Vehicle window glue compliance detection method, device, equipment and storage medium

Abstract

The present application provides a vehicle window gluing compliance detection method, device, equipment and storage medium, which relates to the field of image retrieval technology. The method comprises: obtaining video data containing a target vehicle window and a gluing worker, using a pre-trained target detection model to perform target detection on the four corners of the target vehicle window and the cleaning or gluing action of the gluing worker in each frame of the video data, obtaining a target detection result, judging the cleaning or gluing status of each of the four corners of the target vehicle window according to the target detection result of each frame, and marking the corners of the target vehicle window according to the judgment result, so that it is possible to determine whether the current gluing of the target vehicle window is compliant by obtaining the marking results of the four corners of the target vehicle window, thereby effectively avoiding the generation of non-compliant windows, thereby eliminating the need to rework the window gluing and improving work efficiency.

Description

Technical Field

[0001] The present application relates to the field of image detection technology, and in particular to a vehicle window glue compliance detection method, device, equipment and storage medium. Background Art

[0002] With the development of vehicle manufacturing technology, the requirements for vehicle performance are constantly increasing. As an important part of the vehicle, the safety performance of the window glass is the focus of attention. In order to ensure that the window glass is not damaged when the vehicle body collides, adhesive sealants are needed to connect the window frame and the window glass during vehicle manufacturing to play a sealing and buffering role. At present, in some gluing processes, manual participation is required for gluing.

[0003] In order to ensure the quality of vehicle assembly, it is necessary to ensure that the gluing of the windows is compliant, that is, the gluing is complete and not easy to fall off. Therefore, in the prior art, after the gluing of each window is completed, machine vision related technology is usually used to detect whether the gluing of the window is compliant, and the windows with non-compliant gluing are reworked, and the windows with compliant gluing are sent to the next process.

[0004] However, in the above method, if there are many windows with non-compliant glue coating, it will take a lot of time to rework the glue coating on the windows, thus affecting work efficiency. Summary of the invention

[0005] The present application provides a vehicle window glue compliance detection method, device, equipment and storage medium, which are used to avoid the production of vehicle windows with non-compliant glue coating, thereby eliminating the need to rework the vehicle window glue coating and improving work efficiency.

[0006] In a first aspect, the present application provides a vehicle window glue compliance detection method, comprising:

[0007] Obtain video data containing the target car window and the glue applicator;

[0008] Using a pre-trained target detection model to perform target detection on the four corners of the target vehicle window and the cleaning or gluing action of the gluing personnel in each frame of the video data, to obtain a target detection result;

[0009] According to the target detection result of each frame of the image, the cleaning or gluing state of each of the four corners of the target vehicle window is judged, and the corners of the target vehicle window are marked according to the judgment result;

[0010] Obtain the marking results of the four corners of the target vehicle window, and determine whether the gluing of the target vehicle window is currently compliant based on the marking results.

[0011] Optionally, in the method described above, the target detection result of each frame of the image includes target frames of the four corners of the target vehicle window and target frames of the cleaning or gluing action of the gluing person; and judging the cleaning or gluing state of each of the four corners of the target vehicle window according to the target detection result of each frame of the image includes:

[0012] For each frame of image, if the target detection result of the image includes the target frames of the four corners of the target window and the target frames of the cleaning action of the glue applicator, then the cleaning state of each of the four corners of the target window is determined according to the target frames of the four corners of the target window and the target frames of the cleaning action of the glue applicator;

[0013] If the target detection result of the image includes the target frames of the four corners of the target window and the target frames of the gluing action of the glue applicator, the gluing status of each of the four corners of the target window is judged based on the target frames of the four corners of the target window and the target frames of the gluing action of the glue applicator.

[0014] Optionally, in the above method, judging the cleaning state of each of the four corners of the target window according to the target frames of the four corners of the target window and the target frame of the cleaning action of the glue applicator includes:

[0015] Acquire the first coordinate information of the target frame of the four corners of the target vehicle window and the second coordinate information of the target frame of the cleaning action of the glue applicator;

[0016] According to the first coordinate information and the second coordinate information, determining whether the target frame of the cleaning action of the glue applicator partially overlaps with the target frame of any of the four corners of the target vehicle window;

[0017] If so, it is determined that the cleaning status of the corners where the target frame and the target frame of the cleaning action of the glue applicator partially overlap is cleaned, and the cleaning status of the remaining three corners is not cleaned;

[0018] If not, it is determined that the cleaning status of the four corners of the target vehicle window are all not cleaned.

[0019] Optionally, in the above method, marking the corner of the target window according to the judgment result includes:

[0020] According to the judgment result of the cleaning status of the four corners of the target vehicle window, a first mark is added to the corners whose cleaning status is cleaned; the first mark is used to indicate that the corner has been cleaned.

[0021] Optionally, in the method as described above, judging the gluing state of each of the four corners of the target window according to the target frames of the four corners of the target window and the target frames of the gluing action of the gluing worker includes:

[0022] Acquire the first coordinate information of the target frame of the four corners of the target vehicle window and the third coordinate information of the target frame of the gluing action of the gluing worker;

[0023] According to the first coordinate information and the third coordinate information, determining whether a target frame of the gluing action of the gluing worker partially overlaps with a target frame of any of the four corners of the target vehicle window;

[0024] If so, it is determined that the gluing status of the corners where the target frame and the target frame of the gluing action of the gluing person partially overlap is already glued, and the gluing status of the remaining three corners is not glued;

[0025] If not, it is determined that the glue coating states of the four corners of the target vehicle window are all un-glued.

[0026] Optionally, in the above method, marking the corner of the target window according to the judgment result further includes:

[0027] According to the judgment result of the gluing state of the four corners of the target vehicle window, a second mark is added to the corners whose gluing state is already glued; the second mark is used to indicate that the corner has completed gluing.

[0028] Optionally, in the method described above, obtaining the marking results of the four corners of the target vehicle window, and determining whether the gluing of the target vehicle window is currently compliant according to the marking results, includes:

[0029] Obtaining the marking results of the four corners of the target vehicle window, and determining whether each of the four corners of the target vehicle window is currently added with a first mark and a second mark;

[0030] If so, it is determined that the target vehicle window glue coating is currently compliant;

[0031] If not, it is determined that the target vehicle window glue coating is currently not compliant.

