Dispensing detection method, detection system and electronic device

Abstract

The application discloses a dispensing detection method, a detection system and an electronic device, and relates to the technical field of dispensing testing. The dispensing detection method comprises the following steps: converting depth map data into a point cloud data set. The point cloud data set is divided into vertical point clouds and horizontal point clouds according to the normal vectors of the cloud data set. The horizontal point clouds are subjected to multi-plane segmentation, and the largest plane in the multi-plane is taken as a target plane. The target plane is fitted to obtain a plane equation. The plane equation is visualized, and a reference frame and a to-be-tested frame are framed. A height threshold range is obtained according to the reference frame, and the number of detection points of the to-be-tested frame that meet the height threshold range is obtained. When the number of detection points meets a point number threshold range, it is determined that the to-be-tested frame is successfully dispensed. According to the scheme of the application, whether the dispensing is successful is determined by detecting whether the number of point clouds that meet the height threshold range exists in the to-be-tested panel, so that the dispensing condition of the to-be-tested panel can be more accurately detected, and the production quality of the electronic device is improved.

Description

Technical Field

[0001] The present application relates to the field of dispensing testing technology, and in particular to a dispensing detection method, a detection system and an electronic device. Background Art

[0002] During the assembly of electronic devices, dispensing equipment is often required to apply glue to certain areas of the circuit board to facilitate the attachment of electronic components. Due to the adhesive's viscous properties, the dispensing valve can pull away the glue during dispensing. However, even though the glue on the circuit board is pulled away by the dispensing valve, residual glue remains on the board.

[0003] Currently, 2D dispensing inspection systems are commonly used to detect whether dispensing is successful. However, these systems typically determine whether dispensing is successful based on whether the dispensing trace matches a 2D template. This means that as long as the dispensing trace on the circuit board matches the 2D template, dispensing is considered successful. This results in many circuit boards being judged as successful despite only residual glue remaining, significantly impacting the production quality of electronic equipment.

[0004] Therefore, a new solution is urgently needed to solve the above problems. Summary of the Invention

[0005] The present application provides a dispensing detection method, a detection system, and an electronic device. By acquiring the depth map data of the panel to be tested and processing the depth map data to obtain the point cloud height of the panel to be tested, and then determining whether the dispensing of the panel to be tested is successful based on the number of point clouds that meet the height threshold range, the dispensing condition of the panel to be tested can be detected more accurately, thereby improving the production quality of electronic equipment.

[0006] To achieve the above objectives, this application adopts the following technical solutions:

[0007] In a first aspect, a dispensing detection method is provided, comprising: obtaining depth map data of a panel to be tested, and converting the depth map data into a point cloud dataset. Obtaining a normal vector of the point cloud dataset, and segmenting the point cloud dataset into a vertical point cloud and a horizontal point cloud according to the normal vector. Performing multi-plane segmentation on the horizontal point cloud, and taking the largest plane among the multi-planes as the target plane. Fitting the target plane to obtain a plane equation. Visualizing the plane equation, and selecting a reference frame and a frame to be tested. Obtaining a height threshold range based on the reference frame, and obtaining the number of detection points of the frame to be tested that meet the height threshold range. When the number of detection points meets the point number threshold range, it is determined that the dispensing of the frame to be tested is successful.

[0008] In the embodiments of the present application, first, depth map data of the to-be-tested panel is acquired, and the depth map data is converted into a point cloud data set. Then, a normal vector of the point cloud data set is acquired, and the point cloud data set is segmented into vertical point clouds and horizontal point clouds according to the normal vector. Then, the horizontal point clouds are subjected to multi-plane segmentation, and the maximum plane in the multi-planes is taken as a target plane. Then, the target plane is fitted to obtain a plane equation. Then, the plane equation is visualized, and a reference frame and a to-be-tested frame are framed. Then, a height threshold range is acquired according to the reference frame, and a number of detection points that meet the height threshold range is acquired. Finally, when the number of detection points meets a point number threshold range, it is determined that the dispensing of the to-be-tested frame is successful. Thus, the dispensing of the to-be-tested panel is detected from a three-dimensional perspective, the detection result is more accurate, and thus the production quality of the electronic device is effectively improved.

[0009] Optionally, fitting the target plane can adopt a random sample consensus algorithm to determine a plane equation of the target plane.

[0010] Optionally, the height threshold range can include an upper height threshold, a lower height threshold and an average height value, a maximum value of the height threshold range is the average height value + the upper height threshold, and a minimum value of the height threshold range is the average height value - the lower height threshold, so that the height range of qualified dispensing can be effectively locked.

[0011] In combination with the first aspect, in some implementations of the first aspect, before the depth map data of the to-be-tested panel is acquired, the method further includes: determining whether the number of preset parameters is correct; the preset parameters include the upper height threshold, the lower height threshold and the point number threshold; when the number of preset parameters is correct, the detection process is continued; and when the number of preset parameters is incorrect, the detection process is ended.

[0012] In this implementation, before the depth map data of the to-be-tested panel is acquired, the number of preset parameters input by the user can be first detected, and when the number of preset parameters is correct, the detection process is continued. Otherwise, when the number of preset parameters is incorrect, the detection process is ended, so that the preset parameters can be accurately input and the subsequent process of the dispensing detection method is not affected.

[0013] It should be noted that the preset parameters can include the upper height threshold, the lower height threshold, the point number threshold and a frame selection template of the reference frame and the to-be-tested frame, etc.

[0014] In combination with the first aspect, in some implementations of the first aspect, before the detection process is ended, the method further includes: alarming and outputting error information.

[0015] In this implementation, before the detection process ends due to an incorrect number of preset parameters, an alarm can be issued to remind the detection personnel, and an error message can be output or printed at the same time, so that the detection personnel can understand the link where the problem occurs in the dispensing detection method and correct it in time.

[0016] In combination with the first aspect, in certain implementations of the first aspect, before converting the depth map data into a point cloud dataset, the method further includes: traversing the depth map data and removing invalid values.

[0017] In this implementation, before converting the depth map data into a point cloud dataset, the depth map data may be traversed and invalid values ​​may be removed, thereby ensuring the authenticity and validity of the depth map data.

[0018] In combination with the first aspect, in certain implementations of the first aspect, before converting the depth map data into a point cloud dataset, the method further includes: downsampling the depth map data.

[0019] In this implementation, in order to shorten the detection time and improve the detection efficiency, only the key spatial information of the panel to be tested and the glue can be retained, and the depth map data can be downsampled.

[0020] In combination with the first aspect, in certain implementations of the first aspect, before visualizing the plane equation, the method further includes: performing spatial leveling correction on the maximum plane according to the plane equation.

[0021] In this implementation, in order to obtain more accurate reference frames and test frames and prevent irregular plane equations from affecting the detection results, spatial leveling correction can be performed on the maximum plane according to the plane equations before visualizing the plane equations.

[0022] In combination with the first aspect, in certain implementations of the first aspect, before obtaining the height threshold range according to the reference frame, the method further includes: performing local filtering on the reference frame and the frame to be measured.

[0023] In this implementation, before obtaining the height threshold range according to the reference frame, local filtering is performed on the reference frame and the frame to be measured, which can avoid a large-area filtering process and thus reduce the detection time of the dispensing detection method.

[0024] In conjunction with the first aspect, in certain implementations of the first aspect, the point count threshold range includes a maximum point count threshold and a minimum point count threshold. When the number of detected points is less than the minimum point count threshold, it is determined that the glue dispensed on the test frame is being pulled away. When the number of detected points is greater than the maximum point count threshold, it is determined that the glue dispensed on the test frame is being pulled away.

[0025] In this implementation, if the number of detection points is less than the minimum threshold, it indicates that too few detection points meet the height threshold range, and the glue on the frame to be tested is pulled away, leaving only traces of residual glue. If the number of detection points is greater than the maximum threshold, it indicates that too many detection points meet the height threshold range, and the glue on the frame to be tested is pulled, and the glue height is too high.

[0026] In a second aspect, an inspection system is provided, comprising an assembly line module, a 3D camera module, and a control module. The assembly line module is configured to transport panels to be tested at a preset speed. The 3D camera module is positioned above the assembly line module and is configured to capture a depth map of the panels to be tested. The control module is connected to the assembly line module and the 3D camera module, respectively, to control the operation of the assembly line module and determine whether glue dispensing on the panels to be tested is successful based on the depth map of the panels to be tested.

[0027] In this implementation, the control module first controls the assembly line module, which moves the panel under test at a preset speed. The control module then controls the 3D camera module, which captures a depth map of the panel under test. Finally, the control module determines whether the glue dispensing process was successful based on the depth map. This enables 3D inspection of the panel's glue dispensing, resulting in more accurate results and effectively improving the production quality of electronic devices.

[0028] Optionally, the three-dimensional camera module includes a three-dimensional structured light camera.

[0029] In conjunction with the second aspect, in certain implementations of the second aspect, the detection system further includes an alarm module connected to the control module, and configured to generate an alarm when glue is not dispensed successfully on the panel to be tested.

[0030] In this implementation, the alarm module sounds an alarm when the panel to be tested fails to dispense glue, thereby reminding the inspection personnel to promptly check the panel to be tested that fails to dispense glue, thereby improving the production quality of the panel to be tested.

[0031] In conjunction with the second aspect, in certain implementations of the second aspect, the detection system further includes a support module, the support module is disposed above the assembly line module, and the three-dimensional camera module is disposed on the support module.

[0032] In this implementation, the 3D camera module can be placed above the assembly line module through the bracket module, so that the 3D camera module can easily capture the 3D image of the panel to be tested and detect the dispensing condition of the panel to be tested from a 3D level.

[0033] According to a third aspect, an electronic device is provided, comprising: one or more processors; and a memory. The memory is coupled to the one or more processors and configured to store computer program code, the computer program code comprising computer instructions, and the one or more processors invoke the computer instructions to cause the electronic device to execute the method.

[0034] In a fourth aspect, a chip system is provided, which is applied to an electronic device. The chip system includes one or more processors, and the one or more processors are used to call computer instructions so that the electronic device executes the described method.

