Calibration method, device, medium and product of camera in selective laser melting equipment
By generating a calibration array corresponding to the printed layer plane in a selective laser melting device, laser scanning and image acquisition are performed, solving the problems of image distortion and position error in camera calibration and achieving high-precision camera calibration.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- COMMERCIAL AIRCRAFT CORP OF CHINA LTD
- Filing Date
- 2026-02-12
- Publication Date
- 2026-06-02
Smart Images
Figure CN122134825A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of image processing technology, and in particular to a calibration method, device, medium, and product for a camera in a selective laser melting device. Background Technology
[0002] Selective Laser Melting (SLM) equipment is a mainstream metal additive manufacturing technology widely used in the manufacture of high-value-added parts for aerospace, medical implants, and other applications. To ensure the stability and quality of the SLM printing process, a machine vision-based powder bed quality monitoring system has become a standard feature of high-end SLM equipment. However, due to the extremely compact space within the build chamber and the safety requirements for laser path avoidance, the vision monitoring camera usually cannot be mounted vertically directly above the powder bed. Instead, it is often installed at a large angle, i.e., a pre-set off-axis angle, such as in a corner of the build chamber ceiling or a side window. Figure 1 This is a schematic diagram of camera installation in a selective laser melting device.
[0003] In adopting such Figure 1 The camera mounting method shown solves the field-of-view coverage problem, but it presents significant challenges for camera calibration pre-measurement. For example, existing technologies typically use a calibration reference placed on the substrate for camera shooting calibration. However, during the printing process, to maintain a constant relative distance between the printed layer plane and the SLM device, the substrate is usually moved downwards as the printed layer changes, causing the calibration reference to misalign with the printed layer plane, resulting in inaccurate camera calibration. Furthermore, because the camera in the SLM device uses... Figure 1 The preset angle installation method of the rangefinder shown causes perspective trapezoidal distortion in the acquired images, which makes camera calibration difficult. Summary of the Invention
[0004] This invention provides a method, device, medium, and product for calibrating a camera in a selective laser melting device, in order to improve the accuracy of camera calibration.
[0005] According to one aspect of the present invention, a calibration method for a camera in a selective laser melting apparatus is provided, the method comprising: Based on the installation orientation and field of view of the camera in the selective laser melting equipment, a calibration array corresponding to the current printing layer plane of the camera is generated; The selected area laser melting device is controlled to perform laser scanning on the current printing layer plane according to the calibration array, and to acquire the printing image of the calibration array; Extract the pixel coordinates of the calibration array in the image coordinate system from the printed image, and obtain the physical coordinates of the calibration array; The calibration result of the camera in the selected area laser melting device is determined based on the pixel coordinates and the physical coordinates.
[0006] According to another aspect of the present invention, a calibration device for a camera in a selective laser melting apparatus is provided, the device comprising: The calibration array generation module is used to generate a calibration array corresponding to the current printing layer plane of the camera based on the installation orientation and field of view of the camera in the selected area laser melting equipment. The printing image acquisition module is used to control the selected area laser melting device to perform laser scanning on the current printing layer plane according to the calibration array, and to acquire the printing image of the calibration array; The coordinate acquisition module is used to extract the pixel coordinates of the calibration array in the printed image in the image coordinate system, and to obtain the physical coordinates of the calibration array; The calibration result determination module is used to determine the calibration result of the camera in the selected area laser melting device based on the pixel coordinates and the physical coordinates.
[0007] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising: At least one processor; and a memory communicatively connected to said at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, which enables the at least one processor to perform the camera calibration method in the selective laser melting apparatus according to any embodiment of the present invention.
[0008] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions for causing a processor to execute and implement the camera calibration method in the selective laser melting apparatus according to any embodiment of the present invention.
[0009] According to another aspect of the present invention, a computer program product is provided, comprising a computer program that, when executed by a processor, implements the camera calibration method in a selective laser melting apparatus according to any embodiment of the present invention.
[0010] The technical solution of this invention generates a calibration array corresponding to the current printing layer plane of the camera based on the installation orientation and field of view of the camera in the selective laser melting device; controls the selective laser melting device to perform laser scanning on the current printing layer plane according to the calibration array and acquires the printed image of the calibration array; extracts the pixel coordinates of the calibration array in the image coordinate system in the printed image and obtains the physical coordinates of the calibration array; determines the calibration result of the camera in the selective laser melting device based on the pixel coordinates and physical coordinates, thus solving the calibration problem of the camera in the selective laser melting device. By printing the calibration array in situ on the printing layer plane, the positional error between the external calibration plate and the printing layer plane can be eliminated, improving the calibration accuracy. By generating the calibration array according to the installation orientation and field of view of the camera, it can be applied to the calibration of the camera at the off-axis preset angle, avoiding the influence of perspective trapezoidal distortion on the camera calibration.
