System, method, controller and storage medium for pose calibration of image acquisition device

Abstract

The application discloses a system and method for image acquisition device pose calibration, a controller and a storage medium. The system comprises a double-layer calibration board, which is in the imaging field of view of a to-be-calibrated image acquisition device. The double-layer calibration board comprises a transparent plate, an upper surface pattern on the upper surface of the transparent plate, and a lower surface pattern on the lower surface of the transparent plate. The upper surface pattern and the lower surface pattern jointly form a pair of calibration patterns. The pair of calibration patterns comprises at least one group of geometric pattern pairs and at least one group of measurement line pairs. The geometric pattern pair is composed of a pair of preset geometric patterns. The preset geometric pattern comprises at least two edges, and the two edges share a vertex. The pair of calibration patterns are arranged on the upper and lower surfaces of the double-layer calibration board, the six-degree-of-freedom pose deviation of the image acquisition device can be synchronously detected, the calibration efficiency is improved, the anti-interference capability is enhanced in combination with the double-layer structure, the dependence on the device precision and manual experience is reduced, and the calibration accuracy is greatly improved.

Description

Technical Field

[0001] This application relates to the field of image acquisition device calibration technology, and specifically to a system, method, controller, and storage medium for image acquisition device pose calibration. Background Technology

[0002] In fields such as machine vision measurement and precision inspection, the accurate calibration of the pose of image acquisition equipment directly affects image quality and measurement accuracy. Traditional vision calibration systems often rely on high-precision mechanical positioning equipment or the experience-based judgment of operators, which has significant limitations: mechanical positioning equipment is expensive and susceptible to environmental vibrations and component wear, resulting in insufficient long-term stability; human experience relies on subjective judgment, leading to low calibration efficiency and poor consistency, especially in complex scenarios where it is difficult to guarantee millimeter-level or even sub-millimeter-level accuracy requirements. Therefore, existing image acquisition equipment pose calibration systems suffer from low accuracy. Summary of the Invention

[0003] The purpose of this application is to provide a system, method, controller, and storage medium for image acquisition device pose calibration, in order to solve the problem of low accuracy in existing image acquisition device pose calibration systems.

[0004] To achieve the above objectives, the first aspect of this application provides a system for pose calibration of an image acquisition device, the system comprising: A double-layer calibration plate is located within the imaging field of view of the image acquisition device to be calibrated. The double-layer calibration plate includes a transparent plate, an upper surface pattern on the upper surface of the transparent plate, and a lower surface pattern on the lower surface of the transparent plate. The upper surface pattern and the lower surface pattern together form a pair of calibration patterns. The pair of calibration patterns includes at least one set of geometric shape pairs and at least one set of measurement line pairs. The geometric shape pairs are composed of a pair of preset geometric shapes. The preset geometric shapes include at least two sides, and the two sides share a vertex.

[0005] In this embodiment, when the image acquisition device to be calibrated is in the target pose, the two vertices of the geometric pair and the optical center of the lens of the image acquisition device to be calibrated are on the same light propagation trajectory.

[0006] In this embodiment of the application, the system further includes: a lighting device disposed above and / or below the double-layer calibration plate, for providing illumination to the double-layer calibration plate so that the image acquisition device to be calibrated can capture the paired calibration patterns on the double-layer calibration plate.

[0007] In this embodiment of the application, when the lighting device is disposed above the double-layer calibration plate, the double-layer calibration plate further includes a diffuse reflection film layer that covers the pattern on the lower surface.

[0008] In this embodiment, the measurement line pair is a transfer function measurement line pair, which consists of paired lines with a set length and a set width; the paired calibration pattern includes multiple sets of transfer function measurement line pairs, and each set of transfer function measurement line pairs is arranged in parallel according to a preset interval.

[0009] A second aspect of this application provides a method for pose calibration of an image acquisition device, applied to the aforementioned image acquisition device pose calibration system, the method comprising: Acquire sample images acquired by the image acquisition device to be calibrated, the sample images including paired calibration patterns; Geometric pairs in sample images are identified using target recognition technology, and the actual vertex coordinates of paired vertices in the image pixel coordinate system are determined. Based on the actual vertex coordinates and target vertex coordinates of the paired vertices, determine the offset parameters of the image acquisition device to be calibrated in the X-axis and Y-axis directions in the preset three-dimensional coordinate system, wherein the X-axis and Y-axis directions correspond to the directions of the two coordinate axes of the image pixel coordinate system; Identify measurement line pairs in the sample image and calculate the actual transfer function value and the actual angle of the measurement line pairs in the sample image; Based on the actual transfer function value, actual angle, target transfer function value, and target angle, determine the offset parameter of the image acquisition device to be calibrated in the Z-axis direction in the preset three-dimensional coordinate system, wherein the Z-axis direction is perpendicular to the X-axis direction and the Y-axis direction; The image acquisition device to be calibrated is calibrated based on the offset parameters of the X-axis, Y-axis and Z-axis directions in the preset three-dimensional coordinate system.

[0010] In this embodiment, the offset parameters include positional offset and rotational offset. Based on the actual vertex coordinates and target vertex coordinates of the paired vertices, the offset parameters of the image acquisition device to be calibrated in the X-axis and Y-axis directions of the preset three-dimensional coordinate system are determined. This includes: determining the positional offset and rotational offset of the image acquisition device to be calibrated in the X-axis direction of the preset three-dimensional coordinate system based on the abscissa of the actual vertex coordinates and the abscissa of the target vertex coordinates; and determining the positional offset and rotational offset of the image acquisition device to be calibrated in the Y-axis direction of the preset three-dimensional coordinate system based on the ordinate of the actual vertex coordinates and the ordinate of the target vertex coordinates.

