Wallboard part detection method, system, device and medium

Abstract

The application discloses a wallboard part detection method, system, device and medium, through simple equipment such as an imaging device and a calibration block, a conversion relationship between two-dimensional images is obtained, so that part features in a digital model are projected on two-dimensional images of a part real object, and then errors between part features of the part real object and standard digital models are obtained, the number and complexity of detection equipment are reduced; meanwhile, the application method does not have strict requirements on the placement position of a part to be detected, and the actual position of the part can be quickly obtained through the calibration block for detection; furthermore, the wallboard part as a whole can be measured only through a small amount of pictures, the detection difficulty is reduced, errors caused by multiple measurements for obtaining results in the past are avoided, and the detection accuracy is improved.

Description

Technical Field

[0001] This application relates to the field of part feature detection, and in particular to a method, system, equipment and medium for detecting panel-type parts. Background Technology

[0002] Aircraft panel-like parts are generally flat, and to reduce weight, they often have milled recessed areas. Due to the low overall thickness of these panel parts, the transition radius of these recessed areas is usually less than 1 / 4 of a radius, making them difficult to measure using conventional coordinate measuring machines (CMMs). Current technologies typically use a semi-transparent film with panel outlines drawn on it, and determine the machining accuracy of the recessed area outlines through manual observation and comparison. Alternatively, a video measuring instrument with a moving axis can be used to measure each area individually to obtain the characteristic errors of the panel-like parts. However, both methods have poor accuracy and cannot meet the needs of aircraft assembly technology development. Summary of the Invention

[0003] The main objective of this application is to provide a method, system, device, and medium for detecting panel-type parts, aiming to solve the technical problem that the existing methods have poor accuracy in obtaining feature errors of panel-type parts.

[0004] To achieve the above objectives, this application provides a method for inspecting panel-type parts, wherein the inspection method is applied to the controller of a measuring device; wherein the measuring device further includes a horizontal platform, a calibration block, and an imaging device, comprising:

[0005] Receive a first image of the wall panel-like part to be tested acquired by the imaging device; wherein the wall panel-like part to be tested is disposed on the horizontal platform, and the wall panel-like part to be tested includes at least three reference holes;

[0006] The calibration block is controlled to be inserted into each of the reference holes of the wall panel-like part to be tested in sequence to form multiple calibration combinations, and multiple second images of the multiple calibration combinations are received by the imaging device; wherein, the calibration block is a cylinder, and a flat plate with a calibration pattern is provided on the top of the calibration block;

[0007] Based on the first image and multiple second images, the part features in the digital model of the panel-type part to be tested are mapped to the camera coordinate system to obtain the mapped features; wherein, the camera coordinate system is established based on the second image;

[0008] Based on the mapping features and the first image, the feature error of the panel-type part to be tested is obtained.

[0009] Optionally, the step of mapping the part features in the digital model of the panel-like part to be tested onto the camera coordinate system based on the first image and multiple second images to obtain the mapped features includes:

[0010] The calibration coordinate values ​​of multiple calibration blocks are obtained by using multiple second images;

[0011] The center coordinates of each reference hole in the first image are obtained by using multiple calibration coordinate values.

[0012] Based on the coordinates of the hole center, the part features are mapped onto the camera coordinate system to obtain the mapped features.

[0013] Optionally, the step of obtaining the feature error of the panel-like part under test based on the mapping features and the first image includes:

[0014] The mapped features are projected onto the first image according to the camera parameter matrix to obtain the projected features;

[0015] The feature error is obtained based on the first image and the projection features.

[0016] Optionally, the step of obtaining the feature error based on the first image and the projection features includes:

[0017] Based on the projection features, edge features on the first image are extracted; wherein, the projection features include multiple projection points;

[0018] Based on the edge features and the projection features, obtain the pixel error between each projection point and the edge features;

[0019] The feature error is obtained based on the multiple pixel errors.

[0020] Optionally, the step of obtaining the feature error based on the plurality of pixel errors includes:

[0021] The pixel error corresponding to each projection point is converted into physical distance using the camera parameter matrix to obtain multiple first feature errors;

[0022] The feature error is obtained based on a plurality of the first feature errors.

