3D gluing defect detection method and device and computer equipment

Abstract

The invention discloses a 3D gluing defect detection method and device and computer equipment. The method comprises the following steps: according to an automobile head image, an automobile body image and an automobile tail image for automobile gluing, respectively generating three-dimensional outlines for automobile head, automobile body and automobile tail gluing in the automobile gluing process in a preset three-dimensional direction, and taking an original point in the preset three-dimensional direction as a coordinate starting point, acquiring three-dimensional point cloud data of the vehicle head gluing three-dimensional contour, the vehicle body gluing three-dimensional contour and the vehicle tail gluing three-dimensional contour, and converting the three-dimensional point cloud data into two-dimensional coordinate data; and carrying out comparison detection on the two-dimensional coordinate data of the automobile head glue, the automobile body glue and the automobile tail glue and preset standard coordinate data of each point on the gluing surfaces of the automobile head glue, the automobile body glue and the automobile tail glue to obtain detection results of the automobile head glue, the automobile body glue and the automobile tail glue. Through the mode, the detection difficulty of the automobile gluing defect is reduced, and the detection accuracy of the automobile gluing defect is improved.

Description

Technical Field

[0001] The present invention relates to the field of automobile gluing technology, and in particular to a 3D gluing defect detection method, device and computer equipment. Background Art

[0002] Automobile gluing is a process widely used on automobile bodies. It is a process that mainly uses the mechanical bonding force, physical adsorption force and chemical bonding force generated by the adhesive on the connection surface to connect two adhesive parts. After the glue pattern is formed, the glue coating quality test is required to determine whether the glue coating quality meets the requirements.

[0003] The existing 3D gluing defect detection scheme generally uses a line laser profiler to perform 3D gluing defect detection using laser triangulation. It can obtain the 3D contour data of the gluing in real time, continuously, at high speed and with high precision, and then rely on this 3D contour data to meet subsequent defect detection needs. However, since the glued car body, hood, windshield in the assembly workshop, etc. have different shapes and are uneven, the contour obtained by the line laser profiler has a certain inclination angle in space, and the same 3D contour has multiple curve features at the same time, such as ellipses, straight lines, right angles, etc., which increases the difficulty of detecting gluing defects and reduces the accuracy of automobile gluing defect detection. Summary of the invention

[0004] In view of this, the purpose of the present invention is to propose a 3D gluing defect detection method, device and computer equipment, which can reduce the difficulty of detecting automobile gluing defects and improve the accuracy of automobile gluing defect detection.

[0005] According to one aspect of the present invention, a 3D gluing defect detection method is provided, comprising: generating a three-dimensional contour of the gluing of the front, body and rear of a car in a preset three-dimensional direction according to a front image, body image and rear image of the gluing of the car; taking the origin of the preset three-dimensional direction as the coordinate starting point, obtaining three-dimensional point cloud data of the three-dimensional contour of the gluing of the front, body and rear, and converting the three-dimensional point cloud data into two-dimensional coordinate data; comparing and detecting the two-dimensional coordinate data of the gluing of the front, body and rear with the preset standard coordinate data of each point on the gluing surface of the front, body and rear of the car, to obtain the detection results of the gluing defects of the front, body and rear of the car.

[0006] Among them, according to the front image, body image and rear image of the car, in the preset three-dimensional direction, respectively generate the three-dimensional contour of the front gluing process of the car, the three-dimensional contour of the body gluing and the three-dimensional contour of the rear gluing, including: according to the front image, body image and rear image of the car, in the expected three-dimensional direction, respectively draw the first dimension direction contour image, the second dimension direction contour image and the third dimension direction contour image of the front image, body image and rear image of the car in the three-dimensional direction, apply the three-dimensional reconstruction method, combine the first dimension direction contour image, the second dimension direction contour image and the third dimension direction contour image, and respectively generate the three-dimensional contour of the front gluing process of the car, the three-dimensional contour of the body gluing and the three-dimensional contour of the rear gluing.

[0007] Among them, taking the origin of the preset three-dimensional direction as the coordinate starting point, obtaining the three-dimensional point cloud data of the three-dimensional contour of the glued front of the vehicle, the three-dimensional contour of the glued body and the three-dimensional contour of the glued rear of the vehicle, and converting the three-dimensional point cloud data into two-dimensional coordinate data, includes: taking the origin of the preset three-dimensional direction as the coordinate starting point, obtaining the three-dimensional point cloud data of the three-dimensional contour of the glued front of the vehicle, the three-dimensional contour of the glued body and the three-dimensional contour of the glued rear of the vehicle, and taking a parallel line that intersects with the coordinate starting point and is parallel to the front of the vehicle, the body and the rear of the vehicle as a baseline, based on the baseline, projecting the three-dimensional point cloud data into a plane view, and converting the three-dimensional point cloud data into two-dimensional coordinate data according to the plane view.

