Component registration method and device, equipment, storage medium and product

Abstract

The invention discloses a part registration method and device, equipment, a storage medium and a product. The method comprises the steps that a to-be-registered part detection graph and a to-be-registered part standard graph are acquired; performing target detection on the component detection image and the component standard image, and respectively identifying a detection image component in the component detection image and a standard image component in the component standard image; and matching the detection graph component with the standard graph component in combination with a Hungary algorithm to obtain a target matching result. According to the component registration method disclosed by the invention, registration of the components in the component detection image and the component standard image is carried out by using the Hungary algorithm, the accuracy of component registration is improved, and the labor cost is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of train detection, and particularly to a component registration method, device, equipment, storage medium and product. Background Art

[0002] Any minor or subtle fault in a bullet train running at high speed may lead to a major accident. The current TEDS (Train Operation Fault Image Detection System) generally uses image comparison and recognition to achieve the functions of fault detection and automatic alarm. When performing fault detection, the pictures collected by the TEDS device need to be registered with the standard pictures so that the components in the collected pictures are aligned with the components in the standard pictures one by one before the subsequent fault detection work can be carried out.

[0003] Existing component registration methods often require manual annotation and manual review, so the accuracy of the method is relatively low, and a large amount of manpower is consumed, making it difficult to ensure the quality and efficiency of car inspection operations. Summary of the Invention

[0004] The present invention provides a component registration method, device, equipment, storage medium and product to improve the accuracy of component registration.

[0005] According to one aspect of the present invention, a component registration method is provided, including:

[0006] Obtain a component detection image and a component standard image to be registered;

[0007] Perform object detection on the component detection image and the component standard image, and respectively identify the detected components in the component detection image and the standard components in the component standard image;

[0008] Combine the Hungarian algorithm to match the detected components and the standard components to obtain a target matching result.

[0009] Further, combining the Hungarian algorithm to match the detected components and the standard components includes:

[0010] For each detected component, determine the first alternative target component of the detected component among the standard components;

[0011] Combine the Hungarian algorithm to perform one-to-one matching on each detected component and the corresponding first alternative target component to obtain a preliminary matching result;

[0012] According to the preliminary matching result, determine the second alternative target component of each detected component among the standard components;

[0013] In combination with the Hungarian algorithm, a one-to-one match is performed again between each of the detection image components and the corresponding second candidate target components to determine a one-to-one correspondence between the detection image components and the standard image components.

[0014] Further, according to the preliminary matching result, determining a second candidate target component of each of the detection image components in the standard image components includes:

[0015] For each of the detection image components, determining the distance between the detection image component and the matched standard image component according to the preliminary matching result, and if the distance is greater than a first threshold, canceling the matching relationship between the detection image component and the matched standard image component;

[0016] Adjusting the position of each of the detection image components according to the distance between each of the detection image components and the matching standard image components;

[0017] According to the distance between the detection image component and the standard image component after adjustment, a second candidate target component of each detection image component is determined in the standard image component.

[0018] Furthermore, after obtaining the target matching result, it also includes:

[0019] The position of the missing component in the component detection image is determined according to the target matching result, and the component is supplemented in the component detection image according to the position of the missing component.

[0020] Furthermore, before matching the detection image component with the standard image component in combination with the Hungarian algorithm, the method further includes:

[0021] Component position correction is performed on the component detection image.

[0022] Further, performing component position correction on the component detection image includes:

[0023] Determine respectively a center point of a first space body of the component inspection image and a center point of a second space body of the component standard image;

[0024] The position of the inspection image component in the component inspection image is corrected according to the relative position deviation between the center point of the first spatial body and the center point of the second spatial body.

[0025] According to another aspect of the present invention, there is provided a component registration device, comprising:

[0026] A component inspection image and component standard image acquisition module is used to acquire a component inspection image and a component standard image to be registered;

[0027] A detection image component and standard image component recognition module, used to perform target detection on the component detection image and the component standard image, and respectively recognize the detection image component in the component detection image and the standard image component in the component standard image;

[0028] The detection image component and standard image component matching module is used to match the detection image component with the standard image component in combination with the Hungarian algorithm to obtain a target matching result.

