Wheel hub mark detection method, electronic device and storage medium

Abstract

The present invention provides a wheel hub mark detection method, comprising: photographing an image of the wheel hub surface by a camera device; processing the image photographed by the camera device to identify the characteristic contour of the wheel spoke on the wheel hub; calculating the angle between the center of the wheel hub and the line connecting the center of the characteristic contour; determining multiple rotation angles of the wheel hub according to the angle between the center of the wheel hub and the line connecting the center of the characteristic contour; controlling the wheel hub to rotate sequentially according to the multiple rotation angles so that the mark is sequentially moved into the scanning range of the 3D laser scanning device; when the wheel hub rotates by one rotation angle, controlling the 3D laser scanning device to move and scan the mark that is rotated and moved into the current scanning range; and identifying the mark scanned by the 3D laser scanning device. The present invention also provides an electronic device and a storage medium. The present invention improves the automation and accuracy of wheel hub mark recognition.

Description

Technical Field

[0001] The present invention relates to the technical field of appearance detection, and in particular to a wheel hub mark detection method, an electronic device and a storage medium. Background Art

[0002] In order to improve production automation and intelligence, characters and logos are often engraved on some castings. For example, vehicle wheels are engraved with logos or characters such as manufacturer, specifications, mold number, customer part number, etc. In order to ensure the orderly and correct production process, it is usually necessary to identify the characters or logos on the wheel. At present, the commonly used method of identifying characters and logos is manual recognition. However, manual recognition increases labor costs and has large errors, which leads to reduced accuracy of character and logo recognition.

[0003] Chinese patent application No. 201810003270.6 discloses a method for identifying automobile tire logos. However, this method cannot determine the logo position in advance and requires a laser scanner to blindly scan the entire tire surface. On the one hand, the scanning time is long, and on the other hand, the use of a laser scanner to blindly scan the entire surface makes subsequent logo extraction more difficult. Moreover, the patent application does not provide any specific solution for logo extraction. Summary of the invention

[0004] In view of this, it is necessary to provide a wheel hub logo detection method, an electronic device and a storage medium, and use a camera device and a 3D laser scanning device to automatically identify the wheel hub logo.

[0005] A first aspect of the present invention provides a wheel hub mark detection method, the method comprising:

[0006] Taking an image of a hub surface by a camera device, wherein the hub surface includes a plurality of marks;

[0007] Processing the image captured by the camera device to identify the characteristic contour of the spoke on the hub;

[0008] Calculate the angle between the center of the hub and the line connecting the center of the characteristic profile;

[0009] Determining a plurality of rotation angles of the hub according to an angle between a center of the hub and a line connecting a center of the characteristic profile;

[0010] Controlling the wheel hub to rotate sequentially according to the multiple rotation angles, so that the marks are moved into the scanning range of the 3D laser scanning device sequentially;

[0011] When the wheel hub rotates by a certain angle, the 3D laser scanning device is controlled to scan the mark that is rotated and moved into the current scanning range; and

[0012] The mark scanned by the 3D laser scanning device is identified.

[0013] Preferably, the identifying the mark scanned by the 3D laser scanning device comprises:

[0014] Determining whether the mark meets the preset testing standards; and

[0015] When the identification meets the preset detection standard, it is determined that the wheel hub passes the detection.

[0016] Preferably, the preset detection standard includes that each mark is the same as the corresponding preset mark, each mark has no defects, and the order of the marks conforms to the preset order, and the determination of whether the marks conform to the preset detection standard includes:

[0017] Determine whether the identifier is the same as the corresponding preset identifier, determine whether the identifier has defects, and determine whether the order of the identifiers conforms to the preset order.

[0018] Preferably, the determining whether the identifier is the same as the corresponding preset identifier comprises:

[0019] Comparing the identifier with a corresponding preset identifier in an identifier database to determine whether the identifier is the same as the corresponding preset identifier;

[0020] The determining whether the mark has a defect comprises:

[0021] Whether the multiple logos have defects is determined through deep learning visual matching or point cloud matching.

[0022] Preferably, the method further comprises:

[0023] When it is determined that the mark is different from the corresponding preset mark, and / or it is determined that the mark has a defect, and / or it is determined that the order of the marks does not conform to the preset order, it is determined that the wheel hub has failed the inspection.