[0008] Among them, the two-dimensional coordinate data of the front glue coating, the body glue coating and the rear glue coating are compared and detected with the preset standard coordinate data of each point on the glue surface of the front glue coating, the body glue coating and the rear glue coating of the automobile, so as to obtain the detection result of the glue defects of the front, body and rear glue of the automobile, including: comparing and detecting the two-dimensional coordinate data of the front glue coating, the body glue coating and the rear glue coating with the preset standard coordinate data of each point on the glue surface of the front glue coating, the body glue coating and the rear glue coating of the automobile, marking the position of each type of glue defect with different colors, and obtaining the detection result of the glue defects of the front, body and rear of the automobile.

[0009] Among them, after comparing and detecting the two-dimensional coordinate data of the front glue coating, body glue coating and rear glue coating with the preset standard coordinate data of each point on the glue coating surface of the front glue coating, body glue coating and rear glue coating of the automobile, and obtaining the detection results of the glue coating defects of the front, body and rear of the automobile, it also includes: correcting the glue coating defects of the front, body and rear of the automobile according to the detection results of the glue coating defects of the front, body and rear of the automobile.

[0010] According to another aspect of the present invention, a 3D gluing defect detection device is provided, comprising: a generation module, a conversion module and a detection module; the generation module is used to generate a three-dimensional contour of the front gluing, a three-dimensional contour of the body gluing and a three-dimensional contour of the rear gluing of the automobile in a preset three-dimensional direction according to the front image, the body image and the rear image of the automobile gluing; the conversion module is used to obtain three-dimensional point cloud data of the three-dimensional contour of the front gluing, the three-dimensional contour of the body gluing and the three-dimensional contour of the rear gluing with the origin of the preset three-dimensional direction as the coordinate starting point, and convert the three-dimensional point cloud data into two-dimensional coordinate data; the detection module is used to compare and detect the two-dimensional coordinate data of the front gluing, the body gluing and the rear gluing with the preset standard coordinate data of each point on the gluing surface of the front gluing, the body gluing and the rear gluing of the automobile, so as to obtain the detection results of the gluing defects of the front, body and rear of the automobile.

[0011] Among them, the generation module is specifically used to: draw the first dimension direction contour image, the second dimension direction contour image, and the third dimension direction contour image of the front image, the body image, and the rear image of the car in the three-dimensional direction in the expected three-dimensional direction according to the front image, the body image, and the rear image of the car being glued, and apply a three-dimensional reconstruction method to combine the first dimension direction contour image, the second dimension direction contour image, and the third dimension direction contour image to generate the three-dimensional contour of the front gluing process, the three-dimensional contour of the body gluing process, and the three-dimensional contour of the rear gluing process.

[0012] Among them, the conversion module is specifically used to: take the origin of the preset three-dimensional direction as the coordinate starting point, obtain the three-dimensional point cloud data of the three-dimensional contour of the glued front of the vehicle, the three-dimensional contour of the glued body and the three-dimensional contour of the glued rear of the vehicle, and take the parallel line intersecting with the coordinate starting point and parallel to the front of the vehicle, the body and the rear of the vehicle as the baseline, based on the baseline, project the three-dimensional point cloud data into a plane view, and convert the three-dimensional point cloud data into two-dimensional coordinate data according to the plane view.

[0013] Among them, the detection module is specifically used to: compare and detect the two-dimensional coordinate data of the front glue coating, body glue coating and rear glue coating with the preset standard coordinate data of each point on the glue coating surface of the front glue coating, body glue coating and rear glue coating of the automobile, and use different colors to mark the positions of various types of glue defects to obtain the detection results of the glue coating defects of the front, body and rear of the automobile.

[0014] Among them, the 3D glue coating defect detection device also includes a correction module, which is used to correct the glue coating defects of the front, body and rear of the automobile according to the detection results of the glue coating defects of the front, body and rear of the automobile.

[0015] According to another aspect of the present invention, there is provided a computer device, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the 3D glue coating defect detection method as described in any one of the above.

[0016] According to another aspect of the present invention, a computer-readable storage medium is provided, storing a computer program, wherein when the computer program is executed by a processor, the 3D gluing defect detection method as described in any one of the above is implemented.

[0017] It can be found that the above scheme can generate the three-dimensional contour of the front gluing process of the car, the three-dimensional contour of the body gluing and the three-dimensional contour of the rear gluing process of the car in a preset three-dimensional direction according to the front image, the body image and the rear image of the car gluing, and can use the origin of the preset three-dimensional direction as the coordinate starting point to obtain the three-dimensional point cloud data of the three-dimensional contour of the front gluing, the three-dimensional contour of the body gluing and the three-dimensional contour of the rear gluing, and convert the three-dimensional point cloud data into two-dimensional coordinate data, and can compare and detect the two-dimensional coordinate data of the front gluing, the body gluing and the rear gluing with the preset standard coordinate data of each point on the gluing surface of the front gluing, the body gluing and the rear gluing of the car, and obtain the detection results of the glue defects of the front, body and rear of the car, thereby reducing the difficulty of detecting automobile glue defects and improving the accuracy of automobile glue defect detection.