[0011] In this embodiment, the offset parameters include positional deviation and rotational deviation. The offset parameters of the image acquisition device to be calibrated in the Z-axis direction of the preset three-dimensional coordinate system are determined based on the actual transfer function value, the actual angle, the target transfer function value, and the target angle. This includes: determining the positional deviation of the image acquisition device to be calibrated in the Z-axis direction of the preset three-dimensional coordinate system based on the actual transfer function value and the target transfer function value; and determining the rotational deviation of the image acquisition device to be calibrated in the Z-axis direction of the preset three-dimensional coordinate system based on the actual angle and the target angle.

[0012] A third aspect of this application provides a controller, comprising: a memory configured to store instructions; and a processor configured to retrieve instructions from the memory and, when executing the instructions, to implement the above-described method for image acquisition device pose calibration.

[0013] The fourth aspect of this application provides a machine-readable storage medium on which a program or instruction is stored, and when the program or instruction is executed by a processor, it implements the above-described method for pose calibration of an image acquisition device.

[0014] The above technical solution provides a system for calibrating the pose of an image acquisition device. This system includes a double-layer calibration plate, positioned within the imaging field of view of the image acquisition device to be calibrated. The double-layer calibration plate includes a transparent plate, an upper surface pattern on the upper surface of the transparent plate, and a lower surface pattern on the lower surface of the transparent plate. The upper and lower surface patterns together form a pair of calibration patterns. Each pair of calibration patterns includes at least one set of geometric shape pairs and at least one set of measurement line pairs. Each geometric shape pair consists of a pair of preset geometric shapes, each preset geometric shape including at least two edges sharing a vertex. This application sets paired calibration patterns on the upper and lower surfaces of the double-layer calibration plate, enabling simultaneous detection of the six-degree-of-freedom pose deviation of the image acquisition device. Comprehensive information is obtained in a single imaging operation, improving calibration efficiency. Furthermore, the geometric shape pairs with shared vertices provide precise geometric constraints, enhancing positioning accuracy. The use of measurement line pairs for auxiliary verification, combined with the double-layer structure, enhances anti-interference capabilities, reduces reliance on equipment accuracy and human experience, and significantly improves calibration accuracy and stability.

[0015] Other features and advantages of the embodiments of this application will be described in detail in the following detailed description section. Attached Figure Description

[0016] The accompanying drawings are provided to further illustrate the embodiments of this application and form part of the specification. They are used together with the following detailed description to explain the embodiments of this application, but do not constitute a limitation on the embodiments of this application. In the drawings: Figure 1 This application provides a schematic diagram of the structure of an image acquisition device pose calibration system. Figure 2 This is a schematic diagram of the structure of a double-layer calibration plate provided in an embodiment of this application; Figure 3 A schematic diagram of a geometric pair provided in a specific embodiment of this application; Figure 4 A schematic diagram illustrating the positional relationship of geometric pairs in the field of view of an image acquisition device in a target pose, provided as a specific embodiment of this application; Figure 5 A schematic diagram showing the relationship between an image acquisition device in a target pose and a pair of geometric shapes on a double-layer calibration plate, provided in a specific embodiment of this application; Figure 6 A schematic diagram of a measurement line pair provided in a specific embodiment of this application; Figure 7 A schematic diagram illustrating the positional relationship of measurement line pairs in the field of view of an image acquisition device in a target pose, provided as a specific embodiment of this application; Figure 8 This application provides a flowchart illustrating a method for calibrating the pose of an image acquisition device. Figure 9 A schematic diagram of paired calibration patterns on a double-layer calibration plate provided in a specific embodiment of this application; Figure 10 A schematic diagram of paired calibration patterns on a double-layer calibration plate, provided for another specific embodiment of this application; Figure 11 This is a structural block diagram of a controller provided in an embodiment of this application.

[0017] Explanation of reference numerals in the attached figures Detailed Implementation

[0018] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are only for illustration and explanation of the embodiments of this application and are not intended to limit the embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application.

[0019] It should be noted that if the embodiments of this application involve directional indicators (such as up, down, left, right, front, back, etc.), the directional indicators are only used to explain the relative positional relationship and movement of each component in a certain specific posture (as shown in the figure). If the specific posture changes, the directional indicators will also change accordingly.

[0020] Furthermore, if the embodiments of this application involve descriptions such as "first" or "second," these descriptions are for descriptive purposes only and should not be construed as indicating or implying their relative importance or implicitly specifying the number of technical features indicated. Therefore, features defined with "first" or "second" may explicitly or implicitly include at least one of those features. Additionally, the technical solutions of various embodiments can be combined with each other, but this must be based on the ability of those skilled in the art to implement them. If the combination of technical solutions is contradictory or impossible to implement, it should be considered that such a combination of technical solutions does not exist and is not within the scope of protection claimed in this application.