[0023] Optionally, the calibration pattern is a black and white checkerboard pattern.

[0024] Optionally, before the step of controlling the imaging device to measure the panel-like part under test and obtaining the first image, the method further includes:

[0025] The intrinsic and extrinsic parameters of the imaging device are calibrated.

[0026] Furthermore, to achieve the above objectives, this application also provides a panel-type parts inspection system, wherein the inspection system is applied to the controller of a measuring device; wherein the measuring device further includes a horizontal platform, a calibration block, and an imaging device, comprising:

[0027] The first image acquisition module is used to receive a first image of the wall panel-like part to be tested acquired by the imaging device; wherein the wall panel-like part to be tested is disposed on the horizontal platform, and the wall panel-like part to be tested includes at least three reference holes.

[0028] The second image acquisition module is used to control the calibration block to be inserted into each of the reference holes of the wall panel-like part to be tested in sequence, forming multiple calibration combinations, and to receive multiple second images of the multiple calibration combinations acquired by the imaging device; wherein, the calibration block is a cylinder, and a flat plate with a calibration pattern is provided on the top of the calibration block;

[0029] The mapping feature acquisition module is used to map the part features in the digital model of the wall panel part to be tested to the camera coordinate system based on the first image and multiple second images to obtain the mapping features; wherein, the camera coordinate system is established based on the second image;

[0030] The feature error acquisition module is used to obtain the feature error of the wall panel part to be tested based on the mapping features and the first image.

[0031] In addition, to achieve the above objectives, this application also provides a computer device including a memory and a processor, wherein the memory stores a computer program and the processor executes the computer program to implement the above-described method.

[0032] In addition, to achieve the above objectives, this application also provides a computer-readable storage medium storing a computer program, on which a processor executes the computer program to implement the above-described method.

[0033] The beneficial effects that this application can achieve.

[0034] This application discloses a method, system, device, and medium for detecting panel-like parts. The detection method is applied to the controller of a measuring device. The measuring device further includes a horizontal platform, a calibration block, and an imaging device. The method receives a first image of the panel-like part to be tested, acquired by the imaging device. The panel-like part to be tested is disposed on the horizontal platform and includes at least three reference holes. The calibration block is controlled to be sequentially inserted into each of the reference holes of the panel-like part to form multiple calibration combinations, and multiple second images of the multiple calibration combinations are received by the imaging device. The calibration block is a cylinder, and a flat plate with a calibration pattern is provided on its top. Based on the first image and multiple second images, the part features in the digital model of the panel-like part to be tested are mapped to a camera coordinate system to obtain mapped features. The camera coordinate system is established based on the second image. Based on the mapped features and the first image, the feature error of the panel-like part to be tested is obtained. This method utilizes simple equipment such as imaging devices and calibration blocks to obtain the conversion relationship between two-dimensional images. This allows the part features in the digital model to be projected onto the two-dimensional image of the actual part, thereby obtaining the error between the part features of the actual part and the standard digital model. This reduces the number and complexity of the inspection equipment. At the same time, the method of this application does not have strict requirements on the placement of the part to be tested. The actual position of the part can be quickly obtained through the calibration block for inspection, thereby improving the inspection efficiency. Furthermore, the entire panel part can be measured with only a few images, reducing the inspection difficulty and avoiding the cumulative error of obtaining results through multiple measurements in the past, thus improving the inspection accuracy. Attached Figure Description

[0035] Figure 1 This is a schematic diagram of the computer device structure for the hardware operating environment involved in the embodiments of this application;

[0036] Figure 2 A schematic flowchart illustrating a method for inspecting panel-type parts provided in this application embodiment;

[0037] Figure 3 This is a schematic diagram of the functional modules of a panel-type parts inspection system provided in an embodiment of this application;

[0038] Figure 4 A schematic diagram of an apparatus for acquiring a first image in a method for detecting panel-type parts provided in an embodiment of this application;

[0039] Figure 5 A schematic diagram of the calibration pattern on the top of the calibration block in a measuring device for a method of detecting panel-type parts provided in an embodiment of this application;

[0040] Figure 6This is a schematic diagram of point sampling on a calibration block for a method of detecting panel-type parts provided in an embodiment of this application;

[0041] Figure 7 This is a first image schematic diagram of a method for detecting panel-type parts provided in an embodiment of this application;

[0042] Figure 8 This is a schematic diagram of the projection features of a method for detecting panel-type parts provided in an embodiment of this application.