[0018] Furthermore, the above scheme can draw the first dimension direction contour image, the second dimension direction contour image, and the third dimension direction contour image of the front image, the body image, and the rear image of the car in the three-dimensional direction in the expected three-dimensional direction according to the front image, the body image, and the rear image of the car being glued, and apply a three-dimensional reconstruction method to combine the first dimension direction contour image, the second dimension direction contour image, and the third dimension direction contour image to generate the three-dimensional contour of the front gluing, the body gluing, and the rear gluing of the car in the process of gluing. The advantage of this is that by generating the three-dimensional contour of the front gluing, the body gluing, and the rear gluing of the car in the process of gluing, the actual situation of the car gluing can be displayed in an all-round and three-dimensional manner, which helps to accurately evaluate the quality of the car gluing and timely discover potential gluing defects.

[0019] Furthermore, the above scheme can use the origin of the preset three-dimensional direction as the coordinate starting point to obtain the three-dimensional point cloud data of the three-dimensional contour of the glue coating on the front of the vehicle, the three-dimensional contour of the glue coating on the body of the vehicle, and the three-dimensional contour of the glue coating on the rear of the vehicle, and use the parallel line that intersects with the coordinate starting point and is parallel to the front of the vehicle, the body of the vehicle, and the rear of the vehicle as the baseline. Based on the baseline, the three-dimensional point cloud data is projected into a plane view, and according to the plane view, the three-dimensional point cloud data is converted into two-dimensional coordinate data. The advantage of this is that by converting the three-dimensional point cloud data into two-dimensional coordinate data, the complexity of the three-dimensional data can be intuitively simplified, which is convenient for reducing the difficulty of detecting automobile glue coating defects and facilitating improving the accuracy of automobile glue coating defect detection.

[0020] Furthermore, the above scheme can compare and detect the two-dimensional coordinate data of the front glue coating, body glue coating and rear glue coating with the preset standard coordinate data of each point on the glue surface of the front glue coating, body glue coating and rear glue coating of the automobile, and use different colors to mark the positions of various types of glue defects to obtain the detection results of the glue defects on the front, body and rear of the automobile. The advantage of this is that by using different colors to mark the positions of various types of glue defects, the glue defect detection results are clear at a glance, and it is also easy to quickly locate and repair the glue defects, thereby reducing the difficulty of detecting automobile glue defects and improving the accuracy of automobile glue defect detection.

[0021] Furthermore, the above scheme can correct the glue defects on the front, body and rear of the automobile according to the detection results of the glue defects on the front, body and rear of the automobile. The advantage of this is that by correcting the glue defects on the front, body and rear of the automobile, the efficiency of repairing the glue defects on the automobile can be improved, thereby ensuring the stability and consistency of the repair of the glue defects on the front, body and rear of the automobile. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0023] Figure 1 It is a flow chart of an embodiment of a 3D gluing defect detection method of the present invention;

[0024] Figure 2 It is a flow chart of another embodiment of the 3D gluing defect detection method of the present invention;

[0025] Figure 3 It is a structural schematic diagram of an embodiment of a 3D gluing defect detection device of the present invention;

[0026] Figure 4 It is a structural schematic diagram of another embodiment of the 3D gluing defect detection device of the present invention;

[0027] Figure 5 It is a structural schematic diagram of an embodiment of a computer device of the present invention. DETAILED DESCRIPTION

[0028] The present invention will be further described in detail below in conjunction with the accompanying drawings and examples. It is particularly noted that the following examples are only used to illustrate the present invention, but are not intended to limit the scope of the present invention. Similarly, the following examples are only partial embodiments of the present invention rather than all embodiments, and all other embodiments obtained by those of ordinary skill in the art without creative work are within the scope of protection of the present invention.

[0029] The present invention provides a 3D gluing defect detection method, which can reduce the difficulty of detecting automobile gluing defects and improve the accuracy of automobile gluing defect detection.

[0030] See also Figure 1 , Figure 1 FIG. 1 is a flow chart of an embodiment of a 3D coating defect detection method of the present invention. It should be noted that if there are substantially the same results, the method of the present invention is not limited to Figure 1 The process sequence shown is limited. Figure 1 As shown, the method comprises the following steps:

[0031] S101: generating a front gluing 3D contour, a body gluing 3D contour and a rear gluing 3D contour of the automobile in a preset 3D direction according to the front image, the body image and the rear image of the automobile gluing process.

[0032] The method of generating the front gluing 3D contour, the body gluing 3D contour and the rear gluing 3D contour of the automobile gluing process in a preset 3D direction according to the front image, the body image and the rear image of the automobile gluing process may include:

[0033] According to the front image, body image and rear image of the automobile glue coating, the first dimension direction contour image, the second dimension direction contour image and the third dimension direction contour image of the front image, body image and rear image of the automobile glue coating in the three-dimensional direction are drawn respectively in the expected three-dimensional direction, and the three-dimensional reconstruction method is applied to combine the first dimension direction contour image, the second dimension direction contour image and the third dimension direction contour image to generate the three-dimensional contour of the front gluing, the three-dimensional contour of the body gluing and the three-dimensional contour of the rear gluing of the automobile glue coating process respectively. The advantage of this is that by generating the three-dimensional contour of the front gluing, the three-dimensional contour of the body gluing and the three-dimensional contour of the rear gluing of the automobile glue coating process, the actual situation of the automobile glue coating can be displayed in an all-round and three-dimensional manner, which is helpful to accurately evaluate the quality of the automobile glue coating and timely discover potential glue coating defects.