[0021] It is understandable that during the setup and commissioning phase of a vision measurement and inspection system, the position and orientation of the image acquisition device need to be adjusted to ensure consistency of products of the same model inspected by the system. Existing technologies often use conventional targets to calibrate the image acquisition device, determining some of its position and orientation degrees of freedom parameters based on real-time images acquired. However, for parameters such as the camera optical axis angle, existing technologies can only rely on the precision of the mechanical structure or the experience of the assembly personnel for adjustment, and cannot be calibrated using conventional targets. This results in low accuracy of system debugging results, long debugging cycles, and an inability to guarantee consistency for subsequent products of the same model. To address this, this application provides a system for calibrating the pose of an image acquisition device, employing a double-layer calibration plate to calibrate the pose of the image acquisition device, thereby improving the accuracy of the calibration results.

[0022] Figure 1 This is a schematic diagram of the structure of an image acquisition device pose calibration system provided in an embodiment of this application. Figure 1 As shown in the figure, this application provides a system for calibrating the pose of an image acquisition device, the system comprising: The double-layer calibration plate 2 is located within the imaging field of view of the image acquisition device 1 to be calibrated. The double-layer calibration plate 2 includes a transparent plate 21, an upper surface pattern 22 located on the upper surface of the transparent plate, and a lower surface pattern 23 located on the lower surface of the transparent plate. The upper surface pattern 22 and the lower surface pattern 23 together form a pair of calibration patterns. The pair of calibration patterns includes at least one set of geometric shape pairs and at least one set of measurement line pairs. The geometric shape pairs are composed of a pair of preset geometric shapes. The preset geometric shapes include at least two sides, and the two sides share a vertex.

[0023] Specifically, the image acquisition device pose calibration system in this embodiment includes an image acquisition device 1 to be calibrated and a double-layer calibration plate 2. The double-layer calibration plate 2 is disposed below the image acquisition device and is located within the imaging field of view of the image acquisition device.

[0024] Figure 2This is a schematic diagram of a double-layer calibration plate provided in an embodiment of this application. Figure 2 As shown, the double-layer calibration plate 2 includes a transparent plate 21, an upper surface pattern 22, and a lower surface pattern 23. The transparent plate 21 is a transparent material with a certain thickness, such as a glass plate of a certain thickness. The upper surface pattern 22 and the lower surface pattern 23 are formed on the upper and lower surfaces of the transparent plate 21 respectively through a specific processing technology (such as electroplating). The patterns on the double-layer calibration plate 2 can be observed within the imaging field of view of the image acquisition device. Thus, since the transparent plate 21 has a certain thickness, and the upper surface pattern 22 and the lower surface pattern 23 have a height difference in the vertical direction, a graphic design for measuring all six degrees of freedom position and attitude parameters of the image acquisition device can be constructed.

[0025] In this embodiment of the application, the upper surface pattern 22 and the lower surface pattern 23 in the double-layer calibration plate together form a pair of calibration patterns. The specific content of the pair of calibration patterns can be designed according to the actual situation, but the pair of calibration patterns includes at least one set of geometric pattern pairs and at least one set of measurement line pairs.

[0026] The geometric pair consists of a pair of pre-defined geometric shapes. Each pre-defined geometric shape includes at least two sides that share a common vertex, which coincides in the top view of the double-layer calibration plate. The two geometric shapes in the pair are symmetrically arranged in the top view of the double-layer calibration plate. That is, the pre-defined geometric shape in the upper surface pattern and the pre-defined geometric shape in the lower surface pattern of each geometric pair share a common vertex in the top view of the double-layer calibration plate. For example, the pre-defined geometric shape can be a rectangle or a triangle.

[0027] Figure 3 This is a schematic diagram of a geometric pair provided in a specific embodiment of this application. Preferably, the preset geometric pair can be a triangle, such as... Figure 3 As shown, the left image shows the positioning triangle in the upper surface pattern, and the right image shows the positioning triangle in the lower surface pattern. The triangles in the upper and lower surface patterns are symmetrically arranged in the top view of the double-layer calibration plate.

[0028] In this embodiment of the application, when the image acquisition device to be calibrated is in the target pose, the two vertices of the geometric figure overlap in the imaging field of view of the image acquisition device.

[0029] Figure 4 This is a schematic diagram illustrating the positional relationship of geometric pairs within the field of view of an image acquisition device at a target pose, provided as a specific embodiment of this application. Preferably, the preset geometric pair can be a triangle, such as... Figure 4 As shown, the triangle pair does not overlap in the imaging field of view of the adjusted image acquisition device, except for the shared vertex.

[0030] In this embodiment, when the image acquisition device to be calibrated is in the target pose, the two vertices of the geometric pair and the optical center of the lens of the image acquisition device to be calibrated are on the same light propagation trajectory.

[0031] Figure 5 This is a schematic diagram illustrating the relationship between an image acquisition device in a target pose and a geometric pair on a double-layer calibration plate, provided as a specific embodiment of this application. Figure 5 As shown, when the image acquisition device to be calibrated is in the target pose, it means that the image acquisition device to be calibrated has been calibrated. At this time, within the imaging field of view of the calibrated image acquisition device, the two corresponding vertices of the geometric pair in the upper and lower surface patterns of the double-layer calibration plate and the optical center of the lens of the image acquisition device are on the same light propagation trajectory. The same light ray will be deflected at an angle when passing through the interface of the transparent plate.

[0032] In this embodiment, the measurement line pair is a transfer function measurement line pair, which consists of a pair of lines with a set length and a set width; the paired calibration pattern includes multiple sets of transfer function measurement line pairs, and each set of transfer function measurement line pairs is arranged in parallel according to a preset interval.