[0024] Preferably, the method further comprises:

[0025] When it is determined that the font of any logo is less than a preset percentage when comparing the logo with the corresponding preset logo in the logo database, the font of the logo is added to the logo database to update the logo database;

[0026] When, during defect detection of any marked 3D image using a convolutional neural network model, it is determined that the degree of similarity between the marked 3D image defect features and the 3D image defect features in the convolutional neural network model is less than the preset percentage, the convolutional neural network model is continued to be trained according to the marked 3D image defect features to update the convolutional neural network model.

[0027] Preferably, the calculation of the angle between the center of the hub and the line connecting the center of the characteristic profile comprises:

[0028] Draw a plurality of connecting lines between the center of the wheel hub and the center of the characteristic contour; and

[0029] The plurality of connecting lines are identified by an edge extraction algorithm, and the angles between the plurality of connecting lines are calculated.

[0030] Preferably, when the wheel hub rotates by a rotation angle, controlling the 3D laser scanning device to move on the wheel hub to scan the mark that is rotated and moved into the current scanning range includes:

[0031] When the wheel hub rotates by a rotation angle, the driving device controls the 3D laser scanning device to move linearly along a first direction of the wheel hub to scan a mark on a radial angle of the wheel hub within a current scanning range; and

[0032] When the wheel hub rotates to a next rotation angle, the driving device controls the 3D laser scanning device to move linearly along a second direction of the wheel hub opposite to the first direction to scan the mark on the next radial angle of the wheel hub.

[0033] A second aspect of the present invention provides an electronic device, comprising:

[0034] Processor; and

[0035] A memory, wherein a plurality of program modules are stored in the memory, and the plurality of program modules are loaded by the processor and execute the above-mentioned wheel hub mark detection method.

[0036] A third aspect of the present invention provides a storage medium having at least one computer instruction stored thereon, wherein the instruction is loaded by a processor to execute the above-mentioned wheel hub mark detection method.

[0037] The above-mentioned wheel hub mark detection method, electronic device and storage medium can identify the angle between the center of the wheel hub and the center line of the spoke characteristic contour through a camera device, control the rotation of the wheel hub according to the identified angle, and perform motion scanning and identification of the marks at different radial angles of the wheel hub through a scanning device, thereby reducing labor costs and improving the automation and accuracy of wheel hub mark identification. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0039] Figure 1 It is a schematic diagram of an electronic device provided by a preferred embodiment of the present invention.

[0040] Figure 2 It is a flow chart of a wheel hub mark detection method provided in a preferred embodiment of the present invention.

[0041] Figure 3 It is a schematic diagram of a camera device provided in a preferred embodiment of the present invention capturing an image of a wheel hub surface.

[0042] Figure 4a-4c It is a schematic diagram of the processing process of the hub surface image provided by the preferred embodiment of the present invention.

[0043] Figure 5 It is a 3D image of a logo scanned by a 3D laser scanning device provided in a preferred embodiment of the present invention.

[0044] Figure 6 It is a schematic diagram of the identification database provided by the preferred embodiment of the present invention.

[0045] Figure 7 It is a schematic diagram of a convolutional neural network model provided by a preferred embodiment of the present invention.

[0046] Figure 8 It is a schematic diagram of the wheel hub mark detection process provided by the preferred embodiment of the present invention.

[0047] Fig. 9 It is a flow chart of detecting a designated wheel hub identification provided by a preferred embodiment of the present invention.

[0048] Fig.10 It is a schematic diagram of the structure of an electronic device provided by a preferred embodiment of the present invention.

[0049] Main component symbols

[0050] Electronic Devices 1 processor 10 Memory 20 Identification database 21 Computer Programs 30 Camera device 40 Bracket 41,74 light source 50 Rotating platform 60 3D laser scanning device 70 Drive device 71 Axis of motion 72 Moving Path 73 Display 80 Wheels 2 Spoke 201

[0051] The following specific implementation manner will further illustrate the present invention in conjunction with the above-mentioned drawings. DETAILED DESCRIPTION

[0052] In order to more clearly understand the above-mentioned purpose, features and advantages of the present invention, the present invention is described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that the embodiments of the present application and the features in the embodiments can be combined with each other without conflict.

