Fusion method and device of workpiece defect point positions and detection system

Abstract

The embodiment of the invention provides a workpiece defect point fusion method and device and a detection system, defect points from different acquisition devices can be uniformly converted to a target coordinate system of a workpiece model, the distance between the defect points is accurately calculated, a preset screening threshold value is utilized, and the defect point fusion accuracy is improved. According to the method, the point locations with close distances are intelligently fused to obtain the target defect point location, so that redundant data are reduced, defect information really having detection significance is reserved, the complexity and false alarm rate of data processing are reduced, the finally determined target defect point location is more accurate and reliable, and further, the accuracy of detection is improved. Powerful support is provided for subsequent defect analysis, repair and quality control, and the production efficiency and the product quality are remarkably improved.

Description

Technical Field

[0001] The present application relates to the field of machine vision technology, and in particular to a method, device and detection system for fusing defect points of a workpiece. Background Art

[0002] Traditional manual inspection methods are inefficient and susceptible to subjective factors, making it difficult to ensure the accuracy and consistency of inspection results, and are no longer able to meet the needs of modern manufacturing. With the rise of machine vision technology, automated inspection systems based on a single camera have emerged and have been widely used in the fields of automobile and electronic product manufacturing. However, when faced with multi-faceted or special-shaped parts in complex production environments, single camera inspections have blind spots and misjudgment problems.

[0003] To break through this bottleneck, a multi-camera collaborative inspection system was developed. This technology achieves comprehensive coverage of the inspection area and in-depth mining of image information by deploying multiple cameras to capture parts from different perspectives, significantly improving the comprehensiveness and accuracy of inspection. However, the multi-camera system places higher requirements on software development, configuration, deployment and maintenance, and multiple cameras may capture the same defect from different angles, resulting in a large amount of repeated defect information in the inspection results, which in turn leads to low accuracy and efficiency of defect detection, affecting production efficiency and product quality. Summary of the invention

[0004] The purpose of the embodiments of the present application is to provide a method, device and detection system for fusion of workpiece defect points, so as to improve the accuracy and efficiency of workpiece defect detection and positioning, thereby improving production efficiency and product quality. The specific technical solution is as follows:

[0005] In a first aspect of the present application, a method for fusing defect points of a workpiece is provided, the method comprising:

[0006] Based on the target conversion relationship corresponding to each acquisition device, the initial defect points acquired by each acquisition device from the target workpiece are projected into the target coordinate system to which the workpiece model of the target workpiece belongs, so as to obtain the defect points to be screened;

[0007] Calculating the distance between each of the defect points to be screened;

[0008] According to the distance, the defect points whose distances among the defect points to be screened are merged to obtain the target defect points.

[0009] In a possible implementation, the acquisition device includes a first acquisition device and a plurality of second acquisition devices, and the method further includes:

[0010] Calibrate and obtain a conversion relationship between a first device coordinate system of the first acquisition device and the target coordinate system as a first conversion relationship corresponding to the first acquisition device;

[0011] According to the first position relationship and the first conversion relationship, the conversion relationship between each second acquisition device and the target coordinate system is calculated as the second conversion relationship corresponding to each second acquisition device, wherein the first position relationship is the position relationship between the first acquisition device and the second acquisition device.

[0012] In a possible implementation, the acquisition device is disposed on a robotic arm, and the method further includes:

[0013] Obtaining the positional relationship between each of the acquisition devices and the robotic arm through hand-eye calibration;

[0014] According to the positional relationship between the first acquisition device and the robotic arm and the positional relationship between the second acquisition device and the robotic arm, the positional relationship between the first acquisition device and the second acquisition device is calculated as the first positional relationship.

[0015] In a possible implementation manner, the calibration obtains a conversion relationship between the first device coordinate system of the first acquisition device and the target coordinate system as a first conversion relationship corresponding to the first acquisition device, including:

[0016] Displaying the initial image data obtained by photographing the target workpiece by the first acquisition device and the workpiece model;

[0017] Acquire a plurality of first calibration points inputted from the initial image data, and a plurality of second calibration points inputted from the workpiece model, wherein each of the second calibration points corresponds to one of the first calibration points;

[0018] A conversion relationship between the plurality of first calibration points and the plurality of second calibration points is calculated as a first conversion relationship.

[0019] In a possible implementation, the method further includes:

[0020] Acquire a third calibration point inputted from the initial image data and a fourth calibration point inputted from the workpiece model, wherein the fourth calibration point corresponds to the third calibration point;

[0021] Based on the first conversion relationship, projecting the third calibration point to the target coordinate system to obtain a projected calibration point;

[0022] Calculating the error between the projected calibration point and the fourth calibration point;

[0023] The calculating, based on the first position relationship and the first conversion relationship, the conversion relationship between each of the second acquisition devices and the target coordinate system as the second conversion relationship corresponding to each of the second acquisition devices, includes:

[0024] If the error satisfies a preset error condition, a transformation relationship between each of the second acquisition devices and the target coordinate system is calculated according to the first position relationship and the first transformation relationship as the second transformation relationship corresponding to each of the second acquisition devices.

[0025] In a possible implementation manner, the calculating, as a first conversion relationship, a conversion relationship between the plurality of first calibration points and the plurality of second calibration points includes:

[0026] The conversion relationship between the plurality of first calibration points and the plurality of second calibration points is calculated by a PNP algorithm as a first conversion relationship.

[0027] In a possible implementation, the acquisition device is disposed on a robotic arm, and the robotic arm is deployed on an automobile production line. The method further includes:

[0028] A model is established in advance for each component in the automobile on the automobile production line;

[0029] The type of the target workpiece is obtained, and a model of a corresponding type is searched in the model to serve as the workpiece model of the target workpiece.

[0030] In a second aspect of the present application, a device for fusing defect points of a workpiece is provided, the device comprising:

[0031] A defect projection module is used to project the initial defect points obtained by collecting the target workpiece by each collection device into the target coordinate system to which the workpiece model of the target workpiece belongs based on the target conversion relationship corresponding to each collection device, so as to obtain the defect points to be screened;

[0032] A distance calculation module, used to calculate the distance between each of the defect points to be screened;

[0033] The defect fusion module is used to fuse the defect points whose distances among the defect points to be screened are less than a preset screening threshold according to the distances to obtain target defect points.

