Sensor visual calibration method based on Qt and ROS

Abstract

The invention relates to the field of automatic service, in particular to a sensor visual calibration method based on Qt and ROS, which comprises the following steps: creating a visual user interface by using a Qt framework, and designing a layout manager to realize an interactive control; creating a publisher node, and sending data or a control instruction to other ROS nodes; the point cloud data and the laser scanning data are preprocessed, and point cloud feature extraction is carried out by using a point cloud radius filtering algorithm and a developed point cloud feature extraction algorithm; processing and analyzing the point cloud data to realize calculation of an affine transformation matrix; inputting transformation parameters, and automatically calculating a corresponding affine transformation matrix; point cloud data are updated in real time, parameter values and changes of corresponding point cloud are displayed, and accurate fusion and efficient processing of laser radar and camera data are realized by integrating user interface design of a Qt framework, multi-sensor data fusion capability of ROS, advanced point cloud processing technology of PCL and high-performance three-dimensional visualization function of VTK.

Description

Technical Field

[0001] The present invention relates to the field of automated services, and in particular to a sensor visualization calibration method based on Qt and ROS. Background Art

[0002] In the field of hotel automation services, the efficient operation of luggage delivery robots depends on the accuracy of sensor data. Despite significant progress in sensor technology, existing sensor calibration methods still have deficiencies in accuracy, ease of operation, environmental adaptability, real-time processing capabilities, and hardware dependence. These limiting factors affect the navigation accuracy and operational efficiency of robots in complex hotel environments. In order to address these issues, the present invention proposes an innovative sensor visualization calibration tool, which aims to address the deficiencies of existing sensor calibration methods in terms of accuracy, ease of operation, environmental adaptability, real-time processing capabilities, and hardware dependence. By adopting advanced data processing technology, the calibration accuracy is improved, the calibration process is simplified, and the flexibility and real-time performance of the calibration are enhanced. Summary of the invention

[0003] The object of the present invention is to provide a sensor visualization calibration method based on Qt and ROS to solve the problems raised in the above background technology.

[0004] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0005] A sensor visualization calibration method based on Qt and ROS, applied to a baggage delivery robot, includes:

[0006] S100. Use the Qt framework to create intuitive user interfaces and design layout managers to implement interactive controls;

[0007] S200, using the node and topic mechanism of ROS, create a subscriber node; and create a publisher node to send data or control instructions to other ROS nodes;

[0008] S300, acquiring point cloud and laser scanning data from the sensor, preprocessing the point cloud data and the laser scanning data respectively, and performing point cloud feature extraction using a point cloud radius filtering algorithm and a developed point cloud feature extraction algorithm;

[0009] S400, integrated with Eigen library, processes and analyzes point cloud data to realize the calculation of affine transformation matrix; provides an interface to allow users to change transformation parameters through the user interface and automatically calculate the corresponding affine transformation matrix;

[0010] S500, based on the calculation of the affine transformation matrix, the point cloud data is updated in real time and the changes of the parameter values ​​and the corresponding point clouds are displayed.

[0011] Preferably, S100 comprises:

[0012] S101. Create intuitive user interfaces using the Qt framework.

[0013] S102. Design a layout manager to organize interface elements and ensure the adaptability of the interface under different resolutions and screen sizes;

[0014] S103: Set interactive controls, including buttons, text boxes, and scroll bars.

[0015] Preferably, S200 includes:

[0016] S201, creating a subscriber node for receiving point cloud and laser scanning data from a sensor;

[0017] S202, using the callback function to process the received data, including parsing, filtering and converting the data;

[0018] S203: Create a publisher node for sending processed data or control instructions to other ROS nodes.

[0019] Preferably, S300 includes:

[0020] S301, pre-processing point cloud data and laser scanning data, integrating PCL library for data loading, processing and saving;

[0021] The preprocessing of the point cloud data includes: standardizing and normalizing the point cloud data, and using the PCL library to store and manage the point cloud data to ensure efficient access and update of the data;

[0022] The preprocessing of the laser scanning data includes: converting the original laser scanning data into a point cloud format and merging the data from multiple sensors into a unified point cloud representation; receiving, converting and fusing the laser scanning data;

[0023] S302, using a point cloud radius filtering algorithm to remove noise and outliers;

[0024] S303, identifying and extracting key geometric features from the point cloud data using a point cloud feature extraction algorithm;

[0025] The point cloud feature extraction algorithm includes: preprocessing of point cloud data, geometric feature extraction, topological feature extraction, shape feature extraction, feature description and feature matching recognition, so as to facilitate subsequent point cloud analysis and processing.