[0043] The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0044] It should be understood that the specific embodiments described herein are merely illustrative of this application and are not intended to limit this application.

[0045] The main solution of this application embodiment is: a method, system, device, and medium for detecting panel-like parts. The detection method is applied to the controller of a measuring device. The measuring device further includes a horizontal platform, a calibration block, and an imaging device. It receives a first image of the panel-like part to be tested acquired by the imaging device. The panel-like part to be tested is disposed on the horizontal platform and includes at least three reference holes. The calibration block is controlled to be inserted sequentially into each of the reference holes of the panel-like part to be tested, forming multiple calibration combinations. Multiple second images of the multiple calibration combinations are received by the imaging device. The calibration block is a cylinder, and a flat plate with a calibration pattern is provided on its top. Based on the first image and multiple second images, the part features in the digital model of the panel-like part to be tested are mapped to a camera coordinate system to obtain mapped features. The camera coordinate system is established based on the second image. Based on the mapped features and the first image, the feature error of the panel-like part to be tested is obtained.

[0046] In existing technologies, aircraft panel-like parts are generally flat. To reduce weight, milled recessed areas are often present. Due to the relatively low overall thickness of the panel parts, the transition radius of these recessed areas is typically less than 1 / 4 of a radius, making them difficult to measure using conventional coordinate measuring machines (CMMs). Current technologies often employ a semi-transparent film overlaid with panel outlines, with manual observation and comparison to determine the machining accuracy of the recessed area outlines. Alternatively, a video measuring instrument with a moving axis can be used to measure each area individually to obtain the characteristic errors of the panel-like parts. However, both methods have poor accuracy and are insufficient to meet the demands of aircraft assembly technology development.

[0047] To address this, this application provides a solution that uses simple devices such as imaging equipment and calibration blocks to obtain the conversion relationship between two-dimensional images. This allows the part features in the digital model to be projected onto the two-dimensional image of the actual part, thereby obtaining the error between the part features of the actual part and the standard digital model. This reduces the number and complexity of the testing equipment. Furthermore, the method of this application does not have strict requirements on the placement of the part to be tested; the actual position of the part can be quickly obtained for testing using the calibration block. Moreover, the entire panel part can be measured using only a few images, reducing the difficulty of testing and avoiding the cumulative errors from multiple measurements, thus improving the accuracy of the test.

[0048] Reference Figure 1 , Figure 1 This is a schematic diagram of the computer device structure of the hardware operating environment involved in the embodiments of this application.

[0049] like Figure 1 As shown, the computer device may include: a processor 1001, such as a central processing unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. The communication bus 1002 is used to enable communication between these components. The user interface 1003 may include a display screen and an input unit such as a keyboard; optionally, the user interface 1003 may also include a standard wired interface or a wireless interface. The network interface 1004 may optionally include a standard wired interface or a wireless interface (such as a Wireless Fidelity (WI-FI) interface). The memory 1005 may be a high-speed random access memory (RAM) or a stable non-volatile memory (NVM), such as a disk drive. Optionally, the memory 1005 may also be a storage device independent of the aforementioned processor 1001.

[0050] Those skilled in the art will understand that Figure 1 The structure shown does not constitute a limitation on the computer device and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0051] like Figure 1 As shown, the memory 1005, which serves as a storage medium, may include an operating system, a data storage module, a network communication module, a user interface module, and electronic programs.

[0052] exist Figure 1In the computer device shown, the network interface 1004 is mainly used for data communication with the network server; the user interface 1003 is mainly used for data interaction with the user; the processor 1001 and the memory 1005 in the computer device of the present invention can be set in the computer device, and the computer device calls the wall panel part detection system stored in the memory 1005 through the processor 1001 and executes the wall panel part detection method provided in the embodiment of this application.