[0034] In a possible implementation, the acquisition device includes a first acquisition device and a plurality of second acquisition devices, and the apparatus further includes:

[0035] A first calibration module, used for calibrating a conversion relationship between a first device coordinate system of the first acquisition device and the target coordinate system as a first conversion relationship corresponding to the first acquisition device;

[0036] A second calibration module, configured to calculate a transformation relationship between each of the second acquisition devices and the target coordinate system according to the first position relationship and the first transformation relationship, as a second transformation relationship corresponding to each of the second acquisition devices, wherein the first position relationship is a position relationship between the first acquisition device and the second acquisition device;

[0037] The acquisition device is arranged on a mechanical arm, and the device further comprises:

[0038] A third calibration module, used for obtaining the positional relationship between each of the acquisition devices and the robotic arm through hand-eye calibration;

[0039] a fourth calibration module, configured to calculate a positional relationship between the first acquisition device and the second acquisition device as a first positional relationship according to a positional relationship between the first acquisition device and the robotic arm and a positional relationship between the second acquisition device and the robotic arm;

[0040] The first calibration module includes:

[0041] A first calibration submodule is used to display the initial image data and the workpiece model obtained by photographing the target workpiece by the first acquisition device;

[0042] A second calibration submodule, used for acquiring a plurality of first calibration points inputted from the initial image data and a plurality of second calibration points inputted from the workpiece model, wherein each of the second calibration points corresponds to one of the first calibration points;

[0043] A third calibration submodule is used to calculate a conversion relationship between the plurality of first calibration points and the plurality of second calibration points as a first conversion relationship;

[0044] The device also includes:

[0045] a fifth calibration module, configured to obtain a third calibration point input from the initial image data and a fourth calibration point input from the workpiece model, wherein the fourth calibration point corresponds to the third calibration point;

[0046] a sixth calibration module, configured to project the third calibration point onto the target coordinate system based on the first conversion relationship to obtain a projected calibration point;

[0047] A seventh calibration module, used to calculate the error between the projection calibration point and the fourth calibration point;

[0048] The second calibration module includes:

[0049] A fourth submodule for calibrating, if the error satisfies a preset error condition, a conversion relationship between each of the second acquisition devices and the target coordinate system is calculated according to the first position relationship and the first conversion relationship as a second conversion relationship corresponding to each of the second acquisition devices;

[0050] The calibration third submodule comprises:

[0051] A first calibration subunit, configured to calculate a conversion relationship between the plurality of first calibration points and the plurality of second calibration points by a PNP algorithm as a first conversion relationship;

[0052] The acquisition device is arranged on a mechanical arm, and the mechanical arm is deployed on an automobile production line. The device further comprises:

[0053] A model building module, used to build models for various parts of the automobiles on the automobile production line in advance;

[0054] The model search module is used to obtain the type of the target workpiece and search for a model of a corresponding type in the model as the workpiece model of the target workpiece.

[0055] In a third aspect of the present application, a detection system is provided, the system comprising a robotic arm, a collection device, a control device, and a display device;

[0056] The mechanical arm is used to fix the acquisition device;

[0057] The acquisition device is used to acquire the initial defect points of the target workpiece and send the acquired initial defect points to the control device;

[0058] The control device is used to implement any of the above-mentioned methods for fusing defect points of workpieces.

[0059] In a fourth aspect of the present application, an electronic device is provided, including:

[0060] Memory, used to store computer programs;

[0061] The processor is used to implement any of the above-mentioned methods for fusing workpiece defect points when executing the program stored in the memory.

[0062] Beneficial effects of the embodiments of the present application:

[0063] The workpiece defect point fusion method, device and detection system provided in the embodiments of the present application can uniformly convert defect points from different acquisition devices to the target coordinate system of the workpiece model, and intelligently fuse points with similar distances by accurately calculating the distance between each defect point and using a preset screening threshold to obtain target defect points, thereby reducing redundant data and retaining defect information that is truly meaningful for detection, thereby reducing the complexity and false alarm rate of data processing, making the final determined target defect points more accurate and reliable, and further providing strong support for subsequent defect analysis, repair and quality control, and significantly improving production efficiency and product quality.

[0064] Of course, implementing any product or method of the present application does not necessarily require achieving all of the advantages described above at the same time. BRIEF DESCRIPTION OF THE DRAWINGS

[0065] In order to more clearly illustrate the embodiments of the present application 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 application, and for ordinary technicians in this field, other embodiments can also be obtained based on these drawings.

[0066] Figure 1 A schematic diagram of a scene for workpiece defect detection and positioning provided in an embodiment of the present application;

[0067] Figure 2 A flow chart of a method for fusing defect points of a workpiece provided in an embodiment of the present application;

[0068] Figure 3 A first schematic diagram of the first conversion relationship calibration provided in an embodiment of the present application;

[0069] Figure 4 A second schematic diagram of the first conversion relationship calibration provided in an embodiment of the present application;

[0070] Figure 5 A third schematic diagram of the first conversion relationship calibration provided in the embodiment of the present application;

[0071] Figure 6 A fourth schematic diagram of the first conversion relationship calibration provided in an embodiment of the present application;

[0072] Figure 7 A fifth schematic diagram of the first conversion relationship calibration provided in an embodiment of the present application;

[0073] Figure 8 A sixth schematic diagram of the first conversion relationship calibration provided in an embodiment of the present application;

[0074] Fig. 9A seventh schematic diagram of the first conversion relationship calibration provided in an embodiment of the present application;

[0075] Fig.10 An eighth schematic diagram of the first conversion relationship calibration provided in an embodiment of the present application;

[0076] Fig.11 A ninth schematic diagram of the first conversion relationship calibration provided in an embodiment of the present application;

[0077] Fig.12 A tenth schematic diagram of the first conversion relationship calibration provided in an embodiment of the present application;

[0078] Fig.13 An eleventh schematic diagram of the first conversion relationship calibration provided in an embodiment of the present application;

[0079] Fig.14 A twelfth schematic diagram of the first conversion relationship calibration provided in an embodiment of the present application;

[0080] Fig.15 A thirteenth schematic diagram of the first conversion relationship calibration provided in an embodiment of the present application;

[0081] Fig.16 A fourteenth schematic diagram of the first conversion relationship calibration provided in an embodiment of the present application;

[0082] Fig.17 A fifteenth schematic diagram of the first conversion relationship calibration provided in an embodiment of the present application;

[0083] Fig.18 A sixteenth schematic diagram of the first conversion relationship calibration provided in an embodiment of the present application;

[0084] Fig.19 A seventeenth schematic diagram of the first conversion relationship calibration provided in an embodiment of the present application;

[0085] Fig. 20 A schematic diagram of the structure of the detection system provided in the embodiment of the present application;

[0086] Fig.21 A schematic diagram of the structure of a workpiece defect point fusion device provided in an embodiment of the present application;

[0087] Fig. 22 A schematic diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0088] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field based on the present application belong to the scope of protection of the present application.

[0089] In order to more clearly illustrate the positioning method for workpiece defect detection provided by the present application, a possible application scenario of the positioning method for workpiece defect detection provided by the present application will be exemplified below. It can be understood that the following example is only one possible application scenario of the positioning method for workpiece defect detection provided by the present application. In other possible embodiments, the positioning method for workpiece defect detection provided by the present application can also be applied to other possible application scenarios, and the following examples do not impose any limitations on this.

