Riveting quality automatic detection method and device, electronic equipment, medium and vehicle
Through acquisition equipment and image segmentation technology, combined with riveting point defect detection algorithm, automated detection of vehicle riveting quality is achieved, solving the problems of high manual inspection costs and low accuracy in the existing technology, and improving detection accuracy.
Patent Information
- Application Number
- CN202310769406.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2023-06-27
- Publication Date
- 2024-12-27
AI Technical Summary
In the prior art, vehicle riveting quality inspection relies on manual methods, which has problems such as high cost and low detection accuracy, and it is difficult to realize automated inspection.
The initial image to be detected is collected through multiple acquisition devices, image segmentation and riveting point defect detection algorithm detection, and defects of riveting nuts are automatically detected to realize automatic detection of riveting quality.
It reduces detection costs, improves defect detection accuracy, avoids the dependence of manual detection, and improves detection accuracy.
Smart Images
Figure CN119205602A_ABST
Abstract
Description
Technical Field
[0001] The present disclosure relates to the field of vehicle detection technology, and in particular to a method, device, electronic equipment, medium and vehicle for automatic detection of riveting quality. Background Art
[0002] At present, riveting is often used in the vehicle production process. For example, the shock absorber towers on both sides of the front end of the vehicle are connected to the vehicle body by riveting. However, due to process reasons, the nuts at the riveted points may crack. When the nuts crack severely, it will affect the subsequent production of the vehicle and even cause the nuts at the riveted points to break due to excessive force during the use of the vehicle, causing property and safety impacts on users. Therefore, it is very important to test the riveting quality of vehicles.
[0003] In the prior art, manual methods are usually used to detect the riveting quality of vehicles to determine whether the quality of the nuts at the riveted points is qualified. However, this manual method has the problems of high cost and low detection accuracy, and is extremely dependent on personal experience. It is also difficult to unify the detection standards. Therefore, how to automatically detect the riveting quality has become an urgent problem to be solved. Summary of the invention
[0004] In order to solve the above technical problems, the present disclosure provides a method, device, electronic equipment, medium and vehicle for automatic detection of riveting quality.
[0005] In a first aspect, an embodiment of the present disclosure provides a method for automatically detecting riveting quality, comprising: using a plurality of acquisition devices to respectively acquire initial images to be detected corresponding to the workpiece to be detected, wherein the initial images to be detected include at least one riveted nut to be detected;
[0006] Segmenting the initial image to be detected to obtain at least one target image to be detected, wherein each target image to be detected includes a single riveted nut to be detected;
[0007] Each of the target images to be detected is detected by a riveting point defect detection algorithm to obtain a target detection result, and the target detection result is used to indicate whether each of the riveted nuts to be detected has defects.
[0008] Optionally, the step of respectively acquiring initial images to be detected corresponding to the workpieces to be detected by using a plurality of acquisition devices includes:
[0009] For each of the acquisition devices, obtaining a correspondence between the acquisition device and a preset acquisition viewing angle;
[0010] Based on the corresponding relationship, obtaining a preset acquisition angle corresponding to the acquisition device from a plurality of preset acquisition angles;
[0011] The acquisition device is adjusted based on the preset acquisition viewing angle corresponding to the acquisition device, and the initial image to be detected corresponding to the workpiece to be detected is acquired at the preset acquisition viewing angle using the adjusted acquisition device.
[0012] Optionally, the method further includes:
[0013] After determining that the initial image to be detected is collected, the initial image to be detected is saved in a preset database.
[0014] Optionally, before the initial images to be detected corresponding to the workpieces to be detected are respectively acquired by multiple acquisition devices, the method further includes:
[0015] Obtaining a target placement position corresponding to the workpiece to be detected;
[0016] Based on the target placement position, the workpiece to be detected is moved so that the workpiece to be detected is moved to the target placement position.
