Workpiece grasping method, device and control system based on camera calibration

Abstract

The present application relates to a workpiece grasping method, device, control system and non-volatile computer-readable storage medium based on camera calibration, which obtains calibration information, performs parameter and matrix calculation processing on the feature points in the calibration information in different coordinate systems according to preset calibration steps, and obtains the camera calibration matrix; the origin of the user coordinate system of the robot arm and the xyz axis of the user coordinate system correspond to the origin of the calibration plate coordinate system and the xyz axis of the calibration plate, respectively, and calibrates and overlaps; obtains the transformation matrix of the workpiece in the base coordinate system, and transforms the point cloud in the input camera coordinate system according to the calibration matrix, obtains the transformation posture and performs the grasping action according to the transformation posture. The posture of the part to be grasped in the robot coordinate system can be switched to the user coordinate system of different workpiece platforms for grasping, which is efficient and has low processing cost, and can also be switched and calibrated for use.

Description

Technical Field

[0001] The present disclosure relates to the field of machine vision, and in particular to a workpiece grasping method, device, control system and non-volatile computer-readable storage medium based on camera calibration. Background Art

[0002] With the development of industrial robots and vision technology, it has become an inevitable trend to use industrial cameras and industrial robots to automatically grasp workpieces.

[0003] However, cameras have fixed physical and optical parameters when they leave the factory, such as the optical axis, far point, and coordinate system. Due to the camera's own errors and errors in the assembly process, a camera calibration process is usually required before use to obtain the camera parameters.

[0004] Current industrial cameras cannot adapt well to the camera calibration process during the robotic arm grasping process. Their calibration efficiency is low and they cannot be switched for calibration on different workpiece platforms. This requires additional matching of the robotic arm corresponding to the platform, which increases costs. Summary of the invention

[0005] In view of this, in order to solve the above technical problems, the present disclosure proposes a workpiece grasping method, device, control system and non-volatile computer-readable storage medium based on camera calibration.

[0006] According to one aspect of the present disclosure, a workpiece grasping method based on camera calibration is provided, comprising the following steps:

[0007] S100, obtaining calibration information, wherein the calibration information includes the origin of the calibration plate coordinate system and the xyz axis of the calibration plate;

[0008] S200, performing parameter and matrix calculation processing on the feature points in the calibration information in different coordinate systems according to a preset calibration step, and obtaining a camera calibration matrix;

[0009] S300, respectively correspond the origin of the user coordinate system of the robot arm and the xyz axis of the user coordinate system to the origin of the calibration plate coordinate system and the xyz axis of the calibration plate, and perform calibration and overlap;

[0010] S400, obtaining a transformation matrix of the workpiece in a base coordinate system, and transforming the point cloud in an input camera coordinate system according to the calibration matrix, obtaining a transformed posture, and performing a grasping action according to the transformed posture.

[0011] In a possible implementation, optionally, in step S200, performing parameter and matrix calculation processing in different coordinate systems on the feature points in the calibration information according to the preset calibration step, and obtaining a camera calibration matrix, includes:

[0012] S210, obtaining a calibration plate image, sequentially projecting structured light codes onto the calibration plate, and finding coordinates of feature points in the calibration plate image;

[0013] S220, decoding the projected structured light;

[0014] S230, calculating and obtaining the local unit matrix of the feature point coordinates, and using the local unit matrix to calculate the coordinates of the feature points on the projected image; changing the calibration plate posture, and repeating the above steps.

[0015] In a possible implementation, optionally, the method further includes:

[0016] S240. Utilize the coordinate systems of the feature points found in the camera and the projector to respectively calculate the camera intrinsic parameter matrix and the camera distortion coefficient and the projector intrinsic parameter matrix and the projector distortion coefficient; and calculate and obtain the camera calibration matrix based on the camera intrinsic parameter matrix and the camera distortion coefficient and the projector intrinsic parameter matrix and the projector distortion coefficient.