[0032] Optionally, in the method as described above, after determining whether the target vehicle window glue coating is currently compliant, the method further includes:

[0033] If it is determined that the target window gluing is currently compliant, the target window is controlled to enter the next process and a first light prompt is given to the user;

[0034] If it is determined that the target window glue coating is not currently compliant, the process returns to the step of obtaining the marking results of the four corners of the target window, and according to the marking results, determining whether the target window glue coating is compliant, and providing a second light prompt to the user.

[0035] In a second aspect, the present application provides a vehicle window glue compliance detection device, comprising:

[0036] An acquisition module is used to acquire video data including the target vehicle window and the glue applicator;

[0037] A detection module, for performing target detection on the four corners of the target vehicle window and the cleaning or gluing action of the gluing personnel in each frame of the video data using a pre-trained target detection model to obtain a target detection result;

[0038] A judgment module, used for judging the cleaning or gluing status of each of the four corners of the target vehicle window according to the target detection result of each frame image, and marking the corners of the target vehicle window according to the judgment result;

[0039] The determination module is used to obtain the marking results of the four corners of the target vehicle window, and determine whether the gluing of the target vehicle window is currently compliant based on the marking results.

[0040] In a third aspect, the present application provides a processor, and a memory communicatively connected to the processor;

[0041] The memory stores computer-executable instructions;

[0042] The processor executes the computer-executable instructions stored in the memory to implement the method according to the first aspect.

[0043] In a fourth aspect, the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer-executable instructions, and when the computer-executable instructions are executed by a processor, they are used to implement the method described in the first aspect.

[0044] The present application provides a vehicle window gluing compliance detection method, device, equipment and storage medium, which obtains video data containing a target vehicle window and a glue applicator, uses a pre-trained target detection model to perform target detection on the four corners of the target vehicle window and the cleaning or gluing action of the glue applicator in each frame image of the video data, and obtains a target detection result. According to the target detection result of each frame image, the cleaning or gluing status of each of the four corners of the target vehicle window is judged, and the corners of the target vehicle window are marked according to the judgment result, the marking results of the four corners of the target vehicle window are obtained, and according to the marking results, it is determined whether the gluing of the target vehicle window is compliant. In the present application, video data of the glue coating personnel coating the target vehicle window is obtained in real time. The target detection results obtained by target detection of the four corners of the target vehicle window in the video data and the cleaning or gluing actions of the glue coating personnel are used to judge the cleaning or gluing status of each corner of the target vehicle window and mark the corners. If the four corners of the target vehicle window have been cleaned and glued, it means that the target vehicle window has completed a week of cleaning and gluing. The target vehicle window that has completed a week of cleaning and gluing has complete glue coating and is not easy to fall off, that is, it is compliant. In other words, whether the current gluing of the target vehicle window is compliant can be determined by obtaining the marking results of the four corners of the target vehicle window, thereby effectively avoiding the generation of windows with non-compliant gluing, thereby eliminating the need to rework the window gluing, and improving work efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0046] Figure 1 A schematic diagram of a system architecture provided for an embodiment of the present application;

[0047] Figure 2 A flow chart of a vehicle window glue compliance detection method provided in an embodiment of the present application;

[0048] Figure 3 A flow chart of another vehicle window glue compliance detection method provided in an embodiment of the present application;

[0049] Figure 4 A flow chart of another vehicle window glue compliance detection method provided in an embodiment of the present application;

[0050] Figure 5 A schematic diagram of the structure of a vehicle window glue compliance detection device provided in an embodiment of the present application;

[0051] Figure 6 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application.

[0052] The above drawings have shown clear embodiments of the present application, which will be described in more detail later. These drawings and text descriptions are not intended to limit the scope of the present application in any way, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0053] Here, exemplary embodiments will be described in detail, and examples thereof are shown in the accompanying drawings. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. Instead, they are only examples of devices and methods consistent with some aspects of the present application.

[0054] Gluing of car window glass is an important step to ensure the safety performance of car windows. In some current gluing processes, manual participation is required for gluing. In order to effectively ensure the assembly quality of vehicles, it is necessary to use windows with compliant glue coating, that is, windows with complete glue coating and not easy to fall off for assembly. Therefore, in the prior art, after the gluing of each car window is completed, machine vision related technology is usually used to detect whether the gluing of the car window is compliant, and the car windows with non-compliant glue coating are reworked, and the windows with compliant glue coating enter the next process.

[0055] However, in the above method, if there are many windows with non-compliant glue coating, it will take a lot of time to rework the glue coating on the windows, thus affecting work efficiency.

[0056] The vehicle window glue compliance detection method, device, equipment and storage medium provided in this application are intended to solve the above technical problems of the prior art.

[0057] The technical solution of the present application and how the technical solution of the present application solves the above-mentioned technical problems are described in detail below with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below in conjunction with the accompanying drawings.

[0058] Figure 1 A schematic diagram of a system architecture provided in an embodiment of the present application is shown as follows: Figure 1 As shown, in Figure 1 The system architecture shown may specifically include a video acquisition device 1 and an intelligent industrial control device 2, wherein the intelligent industrial control device 2 is provided with a vehicle window glue compliance detection device.

[0059] Among them, the video acquisition device 1 is used to collect video data containing the target vehicle window and the glue coating personnel. The vehicle window glue coating compliance detection device can be mounted on the intelligent industrial control equipment 2, which is used to obtain the video data collected by the video acquisition device 1 and execute the vehicle window glue coating compliance detection method provided in the method embodiment of the present application.

[0060] Figure 2 A flow chart of a vehicle window glue compliance detection method provided in an embodiment of the present application, such as Figure 2 As shown, the vehicle window glue compliance detection method provided in this embodiment includes the following steps:

[0061] Step 201: Obtain video data including a target vehicle window and a glue applicator.

[0062] Step 202: Use a pre-trained target detection model to perform target detection on the four corners of the target vehicle window and the cleaning or gluing action of the gluing personnel in each frame of the video data to obtain a target detection result.

[0063] Step 203: According to the target detection result of each frame of image, the cleaning or gluing state of each of the four corners of the target vehicle window is determined, and the corners of the target vehicle window are marked according to the determination result.

[0064] Step 204: Obtain the marking results of the four corners of the target vehicle window, and determine whether the gluing of the target vehicle window is currently compliant based on the marking results.