[0017] Optionally, the segmenting the initial image to be detected to obtain at least one target image to be detected includes:
[0018] In each of the initial images to be detected, determining a preset area corresponding to each of the riveted nuts to be detected included in the initial images to be detected;
[0019] Based on at least one of the preset areas, the initial image to be detected is segmented to obtain at least one target image to be detected.
[0020] Optionally, the method further includes:
[0021] In response to the detection end signal, at least one of the to-be-detected images stored in the preset database is cleared.
[0022] Optionally, the method further includes:
[0023] With respect to the target detection result, the target detection result is displayed to the user through a preset interface.
[0024] In a second aspect, an embodiment of the present disclosure provides an automatic riveting quality detection device, comprising:
[0025] An initial image acquisition module for detecting is used to respectively detect initial images corresponding to the workpiece to be detected by using a plurality of acquisition devices, wherein the initial image to be detected includes at least one riveted nut to be detected;
[0026] A target image acquisition module for detecting is used to segment the initial image to be detected to obtain at least one target image to be detected, wherein each of the target images to be detected includes a single riveted nut to be detected;
[0027] The target detection result obtaining module is used to detect each of the target images to be detected by using a riveting point defect detection algorithm to obtain a target detection result, and the target detection result is used to indicate whether each of the riveted nuts to be detected has defects.
[0028] In a third aspect, an embodiment of the present disclosure provides an electronic device, including:
[0029] one or more processors;
[0030] a storage device for storing one or more programs,
[0031] When the one or more programs are executed by the one or more processors, the one or more processors implement any method as described in the first aspect.
[0032] In a fourth aspect, an embodiment of the present disclosure provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements any method described in the first aspect.
[0033] In a fifth aspect, an embodiment of the present disclosure provides a vehicle, comprising: a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the computer program, when executed by the processor, implements any method described in the first aspect.
[0034] Compared with the prior art, the technical solution provided by the embodiments of the present disclosure has the following advantages:
[0035] The automatic detection method for riveting quality provided by the embodiment of the present disclosure collects the initial images to be detected corresponding to the workpiece to be detected by multiple acquisition devices, wherein the initial images to be detected include at least one riveted nut to be detected; the initial images to be detected are segmented to obtain at least one target image to be detected, wherein each target image to be detected includes a single riveted nut to be detected; each target image to be detected is detected by a riveting point defect detection algorithm to obtain a target detection result, and the target detection result is used to indicate whether each riveted nut to be detected has defects. In the above process, the initial images to be detected corresponding to the workpiece to be detected can be automatically collected by multiple acquisition devices, and defect detection processing can be performed on the riveted nuts to be detected in one or more target images to be detected corresponding to the initial images to be detected, so as to realize automatic detection of whether each riveted nut to be detected has defects, avoid manual detection, thereby reducing costs, and because each target image to be detected includes only one riveted nut to be detected, the defect detection accuracy is improved. BRIEF DESCRIPTION OF THE DRAWINGS
[0036] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the present disclosure.
[0037] 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, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.
[0038] Figure 1 It is a flow chart of a method for automatic detection of riveting quality provided by an embodiment of the present disclosure;
[0039] Figure 2 It is a flowchart of another automatic riveting quality detection method provided by an embodiment of the present disclosure;
[0040] Figure 3 is a schematic structural diagram of a device for automatically detecting riveting quality provided by an embodiment of the present disclosure;
[0041] Figure 4 It is a schematic diagram of the structure of an electronic device provided by an embodiment of the present disclosure. DETAILED DESCRIPTION
[0042] In order to more clearly understand the above-mentioned objectives, features and advantages of the present disclosure, the scheme of the present disclosure will be further described below. It should be noted that the embodiments of the present disclosure and the features in the embodiments can be combined with each other without conflict.
[0043] In the following description, many specific details are set forth to facilitate a full understanding of the present disclosure, but the present disclosure may also be implemented in other ways different from those described herein; it is obvious that the embodiments in the specification are only part of the embodiments of the present disclosure, rather than all of the embodiments.