[0011] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description
[0012] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0013] Figure 1 This is a schematic diagram of camera installation in a selective laser melting device. Figure 2 This is a flowchart of a camera calibration method in a selective laser melting device according to Embodiment 1 of the present invention; Figure 3 This is a schematic diagram of a calibration array under different camera orientations according to Embodiment 1 of the present invention; Figure 4 This is a schematic diagram of a printed body formed by an overall translation calibration array according to Embodiment 1 of the present invention; Figure 5 This is a schematic diagram of an overall translation calibration array provided according to Embodiment 1 of the present invention; Figure 6 This is a flowchart of a camera calibration method in a selective laser melting device according to Embodiment 2 of the present invention; Figure 7 This is a schematic diagram of a powder bed image and a printing image provided according to Embodiment 2 of the present invention; Figure 8This is a schematic diagram of a clean printed image provided according to Embodiment 2 of the present invention; Figure 9 This is a schematic diagram of the camera calibration device in a selective laser melting device according to Embodiment 3 of the present invention; Figure 10 This is a schematic diagram of the structure of an electronic device that implements the camera calibration method in the selective laser melting device of this invention. Detailed Implementation
[0014] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.
[0015] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.
[0016] Example 1 Figure 2 This is a flowchart illustrating a camera calibration method in a selective laser melting device according to Embodiment 1 of the present invention. This embodiment is applicable to camera calibration when the camera in a selective laser melting device is installed at a preset off-axis angle. The method can be executed by a camera calibration device in the selective laser melting device. This camera calibration device can be implemented in hardware and / or software, and can be configured in electronic equipment such as a computer or controller. Figure 2 As shown, the method includes: Step 210: Generate a calibration array corresponding to the current printing layer plane of the camera based on the installation orientation and field of view of the camera in the selected area laser melting equipment.
[0017] like Figure 1As shown, in selective laser melting equipment, the camera is installed with an off-axis preset angle greater than 15 degrees, resulting in perspective trapezoidal distortion in the acquired images. Specifically, perspective trapezoidal distortion exhibits significant anisotropy, such as "nearer pixels appear larger, farther pixels smaller, and closer pixels appear denser, farther pixels sparser." To address the inaccurate calibration caused by image distortion during camera calibration, the calibration array can be designed based on the camera's installation orientation and field of view. This reduces image distortion, ensures the reliability of pixel coordinate extraction from the acquired images, and ultimately improves camera calibration accuracy.
[0018] When generating the calibration array, it can be based on the current printing layer plane of the camera. In selective laser melting (SLM) printing, to ensure that the printing layer plane is at the same distance as the laser scanning of the SLM, the substrate can be moved downwards to overcome the problem of the printing layer plane shifting upwards due to powder spreading. If a calibration plate is placed on the substrate for camera calibration, as the substrate moves downwards, there is a positional deviation between the external calibration plate and the printing layer plane. The coordinate origin of the external calibration plate cannot establish a direct hardware association with the physical coordinate origin of the laser scanning system, resulting in inaccurate camera calibration. To solve this technical problem, this embodiment of the invention generates a calibration array corresponding to the current printing layer plane during camera calibration. The SLM performs laser scanning on the calibration array, that is, the calibration array is printed in situ within the SLM, so that the calibration array completely overlaps with the acquired image, eliminating the positional error between the external calibration plate and the printing layer plane, and improving calibration accuracy. Furthermore, in the selective laser melting equipment printing, there is interference between the powder bed and the powder spreading blade. By adopting the method of printing the calibration plate in situ, the risk of collision between the calibration plate and the blade is eliminated, ensuring that the image acquisition will not be deviated due to damage to the calibration plate during camera calibration, and thus the camera calibration will not be deviated.
[0019] Optionally, based on the installation orientation and field of view of the camera in the selective laser melting device, a calibration array corresponding to the current printing layer plane of the camera is generated, including: increasing the size of the feature units in the calibration array relative to the camera when the distance between the feature units in the calibration array and the camera increases based on the installation orientation and field of view of the camera in the selective laser melting device; and / or increasing the distribution density of the feature units in the field of view region when the distance between the field of view region in the calibration array and the camera increases based on the installation orientation and field of view of the camera in the selective laser melting device.