[0033] In this embodiment, the paired calibration patterns on the double-layer calibration plate further include one or more sets of measurement line pairs. These measurement line pairs are transfer function measurement line pairs, which are standard patterns used to measure the modulation transfer function of an optical system. They typically consist of one or more sets of periodically arranged black and white parallel line pairs. The measurement line pairs can also be used to evaluate the imaging resolution of image acquisition equipment.

[0034] It is understandable that modulation transfer function (MTF) measurement line pairs consist of lines of specific length and width. To accurately measure the modulation transfer function and evaluate the imaging performance of an optical system, paired calibration patterns can include multiple sets of MTF measurement line pairs, arranged in parallel at preset intervals. This parallel arrangement helps to evaluate the optical system's ability to transmit information at different spatial frequencies from a unified direction and interval during measurement, facilitating subsequent analysis and processing of the measurement data. The preset length and width can be set according to specific measurement requirements and optical system characteristics; the preset interval can also be set as needed, ensuring that adjacent lines do not interfere with each other due to excessive proximity, affecting measurement accuracy, nor are they too far apart, failing to fully reflect the optical system's performance at different spatial frequencies. It is understandable that when testing lenses, line pairs corresponding to higher spatial frequencies have thinner lines and smaller intervals, while line pairs corresponding to lower spatial frequencies have relatively thicker lines and larger intervals. For example, when measuring a large field-of-view optical system, a smaller preset interval might be used to ensure that imaging changes at different positions within the field of view are captured. Thus, by setting up transfer function measurement line pairs, signals of different spatial frequencies can be simulated during the imaging process of the optical system, thereby calculating the modulation transfer function of the optical system.

[0035] Figure 6 This is a schematic diagram of a measurement line pair provided for a specific embodiment of this application. For example... Figure 6 As shown, one or more standard measurement line pairs are set in both the upper and lower surface patterns. Figure 6 The left image shows the measurement lines in the upper surface pattern, and the right image shows the measurement lines in the lower surface pattern. The width and specific location of the measurement line pairs must match the parameters of the image acquisition device to be calibrated, and can be designed according to the actual situation.

[0036] Figure 7 This is a schematic diagram illustrating the positional relationship of measurement line pairs within the field of view of an image acquisition device in a target pose, provided as a specific embodiment of this application. (See diagram below.) Figure 7 As shown, the measurement line pairs are symmetrically arranged within the imaging field of view of the adjusted image acquisition device.

[0037] The above technical solution provides a system for calibrating the pose of an image acquisition device. This system includes a double-layer calibration plate, positioned within the imaging field of view of the image acquisition device to be calibrated. The double-layer calibration plate includes a transparent plate, an upper surface pattern on the upper surface of the transparent plate, and a lower surface pattern on the lower surface of the transparent plate. The upper and lower surface patterns together form a pair of calibration patterns. Each pair of calibration patterns includes at least one set of geometric shape pairs and at least one set of measurement line pairs. Each geometric shape pair consists of a pair of preset geometric shapes, each preset geometric shape including at least two edges sharing a vertex. This application sets paired calibration patterns on the upper and lower surfaces of the double-layer calibration plate, enabling simultaneous detection of the six-degree-of-freedom pose deviation of the image acquisition device. Comprehensive information is obtained in a single imaging operation, improving calibration efficiency. Furthermore, the geometric shape pairs with shared vertices provide precise geometric constraints, enhancing positioning accuracy. The use of measurement line pairs for auxiliary verification, combined with the double-layer structure, enhances anti-interference capabilities, reduces reliance on equipment accuracy and human experience, and significantly improves calibration accuracy and stability.

[0038] In this embodiment of the application, the system further includes: a lighting device disposed above and / or below the double-layer calibration plate, for providing illumination to the double-layer calibration plate so that the image acquisition device to be calibrated can capture the paired calibration patterns on the double-layer calibration plate.

[0039] It is understood that, in order to ensure that the pattern on the double-layer calibration plate can be observed within the imaging field of view of the image acquisition device, the system for calibrating the pose of the image acquisition device in this embodiment may also include an illumination device. The illumination device may be set above or below the double-layer calibration plate to provide illumination for the double-layer calibration plate so that the image acquisition device to be calibrated can capture the paired calibration patterns on the double-layer calibration plate.

[0040] When the lighting equipment is positioned above the double-layer calibration plate, standard machine vision-specific light sources such as coaxial light sources and ring light sources can be used. When the lighting equipment is positioned below the double-layer calibration plate, a backlight can be used.

[0041] In this embodiment, when the lighting device is positioned above the double-layer calibration plate, to ensure imaging quality, the double-layer calibration plate further includes a diffuse reflection film layer covering the pattern on the lower surface. This allows for the acquisition of complete paired calibration patterns on both the upper and lower surfaces during the calibration of the image acquisition device, improving the accuracy of subsequent calibration results.

[0042] Figure 8 This application provides a flowchart illustrating a method for calibrating the pose of an image acquisition device. Figure 8 As shown, this application provides a method for calibrating the pose of an image acquisition device, applied to the image acquisition device pose calibration system described above. The method may include the following steps: Step S101: Obtain a sample image acquired by the image acquisition device to be calibrated. The sample image includes a pair of calibration patterns.

[0043] It is understood that the image acquisition device pose calibration method in this application embodiment is based on the paired calibration patterns of the double-layer calibration plate in the image acquisition device pose calibration system in the above embodiment, and achieves accurate calibration of the device's six degrees of freedom pose through image analysis and parameter calculation.

