Hand-eye calibration method, electronic equipment and computer program product
By constructing a pose transformation matrix between the camera and robot coordinate systems, the problem of accurate recognition of industrial robots on irregularly shaped workpieces is solved, and efficient processing and recognition effects are achieved.
Patent Information
- Application Number
- CN202510614169.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-05-13
- Publication Date
- 2025-09-16
AI Technical Summary
In the existing technology, when industrial robots are faced with irregularly shaped workpieces to be processed, it is difficult to accurately identify the processing position, resulting in insufficient operational accuracy and efficiency.
By constructing the pose transformation matrix between the camera coordinate system and the robot coordinate system, and using the calibration tooling to build the conversion relationship at different positions, the mapping relationship between the camera and robot coordinate systems is obtained to achieve hand-eye calibration.
It improves the processing accuracy and efficiency of industrial robots on irregular-shaped workpieces, enhances the robot's applicability, and enables rapid assembly line identification and tracking.
Smart Images
Figure CN120645205A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of industrial robots, and in particular to a hand-eye calibration method, electronic equipment, and computer program product. Background Art
[0002] Industrial robots are multi-jointed manipulators or multi-degree-of-freedom devices widely used in industry. They possess a degree of autonomy and can perform various industrial processing and manufacturing functions through their own power and control capabilities. They are widely used in various industries, including electronics, logistics, and chemicals.
[0003] By attaching various tools to the working end of an industrial robot, it can perform various operations on workpieces, such as spraying and gluing. In practical applications, the contours of workpieces are often irregular, and a major challenge for industrial robots in such assembly-line operations is how to accurately identify the workpiece's location. Summary of the Invention
[0004] The present invention provides a hand-eye calibration method, electronic equipment and computer program product, which can overcome certain defects of the prior art.
[0005] A hand-eye calibration method according to the present invention is a hand-eye calibration method between a camera coordinate system and a robot coordinate system, comprising: A calibration tool is placed at a first position to establish a first conversion relationship; wherein the first position is located in a first area, the first area is the image acquisition area of the camera, and the first conversion relationship is a mapping relationship between a first coordinate system where the image acquisition area is located and the camera coordinate system; Placing another calibration tool at a second position to establish a second conversion relationship; wherein the second position is located in a second area, the second area is the executable area of the robot, and the second conversion relationship is a mapping relationship between a second coordinate system where the second area is located and the robot coordinate system; Based on the first coordinate system and the second coordinate system, a third conversion relationship is constructed; wherein the third conversion relationship is a mapping relationship between the first position and the second position; Based on the first transformation relationship, the second transformation relationship and the third transformation relationship, a pose transformation matrix between the camera coordinate system and the robot coordinate system is obtained.
[0006] Preferably, the calibration tool comprises a first calibration body, wherein the first calibration body comprises three non-collinear first markers; The step of placing a calibration tool at a first position and establishing a first conversion relationship includes: Obtaining the first spatial coordinates of each first marker in the camera coordinate system; wherein the three first markers correspond to a total of three first spatial coordinates; A first transformation relationship is constructed based on the three first space coordinates.
[0007] Preferably, the first conversion relationship includes a first rotation relationship and a first translation relationship; The constructing of the first conversion relationship based on the three first space coordinates includes: Selecting one of the three first space coordinates as the origin of the first coordinate system; Taking the direction from one of the three first space coordinates to the second of the three first space coordinates as the X-axis direction of the first coordinate system, obtaining a unit vector in the X-axis direction of the first coordinate system; Taking the direction from one of the three first space coordinates to the third of the three first space coordinates as the temporary Y-axis direction of the first coordinate system, obtaining a unit vector of the temporary Y-axis direction of the first coordinate system; Obtain a unit vector in the Z-axis direction of the first coordinate system based on the unit vector in the X-axis direction of the first coordinate system and the unit vector in the temporary Y-axis direction of the first coordinate system; Obtain a unit vector in the Y-axis direction of the first coordinate system based on the unit vector in the X-axis direction of the first coordinate system and the unit vector in the Z-axis direction of the first coordinate system; Constructing a first rotation relationship based on a unit vector in the X-axis direction of the first coordinate system, a unit vector in the Y-axis direction of the first coordinate system, and a unit vector in the Z-axis direction of the first coordinate system; A first translation relationship is constructed based on the one of the three first space coordinates.