[0035] In a fifth aspect, a computer-readable storage medium is provided, wherein the computer-readable storage medium includes instructions, and when the instructions are executed on an electronic device, the electronic device executes the method described. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 A schematic diagram of a dispensing scenario provided in an embodiment of the present application;

[0037] Figure 2 A schematic diagram of an application scenario of a traditional dispensing detection method provided in another embodiment of the present application;

[0038] Figure 3 This is a schematic diagram of glue being pulled away from a circuit board provided by an embodiment of the present application;

[0039] Figure 4 This is a flow chart of a dispensing detection method provided in an embodiment of the present application;

[0040] Figure 5 This is a flow chart of a dispensing detection method provided by another embodiment of the present application;

[0041] Figure 6 This is a flow chart of a dispensing detection method provided by another embodiment of the present application;

[0042] Figure 7 This is a flow chart of a dispensing detection method provided by another embodiment of the present application;

[0043] Figure 8 This is a flow chart of a dispensing detection method provided by another embodiment of the present application;

[0044] Figure 9 A schematic diagram of the structure of a detection system provided in an embodiment of the present application;

[0045] Figure 10 A schematic structural diagram of a detection system provided in yet another embodiment of the present application;

[0046] Figure 11 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0047] The following is a clear and detailed description of the technical solutions in the embodiments of the present application, with reference to the accompanying drawings. In the description of the embodiments of the present application, unless otherwise specified, " / " represents the meaning of "or." For example, A / B can represent A or B. "and / or" in the text is merely a description of the association relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone.

[0048] The terms "first," "second," and the like are used for descriptive purposes only and should not be construed as suggesting or implying relative importance or implicitly designating the number of the technical features indicated. Thus, features defined as "first" or "second" may explicitly or implicitly include one or more of such features. In the description of the embodiments of this application, unless otherwise specified, "plurality" means two or more.

[0049] In order to facilitate the understanding of the embodiments of the present application, the relevant concepts involved in the embodiments of the present application are first briefly described.

[0050] 1. Glue dispensing

[0051] In the field of electronics, dispensing refers to an operation process, also known as gluing, coating, filling, or dripping. Dispensing involves applying, encapsulating, or dripping electronic glue, oil, or other liquids onto a product to achieve adhesion, encapsulation, insulation, fixation, and surface smoothing.

[0052] Glue dispensing has a wide range of applications, from large-scale aircraft and ships to small-scale clothing and toys. Glue dispensing methods include: manually dispensing glue on electronic products using a manual dispenser; using automated equipment such as automatic dispensers or robots; applying glue directly to a stationary workpiece surface; applying glue to a moving workpiece surface; applying glue in pulses; applying glue in a continuous line. The appropriate dispensing valve can be selected based on specific dispensing requirements. Some glues perform best at specific temperatures, necessitating temperature control during the dispensing process. For mass production, dispensing molds can also be used to maintain consistent dispensing shapes and sizes.

[0053] 2. 3D structured light camera

[0054] In the field of electronics, a 3D structured light camera, also known as a 3D scanning camera, is an advanced digital photography device primarily used for three-dimensional reconstruction and detection. 3D structured light cameras utilize optical principles and image processing algorithms to achieve three-dimensional scanning of an object's surface. A 3D structured light camera emits a beam of specially coded structured light (usually a grating or triangular stripes) onto the surface of an object and uses the camera to record the image after the light is reflected from the object. By analyzing subtle differences in the image, such as light distortion and deformation, the geometric information of the object's surface can be calculated, and the object's three-dimensional model can be derived. This information includes the shape, depth, and texture of the object's surface. At the same time, during this process, the tilt of the lens can be used to achieve clear imaging of the entire surface being photographed. This is known as the Scheimpflug principle, which results in the image directly captured by the 3D structured light camera potentially being tilted.

[0055] 3. Depthmap

[0056] In the field of electronics, a depth map refers to an image used to represent three-dimensional information about a scene. In a depth map, the value of each pixel represents the depth or distance of that pixel in the visual scene, usually expressed as grayscale or color levels from near to far. Depth maps are also widely used in computer vision and image processing, for example: 3D reconstruction: Depth maps can be used to restore the three-dimensional structure of a scene, thereby reconstructing a three-dimensional model. Augmented reality: Depth maps can be used for scene understanding and object interaction in augmented reality. Video editing: Depth maps can be used for depth editing of videos, such as changing backgrounds and adding special effects.

[0057] 4. Point cloud

[0058] In the field of electronics, a point cloud is a massive collection of points that characterize the surface of an object. Specifically, a point cloud is a dataset in which each point represents a set of X, Y, and Z geometric coordinates and an intensity value. Color information (RGB) is sometimes also included. Point clouds can also contain other attributes, such as normal vectors, texture coordinates, and intensity values, that describe the point's shape and properties. Point clouds can be acquired in a variety of ways, primarily through sensor scanning and computer model conversion. For example, sensor scanning can include: LiDAR: This generates point cloud information by emitting a laser beam and measuring the time it takes for it to reflect back to calculate distance. Depth cameras: This uses infrared radiation and image sensors to detect the distance to objects in a scene, generating a point cloud. Computer model conversion can include using computer vision and image processing techniques to convert a 2D image or 3D model into point cloud data. For example, 3D point clouds can be recovered from images using methods such as structured light, stereo vision, or multi-view imaging.

[0059] 5. Random sample consensus (RANSAC) algorithm

[0060] In the field of electronics, RANSAC is an iterative method for estimating the parameters of mathematical models. It is particularly well-suited for datasets containing outliers. It fits the model by randomly selecting a subset of data, then statistically analyzing the deviations between the model and the rest of the data. Ultimately, it selects data that meets a certain threshold for parameter estimation.

[0061] Specifically, the input of the RANSAC algorithm is a set of observations, a parameterized model that can explain or adapt to the observations, and some credible parameters. The RANSAC algorithm achieves its goal by repeatedly selecting a set of random subsets from the data. The selected subsets are assumed to be inliers and verified using the following method: (1) There is a model that fits the assumed inliers, that is, all unknown parameters can be calculated from the assumed inliers. (2) Use the model obtained in (1) to test all other data. If a point fits the estimated model, it is considered to be an inlier. (3) If enough points are classified as assumed inliers, then the estimated model is reasonable enough. (4) Then, use all the assumed inliers to re-estimate the model, because it has only been estimated by the initial assumed inliers. (5) Finally, the model is evaluated by estimating the error rate between the inliers and the model. This process is repeated a fixed number of times, and the model generated each time is either discarded because there are too few inliers or selected because it is better than the existing model.

[0062] 6. Region of interest (ROI)

[0063] In the detection field, ROI refers to an image region of particular interest in image processing or computer vision tasks. By focusing attention on these specific areas, processing efficiency and accuracy can be improved. For example, in object detection, ROIs can help algorithms focus on areas that are likely to contain objects, reducing computational effort and improving detection performance.

[0064] 7. Traversal

[0065] Traversal is the process of accessing the elements of a collection one by one in a certain order or performing an operation. Traversal is typically implemented using a loop structure to process each element in a collection. In programming, traversal is often used to manipulate data structures (such as arrays, linked lists, and trees) or to iteratively access a range of elements. Through traversal, we can access elements in a collection one by one, performing operations such as reading, modifying, and printing.

[0066] 8. Downsampling

[0067] Downsampling is the process of reducing the sampling rate of a specific signal, typically to reduce data transmission rate or data size. The downsampling factor (often represented by the symbol M) is generally an integer or rational number greater than 1. This factor expresses how many times longer the sampling period has become, or equivalently, how much the sampling rate has been reduced to a fraction of the original value. Because downsampling reduces the sampling rate, it is necessary to ensure that the Nyquist sampling theorem still holds at the new lower sampling rate.

[0068] Among them, the Nyquist sampling theorem means that during the conversion process of analog / digital signals, when the sampling frequency fs.max is greater than twice the highest frequency fmax in the signal (fs.max>=2fmax), the digital signal after sampling completely retains the information in the original signal. Generally, in practical applications, the sampling frequency is guaranteed to be 5 to 10 times the highest frequency of the signal.

[0069] The above is a brief introduction to the nouns involved in the embodiments of this application, and no further details will be given below.

[0070] The following combination Figures 1 to 3 Before explaining the dispensing detection method provided in the embodiment of the present application in detail, the application scenarios of the dispensing detection method and the problems existing in the traditional dispensing detection method are first explained.

[0071] Figure 1 A schematic diagram of a dispensing scenario provided in an embodiment of the present application.

[0072] like Figure 1 As shown, for example, in an embodiment of the present application, during the assembly process of an electronic device, a user can use a dispensing device 10 to dispense glue on a circuit board 20 in the electronic device. This embodiment of the present application does not specifically limit the type of electronic device. In some specific embodiments, the electronic device can be a candy bar phone, a foldable phone, a wearable device (such as a smart bracelet, smart watch, headphones, etc.), a tablet computer, a laptop computer, a handheld computer, a notebook computer, an ultra-mobile personal computer (UMPC), a cellular phone, a personal digital assistant (PDA), an augmented reality (AR) or virtual reality (VR) device, and other IoT (Internet of Things) devices. It can also be a television, a large screen, a printer, a projector, and other devices.

[0073] Exemplarily, the dispensing device 10 may be a thermally conductive gel device.

[0074] Figure 2A schematic diagram of an application scenario of a traditional dispensing detection method provided in an embodiment of the present application.

[0075] like Figure 2 As shown, in an exemplary embodiment of the present application, the application scenario of a traditional glue dispensing inspection method includes a circuit board 20 and a two-dimensional (2D) glue dispensing inspection device 30. The 2D glue dispensing inspection device 30 is used to inspect the glue dispensing results of the circuit board 20. Specifically, the 2D glue dispensing inspection device 30 may include a 2D area array industrial camera with an industrial lens. The end of the 2D area array industrial camera near the circuit board 20 is provided with an industrial lens to enhance the image quality. An external power supply is provided on one side of the 2D area array industrial camera to illuminate the 2D area array industrial camera during the image capture process.

[0076] The 2D dispensing inspection device 30 captures the dispensing interface of the circuit board 20 to obtain a two-dimensional image to be tested. This image is then matched against a pre-set dispensing template within the 2D dispensing inspection device 30. If the two-dimensional image contains dispensing traces that match the dispensing template, the circuit board 20 is considered to have been successfully dispensed. If the two-dimensional image contains no dispensing traces that match the dispensing template, the circuit board 20 is considered to have failed dispensing.

[0077] It should be noted that the 2D dispensing inspection device 30 is generally directly installed in the production equipment of the circuit board 20. When the 2D dispensing inspection device 30 fails, it may affect other production processes of the circuit board 20.

[0078] Figure 3 This is a schematic diagram of glue being pulled away from a circuit board provided in an embodiment of the present application.