[0017] In a possible implementation, optionally, in step S400, obtaining a transformation matrix of the workpiece in a base coordinate system, transforming the point cloud in an input camera coordinate system according to the calibration matrix, acquiring a transformation pose, and performing a grasping action according to the transformation pose, includes:

[0018] S410, obtaining a transformation matrix of the object in the base coordinate system by using a preset chain rule;

[0019] S420, using a preset posture calibration process to obtain posture calibration information of the user coordinate system relative to the calibration board coordinate system;

[0020] S430: Acquire the posture calibration information, and perform a grasping action according to the posture calibration information.

[0021] According to another aspect of the present disclosure, there is also provided a device for executing the workpiece grasping method based on camera calibration, comprising a calibration information acquisition module, a camera calibration matrix processing module, a coordinate system calibration module and a posture transformation module, wherein:

[0022] Calibration information acquisition module: used to acquire calibration information, wherein the calibration information includes the origin of the calibration plate coordinate system and the xyz axis of the calibration plate;

[0023] The camera calibration matrix processing module is used to perform parameter and matrix calculation processing on the feature points in the calibration information in different coordinate systems according to the preset calibration steps, and obtain the camera calibration matrix;

[0024] Coordinate system calibration module: used to correspond the origin of the user coordinate system of the robot arm and the xyz axis of the user coordinate system to the origin of the calibration plate coordinate system and the xyz axis of the calibration plate, and perform calibration and coincidence;

[0025] Posture transformation module: used to obtain the transformation matrix of the workpiece in the base coordinate system, and transform the point cloud in the input camera coordinate system according to the calibration matrix, obtain the transformed posture and perform the grasping action according to the transformed posture.

[0026] In a possible implementation, optionally, the camera calibration matrix processing module includes:

[0027] Structured light projection module: used to obtain the calibration plate image, sequentially project the structured light code onto the calibration plate, and find the coordinates of the feature points in the calibration plate image;

[0028] Decoding module: used for decoding the projected structured light;

[0029] Projection coordinate calculation module: used to calculate the local unit matrix to obtain the coordinates of the feature points, and use the local unit matrix to calculate the coordinates of the feature points on the projected image; change the calibration plate posture and repeat the above steps.

[0030] In a possible implementation, optionally, the camera calibration matrix processing module further includes:

[0031] Calibration matrix calculation module: used to use the coordinate systems of the feature points found in the camera and projector to calculate the camera intrinsic parameter matrix and the camera distortion coefficient and the projector intrinsic parameter matrix and the projector distortion coefficient respectively, and calculate and obtain the camera calibration matrix based on the camera intrinsic parameter matrix and the camera distortion coefficient and the projector intrinsic parameter matrix and the projector distortion coefficient.

[0032] In a possible implementation, optionally, the posture transformation module includes a transformation matrix acquisition module, a posture calibration module and an execution module, wherein:

[0033] Transformation matrix acquisition module: used to obtain the transformation matrix of the object in the base coordinate system through the preset chain rule;

[0034] Position and attitude calibration module: used to obtain the position and attitude calibration information of the user coordinate system relative to the calibration board coordinate system by adopting the preset attitude calibration process;

[0035] Execution module: used to obtain the posture calibration information and perform a grasping action according to the posture calibration information.

[0036] According to another aspect of the present disclosure, there is also provided a control system, comprising:

[0037] processor;

[0038] a memory for storing processor-executable instructions;

[0039] Wherein, the processor is configured to implement the above-mentioned workpiece grasping method based on camera calibration when executing the executable instructions.

[0040] According to another aspect of the present disclosure, a non-volatile computer-readable storage medium is provided, on which computer program instructions are stored. When the computer program instructions are executed by a processor, the above-mentioned workpiece grasping method based on camera calibration is implemented.