[0090] Taking the automobile production line as an example, the positioning of workpiece defect detection is an important link in the automobile production line. Figure 1 , Figure 1 A schematic diagram of a scenario for workpiece defect detection and positioning provided in an embodiment of the present application requires detecting whether an automobile workpiece has defects and obtaining the specific location of the defects.

[0091] In order to detect whether the above-mentioned automobile workpiece has defects and obtain the location of the defects, the embodiment of the present application provides a method for fusing the defect points of the workpiece, see Figure 2 , Figure 2 The flowchart of the method for fusing defect points of a workpiece provided in the embodiment of the present application includes:

[0092] S201 , based on the target conversion relationship corresponding to each acquisition device, project the initial defect points acquired by each acquisition device when acquiring the target workpiece into the target coordinate system to which the workpiece model of the target workpiece belongs, to obtain defect points to be screened.

[0093] S202, calculating the distance between each defect point to be screened;

[0094] S203, according to the distance, the defect points whose distances are less than a preset screening threshold among the defect points to be screened are merged to obtain the target defect point.

[0095] By applying the above-mentioned embodiments, defect points from different acquisition devices can be uniformly converted to the target coordinate system of the workpiece model. By accurately calculating the distance between each defect point and using a preset screening threshold, points with similar distances can be intelligently fused to obtain target defect points, thereby reducing redundant data and retaining defect information that is truly meaningful for detection, thereby reducing the complexity and false alarm rate of data processing, making the final target defect points more accurate and reliable, and further providing strong support for subsequent defect analysis, repair and quality control, thereby significantly improving production efficiency and product quality.

[0096] The above S201-S203 will be exemplarily described below:

[0097] In S201, the acquisition device is integrated with visual algorithms for detecting workpieces to obtain defect points, such as FCN (Fully Convolutional Networks), YOLO algorithm (You Only Look Once, target detection model) and other algorithms.

[0098] The acquisition device may be an infrared camera, a visible light camera, or other device with an image acquisition function. In some scenarios, the production line may be equipped with only an infrared camera, only a visible light camera, or both an infrared camera and a visible light camera.

[0099] In a possible embodiment, the acquisition equipment can be set on a wall or an immovable bracket. However, since the inspection objects in the automobile production line are usually relatively large and need to be compatible with multiple models and parts of various specifications, more photo points are required to cover the entire inspection area.

[0100] Based on this, in another possible embodiment, the acquisition device can be set on a robotic arm, which is deployed on an automobile production line. The robotic arm is a six-axis robot. Due to its multi-degree-of-freedom characteristics, the six-axis robot can flexibly adjust the shooting position and accurately align different parts of the inspection object, thereby achieving seamless coverage of the entire inspection area. This setting method not only significantly improves the comprehensiveness and accuracy of the inspection, but also greatly enhances the compatibility and flexibility of the production line. By controlling the six-axis robot, it can quickly adapt to the inspection needs of different models and parts, reduce manual intervention and debugging time, and improve production efficiency and automation level.

[0101] Each robotic arm is equipped with multiple acquisition devices. Figure 1 , the figure only shows that there are two acquisition devices on the robot arm 1, namely an infrared camera 2 and a visible light camera 3, and the automobile workpiece 4 is placed on the work assembly line 5.

[0102] The target conversion relationship is the coordinate conversion relationship between the device coordinate system to which each acquisition device belongs and the target coordinate system to which the workpiece model belongs. In a possible embodiment, each acquisition device can be calibrated to obtain the target conversion relationship corresponding to each acquisition device, but this method is too cumbersome and reduces the efficiency of defect detection.

[0103] Based on this, in another possible embodiment, the acquisition device is divided into a first acquisition device and a second acquisition device. The first acquisition device is a device whose position is convenient for accurate calibration and can achieve a high calibration accuracy in practical applications. For example, it can be an acquisition device installed on the top of a robotic arm, because its position is fixed and it is easy to achieve accurate calibration through technical means. All acquisition devices that do not belong to the first acquisition device category are classified as second acquisition devices.

[0104] The target transformation relationship includes the transformation relationship between the coordinate system belonging to the first acquisition device and the target coordinate system and the transformation relationship between the coordinate system belonging to the second acquisition device and the target coordinate system. For the convenience of description, the transformation relationship between the coordinate system belonging to the first acquisition device and the target coordinate system is called the first transformation relationship, and the transformation relationship between the coordinate system belonging to the second acquisition device and the target coordinate system is called the second transformation relationship.

[0105] First, the first conversion relationship can be obtained by calibration using the following method:

[0106] The initial image data and the workpiece model obtained by photographing the target workpiece by the first acquisition device are displayed.

[0107] A plurality of first calibration points inputted from the initial image data and a plurality of second calibration points inputted from the workpiece model are obtained, wherein the second calibration points are points corresponding to the first calibration points one by one.

[0108] A conversion relationship between the plurality of first calibration points and the plurality of second calibration points is calculated as a first conversion relationship.

[0109] In order to more clearly explain how to obtain the first conversion relationship during the calibration process, the following is an example of the target workpiece being the left rear door inner panel with part code 14 and the acquisition device being the top camera of the R3 robot arm located at position 1:

[0110] See also Figure 3 , Figure 3 A first schematic diagram of the first conversion relationship calibration provided in an embodiment of the present application, Figure 3The figure shows the point mapping interface of the stamping defect detection fusion client. When it is necessary to perform defect detection on the left rear door inner panel of the target workpiece with part code 14, click the Add control in the upper left corner, enter the part code 14 in the new part configuration pop-up box, and then click the Add control in the lower right corner to save the part information.

[0111] After saving the part information, see Figure 4 , Figure 4 The second schematic diagram of the calibration of the first conversion relationship provided in the embodiment of the present application, the number of conversion points (i.e., the number of positions) and the number of cameras (i.e., the number of acquisition devices) are displayed in the newly added part information box. Click the configuration control in the newly added part information box to pop up the basic configuration interface.

[0112] See also Figure 5 , Figure 5 A third schematic diagram of the first conversion relationship calibration provided in the embodiment of the present application, Figure 5 The page shown is the basic configuration page in the site configuration interface. In addition to the basic configuration page, the site configuration interface also includes a camera configuration page, a robot coordinate configuration page, and a matrix configuration page.

[0113] The basic configuration page contains multiple configuration controls directly related to calibration, including part code configuration controls, model storage path configuration controls, point cloud storage path configuration controls, main camera (i.e., first acquisition device) name configuration controls, and newly added conversion controls. The part code configuration control is used to enter the unique identification code of the target workpiece, i.e., the part code, which is set to 14 here, representing the left rear door inner panel. The model storage path configuration control and the point cloud storage path configuration control are used to configure the workpiece model of the target workpiece and the storage location of the workpiece model point cloud data. The main camera name control accessory is used to explicitly specify the first acquisition device involved in the calibration. The following description takes the name of the first acquisition device as TopCamDetect (top detection camera) as an example.