[0026] Preferably, S302, using a point cloud radius filtering algorithm to remove noise and outliers, includes:

[0027] S3.1, set the filter radius radius and the neighborhood point set threshold K;

[0028] S3.2, based on the set radius radius and the neighborhood point set threshold K, read a certain point cloud data, and determine the number of neighboring points within the set radius: when the number of neighboring points is less than the minimum number of neighboring points in the neighborhood point set threshold K, the point cloud data is marked as a noise point; conversely, if the number of neighboring points is greater than the minimum number of neighboring points in the neighborhood point set threshold K, it is marked as a valid point;

[0029] S3.3, filter out noise points, retain valid points, and output the filtered point cloud.

[0030] Preferably, S400 includes:

[0031] S401, based on the filtered point cloud data, integrates the Eigen library for efficient mathematical operations;

[0032] S402, realizing the calculation of the affine transformation matrix, including translation, rotation and scaling operations;

[0033] S403: Provide an interface to allow the user to change transformation parameters through the user interface and automatically calculate the corresponding affine transformation matrix.

[0034] Preferably, S402, implementing calculation of an affine transformation matrix, including translation, rotation and scaling operations, comprises:

[0035] S4.1. Add a scroll bar control in the user interface to adjust key parameters of the point cloud and laser scanning data; the key parameters include the rotation matrix value R and the translation vector T to adjust the position of the point cloud;

[0036] S4.2. Obtain the matrix Rx rotating around the X axis respectively: in The matrix Ry for rotation around the Y axis: in And the matrix Rz of rotation around the Z axis: in

[0037] Then the total rotation matrix is ​​obtained: R = R z R y R x , and the translation vector:

[0038] S4.3. Confirm the affine transformation matrix based on the total rotation matrix R and translation vector T

[0039] Preferably, S500 includes:

[0040] S501, displaying the transformation parameters input by the user through the user interface, and updating the point cloud data in real time based on the calculation of the transformation parameters and the affine transformation matrix;

[0041] S502. Use PCL visualization tools to create a dynamic point cloud view;

[0042] S503, based on the interactive operation of the point cloud view, the user can observe the point cloud data from different angles;

[0043] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps in the above-mentioned sensor visualization calibration method based on Qt and ROS.

[0044] A computer device comprises a memory, a processor and a computer program stored in the memory and executable on the processor. When the processor executes the program, the steps in the above-mentioned sensor visualization calibration method based on Qt and ROS are implemented.

[0045] Compared with the prior art, the beneficial effects achieved by the present invention are:

[0046] The present invention realizes the accurate fusion and efficient processing of lidar and camera data by integrating the efficient user interface design of the Qt framework, the multi-sensor data fusion capability of ROS, the advanced point cloud processing technology of PCL, and the high-performance 3D visualization function of VTK. The present invention can provide richer and more dynamic 3D data visualization, enhancing the user's understanding and analysis capabilities of complex data sets. In addition, the tool reduces the need for manual intervention and enhances the friendliness of the user interface. Through real-time data processing and modular design, the present invention not only improves the response speed and scalability of the system, but also demonstrates its wide application potential and academic value in the field of autonomous driving and robotics through the effective use of open source frameworks and the optimization of hardware resources. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0048] Figure 1 It is a flow chart of a sensor visualization calibration method based on Qt and ROS of the present invention;

[0049] Figure 2 is a principle flow chart of the point cloud radius filtering algorithm in Embodiment 1 of the present invention;

[0050] Figure 3 is a principle flow chart of the point cloud feature extraction algorithm in Example 1 of the present invention;

[0051] Figure 4 It is the Qt GUI window design diagram in Example 2 of the present invention;

[0052] Figure 5 is a real-time update diagram of the transformation matrix in Embodiment 2 of the present invention;

[0053] Figure 6 This is a real-time update diagram of point cloud visualization in Example 2 of the present invention. DETAILED DESCRIPTION

[0054] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0055] See also Figure 1-Figure 6 , the present invention provides a technical solution:

[0056] Embodiment 1:

[0057] A sensor visualization calibration method based on Qt and ROS, applied to a baggage delivery robot, includes:

[0058] S100. Use the Qt framework to create intuitive user interfaces and design layout managers to implement interactive controls;

[0059] S200, using the node and topic mechanism of ROS, create a subscriber node; and create a publisher node to send data or control instructions to other ROS nodes;

[0060] S300, acquiring point cloud and laser scanning data from the sensor, preprocessing the point cloud data and the laser scanning data respectively, and performing point cloud feature extraction using a point cloud radius filtering algorithm and a developed point cloud feature extraction algorithm;

[0061] S400, integrated with Eigen library, processes and analyzes point cloud data to realize the calculation of affine transformation matrix; provides an interface to allow users to change transformation parameters through the user interface and automatically calculate the corresponding affine transformation matrix;

[0062] S500, based on the calculation of the affine transformation matrix, the point cloud data is updated in real time and the changes of the parameter values ​​and the corresponding point clouds are displayed.

[0063] Preferably, S100 comprises:

[0064] S101. Create intuitive user interfaces using the Qt framework.

[0065] S102. Design layout managers, such as QVBoxLayout and QGridLayout, to organize interface elements and ensure the adaptability of the interface to different resolutions and screen sizes;

[0066] S103, setting interactive controls, including buttons, text boxes and scroll bars, so that users can input parameters and control program flow.

[0067] Preferably, S200 includes:

[0068] S201, creating a subscriber node for receiving point cloud and laser scanning data from a sensor;

[0069] S202, using the callback function to process the received data, including parsing, filtering and converting the data;

[0070] The callback function mentioned above is a commonly used design pattern in programming, which allows the program to pass a function (called a callback function) as a parameter to another function. Introduction to the functions of callback functions: (1) Data parsing: The callback function can be used to parse data received from external sources (such as network requests, file reading, etc.). For example, parse JSON formatted data into objects or data structures that can be operated by the program. (2) Event processing: In event-driven programming, the callback function can be used as an event handler and be triggered when a specific event occurs. (3) Chain call: The callback function can be used to implement chain call of functions, that is, the output of one function becomes the input of another function. (4) Code reuse: By encapsulating common logic in callback functions, these logics can be reused in different contexts, improving the reusability of the code.

[0071] S203: Create a publisher node for sending processed data or control instructions to other ROS nodes.

[0072] Preferably, S300 includes:

[0073] S301, pre-processing point cloud data and laser scanning data, integrating PCL library for data loading, processing and saving;

[0074] The preprocessing of the point cloud data includes: standardizing and normalizing the point cloud data, and using the PCL library to store and manage the point cloud data to ensure efficient access and update of the data;

[0075] The preprocessing of the laser scanning data includes: converting the original laser scanning data into a point cloud format and merging the data from multiple sensors into a unified point cloud representation; receiving, converting and fusing the laser scanning data;

[0076] S302, using a point cloud radius filtering algorithm to remove noise and outliers;

[0077] S303, identifying and extracting key geometric features from the point cloud data using a point cloud feature extraction algorithm;

[0078] like Figure 3 As shown, the point cloud feature extraction algorithm includes: preprocessing of point cloud data, geometric feature extraction, topological feature extraction, shape feature extraction, feature description and feature matching recognition, so as to facilitate subsequent point cloud analysis and processing.

[0079] Preferably, Figure 2 As shown, S302, using a point cloud radius filtering algorithm to remove noise and outliers, including:

[0080] S3.1, set the filter radius radius and the neighborhood point set threshold K;

[0081] S3.2, based on the set radius radius and the neighborhood point set threshold K, read a certain point cloud data, and determine the number of neighboring points within the set radius: when the number of neighboring points is less than the minimum number of neighboring points in the neighborhood point set threshold K, the point cloud data is marked as a noise point; conversely, if the number of neighboring points is greater than the minimum number of neighboring points in the neighborhood point set threshold K, it is marked as a valid point;

[0082] S3.3, filter out noise points, retain valid points, and output the filtered point cloud;

[0083] Function of point cloud radius filtering algorithm: The point cloud radius filtering algorithm is mainly used to remove noise and outliers in point cloud data. During the point cloud data acquisition process, due to the limitations of the sensor or the influence of environmental factors, the data may contain some outliers or noise. If these noises are not processed, they will affect the accuracy and efficiency of subsequent point cloud data processing. By setting a search radius, the algorithm can identify outliers that do not have enough neighboring points within the radius and remove them from the point cloud. This will result in a cleaner, denoised point cloud data, laying a good foundation for subsequent feature extraction and point cloud analysis.