[0041] Technical effects of this application:

[0042] The present invention obtains calibration information, performs parameter and matrix calculation processing on the feature points in the calibration information in different coordinate systems according to preset calibration steps, and obtains the camera calibration matrix; the origin of the user coordinate system of the robot arm and the xyz axis of the user coordinate system correspond to the origin of the calibration plate coordinate system and the xyz axis of the calibration plate, respectively, and calibrates and overlaps; obtains the transformation matrix of the workpiece in the base coordinate system, and transforms the point cloud in the input camera coordinate system according to the calibration matrix, obtains the transformation posture and performs the grasping action according to the transformation posture. The posture of the part to be grasped in the robot coordinate system can be switched to the user coordinate system of the corresponding platform for grasping, and the workpiece grasping on multiple different platforms can be realized by using a structured light camera and a robot arm, which is efficient and low in processing cost, and can also be switched and calibrated on different workpiece platforms.

[0043] Further features and aspects of the present disclosure will become apparent from the following detailed description of exemplary embodiments with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] The accompanying drawings, which are incorporated in and constitute a part of the specification, illustrate exemplary embodiments, features, and aspects of the disclosure and, together with the description, serve to explain the principles of the disclosure.

[0045] Figure 1 Shown is a schematic diagram of the implementation process of the workpiece grasping method based on camera calibration of the present invention. DETAILED DESCRIPTION

[0046] Various exemplary embodiments, features and aspects of the present disclosure will be described in detail below with reference to the accompanying drawings. The same reference numerals in the accompanying drawings represent elements with the same or similar functions. Although various aspects of the embodiments are shown in the accompanying drawings, the drawings are not necessarily drawn to scale unless otherwise specified.

[0047] The word “exemplary” is used exclusively herein to mean “serving as an example, example, or illustration.” Any embodiment described herein as “exemplary” is not necessarily to be construed as preferred or advantageous over other embodiments.

[0048] In addition, in order to better illustrate the present disclosure, numerous specific details are given in the following specific embodiments. It should be understood by those skilled in the art that the present disclosure can also be implemented without certain specific details. In some examples, methods, means, components and circuits well known to those skilled in the art are not described in detail in order to highlight the subject matter of the present disclosure.

[0049] Example 1

[0050] like Figure 1 As shown, according to one aspect of the present disclosure, a workpiece grasping method based on camera calibration is provided, comprising the following steps:

[0051] S100, obtaining calibration information, wherein the calibration information includes the origin of the calibration plate coordinate system and the xyz axis of the calibration plate;

[0052] The camera obtains calibration information by photographing the calibration plate, and sets the origin of the calibration plate coordinate system and the xyz axis under the camera on the calibration plate to obtain a transformation matrix. In specific implementation, the calibration plate can be photographed by a three-dimensional camera, and the origin of the calibration plate coordinate system and the xyz axis under the camera can be set on the calibration plate to obtain a calibration matrix.

[0053] S200, performing parameter and matrix calculation processing on the feature points in the calibration information in different coordinate systems according to a preset calibration step, and obtaining a camera calibration matrix;

[0054] The preset calibration steps, that is, the camera calibration steps are as follows:

[0055] When calibrating the camera, obtain the calibration plate image taken by the camera, keep the calibration plate still, and project the structured light codes onto the calibration plate in sequence;

[0056] Find the coordinates of the feature points in the calibration plate image;

[0057] Decode the projection result light captured by the camera;

[0058] Find the local identity matrix for the coordinates of the feature points in the calibration plate image found, and use the local identity matrix to calculate the coordinates of the feature points on the projected image;

[0059] Change the calibration plate posture and repeat the above steps;

[0060] Repeat the above steps at least three times, and use the coordinate systems of the found feature points in the camera and projector to calculate the camera intrinsic parameter matrix and distortion coefficient, the projector intrinsic parameter matrix and distortion coefficient, and obtain the camera calibration matrix.

[0061] S300, respectively correspond the origin of the user coordinate system of the robot arm and the xyz axis of the user coordinate system to the origin of the calibration plate coordinate system and the xyz axis of the calibration plate, and perform calibration and overlap;

[0062] The user coordinate system is a user-defined coordinate system. The robot can work with different workbenches or fixtures, and a user coordinate system is established on each workbench. The origin of the user coordinate system of the robot arm and the xyz axis are determined at the origin of the calibration plate, so that the origins and xyz axes of the two coordinate systems coincide; it is easy to obtain the transformation relationship between the coordinate systems, so as to achieve the posture transformation when executing the action.