[0079] like Figure 3 As shown, illustratively, in an embodiment of the present application, in order to paste a variety of electronic devices on the circuit board 20, it is necessary to dispense glue on the circuit board 20. Exemplarily, the shape of the glue can be a variety of shapes such as round, square, I-shaped, etc. For example, in the assembly process of the electronic device, generally, the glue is dispensed at the preset position of the circuit board 20 by the glue dispensing valve of the glue dispensing device 10, and then the glue dispensing detection device 30 is used to detect whether there are glue dispensing traces at the preset position of the circuit board 20. Specifically, if there are glue dispensing traces at the preset position of the circuit board that match the glue dispensing template, it is determined that the glue dispensing of the circuit board 20 is successful. On the contrary, if there are no glue dispensing traces at the preset position of the circuit board that match the glue dispensing template, it is determined that the glue dispensing of the circuit board 20 has failed.

[0080] However, due to the strong adhesive force of the glue, it is very likely that the glue will be pulled away by the dispensing valve. Figure 3As shown, although the glue is taken away by the glue valve, the glue residue will still be left on the circuit board 20, thereby affecting the detection result of the glue dispensing detection device 30, leading to the misjudgment of the circuit board 20 with only glue residue as successful glue dispensing, and further leading to the reduction of the production quality of the electronic device. At the same time, since the 2D glue dispensing detection device 30 is generally directly arranged in the main production line together with the glue dispenser, when the 2D glue dispensing detection device 30 is down, it cannot be directly isolated, thereby affecting other production processes of the circuit board 20. In addition, the 2D glue dispensing detection device 30 also needs to adjust different detection methods and lighting effects for different colors or materials of glue, which is not conducive to improving the assembly production rhythm of the foldable mobile phone, the straight mobile phone, the tablet and other electronic devices.

[0081] It should be noted that the reasons why the glue is taken away by the single point of the glue valve may include the following two points:

[0082] (1) Glue dispensing height variation. For example, assuming that the standard value of the glue dispensing height is 0.8±0.2mm. When the real-time glue dispensing height is set to 0.9mm, the actual measurement of the circuit board / single board deformation is 0.3mm, and the actual height of the glue dispensing is 1.2mm, which exceeds the standard range of the glue dispensing height, thereby making the glue easy to be taken away by the glue valve.

[0083] (2) Glue dispensing needle nozzle difference. For example, the needle nozzle of model TT-16G generally has two outer diameter specifications: 1.75mm and 2.1mm. Among them, 2.1mm is generally used for problem equipment. The anti-glue hanging ability of the glue dispensing needle nozzle with different outer diameter specifications has difference. At the same time, when the glue dispensing needle nozzle hangs the glue point single point, it is easy to take away the pulling glue.

[0084] Therefore, the embodiment of the present application provides a glue dispensing detection method, which obtains the depth map data of the to-be-tested panel, processes the depth map data to obtain the point cloud height of the to-be-tested panel, and then determines whether the to-be-tested panel is successfully glued according to the number of point clouds meeting the height threshold range, so that the glue dispensing condition of the to-be-tested panel can be more accurately detected, and the production quality of the electronic device is improved.

[0085] The following will be described in combination with Figures 4 to 8, and then a detailed introduction is given to the glue dispensing detection method for detecting whether the glue dispensing of the panel to be tested is successful using 3D point cloud data provided in the embodiment of the present application. In the embodiment of the present application, the connection between the two electrical modules / electronic devices includes a communication connection and an electrical connection. The communication connection here refers to a connection that can transmit communication signals. The communication signal can be an electrical signal or an optical signal, which is not limited here. The electrical connection refers to a connection that can transmit electrical signals. The electrical connection includes a direct connection and an indirect connection. For example, a direct connection between device A and device B means that device A and device B are connected through a wire to transmit electrical signals. An indirect connection between device A and device B means that device A is connected to the first end of device C through a wire, and the second end of device C is connected to device B through a wire, so that device A and device B can transmit electrical signals through device C. For ease of understanding, in the following description, "electrical connection" will be referred to as connection.

[0086] First embodiment: Figure 4 This is a flow chart of a dispensing detection method provided in an embodiment of the present application.

[0087] like Figure 4 As shown, illustratively, an embodiment of the present application provides a dispensing detection method 40, which may specifically include the following steps:

[0088] S401: The electronic device obtains depth map data of the panel to be tested, and converts the depth map data into a point cloud data set.

[0089] For example, when inspecting the glue dispensing of a panel, a 3D area array structured light camera can be used to capture and store depth map data of the panel. Glue dispensing inspection method 40 can then be used to obtain the depth map data from the 3D area array structured light camera and convert the depth map data into a point cloud dataset. This eliminates the need for additional lighting and the need to consider the shape and color of the glue, significantly improving the robustness of the inspection system.

[0090] It should be understood that a depth map is a two-dimensional image that can represent three-dimensional information, generally represented by grayscale or color gradations from near to far. A point cloud is a dataset containing multiple points, where each point represents a set of X, Y, and Z geometric coordinates and an intensity value.

[0091] S402: The electronic device obtains a normal vector of the point cloud data set, and divides the point cloud data set into a vertical point cloud and a horizontal point cloud according to the normal vector.

[0092] For example, since the point cloud dataset of the panel to be measured is also a data point set of the panel shape to be measured, the normal vector of the point cloud dataset of the panel shape to be measured can be obtained. The point cloud dataset can then be segmented into a vertical point cloud and a horizontal point cloud based on the normal vector of the point cloud dataset.

[0093] It should be understood that a vertical point cloud is a set of point clouds that are parallel to the normal vector of the point cloud dataset, and a horizontal point cloud is a set of point clouds that are perpendicular to the normal vector of the point cloud dataset.

[0094] S403: The electronic device performs multi-plane segmentation on the horizontal point cloud and uses the largest plane among the multi-planes as the target plane.

[0095] For example, to detect the height of glue dots in a panel under test, the horizontal point cloud can be segmented into multiple planes to obtain a multi-layer horizontal point cloud. The plane with the largest area in the multi-layer plane can then be found and used as the target plane, which will serve as the reference plane in the subsequent inspection process.

[0096] It should be understood that the largest plane among the multiple planes is generally the lowest plane of the panel to be tested (ie, the substrate or single board). When electronic components are arranged on the substrate, the plane area formed by the electronic components is generally smaller than the area of ​​the substrate.

[0097] S404: The electronic device fits the target plane to obtain a plane equation.

[0098] For example, once the target plane is determined, a plane equation can be obtained by fitting the set of points in the target plane to obtain a plane equation that conforms to the target plane model. For example, the plane equation can be a linear equation with three variables: ax + by + cz - d = 0. Obtaining the plane equation by fitting the target plane is equivalent to obtaining the coefficients of the linear equation with three variables.

[0099] Optionally, the target plane may be fitted using a RANSAC algorithm to determine the plane equation coefficients of the target plane.

[0100] S405: The electronic device visualizes the plane equation and selects a reference frame and a frame to be measured.

[0101] For example, by visualizing the plane equation, that is, rendering the plane equation as a point cloud in real time, the inspector can see, touch, zoom in, or move the 3D model of the panel under test on the computer. For example, the inspector can zoom in or move the 3D model of the panel under test through the touch screen all-in-one machine, interacting with the 3D shape of the panel under test in real time, and quickly locate the abnormal glue dispensing position.

[0102] At the same time, you can also use the frame selection software to select two ROIs in the visualized 3D model of the panel to be tested, one ROI as the reference frame and the other ROI as the detection frame. By comparing the reference frame and the detection frame, you can determine the glue dispensing condition of the detection frame.

[0103] S406: The electronic device obtains a height threshold range according to the reference frame, and obtains the number of detection points of the frame to be measured that meets the height threshold range.

[0104] For example, a standard height threshold range can be obtained based on the point cloud dataset in the reference frame. Then, the point cloud dataset in the frame to be measured is compared with the height threshold range to obtain the number of detection points (account) in the frame to be measured that meet the height threshold range.

[0105] It should be understood that the height threshold range may include an upper height threshold (diff1), a lower height threshold (diff2), and an average height value (average height). The maximum value of the height threshold range is the average height value + the upper height threshold, i.e., average height + diff1. The minimum value of the height threshold range is the average height value - the lower height threshold, i.e., average height - diff2.

[0106] S407: The electronic device determines whether the detection points meet the point threshold range.

[0107] For example, the electronic device can determine whether the glue dispensing of the frame to be tested is qualified by judging whether the number of detection points meets the point threshold range.

[0108] S408: When the number of detection points meets the threshold range, the electronic device determines that the glue dispensing of the frame to be tested is successful.

[0109] Exemplarily, when the number of detection points of the electronic device meets the point threshold range, it means that the number of points within the frame to be tested that meet the height threshold range meets the point threshold range, and the glue dispensing of the frame to be tested is successful.

[0110] S409: When the number of detection points of the electronic device does not meet the point threshold range, it is determined that the dispensing of the frame to be tested has failed.

[0111] For example, when the number of points detected by the electronic device does not meet the point threshold range, it means that the number of points within the frame to be tested that meet the height threshold range does not meet the point threshold range, and the glue dispensing of the frame to be tested fails.

[0112] It should be noted that since glue generally forms an irregular three-dimensional column on the panel to be tested, multiple plane layers are obtained after multi-plane segmentation. Therefore, it is possible to determine whether the number of detection points within the test frame that meet the threshold range is within the threshold range. If it does, it can be determined that the glue dispensing of the test frame is successful. Otherwise, it can be determined that the glue dispensing of the test frame has failed.

[0113] It should be understood that the point count threshold range can include a maximum point count threshold (maxcount) and a minimum point count threshold (mincount). When the detection point count (account) is less than the minimum point count (mincount), it indicates that too few detection points meet the height threshold range, and the glue dispensed on the test frame has been pulled away, leaving only residual glue traces, indicating glue dispensing failure.

[0114] When the number of detection points account is greater than the maximum point threshold maxcount, it means that there are too many detection points that meet the height threshold range, the frame to be tested is glued and the glue height is too high, and the glue fails.

[0115] When the number of detection points account is greater than the minimum point threshold mincoun and less than the maximum point threshold maxcount, it means that the number of detection points that meet the height range is appropriate and the dispensing is successful. Therefore, the dispensing detection method 40 can more accurately detect the dispensing situation of the panel to be tested and improve the production quality of electronic equipment.

[0116] Second embodiment: Figure 5 This is a flow chart of another dispensing detection method provided in an embodiment of the present application, which introduces a solution for determining preset parameters in advance in the dispensing detection method provided in an embodiment of the present application.