[0044] Specifically, the first step is to capture a sample image containing the double-layer calibration plate using an image acquisition device (such as a camera) to ensure that the paired calibration patterns (geometric pairs and measurement line pairs) on the upper and lower surfaces are fully visible in the field of view.

[0045] Step S102: Identify geometric pairs in the sample image using target recognition technology, and determine the actual vertex coordinates of the paired vertices in the image pixel coordinate system.

[0046] It is understandable that the vertices of geometric shapes are stable feature points, and their pixel coordinate deviations can reflect the translation and rotation states of the device. Specifically, geometric pairs (such as paired triangles) in the sample image are located using target recognition techniques (such as template matching and corner detection), and the actual vertex coordinates of the corresponding vertices of the preset geometric shapes on the upper and lower surfaces in the image pixel coordinate system are extracted. This provides a data foundation for subsequent processing.

[0047] Step S103: Based on the actual vertex coordinates and target vertex coordinates of the paired vertices, determine the offset parameters of the X-axis and Y-axis directions of the image acquisition device to be calibrated in the preset three-dimensional coordinate system, wherein the X-axis and Y-axis directions correspond to the directions of the two coordinate axes of the image pixel coordinate system.

[0048] It can be understood that target vertex coordinates refer to the pixel coordinates of the geometric figure relative to its position in the image captured by the image acquisition device when the image acquisition device is at the target position. Specifically, the offset parameters of the image acquisition device to be calibrated in the X-axis and Y-axis directions in the preset three-dimensional coordinate system can be calculated by using the actual vertex coordinates and the target coordinates. The preset three-dimensional coordinate system can be selected according to requirements, such as the image acquisition device coordinate system, the double-layer calibration plate coordinate system, and the world coordinate system. The X and Y axes in the preset three-dimensional coordinate system correspond to the horizontal and vertical axes of the image pixel coordinate system. In this way, the 2D image deviation can be transformed into a planar offset in 3D space through coordinate mapping. Step S104: Identify the measurement line pairs in the sample image, and calculate the actual transfer function value of the measurement line pairs and the actual angle of the measurement line pairs in the sample image.

[0049] Step S105: Based on the actual transfer function value, actual angle, target transfer function value, and target angle, determine the offset parameter of the image acquisition device to be calibrated in the Z-axis direction in the preset three-dimensional coordinate system, wherein the Z-axis direction is perpendicular to the X-axis direction and the Y-axis direction.

[0050] It can be understood that the actual transfer function value refers to the actual imaging sharpness index of the measurement line pair in the sample image, reflecting the image acquisition device's ability to transmit signals of a specific spatial frequency under its current state. The target transfer function value refers to the standard transfer function value of the measurement line pair when the image acquisition device is in the target pose, as designed in the dual-layer calibration plate. The actual angle refers to the tilt angle of the measurement line pair in the sample image, which can be determined by image analysis algorithms, such as Hough transform. The target angle refers to the reference angle of the measurement line pair on the calibration plate during dual-layer calibration plate design, serving as a target reference for the image acquisition device's rotation around the Z-axis.

[0051] Specifically, the transfer function value (MTF) is directly related to the device's working distance, while the angular deviation of the measurement line pairs in the sample image reflects the rotational state of the image acquisition device around the Z-axis in a preset three-dimensional coordinate system. Therefore, this embodiment can calculate the actual MTF and actual angle of the measurement line pairs (such as periodic black and white line pairs) in the sample image by identifying them. Further, based on the actual MTF, actual angle, target MTF, and target angle, the offset parameter of the image acquisition device to be calibrated in the Z-axis direction of the preset three-dimensional coordinate system is determined. Specifically, by comparing the actual MTF and target MTF of the measurement line pairs, the Z-axis position deviation of the image acquisition device in the preset three-dimensional coordinate system can be calculated; by comparing the actual angle and target angle, the rotational deviation of the image acquisition device to be calibrated around the Z-axis can be calculated.

[0052] Step 106: Based on the offset parameters of the image acquisition device to be calibrated in the X-axis, Y-axis and Z-axis directions in the preset three-dimensional coordinate system, calibrate the image acquisition device to be calibrated.

[0053] In this embodiment, when the offset parameters of the image acquisition device to be calibrated in the X-axis, Y-axis and Z-axis directions in the preset three-dimensional coordinate system are all zero, it is determined that the image acquisition device to be calibrated is in the target pose, and the calibration of the image acquisition device to be calibrated is completed.

[0054] Specifically, after determining the offset parameters of the image acquisition device to be calibrated along the X, Y, and Z axes in a preset three-dimensional coordinate system, the processor can synthesize these offset parameters to generate adjustment instructions (such as mechanical drive parameters or manual adjustment prompts) to guide the device to correct its pose until all deviations approach zero. In this way, precise calibration of the device's pose can be achieved through closed-loop feedback, ensuring that it conforms to the preset imaging benchmark.

[0055] The above technical solution, based on the paired calibration patterns of the double-layer calibration plate in the image acquisition device pose calibration system described in the above embodiments, achieves precise calibration of the device's six degrees of freedom pose through image analysis and parameter calculation. This guides installation personnel to accurately and efficiently adjust the installation status of the image acquisition device, avoiding reliance on personnel experience to analyze and judge the deviation direction of the image acquisition device's position and attitude parameters without direct evidence, thereby improving the accuracy of the calibration results.