[0044] At present, the shock towers on both sides of the front end of the vehicle are connected to the vehicle body by riveting. However, due to process reasons, the nuts at each riveting point may crack. When the nuts crack seriously, it will affect the subsequent production of the vehicle, and even cause the nuts at the riveted points to break due to excessive force during the use of the vehicle, causing property and safety impacts on the user. Therefore, it is very important to test the riveting quality of the vehicle. In the prior art, the riveting quality of the vehicle is usually tested manually to determine whether the quality of the nuts at the riveted points is qualified.
[0045] However, this manual method has the problems of high cost and low detection accuracy when manually testing the riveting quality of vehicles due to the large number of rivet points distributed on the shock absorber towers on both sides of the front end of the vehicle, the complex distribution positions of the rivet points, and the large influence of external factors such as light.
[0046] Based on this, the embodiment of the present disclosure provides a method for automatic detection of riveting quality, wherein the initial images to be detected corresponding to the workpiece to be detected are respectively collected by multiple acquisition devices, wherein the initial images to be detected include at least one riveted nut to be detected; the initial images to be detected are segmented to obtain at least one target image to be detected, wherein each target image to be detected includes a single riveted nut to be detected; each target image to be detected is detected by a riveting point defect detection algorithm to obtain a target detection result, and the target detection result is used to indicate whether each riveted nut to be detected has defects. In the above process, the initial images to be detected corresponding to the workpiece to be detected can be automatically collected by multiple acquisition devices, and defect detection processing can be performed on the riveted nuts to be detected in one or more target images to be detected corresponding to the initial images to be detected, so as to realize automatic detection of whether each riveted nut to be detected has defects, avoid manual detection, thereby reducing costs, and because each target image to be detected includes only one riveted nut to be detected, the defect detection accuracy is improved.
[0047] Figure 1 is a flow chart of a method for automatically detecting riveting quality provided by an embodiment of the present disclosure, such as Figure 1 As shown, the automatic riveting quality detection method provided by the embodiment of the present disclosure includes:
[0048] S11, respectively acquiring initial images to be inspected corresponding to the workpiece to be inspected by using a plurality of acquisition devices.
[0049] The workpiece to be inspected refers to a workpiece including a plurality of riveted points where the shock absorber towers on both sides of the front of the vehicle are riveted to the vehicle body, wherein each riveted point corresponds to a riveted nut.
[0050] The initial image to be inspected includes at least one riveted nut to be inspected; the riveted nut to be inspected is used to detect whether there are defects.
[0051] Specifically, when a detection signal is received, in response to the detection signal, multiple acquisition devices are used to photograph the workpiece to be inspected at preset acquisition angles corresponding to the multiple acquisition devices, so as to obtain an initial image to be inspected corresponding to the workpiece to be inspected through each acquisition device, and each initial image to be inspected includes one or more riveted nuts to be inspected.
[0052] Among them, the above-mentioned detection signal refers to a signal used to indicate defect detection on the workpiece to be inspected. The detection signal can be obtained through user input. The acquisition device refers to a device with an image shooting function, that is, a device that can shoot the initial image to be inspected corresponding to the workpiece to be inspected. The acquisition device can be, for example, a camera, a video camera, etc., but is not limited to this. The present disclosure does not specifically limit it, and technical personnel in this field can make specific settings according to actual conditions.
[0053] The above-mentioned preset acquisition angle refers to a pre-set acquisition angle for different acquisition devices in order to accurately obtain the initial image to be inspected corresponding to the workpiece to be inspected, including one or more rivet nuts to be inspected. The acquisition angle is determined according to the parameters such as the height and angle of the acquisition device when each acquisition device is acquiring the image to be inspected corresponding to the workpiece to be inspected, but is not limited to this. The present disclosure does not specifically limit it, and technical personnel in this field can make specific settings according to actual conditions.
[0054] Optionally, based on the above embodiments, in some embodiments of the present disclosure, before the initial images to be detected corresponding to the workpieces to be detected are respectively acquired by multiple acquisition devices, the following steps are further included:
[0055] Get the target placement position corresponding to the workpiece to be detected.