[0053] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. The embodiments described 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 ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0054] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art of the present invention. The terms used in the specification of the present invention herein are only for the purpose of describing specific embodiments and are not intended to limit the present invention.

[0055] See also Figure 1 , which is a schematic diagram of the application environment architecture of the wheel hub mark detection method provided in a preferred embodiment of the present invention.

[0056] The wheel mark detection method of the present invention is applied in an electronic device 1. The electronic device 1 may be an electronic device installed with a wheel mark detection program, such as a personal computer.

[0057] The electronic device 1 may be provided with a hub 2, the hub 2 comprising a plurality of spokes 201, the plurality of spokes 201 being arranged along the radial angle of the hub 2. Logos may be engraved on all or part of the spokes 201. The logos may be any one of Chinese characters, letters, symbols, and graphics, or any combination of several of them.

[0058] See also Figure 2 FIG. 1 is a flow chart of a wheel hub mark detection method provided by a preferred embodiment of the present invention. According to different requirements, the order of the steps in the flow chart can be changed, and some steps can be omitted.

[0059] S201 , capturing an image of the hub surface by using the camera device 40 .

[0060] In this embodiment, the hub surface includes a plurality of marks, which are respectively engraved on the spokes 201. Figure 3As shown, the camera device 40 and the light source 50 are installed on a bracket 41. The camera device 40 is directly facing the hub surface and is coaxial with the hub center. The hub surface is the reverse side of the hub 2. S201 specifically includes: when the hub 2 is placed within the shooting range of the camera device 40, the light source 50 is turned on, and the image of the hub surface is captured by the camera device 40.

[0061] S202 , processing the image captured by the camera device 40 to identify the characteristic contour of the spoke 201 .

[0062] In this embodiment, S202 specifically includes: Figure 4a As shown, the image captured by the camera device 40 is grayscaled and binarized. Figure 4b As shown, the characteristic contour of the spoke 201 in the image is identified by feature extraction. The characteristic contour of the spoke 201 is a rectangular frame, which is used to indicate the approximate position of the mark on the spoke 201.

[0063] S203, calculating the angle between the center of the hub and the line connecting the center of the characteristic profile.

[0064] In this implementation, see Figure 4c As shown, S203 specifically includes: determining the center of the hub 2 in the image captured by the camera device 40, and determining the center of the characteristic contour of the spoke 201, that is, the center of the rectangular frame corresponding to the characteristic contour. S203 further includes: drawing multiple lines between the center of the hub and the centers of multiple characteristic contours, identifying the multiple lines through an edge extraction algorithm, and calculating the angles between the multiple lines. In this embodiment, the edge extraction algorithm can be a Huffman transform algorithm, an edge detection algorithm, a Scale-Invariant Feature Transform (SIFT) algorithm, etc.

[0065] S204, determining a plurality of rotation angles of the hub 2 according to the angle between the hub center and the line connecting the center of the characteristic profile.

[0066] In this embodiment, S204 specifically includes: determining that any spoke 201 is the spoke 201 scanned first by the 3D laser scanning device 70, and then converting the multiple angles between the center of the hub and the characteristic contour center line of the spoke 201 into the multiple rotation angles arranged in sequence in a clockwise or counterclockwise order according to the spoke 201 scanned first. For example, assuming that the order is clockwise, the angle between the center of the hub and the characteristic contour center line of the spoke 201 scanned first and the angle between the center of the hub and the characteristic contour center line of the next spoke 201 in the clockwise direction is 15 degrees, and the angle between the center of the hub and the characteristic contour center line of the next spoke 201 in the clockwise direction and the angle between the center of the hub and the characteristic contour center line of the next spoke 201 in the clockwise direction is 18 degrees, then the multiple rotation angles are 15 degrees, 18 degrees, etc.

[0067] S205 , controlling the wheel hub 2 to rotate sequentially according to the multiple rotation angles, so that the marks are moved into the scanning range of the 3D laser scanning device 70 sequentially.