[0008] Preferably, the other calibration tool has a second calibration body, and the second calibration body has three non-collinear second markers; The step of placing another calibration tool at a second position and establishing a second conversion relationship includes: Obtaining the second space coordinates of each second marker in the camera coordinate system; wherein the three second markers correspond to a total of three second space coordinates; A second transformation relationship is constructed based on the three second space coordinates.
[0009] Preferably, the second conversion relationship includes a second rotation relationship and a second translation relationship; The constructing of the second conversion relationship based on the three second space coordinates includes: Selecting one of the three second space coordinates as the origin of the second coordinate system; Taking the direction from one of the three second space coordinates to the second of the three second space coordinates as the X-axis direction of the second coordinate system, obtaining a unit vector in the X-axis direction of the second coordinate system; Taking the direction from one of the three second space coordinates to the third of the three second space coordinates as the temporary Y-axis direction of the second coordinate system, obtaining a unit vector of the temporary Y-axis direction of the second coordinate system; Obtain a unit vector in the Z-axis direction of the second coordinate system based on the unit vector in the X-axis direction of the second coordinate system and the unit vector in the temporary Y-axis direction of the second coordinate system; Obtain a unit vector in the Y-axis direction of the second coordinate system based on the unit vector in the X-axis direction of the second coordinate system and the unit vector in the Z-axis direction of the second coordinate system; Constructing a second rotation relationship based on the unit vector in the X-axis direction of the second coordinate system, the unit vector in the Y-axis direction of the second coordinate system, and the unit vector in the Z-axis direction of the second coordinate system; A second translation relationship is constructed based on the one of the three second space coordinates.
[0010] Preferably, the constructing of the third conversion relationship based on the first coordinate system and the second coordinate system includes: An offset between the one of the three first space coordinates and the one of the three second space coordinates is obtained, and a third conversion relationship is constructed based on the offset.
[0011] Preferably, the one calibration tool and the another calibration tool are different calibration tools, and the triangle formed by the three first markers and the triangle formed by the three second markers are congruent triangles.
[0012] Preferably, the one calibration tool and the other calibration tool are the same calibration tool, and the three first markers and the three second markers are all set on the same calibration tool.
[0013] Furthermore, the present invention aims to provide an electronic device, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor. The instructions are executed by the at least one processor to enable the at least one processor to perform any one of the above-mentioned hand-eye calibration methods.
[0014] In addition, an object of the present invention is to provide a computer program product, comprising a computer program, which implements any one of the above-mentioned hand-eye calibration methods when executed by a processor.
[0015] The present invention has the following beneficial effects: The pose transformation matrix between the camera coordinate system and the robot coordinate system can be obtained better. BRIEF DESCRIPTION OF THE DRAWINGS
[0016] Figure 1 Schematic diagram of the working trajectory tracking method in Example 1; Figure 2 Schematic diagram of the calibration method in Example 2. DETAILED DESCRIPTION
[0017] In order to further understand the content of the present invention, the present invention is described in detail with reference to the accompanying drawings and embodiments. It should be understood that the embodiments are merely for explaining the present invention and are not intended to limit the present invention.
[0018] Example 1 Seen in Figure 1 This embodiment provides a working trajectory tracking method based on machine vision. When a posture trajectory recording handle is operating in a first area and a robot is operating in a second area, the method tracks a first working trajectory of a first working end of the posture trajectory recording handle to obtain a second working trajectory required by a second working end of the robot. The first area is an image acquisition area of a camera, and the second area is an executable area of the robot. It includes, Obtaining the spatial coordinates of the first working trajectory; Based on the spatial coordinates of the first working trajectory, obtaining the spatial coordinates of the second working trajectory; Based on the spatial coordinates of the second working trajectory, the motion instructions of the robot are obtained.