[0065] It should be noted that the execution subject of the vehicle window glue compliance detection method provided in this embodiment can be a vehicle window glue compliance detection device. In practical applications, the vehicle window glue compliance detection device can be implemented by a computer program, such as application software, etc., or by a medium storing relevant computer programs, such as a USB flash drive, a CD, etc., or by a physical device integrated or installed with relevant computer programs, such as a chip, a board, etc.

[0066] In this embodiment, the vehicle window gluing compliance detection device can first obtain video data containing the target vehicle window and the gluing personnel. Specifically, the video data containing the target vehicle window and the gluing personnel can be collected in real time by a video acquisition device, which can be a network camera. The network camera can be installed in the gluing work area so that the target vehicle window and the gluing personnel are within its visual range.

[0067] After acquiring video data containing the target vehicle window and the glue applicator, the vehicle window glue application compliance detection device can use a pre-trained target detection model to perform target detection on the four corners of the target vehicle window and the glue applicator's cleaning or gluing actions in each frame of the video data to obtain the target detection result.

[0068] The pre-trained target detection model can be obtained by training with training data, and the algorithm used can include but is not limited to a target detection algorithm based on deep learning. In one example, the four corners of the car window and the cleaning or gluing actions of the glue applicator in the sample data can be annotated by an open source tool to obtain training data, and the training data can be used to train the pre-established target detection model, wherein the sample data can be collected by a video acquisition device.

[0069] After obtaining the target detection result, the vehicle window gluing compliance detection device can determine the cleaning or gluing status of each of the four corners of the target vehicle window according to the target detection result of each frame image.

[0070] Based on the above embodiment, in an optional implementation, the target detection result of each frame of image includes the target frames of the four corners of the target window and the target frames of the cleaning or gluing action of the gluing worker. Accordingly, in step 203, judging the cleaning or gluing state of each of the four corners of the target window according to the target detection result of each frame of image includes:

[0071] For each frame of image, if the target detection result of the image includes the target frames of the four corners of the target window and the target frames of the cleaning action of the glue applicator, then the cleaning state of each of the four corners of the target window is determined according to the target frames of the four corners of the target window and the target frames of the cleaning action of the glue applicator;

[0072] If the target detection result of the image includes the target frames of the four corners of the target window and the target frames of the gluing action of the glue applicator, the gluing status of each of the four corners of the target window is judged based on the target frames of the four corners of the target window and the target frames of the gluing action of the glue applicator.

[0073] In this embodiment, since the glue coating personnel perform the cleaning and gluing processes on the vehicle windows separately, the cleaning and gluing actions will not appear simultaneously in the same frame image. Accordingly, for each frame image, in a possible situation, if the image contains the cleaning action of the glue coating personnel, the image is subjected to target detection using a pre-trained target detection model, and the obtained target detection results may include target frames of the four corners of the target vehicle window and the target frames of the cleaning action of the glue coating personnel. The vehicle window gluing compliance detection device can judge the cleaning status of each of the four corners of the target vehicle window based on the target frames of the four corners of the target vehicle window and the target frames of the cleaning action of the glue coating personnel.

[0074] Exemplarily, the vehicle window gluing compliance detection device can judge the cleaning status of each of the four corners of the target window based on the positional relationship between the target frames of the four corners of the target window and the target frames of the gluing personnel's cleaning action. The specific judgment method is not limited in this embodiment.

[0075] In another possible scenario, if the image contains the gluing action of the glue applicator, then after performing target detection on the image using a pre-trained target detection model, the target detection results obtained may include the target frames of the four corners of the target window and the target frames of the glue applicator's gluing action. The window gluing compliance detection device can judge the gluing status of each of the four corners of the target window based on the target frames of the four corners of the target window and the target frames of the glue applicator's gluing action.

[0076] Exemplarily, the vehicle window gluing compliance detection device can judge the gluing status of each of the four corners of the target vehicle window based on the positional relationship between the target frames of the four corners of the target vehicle window and the target frames of the gluing action of the glue applicator. The specific judgment method is not limited in this embodiment.

[0077] In this embodiment, for each frame of image, if the target detection result of the image includes the target frames of the four corners of the target window and the target frame of the glue applicator's cleaning action, the cleaning status of each of the four corners of the target window is judged according to the target frames of the four corners of the target window and the target frame of the glue applicator's cleaning action; if the target detection result of the image includes the target frames of the four corners of the target window and the target frame of the glue applicator's gluing action, the gluing status of each of the four corners of the target window is judged according to the target frames of the four corners of the target window and the target frame of the glue applicator's gluing action. Since the cleaning status of each of the four corners of the target window is judged based on the target frames of the four corners of the target window and the target frame of the glue applicator's cleaning action at the same time, the cleaning status of each of the four corners of the target window can be judged more accurately. Similarly, when judging the gluing status of each of the four corners of the target window, it is judged based on the target frames of the four corners of the target window and the target frames of the gluing action of the glue applicator, so the gluing status of each of the four corners of the target window can be judged more accurately.

[0078] After determining the cleaning or gluing status of each of the four corners of the target vehicle window, the vehicle window gluing compliance detection device can mark the corners of the target vehicle window according to the determination result. Specifically, in one example, if it is determined that any corner of the target vehicle window has completed cleaning or gluing, it can be marked, wherein the cleaning status and the gluing status can correspond to different marks respectively, and the specific marking method is not limited in this embodiment.

[0079] Accordingly, the vehicle window gluing compliance detection device can obtain the marking results of the four corners of the target vehicle window, and determine whether the target vehicle window gluing is currently compliant based on the marking results. Exemplarily, the vehicle window gluing compliance detection device can determine whether the target vehicle window gluing is currently compliant based on whether each of the four corners of the target vehicle window has a mark corresponding to the cleaning state and the gluing state added. The specific determination method is not limited in this embodiment.

