A method, system, device and medium for online detection of beveled edge gypsum board

Abstract

The present invention discloses an online detection method, system, equipment and medium for beveled edge gypsum board, which relates to the field of image data processing technology and includes the following steps: acquiring a detection image based on a top-down perspective of a target gypsum board; identifying pit features of the target gypsum board according to the detection image to obtain a pit defect value; identifying crack features of the target gypsum board according to the detection image to obtain a crack defect value; selecting multiple target measurement points on the beveled edge of the target gypsum board based on a preset selection rule; performing position deviation detection on each target measurement point to obtain a beveled edge slope defect value; inputting the pit defect value, crack defect value and beveled edge slope defect value into a preset defect assessment model to obtain a defect assessment value; judging whether the defect assessment value is greater than a preset standard threshold value, and if so, identifying the target gypsum board as a defective product, and if not, identifying the target gypsum board as a qualified product. The present invention has the advantage of improving the defect detection accuracy of gypsum boards.

Description

Technical Field

[0001] The present invention relates to the technical field of image data processing, and in particular to an online detection method, system, equipment and medium for beveled edge gypsum board. Background Art

[0002] In order to fill the gaps between boards, gypsum boards with beveled edges are now available on the market. The bevel angles are designed according to process requirements. Therefore, when processing beveled gypsum boards, it is necessary to check whether the bevel angles meet the error requirements. It is also necessary to check whether the gypsum boards have surface defects (such as pits, cracks, etc.).

[0003] The existing inspection methods for beveled edge gypsum boards mainly rely on manual visual inspection or the use of simple inspection tools. Due to the large number of inspection items, not only is the inspection accuracy low, but the inspection efficiency is also low for gypsum boards that are transferred and transported in batches on the production line, which ultimately affects the transfer and transportation efficiency. Summary of the Invention

[0004] The main purpose of the present invention is to provide an online detection method, system, equipment and medium for beveled edge gypsum board, aiming to solve the technical problem of low detection accuracy of existing beveled edge gypsum board defect detection methods.

[0005] To achieve the above object, the present invention provides an online detection method for beveled edge gypsum board, comprising the following steps:

[0006] Acquire a detection image based on a top-down perspective of a target gypsum board; wherein the four side walls of the target gypsum board are all provided with beveled edges;

[0007] According to the detection image, the pit features of the target gypsum board are identified to obtain the pit defect value;

[0008] According to the detection image, the crack characteristics of the target gypsum board are identified to obtain the crack defect value;

[0009] Selecting multiple target measurement points on the oblique edge of the target gypsum board based on preset selection rules;

[0010] Perform position deviation detection on each target measurement point to obtain the slope defect value of the bevel;

[0011] Inputting the pit defect value, the crack defect value, and the bevel slope defect value into a preset defect assessment model to obtain a defect assessment value;

[0012] It is determined whether the defect assessment value is greater than a preset standard threshold. If so, the target gypsum board is identified as a defective product. If not, the target gypsum board is identified as a qualified product.

[0013] Optionally, a position deviation test is performed on each target measurement point to obtain a slope defect value of the bevel, including:

[0014] Obtaining a first detection distance from a first detection point to a corresponding target measurement point, and simultaneously obtaining a second detection distance from a second detection point to the same target measurement point; wherein the detection direction of the first detection point is a top-down direction of the target gypsum board, and the detection direction of the second detection point is a side-view direction of the target gypsum board;

[0015] Obtaining a first deviation value between the first detection distance and a preset first theoretical distance;

[0016] Obtaining a second deviation value between the second detection distance and a preset second theoretical distance;

[0017] Outputting an average value of the first deviation value and the second deviation value as a defect characteristic value corresponding to the target measurement point;

[0018] The maximum value of the defect characteristic values corresponding to multiple target measurement points is output as the bevel slope defect value.