[0053] Reference Figure 2 Based on the hardware device of the foregoing embodiments, embodiments of this application provide a method for detecting panel-like parts, wherein the detection method is applied to the controller of a measuring device; wherein the measuring device further includes a horizontal platform, a calibration block, and an imaging device, comprising:

[0054] In a specific embodiment, the detection device is used to detect panel-like parts and includes a controller, a horizontal platform, a calibration block, and an imaging device. The controller controls other components in the measuring device, receives information, and processes information. In this embodiment, the controller can be a component of the aforementioned computer equipment or can directly refer to the aforementioned computer equipment. The computer equipment can be a component of the measuring device. The horizontal platform supports other components in the measuring device and the panel-like part to be measured. The calibration block determines the correspondence between object points and image points. The imaging device is used to acquire or measure the panel-like part to be measured; typically, a camera or other measuring equipment can be used. In this embodiment, a common industrial camera and a common lens are used. In addition, the measuring device also includes components such as a camera bracket.

[0055] As an optional implementation, before the step of controlling the imaging device to measure the panel-like part under test and obtaining the first image, the method further includes:

[0056] The intrinsic and extrinsic parameters of the imaging device are calibrated.

[0057] In practical implementation, to determine the relationship between the three-dimensional geometric position of a point on the surface of a spatial object and its corresponding point in the image, a geometric model of camera imaging must be established. These geometric model parameters are the camera parameters, mainly including intrinsic and extrinsic parameters. The process of solving for these parameters is called camera calibration. The accuracy of the camera calibration results and the stability of the algorithm directly affect the accuracy of the results produced by the camera. Before conducting the detection task, after setting up the measuring device, the intrinsic and extrinsic parameters of the imaging equipment need to be calibrated to provide a fundamental guarantee for the accuracy of subsequent detection results.

[0058] S10: Receive the first image of the wall panel-like part to be tested acquired by the imaging device; wherein, the wall panel-like part to be tested is disposed on the horizontal platform, and the wall panel-like part to be tested includes at least three reference holes;

[0059] In the specific implementation process, such as Figure 4 As shown, the panel-like part to be tested is placed on a horizontal platform directly below the imaging device, ensuring its bottom surface is in good contact with the platform. The imaging device is then activated to photograph the panel-like part, obtaining the image as shown below. Figure 7 The first image shown displays the recessed area and other features of the panel-like part under test. Since subsequent testing steps are based on the information in the first image, there are no strict requirements regarding the placement of the panel-like part, facilitating practical testing, reducing the time and effort spent adjusting the test position, and improving testing efficiency. Most panel-like parts have reference holes, and several holes existing on the part itself can be selected as reference holes. Because the calibration method using the calibration block requires at least three coordinate points, at least three holes must be selected as reference holes. In this embodiment, three reference holes perpendicular to the ground are selected from the panel-like part under test, with a diameter of D.

[0060] S20: Control the calibration block to be inserted into each of the reference holes of the wall panel-like part to be tested in sequence to form multiple calibration combinations, and receive multiple second images of the multiple calibration combinations acquired by the imaging device; wherein, the calibration block is a cylinder, and the top of the calibration block is provided with a flat plate with a calibration pattern;

[0061] In practical implementation, the calibration block refers to the component used for calibration during image detection, such as... Figure 5 As shown, the calibration block includes a flat plate with an identifiable calibration pattern, a cylinder, and a reference base that mates with the cylinder. The bottom surface of the cylinder is parallel to the top surface of the flat plate, and the bottom surface of the cylinder is perpendicular to its axis. The axis of the hole in the reference base is perpendicular to its bottom surface. The calibration pattern on the flat plate is used to subsequently determine the transformation relationship between coordinate systems. The cylinder is used to insert into the corresponding reference hole, and the reference base is used to determine the coordinates of points on the calibration pattern. In this embodiment, the calibration block consists of a flat plate with a black and white checkerboard pattern and a cylinder perpendicular to the flat plate. The diameter of the cylinder is D, which matches the reference hole of the panel-like part to be tested. The calibration block also includes a reference base, which is a cube with a hole of diameter D perpendicular to its upper and lower surfaces at its center.

[0062] Specifically, calibration blocks of corresponding sizes are inserted sequentially into multiple reference holes in the panel-like part to be tested. The entire assembly formed by the calibration blocks and the panel-like part to be tested is the calibration combination. The controller controls the imaging device to take pictures of each calibration combination and obtain the second image corresponding to each calibration combination.