[0117] like Figure 5 As shown, illustratively, an embodiment of the present application provides a dispensing detection method 40, which may specifically include the following steps:

[0118] S400: The electronic device determines whether the number of preset parameters is correct.

[0119] For example, when starting the dispensing detection method 40, the number of preset parameters required for dispensing detection method 40 can be determined to be correct before proceeding to other subsequent steps. For example, the preset parameters may include an upper height threshold, a lower height threshold, a point count threshold, and frame selection templates for the reference frame and the frame to be tested. If the number of preset parameters is correct, the detection process continues, for example, in S401.

[0120] S4001. When the number of preset parameters is incorrect, the detection process ends.

[0121] For example, when the number of preset parameters is incorrect, it indicates that there is a problem with the parameter setting of the dispensing detection method 40 , and the dispensing detection process cannot be completed, so the detection process needs to be terminated.

[0122] In addition, if the number of preset parameters is incorrect and before the detection process ends, an audible and visual alarm can be used to alert the inspector, and an error message can be output or printed at the same time, so that the inspector can understand the link where the problem occurs in the dispensing detection method and make corrections in time.

[0123] S401: The electronic device obtains depth map data of the panel to be tested, and converts the depth map data into a point cloud data set.

[0124] For example, when inspecting the glue dispensing of a panel, a 3D area array structured light camera can be used to capture and store depth map data of the panel. Glue dispensing inspection method 40 can then be used to obtain the depth map data from the 3D area array structured light camera and convert the depth map data into a point cloud dataset. This eliminates the need for additional lighting and the need to consider the shape and color of the glue, significantly improving the robustness of the inspection system.

[0125] It should be understood that a depth map is a two-dimensional image that can represent three-dimensional information, generally represented by grayscale or color gradations from near to far. A point cloud is a dataset containing multiple points, where each point represents a set of X, Y, and Z geometric coordinates and an intensity value.

[0126] S402: The electronic device obtains a normal vector of the point cloud data set, and divides the point cloud data set into a vertical point cloud and a horizontal point cloud according to the normal vector.

[0127] For example, since the point cloud dataset of the panel to be measured is also a data point set of the panel shape to be measured, the normal vector of the point cloud dataset of the panel shape to be measured can be obtained. The point cloud dataset can then be segmented into a vertical point cloud and a horizontal point cloud based on the normal vector of the point cloud dataset.

[0128] It should be understood that a vertical point cloud is a set of point clouds that are parallel to the normal vector of the point cloud dataset, and a horizontal point cloud is a set of point clouds that are perpendicular to the normal vector of the point cloud dataset.

[0129] S403: The electronic device performs multi-plane segmentation on the horizontal point cloud and uses the largest plane among the multi-planes as the target plane.

[0130] For example, to detect the height of glue dots in a panel under test, the horizontal point cloud can be segmented into multiple planes to obtain a multi-layer horizontal point cloud. The plane with the largest area in the multi-layer plane can then be found and used as the target plane, which will serve as the reference plane in the subsequent inspection process.

[0131] It should be understood that the largest plane among the multiple planes is generally the lowest plane of the panel to be tested (ie, the substrate or single board). When electronic components are arranged on the substrate, the plane area formed by the electronic components is generally smaller than the area of ​​the substrate.

[0132] S404: The electronic device fits the target plane to obtain a plane equation.

[0133] For example, once the target plane is determined, a plane equation can be obtained by fitting the set of points in the target plane to obtain a plane equation that conforms to the target plane model. For example, the plane equation can be a linear equation with three variables: ax + by + cz - d = 0. Obtaining the plane equation by fitting the target plane is equivalent to obtaining the coefficients of the linear equation with three variables.

[0134] Optionally, the target plane may be fitted using a RANSAC algorithm to determine the plane equation coefficients of the target plane.

[0135] S405: The electronic device visualizes the plane equation and selects a reference frame and a frame to be measured.

[0136] For example, by visualizing the plane equation, that is, rendering the plane equation as a point cloud in real time, the inspector can see, touch, zoom in, or move the 3D model of the panel under test on the computer. For example, the inspector can zoom in or move the 3D model of the panel under test through the touch screen all-in-one machine, interacting with the 3D shape of the panel under test in real time, and quickly locate the abnormal glue dispensing position.

[0137] At the same time, you can also use the frame selection software to select two ROIs in the visualized 3D model of the panel to be tested, one ROI as the reference frame and the other ROI as the detection frame. By comparing the reference frame and the detection frame, you can determine the glue dispensing condition of the detection frame.

[0138] S406: The electronic device obtains a height threshold range according to the reference frame, and obtains the number of detection points of the frame to be measured that meets the height threshold range.

[0139] For example, a standard height threshold range can be obtained based on the point cloud dataset in the reference frame. Then, the point cloud dataset in the frame to be measured is compared with the height threshold range to obtain the number of detection points (account) in the frame to be measured that meet the height threshold range.

[0140] It should be understood that the height threshold range may include an upper height threshold (diff1), a lower height threshold (diff2), and an average height value (average height). The maximum value of the height threshold range is the average height value + the upper height threshold, i.e., average height + diff1. The minimum value of the height threshold range is the average height value - the lower height threshold, i.e., average height - diff2.

[0141] S407: The electronic device determines whether the detection points meet the point threshold range.

[0142] For example, the electronic device can determine whether the glue dispensing of the frame to be tested is qualified by judging whether the number of detection points meets the point threshold range.

[0143] S408: When the number of detection points meets the threshold range, the electronic device determines that the glue dispensing of the frame to be tested is successful.

[0144] Exemplarily, when the number of detection points of the electronic device meets the point threshold range, it means that the number of points within the frame to be tested that meet the height threshold range meets the point threshold range, and the glue dispensing of the frame to be tested is successful.

[0145] S409: When the number of detection points of the electronic device does not meet the point threshold range, it is determined that the dispensing of the frame to be tested has failed.

[0146] For example, when the number of points detected by the electronic device does not meet the point threshold range, it means that the number of points within the frame to be tested that meet the height threshold range does not meet the point threshold range, and the glue dispensing of the frame to be tested fails.

[0147] It should be noted that since glue generally forms an irregular three-dimensional column on the panel to be tested, multiple plane layers are obtained after multi-plane segmentation. Therefore, it is possible to determine whether the number of detection points within the test frame that meet the threshold range is within the threshold range. If it does, it can be determined that the glue dispensing of the test frame is successful. Otherwise, it can be determined that the glue dispensing of the test frame has failed.

[0148] It should be understood that the point count threshold range can include a maximum point count threshold (maxcount) and a minimum point count threshold (mincount). When the detection point count (account) is less than the minimum point count (mincount), it indicates that too few detection points meet the height threshold range, and the glue dispensed on the test frame has been pulled away, leaving only residual glue traces, indicating glue dispensing failure.

[0149] When the number of detection points account is greater than the maximum point threshold maxcount, it means that there are too many detection points that meet the height threshold range, the frame to be tested is glued and the glue height is too high, and the glue fails.

[0150] When the number of detection points account is greater than the minimum point threshold mincoun and less than the maximum point threshold maxcount, it means that the number of detection points that meet the height range is appropriate and the dispensing is successful. Therefore, the dispensing detection method 40 can more accurately detect the dispensing situation of the panel to be tested and improve the production quality of electronic equipment.

[0151] The third embodiment: Figure 6 This is a flow chart of another dispensing detection method provided in an embodiment of the present application, which introduces the scheme of removing invalid values ​​in advance and downsampling in the dispensing detection method provided in an embodiment of the present application.

[0152] like Figure 6As shown, the embodiment of the present application exemplarily provides a dispensing detection method 40, which can specifically include the following steps:

[0153] S4011, the electronic device obtains depth map data of the to-be-tested panel.

[0154] Exemplarily, when it is necessary to detect the dispensing condition of the to-be-tested panel, the depth map data of the to-be-tested panel can be first captured by a 3D area structured light camera and stored, and then the depth map data is obtained from the 3D area structured light camera by the dispensing detection method 40. Thus, the 3D area structured light camera does not need additional lighting, and does not need to consider the shape and color of the glue, thereby greatly improving the robustness of the detection system.

[0155] It should be understood that the depth map is a two-dimensional image that can represent three-dimensional information, which generally uses gray scale or color level from near to far for representation. The point cloud is a data set containing multiple points, wherein each point represents a set of X, Y, Z geometric coordinates and an intensity value.

[0156] S4012, the electronic device traverses the depth map data and removes invalid values.

[0157] Exemplarily, before converting the depth map data into a point cloud data set, all the depth map data can be traversed and invalid values (not a number, NAN) can be removed, thereby further guaranteeing the authenticity and effectiveness of the depth map data.

[0158] S4013, the electronic device down-samples the depth map data.

[0159] Exemplarily, in order to shorten the detection time and improve the detection efficiency, only the key spatial information of the to-be-tested panel and the glue can be retained, and the depth map data can be down-sampled, thereby greatly reducing the dispensing detection time and guaranteeing the panel passing rhythm of the production line.

[0160] S4014, the electronic device converts the depth map data into a point cloud data set.

[0161] Exemplarily, the point cloud data set is a 3D type point cloud, and the electronic device converts the depth map data into a point cloud data set for subsequent three-dimensional processing.

[0162] S402, the electronic device obtains the normal vector of the point cloud data set, and divides the point cloud data set into vertical point cloud and horizontal point cloud according to the normal vector.

[0163] Exemplarily, since the point cloud data set of the to-be-tested panel is also a data point set of the shape of the to-be-tested panel, the normal vector of the point cloud data set of the shape of the to-be-tested panel can be obtained. And according to the normal vector of the point cloud data set, the point cloud data set can be divided into vertical point cloud and horizontal point cloud.

[0164] It should be understood that a vertical point cloud is a set of point clouds that are parallel to the normal vector of the point cloud dataset, and a horizontal point cloud is a set of point clouds that are perpendicular to the normal vector of the point cloud dataset.

[0165] S403: The electronic device performs multi-plane segmentation on the horizontal point cloud and uses the largest plane among the multi-planes as the target plane.

[0166] For example, to detect the height of glue dots in a panel under test, the horizontal point cloud can be segmented into multiple planes to obtain a multi-layer horizontal point cloud. The plane with the largest area in the multi-layer plane can then be found and used as the target plane, which will serve as the reference plane in the subsequent inspection process.

[0167] It should be understood that the largest plane among the multiple planes is generally the lowest plane of the panel to be tested (ie, the substrate or single board). When electronic components are arranged on the substrate, the plane area formed by the electronic components is generally smaller than the area of ​​the substrate.