[0080] The vehicle window gluing compliance detection method provided in the present embodiment obtains video data containing a target vehicle window and a glue applicator, and uses a pre-trained target detection model to perform target detection on the four corners of the target vehicle window and the cleaning or gluing actions of the glue applicator in each frame image of the video data to obtain a target detection result, and based on the target detection result of each frame image, determines the cleaning or gluing status of each of the four corners of the target vehicle window, and marks the corners of the target vehicle window based on the determination result, obtains the marking results of the four corners of the target vehicle window, and determines whether the gluing of the target vehicle window is compliant based on the marking results. In the present application, video data of the glue coating personnel coating the target vehicle window is obtained in real time. The target detection results obtained by target detection of the four corners of the target vehicle window in the video data and the cleaning or gluing actions of the glue coating personnel are used to judge the cleaning or gluing status of each corner of the target vehicle window and mark the corners. If the four corners of the target vehicle window have been cleaned and glued, it means that the target vehicle window has completed a week of cleaning and gluing. The target vehicle window that has completed a week of cleaning and gluing has complete glue coating and is not easy to fall off, that is, it is compliant. In other words, whether the current gluing of the target vehicle window is compliant can be determined by obtaining the marking results of the four corners of the target vehicle window, thereby effectively avoiding the generation of windows with non-compliant gluing, thereby eliminating the need to rework the window gluing, and improving work efficiency.

[0081] Figure 3 A flowchart of another vehicle window glue compliance detection method provided in an embodiment of the present application is as follows: Figure 3 As shown, on the basis of the above embodiment, in the vehicle window gluing compliance detection method provided in this embodiment, the cleaning state of each of the four corners of the target vehicle window is judged according to the target frames of the four corners of the target vehicle window and the target frames of the cleaning action of the gluing personnel, and specifically includes the following steps:

[0082] Step 301: Obtain first coordinate information of a target frame of four corners of the target vehicle window and second coordinate information of a target frame of the cleaning action of the glue applicator.

[0083] Step 302: According to the first coordinate information and the second coordinate information, it is determined whether the target frame of the cleaning action of the glue applicator partially overlaps with the target frame of any of the four corners of the target vehicle window.

[0084] Step 303: If yes, then determine that the cleaning status of the corners where the target frame and the target frame of the cleaning action of the glue applicator partially overlap is cleaned, and the cleaning status of the remaining three corners is not cleaned.

[0085] Step 304: If not, determine that the cleaning status of the four corners of the target vehicle window are all not cleaned.

[0086] In this embodiment, the vehicle window gluing compliance detection device can obtain the first coordinate information of the target frame of the four corners of the target vehicle window and the second coordinate information of the target frame of the gluing worker's cleaning action. Specifically, the first coordinate information of the target frame of the four corners of the target vehicle window may include the coordinate information of the four vertices of the target frame of each of the four corners of the target vehicle window. Correspondingly, the second coordinate information of the target frame of the gluing worker's cleaning action may include the coordinate information of the four vertices of the target frame of the cleaning action.

[0087] After obtaining the first coordinate information and the second coordinate information, the vehicle window gluing compliance detection device can determine whether the target frame of the gluing personnel's cleaning action partially overlaps with the target frame of any of the four corners of the target vehicle window based on the first coordinate information and the second coordinate information.

[0088] For example, the first coordinate information of the target box at the four corners of the target window may include the coordinate information of the four vertices of the target box at the first corner of the target window, such as (0, 25), (4, 25), (0, 21), (4, 21), the coordinate information of the four vertices of the target box at the second corner of the target window, such as (28, 25), (32, 25), (28, 21), (32, 21), the coordinate information of the four vertices of the target box at the third corner of the target window, such as (0, 4), (4, 4), (0, 0), (4, 0), and the coordinate information of the four vertices of the target box at the fourth corner of the target window, such as (28, 4), (32, 4), (28, 0), (32, 0).

[0089] Accordingly, the second coordinate information of the target frame of the gluing worker's cleaning action may include the coordinate information of the four vertices of the cleaning action target frame. In one example, the coordinate information of the four vertices may be (1, 24), (5, 24), (1, 20), (5, 20), and the vehicle window gluing compliance detection device may determine that the target frame of the gluing worker's cleaning action partially overlaps with the target frame of the first corner of the target vehicle window. In another example, the coordinate information of the four vertices may be (5, 24), (9, 24), (5, 20), (9, 20), and the vehicle window gluing compliance detection device may determine that the target frame of the gluing worker's cleaning action does not partially overlap with the target frame of any of the four corners of the target vehicle window.

[0090] In one possible scenario, if the target frame of the glue coating worker's cleaning action partially overlaps with the target frame of any of the four corners of the target vehicle window, the vehicle window gluing compliance detection device can determine that the cleaning status of the corner where the target frame partially overlaps with the target frame of the glue coating worker's cleaning action is cleaned, and the cleaning status of the other three corners is uncleaned.

[0091] Continuing with the above example, if the target frame of the gluing worker's cleaning action partially overlaps with the target frame of the first corner of the target window, the window gluing compliance detection device can determine that the cleaning status of the first corner is cleaned, and the cleaning status of the other three corners is not cleaned.

[0092] In another possible situation, if the target frame of the gluing worker's cleaning action does not partially overlap with the target frame of any of the four corners of the target window, the window gluing compliance detection device can determine that the cleaning status of the four corners of the target window are all uncleaned.

[0093] The window gluing compliance detection method provided in the present embodiment obtains the first coordinate information of the target frames of the four corners of the target window and the second coordinate information of the target frame of the gluing personnel's cleaning action, and judges whether the target frame of the gluing personnel's cleaning action partially overlaps with the target frame of any of the four corners of the target window based on the first coordinate information and the second coordinate information, and then judges the cleaning status of each of the four corners of the target window. If the target frame of the cleaning action partially overlaps with the target frame of the window corner, it indicates that the cleaning action occurs at the corresponding window corner, so that the cleaning status of each corner of the target window can be accurately judged, laying the foundation for subsequently determining whether the target window is compliant.

[0094] Based on the above embodiment, in an optional implementation, in step 203, the corners of the target window are marked according to the judgment result, including: according to the judgment result of the cleaning status of the four corners of the target window, a first mark is added to the corner whose cleaning status is cleaned; the first mark is used to indicate that the corner has been cleaned.

[0095] Specifically, after determining the cleaning status of each of the four corners of the target vehicle window, the vehicle window glue compliance detection device can add a first mark to the corners whose cleaning status is cleaned according to the determination result of the cleaning status of the four corners of the target vehicle window. The first mark can be used to indicate that the corner has been cleaned.

[0096] The first mark may include but is not limited to a digital mark, a symbol mark or a text mark.