[0029] Optionally, the detection image component and standard image component matching module is further used for:

[0030] For each of the inspection image components, determining a first candidate target component of the inspection image component in the standard image components;

[0031] Using the Hungarian algorithm, one-to-one matching is performed between each of the detection image components and the corresponding first candidate target component to obtain a preliminary matching result;

[0032] Determining, according to the preliminary matching result, a second candidate target component for each of the detection image components in the standard image components;

[0033] In combination with the Hungarian algorithm, a one-to-one match is performed again between each of the detection image components and the corresponding second candidate target components to determine a one-to-one correspondence between the detection image components and the standard image components.

[0034] Optionally, the detection image component and standard image component matching module is further used for:

[0035] For each of the detection image components, determining the distance between the detection image component and the matched standard image component according to the preliminary matching result, and if the distance is greater than a first threshold, canceling the matching relationship between the detection image component and the matched standard image component;

[0036] Adjusting the position of each of the detection image components according to the distance between each of the detection image components and the matching standard image components;

[0037] According to the distance between the detection image component and the standard image component after adjustment, a second candidate target component of each detection image component is determined in the standard image component.

[0038] Optionally, the device further comprises a missing component supplement module, which is used to determine the position of the missing component in the component detection image according to the target matching result, and supplement the component in the component detection image according to the missing component position.

[0039] Optionally, the device further comprises a component position correction module, which is used to perform component position correction on the component detection image.

[0040] Optionally, the component position correction module is further configured to:

[0041] Determine the center point of the first space body of the component detection diagram and the center point of the second space body of the component standard diagram respectively;

[0042] Perform position correction on the detected diagram components in the component detection diagram according to the relative position deviation between the center point of the first space body and the center point of the second space body.

[0043] According to another aspect of the present invention, there is provided an electronic device, which includes:

[0044] At least one processor; and

[0045] A memory communicatively connected to the at least one processor; wherein,

[0046] The memory stores a computer program executable by the at least one processor, and when the computer program is executed by the at least one processor, the at least one processor can execute the component registration method according to any embodiment of the present invention.

[0047] According to another aspect of the present invention, there is provided a computer-readable storage medium, which stores computer instructions, and when the computer instructions are executed by a processor, the component registration method according to any embodiment of the present invention is realized.

[0048] According to another aspect of the present invention, there is provided a computer program product, which includes computer programs / instructions, and when the computer programs / instructions are executed by a processor, the steps of the component registration method according to any embodiment of the present invention are realized.

[0049] For the component registration method disclosed by the present invention, first, a component detection diagram and a component standard diagram to be registered are obtained; then, target detection is performed on the component detection diagram and the component standard diagram, and the detected diagram components in the component detection diagram and the standard diagram components in the component standard diagram are respectively identified; finally, the detected diagram components and the standard diagram components are matched by combining the Hungarian algorithm to obtain a target matching result. For the component registration method disclosed by the present invention, the Hungarian algorithm is used for registering the components in the component detection diagram and the component standard diagram, which improves the accuracy of component registration and reduces the labor cost.

[0050] It should be understood that the content described in this part is not intended to identify the key or important features of the embodiments of the present invention, nor is it used to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. Description of the Drawings

[0051] To more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the accompanying drawings required for the description of the embodiments. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other accompanying drawings can be obtained based on these drawings.

[0052] Figure 1 is a flowchart of a component registration method provided in Embodiment 1 of the present invention;

[0053] Figure 2 is a flowchart of a component registration method provided in Embodiment 2 of the present invention;

[0054] Figure 3 is a schematic structural diagram of a component registration device provided in Embodiment 3 of the present invention;

[0055] Figure 4 is a schematic structural diagram of an electronic device for implementing the component registration method of Embodiment 4 of the present invention. Detailed Embodiments

[0056] To enable those skilled in the art to better understand the solutions of the present invention, the following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0057] It should be noted that the terms "first", "second", etc. in the description and claims of the present invention and the above accompanying drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged under appropriate circumstances so that the embodiments of the present invention described herein can be implemented in an order different from those illustrated or described herein. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products, or devices.