[0063] As an optional implementation, the calibration pattern is a black and white checkerboard pattern.

[0064] In the specific implementation process, the calibration pattern is an identifiable pattern array with fixed spacing, which can be a black and white checkerboard, black and white solid dots, etc.; in this embodiment, a black and white checkerboard pattern is selected as the calibration pattern.

[0065] S30: Based on the first image and multiple second images, map the part features in the digital model of the panel-type part to be tested to the camera coordinate system to obtain the mapped features; wherein, the camera coordinate system is established based on the second image;

[0066] In the specific implementation process, both the first and second images are acquired based on the world coordinate system, while subsequent detection steps require the camera coordinate system. This necessitates calibrating the second image to obtain the transformation relationship between the world and camera coordinate systems, thus establishing the camera coordinate system. The relative relationships between the camera and world coordinate systems are fixed: the Z-axis of the camera coordinate system is collinear with the Z-axis of the world coordinate system, and the XY plane of the camera coordinate system is parallel to the XY plane of the world coordinate system, which serves as a horizontal platform. Transforming the first and second images from the world coordinate system to the camera coordinate system maps the part features of the tested panel-like parts in both images to the camera coordinate system, thus obtaining the mapped features.

[0067] As an optional implementation, the step of mapping the part features in the digital model of the panel-like part to be tested onto the camera coordinate system based on the first image and multiple second images to obtain the mapped features includes:

[0068] The calibration coordinate values ​​of multiple calibration blocks are obtained by using multiple second images;

[0069] The center coordinates of each reference hole in the first image are obtained by using multiple calibration coordinate values.

[0070] Based on the coordinates of the hole center, the part features are mapped onto the camera coordinate system to obtain the mapped features.

[0071] In the specific implementation process, before inspection, the positional relationship between the coordinates of three points in the calibration pattern of the calibration block and its outer contour is obtained using an image measuring instrument, thus obtaining the transformation formula from the coordinates of the three points in the calibration pattern to the center of the corresponding reference hole. Three calibration points are selected in the calibration pattern of each second image, and the corresponding center coordinates of the reference holes are obtained by transformation based on the calibration coordinate values ​​of the three calibration points. The center coordinates of each reference hole are obtained in this way. The part features extracted from the digital model of the panel-type part are mapped onto the camera coordinate system according to the correspondence of the center coordinates of the reference holes, thus obtaining the mapped features.

[0072] Specifically, the distance from the upper surface of the calibration block's flat plate to the lower surface of the calibration block's cylinder is denoted as Δz. The reference block is placed on the platform of the image measuring instrument, and the coordinates (x0, y0) of its hole center are measured. Keeping the reference block in place, the calibration block is inserted, and then the image measuring instrument is used to measure the grid points on the black and white checkerboard pattern on its flat plate. For example... Figure 6 Taking a 3x4 checkerboard pattern as an example, six grid points can be extracted. The bottom left corner point is taken as the origin O, with coordinates (x1, y1) under the image measuring instrument. Its left adjacent point is P, with coordinates (x2, y2), and its upper adjacent point is Q, with coordinates (x3, y3). Since the pattern lacks symmetry, regardless of the measurement orientation, O, P, and Q always correspond to the same points on the pattern, following the same selection criteria. A calibration block coordinate system is established using O, P, and Q, with O as the origin, OP as the X-axis, and OQ as the Y-axis. OP is perpendicular to OQ. The Z-axis is the straight line passing through point O and perpendicular to the OPQ plane downwards, with downwards as the positive direction. Therefore, the coordinates (x0, y0) under the OPQ calibration block coordinate system are... Since the calibration block is a rigid body, its geometric dimensions are constant. Regardless of the measurement orientation, the coordinates will remain unchanged. During measurement, the world coordinate system is established on a horizontal platform, with the Z-axis aligned with the Z-axis of the calibration block. Due to this invariance, when the new OPQ coordinates (x1′, y1′), (x2′, y2′), and (x3′, y3′) are obtained in the new world coordinate system, we have:

[0073]

[0074]

[0075] Let: (x1-x0)(x2-x0)+(y1-y0)(y2-y0)=S

[0076] Given (x1-x0)(x3-x0)+(y1-y0)(y3-y0)=P, we can find the coordinates of the center of the hole in the new world coordinate system.