[0114] After the user clicks the new conversion control, the point configuration page opens. Figure 6 , Figure 6 This is a fourth schematic diagram of the calibration of the first transformation relationship provided in an embodiment of the present application. This page aims to establish, through user interaction or automated means, an accurate coordinate transformation relationship between points in the 2D image of the target workpiece acquired by the first acquisition device (the top camera of the R3 robotic arm) and corresponding points in the 3D workpiece model of the target workpiece.

[0115] In a possible embodiment, the 3D workpiece model can be retrieved by accessing a public database to retrieve the 3D workpiece model corresponding to the target workpiece. This approach may face problems such as insufficient model accuracy, copyright restrictions or delayed updates, which may lead to low accuracy and efficiency in workpiece defect detection and positioning, and high costs.

[0116] Based on this, in order to improve the accuracy and efficiency of workpiece defect detection and positioning, ensure product quality, enhance production flexibility and reduce production costs, in another possible embodiment, a model may be established in advance for each component in the automobile on the automobile production line. When the target workpiece needs to be defect-detected, the type of the target workpiece is obtained, and the model of the corresponding type is found in the model, and then it is used as the workpiece model of the target workpiece. Exemplarily, the user clicks the model selection control at the top of the point configuration page, configures the STL (Stereolithography) model file of the target workpiece, selects the model file of the left rear door inner panel in all model files, clicks the open control, and waits for the workpiece model of the target workpiece to be loaded. All model files include the left rear door, the left rear door inner panel, the left front door, the left front door inner panel, the left fender, etc.

[0117] After the model is loaded, the user can click the Import Camera Intrinsic Parameters control at the bottom left of the point configuration page. Figure 7 , Figure 7 The fifth schematic diagram of the first conversion relationship calibration provided in the embodiment of the present application shows the selectable camera parameters, including HandEye_K90018446_4-0508.mfa, HandEye_K90801468_5-camera.mfa, HandEye_K90018456_2-camera.mfa, HandEye_K90018458_1-camera.mfa and HandEye_L00878254_3-camera.mfa. Among all the selectable camera parameters, select the calibration file HandEye (hand-eye) _K90801468_5-camera.mfa of the first acquisition device whose camera name is TopCamDetect, click to open the control, and wait for the internal reference data of the first acquisition device to be loaded.

[0118] See also Figure 8 , Figure 8The sixth schematic diagram of the first conversion relationship calibration provided in the embodiment of the present application, the user can input the mechanical arm name of the mechanical arm where the first acquisition device is located, the top camera name (i.e., the first acquisition device name) and the specific position of the mechanical arm through the mechanical arm configuration control, the camera name configuration control and the point (position) information configuration control on the right side of the import camera internal parameter control. Exemplarily, the mechanical arm name is R3, the name of the first acquisition device is TopCamDetect and the position of the mechanical arm is position 1.

[0119] After configuring the above content, the user clicks the image selection control in the upper right corner of the point configuration page, see Fig. 9 , Fig. 9 The seventh schematic diagram of the first conversion relationship calibration provided in the embodiment of the present application, after clicking the picture selection control, the point configuration page displays the 2D images of all workpieces acquired by the first acquisition device of the R3 robot arm located at position 1 and the 3D workpiece model corresponding to each workpiece. The 2D image of the workpiece, i.e. Fig. 9 The production pictures in the figure only show production pictures 1, 2 and 3, and the 3D workpiece model of the workpiece, that is, Fig. 9 The figure shows only teaching pictures 1, 2, and 3. The user selects the 2D image of the target workpiece. Fig. 9 Take production picture 1 in the figure as an example. Production picture 1 is the initial image data mentioned above. The user also needs to select the 3D workpiece model of the target workpiece. Fig. 9 Take the teaching picture 1 in the example, after selecting production picture 1 and teaching picture 1, click to open the control to display the initial image data and workpiece model obtained by the first acquisition device shooting the target workpiece. Find the area corresponding to the initial image data on the workpiece model, and use the scroll wheel to enlarge the workpiece model. Pay attention to the front and back of the workpiece model. Fig.10 , Fig.10 The eighth schematic diagram of the first conversion relationship calibration provided in the embodiment of the present application is as follows: Fig.10 The image shown in the left half is a 3D workpiece model of the target workpiece, and the image shown in the right half is initial image data obtained by photographing the target workpiece by the first acquisition device.

[0120] against Fig.10 The user can input multiple first calibration points in the initial image data and input second calibration points corresponding to each first calibration point in the 3D workpiece model. In order to improve the accuracy of the first conversion relationship obtained by calibration, before inputting the calibration points, it is necessary to clear the residual or last input calibration points. For example, see Fig.11 , Fig.11The ninth schematic diagram of the first conversion relationship calibration provided in the embodiment of the present application can click the delete control in the point selection list below the 3D workpiece model and the initial image data to clear the remaining or last entered calibration points.

[0121] When entering the calibration points, for example, see Fig.12 , Fig.12 The tenth schematic diagram of the first conversion relationship calibration provided in the embodiment of the present application is that, first, at an appropriate position of the initial image data, a single click is made using the left button of the mouse to select the first calibration point, and then, the system automatically or manually records the coordinate position of the first calibration point in the initial image data. Subsequently, in the 3D workpiece model, at a model position corresponding to the first calibration point in the initial image data, a single click is also made using the left button of the mouse to select the second calibration point, and similarly, the coordinate position of the second calibration point in the 3D workpiece model is recorded.

[0122] After obtaining the corresponding calibration points, see Fig.13 , Fig.13 The eleventh schematic diagram of the first conversion relationship calibration provided in the embodiment of the present application, the user can record the selected corresponding calibration point to the selection point list by clicking the record point control. The selection point list records the coordinates of each calibration point according to the sequence number of the calibration point, and includes a delete control, an up control, and a down control to the right of the coordinates of each calibration point. The user can delete the corresponding calibration point by clicking the delete control, and adjust the order of the calibration points by clicking the up control or the down control.

[0123] Using the same method, multiple first calibration points and second calibration points can be selected. For example, four corresponding points can be selected. When selecting these calibration points, in order to ensure accuracy and easy identification, positions with obvious features should be selected, such as a corner of a square hole, an edge on an elliptical contour, or a clearly identifiable point on the edge of a circular hole. Such selection helps to improve positioning accuracy and reduce errors.