[0084] Preferably, S400 includes:

[0085] S401, based on the filtered point cloud data, integrates the Eigen library for efficient mathematical operations;

[0086] The Eigen library is an advanced C++ library for linear algebra, matrix and vector operations, geometric transformations, etc. In point cloud data processing, the Eigen library is often used in the following aspects: Point cloud data structure: The Eigen library provides a variety of data structures, such as Eigen::Matrix and Eigen::Vector, for storing and manipulating point cloud data. Geometric transformation: The Eigen library can easily define and apply affine transformation matrices, which is essential for operations such as translation, rotation, and scaling of point clouds. Feature extraction: In point cloud feature extraction, the Eigen library is used to calculate the covariance matrix of the point cloud, principal component analysis (PCA), etc., to extract features such as normals and curvatures of the point cloud;

[0087] S402, realizing the calculation of the affine transformation matrix, including translation, rotation and scaling operations;

[0088] S403, providing an interface to allow the user to change the transformation parameters through the user interface and automatically calculate the corresponding affine transformation matrix;

[0089] For example, if the user inputs a translation distance, the translation affine transformation matrix can be generated; if the user inputs a rotation angle, the rotation affine transformation matrix can be generated; if the user inputs a scaling ratio, the scaling affine transformation matrix can be generated. By combining these basic transformation matrices, more complex affine transformations can be achieved. For example, if you rotate first and then translate, you can get the final affine transformation matrix by multiplying the rotation matrix and the translation matrix.

[0090] Preferably, S402, implementing calculation of an affine transformation matrix, including translation, rotation and scaling operations, comprises:

[0091] S4.1. Add a scroll bar control in the user interface to adjust key parameters of the point cloud and laser scanning data; the key parameters include the rotation matrix value R and the translation vector T to adjust the position of the point cloud;

[0092] S4.2. Obtain the matrix Rx rotating around the X axis respectively: in The matrix Ry for rotation around the Y axis: in And the matrix Rz of rotation around the Z axis: in

[0093] Then the total rotation matrix is ​​obtained: R = R z R y R x , and the translation vector:

[0094] S4.3. Confirm the affine transformation matrix based on the total rotation matrix R and translation vector T

[0095] Preferably, S500 includes:

[0096] S501, displaying the transformation parameters input by the user through the user interface, and updating the point cloud data in real time based on the calculation of the transformation parameters and the affine transformation matrix;

[0097] S502, using a PCL visualization tool, such as PCLVisualizer, to create a dynamic point cloud view;

[0098] S503, interactive operations based on the point cloud view, such as rotation, scaling, translation, etc., enable the user to observe the point cloud data from different angles;

[0099] Embodiment 2:

[0100] Software features:

[0101] S1: Qt GUI window design, such as Figure 4 As shown;

[0102] S1.1: Use QMainWindow as the main window;

[0103] S1.2: Use QVBoxLayout and QGridLayout layout managers to organize interface elements;

[0104] S1.3: Create 6 scroll bars and labels to control the parameters of point cloud and laser scanning;

[0105] S1.4: Use QMdiArea and QMdiSubWindow to create a multiple document interface for displaying the point cloud view.

[0106] S2: Scroll bar event processing:

[0107] S2.1: Connect the valueChanged signal to the slot function for each scroll bar to update the parameter value and calculate the affine transformation matrix;

[0108] S2.2: Changes in parameter values ​​will update the label display in real time and output to the console, such as Figure 5 shown.

[0109] S3: Point cloud processing:

[0110] S3.1: Subscribe to point cloud data through ROS ( / camera_to_scan) and convert the message to point cloud format using PCL;

[0111] S3.2: Filter the point cloud to keep only points within a certain range;

[0112] S3.3: Update global point cloud data.

[0113] S4: Laser scanning processing:

[0114] S4.1: Subscribe to laser scanning data ( / scan) through ROS and convert it into 3D coordinate points;

[0115] S4.2: Update global laser data.

[0116] S5: Point cloud visualization:

[0117] S5.1: Use PCL's PCLVisualizer class to create a point cloud view;

[0118] S5.2: Create a thread (PointCloudUpdater) in which to apply the affine transformation matrix to the point cloud and update the view, e.g. Figure 6 As shown;

[0119] S5.3: Use QThread to ensure that point cloud update operations do not block Qt's main event loop.