[0056] Among them, the target placement position is used to ensure that during the process of photographing the workpiece to be inspected, when the workpiece to be inspected is moved to the preset target placement position, an initial image to be inspected containing one or more rivet nuts to be inspected can be captured by the acquisition device.
[0057] Optionally, on the basis of the above embodiments, in some embodiments of the present disclosure, an implementation method for obtaining the target placement position corresponding to the workpiece to be inspected may be: determining and storing the target placement position through the historical placement position corresponding to the workpiece to be inspected, and after receiving a detection signal, determining the target placement position corresponding to the current workpiece to be inspected from a plurality of pre-stored target placement positions in response to the detection signal according to the identification information of the workpiece to be inspected.
[0058] Furthermore, it should be noted that different target placement positions correspond to the workpieces to be inspected corresponding to the two sides of the front end of the vehicle.
[0059] Based on the target placement position, the workpiece to be inspected is moved so that the workpiece to be inspected is moved to the target placement position.
[0060] Specifically, after receiving the detection signal, the target placement position corresponding to the current workpiece to be detected is obtained in response to the detection signal. After obtaining the target placement position corresponding to the workpiece to be detected, the workpiece to be detected is moved to the target placement position.
[0061] In this way, the automatic riveting quality detection method provided by the embodiment of the present disclosure moves the workpiece to be detected to the target placement position to ensure that when the workpiece to be detected is photographed, an initial image to be detected containing one or more riveted nuts to be detected can be captured by the acquisition device.
[0062] S12: Segment the initial image to be detected to obtain at least one target image to be detected.
[0063] Wherein, each target image to be detected includes a single riveted nut to be detected.
[0064] Specifically, when a plurality of initial images to be detected are obtained, segmentation processing is performed on each initial image to be detected to obtain one or more target images to be detected corresponding to each initial image to be detected, and each target image to be detected includes only one riveted nut to be detected.
[0065] Optional, Figure 2 is a flow chart of another automatic riveting quality detection method provided by an embodiment of the present disclosure. Figure 2 exist Figure 1 On the basis of Figure 2 As shown, one implementation of S12 may be:
[0066] S121 . In each initial image to be detected, determine a preset area corresponding to each riveted nut to be detected included in the initial image to be detected.
[0067] The preset area refers to an area in the initial image to be detected that only includes one riveted nut to be detected.
[0068] S122: Segment the initial image to be detected based on at least one preset area to obtain at least one target image to be detected.
[0069] Specifically, for each initial image to be detected, a preset area corresponding to each riveted nut to be detected included in the initial image to be detected is determined in the initial image to be detected. After obtaining the preset area corresponding to each riveted nut to be detected, the initial image to be detected is segmented based on the multiple preset areas to obtain one or more target images to be detected corresponding to the initial image to be detected, wherein each target image to be detected includes only one riveted nut to be detected.
[0070] In this way, the automatic riveting quality detection method provided by the embodiment of the present disclosure obtains a target image to be detected including only one riveted nut to be detected by segmenting the initial image to be detected including one or more riveted nuts to be detected. In this way, when defect detection is subsequently performed on the riveted nuts to be detected, the size of the detection image can be reduced, thereby improving the detection accuracy.
[0071] S13, detecting each target image to be detected by using a riveting point defect detection algorithm to obtain a target detection result.
[0072] Among them, the target detection result is used to indicate whether each riveted nut to be detected has defects. The defect can be, for example, cracking of the riveted nut to be detected, or the severity of the defect of the riveted nut to be detected, but is not limited to this. The present disclosure does not specifically limit it, and technical personnel in this field can make specific settings according to actual conditions.