[0019] Optionally, obtaining a first detection distance from a first detection point to a corresponding target measurement point, and simultaneously obtaining a second detection distance from a second detection point to the same target measurement point, includes:

[0020] Acquire a first measurement distance from the first detection point to the corresponding target measurement point based on laser ranging, and simultaneously acquire a second measurement distance from the first detection point to the corresponding target measurement point based on machine vision recognition;

[0021] Assigning weights to the first measured distance and the second measured distance by confidence to obtain a first detection distance after data fusion;

[0022] Acquire a third measurement distance from the second detection point to the same target measurement point based on laser ranging, and simultaneously acquire a fourth measurement distance from the second detection point to the same target measurement point based on machine vision recognition;

[0023] The third measured distance and the fourth measured distance are weighted by confidence to obtain a second detection distance after data fusion.

[0024] Optionally, the selection rule is:

[0025] Avoid areas with pit features on the beveled edges of the target drywall;

[0026] Avoid areas with crack features on the beveled edges of the target drywall;

[0027] Multiple target measurement points are selected along the length direction and slope direction of the hypotenuse of the target gypsum board.

[0028] Optionally, identifying pit features of the target gypsum board based on the detection image to obtain a pit defect value includes:

[0029] Based on the detection image, the pit features of the target gypsum board are identified and extracted; wherein the pit features include the pit area S, the pit depth H and the number of pits N1;

[0030] According to the pit characteristics, the pit defect value F is obtained. The expression of F is:

[0031] F=K1*S+K2*H+K3*N1;

[0032] Wherein, K1 is the first adjustment coefficient, K2 is the second adjustment coefficient, and K3 is the third adjustment coefficient.

[0033] Optionally, based on the detection image, identifying crack features of the target gypsum board to obtain a crack defect value includes:

[0034] Identify and extract crack features of the target gypsum board based on the detection image; the crack features include crack length L and crack number N2;

[0035] According to the crack characteristics, the crack defect value R is obtained. The expression of R is:

[0036] R=K4*L+K5*N2;

[0037] Wherein, K4 is the fourth adjustment coefficient, and K5 is the fifth adjustment coefficient.

[0038] Optionally, the defect assessment model is expressed as:

[0039] Q=W1*E+W2*F+W3*R;

[0040] Where Q is the defect evaluation value, E is the hypotenuse slope defect value, F is the pit defect value, R is the crack defect value, W1 is the first weight value, W2 is the second weight value, and W3 is the third weight value.

[0041] To achieve the above object, the present invention further provides an online detection system for beveled edge gypsum board, comprising:

[0042] An image acquisition module is used to acquire a detection image based on a top-down perspective of a target gypsum board, wherein all four side walls of the target gypsum board are provided with beveled edges;

[0043] A pit detection module is used to identify pit features of the target gypsum board based on the detection image to obtain the pit defect value;

[0044] A crack detection module is used to identify crack features of the target gypsum board based on the detection image to obtain the crack defect value;

[0045] A measurement point selection module, for selecting a plurality of target measurement points on the bevel edge of the target gypsum board based on a preset selection rule;

[0046] Bevel detection module, used to detect the position deviation of each target measurement point to obtain the bevel slope defect value;

[0047] A defect assessment module, for inputting a pit defect value, a crack defect value, and a bevel slope defect value into a preset defect assessment model to obtain a defect assessment value;

[0048] The data processing module is used to determine whether the defect assessment value is greater than a preset standard threshold. If so, the target gypsum board is identified as a defective product; if not, the target gypsum board is identified as a qualified product.

[0049] To achieve the above object, the present invention further provides a computer device, which includes a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the above method.

[0050] To achieve the above object, the present invention further provides a computer-readable storage medium, on which a computer program is stored. A processor executes the computer program to implement the above method.

[0051] The beneficial effects that can be achieved by the present invention are as follows:

[0052] The present invention can display the characteristic information of the main detection areas such as the surface and bevel of the gypsum board in the detection image obtained based on the top view of the target gypsum board, including pit characteristics and crack characteristics, so as to calculate the corresponding pit defect value and crack defect value respectively. When performing bevel slope detection, if the slope detection is directly performed on the entire bevel surface, not only is the detection difficult, but it is also difficult to accurately grasp the local deformation information during the whole surface detection, resulting in insufficient detection accuracy. Therefore, the present invention first selects multiple target measurement points on the bevel of the target gypsum board based on a preset selection rule, and then performs position deviation detection on each target measurement point. If there is a slope error, the position of the corresponding target measurement point will be offset relative to the theoretical position, so as to calculate the deviation value according to the offset. The bevel slope defect value is calculated and the bevel slope error can be characterized based on the defect value. The present invention uses a method of position detection at multiple measuring points to effectively detect the local deformation of the bevel and more accurately grasp the local deformation of the bevel. The detection difficulty is also relatively low. Finally, the pit defect value, crack defect value and bevel slope defect value are input into a preset defect assessment model to obtain a defect assessment value. It is judged whether the defect assessment value is greater than a preset standard threshold. If so, the target gypsum board is identified as a defective product. If not, the target gypsum board is identified as a qualified product. This allows online defect detection of the gypsum board and comprehensive detection of multiple defects, overcoming the problems of low accuracy and low efficiency of manual detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following briefly describes the drawings required for the specific embodiments or the description of the prior art. Similar elements or parts are generally identified by similar reference numerals throughout the drawings. Elements or parts in the drawings are not necessarily drawn to scale.

[0054] Figure 1 Schematic diagram of a process of an online detection method for beveled edge gypsum board according to an embodiment of the present invention;

[0055] Figure 2 is a schematic diagram of identifying pit features and crack features based on a detection image in an embodiment of the present invention;

[0056] Figure 3 Schematic diagram of the principle of position deviation detection for a target measurement point in an embodiment of the present invention.

[0057] Reference numerals:

[0058] 110 - target gypsum board, 111 - bevel edge, 120 - pit feature, 130 - crack feature, 140 - target measurement point, 150 - first detection point, 160 - second detection point.

[0059] The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings and in conjunction with the embodiments. DETAILED DESCRIPTION

[0060] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0061] It should be noted that if there are descriptions involving "first", "second", etc. in the embodiments of the present invention, the descriptions of "first", "second", etc. are only for descriptive purposes and cannot be understood as indicating or suggesting their relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of such features. In addition, the technical solutions between the various embodiments can be combined with each other, but they must be based on the fact that they can be implemented by ordinary technicians in this field. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such a combination of technical solutions does not exist and is not within the scope of protection required by the present invention.

[0062] Example 1

[0063] Reference Figure 1-Figure 3This embodiment provides an online detection method for beveled edge gypsum board, comprising the following steps:

[0064] A detection image is acquired based on a top-down perspective of the target gypsum board 110; wherein the four side walls of the target gypsum board 110 are all provided with bevel edges 111;

[0065] Identify the pit feature 120 of the target gypsum board 110 according to the detection image to obtain the pit defect value;

[0066] Identifying crack features 130 of the target gypsum board 110 based on the detection image to obtain a crack defect value;

[0067] Selecting a plurality of target measurement points 140 on the bevel 111 of the target gypsum board 110 based on a preset selection rule;

[0068] Performing position deviation detection on each target measurement point 140 to obtain a slope defect value of the bevel;

[0069] Inputting the pit defect value, the crack defect value, and the bevel slope defect value into a preset defect assessment model to obtain a defect assessment value;

[0070] It is determined whether the defect evaluation value is greater than a preset standard threshold value. If so, the target gypsum board 110 is identified as a defective product. If not, the target gypsum board 110 is identified as a qualified product.

[0071] In this embodiment, the detection image obtained based on the top view of the target gypsum board 110 can display the feature information of the main detection areas such as the upper surface and the bevel 111 of the gypsum board, including the pit feature 120 and the crack feature 130, so as to calculate the corresponding pit defect value and crack defect value respectively. When performing the slope detection of the bevel 111, if the slope detection is directly performed on the entire surface of the bevel 111, not only is the detection difficult, but it is also difficult to accurately grasp the local deformation information by the whole surface detection, resulting in insufficient detection accuracy. Therefore, in this embodiment, a plurality of target measurement points 140 are first selected on the bevel 111 of the target gypsum board 110 based on a preset selection rule, and then a position deviation detection is performed on each target measurement point 140. If there is a slope error, the position of the corresponding target measurement point 140 will be offset relative to the theoretical position, and the position of the target measurement point 140 will be offset from the theoretical position. The slope defect value of the bevel 111 is calculated based on the offset situation, and the slope error of the bevel 111 can be characterized based on the defect value. This embodiment uses a plurality of measuring points for position detection, which can effectively detect the local deformation of the bevel 111 accurately, and more accurately grasp the local deformation of the bevel 111, and the detection difficulty is also relatively low. Finally, the pit defect value, the crack defect value and the slope defect value of the bevel 111 are input into a preset defect assessment model to obtain a defect assessment value, and determine whether the defect assessment value is greater than a preset standard threshold. If so, the target gypsum board 110 is identified as a defective product. If not, the target gypsum board 110 is identified as a qualified product, thereby realizing online defect detection of the gypsum board and performing comprehensive detection of multiple defects, overcoming the problems of low accuracy and low efficiency of manual detection.