[0124] Specifically, see Fig.14 , Fig.14 The twelfth schematic diagram of the first conversion relationship calibration provided in the embodiment of the present application shows an example of selecting one side of an ellipse as a calibration point. Such a point is easy to identify in the initial image data and is also easy to locate in the 3D workpiece model. Fig.15 , Fig.15 This is the thirteenth schematic diagram of the first conversion relationship calibration provided in the embodiment of the present application. The selected calibration point is located at a right angle to the model. Fig.16 , Fig.16The fourteenth schematic diagram of the first conversion relationship calibration provided in the embodiment of the present application shows the situation where an obvious point that is easily identifiable is selected on the edge of a circular hole as a calibration point.

[0125] After selecting a plurality of corresponding calibration points, a conversion relationship between the plurality of first calibration points and the plurality of second calibration points is calculated as a first conversion relationship. Fig.17 , Fig.17 The fifteenth schematic diagram of the calibration of the first conversion relationship provided in the embodiment of the present application, the user can automatically trigger the calculation process by clicking the calculation matrix control in the lower left corner of the point configuration page. This process not only outputs the camera result matrix, which represents the first conversion relationship corresponding to the first acquisition device, but also gives the error value of the matrix calculation for evaluating the accuracy of the conversion relationship.

[0126] In order to improve the accuracy and calculation efficiency of the first conversion relationship, and thus improve the efficiency of workpiece defect detection and positioning, the PNP (Perspective-n-Point) algorithm can be used in the calculation process. The algorithm uses the correspondence between multiple spatial points and their projection points on the image, and solves the optimal coordinate transformation parameters through mathematical optimization, that is, the camera result matrix, which directly corresponds to the first conversion relationship. In other embodiments, any other algorithm that can calculate the camera result matrix can also be used.

[0127] After the camera result matrix is ​​calculated by the above algorithm, if the camera result matrix is ​​0, it means that the selected calibration point may be wrong, the calibration file of the first acquisition device is not correctly configured (such as missing internal reference data), the dongle is not effective, etc. At this time, the relevant settings should be rechecked and adjusted.

[0128] After obtaining the above-mentioned first conversion relationship, in order to improve the accuracy of the first conversion relationship, and then improve the accuracy of workpiece defect detection and positioning, the first conversion relationship can be verified. In a possible embodiment, if the above-mentioned matrix calculation error is within an acceptable range, for example, the error value is less than 10, it indicates that the selected calibration point is relatively accurate, and the obtained first conversion relationship is also relatively accurate.

[0129] In another possible embodiment, a third calibration point inputted in the initial image data and a fourth calibration point inputted in the 3D workpiece model may be obtained, wherein the fourth calibration point corresponds to the third calibration point. Then, based on the first conversion relationship, the third calibration point is projected into the target coordinate system corresponding to the 3D workpiece model to obtain the projected calibration point. The error between the projected calibration point and the fourth calibration point is calculated. If the calculated error satisfies the preset error condition, the first conversion relationship is relatively accurate.

[0130] If a third calibration point and a fourth calibration point are used to verify the first conversion relationship, the error between the third calibration point and the fourth calibration point may be calculated. If the calculated error meets a preset error condition, the first conversion relationship is relatively accurate.

[0131] If multiple third calibration points and multiple fourth calibration points are used to verify the first conversion relationship, the error value between each third calibration point and the corresponding fourth calibration point is first calculated. Subsequently, statistical analysis can be performed based on these error values, such as calculating the mean value and median of the error, or calculating the percentage of points whose error values ​​exceed a preset threshold. If any of these statistical indicators meets the preset error condition (such as the mean value or median is less than a threshold, or the percentage of exceeding the threshold is less than a certain proportion), it can be considered that the first conversion relationship is relatively accurate as a whole.

[0132] After completing the above verification process, if the first conversion relationship is confirmed to be correct, it should be saved for subsequent use. Fig.18 , Fig.18 This is the sixteenth schematic diagram of the first conversion relationship calibration provided in the embodiment of the present application. The user can save the camera result matrix (i.e., the first conversion relationship) to the point information by clicking the set matrix control in the point configuration page. Fig.19 , Fig.19 This is the seventeenth schematic diagram of the first conversion relationship calibration provided in the embodiment of the present application. The user can view the set camera result matrix (ie, the first conversion relationship) on the matrix configuration page.

[0133] After obtaining the first conversion relationship corresponding to the first acquisition device on the R3 robot arm located at position 1, the first conversion relationship corresponding to the first acquisition device on the R3 robot arm located at other positions can also be calibrated in the same way. After obtaining the first conversion relationship corresponding to the current first acquisition device, the calibration file of the first acquisition device on other robot arms can be imported to modify the robot arm name, position information, etc. If the workpiece is a one-mold double-piece, it is necessary to obtain the first conversion relationship corresponding to the left and right first acquisition devices respectively. For example, if a one-mold single-piece part requires 20 first acquisition devices at different positions, a total of 20 camera result matrices, that is, 20 first conversion relationships, are required. If a one-mold double-piece part requires 8 first acquisition devices at different positions, a total of 8x2=16 camera result matrices, that is, 16 first conversion relationships, are required.

[0134] After obtaining the first conversion relationship corresponding to each first acquisition device, click the save control at the lower right corner of the software to prevent information loss after closing the point configuration page.

[0135] By applying the above embodiment, by simultaneously displaying the initial image data acquired by the first acquisition device and the detailed workpiece model, the operator can intuitively determine the corresponding calibration points in two dimensions. By accurately acquiring and matching multiple first calibration points in the initial image with multiple second calibration points in the workpiece model, the accuracy and reliability of the calibration are enhanced. Furthermore, the first conversion relationship calculated based on these calibration points can ensure that the data acquired by the first acquisition device can be accurately mapped to the target coordinate system, thereby improving the accuracy and efficiency of workpiece defect detection and positioning, and providing a solid data foundation for subsequent workpiece defect detection and positioning, thereby greatly improving production efficiency and product quality.

[0136] The above content elaborates on how to obtain the first conversion relationship. The following will explain how to obtain the second conversion relationship. The second conversion relationship can be obtained by the following method:

[0137] According to the first position relationship and the first conversion relationship, the conversion relationship between each second acquisition device and the target coordinate system is calculated as the second conversion relationship corresponding to each second acquisition device.

[0138] Among them, the first position relationship is the position relationship between the first acquisition device and each second acquisition device on the same robotic arm. Specifically, the position relationship between the first acquisition device and the robotic arm, and the position relationship between each second acquisition device and the robotic arm can be obtained through hand-eye calibration.

[0139] Hand-eye calibration is to determine the positional relationship between the coordinate system of the end of the robot arm and the device coordinate system corresponding to the acquisition device, which generally includes the following key steps:

[0140] Prepare a calibration scene, which needs an object to be moved (such as a calibration chessboard), a robotic arm, and at least one acquisition device.