[0020] To improve camera calibration, multiple feature units can be set in the calibration array. To address image distortion, the feature unit size can be increased as the distance between the feature units and the camera increases. Dynamically adjusting the feature unit size can compensate for the perspective distortion (appearing larger than distant) caused by rangefinder imaging, making the pixel area occupied by all feature units on the imaging plane more consistent. For example, based on the camera's mounting orientation and field of view in a selective laser melting device, the feature unit size can be increased for every 3 to 6 millimeters of distance between the feature unit and the camera to counteract the perspective distortion effect.
[0021] To address image distortion, the distribution density of feature cells in the field of view region of the calibration array can be increased as the distance between the determined calibration array's field of view region and the camera increases. By dynamically adjusting the distribution density of feature cells in each field of view region of the calibration array, more control point constraints can be provided in areas of severe optical distortion and perspective distortion, compensating for the "near-sparse, far-dense" perspective effect produced by paraxial imaging. For example, high-density filling (such as double density) can be used in the far end and edge regions of the field of view to enhance constraints in distorted areas.
[0022] In an embodiment of the present invention, optionally, the calibration array includes at least one of the following characteristics: the calibration array is non-uniformly distributed, the feature unit in the calibration array is a solid ring, the inner ring and the ring body are different colors, the outer diameter of the solid ring is greater than a preset size value, the inner diameter of the solid ring is positively correlated with the outer diameter, and a preset buffer margin is reserved between the outline of the calibration array and the physical boundary of the forming chamber of the selective laser melting device.
[0023] By setting the calibration array to a non-uniform distribution, image distortion caused by the camera's off-axis preset angle installation can be compensated. For example, the distortion of paraxial imaging can be compensated by dynamically adjusting the size and distribution density of the feature units in the calibration array. Feature units can be of various shapes, such as checkerboard or circular grids. In practical research, considering that solid-filled feature units are prone to generating central hot spots under continuous laser scanning, leading to molten pool flow or surface bulging, causing the geometric center of feature points to shift and affecting camera calibration accuracy, the feature units can be set as solid rings. To improve recognition stability against powder backgrounds, the outer diameter of the solid ring can be set to a value larger than a preset size, improving camera calibration accuracy through a wide-walled solid ring. For example, the preset size can be between 1.5mm and 2.0mm. Optionally, the inner ring and the ring body can be different colors, for example, white inside and black outside. The obvious color difference between the inner and outer rings facilitates pixel coordinate extraction of the solid ring, ensuring the accuracy of grayscale centroid extraction. The embodiments of the present invention, by setting the feature units in the calibration array as wide-walled solid rings, not only ensure the grayscale weighted recognition area in a low-contrast powder bed environment, but also eliminate the thermal accumulation effect of the feature center.
[0024] Optionally, the inner diameter of the solid ring is positively correlated with its outer diameter. For example, the outer diameter is Dout, and the inner diameter is Din = 0.5 × Dout. Furthermore, to protect the edge of the forming chamber of the selective laser melting equipment, a preset buffer margin is reserved between the contour of the calibration array and the physical boundary of the forming chamber of the selective laser melting equipment.
[0025] For example, Figure 3 This is a schematic diagram of a calibration array under different camera orientations according to Embodiment 1 of the present invention. Figure 3 As shown, under each camera orientation, the physical size and distribution density of the feature units can be increased from the near end to the far end of the field of view according to the camera installation position and field of view angle, in order to compensate for the camera's off-axis imaging distortion. At the same time, a preset safety buffer distance is maintained between the overall outline of the calibration array and the physical boundary of the forming chamber. The feature units uniformly adopt a wide-walled solid ring structure with "black on the outside and white on the inside" to facilitate the camera's accurate identification of image pixels for reliable calibration.
[0026] Optionally, the selective laser melting device includes multiple printing layer planes distributed longitudinally; based on the installation orientation and field of view of the camera in the selective laser melting device, a calibration array corresponding to the current printing layer plane of the camera is generated, including: the calibration arrays corresponding to each printing layer plane are translated as a whole so that the calibration arrays corresponding to all printing layer planes do not overlap.
[0027] By translating the calibration arrays corresponding to each printed layer plane as a whole, so that the calibration arrays corresponding to all printed layer planes do not overlap, more effective feature units can be added in camera calibration, improving camera calibration accuracy and reducing the impact of image distortion.