[0068] In this embodiment, when the wheel hub 2 is placed on the rotating platform 60, the position of the wheel hub 2 is adjusted by the rotating platform 60 until the spoke 201 scanned first determined in S204 is within the scanning range of the 3D laser scanning device 70, and then the wheel hub 2 is controlled to rotate in sequence according to the multiple rotation angles, so that the marks on the spokes 201 are moved into the scanning range of the 3D laser scanning device 70 in sequence. In this embodiment, the scanning range of the 3D laser scanning device 70 is a rectangular range.

[0069] In this embodiment, the moving direction of the 3D laser scanning device 70, that is, the moving axis 72 (such as Figure 1 The angle between the longitudinal axis of the coordinate system corresponding to the image captured by the camera device 40 is such that each time the wheel hub 2 rotates by a certain angle, the mark on the wheel hub 2 is ensured to be within the scanning range of the 3D laser scanning device 70.

[0070] S206, when the wheel hub 2 rotates by a certain angle, the 3D laser scanning device 70 is controlled to scan the mark that is rotated and moved into the current scanning range.

[0071] Specifically, when the wheel hub 2 rotates by a rotation angle, the driving device 71 controls the 3D laser scanning device 70 to move along a first direction of the wheel hub (such as Figure 1The 3D laser scanning device 70 moves in a straight line (in the direction of the arrow at the top of the moving path 73) to scan the mark on the hub 2 at a radial angle within the current scanning range. When the hub 2 rotates to the next rotation angle, the driving device 71 controls the 3D laser scanning device 70 to move in a second direction (such as the direction of the arrow at the top of the moving path 73) of the hub 2. Figure 1 The 3D laser scanning device 70 moves in a straight line (in the direction of the arrow in the middle of the moving path 73) to scan the mark on the next radial angle of the hub.

[0072] like Figure 1 As shown, the motion axis 72 is mounted on the bracket 74. Preferably, in this embodiment, when the hub 2 rotates by a rotation angle, the 3D laser scanning device 70 is controlled to move along the radial direction of the hub to scan the mark that is rotated and moved into the current scanning range. Specifically, the spoke 201 is located at a radial angle of the hub 2. When the hub 2 rotates by a rotation angle, the 3D laser scanning device 70 is located directly above the spoke 201 of the hub 2, and the motion axis of the 3D laser scanning device 70 is parallel to the spoke 201. The 3D laser scanning device 70 is controlled by the driving device 71 to move along the motion axis 72, that is, to move linearly along the first radial direction of the hub, and at the same time, a line laser is emitted to scan a radial angle of the hub 2 within the current scanning range, that is, the mark on the spoke 201. When the wheel hub 2 rotates to the next rotation angle, the driving device 71 controls the 3D laser scanning device 70 to move in the opposite direction along the moving axis 72, that is, to move in a straight line along the second direction of the wheel hub radial direction opposite to the first direction, and at the same time emits a line laser to scan the next radial angle of the wheel hub 2, that is, the mark on the next spoke 201.

[0073] Specifically, in the initial state, the scanning starting point of the line laser of the 3D laser scanning device 70 is the center of the hub 2. When the spoke 201 to be scanned first is within the scanning range of the 3D laser scanning device 70, the 3D laser scanning device 70 emits a line laser from the center of the hub 2 to the end point of the spoke 201 away from the center of the hub to scan the mark on the spoke 201. When the line laser emitted by the 3D laser scanning device 70 reaches the end point of the spoke 201 where the mark is located away from the center of the hub, and the hub 2 is controlled to rotate by a first rotation angle, the next spoke 201 enters the scanning range of the 3D laser scanning device 70. At this time, the scanning starting point of the line laser of the 3D laser scanning device 70 is the end point of the spoke 201 where the next mark is located away from the center of the hub, and the 3D laser scanning device 70 emits a line laser from the end point of the spoke 201 where the next mark is located away from the center of the hub to the center of the hub 2 to scan the next mark. When the line laser emitted by the 3D laser scanning device 70 reaches the center of the wheel hub, the wheel hub 2 is controlled to rotate a second rotation angle, and the above process is repeated until the multiple rotation angles are completed, and the 3D laser scanning device 70 completes scanning the mark on the wheel hub 2.