[0077]

[0078] The center coordinates A, B, and C of at least three reference holes are obtained by inserting calibration blocks into different reference holes. The center coordinates A0, B0, and C0 of three reference holes are selected from the digital model of the panel-like part to be tested. The rigid body transformation matrix T from A0, B0, and C0 to A, B, and C is solved, satisfying A = TA0, B = TB0, and C = TC0. For any point M0 on the digital model, its mapping in the world coordinate system is TM0. The camera projection matrix T can be obtained through camera calibration. camThis matrix can map points in the world coordinate system to the camera coordinate system. Therefore, for any point M0 on the logarithmic modulus, its mapping T in the camera coordinate system can be obtained. cam TM0. According to this method, the part features of the digital model of the panel-type part to be tested are mapped to the camera coordinate system to obtain the mapped features.

[0079] S40: Based on the mapping features and the first image, obtain the feature error of the panel-type part to be tested.

[0080] In the specific implementation process, such as Figure 7 As shown, due to lens parallax, the reference hole and part of the sidewall of the recessed area are visible in the first image. These sidewalls are difficult to detect using traditional methods. By comparing the part features in the first image with the part features in the standard part model in the mapped features, the feature error between the actual part and the part model can be obtained. By exchanging the relationships between the two-dimensional images, the error between the part features of the actual part and the standard model is obtained, reducing the detection difficulty and avoiding the errors accumulated from obtaining results through multiple measurements in the past.

[0081] As an optional implementation, the step of obtaining the feature error of the panel-like part under test based on the mapping features and the first image includes:

[0082] The mapped features are projected onto the first image according to the camera parameter matrix to obtain the projected features;

[0083] The feature error is obtained based on the first image and the projection features.

[0084] In the specific implementation process, the mapped features are projected onto the first image according to the camera projection matrix to obtain the projected features of the part features of the digital model of the panel-type part to be tested; that is, as shown in the figure. Figure 8 As shown in the dashed box, the contour boundaries of the part features mapped to the camera coordinate system are projected point by point onto the two-dimensional image; the feature error is obtained based on the difference between the projection and the features in the two-dimensional image.

[0085] As an optional implementation, the step of obtaining the feature error based on the first image and the projection features includes:

[0086] Based on the projection features, edge features on the first image are extracted; wherein, the projection features include multiple projection points;

[0087] Based on the edge features and the projection features, obtain the pixel error between each projection point and the edge features;

[0088] The feature error is obtained based on the multiple pixel errors.

[0089] In practice, manufacturing factors of the panel-like parts under test mean that the physical object and the digital model of the part will not be completely identical. Therefore, the projected features (part features in the digital model) will not completely overlap with the features in the first image (part features in the physical object). By extracting the edge features of the first image near the projected features and calculating the pixel distance from the edge features to the projected features, the feature error can be obtained.

[0090] Specifically, taking each projection point in the projection feature as the center, a circular region of n pixels is defined in its vicinity. Edges are extracted in this region using edge operators. The point in this region that is closest to the projection point is found, and its Euclidean distance is used as the pixel error at that location.

[0091] As an optional implementation, the step of obtaining the feature error based on the plurality of pixel errors includes:

[0092] The pixel error corresponding to each projection point is converted into physical distance using the camera parameter matrix to obtain multiple first feature errors;

[0093] The feature error is obtained based on a plurality of the first feature errors.

[0094] In the specific implementation process, the pixel error is converted into physical distance through the camera parameter matrix to obtain the conversion coefficient. The product of the pixel distance at a point and the coefficient is the actual error at that point, which is the first feature error. The first feature error corresponding to each feature point is calculated, and the set of them is the feature error between the physical object of the panel-type part to be tested and the digital model of the part.

[0095] Specifically, let the coordinates of the projection point be (u, v), and its corresponding digital model point coordinates be (x, v). M y M , z M ), select a point nearby (x) M ′,y M ′,z M ), calculate its projection point coordinates as (u′, v′), then the conversion factor from pixel distance to actual physical distance at this point is: Multiplying the pixel distance by this coefficient gives the actual error at that point.