[0028] For example, Figure 4 This is a schematic diagram of a printed body formed by an overall translation calibration array according to Embodiment 1 of the present invention. Figure 5 This is a schematic diagram of an overall translation calibration array provided according to Embodiment 1 of the present invention. Figure 5 As shown, when the feature cells in the calibration array are a checkerboard pattern, the entire calibration array can be translated to make... Figure 5 The nine calibration arrays do not overlap. Figure 5 The nine calibration arrays in the middle are also Figure 4 The calibration plate corresponds to the nine cross-sections of the printed object. In other words, when printing with a selective laser melting device, a calibration plate can be used... Figure 5 The nine non-overlapping calibration arrays shown are sequentially used as the printed volume data corresponding to the nine vertically distributed printed layer planes, ultimately forming the following... Figure 4 The printed body shown increases the number of effective feature units in camera calibration, improving camera calibration accuracy; at the same time, printing the calibration array in situ on each printed layer plane can achieve overlap between the calibration board and the printed body layer, eliminating positional errors.
[0029] Step 220: Control the selected area laser melting equipment to perform laser scanning on the current printing layer plane according to the calibration array, and acquire the printing image of the calibration array.
[0030] Step 230: Extract the pixel coordinates of the calibration array in the image coordinate system from the printed image, and obtain the physical coordinates of the calibration array.
[0031] In selective laser melting (SLM) equipment, the calibration array serves as the basis for laser scanning and printing, providing accurate and reliable physical coordinates. By printing the calibration array corresponding to the printing layer plane using the SLM equipment and acquiring images to obtain pixel coordinates, the positional deviation between the calibration plate and the printing layer plane can be eliminated, ensuring that the calibration plate plane is absolutely parallel to the actual printing layer plane. By generating a calibration array corresponding to the current printing layer plane of the camera based on the camera's installation orientation and field of view angle in the SLM equipment, image distortion can be compensated for to improve the reliability of pixel coordinate acquisition while ensuring accurate physical coordinates, thereby enhancing the reliability of camera calibration.
[0032] Step 240: Determine the calibration results of the camera in the selected area laser melting device based on the pixel coordinates and physical coordinates.
[0033] There are several ways to calibrate a camera based on pixel coordinates and physical coordinates. For example, it can be done using existing camera calibration algorithm models, iterative solutions using nonlinear least squares methods, and solutions using linear least squares methods.
[0034] The technical solution of this embodiment generates a calibration array corresponding to the current printing layer plane of the camera based on the installation orientation and field of view of the camera in the selective laser melting device; controls the selective laser melting device to perform laser scanning on the current printing layer plane according to the calibration array and acquires the printed image of the calibration array; extracts the pixel coordinates of the calibration array in the image coordinate system in the printed image and obtains the physical coordinates of the calibration array; determines the calibration result of the camera in the selective laser melting device based on the pixel coordinates and physical coordinates, thus solving the calibration problem of the camera in the selective laser melting device. By printing the calibration array in situ on the printing layer plane, the positional error between the external calibration plate and the printing layer plane can be eliminated, improving the calibration accuracy. By generating the calibration array according to the installation orientation and field of view of the camera, it can be applied to the calibration of the camera at the off-axis preset angle, avoiding the influence of perspective trapezoidal distortion on the camera calibration.
[0035] Example 2 Figure 6 This is a flowchart of a camera calibration method in a selective laser melting device according to Embodiment 2 of the present invention. This embodiment is a further refinement of the above technical solution, and the technical solution in this embodiment can be combined with various optional solutions in one or more of the above embodiments. Figure 6 As shown, the method includes: Step 610: Based on the installation orientation and field of view of the camera in the selected area laser melting equipment, determine that when the distance between the feature unit in the calibration array and the camera increases, increase the size of the feature unit.
[0036] Step 620: Based on the installation orientation and field of view angle of the camera in the selected area laser melting equipment, when the distance between the field of view area in the calibration array and the camera increases, increase the distribution density of feature units in the field of view area.
[0037] Optionally, the calibration array includes at least one of the following characteristics: the calibration array is non-uniformly distributed; the feature units in the calibration array are solid rings; the inner ring and the ring body are different colors; the outer diameter of the solid ring is greater than a preset size value; the inner diameter of the solid ring is positively correlated with the outer diameter; and a preset buffer margin is reserved between the outline of the calibration array and the physical boundary of the forming chamber of the selective laser melting equipment.