[0074] It can be understood that in other embodiments, when the hub 2 rotates through an angle, the first direction and the second direction of movement of the 3D laser scanning device 70 when scanning the mark rotated into the current scanning range can also be at a certain angle to the radial direction of the hub, thereby ensuring that the radial angle of the hub 2, that is, the spoke 201 is within the scanning range of the 3D laser scanning device 70.

[0075] S207, identifying the mark scanned by the 3D laser scanning device 70.

[0076] See also Figure 5 As shown, it is a 3D image of the mark scanned by the 3D laser scanning device 70. In this embodiment, the mark scanned by the 3D laser scanning device 70 is identified to determine whether the mark meets the preset detection standard. In this embodiment, the preset detection standard includes that the mark is the same as the corresponding preset mark, the mark does not have defects, and the order of the marks meets the preset order. That is, the mark scanned by the 3D laser scanning device 70 is identified to determine whether the mark is the same as the corresponding preset mark, determine whether the mark has defects, and determine whether the order of the marks meets the preset order.

[0077] Specifically, the logo is compared with the corresponding preset logo in the logo database 21 to determine whether the logo is the same as the corresponding preset logo, and whether the logo has defects is determined through deep learning visual matching and / or point cloud matching, and whether the order of the logos scanned by the 3D laser scanning device 70 conforms to the preset order.

[0078] See also Figure 6 As shown, in this embodiment, the identification database 21 includes a plurality of preset identifications arranged in the preset order. The plurality of preset identifications are generated by abstracting, refining and digitalizing the known correct identifications on the wheel hub, and represent the fonts of the correct identifications. It is determined whether the identification database 21 contains a preset identification with the same font as the identification scanned by the 3D laser scanning device 70. When it is determined that the identification database 21 contains a preset identification with the same font as the identification scanned by the 3D laser scanning device 70, it is determined that the identification is the same as the corresponding preset identification. When it is determined that the identification database 21 does not contain a preset identification with the same font as the identification scanned by the 3D laser scanning device 70, the identification is re-scanned by the 3D laser scanning device 70, and then it is determined whether the identification database 21 contains a preset identification with the same font as the identification re-scanned by the 3D laser scanning device 70. When the fonts of the identification scanned by the 3D laser scanning device 70 multiple times are all different from the preset identification in the identification database 21, it is determined that the identification is different from the corresponding preset identification. In this embodiment, the multiple times are three times.

[0079] In this embodiment, the deep learning visual matching is implemented through a pre-trained convolutional neural network model. Figure 7 As shown, the convolutional neural network model includes an input layer, a first convolutional layer, a first downsampling layer, a second convolutional layer, a second downsampling layer, a fully connected layer and an output layer. Among them, the input layer is the 3D logo image scanned by the 3D laser scanning device 70, and the output layer includes a fully connected layer and a softmax layer. The input of the first convolutional layer is connected to the input layer, and the output of the first convolutional layer is connected to the input of the first downsampling layer; the output of the first downsampling layer is connected to the input of the second convolutional layer; the output of the second convolutional layer is connected to the input of the second downsampling layer; the output of the second downsampling layer is connected to the input of the output layer through the fully connected layer. The input 3D logo image is automatically iterated and converged through the convolutional neural network model to determine whether the logo has defects and obtain defect features.

[0080] In other embodiments, the 3D laser scanning device 70 can scan the obtained two-dimensional image and point cloud data of the logo. Visual recognition of the two-dimensional image of the logo is performed through a pre-trained convolutional neural network model to determine whether the two-dimensional image of the logo has defects, and the point cloud data is matched with a preset point cloud model through an iterative closest point algorithm (Iterative Closest Point, ICP) to determine whether the point cloud data of the logo has defects. When it is determined that both the two-dimensional image and the point cloud data of the logo have no defects, it is determined that the logo has no defects. When it is determined that the two-dimensional image and / or point cloud data of the logo have defects, it is determined that the logo has defects.