[0056] In this embodiment, the offset parameters include positional offset and rotational offset. Determining the offset parameters of the image acquisition device to be calibrated in the X-axis and Y-axis directions of the preset three-dimensional coordinate system based on the actual vertex coordinates and target vertex coordinates of the paired vertices may include: determining the positional offset and rotational offset of the image acquisition device to be calibrated in the X-axis direction of the preset three-dimensional coordinate system based on the abscissa of the actual vertex coordinates and the abscissa of the target vertex coordinates; and determining the positional offset and rotational offset of the image acquisition device to be calibrated in the Y-axis direction of the preset three-dimensional coordinate system based on the ordinate of the actual vertex coordinates and the ordinate of the target vertex coordinates.

[0057] It is understood that the offset parameters include positional deviation and rotational deviation. Positional deviation includes the positional deviation of the image acquisition device to be calibrated in the X and Y axis directions in the preset three-dimensional coordinate system, and rotational deviation includes the rotational deviation of the image acquisition device to be calibrated in the X and Y axis directions in the preset three-dimensional coordinate system.

[0058] In one example, the processor determines the average x-coordinate of the actual x-coordinates of each vertex in the geometric pair. It then calculates the difference between the target x-coordinate and the average x-coordinate of the actual x-coordinates of the target vertex, and determines the X-axis position deviation based on this difference. The Y-axis position deviation is calculated similarly.

[0059] In one example, the processor can calculate the difference in the x-coordinates and y-coordinates of paired vertices in a geometric pair based on the actual vertex coordinates, and determine the X-axis rotation deviation and Y-axis rotation deviation based on the difference in the x-coordinates and y-coordinates, respectively.

[0060] In this embodiment, the offset parameters include positional deviation and rotational deviation. Determining the offset parameters of the image acquisition device to be calibrated in the Z-axis direction of a preset three-dimensional coordinate system based on the actual transfer function value, the actual angle, the target transfer function value, and the target angle may include: determining the positional deviation of the image acquisition device to be calibrated in the Z-axis direction of the preset three-dimensional coordinate system based on the actual transfer function value and the target transfer function value; and determining the rotational deviation of the image acquisition device to be calibrated in the Z-axis direction of the preset three-dimensional coordinate system based on the actual angle and the target angle.

[0061] The actual transfer function value refers to the actual imaging sharpness index of the measurement line pair in the sample image, reflecting the image acquisition device's ability to transmit signals of a specific spatial frequency under its current state. The target transfer function value refers to the standard value of the measurement line pair when the image acquisition device is in the target pose, as designed in a dual-layer calibration plate. The actual angle refers to the tilt angle of the measurement line pair in the sample image, which can be determined through image analysis algorithms, such as Hough transform. The target angle refers to the reference angle of the measurement line pair on the calibration plate during dual-layer calibration plate design, serving as a target reference for the image acquisition device's rotation around the Z-axis.

[0062] Specifically, the transfer function value is directly related to the working distance of the image acquisition device (i.e., its position in the Z-axis direction). When the image acquisition device deviates from the reference position along the Z-axis, the imaging clarity of the image acquisition device decreases, causing a deviation between the actual transfer function value and the target transfer function value. For example, distances that are too close or too far will lead to a decrease in the transfer function value of the measured line pair. Therefore, in this embodiment, a mapping relationship between the transfer function value and the working distance of the image acquisition device can be pre-established through experiments. Then, by comparing the difference between the actual and target transfer function values, and combining this mapping relationship, the positional deviation of the image acquisition device in the Z-axis direction can be determined. For example, a larger difference in transfer function values ​​indicates a greater deviation of the image acquisition device from the reference working distance.

[0063] Furthermore, since the target angle of the measurement line pair on the calibration plate is fixed, when the image acquisition device rotates around the Z-axis, the angle of the imaged measurement line pair will deflect synchronously, causing a deviation between the actual angle and the target angle. Therefore, the processor can determine the rotational deviation of the image acquisition device in the Z-axis direction of the preset three-dimensional coordinate system by calculating the difference between the actual angle and the target angle.

[0064] In this way, by correlating optical performance indicators with spatial pose, accurate analysis of the three-dimensional deviation of the image acquisition device can be achieved.

[0065] Figure 9 This is a schematic diagram of paired calibration patterns on a double-layer calibration plate according to a specific embodiment of this application. Figure 9 As shown, from left to right, these are the overlapping calibration patterns, the upper surface pattern, and the lower surface pattern of the upper calibration plate from a vertical perspective. A specific embodiment of this application uses a double-layer calibration plate with a pair of positioning triangles and multiple pairs of measurement lines as an example to illustrate the calibration process of the image acquisition device. Figure 9 The calibration process for the image acquisition device, as shown in the double-layer calibration board design, is as follows: The lighting equipment illuminates the double-layer calibration plate, allowing the adjusted camera and lens to observe the paired calibration patterns on the double-layer calibration plate.

[0066] The accompanying software acquires patterns on the double-layer calibration board in real time using the camera being adjusted, and outputs corresponding adjustment direction prompts in real time. This helps the setup personnel adjust the position and attitude of the camera to be adjusted to the target pose based on the location of the double-layer calibration board. The operating logic of the accompanying software is as follows: S11, capture a real-time sample image taken by the adjusted camera.

[0067] S12, using target recognition technology, identifies a pair of positioning triangles in the sample image within the positioning triangle area in the above figure, and further locates the actual vertex coordinates (Xa, Ya) of the upper surface triangle and the actual vertex coordinates (Xb, Yb) of the lower surface triangle.