[0038] Optionally, the selective laser melting device includes multiple longitudinally distributed printing layer planes; the calibration arrays corresponding to each printing layer plane are translated as a whole, so that the calibration arrays corresponding to all printing layer planes do not overlap.
[0039] Step 630: Control the selected area laser melting equipment to spread powder on the current printing layer plane and acquire powder bed image.
[0040] Step 640: Control the selected area laser melting equipment to perform laser scanning on the current printing layer plane according to the calibration array, and acquire the printing image of the calibration array.
[0041] Step 650: Perform image difference processing on the printed image and the toner bed image to obtain a clean printed image.
[0042] For example, Figure 7 This is a schematic diagram of a powder bed image and a printed image provided according to Embodiment 2 of the present invention. Figure 8 This is a schematic diagram of a clean printed image provided according to Embodiment 2 of the present invention. Figure 7 As shown, taking additive printing as an example, the toner bed can affect the sharpness of the printed image, leading to unreliable camera calibration. To improve the sharpness of the printed image, image difference processing can be performed between the printed image and the toner bed image to obtain the result shown below. Figure 8 The clean printed image shown. For example, a clean printed image is represented as... .in, Represents a powder bed image. Indicates a printed image. These are the pixel coordinates of the image. For clean printed images, preprocessing such as binarization and morphological repair can be performed to improve the accuracy of pixel coordinate extraction. For example, if a pixel value in a clean printed image exceeds a certain threshold, the pixel value can be updated to 1; otherwise, the pixel value can be updated to 0.
[0043] Step 660: Extract the pixel coordinates of the calibration array in the image coordinate system from the clean printed image.
[0044] For example, the pixel coordinates of the calibration array in the image coordinate system can be extracted from a clean printed image using methods such as the centroid method.
[0045] Step 670: Obtain the physical coordinates of the calibration array.
[0046] Step 680: Determine the calibration results of the camera in the selected area laser melting device based on the pixel coordinates and physical coordinates.
[0047] Optionally, the calibration result of the camera in the selected area laser melting device is determined based on the pixel coordinates and physical coordinates, including: constructing multiple sets of one-to-one corresponding coordinate mapping data pairs based on the pixel coordinates and physical coordinates; constructing a high-order polynomial regression model containing cross-coupling terms based on the coordinate mapping data pairs, and solving the high-order polynomial regression model to obtain the mapping relationship from the image coordinate system to the physical coordinate system of the current printing layer plane; and using the mapping relationship as the calibration result of the camera in the selected area laser melting device for the current printing layer plane.
[0048] Coordinate mapping data pairs can be represented as Cross-coupling terms can refer to pixel coordinates. and The cross-coupling. A higher-order polynomial regression model can refer to a polynomial regression model of order two or higher. Optionally, constructing a higher-order polynomial regression model containing cross-coupling terms based on coordinate mapping data includes: constructing a higher-order polynomial regression model containing cross-coupling terms based on coordinate mapping data as follows: ;in, For pixel coordinates in coordinate mapping data pairs, For the physical coordinates in the coordinate mapping data pair; to ,as well as to The coefficients to be solved; constant term Used to characterize the translational deviation between the origin of the image coordinate system and the origin of the physical coordinate system of the current printed layer plane; first-order term Used to characterize the linear scaling and fundamental rotation relationship between the image and the physical plane; quadratic cross-coupling term. Used to characterize and correct affine shearing distortion, since the optical axis of a rangefinder camera is usually rotated and the imaging plane is rarely perfectly parallel to the printed layer plane, rectangular features are distorted into parallelograms in the image. This cross-coupling term is key to decoupling this type of distortion; the quadratic term Used to characterize and correct perspective trapezoidal distortion caused by shooting at a preset angle by the camera in a selective laser melting device, i.e., the phenomenon of "near objects appearing larger and farther objects smaller, near objects appearing sparser and farther objects denser, and the top narrower and the bottom wider" in the image; cubic term It is used to characterize and correct the inherent nonlinear optical distortion of wide-angle lenses and the high-order composite errors at the edge of the field of view.
[0049] This high-order polynomial regression model, which includes cross-coupling terms, involves 20 coefficients to be solved. By collecting at least 10 sets of coordinate mapping data pairs, pixel coordinates and physical coordinates can be substituted, and a unique optimal solution can be obtained using the linear least squares method. Solving the model coefficients using the linear least squares method establishes a direct nonlinear mapping relationship from the image pixel coordinate system to the printing layer physical coordinate system, enabling full-field-of-view geometric correction.