[0058] Embodiment 1

[0059] Figure 1The following is a flowchart of a component registration method provided by Embodiment 1 of the present invention. This embodiment is applicable to the situation of registering components in a detection image with components in a standard image. This method can be executed by a component registration device, which can be implemented in the form of hardware and / or software, and the component registration device can be configured in an electronic device. As Figure 1 shown, the method includes:

[0060] S110. Obtain a component detection image and a component standard image to be registered.

[0061] Among them, the component detection image is a physical image containing train components obtained by photographing the train underbody and the train side, and the component standard image is a standard format image file containing each component of the train underbody and the train side.

[0062] In this embodiment, the purpose of registering the component detection image and the component standard image is to make the same components included in the component detection image and the component standard image correspond one by one.

[0063] S120. Perform object detection on the component detection image and the component standard image, and respectively identify the detected components in the component detection image and the standard components in the component standard image.

[0064] Among them, the detected components and the standard components are respectively component information identified from the component detection image and the component standard image.

[0065] In this embodiment, the way to identify the detected components and the standard components can be to perform object detection on the component detection image and the component standard image. In this way, the positions of each component can be determined from the image and the corresponding types can be identified.

[0066] Preferably, an object detection algorithm can be applied to identify the detected components and the standard components. Among them, the object detection algorithm is an important issue in the field of computer vision, aiming to accurately find the positions of objects in a given image and identify them. YOLO (You Only Look Once) is an object detection algorithm based on deep learning. Its core idea is to transform the object detection problem into a regression problem and achieve end-to-end prediction through a single convolutional neural network (CNN), thus greatly improving the detection speed and efficiency. In this embodiment, the YOLO algorithm can be applied to identify the detected components and the standard components.

[0067] S130. Combine the Hungarian algorithm to match the detected components and the standard components to obtain a target matching result.

[0068] Among them, the Hungarian algorithm, that is, the algorithm for finding the maximum matching in graph theory, is mainly used to solve some problems related to bipartite graph matching.

[0069] In this embodiment, after identifying the detected parts in the part detection diagram and the standard parts in the part standard diagram, the Hungarian algorithm can be used to match the detected parts in the detection diagram with the standard parts in the standard diagram to obtain the correct corresponding relationship of the same parts among them.

[0070] Further, after obtaining the target matching result, it is also possible to: determine the positions of the missing parts in the part detection diagram according to the target matching result, and supplement the parts in the part detection diagram according to the positions of the missing parts.

[0071] In this embodiment, compared with the part standard diagram, the detected parts identified in the part detection diagram may be missing. For example, if the part standard diagram contains 8 parts, and only 7 parts are identified after performing target detection on the part detection diagram, then the 1 unrecognized part is the missing part in the part detection diagram.

[0072] Optionally, the method for determining the positions of the missing parts can be: according to the target matching result, regard the parts in the part standard diagram that are not successfully matched as the missing parts in the part detection diagram, then obtain the three successfully matched parts closest to the missing parts in the part standard diagram, calculate the relative position information between these three successfully matched parts and the missing part, and then determine the positions of the missing parts in the part detection diagram and supplement the missing parts in the part detection diagram according to the positions of the matched parts of these three successfully matched parts in the part detection diagram and the relative position information.

[0073] Further, before matching the detected parts in the detection diagram with the standard parts in the standard diagram by combining the Hungarian algorithm, it is also possible to: correct the positions of the parts in the part detection diagram.

[0074] In this embodiment, to improve the matching accuracy, before using the Hungarian algorithm to match the detected parts in the detection diagram with the standard parts in the standard diagram, the positions of the parts in the part detection diagram can be corrected first to make the parts in the part detection diagram closer to the parts in the part standard diagram in terms of position.