[0141] The acquisition equipment calibration is the process of determining the internal and external parameters of the camera, including the focal length of the camera lens, distortion parameters, camera optical center, etc., usually using methods such as checkerboard calibration or multi-angle calibration.

[0142] Robot arm calibration, using the calibration tool that comes with the robot arm or an external calibration tool for calibration, requires the robot arm's end effector to be aligned with the calibration object, and the robot arm's joint angles and the end effector's position and posture are calculated through the kinematic inverse algorithm.

[0143] Data collection, collects a series of posture data between the end effector of the robot and the collection device. These data can be measured by the joint angle of the robot and the posture of the end effector, or by using external measurement equipment for data collection.

[0144] Select the calibration method and choose the appropriate hand-eye calibration method according to the actual situation, such as point-to-point method, voxel method, direct solution method, least squares method, etc.

[0145] Calculate the transformation relationship and calculate the relative position and posture relationship between the robot arm and the visual sensor through the selected calibration method.

[0146] The relative position and posture relationship between the robot arm and the visual sensor obtained by the hand-eye calibration method can be used to obtain the position relationship between each acquisition device and the robot arm. According to the position relationship between each acquisition device and the robot arm, the relative position relationship between each acquisition device can be obtained, that is, the position relationship between the first acquisition device and the second acquisition device, and the position relationship between the first acquisition device and the second acquisition device is taken as the first position relationship.

[0147] By applying the above embodiment, the acquisition device is directly set on the robotic arm, and combined with the hand-eye calibration technology, the rapid acquisition of the precise positional relationship between multiple acquisition devices is realized. It not only simplifies the cumbersome operation steps in the traditional calibration process, greatly improves the overall performance and flexibility of workpiece defect detection and positioning, but also greatly improves the calculation accuracy and efficiency of the positional relationship, thereby improving the accuracy and efficiency of workpiece defect detection and positioning, providing a solid data foundation for subsequent workpiece defect detection and positioning, thereby greatly improving production efficiency and product quality.

[0148] After obtaining the first position relationship, the transformation relationship between each second acquisition device and the target coordinate system, that is, the second transformation relationship corresponding to each second acquisition device, can be calculated based on the first position relationship and the first transformation relationship corresponding to the aforementioned first acquisition device.

[0149] By applying the above-mentioned embodiment, a conversion system with the first acquisition device as the core reference point is constructed, which greatly simplifies the calculation process of the complex conversion relationship between multiple acquisition devices and the target coordinate system. Specifically, the conversion relationship between the first device coordinate system of the first acquisition device and the target coordinate system (i.e., the first conversion relationship) is first calibrated. Subsequently, by using the known positional relationship between the first acquisition device and multiple second acquisition devices (i.e., the first positional relationship), combined with the first conversion relationship, the conversion relationship between each second acquisition device and the target coordinate system (i.e., each second conversion relationship) can be efficiently and accurately derived. This method not only reduces the workload of repeated calibration, but also significantly improves the calculation accuracy and efficiency of the conversion relationship, thereby improving the accuracy and efficiency of workpiece defect detection and positioning, providing strong support for subsequent defect analysis, repair and quality control, and significantly improving production efficiency and product quality.

[0150] The first transformation relationship and the second transformation relationship are target transformation relationships. Based on the target transformation relationships corresponding to each acquisition device, the initial defect points in the 2D image obtained by each acquisition device to acquire the target workpiece are projected into the target coordinate system to which the 3D workpiece model of the target workpiece belongs, so as to obtain the defect points to be screened.

[0151] In S202, the distance between each defect point to be screened may be calculated using the Euclidean distance formula, or using a vector method, or using other methods that can obtain the distance between two points.

[0152] In S203, it can be understood that, without considering scaling, the distances between the various defect points are the same in different coordinate systems, so before projecting the initial defect points to the target coordinate system to which the workpiece model of the target workpiece belongs, the distances between the initial defect points can be calculated as the distances between the defect points to be screened. Then, the defect points to be screened whose distances are less than the preset screening threshold are merged according to the distances, and then projected to the target coordinate system.

[0153] Specifically, when the distance between multiple defect points to be screened is less than a preset screening threshold, there are two main fusion methods that can be applied to these points to obtain the target defect points.

[0154] The first method is to select one of the defect points to be screened as a representative, and fuse all other defect points whose distance is less than the threshold to this representative point, so as to form a more comprehensive or significant target defect point. For example, the geometric center, weighted average position of these points can be calculated, or the most representative point can be selected as the fusion result.

[0155] The second way is to create a new defect point, which is not based on any of the existing defect points to be screened, but is calculated based on the location information of all points whose distance is less than the threshold and other possible attributes (such as defect type, size, severity, etc.). This newly generated defect point will be used as the target defect point for subsequent defect analysis or processing. When creating a new point, its specific location may be determined by using algorithms such as the center point of the minimum bounding box, weighted centroid, or other more complex algorithms.

[0156] After the target defect points are obtained by fusion, in a possible embodiment, the target defect points can also be displayed. Specifically, the target defect points can be superimposed on the workpiece model for display. When the workpiece model superimposed with the target defect points is output, in order to ensure that the user can intuitively and conveniently observe each target defect point, thereby helping the user to perform defect detection and processing more efficiently, the target defect points can be enhanced or marked.

[0157] First, the most intuitive way is to visually highlight these target defect points and mark them with colors that contrast sharply with the main color of the workpiece model. For example, if the workpiece model is mainly gray or silver, you can choose bright colors such as red, yellow or blue to mark the defect points.

[0158] In addition to color marking, you can also use icons or symbols to mark, such as superimposing specific icons or symbols such as circles, crosses or arrows at the defect points. These icons can not only indicate the location of the defect, but also convey additional information (such as defect type, severity, etc.) through their shape or color. Text annotation can also be used, such as adding a short text description near the defect point to directly explain the nature of the defect or matters that need attention. The text can be set to the same or similar font color as the mark color to ensure the coordination of the overall visual effect.

[0159] The present application also provides a detection system, see Fig. 20 , Fig. 20 A schematic diagram of the structure of a detection system provided in an embodiment of the present application, wherein the detection system 2000 includes a robotic arm 2001, a collection device 2002, and a control device 2003;

[0160] Robotic arm 2001 is used to fix the acquisition equipment.

[0161] The acquisition device 2002 is used to acquire initial defect points of the target workpiece and send the acquired initial defect points to the control device.

[0162] The control device 2003 is used to execute any of the above-mentioned workpiece defect point fusion methods.

[0163] For the steps executed by the robot arm 2001, the acquisition device 2002 and the control device 2003, please refer to the description in the aforementioned steps 201 to 203, which will not be repeated here.

[0164] The acquisition device 2002 establishes a communication connection with the control device 2003 .