[0072] It should be noted that industrial cameras and other detection instruments can be configured at the corresponding positions of the conveyor frame used to transport gypsum boards, so as to realize online image acquisition and recognition of the moving gypsum boards. The industrial camera is electrically connected to an industrial computer, which can process and analyze the collected images, and finally obtain and display the detection data for easy viewing.

[0073] As an optional embodiment, performing position deviation detection on each target measurement point 140 to obtain a bevel slope defect value includes:

[0074] Obtain a first detection distance from a first detection point 150 to a corresponding target measurement point 140, and simultaneously obtain a second detection distance from a second detection point 160 to the same target measurement point 140; wherein the detection direction of the first detection point 150 is a top-down direction of the target gypsum board 110, and the detection direction of the second detection point 160 is a side-down direction of the target gypsum board 110;

[0075] Obtaining a first deviation value between the first detection distance and a preset first theoretical distance;

[0076] Obtaining a second deviation value between the second detection distance and a preset second theoretical distance;

[0077] Outputting an average of the first deviation value and the second deviation value as a defect characteristic value corresponding to the target measurement point 140;

[0078] The maximum value of the defect characteristic values corresponding to the plurality of target measurement points 140 is output as the hypotenuse slope defect value.

[0079] In this embodiment, corresponding first and second detection points 150 and 160 are established based on the top-view and side-view directions of the target gypsum board 110, respectively. A first detection distance h1 from the first detection point 150 to the corresponding target measurement point 140, and a second detection distance h2 from the second detection point 160 to the same target measurement point 140, are calculated. Acquiring detection data from two different detection directions reduces the risk of inaccurate calculations caused by distortion of a single detection data, thereby improving data accuracy. If there is a slope deviation, the position of the target measurement point 140 will be offset. In this case, a first deviation value |h1-d1| between the first detection distance h1 and the corresponding first theoretical distance d1, and a second deviation value |h2-d2| between the second detection distance h2 and the corresponding second theoretical distance d2 are calculated. Finally, the average of the first and second deviation values is output as the defect characteristic value corresponding to the target measurement point 140. Defect characteristic values corresponding to multiple target measurement points 140 are calculated using the above measurement method, and the maximum value is output as the hypotenuse slope defect value, thereby effectively characterizing the error in the hypotenuse slope.

[0080] It should be noted that after the positions of the first detection point 150 and the second detection point 160 are determined, corresponding detection instruments, such as industrial cameras, laser rangefinders, etc., can be installed at these positions.

[0081] As an optional embodiment, obtaining a first detection distance from the first detection point 150 to the corresponding target measurement point 140 and simultaneously obtaining a second detection distance from the second detection point 160 to the same target measurement point 140 include:

[0082] Acquire a first measurement distance from the first detection point 150 to the corresponding target measurement point 140 based on laser ranging, and simultaneously acquire a second measurement distance from the first detection point 150 to the corresponding target measurement point 140 based on machine vision recognition;

[0083] Assigning weights to the first measured distance and the second measured distance by confidence to obtain a first detection distance after data fusion;

[0084] Acquire a third measured distance from the second detection point 160 to the same target measurement point 140 based on laser ranging, and simultaneously acquire a fourth measured distance from the second detection point 160 to the same target measurement point 140 based on machine vision recognition;

[0085] The third measured distance and the fourth measured distance are weighted by confidence to obtain a second detection distance after data fusion.