[0081] In this embodiment, it is determined whether the order of the scanned identifiers is the same as the order of the corresponding preset identifiers in the identifier database 21 to determine whether the order of the identifiers conforms to the preset order. For example, the preset order is Figure 6 1-14 in the sequence. When it is determined that the order in which the identifiers are scanned is the same as the order of the corresponding preset identifiers in the identifier database 21, it is determined that the order of the identifiers conforms to the preset order. For example, when the identifier scanned for the third time by the 3D laser scanning device 70 is the third preset identifier in the identifier database 21, it is determined that the order of the identifiers conforms to the preset order. When it is determined that the order in which the identifiers are scanned is different from the order of the corresponding preset identifiers in the identifier database 21, it is determined that the order of the identifiers does not conform to the preset order.

[0082] When the identification meets the preset detection standard, it is determined that the wheel hub 2 passes the detection.

[0083] In this embodiment, when it is determined that all the marks are the same as the corresponding preset marks, it is determined that all the marks do not have defects, and it is determined that the order of all the marks conforms to the preset order, it is determined that the wheel hub 2 passes the inspection.

[0084] When the mark does not meet the preset detection standard, it is determined that the wheel hub 2 has failed the detection.

[0085] In this embodiment, when it is determined that any mark is different from the corresponding preset mark, and / or any mark is determined to be defective, and / or the order of any mark does not conform to the preset order, it is determined that the wheel hub 2 has failed the inspection.

[0086] See also Figure 8As shown, specifically, S81, import the identification database 21. S82, whenever the 3D laser scanning device 70 scans and obtains an identification, the identification is detected to be correct or not, and the identification is compared with the corresponding preset identification in the identification database 21. S83, when the identification is the same as the preset identification, the identification is detected for defects. S84, whether the identification is defective is determined according to the defect detection result. S85, when the identification is different from the preset identification, whether the number of scans of the identification is greater than the preset number. When it is determined that the number of scans of the identification is greater than the preset number, it is determined that the wheel hub 2 has not passed the detection, and the process proceeds to S88 to remove the wheel hub 2. When it is determined that the number of scans of the identification is not greater than the preset number, the process returns to S82, and the identification re-scanned by the 3D laser scanning device 70 is compared with the corresponding preset identification in the identification database 21. When it is determined that the identification is defective, it is determined that the wheel hub 2 has not passed the detection, and the process proceeds to S88 to remove the wheel hub 2. When it is determined that the identification is not defective, the process proceeds to S86 to perform sequential detection on the identification. S87, judging whether the sequence of the marks conforms to the preset sequence according to the sequence detection result. When it is determined that the sequence of the marks conforms to the preset sequence, it is determined that the wheel hub 2 has passed the detection, and the process proceeds to S89, and the wheel hub 2 enters the next process. When it is determined that the sequence of the marks does not conform to the preset sequence, it is determined that the wheel hub 2 has not passed the detection, and the process proceeds to S88, and the wheel hub 2 is removed.

[0087] Furthermore, the method further includes the following steps: in the process of comparing any logo with the corresponding preset logo in the logo database 21, when it is determined that the similarity between the font of any logo and the corresponding preset logo is less than a preset percentage, for example, 50%, it means that the font of the scanned logo is too different from the font of the preset logo in the current logo database 21, and the font of the scanned logo is added to the logo database 21 to update the logo database 21. In the process of performing defect detection on the 3D image of any logo through the convolutional neural network model, when it is determined that the similarity between the 3D image defect feature of any scanned logo and the 3D image defect feature in the pre-trained convolutional neural network model is less than a preset percentage, for example, 50%, it means that the 3D image defect feature of the scanned logo is too different from the 3D image defect feature in the convolutional neural network model, and the convolutional neural network model is continuously trained according to the 3D image defect feature of the logo to update the convolutional neural network model.

[0088] Furthermore, the method further comprises the following steps: displaying the identification detection result of the wheel hub 2 on the display screen 80. The identification detection result includes whether the wheel hub passes the detection or fails the detection.

[0089] Furthermore, the method also includes the following steps: when the wheel hub 2 passes the inspection, the robot arm (not shown) is controlled to place the wheel hub 2 in the next production process; when the wheel hub 2 fails the inspection, the robot arm is controlled to remove the wheel hub 2 from the current production process.