[0097] Exemplarily, if the first mark is a digital mark, the vehicle window glue compliance detection device can add a digital mark, such as 1, to the corner whose cleaning status is cleaned. Correspondingly, if a digital mark 1 is added to a corner of the target vehicle window, it indicates that the corner has been cleaned.

[0098] In this embodiment, the corners of the target window are marked according to the judgment result, including: according to the judgment result of the cleaning status of the four corners of the target window, a first mark is added to the corner whose cleaning status is cleaned; the first mark is used to indicate that the corner has been cleaned, so as to facilitate the subsequent determination of whether the target window is compliant.

[0099] Figure 4 A flowchart of another vehicle window glue compliance detection method provided in an embodiment of the present application, such as Figure 4 As shown, on the basis of the above embodiment, in the vehicle window gluing compliance detection method provided in this embodiment, the gluing state of each of the four corners of the target vehicle window is judged according to the target frames of the four corners of the target vehicle window and the target frames of the gluing action of the gluing personnel, and specifically includes the following steps:

[0100] Step 401: Acquire first coordinate information of target frames of four corners of the target vehicle window and third coordinate information of the target frame of the gluing action of the gluing worker.

[0101] Step 402: judging, based on the first coordinate information and the third coordinate information, whether the target frame of the gluing action of the gluing worker partially overlaps with the target frame of any of the four corners of the target vehicle window.

[0102] Step 403: If yes, determine that the target frame and the target frame of the gluing action of the gluing person have a partially overlapping gluing state at the corner as already glued, and the gluing state at the other three corners as not glued.

[0103] Step 404: If not, determine that the glue coating status of the four corners of the target vehicle window is not glued.

[0104] In this embodiment, the vehicle window gluing compliance detection device can obtain the first coordinate information of the target frame of the four corners of the target vehicle window and the third coordinate information of the target frame of the gluing action of the gluing person. Specifically, the first coordinate information of the target frame of the four corners of the target vehicle window may include the coordinate information of the four vertices of the target frame of each of the four corners of the target vehicle window. Correspondingly, the third coordinate information of the target frame of the gluing action of the gluing person may include the coordinate information of the four vertices of the target frame of the gluing action.

[0105] After obtaining the first coordinate information and the third coordinate information, the vehicle window gluing compliance detection device can determine whether the target frame of the gluing action of the glue applicator partially overlaps with the target frame of any of the four corners of the target vehicle window based on the first coordinate information and the third coordinate information.

[0106] For example, the first coordinate information of the target box at the four corners of the target window may include the coordinate information of the four vertices of the target box at the first corner of the target window, such as (0, 25), (4, 25), (0, 21), (4, 21), the coordinate information of the four vertices of the target box at the second corner of the target window, such as (28, 25), (32, 25), (28, 21), (32, 21), the coordinate information of the four vertices of the target box at the third corner of the target window, such as (0, 4), (4, 4), (0, 0), (4, 0), and the coordinate information of the four vertices of the target box at the fourth corner of the target window, such as (28, 4), (32, 4), (28, 0), (32, 0).

[0107] Accordingly, the third coordinate information of the target frame of the gluing action of the glue applicator may include the coordinate information of the four vertices of the target frame of the gluing action. In one example, the coordinate information of the four vertices may be (22, 24), (30, 24), (22, 20), (30, 20), and the vehicle window gluing compliance detection device may determine that the target frame of the gluing action of the glue applicator partially overlaps with the target frame of the second corner of the target vehicle window. In another example, the coordinate information of the four vertices may be (5, 24), (9, 24), (5, 20), (9, 20), and the vehicle window gluing compliance detection device may determine that the target frame of the gluing action of the glue applicator does not partially overlap with the target frame of any of the four corners of the target vehicle window.

[0108] In one possible scenario, if the target frame of the glue coating action of the glue coating person partially overlaps with the target frame of any of the four corners of the target vehicle window, the vehicle window gluing compliance detection device can determine that the gluing status of the corner where the target frame partially overlaps with the target frame of the glue coating action of the glue coating person is glued, and the gluing status of the other three corners is un-glued.

[0109] Continuing with the above example, if the target frame of the gluing action of the glue applicator partially overlaps with the target frame of the first corner of the target vehicle window, the vehicle window gluing compliance detection device can determine that the gluing status of the first corner is glued, and the gluing status of the other three corners is un-glued.

[0110] In another possible situation, if the target frame of the gluing action of the glue applicator does not partially overlap with the target frame of any of the four corners of the target window, the window gluing compliance detection device can determine that the gluing status of the four corners of the target window is not glued.

[0111] The vehicle window gluing compliance detection method provided in the present embodiment obtains the first coordinate information of the target frames of the four corners of the target vehicle window and the third coordinate information of the target frame of the gluing action of the glue applicator, and judges whether the target frame of the gluing action of the glue applicator partially overlaps with the target frame of any of the four corners of the target vehicle window based on the first coordinate information and the third coordinate information, and then judges the gluing status of each of the four corners of the target vehicle window. If the target frame of the gluing action partially overlaps with the target frame of the window corner, it indicates that the gluing action occurs at the corresponding window corner, so that the gluing status of each corner of the target vehicle window can be accurately judged, laying the foundation for subsequently determining whether the target vehicle window is compliant.

[0112] Based on the above embodiment, in an optional implementation, in step 203, the marking of the corners of the target window according to the judgment result also includes: adding a second mark to the corners whose gluing state is glued according to the judgment result of the gluing state of the four corners of the target window; the second mark is used to indicate that the corner has been glued.

[0113] Specifically, after determining the glue coating status of each of the four corners of the target vehicle window, the vehicle window glue coating compliance detection device can add a second mark to the corners whose glue coating status is glued according to the determination result of the glue coating status of the four corners of the target vehicle window, which can be used to characterize that the corners have completed gluing.

[0114] The second mark is different from the first mark, and may include but is not limited to a digital mark, a symbol mark or a text mark.

[0115] Exemplarily, if the second mark is a digital mark, the vehicle window gluing compliance detection device can add a digital mark, such as 2, to the corners whose gluing status is glued. Accordingly, if a digital mark 2 is added to a corner of the target vehicle window, it indicates that the corner has been glued.

[0116] In this embodiment, marking the corners of the target vehicle window according to the judgment result also includes: adding a second mark to the corners whose gluing state is already glued according to the judgment result of the gluing state of the four corners of the target vehicle window; the second mark is used to indicate that the corner has been glued. This facilitates the subsequent determination of whether the target vehicle window is compliant.