[0019] Based on the above method, the spatial coordinates of the second working trajectory required by the robot can be obtained based on the spatial coordinates of the first working trajectory recorded by the posture trajectory recording handle, and the trajectory tracking of the first working end of the posture trajectory recording handle by the second working end of the robot can be realized by converting the spatial coordinates of the second working trajectory into the action instructions of the robot; this enables the robot to manually hold the posture trajectory recording handle in actual applications, and keep the first working end depicting the position to be processed of a template workpiece to thereby obtain the spatial coordinates of the first working trajectory, and then the second working end can operate with the second working trajectory corresponding to the first working trajectory based on the action instructions of the robot, thereby better realizing the rapid and accurate identification and tracking of the position to be processed of the workpiece to be processed, thereby better improving the application versatility of the industrial robot.
[0020] It can be understood that when the method in this embodiment is actually used, the template workpiece and the workpiece to be processed are workpieces of the same size and model; and after obtaining the robot's action instructions, the action instructions can be repeatedly executed, thereby realizing assembly line processing of the workpiece to be processed.
[0021] In this embodiment, the posture trajectory recording handle has a mounting plane, on which a sensing component is provided, and the sensing component has three non-collinear markers; wherein the first working end and the markers have a relatively fixed spatial position relationship; The obtaining of the spatial coordinates of the first working trajectory includes: Obtain the marker space coordinates of each marker in the camera coordinate system; wherein the three markers correspond to a total of three marker space coordinates; Based on the three marker space coordinates, the first working end camera space coordinates of the first working end in the camera coordinate system are obtained.
[0022] Based on the above, the spatial coordinates of the first working trajectory of the first working end can be preferably acquired.
[0023] It can be understood that for the three non-collinear markers on the same installation plane, their coordinates are set as 、 and , under the premise that there is a relatively fixed spatial position relationship between the first working end and the marking body, the coordinates of the first working end The three markers that are not collinear with the same mounting plane must have the following relationship: ; That is, ; It is understandable that after the posture trajectory recording handle is manufactured, the spatial position relationship between the first working end and the three non-collinear markers on the same installation plane has been determined, and the parameters 、 and The value of will be determined. . .
[0024] Based on this, the method in this embodiment only needs to use a camera to identify and obtain the positional relationship of three non-collinear markers on the same installation plane to obtain the spatial coordinates of the first working trajectory of the first working end.
[0025] In this embodiment, the posture trajectory recording handle has 6 installation planes, and the 6 installation planes correspond to 6 directions in space respectively; a sensing component is provided at any installation plane, and any sensing component has 3 non-collinear markers.
[0026] Based on the above, when the posture trajectory recording handle is in various postures in space, the camera can better capture the three markers on at least one installation plane, which makes the posture trajectory recording handle more flexible to use and can be used on workpieces with more complex surface morphology.
[0027] In this embodiment, the triangle formed by the three marking bodies at any installation plane and the triangle formed by the three marking bodies at any other installation planes do not form similar triangles.
[0028] Based on this, when acquiring three markers on the same installation plane, the currently detected installation plane can be better known based on the relative positional relationship of the three markers on each installation plane, thereby ensuring the detection accuracy of the spatial coordinates of the first working trajectory.
[0029] It can be understood that the six directions of the space correspond to up, down, left, right, front and back, and the parameters between the three markers and the first working end at different installation planes are 、 and In this embodiment, since the triangle formed by the three markers at any installation plane does not form a similar triangle to the triangle formed by the three markers at any other installation plane, after the camera obtains the spatial coordinates of the three markers at the same installation plane, it can know the number of the currently identified installation plane based on features such as the spatial distance between the spatial coordinates of the three markers, and then substitute the corresponding parameters 、 and The spatial coordinates of the first working trajectory of the first working end can be obtained by using the value of
[0030] Specifically, after the camera detects the spatial coordinates of three markers on the same installation plane, it can obtain the length of each side of the triangle formed by the three markers. At this time, the numbering of the installation plane can be determined based on the ratio between the side lengths (the ratio of the side lengths between any two sides).