[0075] Optionally, the method for correcting the positions of the parts in the part detection diagram can be: respectively determine the center point of the first space body of the part detection diagram and the center point of the second space body of the part standard diagram; correct the positions of the detected parts in the part detection diagram according to the relative position deviation between the center point of the first space body and the center point of the second space body.

[0076] Specifically, based on all the detected components in the component detection diagram, the whole of all the detected components in the component detection diagram can be used as the first spatial body corresponding to the component detection diagram, and the center point of the first spatial body, that is, the center point of the first spatial body, can be determined. Similarly, the whole of all the standard components in the component standard diagram can be used as the second spatial body, and the center point of the second spatial body can be determined. The coordinates of the center point of the first spatial body and the center point of the second spatial body in the same coordinate system are calculated respectively, and the relative position deviation between the center point of the first spatial body and the center point of the second spatial body is determined according to the two coordinates. Then, each detected component in the component detection diagram is translated as a whole according to the relative position deviation.

[0077] The component registration method disclosed in the present invention first obtains a component detection diagram and a component standard diagram to be registered; then performs object detection on the component detection diagram and the component standard diagram, and respectively identifies the detected components in the component detection diagram and the standard components in the component standard diagram; finally, combines the Hungarian algorithm to match the detected components and the standard components to obtain the target matching result. The component registration method disclosed in the present invention uses the Hungarian algorithm to perform component registration between the component detection diagram and the component standard diagram, improves the accuracy of component registration, and reduces the labor cost.

[0078] Embodiment 2

[0079] Figure 2 It is a flowchart of a component registration method provided by Embodiment 2 of the present invention. This embodiment is a refinement of the above embodiment. As Figure 2 shown, the method includes:

[0080] S210. Obtain a component detection diagram and a component standard diagram to be registered.

[0081] Among them, the component detection diagram is a physical diagram containing train components obtained by photographing the train underbody and the train side, and the component standard diagram is a standard format image file containing each component of the train underbody and the train side.

[0082] In this embodiment, the purpose of registering the component detection diagram and the component standard diagram is to correspond one by one the same components contained in the component detection diagram and the component standard diagram.

[0083] S220. Perform object detection on the component detection diagram and the component standard diagram, and respectively identify the detected components in the component detection diagram and the standard components in the component standard diagram.

[0084] Among them, the detected components and the standard components are respectively component information identified from the component detection diagram and the component standard diagram.

[0085] In this embodiment, the method for identifying and detecting the component in the detection graph and the standard graph component can be to perform object detection on the component detection graph and the component standard graph. Through this method, the positions of each component can be determined from the image and the corresponding types can be identified.

[0086] Preferably, an object detection algorithm can be applied to identify the component in the detection graph and the standard graph component. Among them, the object detection algorithm is an important issue in the field of computer vision, aiming to accurately find the position of an object in a given image and identify it. YOLO (You Only Look Once) is an object detection algorithm based on deep learning. Its core idea is to transform the object detection problem into a regression problem and achieve end-to-end prediction through a single convolutional neural network (CNN), thereby greatly improving the detection speed and efficiency. In this embodiment, the YOLO algorithm can be applied to identify the component in the detection graph and the standard graph component.

[0087] S230. For each component in the detection graph, determine the first alternative target component of the component in the detection graph in the standard graph component.

[0088] Among them, for each component in the detection graph, the first alternative target component is the standard graph component in the component standard graph that may match the component in the detection graph.

[0089] In this embodiment, the matching between the component in the detection graph and the standard graph component can be achieved through two registrations. Before the first registration, each component in the detection graph can be screened in the standard graph component according to certain rules. After excluding the standard graph components that are impossible to match, the standard graph components that may match are used as the first alternative target components of the corresponding components in the detection graph, and then the Hungarian algorithm is used for matching.