[0073] Specifically, after obtaining multiple target images to be detected, the target images to be detected are used as input images of the rivet point defect detection algorithm, and defect detection processing is performed on each target image to be detected by the rivet point defect detection algorithm, and the target detection results corresponding to each target image to be detected output by the rivet point defect detection algorithm are obtained, so as to determine whether each rivet nut to be detected has defects through the target detection results.
[0074] It should be noted that the above-mentioned riveting point defect detection algorithm can be a defect detection algorithm of a support vector machine based on machine learning, or a defect detection algorithm of a convolutional neural network model based on deep learning, but is not limited thereto. The present disclosure does not specifically limit this, and those skilled in the art can make specific settings according to actual conditions. Further, the riveting point defect detection algorithm is used to detect each target image to be detected, and the target detection results can be obtained by referring to the prior art, which will not be described in detail here.
[0075] In this way, the automatic detection method for riveting quality provided by the embodiment of the present disclosure collects the initial images to be detected corresponding to the workpiece to be detected through multiple acquisition devices, wherein the initial images to be detected include at least one riveted nut to be detected; the initial images to be detected are segmented to obtain at least one target image to be detected, wherein each target image to be detected includes a single riveted nut to be detected; each target image to be detected is detected by a riveting point defect detection algorithm to obtain a target detection result, and the target detection result is used to indicate whether each riveted nut to be detected has defects. In the above process, the initial images to be detected corresponding to the workpiece to be detected can be automatically collected through multiple acquisition devices, and defect detection processing can be performed on the riveted nuts to be detected in one or more target images to be detected corresponding to the initial images to be detected, so as to realize automatic detection of whether each riveted nut to be detected has defects, avoid manual detection, thereby reducing costs, and because each target image to be detected includes only one riveted nut to be detected, the defect detection accuracy is improved.
[0076] Optionally, based on the above embodiment, in some embodiments of the present disclosure, an implementation method of respectively acquiring initial images to be detected corresponding to the workpiece to be detected by multiple acquisition devices may be:
[0077] S111. For each acquisition device, obtain a correspondence between the acquisition device and a preset acquisition viewing angle.
[0078] The corresponding relationship is used to determine the preset acquisition viewing angle corresponding to the acquisition device.
[0079] S112. Based on the corresponding relationship, obtain a preset acquisition angle of view corresponding to the acquisition device from multiple preset acquisition angles.
[0080] Specifically, for each acquisition device, a correspondence between each acquisition device and a preset acquisition viewing angle is obtained. After the correspondence is obtained, the preset acquisition viewing angle of the acquisition device is determined according to the correspondence among multiple preset acquisition viewing angles.
[0081] Optionally, a correspondence may be established between the identification information of the acquisition device and the identification information of the preset acquisition perspective. After the correspondence is obtained, the identification information corresponding to multiple preset acquisition perspectives may be matched according to the identification information of the acquisition device to determine the preset acquisition perspective of the acquisition device. However, this is not limited to this and the present disclosure does not specifically limit this. Technical personnel in this field may make specific settings based on actual conditions.
[0082] S113, adjusting the acquisition device based on a preset acquisition viewing angle corresponding to the acquisition device, and using the adjusted acquisition device to acquire an initial image to be detected corresponding to the workpiece to be detected at the preset acquisition viewing angle.
[0083] Specifically, after obtaining the preset acquisition viewing angle corresponding to each acquisition device, the acquisition device is adjusted, and the initial image to be detected corresponding to the workpiece to be detected is acquired by the adjusted acquisition device at the preset acquisition viewing angle.
[0084] Optionally, based on the above embodiment, in some embodiments of the present disclosure, after executing S113, the following step is further included:
[0085] After determining that the initial image to be detected is acquired, the initial image to be detected is saved in a preset database.
[0086] The preset database may be a temporary image cache area, but is not limited thereto. The present disclosure does not specifically limit this, and those skilled in the art may make specific settings according to actual conditions.
[0087] Specifically, when the initial image to be detected corresponding to the workpiece to be detected is collected by the collection device, the initial image to be detected is saved in a preset database.