[0063] The steps to calibrate the user coordinate system are as follows:

[0064] The first teaching point is the origin O of the user coordinate system, and the first teaching point is the origin of the calibration plate, so that the origins of the two coordinate systems coincide;

[0065] Teach a point on any xyz axis, for example, teach a point Px on the X axis, then the unit vector of the x axis of the user coordinate system is n = (P x -O) / norm(P x -O);

[0066] Teach a point on the remaining two axes, for example, teach a point Py on the Y axis, then the unit vector of the y axis of the user coordinate system is o=(P y -O) / norm(P y -O);

[0067] The z-axis unit vector of the user coordinate system is calculated to be a=n×o; that is, the established user coordinate system is:

[0068]

[0069] Among them, base is the base coordinate system and U is the user coordinate system.

[0070] S400, obtaining a transformation matrix of the workpiece in a base coordinate system, and transforming the point cloud in an input camera coordinate system according to the calibration matrix, obtaining a transformed posture, and performing a grasping action according to the transformed posture.

[0071] Each time you grab a workpiece in a different coordinate system, first find the transformation matrix of the object in the base coordinate system, and then transform the point cloud in the input camera coordinate system according to the calibration matrix; the transformation matrix can be directly read on the robot control system, and the transformation posture can be obtained according to the posture calibration steps set by the user. When performing the grab, the 6D posture result of the object is identified relative to the camera coordinate system. The posture of the part to be grabbed in the robot coordinate system, that is, the user coordinate system, can be obtained through the above calibration results. Transform the robot arm to the corresponding user coordinate system to complete the grabbing of the workpiece.

[0072] When grabbing workpieces on different platforms, the above obtains the position and posture of the part to be grabbed in the robot coordinate system, and then switches to the user coordinate system of the corresponding platform to grab the workpiece. A structured light camera plus a robotic arm can be used to grab workpieces on multiple different platforms. For a robot, the present invention can fix the camera on the robotic arm, and can realize the grabbing of workpieces on multiple platforms by transforming the calibration matrix.

[0073] In a possible implementation, optionally, in step S200, performing parameter and matrix calculation processing in different coordinate systems on the feature points in the calibration information according to the preset calibration step, and obtaining a camera calibration matrix, includes:

[0074] S210, obtaining a calibration plate image, sequentially projecting structured light codes onto the calibration plate, and finding coordinates of feature points in the calibration plate image;

[0075] S220, decoding the projected structured light;

[0076] S230, calculating and obtaining the local unit matrix of the feature point coordinates, and using the local unit matrix to calculate the coordinates of the feature points on the projected image; changing the calibration plate posture, and repeating the above steps.

[0077] See the above description of S200 for details.

[0078] In a possible implementation, optionally, the method further includes:

[0079] S240. Utilize the coordinate systems of the feature points found in the camera and the projector to respectively calculate the camera intrinsic parameter matrix and the camera distortion coefficient and the projector intrinsic parameter matrix and the projector distortion coefficient; and calculate and obtain the camera calibration matrix based on the camera intrinsic parameter matrix and the camera distortion coefficient and the projector intrinsic parameter matrix and the projector distortion coefficient.

[0080] See the above description of S200 for details.

[0081] In a possible implementation, optionally, in step S400, obtaining a transformation matrix of the workpiece in a base coordinate system, transforming the point cloud in an input camera coordinate system according to the calibration matrix, acquiring a transformation pose, and performing a grasping action according to the transformation pose, includes:

[0082] S410, obtaining a transformation matrix of the object in the base coordinate system by using a preset chain rule;

[0083] S420, using a preset posture calibration process to obtain posture calibration information of the user coordinate system relative to the calibration board coordinate system;

[0084] S430: Acquire the posture calibration information, and perform a grasping action according to the posture calibration information.