[0031] In this embodiment, the marking body can adopt an infrared lamp assembly that can emit infrared light, thereby preferably improving the recognition sensitivity and accuracy of the camera.
[0032] In this embodiment, the acquisition of the spatial coordinates of the second working trajectory based on the spatial coordinates of the first working trajectory includes: Get the pose transformation matrix between the camera coordinate system and the robot coordinate system; Based on the pose transformation matrix between the camera coordinate system and the robot coordinate system, the spatial coordinates of the second working trajectory are obtained.
[0033] Therefore, the pose transformation matrix obtained based on the achieved calibration can be better used to better obtain the second working trajectory based on the first working trajectory.
[0034] Example 2 Seen in Figure 2 In order to better obtain the pose transformation matrix between the camera coordinate system and the robot coordinate system, this embodiment provides a hand-eye calibration method between the camera coordinate system and the robot coordinate system, which includes: A calibration tool is placed at a first position to establish a first conversion relationship; wherein the first position is located in a first area, the first area is the image acquisition area of the camera, and the first conversion relationship is a mapping relationship between a first coordinate system where the image acquisition area is located and the camera coordinate system; Placing another calibration tool at a second position to establish a second conversion relationship; wherein the second position is located in a second area, the second area is the executable area of the robot, and the second conversion relationship is a mapping relationship between a second coordinate system where the second area is located and the robot coordinate system; Based on the first coordinate system and the second coordinate system, a third conversion relationship is constructed; wherein the third conversion relationship is a mapping relationship between the first position and the second position; Based on the first transformation relationship, the second transformation relationship and the third transformation relationship, a pose transformation matrix between the camera coordinate system and the robot coordinate system is obtained.
[0035] Based on the above, the pose transformation matrix between the camera coordinate system and the robot coordinate system can be obtained relatively easily.
[0036] The calibration tool has a first calibration body, and the first calibration body has three non-collinear first markers; The step of placing a calibration tool at a first position and establishing a first conversion relationship includes: Obtaining the first spatial coordinates of each first marker in the camera coordinate system; wherein the three first markers correspond to a total of three first spatial coordinates; A first transformation relationship is constructed based on the three first space coordinates.
[0037] Based on the above, the three first markers can form a unique plane in space, thereby better enabling the acquisition of the first conversion relationship.
[0038] Wherein, the first conversion relationship includes a first rotation relationship and a first translation relationship; The constructing of the first conversion relationship based on the three first space coordinates includes: Selecting one of the three first space coordinates as the origin of the first coordinate system; Taking the direction from one of the three first space coordinates to the second of the three first space coordinates as the X-axis direction of the first coordinate system, obtaining a unit vector in the X-axis direction of the first coordinate system; Taking the direction from one of the three first space coordinates to the third of the three first space coordinates as the temporary Y-axis direction of the first coordinate system, obtaining a unit vector of the temporary Y-axis direction of the first coordinate system; Obtain a unit vector in the Z-axis direction of the first coordinate system based on the unit vector in the X-axis direction of the first coordinate system and the unit vector in the temporary Y-axis direction of the first coordinate system; Obtain a unit vector in the Y-axis direction of the first coordinate system based on the unit vector in the X-axis direction of the first coordinate system and the unit vector in the Z-axis direction of the first coordinate system; Constructing a first rotation relationship based on a unit vector in the X-axis direction of the first coordinate system, a unit vector in the Y-axis direction of the first coordinate system, and a unit vector in the Z-axis direction of the first coordinate system; A first translation relationship is constructed based on the one of the three first space coordinates.
[0039] Based on the above, the first rotation relationship and the first translation relationship can be preferably obtained.