[0068] S13, retrieve the target vertex coordinates (X0, Y0) of the triangle determined during pattern design using the pre-saved double-layer calibration plate, and calculate the offset parameters of the camera being adjusted based on the actual vertex coordinates and the target vertex coordinates.

[0069] X-axis position deviation of the adjusted camera: Xd = X0 - (Xa + Xb) / 2; The Y-axis position deviation of the adjusted camera is: Yd = Y0 - (Ya + Yb) / 2; The X-axis rotation deviation of the adjusted camera is: θxd = Ya - Yb; The Y-axis rotation deviation of the adjusted camera is: θyd = Xa - Xb.

[0070] S14. Based on the characteristics of the region and shape, identify the measurement line pairs in the sample image that belong to the upper surface pattern a and the lower surface pattern b respectively, calculate the mean value of the transfer function of the upper surface measurement line MTFa and the mean value of the transfer function of the lower surface measurement line MTFb, and calculate the tilt angle θz of the measurement line pair in the image.

[0071] S15, retrieve the pre-saved target transfer function values ​​MTFa0 and MTFb0 corresponding to the upper and lower surface patterns determined during the pattern design of the double-layer calibration board. Calculate the camera working distance deviation, i.e., the Z-axis position deviation, based on MTFa, MTFb, MTFa0, and MTFb0 as follows: Z-axis position deviation: .

[0072] in, The numerical value representing the Z-axis position deviation. Indicates the direction of the deviation.

[0073] S16, retrieve the angle value θz0 of the transfer function measurement line corresponding to the chrome-plated patterns on the upper and lower surfaces of the double-layer calibration plate, which was determined during the pattern design process. The following parameters are calculated: Camera Z-axis rotation deviation: θzd = θz0 - θz.

[0074] S17, refresh and display the above calculation results on the human-machine interface: Xd, Yd, Zd, θxd, θyd, θzd. Then, start the loop again from step S11 until all the above bias parameters are zero.

[0075] Figure 10 This is a schematic diagram of paired calibration patterns on a double-layer calibration plate, provided as another specific embodiment of this application. As shown in Figure 10, from left to right, the overlapping paired calibration patterns, the upper surface pattern, and the lower surface pattern are shown from a vertical perspective of the upper calibration plate. This other specific embodiment of the application uses a double-layer calibration plate with two pairs of positioning triangles and multiple pairs of measurement lines as an example to illustrate the calibration process of an image acquisition device, based on... Figure 10 The calibration process for the image acquisition device, as shown in the double-layer calibration board design, is as follows: The lighting equipment illuminates the double-layer calibration plate, allowing the adjusted camera and lens to observe the pattern on the double-layer calibration plate. The accompanying software uses the camera being adjusted to capture patterns on the double-layer calibration board in real time and outputs corresponding adjustment direction prompts to help the setup personnel adjust the camera's position and orientation to the target position based on the location of the double-layer calibration board. The operating logic of the accompanying software is as follows: S21, capture a real-time sample image from the camera.

[0076] S22, using target recognition technology, within the triangular region shown in the above figure, identify two pairs of localization triangles in the sample image, and further locate the vertex coordinates (Xa1, Ya1) of the first triangle on the upper surface and the vertex coordinates (Xb1, Yb1) of the first triangle on the lower surface. Locate the vertex coordinates (Xa2, Ya2) of the second triangle on the upper surface and the vertex coordinates (Xb2, Yb2) of the second triangle on the lower surface.

[0077] S23, retrieve the pre-saved target vertex coordinates (X01, Y01) of the first pair of triangles and the target vertex coordinates (X02, Y02) of the second pair of triangles, determined during the pattern design of the double-layer calibration plate. The following parameters are calculated: Camera X-axis position deviation Xd = X01 - (Xa1 + Xb1) / 2 + X02 - (Xa2 + Xb2) / 2; Camera Y-axis position deviation Yd = Y01 - (Ya1 + Yb1) / 2 + Y02 - (Ya2 + Yb2) / 2; Camera X-axis rotation deviation θxd = Ya1 - Yb1 + Ya2 - Yb2; The camera's Y-axis rotation deviation θyd = Xa1 - Xb1 + Xa2 - Xb2.

[0078] S24. Based on features such as location and shape, identify the transfer function measurement line pairs belonging to the upper and lower surface patterns in the sample image, respectively. Calculate their average transfer functions MTFa and MTFb, respectively. Calculate the angle θz of the measurement line pair in the image.

[0079] S25, retrieve the target transfer function values ​​MTFb0 and MTFc0 of the transfer function measurement lines corresponding to the chrome-plated patterns on the upper and lower surfaces of the double-layer calibration plate, which were determined during the pattern design process. The following parameters are calculated: Z-axis position deviation: .

[0080] in, The numerical value representing the Z-axis position deviation. Indicates the direction of the deviation.

[0081] S26, retrieve the angle value θz0 of the transfer function measurement line corresponding to the chrome-plated patterns on the upper and lower surfaces of the double-layer calibration plate, which was determined during the pattern design process. The following parameters are calculated: Camera Z-axis rotation deviation θzd = θz0 - θz; S27, refresh and display the above calculation results on the human-machine interface: Xd, Yd, Zd, θxd, θyd, θzd. Then, start the loop again from step S21 until the result is zero.

[0082] This application also provides a controller, including: a memory configured to store instructions; and a processor configured to retrieve instructions from the memory and, when executing the instructions, to implement the image acquisition device pose calibration method described above.