[0090] Specifically, when determining the first alternative target component, the center point coordinates of each component in the detection graph and each standard graph component in the same coordinate system can be calculated respectively, and the target boxes corresponding to each component in the detection graph and each standard graph component can be determined. For each component in the detection graph, determine the relative distance between its center point coordinate and the center point coordinates of each standard graph component, including the distance dx on the x-axis and the distance dy on the y-axis, and calculate the IOU data between it and each standard graph component. Among them, IOU is the intersection area of the target boxes of two components divided by their union area. According to the preset value ranges of dx, dy, and IOU, the standard graph components whose dx, dy, and IOU values all belong to the corresponding value ranges are used as the first alternative target components of the corresponding components in the detection graph, and the remaining standard graph components that do not meet the corresponding value ranges do not participate in the registration of the component in the detection graph.

[0091] S240. Combine the Hungarian algorithm to perform one-to-one matching on each component in the detection graph and the corresponding first alternative target component to obtain a preliminary matching result.

[0092] In this embodiment, after respectively determining the first candidate target component corresponding to each detection image component, the Hungarian algorithm can be used to perform a first registration of the detection image component with the standard image component to obtain a one-to-one matching result between each detection image component and the corresponding first candidate target component, and use it as a preliminary matching result for a second registration.

[0093] S250: Determine a second candidate target component for each detection image component in the standard image components according to the preliminary matching result.

[0094] For each detection image component, the second candidate target component is a standard image component that is re-screened based on the preliminary matching result and that is likely to match the detection image component.

[0095] Optionally, the method for determining the second candidate target component of each detection image component in the standard image component based on the preliminary matching result may be: for each detection image component, determining the distance between the detection image component and the matched standard image component based on the preliminary matching result, if the distance is greater than a first threshold, releasing the matching relationship between the detection image component and the matched standard image component; adjusting the position of each detection image component according to the distance between each detection image component and the matched standard image component; determining the second candidate target component of each detection image component in the standard image component according to the distance between the detection image component and the standard image component after adjustment.

[0096] Specifically, before the second registration, you can first screen the preliminary matching results, calculate the distance between each detection image component and the matching standard image component, and if the distance is greater than the first threshold, the matching relationship between the detection image component and the matching standard image component is released. Then, according to the distance between each detection image component and the matching standard image component, calculate the median distance, including the median distance x_med on the x-axis and the median distance y_med on the y-axis, and adjust the position of each detection image component according to x_med and y_med. Finally, for each detection image component, according to the distance between each standard image component after adjustment, the distance between the x-axis and the y-axis, and the standard image component belonging to the corresponding numerical range is used as the second candidate target component of the corresponding detection image component, and the remaining standard image components that do not meet the corresponding value range do not participate in the registration of the detection image component.

[0097] S260, combining the Hungarian algorithm, again performing one-to-one matching between each detection image component and the corresponding second candidate target component, determining a one-to-one correspondence between the detection image component and the standard image component, and obtaining a target matching result.

[0098] In this embodiment, after determining the second alternative target components corresponding to each detected graph component respectively, the Hungarian algorithm can be used for the second registration of the detected graph components and the standard graph components, to obtain a one-to-one correspondence between each detected graph component and the corresponding second alternative target component, and use it as the target matching result.

[0099] The component registration method provided by the embodiment of the present invention first obtains a component detection graph and a component standard graph to be registered, then performs target detection on the component detection graph and the component standard graph, respectively identifies the detected graph components in the component detection graph and the standard graph components in the component standard graph, and then for each detected graph component, determines the first alternative target component of the detected graph component in the standard graph components, and then combines the Hungarian algorithm to perform one-to-one matching on each detected graph component and the corresponding first alternative target component to obtain a preliminary matching result, and then according to the preliminary matching result, determines the second alternative target component of each detected graph component in the standard graph components, and finally combines the Hungarian algorithm to perform one-to-one matching on each detected graph component and the corresponding second alternative target component again to determine the one-to-one correspondence between the detected graph components and the standard graph components, and obtain the target matching result. The component registration method provided by the embodiment of the present invention uses the Hungarian algorithm for the registration of components in the component detection graph and the component standard graph, and adopts the method of two registrations in the registration, which further improves the accuracy of component registration and reduces the labor cost.