[0040] Specifically, in the actual processing process, The camera can obtain a total of 3 first space coordinates corresponding to 3 first markers, which are 、 and ; Afterwards, you can 、 and As the origin, the first coordinate system is constructed (in this embodiment, any one of as an example); Afterwards, we can define point to The direction of is the X-axis direction of the first coordinate system, then the unit vector in the X-axis direction of the first coordinate system is Can be expressed as, ; in, Indicates the modulus of the corresponding vector; Afterwards, we can define point to The direction of is the temporary Y-axis direction of the first coordinate system, then the unit vector of the temporary Y-axis direction of the first coordinate system is Can be expressed as, ; in, Indicates the modulus of the corresponding vector; Afterwards, based on the cross multiplication orthogonalization calculation, the Z-axis direction of the first coordinate system and the unit vector of the Z-axis direction of the first coordinate system can be obtained. Can be expressed as, ; in, Indicates the modulus of the corresponding vector; Afterwards, based on the cross multiplication orthogonalization calculation, the Y-axis direction of the first coordinate system and the unit vector of the Y-axis direction of the first coordinate system can be obtained. Can be expressed as, ； in, Indicates the magnitude of the corresponding vector.
[0041] Based on unit vectors 、 and The first rotation relationship can be constructed and the first translation relationship ,in, ， in, It is a 3*3 matrix.
[0042] Based on the first space coordinate ,, you can get the first translation relationship , .
[0043] Based on the above, the first conversion relationship can be preferably obtained.
[0044] In this embodiment, the other calibration tool has a second calibration body, and the second calibration body has three non-collinear second markers; The step of placing another calibration tool at a second position and establishing a second conversion relationship includes: Obtaining the second space coordinates of each second marker in the camera coordinate system; wherein the three second markers correspond to a total of three second space coordinates; A second transformation relationship is constructed based on the three second space coordinates.
[0045] Based on the above, the three second markers can form a unique plane in space, thereby enabling better acquisition of the second conversion relationship.
[0046] Wherein, the second conversion relationship includes a second rotation relationship and a second translation relationship; The constructing of the second conversion relationship based on the three second space coordinates includes: Selecting one of the three second space coordinates as the origin of the second coordinate system; Taking the direction from one of the three second space coordinates to the second of the three second space coordinates as the X-axis direction of the second coordinate system, obtaining a unit vector in the X-axis direction of the second coordinate system; Taking the direction from one of the three second space coordinates to the third of the three second space coordinates as the temporary Y-axis direction of the second coordinate system, obtaining a unit vector of the temporary Y-axis direction of the second coordinate system; Obtain a unit vector in the Z-axis direction of the second coordinate system based on the unit vector in the X-axis direction of the second coordinate system and the unit vector in the temporary Y-axis direction of the second coordinate system; Obtain a unit vector in the Y-axis direction of the second coordinate system based on the unit vector in the X-axis direction of the second coordinate system and the unit vector in the Z-axis direction of the second coordinate system; Constructing a second rotation relationship based on the unit vector in the X-axis direction of the second coordinate system, the unit vector in the Y-axis direction of the second coordinate system, and the unit vector in the Z-axis direction of the second coordinate system; A second translation relationship is constructed based on the one of the three second space coordinates.
[0047] Based on the above, the second rotation relationship and the second translation relationship can be preferably obtained.
[0048] It can be understood that the second rotation relationship Relationship with the second translation The construction and first rotation relationship and the first translation relationship The construction process is the same as that of , and will not be described in detail in this embodiment.
[0049] In this embodiment, the third conversion relationship is constructed based on the first coordinate system and the second coordinate system, including: An offset between the one of the three first space coordinates and the one of the three second space coordinates is obtained, and a third conversion relationship is constructed based on the offset.
[0050] Based on the above, the corresponding relationship between the origin of the first coordinate system and the origin of the second coordinate system can be preferably obtained, so that the relationship between the first coordinate system and the second coordinate system can be better constructed.