[0088] In this way, the automatic riveting quality detection method provided by the embodiment of the present disclosure improves the accuracy of obtaining the image to be detected including one or more riveted nuts to be detected by adjusting the acquisition angle of each acquisition device to a preset acquisition angle so that when the image to be detected corresponding to the workpiece to be detected is acquired by the acquisition device.
[0089] Optionally, based on the above embodiments, in some embodiments of the present disclosure, the method further includes:
[0090] In response to the detection end signal, at least one image to be detected stored in the preset database is cleared.
[0091] Specifically, when the detection end signal is received, in response to the detection end signal, defect detection of the riveted nut to be detected on the workpiece to be detected is stopped, and one or more images to be detected stored in the preset database are cleared.
[0092] In this way, the automatic riveting quality detection method provided by the embodiment of the present disclosure can clear at least one image to be detected stored in the preset database when receiving the end detection signal, thereby saving resources.
[0093] Optionally, based on the above embodiments, in some embodiments of the present disclosure, the method further includes:
[0094] The target detection result is displayed to the user through a preset interface.
[0095] Specifically, for the riveted nut to be detected, after obtaining the target detection result corresponding to the riveted nut to be detected, it is possible to display to the user on a preset interface whether the riveted nut to be detected has defects.
[0096] Optionally, on the basis of the above embodiments, in some embodiments of the present disclosure, for the target detection result, an implementation method of displaying the target detection result to the user through a preset interface may be: for at least one riveted nut to be detected included in the image to be detected, a target detection result corresponding to each riveted nut to be detected is obtained, and it is determined whether each riveted nut to be detected has defects, and on the preset interface, different marking processing is performed on the defective riveted nuts to be detected and the non-defective riveted nuts to be detected, for example, the defective riveted nuts to be detected are marked with a red frame, and the non-defective riveted nuts to be detected are marked with a green frame, so as to display the target detection results of each riveted nut to be detected to the user.
[0097] In this way, the automatic riveting quality detection method provided by the embodiment of the present disclosure improves the user experience by intuitively showing the user whether the riveted nut to be detected has defects through a preset interface after obtaining the target detection result.
[0098] Figure 3 is a schematic diagram of the structure of an automatic riveting quality detection device provided by an embodiment of the present disclosure, such as Figure 3 As shown, the automatic riveting quality detection device includes: an initial to-be-detected image acquisition module 11, a target to-be-detected image acquisition module 12 and a target detection result acquisition module 13.
[0099] The initial to-be-detected image acquisition module 11 is used to respectively acquire the initial to-be-detected images corresponding to the to-be-detected workpieces through a plurality of acquisition devices, wherein the initial to-be-detected images include at least one to-be-detected riveted nut;
[0100] The target image acquisition module 12 is used to segment the initial image to be detected to obtain at least one target image to be detected, wherein each target image to be detected includes a single riveted nut to be detected;
[0101] The target detection result obtaining module 13 is used to detect each of the target images to be detected by using a riveting point defect detection algorithm to obtain a target detection result, and the target detection result is used to indicate whether each of the riveted nuts to be detected has defects.
[0102] The automatic riveting quality detection device provided by the embodiment of the present disclosure comprises an initial image acquisition module for acquiring initial images to be detected corresponding to the workpiece to be detected through multiple acquisition devices, wherein the initial images to be detected include at least one riveted nut to be detected; a target image acquisition module for segmenting the initial images to be detected to obtain at least one target image to be detected, wherein each target image to be detected includes a single riveted nut to be detected; and a target detection result acquisition module for detecting each target image to be detected through a riveting point defect detection algorithm to obtain a target detection result, which is used to indicate whether each riveted nut to be detected has a defect. In the above process, the initial images to be detected corresponding to the workpiece to be detected can be automatically acquired through multiple acquisition devices, and defect detection processing can be performed on the riveted nuts to be detected in one or more target images to be detected corresponding to the initial images to be detected, so as to realize automatic detection of whether each riveted nut to be detected has a defect, avoid manual detection, thereby reducing costs, and because each target image to be detected includes only one riveted nut to be detected, the defect detection accuracy is improved.