[0100] Embodiment III

[0101] Figure 3 FIG. is a schematic structural diagram of a component registration device provided by Embodiment III of the present invention, as Figure 3 shown, the device includes: a component detection graph and a component standard graph acquisition module 310, a detected graph component and a standard graph component recognition module 320, and a detected graph component and a standard graph component matching module 330.

[0102] The component detection graph and the component standard graph acquisition module 310 is used to obtain a component detection graph and a component standard graph to be registered.

[0103] The detected graph component and the standard graph component recognition module 320 is used to perform target detection on the component detection graph and the component standard graph, and respectively identify the detected graph components in the component detection graph and the standard graph components in the component standard graph.

[0104] The detected graph component and the standard graph component matching module 330 is used to combine the Hungarian algorithm to match the detected graph components and the standard graph components to obtain the target matching result.

[0105] Optionally, the detected graph component and the standard graph component matching module 330 is further used for:

[0106] For each detection image component, a first candidate target component of the detection image component is determined in the standard image components; each detection image component is matched with the corresponding first candidate target component one-to-one in combination with the Hungarian algorithm to obtain a preliminary matching result; based on the preliminary matching result, a second candidate target component of each detection image component is determined in the standard image components; each detection image component is matched with the corresponding second candidate target component one-to-one again in combination with the Hungarian algorithm to determine a one-to-one correspondence between the detection image component and the standard image component.

[0107] Optionally, the detection image component and standard image component matching module 330 is further used for:

[0108] For each detection image component, the distance between the detection image component and the matched standard image component is determined according to the preliminary matching result. If the distance is greater than a first threshold, the matching relationship between the detection image component and the matched standard image component is released; the position of each detection image component is adjusted according to the distance between each detection image component and the matched standard image component; and the second candidate target component of each detection image component is determined in the standard image component according to the distance between the detection image component and the standard image component after adjustment.

[0109] Optionally, the device further comprises a missing component supplement module, which is used to determine the position of the missing component in the component detection image according to the target matching result, and to supplement the component in the component detection image according to the position of the missing component.

[0110] Optionally, the device further comprises a component position correction module for performing component position correction on the component detection image.

[0111] Optionally, the component position correction module is also used for:

[0112] The center point of the first space body of the component inspection image and the center point of the second space body of the component standard image are determined respectively; and the position of the inspection image component in the component inspection image is corrected according to the relative position deviation between the center point of the first space body and the center point of the second space body.

[0113] The component registration device provided in the embodiment of the present invention can execute the component registration method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0114] Embodiment 4

[0115] Figure 4The structural schematic diagram of an electronic device 10 that can be used to implement the embodiments of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or claimed herein.

[0116] As Figure 4 shown, the electronic device 10 includes at least one processor 11, and a memory communicatively connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc. The memory stores a computer program executable by the at least one processor. The processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 into the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0117] Multiple components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a magnetic disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0118] The processor 11 can be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the processor 11 include but are not limited to a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as the component registration method.

[0119] In some embodiments, the component registration method may be implemented as a computer program tangibly embodied in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed onto the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the component registration described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to execute the component registration method by any other suitable means (e.g., by means of firmware).

[0120] Various embodiments of the systems and techniques described above in this document can be implemented in digital electronic circuitry, integrated circuit systems, field programmable gate arrays (FPGA), application specific integrated circuits (ASIC), application specific standard products (ASSP), systems on a chip (SOC), complex programmable logic devices (CPLD), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special-purpose or general-purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit the data and instructions to the storage system, the at least one input device, and the at least one output device.

[0121] The computer program for implementing the method of the present invention can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when the computer program is executed by the processor, the functions / operations specified in the flowchart and / or block diagram are implemented. The computer program can be executed entirely on the machine, partially on the machine, as a stand-alone software package partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0122] In the context of the present invention, a computer-readable storage medium can be a tangible medium that can contain or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. The computer-readable storage medium can include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. Alternatively, the computer-readable storage medium can be a machine-readable signal medium. More specific examples of the machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0123] In order to provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the electronic device. Other kinds of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0124] The systems and techniques described herein can be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer having a graphical user interface or a web browser through which the user can interact with an implementation of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local area network (LAN), wide area network (WAN), blockchain network, and the Internet.