[0034] S102: Taking the origin of the preset three-dimensional direction as the coordinate starting point, obtaining three-dimensional point cloud data of the three-dimensional contour of the front of the vehicle, the three-dimensional contour of the body of the vehicle and the three-dimensional contour of the rear of the vehicle, and converting the three-dimensional point cloud data into two-dimensional coordinate data.

[0035] The method of taking the origin of the preset three-dimensional direction as the coordinate starting point, obtaining the three-dimensional point cloud data of the three-dimensional contour of the front of the vehicle, the three-dimensional contour of the body of the vehicle and the three-dimensional contour of the rear of the vehicle, and converting the three-dimensional point cloud data into two-dimensional coordinate data may include:

[0036] Taking the origin of the preset three-dimensional direction as the coordinate starting point, the three-dimensional point cloud data of the three-dimensional contour of the glue coating on the front of the vehicle, the three-dimensional contour of the glue coating on the body and the three-dimensional contour of the glue coating on the rear of the vehicle are obtained, and the parallel line intersecting with the coordinate starting point and parallel to the front of the vehicle, the body of the vehicle and the rear of the vehicle is taken as the baseline. Based on the baseline, the three-dimensional point cloud data is projected into a plane view, and according to the plane view, the three-dimensional point cloud data is converted into two-dimensional coordinate data. The advantage of this is that by converting the three-dimensional point cloud data into two-dimensional coordinate data, the complexity of the three-dimensional data can be intuitively simplified, which is convenient for reducing the difficulty of detecting automobile glue coating defects and facilitating improving the accuracy of automobile glue coating defect detection.

[0037] S103: Compare and detect the two-dimensional coordinate data of the front glue coating, the body glue coating and the rear glue coating with the preset standard coordinate data of each point on the glue coating surface of the front glue coating, the body glue coating and the rear glue coating of the automobile, and obtain the detection results of the glue coating defects of the front glue coating, the body glue coating and the rear glue coating of the automobile.

[0038] Among them, the two-dimensional coordinate data of the front glue coating, the body glue coating and the rear glue coating are compared and detected with the preset standard coordinate data of each point on the glue coating surface of the front glue coating, the body glue coating and the rear glue coating of the automobile, and the detection results of the glue coating defects of the front, body and rear of the automobile are obtained, which may include:

[0039] The two-dimensional coordinate data of the front glue coating, body glue coating and rear glue coating are compared with the preset standard coordinate data of each point on the glue coating surface of the front glue coating, body glue coating and rear glue coating of the automobile, and different colors are used to mark the positions of various types of glue defects to obtain the detection results of the glue coating defects of the front, body and rear of the automobile. The advantage of this is that by marking the positions of various types of glue defects with different colors, the glue coating defect detection results are clear at a glance, and it is also easy to quickly locate and repair the glue coating defects, thereby reducing the difficulty of detecting automobile glue coating defects and improving the accuracy of automobile glue coating defect detection.

[0040] In this embodiment, different colors can be used to mark the positions of various types of glue defects. For example, glue areas that exceed the standard range can be marked with red, and areas with insufficient or missing glue can be marked with yellow or green, etc. The present invention is not limited to this.

[0041] Among them, after comparing and detecting the two-dimensional coordinate data of the front glue coating, the body glue coating and the rear glue coating with the preset standard coordinate data of each point on the glue coating surface of the front glue coating, the body glue coating and the rear glue coating of the automobile, and obtaining the detection results of the defects of the front glue coating, the body glue coating and the rear glue coating of the automobile, it can also include:

[0042] According to the detection results of the glue defects on the front, body and rear of the automobile, the glue defects on the front, body and rear of the automobile are corrected. The advantage of this is that by correcting the glue defects on the front, body and rear of the automobile, the efficiency of repairing the glue defects of the automobile can be improved, ensuring the stability and consistency of the repair of the glue defects on the front, body and rear of the automobile.

[0043] It can be found that in this embodiment, according to the front image, body image and rear image of the automobile gluing, a three-dimensional contour of the front gluing, a three-dimensional contour of the body gluing and a three-dimensional contour of the rear gluing of the automobile can be generated in a preset three-dimensional direction respectively, and the origin of the preset three-dimensional direction can be used as the coordinate starting point to obtain the three-dimensional point cloud data of the three-dimensional contour of the front gluing, the three-dimensional contour of the body gluing and the three-dimensional contour of the rear gluing, and the three-dimensional point cloud data can be converted into two-dimensional coordinate data, and the two-dimensional coordinate data of the front gluing, the body gluing and the rear gluing can be compared and detected with the preset standard coordinate data of each point on the gluing surface of the front gluing, the body gluing and the rear gluing of the automobile, so as to obtain the detection results of the glue defects of the front, body and rear of the automobile, thereby reducing the difficulty of detecting automobile glue defects and improving the accuracy of automobile glue defect detection.