[0086] In this embodiment, when calculating the first detection distance, a first measurement distance from the first detection point 150 to the corresponding target measurement point 140 is calculated at the first detection point 150 based on the principle of laser ranging (i.e., using a laser rangefinder). A depth image is captured based on the principle of machine vision recognition (i.e., using a depth camera), thereby calculating a second measurement distance from the pixel corresponding to the target measurement point 140 to the first detection point 150. Using two measuring instruments to collect data for the same detection point further reduces the risk of measurement data distortion or large accidental errors caused by using a single measuring instrument. The first and second measurement distances are then weighted based on confidence levels. The weighting can be based on historical big data training, for example, a weight of 0.6 for the first measurement distance and a weight of 0.4 for the second measurement distance. This results in the calculation of the first detection distance after data fusion, providing an accurate data source for the subsequent accurate calculation of the hypotenuse slope defect value. Similarly, when calculating the second detection distance, data is collected using the two measuring instruments, and weights are assigned based on confidence levels, thereby achieving a more accurate second detection distance.

[0087] It should be noted that the first detection point 150 and the second detection point 160 mainly refer to the horizontal line with the same spacing as the target gypsum board 110. Any point on the horizontal line with the same spacing can be used as the first detection point 150 or the second detection point 160. Therefore, the above two measuring instruments can be respectively set at the same horizontal line with the same spacing. For example, when the target gypsum board 110 is moved to the measurement area of the laser rangefinder to complete the measurement, it is moved again to the measurement area of the depth camera for measurement. The laser rangefinder and depth camera located on the same horizontal line with the same spacing are at the same height position, and then the two measurement data can be integrated.

[0088] As an optional implementation, the selection rule is:

[0089] Avoid the area with the dimple feature 120 on the bevel edge 111 of the target gypsum board 110;

[0090] Avoid areas with crack features 130 on the beveled edge 111 of the target gypsum board 110;

[0091] A plurality of target measurement points 140 are selected along the length direction and the slope direction of the hypotenuse 111 of the target gypsum board 110 .

[0092] In this embodiment, when selecting the target measurement points 140, the areas corresponding to the previously identified pit features 120 and crack features 130 should be avoided to avoid distortion of the detection data. At the same time, multiple target measurement points 140 are selected in the length direction and the slope direction of the hypotenuse 111 to ensure the discreteness of the target measurement points 140, so as to ensure that the measurement data can simultaneously characterize the overall and local errors of the hypotenuse 111, thereby improving the accuracy of the detection data.

[0093] As an optional embodiment, identifying the pit feature 120 of the target gypsum board 110 according to the detection image to obtain the pit defect value includes:

[0094] According to the detection image, the pit features 120 of the target gypsum board 110 are identified and extracted; wherein the pit features 120 include the pit area S, the pit depth H and the number of pits N1;

[0095] According to the pit feature 120, the pit defect value F is obtained. The expression of F is:

[0096] F=K1*S+K2*H+K3*N1;

[0097] Wherein, K1 is the first adjustment coefficient, K2 is the second adjustment coefficient, and K3 is the third adjustment coefficient.

[0098] In this embodiment, the detection image here should be a depth image, that is, the pit area S, pit depth H and pit number N1 can be identified and calculated, and then the expression of the pit defect value F is input. At the same time, considering the different attributes of the above parameters, corresponding adjustment coefficients (which may include weight coefficients) are assigned respectively, so that the parameters of the above three different attributes can be quantitatively superimposed. Therefore, based on the above formula, the corresponding pit defect value F can be finally quantified and calculated. Among them, a pit area S that is too large, a pit depth H that is too deep or an excessive number of pits N1 will affect the surface quality of the gypsum board. Therefore, based on the above formula, the influence of a single defect manifestation on the overall quality can be characterized, and the influence of the superposition of all defect manifestations on the overall quality can also be characterized. Therefore, the degree of influence of the pit defect on the surface quality of the gypsum board can be accurately characterized, and the calculation is accurate and effective.

[0099] As an optional embodiment, identifying the crack feature 130 of the target gypsum board 110 according to the detection image to obtain the crack defect value includes:

[0100] According to the detection image, the crack feature 130 of the target gypsum board 110 is identified and extracted; wherein the crack feature 130 includes the crack length L and the number of cracks N2;

[0101] According to the crack feature 130, the crack defect value R is obtained. The expression of R is:

[0102] R=K4*L+K5*N2;

[0103] Wherein, K4 is the fourth adjustment coefficient, and K5 is the fifth adjustment coefficient.