[0083] Figure 11 This is a structural block diagram of a controller provided in an embodiment of this application. Figure 11 As shown in the figure, this application provides a controller that may include: Memory 110 is configured to store instructions; The processor 120 is configured to retrieve instructions from the memory 110 and, when executing the instructions, to implement the method for calibrating the pose of the image acquisition device described above.

[0084] This application also provides a machine-readable storage medium on which a program or instruction is stored, and when the program or instruction is executed by a processor, it implements the method for pose calibration of the image acquisition device described above.

[0085] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0086] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0087] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0088] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0089] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0090] Memory may include non-persistent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0091] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0092] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. 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 apparatus that includes that element.

[0093] The above are merely embodiments of this application and are not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. A system for calibrating the pose of an image acquisition device, characterized in that, The system includes: A double-layer calibration plate is located within the imaging field of view of the image acquisition device to be calibrated. The double-layer calibration plate includes a transparent plate, an upper surface pattern on the upper surface of the transparent plate, and a lower surface pattern on the lower surface of the transparent plate. The upper surface pattern and the lower surface pattern together form a pair of calibration patterns. The pair of calibration patterns includes at least one set of geometric shape pairs and at least one set of measurement line pairs. The geometric shape pairs are composed of a pair of preset geometric shapes. The preset geometric shapes include at least two sides, and the two sides share a vertex. Specifically, when the image acquisition device to be calibrated is in the target pose, the two vertices of the geometric pair are on the same light propagation trajectory as the optical center of the lens of the image acquisition device to be calibrated.

2. The system according to claim 1, characterized in that, The system also includes: A lighting device is disposed above and / or below the double-layer calibration plate to provide illumination for the double-layer calibration plate so that the image acquisition device to be calibrated can capture the paired calibration patterns on the double-layer calibration plate.

3. The system according to claim 2, characterized in that, When the lighting device is positioned above the double-layer calibration plate, the double-layer calibration plate further includes a diffuse reflection film layer that covers the pattern on the lower surface.

4. The system according to claim 1, characterized in that, The measurement line pair is a transfer function measurement line pair, which consists of a pair of lines with a set length and a set width. The paired calibration pattern includes multiple sets of the transfer function measurement line pairs, and each set of the transfer function measurement line pairs is arranged in parallel according to a preset interval.

5. A method for pose calibration of an image acquisition device, characterized in that, The method, applied to the system for pose calibration of an image acquisition device according to any one of claims 1 to 4, comprises: Acquire a sample image acquired by the image acquisition device to be calibrated, wherein the sample image includes the paired calibration pattern; The geometric pair in the sample image is identified by target recognition technology, and the actual vertex coordinates of the paired vertices in the image pixel coordinate system are determined. Based on the actual vertex coordinates and target vertex coordinates of the paired vertices, the offset parameters of the image acquisition device to be calibrated in the X-axis and Y-axis directions in the preset three-dimensional coordinate system are determined, wherein the X-axis direction and the Y-axis direction correspond to the directions of the two coordinate axes of the image pixel coordinate system; Identify the measurement line pairs in the sample image, and calculate the actual transfer function value of the measurement line pairs and the actual angle of the measurement line pairs in the sample image; Based on the actual transfer function value, the actual angle, the target transfer function value, and the target angle, the offset parameter of the image acquisition device to be calibrated in the Z-axis direction in the preset three-dimensional coordinate system is determined, wherein the Z-axis direction is perpendicular to the X-axis direction and the Y-axis direction; The image acquisition device to be calibrated is calibrated according to the offset parameters of the X-axis direction, the Y-axis direction, and the Z-axis direction in the preset three-dimensional coordinate system.

6. The method according to claim 5, characterized in that, The offset parameters include positional offset and rotational offset. Determining the offset parameters of the image acquisition device to be calibrated in the X-axis and Y-axis directions in a preset three-dimensional coordinate system based on the actual vertex coordinates and target vertex coordinates of the paired vertices includes: Based on the x-coordinate in the actual vertex coordinates and the x-coordinate in the target vertex coordinates, determine the positional deviation and rotational deviation of the image acquisition device to be calibrated in the X-axis direction in the preset three-dimensional coordinate system; Based on the ordinate in the actual vertex coordinates and the ordinate in the target vertex coordinates, the position deviation and rotation deviation of the image acquisition device to be calibrated in the Y-axis direction in the preset three-dimensional coordinate system are determined.

7. The method according to claim 5, characterized in that, The offset parameters include positional offset and rotational offset. Determining the offset parameters of the image acquisition device to be calibrated in the Z-axis direction of the preset three-dimensional coordinate system based on the actual transfer function value, the actual angle, the target transfer function value, and the target angle includes: Based on the actual transfer function value and the target transfer function value, determine the positional deviation of the image acquisition device to be calibrated in the Z-axis direction in the preset three-dimensional coordinate system; Based on the actual angle and the target angle, the rotational deviation of the image acquisition device to be calibrated in the Z-axis direction in the preset three-dimensional coordinate system is determined.

8. A controller, characterized in that, include: The memory is configured to store instructions; as well as The processor is configured to retrieve the instructions from the memory and, when executing the instructions, to implement the method for pose calibration of the image acquisition device according to any one of claims 5 to 7.

9. A machine-readable storage medium on which a program or instructions are stored, characterized in that, When the program or the instructions are executed by the processor, the method for pose calibration of the image acquisition device according to any one of claims 5 to 7 is implemented.

Images