[0051] It can be understood that the third transformation relationship is also a transformation relationship of spatial position, so it can also be represented by rotation and translation, that is, the third transformation relationship includes the third rotation relationship and the second translation relationship ; More specifically, For any point in the first region, its coordinates in the first coordinate system are , whose coordinates in the camera coordinate system are , then there is, ; For any point in the second region, its coordinates in the first coordinate system are , whose coordinates in the robot coordinate system are , then there is, ; When any point at the second region has a corresponding relationship with any point at the first region, then there exists, ; Based on the above conversion relationship, we can better obtain and The conversion relationship between them is obtained, and then the pose transformation matrix between the camera coordinate system and the robot coordinate system is obtained.
[0052] It can be understood that the first area is used to place the template workpiece, and the second area is used to place the workpiece to be processed. The template workpiece and the workpiece to be processed are workpieces of the same size and model. In actual application scenarios, the first working end of the posture trajectory recording handle will draw a first working trajectory along the position of the template workpiece to be processed. Based on the first working trajectory, a second working trajectory can be generated, and the second working end of the robot will operate according to the second working trajectory. During this process, it is necessary to ensure that the second working trajectory fits the processing position of the workpiece to be processed; that is, the third conversion relationship is related to the spatial posture of the calibration tooling at the first position and the second position, as well as the spatial position relationship between the first position and the second position and the template workpiece and the required placement position of the workpiece to be processed, and the spatial position relationship between the first calibration body and the second calibration body.
[0053] To simplify the process of constructing the third conversion relationship, in this embodiment, the first calibration fixture and the second calibration fixture can be different calibration fixtures, and the triangle formed by the three first markers and the triangle formed by the three second markers are congruent triangles. This allows the calculation of the third conversion relationship to be omitted by placing the first calibration fixture and the second calibration fixture in corresponding positions in the same posture.
[0054] However, considering the objective fact that manual errors are inevitable in actual operation, in this embodiment, the first calibration fixture and the second calibration fixture are the same calibration fixture, and the three first markers and the three second markers are all placed on the same calibration fixture. This ensures that the relative positional relationship between the first markers and the second markers is fixed, thereby effectively reducing operational errors.
[0055] Furthermore, the present invention also aims to provide an electronic device comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor. The instructions are executed by the at least one processor to enable the at least one processor to perform the above-mentioned hand-eye calibration method.
[0056] In addition, an object of the present invention is to provide a computer program product, which includes a computer program, and when the computer program is executed by a processor, it implements the above-mentioned hand-eye calibration method.
[0057] The above is a schematic description of the present invention and its embodiments, which is not restrictive. The drawings show only one embodiment of the present invention, and the actual structure is not limited thereto. Therefore, if a person skilled in the art is inspired by this and, without departing from the purpose of the present invention, designs a structure and embodiment similar to this technical solution without inventiveness, they shall fall within the scope of protection of the present invention.
Claims
1. The hand-eye calibration method between the camera coordinate system and the robot coordinate system includes: A calibration tool is placed at a first position to establish a first conversion relationship; wherein the first position is located in a first area, the first area is the image acquisition area of the camera, and the first conversion relationship is a mapping relationship between a first coordinate system where the image acquisition area is located and the camera coordinate system; Placing another calibration tool at a second position to establish a second conversion relationship; wherein the second position is located in a second area, the second area is the executable area of the robot, and the second conversion relationship is a mapping relationship between a second coordinate system where the second area is located and the robot coordinate system; Based on the first coordinate system and the second coordinate system, a third conversion relationship is constructed; wherein the third conversion relationship is a mapping relationship between the first position and the second position; Based on the first transformation relationship, the second transformation relationship and the third transformation relationship, a pose transformation matrix between the camera coordinate system and the robot coordinate system is obtained.
2. The hand-eye calibration method according to claim 1, wherein: The calibration tool has a first calibration body, and the first calibration body has three non-collinear first markers; The step of placing a calibration tool at a first position and establishing a first conversion relationship includes: Obtaining the first spatial coordinates of each first marker in the camera coordinate system; wherein the three first markers correspond to a total of three first spatial coordinates; A first transformation relationship is constructed based on the three first space coordinates.