[0104] In this embodiment, based on the detection image, the crack length L and the number of cracks N2 can be identified and calculated. By inputting the above formula, the crack defect value R can be quantified and calculated. Also, considering the different parameter properties, they are converted through the corresponding adjustment coefficients respectively, so that the two parameters can be quantitatively superimposed, and finally the corresponding crack defect value R can be accurately calculated.

[0105] As an optional implementation, the defect assessment model is expressed as:

[0106] Q=W1*E+W2*F+W3*R;

[0107] Where Q is the defect evaluation value, E is the hypotenuse slope defect value, F is the pit defect value, R is the crack defect value, W1 is the first weight value, W2 is the second weight value, and W3 is the third weight value.

[0108] In this embodiment, after calculating the pit defect value, crack defect value and bevel slope defect value, they are substituted into the above formula. Taking into account the different degrees of influence of different defects on the overall quality, different weight values are also assigned here. According to historical big data training, W1=0.4, W2=0.35, and W3=0.25 are preferably used here, and the defect assessment value Q can be quantitatively calculated, which has strong reference and guidance value.

[0109] Example 2

[0110] Based on the same inventive concept as the above embodiment, this embodiment further provides an online detection system for beveled edge gypsum boards, comprising:

[0111] An image acquisition module, configured to acquire a detection image based on a top-down perspective of a target gypsum board 110 , wherein the four side walls of the target gypsum board 110 are all provided with bevel edges 111 ;

[0112] a pit detection module, configured to identify a pit feature 120 of the target gypsum board 110 based on the detection image to obtain a pit defect value;

[0113] A crack detection module, configured to identify crack features 130 of the target gypsum board 110 based on the detection image to obtain a crack defect value;

[0114] A measurement point selection module, configured to select a plurality of target measurement points 140 on the bevel 111 of the target gypsum board 110 based on a preset selection rule;

[0115] A bevel detection module is used to perform position deviation detection on each target measurement point 140 to obtain a bevel slope defect value;

[0116] A defect assessment module, for inputting a pit defect value, a crack defect value, and a bevel slope defect value into a preset defect assessment model to obtain a defect assessment value;

[0117] The data processing module is used to determine whether the defect assessment value is greater than a preset standard threshold. If so, the target gypsum board 110 is identified as a defective product. If not, the target gypsum board 110 is identified as a qualified product.

[0118] The relevant explanations and examples of each module in the system of this embodiment can refer to the methods of the aforementioned embodiments and will not be repeated here.

[0119] Example 3

[0120] Based on the same inventive concept as the above embodiment, this embodiment provides a computer device, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the above method.

[0121] Example 4

[0122] Based on the same inventive concept as the above embodiment, this embodiment provides a computer-readable storage medium, on which a computer program is stored. A processor executes the computer program to implement the above method.

[0123] The above are only preferred embodiments of the present invention and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention description and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A method for online detection of beveled edge gypsum board, characterized in that: The following steps are involved: Acquire a detection image based on a top-down perspective of a target gypsum board; wherein the four side walls of the target gypsum board are all provided with beveled edges; According to the detection image, the pit features of the target gypsum board are identified to obtain the pit defect value; According to the detection image, the crack characteristics of the target gypsum board are identified to obtain the crack defect value; Selecting multiple target measurement points on the oblique edge of the target gypsum board based on preset selection rules; Perform position deviation detection on each target measurement point to obtain the slope defect value of the bevel; Inputting the pit defect value, the crack defect value, and the bevel slope defect value into a preset defect assessment model to obtain a defect assessment value; It is determined whether the defect assessment value is greater than a preset standard threshold. If so, the target gypsum board is identified as a defective product. If not, the target gypsum board is identified as a qualified product.