[0168] S404: The electronic device fits the target plane to obtain a plane equation.

[0169] For example, once the target plane is determined, a plane equation can be obtained by fitting the set of points in the target plane to obtain a plane equation that conforms to the target plane model. For example, the plane equation can be a linear equation with three variables: ax + by + cz - d = 0. Obtaining the plane equation by fitting the target plane is equivalent to obtaining the coefficients of the linear equation with three variables.

[0170] Optionally, the target plane may be fitted using a RANSAC algorithm to determine the plane equation coefficients of the target plane.

[0171] S405: The electronic device visualizes the plane equation and selects a reference frame and a frame to be measured.

[0172] For example, by visualizing the plane equation, that is, rendering the plane equation as a point cloud in real time, the inspector can see, touch, zoom in, or move the 3D model of the panel under test on the computer. For example, the inspector can zoom in or move the 3D model of the panel under test through the touch screen all-in-one machine, interacting with the 3D shape of the panel under test in real time, and quickly locate the abnormal glue dispensing position.

[0173] At the same time, you can also use the frame selection software to select two ROIs in the visualized 3D model of the panel to be tested, one ROI as the reference frame and the other ROI as the detection frame. By comparing the reference frame and the detection frame, you can determine the glue dispensing condition of the detection frame.

[0174] S406: The electronic device obtains a height threshold range according to the reference frame, and obtains the number of detection points of the frame to be measured that meets the height threshold range.

[0175] For example, a standard height threshold range can be obtained based on the point cloud dataset in the reference frame. Then, the point cloud dataset in the frame to be measured is compared with the height threshold range to obtain the number of detection points (account) in the frame to be measured that meet the height threshold range.

[0176] It should be understood that the height threshold range may include an upper height threshold (diff1), a lower height threshold (diff2), and an average height value (average height). The maximum value of the height threshold range is the average height value + the upper height threshold, i.e., average height + diff1. The minimum value of the height threshold range is the average height value - the lower height threshold, i.e., average height - diff2.

[0177] S407: The electronic device determines whether the detection points meet the point threshold range.

[0178] For example, the electronic device can determine whether the glue dispensing of the frame to be tested is qualified by judging whether the number of detection points meets the point threshold range.

[0179] S408: When the number of detection points meets the threshold range, the electronic device determines that the glue dispensing of the frame to be tested is successful.

[0180] Exemplarily, when the number of detection points of the electronic device meets the point threshold range, it means that the number of points within the frame to be tested that meet the height threshold range meets the point threshold range, and the glue dispensing of the frame to be tested is successful.

[0181] S409: When the number of detection points of the electronic device does not meet the point threshold range, it is determined that the dispensing of the frame to be tested has failed.

[0182] For example, when the number of points detected by the electronic device does not meet the point threshold range, it means that the number of points within the frame to be tested that meet the height threshold range does not meet the point threshold range, and the glue dispensing of the frame to be tested fails.

[0183] It should be noted that since glue generally forms an irregular three-dimensional column on the panel to be tested, multiple plane layers are obtained after multi-plane segmentation. Therefore, it is possible to determine whether the number of detection points within the test frame that meet the threshold range is within the threshold range. If it does, it can be determined that the glue dispensing of the test frame is successful. Otherwise, it can be determined that the glue dispensing of the test frame has failed.

[0184] It should be understood that the point count threshold range can include a maximum point count threshold (maxcount) and a minimum point count threshold (mincount). When the detection point count (account) is less than the minimum point count (mincount), it indicates that too few detection points meet the height threshold range, and the glue dispensed on the test frame has been pulled away, leaving only residual glue traces, indicating glue dispensing failure.

[0185] When the number of detection points account is greater than the maximum point threshold maxcount, it means that there are too many detection points that meet the height threshold range, the frame to be tested is glued and the glue height is too high, and the glue fails.

[0186] When the number of detection points account is greater than the minimum point threshold mincoun and less than the maximum point threshold maxcount, it means that the number of detection points that meet the height range is appropriate and the dispensing is successful. Therefore, the dispensing detection method 40 can more accurately detect the dispensing situation of the panel to be tested and improve the production quality of electronic equipment.

[0187] Fourth embodiment: Figure 7 This is a flow chart of another dispensing detection method provided in an embodiment of the present application, which introduces a solution for performing spatial leveling correction on the maximum plane in the dispensing detection method provided in an embodiment of the present application.

[0188] like Figure 7 As shown, illustratively, an embodiment of the present application provides a dispensing detection method 40, which may specifically include the following steps:

[0189] S401: The electronic device obtains depth map data of the panel to be tested, and converts the depth map data into a point cloud data set.

[0190] For example, when inspecting the glue dispensing of a panel, a 3D area array structured light camera can be used to capture and store depth map data of the panel. Glue dispensing inspection method 40 can then be used to obtain the depth map data from the 3D area array structured light camera and convert the depth map data into a point cloud dataset. This eliminates the need for additional lighting and the need to consider the shape and color of the glue, significantly improving the robustness of the inspection system.

[0191] It should be understood that a depth map is a two-dimensional image that can represent three-dimensional information, generally represented by grayscale or color gradations from near to far. A point cloud is a dataset containing multiple points, where each point represents a set of X, Y, and Z geometric coordinates and an intensity value.

[0192] S402: The electronic device obtains a normal vector of the point cloud data set, and divides the point cloud data set into a vertical point cloud and a horizontal point cloud according to the normal vector.

[0193] For example, since the point cloud dataset of the panel to be measured is also a data point set of the panel shape to be measured, the normal vector of the point cloud dataset of the panel shape to be measured can be obtained. The point cloud dataset can then be segmented into a vertical point cloud and a horizontal point cloud based on the normal vector of the point cloud dataset.

[0194] It should be understood that a vertical point cloud is a set of point clouds that are parallel to the normal vector of the point cloud dataset, and a horizontal point cloud is a set of point clouds that are perpendicular to the normal vector of the point cloud dataset.

[0195] S403: The electronic device performs multi-plane segmentation on the horizontal point cloud and uses the largest plane among the multi-planes as the target plane.

[0196] For example, to detect the height of glue dots in a panel under test, the horizontal point cloud can be segmented into multiple planes to obtain a multi-layer horizontal point cloud. The plane with the largest area in the multi-layer plane can then be found and used as the target plane, which will serve as the reference plane in the subsequent inspection process.

[0197] It should be understood that the largest plane among the multiple planes is generally the lowest plane of the panel to be tested (ie, the substrate or single board). When electronic components are arranged on the substrate, the plane area formed by the electronic components is generally smaller than the area of ​​the substrate.

[0198] S404: The electronic device fits the target plane to obtain a plane equation.

[0199] For example, once the target plane is determined, a plane equation can be obtained by fitting the set of points in the target plane to obtain a plane equation that conforms to the target plane model. For example, the plane equation can be a linear equation with three variables: ax + by + cz - d = 0. Obtaining the plane equation by fitting the target plane is equivalent to obtaining the coefficients of the linear equation with three variables.

[0200] Optionally, the target plane may be fitted using a RANSAC algorithm to determine the plane equation coefficients of the target plane.

[0201] S4041. The electronic device performs spatial leveling correction on the maximum plane according to the plane equation.

[0202] For example, due to the unique imaging principles of 3D structured light cameras, the image may be tilted. To obtain more accurate reference frames and test frames and prevent irregular plane equations from affecting the detection results, spatial leveling correction can be performed on the largest plane based on the plane equation before visualizing the plane equation. This can, to a certain extent, correct problems such as one side being higher than the other due to 3D array structured light imaging, track jitter on the board transfer platform, and unstable single board docking. This allows only one reference frame, the reference plane detection frame (base), to be drawn to determine the reference plane of all test frames (detect) for the entire single board, eliminating the need to repeatedly draw multiple reference frames.

[0203] S405: The electronic device visualizes the plane equation and selects a reference frame and a frame to be measured.

[0204] For example, by visualizing the plane equation, that is, rendering the plane equation as a point cloud in real time, the inspector can see, touch, zoom in, or move the 3D model of the panel under test on the computer. For example, the inspector can zoom in or move the 3D model of the panel under test through the touch screen all-in-one machine, interacting with the 3D shape of the panel under test in real time, and quickly locate the abnormal glue dispensing position.

[0205] At the same time, you can also use the frame selection software to select two ROIs in the visualized 3D model of the panel to be tested, one ROI as the reference frame and the other ROI as the detection frame. By comparing the reference frame and the detection frame, you can determine the glue dispensing condition of the detection frame.

[0206] S406: The electronic device obtains a height threshold range according to the reference frame, and obtains the number of detection points of the frame to be measured that meets the height threshold range.

[0207] For example, a standard height threshold range can be obtained based on the point cloud dataset in the reference frame. Then, the point cloud dataset in the frame to be measured is compared with the height threshold range to obtain the number of detection points (account) in the frame to be measured that meet the height threshold range.

[0208] It should be understood that the height threshold range may include an upper height threshold (diff1), a lower height threshold (diff2), and an average height value (average height). The maximum value of the height threshold range is the average height value + the upper height threshold, i.e., average height + diff1. The minimum value of the height threshold range is the average height value - the lower height threshold, i.e., average height - diff2.

[0209] S407: The electronic device determines whether the detection points meet the point threshold range.

[0210] For example, the electronic device can determine whether the glue dispensing of the frame to be tested is qualified by judging whether the number of detection points meets the point threshold range.

[0211] S408: When the number of detection points meets the threshold range, the electronic device determines that the glue dispensing of the frame to be tested is successful.

[0212] Exemplarily, when the number of detection points of the electronic device meets the point threshold range, it means that the number of points within the frame to be tested that meet the height threshold range meets the point threshold range, and the glue dispensing of the frame to be tested is successful.

[0213] S409: When the number of detection points of the electronic device does not meet the point threshold range, it is determined that the dispensing of the frame to be tested has failed.

[0214] For example, when the number of points detected by the electronic device does not meet the point threshold range, it means that the number of points within the frame to be tested that meet the height threshold range does not meet the point threshold range, and the glue dispensing of the frame to be tested fails.

[0215] It should be noted that since glue generally forms an irregular three-dimensional column on the panel to be tested, multiple plane layers are obtained after multi-plane segmentation. Therefore, it is possible to determine whether the number of detection points within the test frame that meet the threshold range is within the threshold range. If it does, it can be determined that the glue dispensing of the test frame is successful. Otherwise, it can be determined that the glue dispensing of the test frame has failed.