[0117] Based on the above embodiment, in an optional implementation, step 204 includes: obtaining the marking results of the four corners of the target vehicle window, and determining whether each of the four corners of the target vehicle window is currently added with a first mark and a second mark; if so, determining that the gluing of the target vehicle window is currently compliant; if not, determining that the gluing of the target vehicle window is currently not compliant.

[0118] Specifically, the vehicle window glue compliance detection device can obtain the marking results of the four corners of the target vehicle window, and determine whether each of the four corners of the target vehicle window is currently added with a first mark and a second mark. For example, the first mark can be a digital mark 1, and correspondingly, the second mark can be a digital mark 2.

[0119] In one possible scenario, if each of the four corners of the target vehicle window is currently added with a first mark and a second mark, it indicates that each corner of the target vehicle window has currently completed cleaning and gluing, that is, the target vehicle window has currently completed a week of cleaning and gluing, then the vehicle window gluing compliance detection device can determine that the target vehicle window gluing is currently compliant.

[0120] In another possible situation, if any of the four corners of the target vehicle window has no first mark or second mark added to it, it indicates that any of the four corners of the target vehicle window has not completed cleaning or gluing, that is, the target vehicle window has not completed a week of cleaning or gluing. The vehicle window gluing compliance detection device can determine that the target vehicle window gluing is currently not compliant.

[0121] The vehicle window glue coating compliance detection method provided in this embodiment can accurately determine whether the target vehicle window glue coating is currently compliant by judging whether each of the four corners of the target vehicle window currently has a first mark and a second mark added. The determination method is convenient and quick.

[0122] Based on any of the above embodiments, in an optional implementation manner, after determining whether the target window glue coating is currently compliant, the method further includes: if it is determined that the target window glue coating is currently compliant, controlling the target window to enter the next process, and providing a first light prompt to the user; if it is determined that the target window glue coating is currently not compliant, returning to execute the step of obtaining the marking results of the four corners of the target window, and determining whether the target window glue coating is currently compliant based on the marking results, and providing a second light prompt to the user.

[0123] In this embodiment, after determining whether the target vehicle window glue coating is currently compliant, the vehicle window glue coating compliance detection device can perform corresponding subsequent processing according to different situations.

[0124] In one possible scenario, if it is determined that the target vehicle window gluing is currently compliant, the vehicle window gluing compliance detection device can control the target vehicle window to enter the next process to perform subsequent assembly processing on the target vehicle window. In addition, the vehicle window gluing compliance detection device can also control a light emitting device, such as an LED indicator light, to provide a first light prompt to the user. Exemplarily, the first light can be a green light.

[0125] In another possible scenario, if it is determined that the target vehicle window glue coating is not currently compliant, the vehicle window glue coating compliance detection device may return to the step of obtaining the marking results of the four corners of the target vehicle window, and determine whether the target vehicle window glue coating is currently compliant based on the marking results. In addition, the vehicle window glue coating compliance detection device may also control a light emitting device, such as an LED indicator light, to provide a second light prompt to the user. Exemplarily, the second light may be a yellow light.

[0126] In addition, it should be noted that in addition to being directly mounted in intelligent industrial control equipment, in a possible implementation, the vehicle window glue coating compliance detection device can also be mounted in a cloud server. Accordingly, the vehicle window glue coating compliance detection device can be used to execute the vehicle window glue coating compliance detection method provided in any of the above embodiments of the present application, and send the current glue coating compliance detection result of the target vehicle window to the terminal industrial control computer, so that the terminal industrial control computer performs corresponding processing according to the current glue coating compliance detection result of the target vehicle window.

[0127] In one possible scenario, if it is determined that the target window glue coating is currently compliant, the window glue coating compliance detection device can send a first detection result that the target window glue coating is currently compliant to the terminal industrial computer, so that the terminal industrial computer controls the target window to enter the next process according to the first detection result, and provides a first light prompt to the user.

[0128] In another possible situation, if it is determined that the target window glue coating is not currently compliant, the window glue coating compliance detection device can return to the step of obtaining the marking results of the four corners of the target window, and determine whether the target window glue coating is currently compliant based on the marking results, and send the second detection result that the target window glue coating is not currently compliant to the terminal industrial computer, so that the terminal industrial computer can provide a second light prompt to the user based on the second detection result.

[0129] The vehicle window gluing compliance detection method provided in this embodiment controls whether the target vehicle window enters the next process according to the current different gluing compliance detection results of the target vehicle window, and provides different light prompts to the user, so that the user can intuitively understand the current gluing status of the target vehicle window, thereby effectively avoiding the generation of vehicle windows with non-compliant gluing.

[0130] Figure 5 A schematic diagram of the structure of a vehicle window glue compliance detection device provided in an embodiment of the present application, such as Figure 5 As shown, the vehicle window gluing compliance detection device provided in this embodiment includes: an acquisition module 51, a detection module 52, a judgment module 53 and a determination module 54. Among them, the acquisition module 51 is used to obtain video data containing a target vehicle window and a gluing person. The detection module 52 is used to use a pre-trained target detection model to perform target detection on the four corners of the target vehicle window in each frame image of the video data and the cleaning or gluing action of the gluing person to obtain a target detection result. The judgment module 53 is used to judge the cleaning or gluing status of each of the four corners of the target vehicle window according to the target detection result of each frame image, and mark the corners of the target vehicle window according to the judgment result. The determination module 54 is used to obtain the marking results of the four corners of the target vehicle window, and determine whether the gluing of the target vehicle window is currently compliant according to the marking results.

[0131] In an optional embodiment, the target detection result of each frame of the image includes the target frames of the four corners of the target window and the target frames of the gluing person's cleaning or gluing action. The judgment module 53 is specifically used for judging the cleaning state of each of the four corners of the target window according to the target frames of the four corners of the target window and the target frames of the gluing person's cleaning action for each frame of the image, if the target detection result of the image includes the target frames of the four corners of the target window and the target frames of the gluing person's gluing action; if the target detection result of the image includes the target frames of the four corners of the target window and the target frames of the gluing person's gluing action, judging the gluing state of each of the four corners of the target window according to the target frames of the four corners of the target window and the target frames of the gluing person's gluing action.