[0165] By applying the above-mentioned embodiments, defect points from different acquisition devices can be uniformly converted to the target coordinate system of the workpiece model. By accurately calculating the distance between each defect point and using a preset screening threshold, points with similar distances can be intelligently fused to obtain target defect points, thereby reducing redundant data and retaining defect information that is truly meaningful for detection, thereby reducing the complexity and false alarm rate of data processing, making the target defect points ultimately determined more accurate and reliable, providing strong support for subsequent defect analysis, repair and quality control, and significantly improving production efficiency and product quality.

[0166] Corresponding to the aforementioned positioning method for workpiece defect detection, the present application embodiment also provides a positioning device for workpiece defect detection, see Fig.21 , Fig.21 The schematic diagram of the structure of the workpiece defect point fusion device provided in the embodiment of the present application includes:

[0167] The defect projection module 2101 is used to project the initial defect points obtained by collecting the target workpiece by each collection device to the target coordinate system to which the workpiece model of the target workpiece belongs based on the target conversion relationship corresponding to each collection device, so as to obtain the defect points to be screened;

[0168] The distance calculation module 2102 is used to calculate the distance between each of the defect points to be screened;

[0169] The defect fusion module 2103 is used to fuse the defect points whose distances among the defect points to be screened are less than a preset screening threshold according to the distances to obtain target defect points.

[0170] By applying the above-mentioned embodiments, defect points from different acquisition devices can be uniformly converted to the target coordinate system of the workpiece model. By accurately calculating the distance between each defect point and using a preset screening threshold, points with similar distances can be intelligently fused to obtain target defect points, thereby reducing redundant data and retaining defect information that is truly meaningful for detection, thereby reducing the complexity and false alarm rate of data processing, making the final target defect points more accurate and reliable, and further providing strong support for subsequent defect analysis, repair and quality control, thereby significantly improving production efficiency and product quality.

[0171] In a possible implementation, the acquisition device includes a first acquisition device and a plurality of second acquisition devices, and the apparatus further includes:

[0172] A first calibration module, used for calibrating a conversion relationship between a first device coordinate system of the first acquisition device and the target coordinate system as a first conversion relationship corresponding to the first acquisition device;

[0173] A second calibration module, configured to calculate a transformation relationship between each of the second acquisition devices and the target coordinate system according to the first position relationship and the first transformation relationship, as a second transformation relationship corresponding to each of the second acquisition devices, wherein the first position relationship is a position relationship between the first acquisition device and the second acquisition device;

[0174] The acquisition device is arranged on a mechanical arm, and the device further comprises:

[0175] A third calibration module, used for obtaining the positional relationship between each of the acquisition devices and the robotic arm through hand-eye calibration;

[0176] a fourth calibration module, configured to calculate a positional relationship between the first acquisition device and the second acquisition device as a first positional relationship according to a positional relationship between the first acquisition device and the robotic arm and a positional relationship between the second acquisition device and the robotic arm;

[0177] The first calibration module includes:

[0178] A first calibration submodule is used to display the initial image data and the workpiece model obtained by photographing the target workpiece by the first acquisition device;

[0179] A second calibration submodule, used for acquiring a plurality of first calibration points inputted from the initial image data and a plurality of second calibration points inputted from the workpiece model, wherein each of the second calibration points corresponds to one of the first calibration points;

[0180] A third calibration submodule is used to calculate a conversion relationship between the plurality of first calibration points and the plurality of second calibration points as a first conversion relationship;

[0181] The device also includes:

[0182] a fifth calibration module, configured to obtain a third calibration point input from the initial image data and a fourth calibration point input from the workpiece model, wherein the fourth calibration point corresponds to the third calibration point;

[0183] a sixth calibration module, configured to project the third calibration point onto the target coordinate system based on the first conversion relationship to obtain a projected calibration point;

[0184] A seventh calibration module, used to calculate the error between the projection calibration point and the fourth calibration point;

[0185] The second calibration module includes:

[0186] A fourth submodule for calibrating, if the error satisfies a preset error condition, a conversion relationship between each of the second acquisition devices and the target coordinate system is calculated according to the first position relationship and the first conversion relationship as a second conversion relationship corresponding to each of the second acquisition devices;

[0187] The calibration third submodule comprises:

[0188] A first calibration subunit, configured to calculate a conversion relationship between the plurality of first calibration points and the plurality of second calibration points by a PNP algorithm as a first conversion relationship;

[0189] The acquisition device is arranged on a mechanical arm, and the mechanical arm is deployed on an automobile production line. The device further comprises:

[0190] A model building module, used to build models for various parts of the automobiles on the automobile production line in advance;

[0191] The model search module is used to obtain the type of the target workpiece and search for a model of a corresponding type in the model as the workpiece model of the target workpiece.

[0192] The present application also provides an electronic device, such as Fig. 22 As shown, including:

[0193] Memory 2201, used for storing computer programs;

[0194] The processor 2202 is used to implement the following steps when executing the program stored in the memory 2201:

[0195] Based on the target conversion relationship corresponding to each acquisition device, the initial defect points acquired by each acquisition device from the target workpiece are projected into the target coordinate system to which the workpiece model of the target workpiece belongs, so as to obtain the defect points to be screened;

[0196] Calculating the distance between each of the defect points to be screened;

[0197] According to the distance, the defect points whose distances among the defect points to be screened are merged to obtain the target defect points.

[0198] In addition, the electronic device may further include a communication bus and / or a communication interface, and the processor 2202, the communication interface, and the memory 2201 communicate with each other via the communication bus.

[0199] The communication bus mentioned in the above electronic device can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The communication bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, only one thick line is used in the figure, but it does not mean that there is only one bus or one type of bus.

[0200] The communication interface is used for communication between the above electronic device and other devices.

[0201] The memory may include a random access memory (RAM) or a non-volatile memory (NVM), such as at least one disk memory. Optionally, the memory may also be at least one storage device located away from the aforementioned processor.

[0202] The above-mentioned processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0203] In another embodiment provided in the present application, a computer-readable storage medium is provided, in which a computer program is stored. When the computer program is executed by a processor, the steps of any of the above-mentioned methods for fusing defect points of a workpiece are implemented.

[0204] In another embodiment provided in the present application, a computer program product including instructions is also provided, which, when executed on a computer, enables the computer to execute any of the workpiece defect point fusion methods in the above embodiments.

[0205] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from a website site, computer, server or data center to another website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium may be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more available media integrated. The available medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a solid-state hard disk (SSD), etc.

[0206] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0207] Each embodiment in this specification is described in a related manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0208] The above description is only a preferred embodiment of the present application and is not intended to limit the protection scope of the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application are included in the protection scope of the present application.