2. The online detection method for beveled edge gypsum board according to claim 1, characterized in that: Perform position deviation detection on each target measurement point to obtain the slope defect value of the bevel, including: Obtaining a first detection distance from a first detection point to a corresponding target measurement point, and simultaneously obtaining a second detection distance from a second detection point to the same target measurement point; wherein the detection direction of the first detection point is a top-down direction of the target gypsum board, and the detection direction of the second detection point is a side-view direction of the target gypsum board; Obtaining a first deviation value between the first detection distance and a preset first theoretical distance; Obtaining a second deviation value between the second detection distance and a preset second theoretical distance; Outputting an average value of the first deviation value and the second deviation value as a defect characteristic value corresponding to the target measurement point; The maximum value of the defect characteristic values corresponding to multiple target measurement points is output as the bevel slope defect value.

3. The online detection method for beveled edge gypsum board according to claim 2, characterized in that: Acquiring a first detection distance from a first detection point to a corresponding target measurement point, and simultaneously acquiring a second detection distance from a second detection point to the same target measurement point, including: Acquire a first measurement distance from the first detection point to the corresponding target measurement point based on laser ranging, and simultaneously acquire a second measurement distance from the first detection point to the corresponding target measurement point based on machine vision recognition; Assigning weights to the first measured distance and the second measured distance by confidence to obtain a first detection distance after data fusion; Acquire a third measurement distance from the second detection point to the same target measurement point based on laser ranging, and simultaneously acquire a fourth measurement distance from the second detection point to the same target measurement point based on machine vision recognition; The third measured distance and the fourth measured distance are weighted by confidence to obtain a second detection distance after data fusion.

4. The online detection method for beveled edge gypsum board according to claim 1, characterized in that: The selection rules are: Avoid areas with pit features on the beveled edges of the target drywall; Avoid areas with crack features on the beveled edges of the target drywall; Multiple target measurement points are selected along the length direction and slope direction of the hypotenuse of the target gypsum board.

5. The online detection method for beveled edge gypsum board according to claim 1, characterized in that: Based on the inspection image, the pit features of the target gypsum board are identified to obtain the pit defect value, including: Based on the detection image, the pit features of the target gypsum board are identified and extracted; wherein the pit features include the pit area S, the pit depth H and the number of pits N1; According to the pit characteristics, the pit defect value F is obtained. The expression of F is: F=K1*S+K2*H+K3*N1; Wherein, K1 is the first adjustment coefficient, K2 is the second adjustment coefficient, and K3 is the third adjustment coefficient.

6. The online detection method for beveled edge gypsum board according to claim 1, characterized in that: Based on the inspection image, the crack characteristics of the target gypsum board are identified to obtain the crack defect value, including: Identify and extract crack features of the target gypsum board based on the detection image; the crack features include crack length L and crack number N2; According to the crack characteristics, the crack defect value R is obtained. The expression of R is: R=K4*L+K5*N2; Wherein, K4 is the fourth adjustment coefficient, and K5 is the fifth adjustment coefficient.

7. An online detection method for beveled edge gypsum board according to any one of claims 1 to 6, characterized in that: The expression of the defect assessment model is: Q=W1*E+W2*F+W3*R; Where Q is the defect evaluation value, E is the hypotenuse slope defect value, F is the pit defect value, R is the crack defect value, W1 is the first weight value, W2 is the second weight value, and W3 is the third weight value.

8. An online detection system for beveled edge gypsum board, characterized in that: include: An image acquisition module is used to acquire a detection image based on a top-down perspective of a target gypsum board, wherein all four side walls of the target gypsum board are provided with beveled edges; A pit detection module is used to identify pit features of the target gypsum board based on the detection image to obtain the pit defect value; A crack detection module is used to identify crack features of the target gypsum board based on the detection image to obtain the crack defect value; A measurement point selection module, for selecting a plurality of target measurement points on the bevel edge of the target gypsum board based on a preset selection rule; Bevel detection module, used to detect the position deviation of each target measurement point to obtain the bevel slope defect value; A defect assessment module, for inputting a pit defect value, a crack defect value, and a bevel slope defect value into a preset defect assessment model to obtain a defect assessment value; The data processing module is used to determine whether the defect assessment value is greater than a preset standard threshold. If so, the target gypsum board is identified as a defective product; if not, the target gypsum board is identified as a qualified product.

9. A computer device, characterized in that: The computer device includes a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement an online detection method for beveled edge gypsum board according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, and the processor executes the computer program to implement the online detection method for beveled edge gypsum board according to any one of claims 1 to 7.

Images