[0090] See also Fig. 9 As shown, it is a flowchart for identifying a designated mark provided by another embodiment of the present invention. Steps S901-S907 are the same as steps S201-S207. S908. When identifying a designated mark, determine the angle between the center line of the hub circle and the characteristic contour center line of the spoke 201 where the designated mark is located and the angle between the center line of the hub circle and the characteristic contour center line of the spoke 201 within the current scanning range based on the image captured by the camera device 40. S909. Determine the designated rotation angle of the hub 2 based on the angle. S910. Control the hub 2 to rotate by the designated rotation angle so that the spoke 201 where the designated mark is located moves into the scanning range of the 3D laser scanning device 70. S911. Control the 3D laser scanning device 70 to move in a straight line through the driving device 71 to scan the designated mark and identify the designated mark.

[0091] See also Fig.10 , which is a schematic diagram of the structure of an electronic device provided in a preferred embodiment of the present invention.

[0092] The electronic device 1 includes, but is not limited to, a processor 10, a memory 20, a computer program 30 stored in the memory 20 and executable on the processor 10, a camera 40, a light source 50, a rotating platform 60, a 3D laser scanning device 70, a driving device 71, a motion axis 72, and a display screen 80. For example, the computer program 30 is a wheel hub mark detection program. When the processor 10 executes the computer program 30, steps in the wheel hub mark detection method are implemented, such as Figure 2 Steps S201 to S207 and Fig. 9 Steps S901 to S911 are shown.

[0093] Those skilled in the art will understand that the schematic diagram is merely an example of the electronic device 1 and does not constitute a limitation of the electronic device 1. The electronic device 1 may include more or fewer components than shown in the diagram, or a combination of certain components, or different components. For example, the electronic device 1 may also include input and output devices, network access devices, buses, etc.

[0094] The processor 10 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or the processor 10 may be any conventional processor, etc. The processor 10 is the control center of the electronic device 1, and uses various interfaces and lines to connect various parts of the entire electronic device 1.

[0095] The memory 20 can be used to store the computer program 30 and / or modules / units. The processor 10 realizes various functions of the electronic device 1 by running or executing the computer program and / or modules / units stored in the memory 20 and calling the data stored in the memory 20. The memory 20 can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area can store data created according to the use of the electronic device 1 (such as audio data, a phone book, etc.), etc. In addition, the memory 20 can include a volatile memory and a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other storage devices. In this embodiment, the memory 20 stores an identification database 21, and the identification database 21 stores a plurality of preset identifications.

[0096] In this embodiment, the camera device 40 is an area array camera with 20 million pixels, including an industrial lens. The focal length of the industrial lens includes 8 mm and 16 mm. The light source 50 is an open-hole surface light source with a size of 750 mm*750 mm.

[0097] In this embodiment, the rotating platform 60 is used to carry the wheel hub 2 and can drive the wheel hub 2 to rotate. The 3D laser scanning device 70 is a 3D line laser, which is used to emit laser to scan the wheel hub 2. The 3D laser scanning device 70 and the driving device 71 are installed on the motion axis 72. The driving device 71 is a linear motor, which is used to drive the 3D laser scanning device 70 to move along the motion axis 72. In this embodiment, the display screen 80 is a liquid crystal display screen.

[0098] If the module / unit integrated in the electronic device 1 is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device that can carry the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory).

[0099] The wheel hub mark detection method, electronic device and storage medium provided by the present invention can identify the angle between the wheel hub marks through a camera device, and automatically scan and identify the marks in sequence according to the angle between the wheel hub marks through a scanning device, thereby reducing labor costs and improving the automation and accuracy of wheel hub mark recognition.

[0100] It is obvious to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential features of the present invention. Therefore, from any point of view, the embodiments should be regarded as exemplary and non-restrictive, and the scope of the present invention is defined by the appended claims rather than the above description, and it is intended that all changes falling within the meaning and scope of the equivalent elements of the claims are included in the present invention. Any figure mark in the claims should not be regarded as limiting the claims involved. In addition, it is obvious that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or devices stated in the device claim can also be implemented by the same unit or device through software or hardware. The words first, second, etc. are used to indicate names, and do not indicate any particular order.