[0096] It should be understood that the above are merely illustrative examples and do not constitute any limitation on the technical solution of this application. Those skilled in the art can make settings as needed in practical applications, and no restrictions are imposed here.

[0097] As can be seen from the above description, this embodiment uses simple devices such as imaging equipment and calibration blocks to obtain the conversion relationship between two-dimensional images, so that the part features in the digital model are projected onto the two-dimensional image of the actual part, thereby obtaining the error between the part features of the actual part and the standard digital model, reducing the number and complexity of the detection equipment. At the same time, the method of this application does not have strict requirements on the placement of the part to be tested. The actual position of the part can be quickly obtained for detection through the calibration block. Furthermore, the entire panel part can be measured with only a few images, reducing the detection difficulty and avoiding the cumulative error of obtaining results through multiple measurements in the past, thus improving the accuracy of detection.

[0098] Reference Figure 3 Based on the same inventive concept, embodiments of this application also provide a panel-type parts inspection system, wherein the inspection system is applied to the controller of a measuring device; wherein the measuring device further includes a horizontal platform, a calibration block, and an imaging device, comprising:

[0099] The first image acquisition module is used to receive a first image of the wall panel-like part to be tested acquired by the imaging device; wherein the wall panel-like part to be tested is disposed on the horizontal platform, and the wall panel-like part to be tested includes at least three reference holes.

[0100] The second image acquisition module is used to control the calibration block to be inserted into each of the reference holes of the wall panel-like part to be tested in sequence, forming multiple calibration combinations, and to receive multiple second images of the multiple calibration combinations acquired by the imaging device; wherein, the calibration block is a cylinder, and a flat plate with a calibration pattern is provided on the top of the calibration block;

[0101] The mapping feature acquisition module is used to map the part features in the digital model of the wall panel part to be tested to the camera coordinate system based on the first image and multiple second images to obtain the mapping features; wherein, the camera coordinate system is established based on the second image;

[0102] The feature error acquisition module is used to obtain the feature error of the wall panel part to be tested based on the mapping features and the first image.

[0103] It should be noted that each module in the panel-type parts detection system in this embodiment corresponds one-to-one with each step in the panel-type parts detection method in the aforementioned embodiment. Therefore, the specific implementation of this embodiment can refer to the implementation of the aforementioned panel-type parts detection method, and will not be repeated here.

[0104] Furthermore, in one embodiment, the present application also provides a computer device, the device including a processor, a memory, and a computer program stored in the memory, the computer program being executed by the processor to implement the steps of the methods in the foregoing embodiments.

[0105] Furthermore, in one embodiment, the present application also provides a computer storage medium storing a computer program, which, when executed by a processor, implements the steps of the methods described in the foregoing embodiments.

[0106] In some embodiments, the computer-readable storage medium may be a memory such as FRAM, ROM, PROM, EPROM, EEPROM, flash memory, magnetic surface memory, optical disk, or CD-ROM; or it may be a device including one or any combination of the above-mentioned memories. The computer may be a variety of computing devices, including smart terminals and servers.

[0107] In some embodiments, executable instructions may take the form of a program, software, software module, script, or code, written in any form of programming language (including compiled or interpreted languages, or declarative or procedural languages), and may be deployed in any form, including as a standalone program or as a module, component, subroutine, or other unit suitable for use in a computing environment.

[0108] As an example, executable instructions may, but do not necessarily, correspond to files in a file system. They may be stored as part of a file that holds other programs or data, for example, in one or more scripts in a Hyper Text Markup Language (HTML) document, in a single file dedicated to the program in question, or in multiple collaborating files (e.g., a file that stores one or more modules, subroutines, or code sections).

[0109] As an example, executable instructions can be deployed to execute on a single computing device, or on multiple computing devices located in one location, or on multiple computing devices distributed across multiple locations and interconnected via a communication network.

[0110] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or system. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or system that includes that element.

[0111] The sequence numbers of the embodiments in this application are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0112] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as read-only memory / random access memory, magnetic disk, optical disk) and includes several instructions to cause a multimedia terminal device (which may be a mobile phone, computer, television receiver, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0113] The above are merely preferred embodiments of this application and do not limit the patent scope of this application. Any equivalent structural or procedural transformations made using the content of this application's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of this application.