[0050] The core requirement for SLM process monitoring is "planar mapping from pixel coordinates to physical coordinates," rather than 3D spatial reconstruction. Using the existing linear least squares method to solve for the parameters in the calibration results avoids the increased computational complexity and unnecessary parameter coupling errors introduced by using existing calibration algorithms to solve for redundant camera intrinsic and extrinsic parameters. Furthermore, iteratively solving for camera parameters using nonlinear least squares methods is sensitive to initial values; in SLM images with large distortions, the distribution of feature points exhibits significant anisotropy (larger near points, smaller far points, sparser near points, denser far points), easily causing the iterative algorithm to get trapped in local optima, resulting in unstable calibration results. The linear least squares method avoids this problem, as the calculation process requires no iteration and is free from local optimum traps, greatly improving the speed and robustness of industrial field calibration.
[0051] Solving the model coefficients using the linear least squares method to ,as well as to This allows us to obtain the mapping relationship from the image coordinate system to the physical coordinate system of the current printing layer plane, which is the calibration result of the camera in the selected area laser melting device for the current printing layer plane.
[0052] The technical solution of this invention solves the camera calibration problem in selective laser melting equipment by increasing the size of the feature units relative to the camera when the distance between the feature units in the calibration array and the camera increases, based on the installation orientation and field of view angle of the camera in the selective laser melting equipment; increasing the distribution density of feature units in the field of view region when the distance between the field of view region and the camera increases, based on the installation orientation and field of view angle of the camera in the selective laser melting equipment; controlling the selective laser melting equipment to spread powder on the current printing layer plane and acquiring powder bed images; controlling the selective laser melting equipment to perform laser scanning on the current printing layer plane according to the calibration array and acquiring the printed image of the calibration array; performing image difference processing based on the printed image and the powder bed image to obtain a clean printed image; extracting the pixel coordinates of the calibration array in the image coordinate system in the clean printed image; obtaining the physical coordinates of the calibration array; and determining the calibration result of the camera in the selective laser melting equipment based on the pixel coordinates and physical coordinates. This solves the camera calibration problem in selective laser melting equipment by using the high-precision laser galvanometer system of the SLM equipment itself to print a calibration plate, directly calibrating the visual coordinate system to the laser processing. The coordinate system (i.e., the "true value") eliminates placement errors and mechanical coordinate transformation errors introduced by external calibration plates, achieving "what you see is what you get" closed-loop control; a wide-walled solid ring, similar to a "donut," provides high-contrast visual features compared to a single thin line, exhibiting strong noise resistance; compared to a solid dot, its central hollow design avoids overheating collapse, ensuring centroid geometric accuracy while reducing laser heat input; variable density and / or variable size of feature units in hardware compensate for trapezoidal perspective and barrel distortion caused by a camera mounted at a preset angle on the rangefinder; and by constructing a package... The high-order polynomial model with cross terms, solved using the linear least squares method, can compensate for shear deformation, maintain extremely high geometric correction accuracy, and eliminate the complex iterative solution process of camera intrinsic parameters. It transforms the calibration problem into a linear least squares plane regression problem, eliminating the need for iteration and local optima traps in the calculation process, which greatly improves the speed and robustness of industrial field calibration. In addition, the fully automated in-situ printing and acquisition eliminates the need for manual opening of the chamber to place the calibration plate, thus eliminating the risk of collision between the calibration plate and the scraper. It is particularly suitable for automated calibration in inert gas protection environments.
[0053] Example 3 Figure 9 This is a schematic diagram of the camera calibration device in a selective laser melting apparatus according to Embodiment 3 of the present invention. Figure 9 As shown, the device includes: a calibration array generation module 910, a print image acquisition module 920, a coordinate acquisition module 930, and a calibration result determination module 940. Wherein: The calibration array generation module 910 is used to generate a calibration array corresponding to the current printing layer plane of the camera based on the installation orientation and field of view of the camera in the selected area laser melting equipment. The print image acquisition module 920 is used to control the selected area laser melting equipment to perform laser scanning on the current print layer plane according to the calibration array and acquire the print image of the calibration array; The coordinate acquisition module 930 is used to extract the pixel coordinates of the calibration array in the image coordinate system in the printed image and obtain the physical coordinates of the calibration array; The calibration result determination module 940 is used to determine the calibration result of the camera in the selected area laser melting device based on the pixel coordinates and physical coordinates.