3. The hand-eye calibration method according to claim 2, wherein: The first conversion relationship includes a first rotation relationship and a first translation relationship; The constructing of the first conversion relationship based on the three first space coordinates includes: Selecting one of the three first space coordinates as the origin of the first coordinate system; Taking the direction from one of the three first space coordinates to the second of the three first space coordinates as the X-axis direction of the first coordinate system, obtaining a unit vector in the X-axis direction of the first coordinate system; Taking the direction from one of the three first space coordinates to the third of the three first space coordinates as the temporary Y-axis direction of the first coordinate system, obtaining a unit vector of the temporary Y-axis direction of the first coordinate system; Obtain a unit vector in the Z-axis direction of the first coordinate system based on the unit vector in the X-axis direction of the first coordinate system and the unit vector in the temporary Y-axis direction of the first coordinate system; Obtain a unit vector in the Y-axis direction of the first coordinate system based on the unit vector in the X-axis direction of the first coordinate system and the unit vector in the Z-axis direction of the first coordinate system; Constructing a first rotation relationship based on a unit vector in the X-axis direction of the first coordinate system, a unit vector in the Y-axis direction of the first coordinate system, and a unit vector in the Z-axis direction of the first coordinate system; A first translation relationship is constructed based on the one of the three first space coordinates.
4. The hand-eye calibration method according to claim 3, wherein: The other calibration tool has a second calibration body, and the second calibration body has three second markers that are not collinear; The step of placing another calibration tool at a second position and establishing a second conversion relationship includes: Obtaining the second space coordinates of each second marker in the camera coordinate system; wherein the three second markers correspond to a total of three second space coordinates; A second transformation relationship is constructed based on the three second space coordinates.
5. The hand-eye calibration method according to claim 4, characterized in that: The second conversion relationship includes a second rotation relationship and a second translation relationship; The constructing of the second conversion relationship based on the three second space coordinates includes: Selecting one of the three second space coordinates as the origin of the second coordinate system; Taking the direction from one of the three second space coordinates to the second of the three second space coordinates as the X-axis direction of the second coordinate system, obtaining a unit vector in the X-axis direction of the second coordinate system; Taking the direction from one of the three second space coordinates to the third of the three second space coordinates as the temporary Y-axis direction of the second coordinate system, obtaining a unit vector of the temporary Y-axis direction of the second coordinate system; Obtain a unit vector in the Z-axis direction of the second coordinate system based on the unit vector in the X-axis direction of the second coordinate system and the unit vector in the temporary Y-axis direction of the second coordinate system; Obtain a unit vector in the Y-axis direction of the second coordinate system based on the unit vector in the X-axis direction of the second coordinate system and the unit vector in the Z-axis direction of the second coordinate system; Constructing a second rotation relationship based on the unit vector in the X-axis direction of the second coordinate system, the unit vector in the Y-axis direction of the second coordinate system, and the unit vector in the Z-axis direction of the second coordinate system; A second translation relationship is constructed based on the one of the three second space coordinates.
6. The hand-eye calibration method according to claim 5, characterized in that: The constructing of the third conversion relationship based on the first coordinate system and the second coordinate system includes: An offset between the one of the three first space coordinates and the one of the three second space coordinates is obtained, and a third conversion relationship is constructed based on the offset.
7. The hand-eye calibration method according to claim 6, wherein: The one calibration tool and the other calibration tool are different calibration tools, and the triangle formed by the three first markers and the triangle formed by the three second markers are congruent triangles.
8. The hand-eye calibration method according to claim 7, wherein: The one calibration tool and the other calibration tool are the same calibration tool, and the three first markers and the three second markers are all set on the same calibration tool.
9. An electronic device comprising: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the hand-eye calibration method according to any one of claims 1 to 8.
10. A computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the computer program implements the hand-eye calibration method according to any one of claims 1 to 8.