[0132] In an optional embodiment, the judgment module 53 is further specifically used to obtain the first coordinate information of the target frames of the four corners of the target window and the second coordinate information of the target frame of the cleaning action of the glue applicator; based on the first coordinate information and the second coordinate information, it is judged whether the target frame of the cleaning action of the glue applicator partially overlaps with the target frame of any of the four corners of the target window; if so, the cleaning status of the corner where the target frame partially overlaps with the target frame of the cleaning action of the glue applicator is judged to be cleaned, and the cleaning status of the other three corners is not cleaned; if not, it is judged that the cleaning status of the four corners of the target window are all not cleaned.

[0133] In an optional embodiment, the judgment module 53 includes a marking unit for adding a first mark to the corners whose cleaning status is cleaned according to the judgment result of the cleaning status of the four corners of the target vehicle window; the first mark is used to indicate that the corner has been cleaned.

[0134] In an optional embodiment, the judgment module 53 is further specifically used to obtain the first coordinate information of the target frames of the four corners of the target vehicle window and the third coordinate information of the target frame of the gluing action of the glue applicator; based on the first coordinate information and the third coordinate information, it is judged whether the target frame of the gluing action of the glue applicator partially overlaps with the target frame of any of the four corners of the target vehicle window; if so, the gluing status of the corner where the target frame partially overlaps with the target frame of the gluing action of the glue applicator is judged to be glued, and the gluing status of the other three corners is un-glued; if not, it is judged that the gluing status of the four corners of the target vehicle window is all un-glued.

[0135] In an optional embodiment, the marking unit is further used to add a second mark to the corners whose gluing status is already glued according to the judgment result of the gluing status of the four corners of the target vehicle window; the second mark is used to indicate that the corner has been glued.

[0136] In an optional implementation, the determination module 54 is specifically used to obtain the marking results of the four corners of the target vehicle window, and determine whether each of the four corners of the target vehicle window is currently added with the first mark and the second mark; if so, it is determined that the gluing of the target vehicle window is currently compliant; if not, it is determined that the gluing of the target vehicle window is currently not compliant.

[0137] In an optional embodiment, the device further includes a control module and a return module. The control module is used to control the target window to enter the next process if it is determined that the gluing of the target window is currently compliant, and to provide a first light prompt to the user. The return module is used to return to the step of obtaining the marking results of the four corners of the target window if it is determined that the gluing of the target window is currently not compliant, and to determine whether the gluing of the target window is currently compliant based on the marking results, and to provide a second light prompt to the user.

[0138] It should be noted that the technical solutions and effects implemented by the vehicle window glue compliance detection device provided in this embodiment can be found in the relevant contents of the aforementioned method embodiments, and will not be repeated here.

[0139] Figure 6 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application, such as Figure 6 As shown, the present application also provides an electronic device 600 , including: a memory 601 and a processor 602 .

[0140] The memory 601 is used to store programs. Specifically, the program may include program codes, and the program codes include computer-executable instructions. The memory 601 may include a high-speed RAM memory, and may also include a non-volatile memory, such as at least one disk memory.

[0141] The processor 602 is used to execute the program stored in the memory 601 .

[0142] The computer program is stored in the memory 601 and is configured to be executed by the processor 602 to implement the vehicle window glue compliance detection method provided in any embodiment of the present application. The relevant description can be understood by referring to the relevant descriptions and effects corresponding to the steps in the accompanying drawings, and no further elaboration is given here.

[0143] In this embodiment, the memory 601 and the processor 602 are connected via a bus. The bus may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 6 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0144] An embodiment of the present application also provides a computer-readable storage medium on which a computer program is stored. The computer program is executed by a processor to implement the vehicle window glue compliance detection method provided in any embodiment of the present application.

[0145] An embodiment of the present application also provides a computer program product, including a computer program, which, when executed by a processor, implements a vehicle window glue coating compliance detection method provided by any embodiment of the present application.

[0146] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of modules is only a logical function division. There may be other division methods in actual implementation, such as multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or modules, which can be electrical, mechanical or other forms.

[0147] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical modules, that is, they may be located in one place or distributed on multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0148] In addition, each functional module in each embodiment of the present application can be integrated into one processing module, or each module can exist physically separately, or two or more modules can be integrated into one module. The above integrated modules can be implemented in the form of hardware or in the form of hardware plus software functional modules.

[0149] The program code for implementing the method of the present application can be written in any combination of one or more programming languages. These program codes can be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable vehicle window glue compliance detection device, so that when the program code is executed by the processor or controller, the functions / operations specified in the flow chart and / or block diagram are implemented. The program code can be executed entirely on the machine, partially on the machine, partially on the machine as a stand-alone software package and partially on a remote machine, or entirely on a remote machine or server.

[0150] In the context of the present application, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0151] In addition, although each operation is described in a specific order, this should be understood as requiring such operation to be performed in the specific order shown or in a sequential order, or requiring that all illustrated operations should be performed to obtain desired results. Under certain circumstances, multitasking and parallel processing may be advantageous. Similarly, although some specific implementation details are included in the above discussion, these should not be interpreted as limiting the scope of the application. Some features described in the context of a separate embodiment can also be implemented in a single implementation in combination. On the contrary, the various features described in the context of a single implementation can also be implemented in multiple implementations individually or in any suitable sub-combination mode.

[0152] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the invention disclosed herein. The present application is intended to cover any modification, use or adaptation of the present application, which follows the general principles of the present application and includes common knowledge or customary techniques in the art that are not disclosed in the present application. The specification and examples are intended to be exemplary only, and the true scope and spirit of the present application are indicated by the following claims.

[0153] It should be understood that the present application is not limited to the precise structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present application is limited only by the appended claims.