[0054] Optionally, the calibration array generation module 910 includes: A size adjustment unit is used to increase the size of the feature elements in the calibration array relative to the camera when the distance between the feature elements and the camera increases, based on the camera's mounting orientation and field of view in the selective laser melting equipment; and / or, The density adjustment unit is used to increase the distribution density of feature units in the field of view region when the distance between the field of view region and the camera in the calibration array increases, based on the installation orientation and field of view angle of the camera in the selective laser melting equipment.
[0055] Optionally, the calibration array includes at least one of the following characteristics: The calibration array is non-uniformly distributed, the feature units in the calibration array are solid rings, the inner ring and the ring body are different colors, the outer diameter of the solid ring is larger than the preset size value, the inner diameter of the solid ring is positively correlated with the outer diameter, and a preset buffer margin is reserved between the outline of the calibration array and the physical boundary of the forming chamber of the selective laser melting equipment.
[0056] Optionally, the device may also include: The powder bed image acquisition module is used to control the selective laser melting device to spread powder on the current printing layer plane and acquire powder bed images before the selected laser melting device performs laser scanning on the current printing layer plane according to the calibration array and acquires the printing image of the calibration array. Optional, the coordinate acquisition module 930 includes: A clean print image determination unit is used to perform image difference processing based on the print image and the powder bed image to obtain a clean print image; The pixel coordinate extraction unit is used to extract the pixel coordinates of the calibration array in the image coordinate system in the clean printed image.
[0057] Optionally, the calibration result determination module 940 includes: The coordinate mapping data pair building unit is used to construct multiple sets of one-to-one coordinate mapping data pairs based on pixel coordinates and physical coordinates; The mapping relationship determination unit is used to construct a high-order polynomial regression model containing cross-coupling terms based on coordinate mapping data, and to solve the high-order polynomial regression model to obtain the mapping relationship from the image coordinate system to the physical coordinate system of the current printing layer plane. The calibration result determination unit is used to use the mapping relationship as the calibration result of the camera in the selected area laser melting device for the current printing layer plane.
[0058] Optionally, the mapping relationship determination unit includes: The regression model determines the sub-units used to construct a high-order polynomial regression model containing cross-coupling terms based on coordinate mapping data: ; in, For pixel coordinates in coordinate mapping data pairs, For the physical coordinates in the coordinate mapping data pair; to ,as well as to The coefficients to be solved; constant term Used to characterize the translational deviation between the origin of the image coordinate system and the origin of the physical coordinate system of the current printed layer plane; first-order term Used to characterize the linear scaling and fundamental rotation relationship between an image and a physical plane; Secondary cross-coupling term Used to characterize and correct affine shear deformation; quadratic term Used to characterize and correct perspective trapezoidal distortion caused by shooting at a preset angle by the camera in a selective laser melting device; cubic term It is used to characterize and correct the inherent nonlinear optical distortion of wide-angle lenses and the high-order composite errors at the edge of the field of view.
[0059] Optionally, the selective laser melting device includes multiple longitudinally distributed printing layer planes; The calibration array generation module 910 includes: The translation adjustment unit is used to perform an overall translation of the calibration arrays corresponding to each printing layer plane, so that the calibration arrays corresponding to all printing layer planes do not overlap.
[0060] The camera calibration device in the selective laser melting equipment provided in this embodiment of the invention can execute the camera calibration method in the selective laser melting equipment provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the execution method.
[0061] Example 4 Figure 10A schematic diagram of an electronic device 10, which can be used to implement embodiments of the present invention, is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.
[0062] like Figure 10 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) or random access memory (RAM), communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded into the RAM 13 from the storage unit 18. The RAM 13 can also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. Input / output (I / O) interfaces are also connected to the bus 14.
[0063] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.
[0064] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as the camera calibration method in a selective laser melting device.
[0065] In some embodiments, the camera calibration method in a selective laser melting apparatus can be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the camera calibration method in a selective laser melting apparatus described above can be performed. Alternatively, in other embodiments, processor 11 can be configured to perform the camera calibration method in a selective laser melting apparatus by any other suitable means (e.g., by means of firmware).
[0066] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.
[0067] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.
[0068] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, RAM, ROM, erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.
[0069] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).
[0070] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.
[0071] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.
[0072] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.
[0073] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.