[0085] Each time you grab a workpiece in a different coordinate system, first find the transformation matrix of the object in the base coordinate system, and then transform the point cloud in the input camera coordinate system according to the calibration matrix;

[0086] The following chain rule can be used to obtain the transformation matrix of the object in the base coordinate system:

[0087]

[0088] in Can be read directly on the robot control system.

[0089] for The following steps are used for calibration

[0090] Preset a fixed point within the robot's working range;

[0091] Teach three pose points in an arbitrary posture so that the origin of the user coordinate system coincides with the fixed point;

[0092] Teach the fourth pose point in the same way, perpendicular to the fixed point;

[0093] Taking the fourth pose point as the starting point, move along the positive direction of the x-axis of the set user coordinate system without changing the pose, which is defined as the fifth pose point;

[0094] Taking the fifth pose point as the starting point, move along the positive direction of the z-axis of the set user coordinate system without changing the posture, which is defined as the sixth pose point.

[0095] The first four points are used for the origin of the user coordinate system. The other two points are used to calibrate the user coordinate system posture Then the pose of the user coordinate system relative to the calibration plate coordinate system is obtained as follows:

[0096]

[0097] for It can be calculated by hand-eye calibration method;

[0098] When performing a grasp, the 6D pose of the object is determined relative to the camera coordinate system. The above calibration results can be used to obtain the position and posture of the part to be grasped in the robot coordinate system, i.e., the user coordinate system.

[0099] The robot arm is transformed to the corresponding user coordinate system to complete the grasping of the workpiece. When grasping workpieces on different platforms, the above obtains the position and posture of the part to be grasped in the robot coordinate system, and then switches to the user coordinate system of the corresponding platform to grasp the workpiece. A structured light camera plus a robot arm is used to grasp workpieces on multiple different platforms.

[0100] It should be noted that although the above calibration information processing method is introduced by taking a three-dimensional camera and projected structured light as examples, those skilled in the art will understand that the present disclosure should not be limited thereto. In fact, users can flexibly set the acquisition tool according to personal preferences and / or actual application scenarios, as long as the calibration information can be obtained.

[0101] In this way, by obtaining the calibration information, the characteristic points in the calibration information are processed with parameters and matrices in different coordinate systems according to the preset calibration steps, and the camera calibration matrix is ​​obtained; the origin of the user coordinate system of the robot arm and the xyz axis of the user coordinate system are respectively corresponded to the origin of the calibration plate coordinate system and the xyz axis of the calibration plate, and the calibration coincidence is performed; the transformation matrix of the workpiece in the base coordinate system is obtained, and the point cloud in the input camera coordinate system is transformed according to the calibration matrix, the transformation posture is obtained, and the grasping action is performed according to the transformation posture. The posture of the part to be grasped in the robot coordinate system can be switched to the user coordinate system of the corresponding platform for grasping, and the workpiece on multiple different platforms can be grasped by a structured light camera plus a robot arm, which is efficient and low in processing cost, and can also be switched and calibrated for use on different workpiece platforms.

[0102] Example 2

[0103] Based on the technical implementation principle of Example 1, this embodiment correspondingly provides a device to implement the workpiece grasping method based on camera calibration.

[0104] According to another aspect of the present disclosure, there is also provided a device for executing the workpiece grasping method based on camera calibration, comprising a calibration information acquisition module, a camera calibration matrix processing module, a coordinate system calibration module and a posture transformation module, wherein:

[0105] Calibration information acquisition module: used to acquire calibration information, wherein the calibration information includes the origin of the calibration plate coordinate system and the xyz axis of the calibration plate;

[0106] The calibration information acquisition module includes a three-dimensional camera and a structured light projection device, and the calibration information can be collected according to the steps and methods of Example 1.