Claims

1. A vehicle window glue compliance detection method, characterized in that: include: Obtain video data containing the target car window and the glue applicator; Using a pre-trained target detection model to perform target detection on the four corners of the target vehicle window and the cleaning or gluing action of the gluing personnel in each frame of the video data, to obtain a target detection result; According to the target detection result of each frame of the image, the cleaning or gluing state of each of the four corners of the target vehicle window is judged, and the corners of the target vehicle window are marked according to the judgment result; Obtaining the marking results of the four corners of the target vehicle window, and determining whether the gluing of the target vehicle window is currently compliant according to the marking results; The target detection result of each frame of the image includes the target frames of the four corners of the target vehicle window and the target frame of the cleaning or gluing action of the gluing person; The step of judging the cleaning or gluing state of each of the four corners of the target vehicle window according to the target detection result of each frame of the image includes: For each frame of image, if the target detection result of the image includes the target frames of the four corners of the target window and the target frames of the cleaning action of the glue applicator, then the cleaning state of each of the four corners of the target window is determined according to the target frames of the four corners of the target window and the target frames of the cleaning action of the glue applicator; If the target detection result of the image includes the target frames of the four corners of the target window and the target frames of the gluing action of the gluing worker, then judging the gluing state of each of the four corners of the target window according to the target frames of the four corners of the target window and the target frames of the gluing action of the gluing worker; The step of judging the cleaning state of each of the four corners of the target window according to the target frames of the four corners of the target window and the target frame of the cleaning action of the glue applicator includes: Acquire the first coordinate information of the target frame of the four corners of the target vehicle window and the second coordinate information of the target frame of the cleaning action of the glue applicator; According to the first coordinate information and the second coordinate information, determining whether the target frame of the cleaning action of the glue applicator partially overlaps with the target frame of any of the four corners of the target vehicle window; If so, it is determined that the cleaning status of the corners where the target frame and the target frame of the cleaning action of the glue applicator partially overlap is cleaned, and the cleaning status of the remaining three corners is not cleaned; If not, it is determined that the cleaning status of the four corners of the target vehicle window are all not cleaned; The step of judging the gluing state of each of the four corners of the target window according to the target frames of the four corners of the target window and the target frames of the gluing action of the gluing worker includes: Acquire the first coordinate information of the target frame of the four corners of the target vehicle window and the third coordinate information of the target frame of the gluing action of the gluing worker; According to the first coordinate information and the third coordinate information, determining whether a target frame of the gluing action of the gluing worker partially overlaps with a target frame of any of the four corners of the target vehicle window; If so, it is determined that the gluing status of the corners where the target frame and the target frame of the gluing action of the gluing person partially overlap is already glued, and the gluing status of the remaining three corners is not glued; If not, it is determined that the glue coating states of the four corners of the target vehicle window are all un-glued.

2. The method according to claim 1, characterized in that: The step of marking the corner of the target vehicle window according to the judgment result includes: According to the judgment result of the cleaning status of the four corners of the target vehicle window, a first mark is added to the corners whose cleaning status is cleaned; the first mark is used to indicate that the corner has been cleaned.

3. The method according to claim 1, characterized in that The step of marking the corner of the target vehicle window according to the judgment result further includes: According to the judgment result of the gluing state of the four corners of the target vehicle window, a second mark is added to the corners whose gluing state is already glued; the second mark is used to indicate that the corner has completed gluing.

4. The method according to claim 3, characterized in that The obtaining of the marking results of the four corners of the target vehicle window and determining whether the gluing of the target vehicle window is currently compliant according to the marking results include: Obtaining the marking results of the four corners of the target vehicle window, and determining whether each of the four corners of the target vehicle window is currently added with a first mark and a second mark; If so, it is determined that the target vehicle window glue coating is currently compliant; If not, it is determined that the target vehicle window glue coating is currently not compliant.

5. The method according to any one of claims 1 to 4, characterized in that: After determining whether the target vehicle window glue coating is currently compliant, the method further includes: If it is determined that the target window gluing is currently compliant, the target window is controlled to enter the next process and a first light prompt is given to the user; If it is determined that the target window glue coating is not currently compliant, return to execute the step of obtaining the marking results of the four corners of the target window, and determine whether the target window glue coating is currently compliant based on the marking results, and provide a second light prompt to the user.

6. A vehicle window glue compliance detection device, characterized in that: include: An acquisition module is used to acquire video data including the target vehicle window and the glue applicator; A detection module, for performing target detection on the four corners of the target vehicle window and the cleaning or gluing action of the gluing personnel in each frame of the video data using a pre-trained target detection model to obtain a target detection result; A judgment module, used for judging the cleaning or gluing status of each of the four corners of the target vehicle window according to the target detection result of each frame image, and marking the corners of the target vehicle window according to the judgment result; A determination module, used to obtain the marking results of the four corners of the target vehicle window, and determine whether the gluing of the target vehicle window is currently compliant according to the marking results; The target detection result of each frame of the image includes the target frames of the four corners of the target vehicle window and the target frame of the cleaning or gluing action of the gluing person; The judgment module is specifically configured to, for each frame of image, if the target detection result of the image includes the target frames of the four corners of the target window and the target frames of the cleaning action of the glue applicator, judge the cleaning state of each of the four corners of the target window according to the target frames of the four corners of the target window and the target frames of the cleaning action of the glue applicator; If the target detection result of the image includes the target frames of the four corners of the target window and the target frames of the gluing action of the gluing worker, then judging the gluing state of each of the four corners of the target window according to the target frames of the four corners of the target window and the target frames of the gluing action of the gluing worker; The judgment module is further specifically used to obtain the first coordinate information of the target frame of the four corners of the target window and the second coordinate information of the target frame of the cleaning action of the glue applicator; According to the first coordinate information and the second coordinate information, determining whether the target frame of the cleaning action of the glue applicator partially overlaps with the target frame of any of the four corners of the target vehicle window; If so, it is determined that the cleaning status of the corners where the target frame and the target frame of the cleaning action of the glue applicator partially overlap is cleaned, and the cleaning status of the remaining three corners is not cleaned; If not, it is determined that the cleaning status of the four corners of the target vehicle window are all not cleaned; The judgment module is further specifically used to obtain first coordinate information of target frames of four corners of the target vehicle window and third coordinate information of the target frame of the gluing action of the gluing worker; According to the first coordinate information and the third coordinate information, determining whether a target frame of the gluing action of the gluing worker partially overlaps with a target frame of any of the four corners of the target vehicle window; If so, it is determined that the gluing status of the corners where the target frame and the target frame of the gluing action of the gluing person partially overlap is already glued, and the gluing status of the remaining three corners is not glued; If not, it is determined that the glue coating states of the four corners of the target vehicle window are all un-glued.

7. An electronic device comprising: A processor, and a memory communicatively connected to the processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory to implement the method according to any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, which are used to implement the method according to any one of claims 1 to 5 when executed by a processor.

Images