[0101] The above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A wheel hub mark detection method, characterized in that: The method comprises: Taking an image of a hub surface by a camera device, wherein the hub surface includes a plurality of marks; Processing the image captured by the camera device to identify the characteristic contour of the spoke on the hub, wherein the characteristic contour is used to indicate the position of the mark on the spoke; Calculate the angle between the center of the wheel hub and the line connecting the center of the characteristic profile; Determining a plurality of rotation angles of the hub according to an angle between a center of the hub and a line connecting a center of the characteristic profile; Controlling the wheel hub to rotate sequentially according to the multiple rotation angles, so that the marks are moved into the scanning range of the 3D laser scanning device sequentially; When the wheel hub rotates by a certain angle, the 3D laser scanning device is controlled to scan the mark that is rotated and moved into the current scanning range; and The mark scanned by the 3D laser scanning device is identified.

2. The wheel hub mark detection method according to claim 1, characterized in that: The identifying the mark scanned by the 3D laser scanning device comprises: Determining whether the mark meets the preset testing standards; and When the identification meets the preset detection standard, it is determined that the wheel hub passes the detection.

3. The wheel hub mark detection method according to claim 2, characterized in that: The preset inspection standard includes that each mark is the same as the corresponding preset mark, each mark does not have defects, and the order of the marks conforms to the preset order. The determination of whether the marks conform to the preset inspection standard includes: Determine whether the identifier is the same as the corresponding preset identifier, determine whether the identifier has defects, and determine whether the order of the identifiers conforms to the preset order.

4. The wheel hub mark detection method according to claim 3, characterized in that: The determining whether the identifier is the same as the corresponding preset identifier includes: Comparing the identifier with a corresponding preset identifier in an identifier database to determine whether the identifier is the same as the corresponding preset identifier; The determining whether the mark has a defect comprises: Whether the multiple logos have defects is determined through deep learning visual matching or point cloud matching.

5. The wheel hub mark detection method according to claim 4, characterized in that: The method further comprises: When it is determined that the mark is different from the corresponding preset mark, and / or it is determined that the mark has a defect, and / or it is determined that the order of the marks does not conform to the preset order, it is determined that the wheel hub has failed the inspection.

6. The wheel hub mark detection method according to claim 5, characterized in that: The method further comprises: In the process of comparing any logo with the corresponding preset logo in the logo database, when it is determined that the similarity between the font of the logo and the corresponding preset logo is less than a preset percentage, the font of the logo is added to the logo database to update the logo database; In the process of performing defect detection on any marked 3D image through a convolutional neural network model, when it is determined that the degree of similarity between the marked 3D image defect features and the 3D image defect features in the convolutional neural network model is less than the preset percentage, the convolutional neural network model is continued to be trained according to the marked 3D image defect features to update the convolutional neural network model.

7. The wheel hub mark detection method according to claim 1, characterized in that: The calculation of the angle between the center of the hub and the connecting line of the center of the characteristic profile comprises: Draw a plurality of connecting lines between the center of the wheel hub and the center of the characteristic contour; and The plurality of connecting lines are identified by an edge extraction algorithm, and the angles between the plurality of connecting lines are calculated.

8. The wheel hub mark detection method according to claim 1, characterized in that: When the wheel hub rotates by a rotation angle, controlling the 3D laser scanning device to move on the wheel hub to scan the mark that is rotated and moved into the current scanning range includes: When the wheel hub rotates by a rotation angle, the driving device controls the 3D laser scanning device to move linearly along a first direction of the wheel hub to scan a mark on a radial angle of the wheel hub within a current scanning range; and When the wheel hub rotates to a next rotation angle, the driving device controls the 3D laser scanning device to move linearly along a second direction of the wheel hub opposite to the first direction to scan the mark on the next radial angle of the wheel hub.

9. An electronic device, characterized in that: The electronic device comprises: Processor; and A memory, wherein a plurality of program modules are stored in the memory, and the plurality of program modules are loaded by the processor and execute the wheel hub mark detection method according to any one of claims 1 to 8.

10. A storage medium having at least one computer instruction stored thereon, characterized in that: The instructions are loaded by the processor and executed by the wheel hub mark detection method according to any one of claims 1 to 8.

Images