[0107] The camera calibration matrix processing module is used to perform parameter and matrix calculation processing on the feature points in the calibration information in different coordinate systems according to the preset calibration steps, and obtain the camera calibration matrix;

[0108] Coordinate system calibration module: used to correspond the origin of the user coordinate system of the robot arm and the xyz axis of the user coordinate system to the origin of the calibration plate coordinate system and the xyz axis of the calibration plate, and perform calibration and coincidence;

[0109] Posture transformation module: used to obtain the transformation matrix of the workpiece in the base coordinate system, and transform the point cloud in the input camera coordinate system according to the calibration matrix, obtain the transformed posture and perform the grasping action according to the transformed posture.

[0110] In a possible implementation, optionally, the camera calibration matrix processing module includes:

[0111] Structured light projection module: used to obtain the calibration plate image, sequentially project the structured light code onto the calibration plate, and find the coordinates of the feature points in the calibration plate image;

[0112] Decoding module: used for decoding the projected structured light;

[0113] Projection coordinate calculation module: used to calculate the local unit matrix to obtain the coordinates of the feature points, and use the local unit matrix to calculate the coordinates of the feature points on the projected image; change the calibration plate posture and repeat the above steps.

[0114] In a possible implementation, optionally, the camera calibration matrix processing module further includes:

[0115] Calibration matrix calculation module: used to use the coordinate systems of the feature points found in the camera and projector to calculate the camera intrinsic parameter matrix and the camera distortion coefficient and the projector intrinsic parameter matrix and the projector distortion coefficient respectively, and calculate and obtain the camera calibration matrix based on the camera intrinsic parameter matrix and the camera distortion coefficient and the projector intrinsic parameter matrix and the projector distortion coefficient.

[0116] In a possible implementation, optionally, the posture transformation module includes a transformation matrix acquisition module, a posture calibration module and an execution module, wherein:

[0117] Transformation matrix acquisition module: used to obtain the transformation matrix of the object in the base coordinate system through the preset chain rule;

[0118] Position and attitude calibration module: used to obtain the position and attitude calibration information of the user coordinate system relative to the calibration board coordinate system by adopting the preset attitude calibration process;

[0119] Execution module: used to obtain the posture calibration information and perform a grasping action according to the posture calibration information.

[0120] Obviously, those skilled in the art should understand that the above modules or steps of the present invention can be implemented by a general computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, and optionally, they can be implemented by a program code executable by a computing device, so that they can be stored in a storage device and executed by the computing device, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present invention is not limited to any specific combination of hardware and software.

[0121] Example 3

[0122] Furthermore, according to another aspect of the present disclosure, a control system is provided, comprising:

[0123] processor;

[0124] a memory for storing processor-executable instructions;

[0125] Wherein, the processor is configured to implement the above-mentioned workpiece grasping method based on camera calibration when executing the executable instructions.

[0126] The control system of the embodiment of the present disclosure includes a processor and a memory for storing processor executable instructions, wherein the processor is configured to implement any of the above-mentioned workpiece grasping methods based on camera calibration when executing the executable instructions.

[0127] Here, it should be noted that the number of processors can be one or more. At the same time, in the control system of the embodiment of the present disclosure, an input device and an output device may also be included. Among them, the processor, memory, input device and output device may be connected through a bus or in other ways, which are not specifically limited here.

[0128] The memory, as a computer-readable storage medium for a workpiece grasping method based on camera calibration, can be used to store software programs, computer executable programs, and various modules, such as: a program or module corresponding to a workpiece grasping method based on camera calibration in an embodiment of the present disclosure. The processor executes various functional applications and data processing of the control system by running the software programs or modules stored in the memory.

[0129] The input device can be used to receive input numbers or signals. The signal can be a key signal related to user settings and function control of the device / terminal / server. The output device can include a display device such as a display screen.

[0130] Example 4

[0131] According to another aspect of the present disclosure, a non-volatile computer-readable storage medium is provided, on which computer program instructions are stored. When the computer program instructions are executed by a processor, the above-mentioned workpiece grasping method based on camera calibration is implemented.

[0132] As a computer-readable storage medium for a workpiece grasping method based on camera calibration, a non-volatile computer-readable storage medium can be used to store software programs, computer executable programs, and various modules, such as: a program or module corresponding to a workpiece grasping method based on camera calibration in an embodiment of the present disclosure. The processor executes various functional applications and data processing of the control system by running the software program or module stored in the memory.