Claims
1. A calibration method for a camera in a selective laser melting device, characterized in that, include: Based on the installation orientation and field of view of the camera in the selective laser melting equipment, a calibration array corresponding to the current printing layer plane of the camera is generated; The selected area laser melting device is controlled to perform laser scanning on the current printing layer plane according to the calibration array, and to acquire the printing image of the calibration array; Extract the pixel coordinates of the calibration array in the image coordinate system from the printed image, and obtain the physical coordinates of the calibration array; The calibration result of the camera in the selected area laser melting device is determined based on the pixel coordinates and the physical coordinates.
2. The method according to claim 1, characterized in that, Based on the camera's installation orientation and field of view in the selective laser melting equipment, a calibration array corresponding to the camera's current printing layer plane is generated, including: When the distance between the feature element in the calibration array and the camera increases, based on the camera's installation orientation and field of view in the selective laser melting equipment, the size of the feature element is increased; and / or, Based on the installation orientation and field of view angle of the camera in the selective laser melting device, when the distance between the field of view area in the calibration array and the camera increases, the distribution density of feature units in the field of view area is increased.
3. The method according to claim 1, characterized in that, The calibration array includes at least one of the following characteristics: The calibration array is non-uniformly distributed, the feature unit in the calibration array is a solid ring, the inner part of the solid ring is a different color from the ring body, the outer diameter of the solid ring is greater than a preset size value, the inner diameter of the solid ring is positively correlated with the outer diameter, and a preset buffer margin is reserved between the outline of the calibration array and the physical boundary of the forming chamber of the selective laser melting equipment.
4. The method according to claim 1, characterized in that, Before controlling the selected area laser melting device to perform laser scanning on the current printing layer plane according to the calibration array and acquire the printing image of the calibration array, the method further includes: The selective laser melting device is controlled to spread powder on the current printing layer plane and to acquire powder bed images; Extracting the pixel coordinates of the calibration array in the image coordinate system from the printed image includes: A clean printed image is obtained by performing image difference processing between the printed image and the powder bed image; Extract the pixel coordinates of the calibration array in the image coordinate system from the clean printed image.
5. The method according to claim 1, characterized in that, Based on the pixel coordinates and the physical coordinates, the calibration results of the camera in the selected area laser melting device are determined, including: Based on the pixel coordinates and the physical coordinates, construct multiple sets of one-to-one corresponding coordinate mapping data pairs; Based on the coordinate mapping data, a high-order polynomial regression model containing cross-coupling terms is constructed, and the high-order polynomial regression model is solved to obtain the mapping relationship from the image coordinate system to the physical coordinate system of the current printing layer plane. The mapping relationship is used as the calibration result of the camera in the selected area laser melting device for the current printing layer plane.
6. The method according to claim 5, characterized in that, Based on the coordinate mapping data, a high-order polynomial regression model containing cross-coupling terms is constructed, including: Based on the coordinate mapping data, a higher-order polynomial regression model containing cross-coupling terms is constructed as follows: ; in, For the pixel coordinates in the coordinate mapping data pair, The physical coordinates in the coordinate mapping data pair; to ,as well as to The coefficients to be solved; constant term Used to characterize the translational deviation between the origin of the image coordinate system and the origin of the physical coordinate system of the current printed layer plane; first-order term Used to characterize the linear scaling and fundamental rotation relationship between an image and a physical plane; Secondary cross-coupling term Used to characterize and correct affine shear deformation; quadratic term Used to characterize and correct perspective trapezoidal distortion caused by shooting at a preset angle by the camera in the selective laser melting device; cubic term It is used to characterize and correct the inherent nonlinear optical distortion of wide-angle lenses and the high-order composite errors at the edge of the field of view.
7. The method according to claim 1, characterized in that, The selective laser melting device includes multiple longitudinally distributed printing layer planes; Based on the camera's installation orientation and field of view in the selective laser melting equipment, a calibration array corresponding to the camera's current printing layer plane is generated, including: The calibration arrays corresponding to each printing layer plane are translated as a whole, so that the calibration arrays corresponding to all printing layer planes do not overlap.
8. An electronic device, characterized in that, The electronic device includes: At least one processor; and a memory communicatively connected to said at least one processor; wherein, The memory stores a computer program executable by the at least one processor, which enables the at least one processor to perform the camera calibration method in the selective laser melting apparatus according to any one of claims 1-7.
9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that, when executed by a processor, implement the camera calibration method in the selective laser melting apparatus according to any one of claims 1-7.
10. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the camera calibration method in the selective laser melting apparatus according to any one of claims 1-7.