feature points, a multi-dimensional model is generated by assigning digital labels to individual materials.

[0049] Step S130: Based on the reverse engineering artificial intelligence algorithm, a single material model is generated by splitting the multi-dimensional model into single materials.

[0050] Step S140: Based on the single material model, the single material is picked up and sorted by the logistics sorting module to complete the intelligent identification, splitting and warehousing of auxiliary materials.

[0051] This disclosure discloses an exemplary embodiment of a machine vision-based intelligent identification, splitting, and warehousing method and apparatus for auxiliary materials. The method includes: a rapid 3D model generation algorithm based on multi-view vision imaging, using multi-view machine vision to acquire images of palletized auxiliary materials and perform laser scanning to generate a 3D model of the palletized auxiliary materials; a multi-dimensional feature point extraction algorithm, using surrounding video scanning to extract multi-dimensional features from the 3D model of the palletized auxiliary materials to generate auxiliary material feature points; based on the auxiliary material feature points, assigning digital labels to individual materials to generate a multi-dimensional model; a reverse engineering artificial intelligence algorithm, using a single-material splitting method to generate a single-material model; and based on the single-material model, using a logistics sorting module to grasp and sort the single materials, completing the intelligent identification, splitting, and warehousing of the auxiliary materials. On one hand, this disclosure achieves individual splitting and analysis of palletized auxiliary materials through accurate identification and recognition; on the other hand, based on the individual splitting and analysis of auxiliary materials, this disclosure completes accurate grasping, sorting, and intelligent identification and warehousing of auxiliary materials through a logistics sorting module.

[0052] The following will further explain a machine vision-based intelligent identification, splitting, and warehousing method for auxiliary materials in this example embodiment.

[0053] In the template configuration step S110, a rapid 3D model generation algorithm based on multi-view vision imaging can be used to generate a 3D model of the palletizing auxiliary materials by acquiring images and performing laser scanning through multi-view machine vision.

[0054] In the embodiments of this example, as Figures 2-5 As shown, after the logistics auxiliary materials are assembled onto the pallet, a visual capture 3D scanning area is defined along the path between the logistics conveyor belt and the sorting robot arm (sorting device) of the servo module. A visual capture camera (typically arranged in a triangular pattern with three support poles and a horizontal bar extending directly above the pallet) is used within this 3D scanning area to capture images of the palletized auxiliary materials. Each support pole has a high-definition intelligent camera mounted at height above the incoming materials, and the horizontal bar has another high-definition intelligent camera mounted at horizontal height above the incoming materials, serving as the visual capture camera for the auxiliary materials. This method, using four high-definition cameras for omnidirectional shooting, perfectly captures the entire visual image of the incoming auxiliary materials, preparing for the next step of 3D modeling.

[0055] Simultaneously, by installing 3D laser scanning modules on each of the equipment's uprights and crossbars, the positional information of various auxiliary materials on the auxiliary material tray is scanned in 3D. Based on the auxiliary material image information (i.e., the characteristics of the items in the image), a 3D model is rapidly generated using a multi-view vision imaging 3D modeling algorithm, simultaneously constructing a 3D model of the palletizing machine. This method identifies and fully reconstructs the shape and feature markings of the palletizing auxiliary materials, enabling the identification of the shape features of all auxiliary materials in three-dimensional space and allowing for a preliminary assessment of the auxiliary material information based on these features.

[0056] In the embodiments of this example, as Figures 2-5 The example illustrates a manual-guided approach where images of palletizing materials are captured using human vision to generate training images. Based on these training images, a 3D laser scanning module is used to model the palletizing materials, generating a 3D training model. In other words, in the initial stages of this example, images of the palletizing materials can be captured and modeled using manual guidance to generate a 3D training model. This facilitates subsequent self-learning by the artificial intelligence system.

[0057] Finally, by combining the three-dimensional model of the palletizing machine and the three-dimensional model of the palletizing training, a three-dimensional model of the palletizing auxiliary materials is generated.