[0133] The embodiments of the present disclosure have been described above, and the above description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The selection of terms used herein is intended to best explain the principles of the embodiments, practical applications, or technical improvements to the technology in the market, or to enable other persons of ordinary skill in the art to understand the embodiments disclosed herein.

Claims

1. A workpiece grasping method based on camera calibration, characterized in that: The steps include: S100, obtaining calibration information, wherein the calibration information includes the origin of the calibration plate coordinate system and the xyz axis of the calibration plate; S200, performing parameter and matrix calculation processing on the feature points in the calibration information in different coordinate systems according to a preset calibration step, and obtaining a camera calibration matrix; S300, respectively correspond the origin of the user coordinate system of the robot arm and the xyz axis of the user coordinate system to the origin of the calibration plate coordinate system and the xyz axis of the calibration plate, and perform calibration and overlap; Through steps S410-S430, the transformed posture is acquired and the action of grasping the workpiece is performed according to the transformed posture; In step S200, the parameter and matrix calculation processing of the feature points in the calibration information in different coordinate systems is performed according to the preset calibration steps, and the camera calibration matrix is ​​obtained, including: S210, obtaining a calibration plate image, sequentially projecting structured light codes onto the calibration plate, and finding coordinates of feature points in the calibration plate image; S220, decoding the projected structured light; S230, calculating and obtaining the local unit matrix of the feature point coordinates, and using the local unit matrix to calculate the coordinates of the feature points on the projected image; changing the calibration plate posture, and repeating the above steps; Obtaining a transformed posture and performing a grasping action according to the transformed posture, including: S410, obtaining a transformation matrix of the object in the base coordinate system by using a preset chain rule; S420, using a preset posture calibration process to obtain posture calibration information of the user coordinate system relative to the calibration board coordinate system; S430, acquiring the posture calibration information, and performing a grasping action according to the posture calibration information; The user coordinate system is a user-defined coordinate system. The robot arm works with different workbenches or fixtures. A user coordinate system is established on each workbench. The origin of the user coordinate system of the robot arm and the xyz axis are determined on the origin of the calibration plate so that the origins and xyz axes of the two coordinate systems coincide. The transformation relationship between the coordinate systems is obtained to realize the posture transformation of the robot arm when performing an action. The steps to calibrate the user coordinate system are as follows: The first teaching point is the origin O of the user coordinate system, and the first teaching point is the origin of the calibration plate, so that the origins of the two coordinate systems coincide; If a point Px is taught on any xyz axis, the x-axis unit vector of the user coordinate system is n=(P x -O) / norm(P x -O); Teach a point Py on the remaining two axes, then the unit vector of the y-axis of the user coordinate system is o=(P y -O) / norm(P y -O); The z-axis unit vector a of the user coordinate system is calculated to be a=n×o; the established user coordinate system is: Among them, base is the base coordinate system and U is the user coordinate system.

2. A workpiece grasping method based on camera calibration according to claim 1, characterized in that: Also includes: S240. Utilize the coordinate systems of the feature points found in the camera and the projector to respectively calculate the camera intrinsic parameter matrix and the camera distortion coefficient and the projector intrinsic parameter matrix and the projector distortion coefficient; and calculate and obtain the camera calibration matrix based on the camera intrinsic parameter matrix and the camera distortion coefficient and the projector intrinsic parameter matrix and the projector distortion coefficient.

3. A workpiece grasping device based on camera calibration, characterized in that: The device executes the method according to claim 1 or 2.

4. A control system, characterized in that: include: processor; a memory for storing processor-executable instructions; Wherein, the processor is configured to implement the workpiece grasping method based on camera calibration described in claim 1 or 2 when executing the executable instructions.

5. A non-volatile computer-readable storage medium having computer program instructions stored thereon, characterized in that: When the computer program instructions are executed by a processor, the workpiece grasping method based on camera calibration according to claim 1 or 2 is implemented.

Images