[0044] Furthermore, in the present embodiment, based on the front image, body image and rear image of the automobile, a first dimension direction contour image, a second dimension direction contour image and a third dimension direction contour image of the front image, body image and rear image of the automobile can be drawn in the expected three-dimensional direction respectively, and a three-dimensional reconstruction method is applied to generate a three-dimensional contour of the front gluing, a three-dimensional contour of the body gluing and a three-dimensional contour of the rear gluing of the automobile in the gluing process respectively in combination with the first dimension direction contour image, the second dimension direction contour image and the third dimension direction contour image. The advantage of this is that by generating the three-dimensional contour of the front gluing, the body gluing and the rear gluing of the automobile in the gluing process, the actual situation of the automobile gluing can be displayed in an all-round and three-dimensional manner, which helps to accurately evaluate the quality of the automobile gluing and timely discover potential gluing defects.

[0045] Furthermore, in the present embodiment, the origin of the preset three-dimensional direction can be used as the coordinate starting point to obtain three-dimensional point cloud data of the three-dimensional contour of the glue coating on the front of the vehicle, the three-dimensional contour of the glue coating on the body of the vehicle, and the three-dimensional contour of the glue coating on the rear of the vehicle, and a parallel line intersecting with the coordinate starting point and parallel to the front of the vehicle, the body of the vehicle, and the rear of the vehicle is used as a baseline. Based on the baseline, the three-dimensional point cloud data is projected into a plane view, and based on the plane view, the three-dimensional point cloud data is converted into two-dimensional coordinate data. The advantage of this is that by converting the three-dimensional point cloud data into two-dimensional coordinate data, the complexity of the three-dimensional data can be intuitively simplified, which facilitates reducing the difficulty of detecting automobile glue coating defects and facilitating improving the accuracy of automobile glue coating defect detection.

[0046] Furthermore, in the present embodiment, the two-dimensional coordinate data of the front glue coating, the body glue coating and the rear glue coating can be compared with the preset standard coordinate data of each point on the glue surface of the front glue coating, the body glue coating and the rear glue coating of the automobile, and different colors can be used to mark the positions of various types of glue defects to obtain the detection results of the glue defects on the front, body and rear of the automobile. The advantage of this is that by marking the positions of various types of glue defects with different colors, the glue defect detection results are clear at a glance, and it is also convenient to quickly locate and repair the glue defects, thereby reducing the difficulty of detecting automobile glue defects and improving the accuracy of automobile glue defect detection.

[0047] See also Figure 2 , Figure 2 3D coating defect detection method according to another embodiment of the present invention is shown in FIG. 3D coating defect detection method according to another embodiment of the present invention. In this embodiment, the method comprises the following steps:

[0048] S201: Based on the front image, the body image and the rear image of the automobile, a front gluing 3D contour, a body gluing 3D contour and a rear gluing 3D contour of the automobile are generated in a preset 3D direction.

[0049] This can be as described in S101 above and will not be elaborated here.

[0050] S202: Taking the origin of the preset three-dimensional direction as the coordinate starting point, obtaining three-dimensional point cloud data of the three-dimensional contour of the front of the vehicle, the three-dimensional contour of the body of the vehicle and the three-dimensional contour of the rear of the vehicle, and converting the three-dimensional point cloud data into two-dimensional coordinate data.

[0051] This can be as described in S102 above, and will not be elaborated here.

[0052] S203: Compare and detect the two-dimensional coordinate data of the front glue coating, the body glue coating and the rear glue coating with the preset standard coordinate data of each point on the glue coating surface of the front glue coating, the body glue coating and the rear glue coating of the automobile, and obtain the detection results of the glue coating defects of the front glue coating, the body glue coating and the rear glue coating of the automobile.

[0053] This can be as described in S103 above, and will not be elaborated here.

[0054] S204: According to the inspection results of the glue coating defects on the front, body and rear of the automobile, the glue coating defects on the front, body and rear of the automobile are corrected.

[0055] It can be found that in this embodiment, the glue defects on the front, body and rear of the automobile can be corrected according to the detection results of the glue defects on the front, body and rear of the automobile. The advantage of this is that by correcting the glue defects on the front, body and rear of the automobile, the efficiency of repairing the glue defects on the automobile can be improved, thereby ensuring the stability and consistency of the repair of the glue defects on the front, body and rear of the automobile.

[0056] The present invention also provides a 3D gluing defect detection device, which can reduce the difficulty of detecting automobile gluing defects and improve the accuracy of automobile gluing defect detection.

[0057] See also Figure 3 , Figure 3 3D gluing defect detection device 30 includes a generating module 31 , a converting module 32 and a detecting module 33 .

[0058] The generating module 31 is used to generate the front gluing 3D contour, the body gluing 3D contour and the rear gluing 3D contour of the automobile in the preset 3D direction according to the front image, the body image and the rear image of the automobile gluing process.