[0216] It should be understood that the point count threshold range can include a maximum point count threshold (maxcount) and a minimum point count threshold (mincount). When the detection point count (account) is less than the minimum point count (mincount), it indicates that too few detection points meet the height threshold range, and the glue dispensed on the test frame has been pulled away, leaving only residual glue traces, indicating glue dispensing failure.

[0217] When the number of detection points account is greater than the maximum point threshold maxcount, it means that there are too many detection points that meet the height threshold range, the frame to be tested is glued and the glue height is too high, and the glue fails.

[0218] When the number of detection points account is greater than the minimum point threshold mincoun and less than the maximum point threshold maxcount, it means that the number of detection points that meet the height range is appropriate and the dispensing is successful. Therefore, the dispensing detection method 40 can more accurately detect the dispensing situation of the panel to be tested and improve the production quality of electronic equipment.

[0219] Fifth embodiment: Figure 8 This is a flow chart of another dispensing detection method provided in an embodiment of the present application, which introduces a solution of performing local filtering on the reference frame and the frame to be tested in the dispensing detection method provided in an embodiment of the present application.

[0220] like Figure 8 Exemplarily, the embodiment of the present application provides a dispensing detection method 40, which can specifically include the following steps:

[0221] S401, the electronic device obtains the depth map data of the to-be-tested panel and converts the depth map data into a point cloud data set.

[0222] Exemplarily, when it is necessary to detect the dispensing condition of the to-be-tested panel, the depth map data of the to-be-tested panel can be first captured by a 3D area structured light camera and stored, and then the depth map data is obtained from the 3D area structured light camera by the dispensing detection method 40, and the depth map data is converted into a point cloud data set. Thus, the 3D area structured light camera does not need additional lighting and does not need to consider the shape and color of the glue, greatly improving the robustness of the detection system.

[0223] It should be understood that the depth map is a two-dimensional image that can represent three-dimensional information, generally using gray scale or color level from near to far to represent. The point cloud is a data set containing multiple points, where each point represents a set of X, Y, Z geometric coordinates and an intensity value.

[0224] S402, the electronic device obtains the normal vector of the point cloud data set, and divides the point cloud data set into vertical point cloud and horizontal point cloud according to the normal vector.

[0225] Exemplarily, since the point cloud data set of the to-be-tested panel is also a data point set of the shape of the to-be-tested panel, the normal vector of the point cloud data set of the shape of the to-be-tested panel can be obtained. And according to the normal vector of the point cloud data set, the point cloud data set can be divided into vertical point cloud and horizontal point cloud.

[0226] It should be understood that the vertical point cloud is a point cloud set parallel to the normal vector of the point cloud data set. The horizontal point cloud is a point cloud set perpendicular to the normal vector of the point cloud data set.

[0227] S403, the electronic device performs multi-plane segmentation on the horizontal point cloud, and takes the largest plane in the multi-plane as the target plane.

[0228] Exemplarily, in order to detect the height value of the dispensing in the to-be-tested panel, the horizontal point cloud can be subjected to multi-plane segmentation, so as to obtain the horizontal point cloud of the multi-layer plane. Then the largest plane in the multi-layer plane can be found, and it is taken as the target plane for subsequent detection process as the reference plane.

[0229] It should be understood that the largest plane in the multi-plane is generally the lowest surface of the to-be-tested panel (i.e. the substrate or single board). When electronic devices are arranged on the substrate, the plane area composed of the electronic devices is generally smaller than the area size of the substrate.

[0230] S404: The electronic device fits the target plane to obtain a plane equation.

[0231] For example, once the target plane is determined, a plane equation can be obtained by fitting the set of points in the target plane to obtain a plane equation that conforms to the target plane model. For example, the plane equation can be a linear equation with three variables: ax + by + cz - d = 0. Obtaining the plane equation by fitting the target plane is equivalent to obtaining the coefficients of the linear equation with three variables.

[0232] Optionally, the target plane may be fitted using a RANSAC algorithm to determine the plane equation coefficients of the target plane.

[0233] S405: The electronic device visualizes the plane equation and selects a reference frame and a frame to be measured.

[0234] For example, by visualizing the plane equation, that is, rendering the plane equation as a point cloud in real time, the inspector can see, touch, zoom in, or move the 3D model of the panel under test on the computer. For example, the inspector can zoom in or move the 3D model of the panel under test through the touch screen all-in-one machine, interacting with the 3D shape of the panel under test in real time, and quickly locate the abnormal glue dispensing position.

[0235] At the same time, you can also use the frame selection software to select two ROIs in the visualized 3D model of the panel to be tested, one ROI as the reference frame and the other ROI as the detection frame. By comparing the reference frame and the detection frame, you can determine the glue dispensing condition of the detection frame.

[0236] S4051. The electronic device performs local filtering on the reference frame and the frame to be measured.

[0237] For example, before obtaining the height threshold range based on the reference frame, local filtering is performed on the reference frame and the frame to be tested. This can avoid a large-area filtering process, thereby reducing the detection time of the dispensing detection method and further compressing the detection time of the computed tomography image (CT).

[0238] S406: The electronic device obtains a height threshold range according to the reference frame, and obtains the number of detection points of the frame to be measured that meets the height threshold range.

[0239] For example, a standard height threshold range can be obtained based on the point cloud dataset in the reference frame. Then, the point cloud dataset in the frame to be measured is compared with the height threshold range to obtain the number of detection points (account) in the frame to be measured that meet the height threshold range.

[0240] It should be understood that the height threshold range may include an upper height threshold (diff1), a lower height threshold (diff2), and an average height value (average height). The maximum value of the height threshold range is the average height value + the upper height threshold, i.e., average height + diff1. The minimum value of the height threshold range is the average height value - the lower height threshold, i.e., average height - diff2.

[0241] S407: The electronic device determines whether the detection points meet the point threshold range.

[0242] For example, the electronic device can determine whether the glue dispensing of the frame to be tested is qualified by judging whether the number of detection points meets the point threshold range.

[0243] S408: When the number of detection points meets the threshold range, the electronic device determines that the glue dispensing of the frame to be tested is successful.

[0244] Exemplarily, when the number of detection points of the electronic device meets the point threshold range, it means that the number of points within the frame to be tested that meet the height threshold range meets the point threshold range, and the glue dispensing of the frame to be tested is successful.

[0245] S409: When the number of detection points of the electronic device does not meet the point threshold range, it is determined that the dispensing of the frame to be tested has failed.

[0246] For example, when the number of points detected by the electronic device does not meet the point threshold range, it means that the number of points within the frame to be tested that meet the height threshold range does not meet the point threshold range, and the glue dispensing of the frame to be tested fails.

[0247] It should be noted that since glue generally forms an irregular three-dimensional column on the panel to be tested, multiple plane layers are obtained after multi-plane segmentation. Therefore, it is possible to determine whether the number of detection points within the test frame that meet the threshold range is within the threshold range. If it does, it can be determined that the glue dispensing of the test frame is successful. Otherwise, it can be determined that the glue dispensing of the test frame has failed.

[0248] It should be understood that the point count threshold range can include a maximum point count threshold (maxcount) and a minimum point count threshold (mincount). When the detection point count (account) is less than the minimum point count (mincount), it indicates that too few detection points meet the height threshold range, and the glue dispensed on the test frame has been pulled away, leaving only residual glue traces, indicating glue dispensing failure.

[0249] When the number of detection points account is greater than the maximum point threshold maxcount, it means that there are too many detection points that meet the height threshold range, the frame to be tested is glued and the glue height is too high, and the glue fails.

[0250] When the number of detection points account is greater than the minimum point threshold mincoun and less than the maximum point threshold maxcount, it means that the number of detection points that meet the height range is appropriate and the dispensing is successful. Therefore, the dispensing detection method 40 can more accurately detect the dispensing situation of the panel to be tested and improve the production quality of electronic equipment.

[0251] Therefore, the dispensing detection method 40 provided in the embodiment of the present application first obtains the depth map data of the panel to be tested and converts the depth map data into a point cloud data set. Then, the normal vector of the point cloud data set is obtained, and the point cloud data set is divided into a vertical point cloud and a horizontal point cloud according to the normal vector. The horizontal point cloud is then segmented into multiple planes, and the largest plane in the multiple planes is used as the target plane. The target plane is then fitted to obtain the plane equation. The plane equation is then visualized, and the reference frame and the frame to be tested are selected. Then, the height threshold range is obtained according to the reference frame, and the number of detection points of the frame to be tested that meets the height threshold range is obtained. Finally, when the number of detection points meets the point number threshold range, it is determined that the dispensing of the frame to be tested is successful. This realizes the detection of the dispensing situation of the panel to be tested from a three-dimensional level, and the detection results are more accurate, thereby effectively improving the production quality of electronic equipment.

[0252] The following combination Figures 9 and 10 , and then a detailed introduction is given to the detection system provided in the embodiment of the present application that uses 3D point cloud data to detect whether the glue dispensing of the panel to be tested is successful.

[0253] First embodiment: Figure 9 A schematic diagram of the structure of a detection system provided in an embodiment of the present application.

[0254] like Figure 9 As shown, illustratively, an embodiment of the present application provides a detection system 50, which may include an assembly line module 501, a three-dimensional camera module 502, and a control module 503. The assembly line module 501 is used to transport the panel to be tested at a preset speed. The three-dimensional camera module 502 is arranged above the assembly line module 501 and is used to capture a depth map of the panel to be tested. The control module 503 is connected to the assembly line module 501 and the three-dimensional camera module 502 respectively. The control module 503 is used to control the operation of the assembly line module 501 and determine whether the dispensing of the panel to be tested is successful based on the depth map of the panel to be tested.

[0255] For example, the 3D camera module 502 may be a 3D structured light camera.

[0256] Exemplarily, the control module 503 may be an electronic device such as an all-in-one machine or a computer with data analysis and calculation functions.

[0257] In an embodiment of the present application, the control module 503 is first used to control the operation of the pipeline module 501, so that the pipeline module 501 controls the panel to be tested to move at a preset speed, thereby facilitating the detection of the glue dispensing conditions at different positions of the panel to be tested. Then, the control module 503 controls the operation of the three-dimensional camera module 502, and the three-dimensional camera module 502 captures a depth map of the panel to be tested. Finally, the control module 503 determines whether the glue dispensing of the panel to be tested is successful based on the depth map of the panel to be tested. In other words, the detection system 50, combined with the above-mentioned glue dispensing detection method 40, can reconstruct point cloud information on a three-dimensional level based on the real-time thermal conductive gel of the panel to be tested on the pipeline module 501, thereby realizing glue dispensing error detection and alarm.