[0103] Optionally, the initial to-be-detected image acquisition module 11 is specifically configured to acquire, for each of the acquisition devices, a correspondence between the acquisition device and a preset acquisition viewing angle;
[0104] Based on the corresponding relationship, obtaining a preset acquisition angle corresponding to the acquisition device from a plurality of preset acquisition angles;
[0105] The acquisition device is adjusted based on the preset acquisition viewing angle corresponding to the acquisition device, and the adjusted acquisition device is used to acquire the initial image to be detected corresponding to the workpiece to be detected under the preset acquisition viewing angle.
[0106] Optionally, the initial image to be detected acquiring module 11 is further configured to save the initial image to be detected into a preset database after determining that the initial image to be detected is acquired.
[0107] Optionally, the device further comprises: an acquisition module and a moving module, wherein the acquisition module is used to acquire a target placement position corresponding to the workpiece to be detected;
[0108] The moving module is used to move the workpiece to be detected based on the target placement position, so as to move the workpiece to be detected to the target placement position.
[0109] Optionally, the target image acquisition module 12 is specifically used to determine, in each of the initial images to be detected, a preset area corresponding to each of the riveted nuts to be detected included in the initial images to be detected;
[0110] Based on at least one of the preset areas, the initial image to be detected is segmented to obtain at least one target image to be detected.
[0111] Optionally, the device further includes: a clearing module, configured to clear at least one of the to-be-detected images stored in the preset database in response to an end detection signal.
[0112] Optionally, the device further includes: a display module, configured to display the target detection result to a user via a preset interface.
[0113] The device provided by the embodiment of the present invention can execute the method provided by any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.
[0114] It is worth noting that in the embodiment of the above-mentioned device, the various units and modules included are only divided according to functional logic, but are not limited to the above-mentioned division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present invention.
[0115] Figure 4 is a schematic diagram of the structure of an electronic device provided by an embodiment of the present disclosure, such as Figure 4 As shown, the electronic device includes a processor 410, a memory 420, an input device 430, and an output device 440; the number of processors 410 in the computer device can be one or more. Figure 4 A processor 410 is taken as an example; the processor 410, the memory 420, the input device 430 and the output device 440 in the electronic device can be connected via a bus or other means. Figure 4 The example of connecting through bus is taken in the following.
[0116] The memory 420 is a computer-readable storage medium that can be used to store software programs, computer executable programs and modules, such as program instructions / modules corresponding to the method in the embodiment of the present invention. The processor 410 executes various functional applications and data processing of the computer device by running the software programs, instructions and modules stored in the memory 420, that is, implements the method provided in the embodiment of the present invention.
[0117] The memory 420 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system and at least one application required for a function; the data storage area may store data created according to the use of the terminal, etc. In addition, the memory 420 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some instances, the memory 420 may further include a memory remotely arranged relative to the processor 410, and these remote memories may be connected to the computer device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.
[0118] The input device 430 may be used to receive input digital or character information and generate key signal input related to user settings and function control of the electronic device, and may include a keyboard, a mouse, etc. The output device 440 may include a display device such as a display screen.
[0119] The present disclosure also provides a storage medium containing computer executable instructions. When the computer executable instructions are executed by a computer processor, the method provided by the present disclosure includes:
[0120] Using a plurality of acquisition devices, respectively acquire initial images to be detected corresponding to the workpiece to be detected, wherein the initial images to be detected include at least one riveted nut to be detected;
[0121] Segmenting the initial image to be detected to obtain at least one target image to be detected, wherein each target image to be detected includes a single riveted nut to be detected;
[0122] Each of the target images to be detected is detected by a riveting point defect detection algorithm to obtain a target detection result, and the target detection result is used to indicate whether each of the riveted nuts to be detected has defects.