[0059] The conversion module 32 is used to obtain the three-dimensional point cloud data of the three-dimensional contour of the front of the vehicle, the three-dimensional contour of the body of the vehicle and the three-dimensional contour of the rear of the vehicle with the origin of the preset three-dimensional direction as the coordinate starting point, and convert the three-dimensional point cloud data into two-dimensional coordinate data.

[0060] The detection module 33 is used to compare and detect the two-dimensional coordinate data of the front glue coating, the body glue coating and the rear glue coating with the preset standard coordinate data of each point on the glue coating surface of the front glue coating, the body glue coating and the rear glue coating of the automobile, so as to obtain the detection results of the defects of the glue coating on the front, the body and the rear of the automobile.

[0061] Optionally, the generating module 31 may be specifically used for:

[0062] According to the front image, body image and rear image of the automobile being glued, in the expected three-dimensional direction, the first dimension direction contour image, the second dimension direction contour image and the third dimension direction contour image of the front image, body image and rear image of the automobile being glued are respectively drawn in the three-dimensional direction, and a three-dimensional reconstruction method is applied to combine the first dimension direction contour image, the second dimension direction contour image and the third dimension direction contour image to generate the three-dimensional contour of the front gluing, the three-dimensional contour of the body gluing and the three-dimensional contour of the rear gluing in the automobile gluing process respectively.

[0063] Optionally, the conversion module 32 may be specifically used for:

[0064] Taking the origin of the preset three-dimensional direction as the coordinate starting point, obtain the three-dimensional point cloud data of the three-dimensional contour of the glue-painted front of the vehicle, the three-dimensional contour of the glue-painted body and the three-dimensional contour of the glue-painted rear of the vehicle, and take the parallel line that intersects with the coordinate starting point and is parallel to the front of the vehicle, the body of the vehicle and the rear of the vehicle as the baseline. Based on the baseline, project the three-dimensional point cloud data into a plane view, and according to the plane view, convert the three-dimensional point cloud data into two-dimensional coordinate data.

[0065] Optionally, the detection module may be specifically used for:

[0066] The two-dimensional coordinate data of the front glue coating, body glue coating and rear glue coating of the vehicle are compared and detected with the preset standard coordinate data of each point on the glue coating surface of the front glue coating, body glue coating and rear glue coating of the vehicle, and the positions of various types of glue coating defects are marked with different colors to obtain the detection results of the glue coating defects of the front, body and rear of the vehicle.

[0067] See also Figure 4 , Figure 4 3D gluing defect detection device 40 of the present invention is a schematic diagram of another embodiment of the present invention. Different from the previous embodiment, the 3D gluing defect detection device 40 of the present embodiment further includes a correction module 41.

[0068] The correction module 41 is used to correct the glue coating defects on the front, body and rear of the automobile according to the detection results of the glue coating defects on the front, body and rear of the automobile.

[0069] Each unit module of the 3D glue coating defect detection device 30 / 40 can respectively execute the corresponding steps in the above method embodiment, so each unit module will not be described in detail here. Please refer to the description of the above corresponding steps for details.

[0070] The present invention further provides a computer device, such as Figure 5 As shown, it includes: at least one processor 51; and a memory 52 that is communicatively connected to the at least one processor 51; wherein the memory 52 stores instructions that can be executed by the at least one processor 51, and the instructions are executed by the at least one processor 51 so that the at least one processor 51 can execute the above-mentioned 3D glue coating defect detection method.

[0071] The memory 52 and the processor 51 are connected in a bus manner, and the bus may include any number of interconnected buses and bridges, and the bus connects various circuits of one or more processors 51 and the memory 52 together. The bus can also connect various other circuits such as peripheral devices, voltage regulators, and power management circuits, which are well known in the art and are therefore not further described herein. The bus interface provides an interface between the bus and the transceiver. The transceiver can be one element or multiple elements, such as multiple receivers and transmitters, providing a unit for communicating with various other devices on a transmission medium. The data processed by the processor 51 is transmitted on a wireless medium via an antenna, and further, the antenna also receives data and transmits the data to the processor 51.

[0072] The processor 51 is responsible for managing the bus and general processing, and can also provide various functions, including timing, peripheral interfaces, voltage regulation, power management and other control functions. The memory 52 can be used to store data used by the processor 51 when performing operations.

[0073] The present invention further provides a computer-readable storage medium storing a computer program, which implements the above method embodiment when executed by a processor.

[0074] It can be found that the above scheme can generate the three-dimensional contour of the front gluing process of the car, the three-dimensional contour of the body gluing and the three-dimensional contour of the rear gluing process of the car in a preset three-dimensional direction according to the front image, the body image and the rear image of the car gluing, and can use the origin of the preset three-dimensional direction as the coordinate starting point to obtain the three-dimensional point cloud data of the three-dimensional contour of the front gluing, the three-dimensional contour of the body gluing and the three-dimensional contour of the rear gluing, and convert the three-dimensional point cloud data into two-dimensional coordinate data, and can compare and detect the two-dimensional coordinate data of the front gluing, the body gluing and the rear gluing with the preset standard coordinate data of each point on the gluing surface of the front gluing, the body gluing and the rear gluing of the car, and obtain the detection results of the glue defects of the front, body and rear of the car, thereby reducing the difficulty of detecting automobile glue defects and improving the accuracy of automobile glue defect detection.