[0058] In template configuration step S120, a multi-dimensional feature point extraction algorithm can be used to extract multi-dimensional features from the three-dimensional model of the palletizing auxiliary materials by scanning the surrounding video, generating auxiliary material feature points. Based on the auxiliary material feature points, a multi-dimensional model is generated by assigning digital labels to individual materials.

[0059] In the embodiments of this example, as Figure 2 As shown, the multi-dimensional feature point extraction algorithm based on surrounding video scanning technology extracts multi-dimensional features such as the three-dimensional outline of the palletized auxiliary materials, the color of the palletized auxiliary materials, the label of the palletized auxiliary materials, the barcode of the palletized auxiliary materials, the QR code of the palletized auxiliary materials, and the production batch number of the palletized auxiliary materials through surrounding video scanning, and generates auxiliary material feature points.

[0060] Subsequently, based on the AI ​​self-learning auxiliary material verification algorithm, the auxiliary material feature points are corrected by assigning digital labels to them on the palletizing training 3D model, thereby generating multi-dimensional feature values.

[0061] Finally, based on the multi-dimensional feature values, multi-dimensional assignment is performed on the 3D model of the palletizing machine. The extracted and corrected multi-dimensional feature values ​​are assigned to different 3D contours in the model to generate a multi-dimensional model. This example uses AI self-learning to repeatedly verify different palletizing materials to continuously correct extraction and assignment errors.

[0062] In template configuration step S130, a single-material model can be generated by splitting the multi-dimensional model into single materials based on a reverse engineering artificial intelligence algorithm.

[0063] In the embodiments of this example, as Figure 2 As shown, based on an artificial intelligence self-learning algorithm, visual image information is manually collected and the information of the palletizing training 3D model is calibrated to generate a training set. Then, by artificially setting obstacle scenarios, the training set is used for scene recognition training and testing to generate a test set.

[0064] This example demonstrates how continuously enriching the training data and introducing obstacle scenarios can improve the accuracy of target object recognition in a machine self-learning system, enhance the system's intelligence, and reduce the error rate in identifying auxiliary material information.

[0065] In the embodiments of this example, as Figure 2 As shown, firstly, based on artificial intelligence algorithms and reverse engineering algorithms, the model assignment algorithm is developed through the test set to improve the automatic splitting algorithm of the material model and generate an automatic splitting algorithm for palletized material models.

[0066] Subsequently, based on the automatic splitting algorithm of the palletizing material model, the multi-dimensional model can be quickly and automatically split, enabling machine recognition to split the palletizing auxiliary materials into single materials and generate a single material model.

[0067] In template configuration step S140, the single material model can be used to grab and sort the single material through the logistics sorting module to complete the intelligent identification, splitting and warehousing of auxiliary materials.

[0068] In the embodiments of this example, as Figure 2 As shown, based on the single-material model, the logistics sorting module and servo module work together to intelligently identify features such as the color, shape, and barcode of the palletizing materials, generating palletizing material information such as the type of palletizing material, the manufacturer, and the production batch. This palletizing material information is then uploaded to the logistics control center platform for archiving.

[0069] Meanwhile, the logistics control center platform issues inbound task instructions to the logistics sorting module based on the preset inbound task. The logistics sorting module generates single material location information by locking the position of the preset single material based on the palletized material information.

[0070] Finally, based on the single material location information, the servo module controls the robotic arm to accurately grasp and sort the single material, completing the intelligent identification, splitting, and warehousing of palletizing auxiliary materials.

[0071] It should be noted that although the steps of the method in this disclosure are described in a specific order in the accompanying drawings, this does not require or imply that the steps must be performed in that specific order, or that all the steps shown must be performed to achieve the desired result. Additional or alternative steps may be omitted, multiple steps may be combined into one step, and / or a step may be broken down into multiple steps.

[0072] Furthermore, in this example embodiment, a machine vision-based intelligent identification, splitting, and warehousing device for auxiliary materials is also provided. (Refer to...) Figure 3 As shown, the machine vision-based intelligent identification, splitting, and warehousing device 300 for auxiliary materials may include: an image acquisition module 310, a feature extraction module 320, a material splitting module 330, and a gripping and sorting module 340. Wherein:

[0073] Image acquisition module 310 is used to acquire images of palletizing auxiliary materials through multi-view machine vision and generate a three-dimensional model of the palletizing auxiliary materials.