[0258] For example, the detection system 50 may further include a buzzer, which is electrically connected to the control module 503. When the control module 503 detects that the dispensing of the panel to be tested fails, the buzzer sounds an alarm.

[0259] The inspection process of the inspection system 50 includes the following: If a panel fails the inspection, the inspection system 50 will pause and a buzzer will sound. At this time, the inspection personnel will check whether the panel has failed the dispensing, such as glue leaks, glue residue, or glue stringing. If the panel fails, in addition to re-dispensing the glue on the current panel, the inspection personnel can also review the previous two panels to see if there was a glue failure.

[0260] It should be noted that during the inspection process of some panels to be tested, three groups of panels to be tested can be used as a unit for glue dispensing inspection. Therefore, when a problem occurs in a panel to be tested, it is necessary to review whether the glue dispensing of the first two panels to be tested failed.

[0261] If the panel under test does indeed have a dispensing failure, and the inspector has completed processing the panel under test where the alarm occurred, they can use the reset button or reset icon in the inspection system 50 to clear the alarm, allowing the inspection system 50 to resume operation. If the inspector determines that the alarm is a false alarm and the panel under test does not have a dispensing failure, they can simply click the reset button or reset icon to clear the alarm and allow the inspection system 50 to resume operation. This allows for three-dimensional inspection of the dispensing condition of the panel under test, resulting in more accurate inspection results and effectively improving the production quality of electronic equipment.

[0262] Furthermore, because the inspection system 50 utilizes a miniaturized, modular inspection method, it is compatible with a variety of electronic devices, including candy-bar phones, folders, and tablets, and can be deployed at various locations, demonstrating its high versatility. Furthermore, the inspection system 50 in the present embodiment is separated from the dispensing machine, thereby achieving the functionality of a 3D inspection system costing tens of millions of yuan at a very low cost. This does not interfere with main production lines, allowing for the immediate isolation of downtime, further improving the production quality and efficiency of electronic devices.

[0263] Second embodiment: Figure 10 This is a schematic diagram of the structure of another detection system provided in an embodiment of the present application, which introduces a solution of adding an alarm module and a bracket module to the detection system provided in an embodiment of the present application.

[0264] like Figure 10 As shown, illustratively, an embodiment of the present application provides a detection system 50, which may include an assembly line module 501, a three-dimensional camera module 502, a control module 503, an alarm module 504, and / or a support module 505. The assembly line module 501 is used to transport the panel to be tested at a preset speed. The three-dimensional camera module 502 is arranged above the assembly line module 501, and the three-dimensional camera module 502 is used to capture a depth map of the panel to be tested. The control module 503 is connected to the assembly line module 501 and the three-dimensional camera module 502 respectively, and the control module 503 is used to control the operation of the assembly line module 501 and determine whether the dispensing of the panel to be tested is successful based on the depth map of the panel to be tested.

[0265] For example, the 3D camera module 502 may be a 3D structured light camera.

[0266] Exemplarily, the control module 503 may be an electronic device such as an all-in-one machine or a computer with data analysis and calculation functions.

[0267] It should be noted that the alarm module 504 is connected to the control module 503. The alarm module 504 is used to alarm when the panel to be tested fails to dispense glue, thereby reminding the inspection personnel to promptly check the panel to be tested that has not dispensed glue successfully, thereby improving the production quality of the panel to be tested. The bracket module 505 is arranged above the assembly line module 501, and the three-dimensional camera module 502 is arranged on the bracket module, so that the three-dimensional camera module 502 can easily capture a three-dimensional image of the panel to be tested. For example, the bracket module 505 can be a magnetic gantry, and an isolation switch can be set on the magnetic gantry. When the isolation switch is set to "0", the isolation process of the three-dimensional camera module 502 can be realized.

[0268] In an embodiment of the present application, the control module 503 is first used to control the operation of the pipeline module 501, so that the pipeline module 501 controls the panel to be tested to move at a preset speed, thereby facilitating the detection of the glue dispensing conditions at different positions of the panel to be tested. Then, the control module 503 controls the operation of the three-dimensional camera module 502, and the three-dimensional camera module 502 captures a depth map of the panel to be tested. Finally, the control module 503 determines whether the glue dispensing of the panel to be tested is successful based on the depth map of the panel to be tested. In other words, the detection system 50, combined with the above-mentioned glue dispensing detection method 40, can reconstruct point cloud information on a three-dimensional level based on the real-time thermal conductive gel of the panel to be tested on the pipeline module 501, thereby realizing glue dispensing error detection and alarm.

[0269] For example, the detection system 50 may further include a buzzer, which is electrically connected to the control module 503. When the control module 503 detects that the dispensing of the panel to be tested fails, the buzzer sounds an alarm.

[0270] The inspection process of the inspection system 50 includes the following: If a panel fails the inspection, the inspection system 50 will suspend operation, and the alarm module 504 will sound an alarm light and a buzzer will sound an alarm. At this time, the inspection personnel will check whether the panel has failed the dispensing, such as glue leaks, glue residue, or glue stringing. If the panel fails the dispensing, in addition to re-dispensing the current panel, the previous two panels can also be reviewed to see if the dispensing failed.

[0271] It should be noted that during the inspection process of some panels to be tested, three groups of panels to be tested can be used as a unit for glue dispensing inspection. Therefore, when a problem occurs in a panel to be tested, it is necessary to review whether the glue dispensing of the first two panels to be tested failed.

[0272] If the panel under test does indeed have a dispensing failure, and the inspector has completed processing the panel under test where the alarm occurred, they can use the reset button or reset icon in the inspection system 50 to clear the alarm, allowing the inspection system 50 to resume operation. If the inspector determines that the alarm is a false alarm and the panel under test does not have a dispensing failure, they can simply click the reset button or reset icon to clear the alarm and allow the inspection system 50 to resume operation. This allows for three-dimensional inspection of the dispensing condition of the panel under test, resulting in more accurate inspection results and effectively improving the production quality of electronic equipment.

[0273] Furthermore, because the inspection system 50 utilizes a miniaturized, modular inspection method, it is compatible with a variety of electronic devices, including candy-bar phones, folders, and tablets, and can be deployed at various locations, demonstrating its high versatility. Furthermore, the inspection system 50 in the present embodiment is separated from the dispensing machine, thereby achieving the functionality of a 3D inspection system costing tens of millions of yuan at a very low cost. This does not interfere with main production lines, allowing for the immediate isolation of downtime, further improving the production quality and efficiency of electronic devices.

[0274] In addition, if the detection system 50 has continuous false alarms, affecting the normal production of electronic equipment, the isolation switch on the bracket module 505 (such as the magnetic gantry) can be set to "0" to complete the automatic switching to manual operation, realize the isolation of the detection equipment operation, and then contact the detection personnel for subsequent processing.

[0275] It should be noted that the above electronic device is embodied in the form of functional modules. The term "module" here can be implemented in the form of software and / or hardware, and is not specifically limited to this.

[0276] For example, the "module" can be a software program, a hardware circuit, or a combination of both, which implements the above functions. The hardware circuit can include an application specific integrated circuit (ASIC), an electronic circuit, a processor (for example, a shared processor, a dedicated processor, or a group processor, etc.) and a memory for executing one or more software or firmware programs, and a combination logic circuit, and / or other suitable components that support the described functions.

[0277] Therefore, the units of each example described in the embodiments of the present application can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether the functions are performed in hardware or software depends on the specific application and design constraints of the technical solutions. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0278] The electronic device to which the dispensing detection method provided by the embodiments of the present application is applicable is introduced below. Figure 11 A structural schematic diagram of an electronic device provided by an embodiment of the present application is shown in the figure. Figure 11 The dashed line in the figure indicates that the unit or the module is optional; the electronic device can be used to implement the dispensing detection method described in the method embodiment.

[0279] Exemplarily, the embodiments of the present application do not make specific limitation on the type of the electronic device. In some specific embodiments, the electronic device can be a straight phone, a folding phone, a wearable device (for example, a smart bracelet, a smart watch, earphones, etc.), a tablet computer, a laptop, a handheld computer, a notebook computer, an ultra-mobile personal computer (UMPC), a cellular phone, a personal digital assistant (PDA), an augmented reality (AR) \ virtual reality (VR) device, and other IOT (internet of things) devices, and can also be a television, a large screen, a printer, a projector, and other devices. Herein, the embodiments of the present application take a computer as an example for exemplarily description.

[0280] Exemplarily, the electronic device can include one or more processors 110 and a memory 902. The memory 902 is coupled to the one or more processors 110, and the memory 902 is used to store computer program code including computer instructions, and the one or more processors 110 invoke the computer instructions to enable the electronic device to perform the dispensing detection method described above.

[0281] It should be noted that, Figure 11 The structure shown does not constitute a specific limitation on the electronic device. In other embodiments of the application, the electronic device can include more or fewer components than those shown, or the electronic device can include a combination of some of the components shown, or the electronic device can include sub-components of some of the components shown. Figure 11 The structure shown does not constitute a specific limitation on the electronic device. In other embodiments of the application, the electronic device can include more or fewer components than those shown, or the electronic device can include a combination of some of the components shown, or the electronic device can include sub-components of some of the components shown. Figure 11 The structure shown does not constitute a specific limitation on the electronic device. In other embodiments of the application, the electronic device can include more or fewer components than those shown, or the electronic device can include a combination of some of the components shown, or the electronic device can include sub-components of some of the components shown. Figure 11 The structure shown does not constitute a specific limitation on the electronic device. In other embodiments of the application, the electronic device can include more or fewer components than those shown, or the electronic device can include a combination of some of the components shown, or the electronic device can include sub-components of some of the components shown. Figure 11 The components shown can be implemented in hardware, software, or a combination of software and hardware.

[0282] The processor 110 can be a general-purpose processor or a special-purpose processor. For example, the processor 110 can be a central processing unit (CPU), an application processor (AP), a modem processor, a graphics processing unit (GPU), an image signal processor (ISP), a controller, a video codec, a digital signal processor (DSP), a baseband processor, a neural-network processing unit (NPU), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA), or other programmable logic device such as a discrete gate or transistor logic device, or a discrete hardware component. Different processors can be independent devices or integrated devices. The controller can generate operation control signals according to instruction operation codes and timing signals, and complete the control of fetching and executing instructions.