[0075] Furthermore, the above scheme can draw the first dimension direction contour image, the second dimension direction contour image, and the third dimension direction contour image of the front image, the body image, and the rear image of the car in the three-dimensional direction in the expected three-dimensional direction according to the front image, the body image, and the rear image of the car being glued, and apply a three-dimensional reconstruction method to combine the first dimension direction contour image, the second dimension direction contour image, and the third dimension direction contour image to generate the three-dimensional contour of the front gluing, the body gluing, and the rear gluing of the car in the process of gluing. The advantage of this is that by generating the three-dimensional contour of the front gluing, the body gluing, and the rear gluing of the car in the process of gluing, the actual situation of the car gluing can be displayed in an all-round and three-dimensional manner, which helps to accurately evaluate the quality of the car gluing and timely discover potential gluing defects.

[0076] Furthermore, the above scheme can use the origin of the preset three-dimensional direction as the coordinate starting point to obtain the three-dimensional point cloud data of the three-dimensional contour of the glue coating on the front of the vehicle, the three-dimensional contour of the glue coating on the body of the vehicle, and the three-dimensional contour of the glue coating on the rear of the vehicle, and use the parallel line that intersects with the coordinate starting point and is parallel to the front of the vehicle, the body of the vehicle, and the rear of the vehicle as the baseline. Based on the baseline, the three-dimensional point cloud data is projected into a plane view, and according to the plane view, the three-dimensional point cloud data is converted into two-dimensional coordinate data. The advantage of this is that by converting the three-dimensional point cloud data into two-dimensional coordinate data, the complexity of the three-dimensional data can be intuitively simplified, which is convenient for reducing the difficulty of detecting automobile glue coating defects and facilitating improving the accuracy of automobile glue coating defect detection.

[0077] Furthermore, the above scheme can compare and detect the two-dimensional coordinate data of the front glue coating, body glue coating and rear glue coating with the preset standard coordinate data of each point on the glue surface of the front glue coating, body glue coating and rear glue coating of the automobile, and use different colors to mark the positions of various types of glue defects to obtain the detection results of the glue defects on the front, body and rear of the automobile. The advantage of this is that by using different colors to mark the positions of various types of glue defects, the glue defect detection results are clear at a glance, and it is also easy to quickly locate and repair the glue defects, thereby reducing the difficulty of detecting automobile glue defects and improving the accuracy of automobile glue defect detection.

[0078] Furthermore, the above scheme can correct the glue defects on the front, body and rear of the automobile according to the detection results of the glue defects on the front, body and rear of the automobile. The advantage of this is that by correcting the glue defects on the front, body and rear of the automobile, the efficiency of repairing the glue defects on the automobile can be improved, thereby ensuring the stability and consistency of the repair of the glue defects on the front, body and rear of the automobile.

[0079] In the several embodiments provided by the present invention, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device implementation described above is only schematic, for example, the division of modules or units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0080] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0081] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0082] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, server, or network device, etc.) or a processor (processor) to perform all or part of the steps of each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0083] The above descriptions are only some embodiments of the present invention, and are not intended to limit the protection scope of the present invention. Any equivalent device or equivalent process transformation made using the contents of the present invention specification 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 3D gluing defect detection method, characterized in that: include: According to the front image, body image and rear image of the automobile, a front gluing 3D profile, a body gluing 3D profile and a rear gluing 3D profile of the automobile are generated in a preset 3D direction. Taking the origin of the preset three-dimensional direction as the coordinate starting point, obtaining the three-dimensional point cloud data of the three-dimensional contour of the front of the vehicle, the three-dimensional contour of the body of the vehicle and the three-dimensional contour of the rear of the vehicle, and converting the three-dimensional point cloud data into two-dimensional coordinate data; The two-dimensional coordinate data of the front glue coating, the body glue coating and the rear glue coating are compared and detected with the preset standard coordinate data of each point on the glue coating surface of the front glue coating, the body glue coating and the rear glue coating of the automobile to obtain the detection results of the defects of the front glue coating, the body glue coating and the rear glue coating of the automobile.

2. The 3D coating defect detection method according to claim 1, characterized in that: The method generates a three-dimensional profile of the front gluing process, a three-dimensional profile of the body gluing process and a three-dimensional profile of the rear gluing process of the automobile in a preset three-dimensional direction according to the front image, the body image and the rear image of the automobile gluing process, respectively, including: According to the front image, body image and rear image of the automobile being glued, in the expected three-dimensional direction, the first dimension direction contour image, the second dimension direction contour image and the third dimension direction contour image of the front image, body image and rear image of the automobile being glued are respectively drawn in the three-dimensional direction, and the three-dimensional reconstruction method is applied to combine the first dimension direction contour image, the second dimension direction contour image and the third dimension direction contour image to generate the three-dimensional contour of the front gluing, the three-dimensional contour of the body gluing and the three-dimensional contour of the rear gluing of the automobile in the gluing process.