[0074] The feature extraction module 320 is used to extract multi-dimensional features from the three-dimensional model of the palletized auxiliary materials by scanning the surrounding video, and to generate auxiliary material feature points. It is used to generate a multi-dimensional model by assigning digital labels to individual materials.

[0075] The material splitting module 330 is used to generate a single-material model by splitting the multi-dimensional model into single materials.

[0076] The grabbing and sorting module 340 is used to grab and sort single materials, and complete the intelligent identification, splitting and warehousing of auxiliary materials.

[0077] The specific details of each of the machine vision-based intelligent identification, splitting and warehousing device modules for auxiliary materials mentioned above have been described in detail in the corresponding machine vision-based intelligent identification, splitting and warehousing method for auxiliary materials, so they will not be repeated here.

[0078] It should be noted that although several modules or units of a machine vision-based intelligent identification, splitting, and warehousing device 300 for auxiliary materials are mentioned in the detailed description above, this division is not mandatory. In fact, according to embodiments of this disclosure, the features and functions of two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided and embodied by multiple modules or units.

[0079] Furthermore, in an exemplary embodiment of this disclosure, an electronic device capable of implementing the above-described method is also provided.

[0080] Those skilled in the art will understand that various aspects of the present invention can be implemented as systems, methods, or program products. Therefore, various aspects of the present invention can be specifically implemented as entirely hardware embodiments, entirely software embodiments (including firmware, microcode, etc.), or embodiments combining hardware and software aspects, collectively referred to herein as “circuit,” “module,” or “system.”

[0081] From the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein can be implemented by software or by combining software with necessary hardware. Therefore, the technical solutions according to the embodiments of this disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, USB flash drive, external hard drive, etc.) or on a network, including several instructions to cause a computing device (such as a personal computer, server, terminal device, or network device, etc.) to execute the methods according to the embodiments of this disclosure.

[0082] In exemplary embodiments of this disclosure, a computer-readable storage medium is also provided, on which a program product capable of implementing the methods described above is stored. In some possible embodiments, various aspects of the invention may also be implemented as a program product comprising program code that, when the program product is run on a terminal device, causes the terminal device to perform the steps of the various exemplary embodiments of the invention described in the "Exemplary Methods" section above.

[0083] Furthermore, the above figures are merely illustrative of the processes included in the method according to exemplary embodiments of the present invention, and are not intended to be limiting. It is readily understood that the processes shown in the above figures do not indicate or limit the temporal order of these processes. Additionally, it is readily understood that these processes may be executed synchronously or asynchronously, for example, in multiple modules.

[0084] Other embodiments of this disclosure will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not disclosed herein. The specification and embodiments are to be considered exemplary only, and the true scope and spirit of this disclosure are indicated by the claims.

[0085] It should be understood that this disclosure is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this disclosure is limited only by the appended claims.

Claims

1. A machine vision-based intelligent identification and splitting of auxiliary materials into a warehouse method, characterized in that, The method comprises: a three-dimensional model rapid generation algorithm based on multi-view visual imaging, image acquisition of the palletizing auxiliary materials by multi-view machine vision, laser scanning, and generation of a three-dimensional model of the palletizing auxiliary materials; a multi-dimensional feature point extraction algorithm, multi-dimensional feature extraction of the three-dimensional model of the palletizing auxiliary materials by peripheral video scanning, generation of auxiliary material feature points, and generation of a multi-dimensional model by assigning digital labels to single materials based on the auxiliary material feature points; a reverse engineering artificial intelligence algorithm, single material model generation by single material separation of the multi-dimensional model; based on the single material model, the single material is grabbed and sorted by the logistics sorting module, and the intelligent recognition and separation of the auxiliary materials into the warehouse is completed.