Claims

1. A method for inspecting panel-type parts, characterized in that, The detection method is applied to the controller of the measuring device; wherein the measuring device further includes a horizontal platform, a calibration block, and an imaging device, and includes the following steps: Receive a first image of the wall panel-like part to be tested acquired by the imaging device; wherein the wall panel-like part to be tested is disposed on the horizontal platform, and the wall panel-like part to be tested includes at least three reference holes; The calibration block is controlled to be inserted into each of the reference holes of the wall panel-like part to be tested in sequence to form multiple calibration combinations, and multiple second images of the multiple calibration combinations are received by the imaging device; wherein, the calibration block is a cylinder, and a flat plate with a calibration pattern is provided on the top of the calibration block; Based on the first image and multiple second images, the part features in the digital model of the panel-type part to be tested are mapped to the camera coordinate system to obtain the mapped features; wherein, the camera coordinate system is established based on the second image; Based on the mapping features and the first image, the feature error of the panel-type part to be tested is obtained.

2. The method for inspecting panel-type parts as described in claim 1, characterized in that, The step of mapping the part features in the digital model of the panel-like part to be tested onto the camera coordinate system based on the first image and multiple second images to obtain the mapped features includes: The calibration coordinate values ​​of multiple calibration blocks are obtained by using multiple second images; The center coordinates of each reference hole in the first image are obtained by using multiple calibration coordinate values. Based on the coordinates of the hole center, the part features are mapped onto the camera coordinate system to obtain the mapped features.

3. The method for inspecting panel-type parts as described in claim 1, characterized in that, The step of obtaining the feature error of the wall panel-type part to be tested based on the mapping features and the first image includes: The mapped features are projected onto the first image according to the camera parameter matrix to obtain the projected features; The feature error is obtained based on the first image and the projection features.

4. The method for inspecting panel-type parts as described in claim 3, characterized in that, The step of obtaining the feature error based on the first image and the projection features includes: Based on the projection features, edge features on the first image are extracted; wherein, the projection features include multiple projection points; Based on the edge features and the projection features, obtain the pixel error between each projection point and the edge features; The feature error is obtained based on the multiple pixel errors.

5. The method for inspecting panel-type parts as described in claim 4, characterized in that, The step of obtaining the feature error based on the plurality of pixel errors includes: The pixel error corresponding to each projection point is converted into physical distance using the camera parameter matrix to obtain multiple first feature errors; The feature error is obtained based on a plurality of the first feature errors.

6. The method for inspecting panel-type parts as described in claim 1, characterized in that, The calibration pattern is a black and white checkerboard pattern.

7. The method for inspecting panel-type parts as described in claim 1, characterized in that, Before the step of receiving the first image of the panel-like part to be tested acquired by the imaging device, the method further includes: The intrinsic and extrinsic parameters of the imaging device are calibrated.

8. A detection system for panel-type parts, characterized in that, The detection system is applied to the controller of the measuring device; wherein, the measuring device further includes a horizontal platform, a calibration block, and an imaging device, comprising: The first image acquisition module is used to receive a first image of the wall panel-like part to be tested acquired by the imaging device; wherein the wall panel-like part to be tested is disposed on the horizontal platform, and the wall panel-like part to be tested includes at least three reference holes. The second image acquisition module is used to control the calibration block to be inserted into each of the reference holes of the wall panel-like part to be tested in sequence, forming multiple calibration combinations, and to receive multiple second images of the multiple calibration combinations acquired by the imaging device; wherein, the calibration block is a cylinder, and a flat plate with a calibration pattern is provided on the top of the calibration block; The mapping feature acquisition module is used to map the part features in the digital model of the wall panel part to be tested to the camera coordinate system based on the first image and multiple second images to obtain the mapping features; wherein, the camera coordinate system is established based on the second image; The feature error acquisition module is used to obtain the feature error of the wall panel part to be tested based on the mapping features and the first image.

9. A computer device, characterized in that, The computer device includes a memory and a processor, wherein the memory stores a computer program and the processor executes the computer program to implement the method as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, and the processor executes the computer program to implement the method as described in any one of claims 1-7.

Images