[0123] Of course, the computer executable instructions of a storage medium including computer executable instructions provided by an embodiment of the present invention are not limited to the operations of the method described above, but can also execute related operations in the method provided by any embodiment of the present invention.
[0124] Through the above description of the implementation methods, the technicians in the relevant field can clearly understand that the present invention can be implemented by means of software and necessary general hardware, and of course it can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as a computer floppy disk, a read-only memory (ROM), a random access memory (RAM), a flash memory (FLASH), a hard disk or an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present invention.
[0125] It should be noted that, in this article, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.
[0126] The above description is only a specific embodiment of the present disclosure, so that those skilled in the art can understand or implement the present disclosure. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present disclosure. Therefore, the present disclosure will not be limited to the embodiments described herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.
Claims
1. A method for automatic detection of riveting quality, characterized in that: include: Using a plurality of acquisition devices, respectively acquire initial images to be detected corresponding to the workpiece to be detected, wherein the initial images to be detected include at least one riveted nut to be detected; Segmenting the initial image to be detected to obtain at least one target image to be detected, wherein each target image to be detected includes a single riveted nut to be detected; Each of the target images to be detected is detected by a riveting point defect detection algorithm to obtain a target detection result, and the target detection result is used to indicate whether each of the riveted nuts to be detected has defects.
2. The method according to claim 1, characterized in that The method of collecting the initial images to be detected corresponding to the workpieces to be detected by using multiple acquisition devices respectively includes: For each of the acquisition devices, obtaining a correspondence between the acquisition device and a preset acquisition viewing angle; Based on the corresponding relationship, obtaining a preset acquisition angle corresponding to the acquisition device from a plurality of preset acquisition angles; The acquisition device is adjusted based on the preset acquisition viewing angle corresponding to the acquisition device, and the adjusted acquisition device is used to acquire the initial image to be detected corresponding to the workpiece to be detected under the preset acquisition viewing angle.
3. The method according to claim 2, characterized in that The method further comprises: After determining that the initial image to be detected is collected, the initial image to be detected is saved in a preset database.
4. The method according to claim 1, characterized in that Before the initial images to be detected corresponding to the workpieces to be detected are respectively acquired by multiple acquisition devices, the method further includes: Obtaining a target placement position corresponding to the workpiece to be detected; Based on the target placement position, the workpiece to be detected is moved so that the workpiece to be detected is moved to the target placement position.
5. The method according to claim 1, characterized in that: The segmenting process of the initial image to be detected to obtain at least one target image to be detected includes: In each of the initial images to be detected, determining a preset area corresponding to each of the riveted nuts to be detected included in the initial images to be detected; Based on at least one of the preset areas, the initial image to be detected is segmented to obtain at least one target image to be detected.
6. The method according to claim 3, characterized in that The method further comprises: In response to the detection end signal, at least one of the to-be-detected images stored in the preset database is cleared.
7. The method according to claim 1, characterized in that The method further comprises: With respect to the target detection result, the target detection result is displayed to the user through a preset interface.
8. An automatic riveting quality detection device, characterized in that: include: An initial image acquisition module for detecting is used to respectively detect initial images corresponding to the workpiece to be detected by using a plurality of acquisition devices, wherein the initial image to be detected includes at least one riveted nut to be detected; A target image acquisition module for detecting is used to segment the initial image to be detected to obtain at least one target image to be detected, wherein each of the target images to be detected includes a single riveted nut to be detected; The target detection result obtaining module is used to detect each of the target images to be detected by using a riveting point defect detection algorithm to obtain a target detection result, and the target detection result is used to indicate whether each of the riveted nuts to be detected has defects.
9. An electronic device, characterized in that: include: one or more processors; a storage device for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors implement the automatic riveting quality detection method according to any one of claims 1 to 7.
10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the automatic riveting quality detection method according to any one of claims 1 to 7 is implemented.
11. A vehicle, characterized in that: include: A processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the computer program, when executed by the processor, implements the automatic riveting quality detection method according to any one of claims 1 to 7.