3. The 3D gluing defect detection method according to claim 1, characterized in that: The method takes the origin of the preset three-dimensional direction as the coordinate starting point, obtains the three-dimensional point cloud data of the three-dimensional contour of the front glue coating, the three-dimensional contour of the body glue coating and the three-dimensional contour of the rear glue coating, and converts the three-dimensional point cloud data into two-dimensional coordinate data, including: Taking the origin of the preset three-dimensional direction as the coordinate starting point, obtain the three-dimensional point cloud data of the three-dimensional contour of the glue-painted front of the vehicle, the three-dimensional contour of the glue-painted body of the vehicle and the three-dimensional contour of the glue-painted rear of the vehicle, and take the parallel line intersecting with the coordinate starting point and parallel to the front of the vehicle, the body of the vehicle and the rear of the vehicle as the baseline, based on the baseline, project the three-dimensional point cloud data into a plane view, and according to the plane view, convert the three-dimensional point cloud data into two-dimensional coordinate data.

4. The 3D gluing defect detection method according to claim 1, characterized in that: The two-dimensional coordinate data of the front glue coating, the body glue coating and the rear glue coating are compared and detected with the preset standard coordinate data of each point on the glue coating surface of the front glue coating, the body glue coating and the rear glue coating of the automobile, and the detection results of the defects of the glue coating of the front, the body and the rear of the automobile are obtained, including: The two-dimensional coordinate data of the front glue coating, body glue coating and rear glue coating of the vehicle are compared and detected with the preset standard coordinate data of each point on the glue coating surface of the front glue coating, body glue coating and rear glue coating of the vehicle, and the positions of various types of glue coating defects are marked with different colors to obtain the detection results of the glue coating defects of the front, body and rear of the vehicle.

5. The 3D coating defect detection method according to claim 1, characterized in that: After comparing and detecting the two-dimensional coordinate data of the front glue coating, the body glue coating and the rear glue coating with the preset standard coordinate data of each point on the glue coating surface of the front glue coating, the body glue coating and the rear glue coating of the automobile, and obtaining the detection results of the glue coating defects of the front glue coating, the body glue coating and the rear glue coating of the automobile, the method further includes: According to the detection results of the glue coating defects on the front, body and rear of the automobile, the glue coating defects on the front, body and rear of the automobile are corrected.

6. A 3D gluing defect detection device, characterized in that: include: Generation module, conversion module and detection module; The generating module is used to generate the front gluing 3D contour, the body gluing 3D contour and the rear gluing 3D contour of the automobile in the gluing process in a preset 3D direction according to the front image, the body image and the rear image of the automobile; The conversion module is used to obtain the three-dimensional point cloud data of the three-dimensional contour of the front of the vehicle, the three-dimensional contour of the body of the vehicle and the three-dimensional contour of the rear of the vehicle with the origin of the preset three-dimensional direction as the coordinate starting point, and convert the three-dimensional point cloud data into two-dimensional coordinate data; The detection module is used to compare and detect the two-dimensional coordinate data of the front glue coating, the body glue coating and the rear glue coating with the preset standard coordinate data of each point on the glue coating surface of the front glue coating, the body glue coating and the rear glue coating of the automobile, so as to obtain the detection results of the defects of the glue coating on the front, the body and the rear of the automobile.

7. The 3D coating defect detection device according to claim 6, characterized in that: The generation module is specifically used for: According to the front image, body image and rear image of the automobile being glued, in the expected three-dimensional direction, the first dimension direction contour image, the second dimension direction contour image and the third dimension direction contour image of the front image, body image and rear image of the automobile being glued are respectively drawn in the three-dimensional direction, and the three-dimensional reconstruction method is applied to combine the first dimension direction contour image, the second dimension direction contour image and the third dimension direction contour image to generate the three-dimensional contour of the front gluing, the three-dimensional contour of the body gluing and the three-dimensional contour of the rear gluing of the automobile in the gluing process.

8. The 3D glue coating defect detection device according to claim 6, characterized in that: The conversion module is specifically used for: Taking the origin of the preset three-dimensional direction as the coordinate starting point, obtain the three-dimensional point cloud data of the three-dimensional contour of the glue-painted front of the vehicle, the three-dimensional contour of the glue-painted body of the vehicle and the three-dimensional contour of the glue-painted rear of the vehicle, and take the parallel line intersecting with the coordinate starting point and parallel to the front of the vehicle, the body of the vehicle and the rear of the vehicle as the baseline, based on the baseline, project the three-dimensional point cloud data into a plane view, and according to the plane view, convert the three-dimensional point cloud data into two-dimensional coordinate data.

9. A computer device, characterized in that: include: at least one processor; And, a memory communicatively connected to at least one processor; wherein the memory stores instructions executable by at least one processor, and the instructions are executed by at least one processor so that at least one processor can execute the 3D coating defect detection method as described in any one of claims 1 to 5.

10. A computer-readable storage medium, characterized in that: A computer program is stored, and when the computer program is executed by a processor, the 3D gluing defect detection method according to any one of claims 1 to 5 is implemented.

Images