Claims

1. A method for fusing defect points of a workpiece, characterized in that: The method comprises: Based on the target conversion relationship corresponding to each acquisition device, the initial defect points acquired by each acquisition device from the target workpiece are projected into the target coordinate system to which the workpiece model of the target workpiece belongs, so as to obtain the defect points to be screened; Calculating the distance between each of the defect points to be screened; According to the distance, the defect points whose distances among the defect points to be screened are merged to obtain the target defect points.

2. The method according to claim 1, characterized in that The acquisition device includes a first acquisition device and a plurality of second acquisition devices, and the method further includes: Calibrate and obtain a conversion relationship between a first device coordinate system of the first acquisition device and the target coordinate system as a first conversion relationship corresponding to the first acquisition device; According to the first position relationship and the first conversion relationship, the conversion relationship between each second acquisition device and the target coordinate system is calculated as the second conversion relationship corresponding to each second acquisition device, wherein the first position relationship is the position relationship between the first acquisition device and the second acquisition device.

3. The method according to claim 2, characterized in that The acquisition device is arranged on a mechanical arm, and the method further comprises: Obtaining the positional relationship between each of the acquisition devices and the robotic arm through hand-eye calibration; According to the positional relationship between the first acquisition device and the robotic arm and the positional relationship between the second acquisition device and the robotic arm, the positional relationship between the first acquisition device and the second acquisition device is calculated as the first positional relationship.

4. The method according to claim 2, characterized in that: The calibration obtains a conversion relationship between the first device coordinate system of the first acquisition device and the target coordinate system as a first conversion relationship corresponding to the first acquisition device, including: Displaying the initial image data obtained by photographing the target workpiece by the first acquisition device and the workpiece model; Acquire a plurality of first calibration points inputted from the initial image data, and a plurality of second calibration points inputted from the workpiece model, wherein each of the second calibration points corresponds to one of the first calibration points; A conversion relationship between the plurality of first calibration points and the plurality of second calibration points is calculated as a first conversion relationship.

5. The method according to claim 4, characterized in that The method further comprises: Acquire a third calibration point inputted from the initial image data and a fourth calibration point inputted from the workpiece model, wherein the fourth calibration point corresponds to the third calibration point; Based on the first conversion relationship, projecting the third calibration point to the target coordinate system to obtain a projected calibration point; Calculating the error between the projected calibration point and the fourth calibration point; The calculating, based on the first position relationship and the first conversion relationship, the conversion relationship between each of the second acquisition devices and the target coordinate system as the second conversion relationship corresponding to each of the second acquisition devices, includes: If the error satisfies a preset error condition, a transformation relationship between each of the second acquisition devices and the target coordinate system is calculated according to the first position relationship and the first transformation relationship as the second transformation relationship corresponding to each of the second acquisition devices.

6. The method according to claim 4, characterized in that The calculating, as a first conversion relationship, a conversion relationship between the plurality of first calibration points and the plurality of second calibration points includes: The conversion relationship between the plurality of first calibration points and the plurality of second calibration points is calculated by a PNP algorithm as a first conversion relationship.

7. The method according to claim 1, characterized in that The acquisition device is arranged on a mechanical arm, and the mechanical arm is deployed on an automobile production line. The method further comprises: A model is established in advance for each component in the automobile on the automobile production line; The type of the target workpiece is obtained, and a model of a corresponding type is searched in the model to serve as the workpiece model of the target workpiece.

8. A device for fusing defect points of a workpiece, characterized in that: The device comprises: A defect projection module is used to project the initial defect points obtained by collecting the target workpiece by each collection device into the target coordinate system to which the workpiece model of the target workpiece belongs based on the target conversion relationship corresponding to each collection device, so as to obtain the defect points to be screened; A distance calculation module, used to calculate the distance between each of the defect points to be screened; The defect fusion module is used to fuse the defect points whose distances among the defect points to be screened are less than a preset screening threshold according to the distances to obtain target defect points.

9. The device according to claim 8, characterized in that The acquisition device includes a first acquisition device and a plurality of second acquisition devices, and the apparatus further includes: A first calibration module, used for calibrating a conversion relationship between a first device coordinate system of the first acquisition device and the target coordinate system as a first conversion relationship corresponding to the first acquisition device; A second calibration module, configured to calculate a transformation relationship between each of the second acquisition devices and the target coordinate system according to the first position relationship and the first transformation relationship, as a second transformation relationship corresponding to each of the second acquisition devices, wherein the first position relationship is a position relationship between the first acquisition device and the second acquisition device; The acquisition device is arranged on a mechanical arm, and the device further comprises: A third calibration module, used for obtaining the positional relationship between each of the acquisition devices and the robotic arm through hand-eye calibration; a fourth calibration module, configured to calculate a positional relationship between the first acquisition device and the second acquisition device as a first positional relationship according to a positional relationship between the first acquisition device and the robotic arm and a positional relationship between the second acquisition device and the robotic arm; The first calibration module includes: A first calibration submodule is used to display the initial image data and the workpiece model obtained by photographing the target workpiece by the first acquisition device; A second calibration submodule, used for acquiring a plurality of first calibration points inputted from the initial image data and a plurality of second calibration points inputted from the workpiece model, wherein each of the second calibration points corresponds to one of the first calibration points; A third calibration submodule is used to calculate a conversion relationship between the plurality of first calibration points and the plurality of second calibration points as a first conversion relationship; The device also includes: a fifth calibration module, configured to obtain a third calibration point input from the initial image data and a fourth calibration point input from the workpiece model, wherein the fourth calibration point corresponds to the third calibration point; a sixth calibration module, configured to project the third calibration point onto the target coordinate system based on the first conversion relationship to obtain a projected calibration point; A seventh calibration module, used to calculate the error between the projection calibration point and the fourth calibration point; The second calibration module includes: A fourth submodule for calibrating, if the error satisfies a preset error condition, a conversion relationship between each of the second acquisition devices and the target coordinate system is calculated according to the first position relationship and the first conversion relationship as a second conversion relationship corresponding to each of the second acquisition devices; The calibration third submodule comprises: A first calibration subunit, configured to calculate a conversion relationship between the plurality of first calibration points and the plurality of second calibration points by a PNP algorithm as a first conversion relationship; The acquisition device is arranged on a mechanical arm, and the mechanical arm is deployed on an automobile production line. The device further comprises: A model building module, used to build models for various parts of the automobiles on the automobile production line in advance; The model search module is used to obtain the type of the target workpiece and search for a model of a corresponding type in the model as the workpiece model of the target workpiece.

10. A detection system, characterized in that: The system includes a robotic arm, a collection device, and a control device; The mechanical arm is used to fix the acquisition device; The acquisition device is used to acquire the initial defect points of the target workpiece and send the acquired initial defect points to the control device; The control device is used to implement the method described in any one of claims 1-7.

Images