[0125] A computing system may include a client and a server. The client and the server are generally far from each other and usually interact via a communication network. The client-server relationship is created by computer programs running on respective computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or a cloud host, which is a host product in the cloud computing service system, solving the defects of difficult management and weak business scalability existing in traditional physical hosts and VPS services.

[0126] It should be understood that various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in the present invention can be executed in parallel, sequentially, or in a different order, as long as the desired results of the technical solution of the present invention can be achieved, and no limitations are imposed herein.

[0127] The above specific embodiments do not constitute a limitation on the protection scope of the present invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A component registration method, characterized in that, include: Obtaining a component inspection image and a component standard image to be registered; Performing target detection on the component detection image and the component standard image, and respectively identifying the detection image components in the component detection image and the standard image components in the component standard image; The detection image component is matched with the standard image component in combination with the Hungarian algorithm to obtain a target matching result.

2. The method according to claim 1, wherein The detection image component is matched with the standard image component in combination with the Hungarian algorithm, including: For each of the inspection image components, determining a first candidate target component of the inspection image component in the standard image components; Using the Hungarian algorithm, one-to-one matching is performed between each of the detection image components and the corresponding first candidate target component to obtain a preliminary matching result; Determining, according to the preliminary matching result, a second candidate target component for each of the detection image components in the standard image components; In combination with the Hungarian algorithm, a one-to-one match is performed again between each of the detection image components and the corresponding second candidate target components to determine a one-to-one correspondence between the detection image components and the standard image components.

3. The method according to claim 2, wherein Determining a second candidate target component for each of the detection image components in the standard image components according to the preliminary matching result includes: For each of the detection image components, determine the distance between the detection image component and the matched standard image component according to the preliminary matching result, and if the distance is greater than a first threshold, cancel the matching relationship between the detection image component and the matched standard image component; Adjusting the position of each of the detection image components according to the distance between each of the detection image components and the matching standard image components; According to the distance between the detection image component and the standard image component after adjustment, a second candidate target component of each detection image component is determined in the standard image component.

4. The method according to claim 1, wherein After obtaining the target matching result, it also includes: The position of the missing component in the component detection image is determined according to the target matching result, and the component is supplemented in the component detection image according to the position of the missing component.

5. The method according to claim 1, characterized in that, Before matching the detection image component with the standard image component in combination with the Hungarian algorithm, the method further includes: Component position correction is performed on the component detection image.

6. The method according to claim 5, characterized in that, Performing component position correction on the component detection image includes: Determine respectively a center point of a first space body of the component inspection image and a center point of a second space body of the component standard image; The position of the inspection image component in the component inspection image is corrected according to the relative position deviation between the center point of the first spatial body and the center point of the second spatial body.

7. A component registration device, characterized in that, include: A component inspection image and component standard image acquisition module is used to acquire a component inspection image and a component standard image to be registered; A detection image component and standard image component recognition module, used to perform target detection on the component detection image and the component standard image, and respectively recognize the detection image components in the component detection image and the standard image components in the component standard image; The detection image component and standard image component matching module is used to match the detection image component with the standard image component in combination with the Hungarian algorithm to obtain a target matching result.

8. An electronic device, characterized in that, The electronic device comprises: at least one processor; and A memory communicatively connected to the at least one processor; wherein, the memory stores a computer program executable by the at least one processor, and when the computer program is executed by the at least one processor, the at least one processor is enabled to execute the component registration method according to any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for implementing the component registration method according to any one of claims 1-6 when the computer instructions are executed by a processor.

10. A computer program product, comprising a computer program / instructions, characterized in that, When the computer program / instructions are executed by a processor, the steps of the component registration method according to any one of claims 1-6 are implemented.

Images