2. The machine vision-based intelligent auxiliary material identification, splitting and warehousing method according to claim 1, characterized in that, The method further comprises: a three-dimensional model rapid generation algorithm based on multi-view visual imaging, image acquisition of the palletizing auxiliary materials by auxiliary visual, and generation of auxiliary material picture information; based on the auxiliary material picture information, modeling of the palletizing auxiliary materials by a three-dimensional laser scanning module, and generation of a three-dimensional model of the palletizing machine. 3.The machine vision-based intelligent auxiliary material identification, splitting and storage method of claim 2, wherein, The method further comprises: based on an artificial auxiliary guidance mode, image acquisition of the palletizing auxiliary materials by artificial vision, and generation of training picture information; based on the training picture information, modeling of the palletizing auxiliary materials by a three-dimensional laser scanning module, and generation of a three-dimensional model of the palletizing training; by combining the three-dimensional model of the palletizing machine and the three-dimensional model of the palletizing training, a three-dimensional model of the palletizing auxiliary materials is generated.

4. The machine vision-based intelligent auxiliary material identification, splitting and warehousing method according to claim 3, characterized in that, The method further comprises: a multi-dimensional feature point extraction algorithm, multi-dimensional feature extraction of the three-dimensional contour line of the palletizing auxiliary materials, the color of the palletizing auxiliary materials, the label of the palletizing auxiliary materials, the bar code of the palletizing auxiliary materials, the two-dimensional code of the palletizing auxiliary materials, and the production batch number of the palletizing auxiliary materials by peripheral video scanning, and generation of auxiliary material feature points; based on an artificial intelligence self-learning auxiliary material verification algorithm, multi-dimensional feature values are generated by correcting the auxiliary material feature points; based on the multi-dimensional feature values, a multi-dimensional model is generated by assigning digital labels to single materials of the three-dimensional model of the palletizing auxiliary materials. 5.The machine vision-based intelligent auxiliary material identification, splitting and storage method of claim 3, wherein, The method further comprises: based on an artificial intelligence self-learning algorithm, a training set is generated by information calibration of the three-dimensional model of the palletizing training; based on an artificial intelligence self-learning algorithm, a test set is generated by preset obstacle scene recognition of the training set.

6. The machine vision-based intelligent auxiliary material identification, splitting, and warehousing method of claim 5, wherein, The method further comprises: based on an artificial intelligence algorithm and a reverse engineering algorithm, a palletizing material model automatic separation algorithm is generated by developing a model assignment algorithm based on the test set; based on the palletizing material model automatic separation algorithm, a single material model is generated by separating the multi-dimensional model.

7. The machine vision-based intelligent auxiliary material identification, splitting, and warehousing method of claim 1, wherein, The method further comprises: based on the single material model, palletizing auxiliary material types, palletizing auxiliary material manufacturers, and palletizing auxiliary material production batches are identified, and palletizing material information is generated; based on a preset warehousing task, the logistics sorting module locks the preset single material position based on the palletizing material information, and generates single material position information; based on the single material position information, a servo module grabs and sorts single materials by a mechanical arm, and completes the intelligent recognition and separation of the palletizing auxiliary materials into the warehouse.

8. A machine vision-based auxiliary material intelligent identification, splitting and warehousing device, characterized in that, The device comprises: An image acquisition module is configured to acquire images of the palletizing auxiliary materials through multi-view machine vision, and generate a three-dimensional model of the palletizing auxiliary materials; A feature extraction module is configured to extract multi-dimensional features of the three-dimensional model of the palletizing auxiliary materials through peripheral video scanning, and generate auxiliary material feature points, and to assign digital labels to single materials, and generate a multi-dimensional model; A material splitting module is configured to split single materials based on a reverse engineering artificial intelligence algorithm, and generate a single material model through the multi-dimensional model; A grabbing and sorting module is configured to grab and sort the single materials, and complete intelligent identification, splitting and warehousing of the auxiliary materials.

9. An electronic device, comprising: comprising a processor; and a memory having computer readable instructions stored thereon, the computer readable instructions, when executed by the processor, implement the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, a computer program stored thereon, the computer program, when executed by a processor, implements the method according to any one of claims 1 to 7.

Images