[0283] The processor 110 can also be provided with a memory for storing instructions and data. In some embodiments, the memory in the processor 110 is a cache memory. The memory can store instructions or data that have just been used or are frequently used by the processor 110. If the processor 110 needs to use the instructions or data again, it can directly call them from the memory. This avoids repeated access and reduces the waiting time of the processor 110, thereby improving the efficiency of the system.

[0284] The modem processor may include a modulator and a demodulator. The modulator is used to modulate the low-frequency baseband signal to be transmitted into a medium- or high-frequency signal. The demodulator is used to demodulate the received electromagnetic wave signal into a low-frequency baseband signal. The demodulator then transmits the demodulated low-frequency baseband signal to the baseband processor for processing. After being processed by the baseband processor, the low-frequency baseband signal is passed to the application processor. The application processor outputs the sound signal through the audio device or displays an image or video through the display screen. In some embodiments, the modem processor may be an independent device. In other embodiments, the modem processor may be independent of the processor 110 and be provided in the same device as other functional modules.

[0285] Optionally, the processor 110 may be used to control the electronic device, execute software programs, and process data of the software programs. The electronic device may further include a communication unit 905 for implementing signal input (reception) and output (transmission).

[0286] For example, the electronic device may be a chip, and the communication unit 905 may be an input and / or output circuit of the chip, or the communication unit 905 may be a communication interface of the chip, and the chip may be a component of the electronic device or other electronic devices. For another example, the communication unit 905 may be a transceiver of the electronic device, or the communication unit 905 may include one or more memories 902 on which a program 904 is stored, and the program 904 can be executed by the processor 110 to generate instructions 903, so that the processor 110 executes the dispensing detection method described in the above method embodiment according to the instructions 903.

[0287] Optionally, data may also be stored in the memory 902 .

[0288] Optionally, the processor 110 may also read data stored in the memory 902 . The data may be stored at the same storage address as the program 904 , or may be stored at a different storage address from the program 904 .

[0289] Optionally, the processor 110 and the memory 902 may be provided separately or integrated together, for example, integrated on a system on chip (SOC) of the electronic device.

[0290] Exemplarily, the memory 902 can be used to store the relevant program 904 of the dispensing detection method provided in the embodiment of the present application, and the processor 110 can be used to call the relevant program 904 of the dispensing detection method stored in the memory 902 when executing the dispensing detection method to execute the dispensing detection method of the embodiment of the present application.

[0291] Optionally, the present application also provides a computer program product, which, when executed by the processor 110, implements the dispensing detection method in any method embodiment of the present application.

[0292] For example, the computer program product may be stored in the memory 902 , such as a program 904 , which is converted into an executable target file that can be executed by the processor 110 after undergoing processes such as preprocessing, compilation, assembly, and linking.

[0293] Optionally, the present application also provides a chip system, which is applied to an electronic device. The chip system includes one or more processors, and the one or more processors are used to call computer instructions to enable the electronic device to execute the dispensing detection method.

[0294] Optionally, the present application further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a computer, implements the dispensing detection method described in any method embodiment of the present application. The computer program may be a high-level language program or an executable target program.

[0295] For example, the computer-readable storage medium is memory 902. Memory 902 may be volatile memory or non-volatile memory, or may include both volatile memory and non-volatile memory. The non-volatile memory may be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. The volatile memory may be random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of RAM are available, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link DRAM (SLDRAM), and direct rambus RAM (DR RAM).

[0296] Those skilled in the art can clearly understand that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be realized by electronic hardware or a combination of computer software and electronic hardware. Whether the functions are realized in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to realize the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0297] Those skilled in the art can clearly understand that, for the convenience and brevity of the description, the specific working processes of the above-described system, device and unit can refer to the corresponding processes in the foregoing method embodiments, which will not be repeated here.

[0298] The beneficial effects that the electronic device provided by the embodiments of the present application can achieve can refer to the beneficial effects of the corresponding modules provided in the foregoing, which will not be repeated here.

[0299] It should be understood that the above is only to help those skilled in the art better understand the embodiments of the present application, and is not intended to limit the scope of the embodiments of the present application. Those skilled in the art can obviously make various equivalent modifications or changes according to the above examples, for example, some steps in the above detection method embodiments can be unnecessary, or some steps can be newly added, etc. Or a combination of any two or any multiple embodiments. Such modifications, changes or combinations also fall within the scope of the embodiments of the present application. In addition, the coupling or direct coupling or communication connection between the displayed or discussed can be indirect coupling or communication connection through some interface, device or unit, which can be electrical, mechanical or other forms.

[0300] The units described as separate components can or can not be physically separated, and the components shown as units can or can not be physical units, i.e. they can be located in one place or distributed on multiple network units. Some or all of the units can be selected to achieve the purpose of the embodiments of the present application according to actual needs.

[0301] In addition, each functional unit in each embodiment of the present application can be integrated in one processing unit, or each unit can exist physically, or two or more units can be integrated in one unit.

[0302] It should also be understood that the above description of the embodiments of the present application focuses on the differences between the various embodiments, and the same or similar parts not mentioned can be mutually referred to, and for the sake of brevity, will not be repeated here.

[0303] It should also be understood that in the various embodiments of the present application, the size of the serial number of each process does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0304] It should also be understood that in the embodiments of the present application, "pre-setting" and "pre-definition" can be achieved by pre-saving corresponding codes, tables or other methods that can be used to indicate relevant information in a device (for example, including an electronic device), and the present application does not limit its specific implementation method.

[0305] It should also be understood that the division of the modes, situations, categories and embodiments in the embodiments of the present application is only for the convenience of description and should not constitute a special limitation. The features of various modes, categories, situations and embodiments can be combined without contradiction.

[0306] It should also be understood that in the various embodiments of the present application, unless otherwise specified or there is a logical conflict, the terms and / or descriptions between different embodiments are consistent and can be referenced to each other, and the technical features in different embodiments can be combined to form new embodiments according to their internal logical relationships.

[0307] Finally, it should be noted that the above is only a specific implementation method of the present application, but the scope of protection of the present application is not limited to this. Any technician familiar with the technical field can easily think of changes or replacements within the technical scope disclosed in this application, which should be included in the scope of protection of the present application. Therefore, the scope of protection of the present application should be based on the scope of protection of the claims. In short, the above is only a preferred embodiment of the technical solution of the present application, and is not used to limit the scope of protection of the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of this application should be included in the scope of protection of the present application.

Claims

1. A dispensing detection method, characterized in that: include: Acquire depth map data of the panel to be tested, and convert the depth map data into a point cloud data set; Obtaining a normal vector of the point cloud dataset, and dividing the point cloud dataset into a vertical point cloud and a horizontal point cloud according to the normal vector; Performing multi-plane segmentation on the horizontal point cloud, and taking the largest plane among the multi-planes as the target plane; Fitting the target plane to obtain a plane equation; Visualizing the plane equation and selecting a reference frame and a frame to be measured; Obtaining a height threshold range according to the reference frame, and obtaining the number of detection points of the frame to be measured that meets the height threshold range; When the number of detection points meets the point threshold range, it is determined that the glue dispensing of the frame to be tested is successful.

2. The dispensing detection method according to claim 1, wherein: Before obtaining the depth map data of the panel to be tested, the method further includes: Determine whether the number of preset parameters is correct; the preset parameters include an upper height threshold, a lower height threshold, and a point threshold; When the number of the preset parameters is correct, the detection process continues; When the number of the preset parameters is incorrect, the detection process ends.

3. The dispensing detection method according to claim 2, wherein: Before the detection process ends, the following steps are also included: Alarm and output error information.

4. The dispensing detection method according to any one of claims 1 to 3, characterized in that: Before converting the depth map data into a point cloud data set, the method further includes: The depth map data is traversed and invalid values ​​are removed.

5. The dispensing detection method according to any one of claims 1 to 3, characterized in that: Before converting the depth map data into a point cloud data set, the method further includes: The depth map data is downsampled.

6. The dispensing detection method according to any one of claims 1 to 3, characterized in that: The target plane is fitted using a random sampling consensus algorithm.

7. The dispensing detection method according to any one of claims 1 to 3, characterized in that: Before visualizing the plane equation, the method further includes: Performing spatial leveling correction on the maximum plane according to the plane equation.

8. The dispensing detection method according to any one of claims 1 to 3, characterized in that: Before acquiring the height threshold range according to the reference frame, the method further includes: Local filtering is performed on the reference frame and the frame to be measured.

9. The dispensing detection method according to any one of claims 1 to 3, characterized in that: The altitude threshold range includes an upper altitude threshold, a lower altitude threshold and an average altitude value; The maximum value of the height threshold range is the average height value+the upper height threshold, and the minimum value of the height threshold range is the average height value-the lower height threshold.

10. The dispensing detection method according to any one of claims 1 to 3, characterized in that: The point threshold range includes a maximum point threshold and a minimum point threshold; When the number of detection points is less than the minimum point threshold, it is determined that the glue of the frame to be tested is pulled away; When the number of detection points is greater than the maximum point threshold, it is determined that the frame to be tested is glued and wire-drawn.

11. A detection system based on the dispensing detection method according to any one of claims 1 to 10, characterized in that: Including pipeline module, 3D camera module and control module; The assembly line module is used to transport the panel to be tested at a preset speed; The three-dimensional camera module is arranged above the assembly line module, and the three-dimensional camera module is used to capture a depth map of the panel to be tested; The control module is connected to the pipeline module and the three-dimensional camera module respectively. The control module is used to control the operation of the pipeline module and determine whether the dispensing of the panel to be tested is successful based on the depth map of the panel to be tested.

12. The detection system according to claim 11, wherein: The detection system also includes an alarm module; The alarm module is connected to the control module, and is used to alarm when the glue dispensing of the panel to be tested is not successful.

13. The detection system according to claim 11 or 12, characterized in that: The detection system also includes a bracket module; The support module is arranged above the assembly line module, and the three-dimensional camera module is arranged on the support module.

14. The detection system according to any one of claims 11 or 12, characterized in that: The three-dimensional camera module includes a three-dimensional structured light camera.

15. An electronic device, characterized in that: The electronic device includes: one or more processors, and a memory; The memory is coupled to the one or more processors, and is used to store computer program code, where the computer program code includes computer instructions. The one or more processors call the computer instructions to enable the electronic device to execute the method according to any one of claims 1 to 10.

16. A computer-readable storage medium, characterized in that The computer-readable storage medium includes instructions, and when the instructions are executed on an electronic device, the electronic device executes the method according to any one of claims 1 to 10.

Images