[0120] S6: ROS node processing:

[0121] S6.1: Create a thread (SimpleThreadOne) and run the ROS event loop in this thread;

[0122] S6.2: Ensure that the ROS nodes are running normally and processing the subscribed data.

[0123] Embodiment 3:

[0124] The computer-readable storage medium of this embodiment stores a computer program thereon, and when the program is executed by a processor, the steps in the sensor visualization calibration method based on Qt and ROS in Embodiment 1 are implemented.

[0125] The computer-readable storage medium of this embodiment may be an internal storage unit of the terminal, such as a hard disk or memory of the terminal; the computer-readable storage medium of this embodiment may also be an external storage device of the terminal, such as a plug-in hard disk, a smart memory card, a secure digital card, a flash memory card, etc. equipped on the terminal; further, the computer-readable storage medium may also include both an internal storage unit of the terminal and an external storage device.

[0126] The computer-readable storage medium of this embodiment is used to store computer programs and other programs and data required by the terminal. The computer-readable storage medium can also be used to temporarily store data that has been output or is to be output.

[0127] Embodiment 4:

[0128] The computer device of this embodiment includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, the steps of a sensor visualization calibration method based on Qt and ROS in Embodiment 1 are implemented.

[0129] In this embodiment, the processor may be a central processing unit, or other general-purpose processors, digital signal processors, application-specific integrated circuits, readily available programmable gate arrays or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. The memory may include a read-only memory and a random access memory, and provide instructions and data to the processor. A portion of the memory may also include a non-volatile random access memory. For example, the memory may also store information about the device type.

[0130] Those skilled in the art will appreciate that the disclosed content of the embodiments may be provided as methods, systems, or computer program products. Therefore, the present solution may adopt the form of hardware embodiments, software embodiments, or embodiments combining software and hardware. Moreover, the present solution may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage and optical storage, etc.) containing computer-usable program codes.

[0131] The present solution is described with reference to the method according to the embodiment of the present solution and the flowchart and / or block diagram of the computer program product. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of the processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions; these computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 one or more processes and / or methods Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0132] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 one or more processes and / or methods Figure 1 A function specified in one or more boxes.

[0133] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 one or more processes and / or methods Figure 1 The steps for the functions specified in one or more boxes.

[0134] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing related hardware through a computer program, and the program can be stored in a computer-readable storage medium, and when the program is executed, it can include the processes of the embodiments of the above-mentioned methods. The storage medium can be a disk, an optical disk, a read-only memory (ROM) or a random access memory (RAM).

[0135] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A sensor visualization calibration method based on Qt and ROS, applied to baggage delivery robots, characterized by: The method comprises: S100. Use the Qt framework to create intuitive user interfaces and design layout managers to implement interactive controls; S200, using the node and topic mechanism of ROS, create a subscriber node; and create a publisher node to send data or control instructions to other ROS nodes; S300, acquiring point cloud and laser scanning data from the sensor, preprocessing the point cloud data and the laser scanning data respectively, and performing point cloud feature extraction using a point cloud radius filtering algorithm and a developed point cloud feature extraction algorithm; S400, integrated with Eigen library, processes and analyzes point cloud data to realize the calculation of affine transformation matrix; provides an interface to allow users to change transformation parameters through the user interface and automatically calculate the corresponding affine transformation matrix; S500, based on the calculation of the affine transformation matrix, the point cloud data is updated in real time and the changes of the parameter values ​​and the corresponding point clouds are displayed.

2. A sensor visualization calibration method based on Qt and ROS as claimed in claim 1, characterized in that: The S100 includes: S101. Create intuitive user interfaces using the Qt framework. S102. Design a layout manager to organize interface elements and ensure the adaptability of the interface under different resolutions and screen sizes; S103: Set interactive controls, including buttons, text boxes, and scroll bars.

3. A sensor visualization calibration method based on Qt and ROS as claimed in claim 1, characterized in that: The S200 includes: S201, creating a subscriber node for receiving point cloud and laser scanning data from a sensor; S202, using the callback function to process the received data, including parsing, filtering and converting the data; S203: Create a publisher node for sending processed data or control instructions to other ROS nodes.

4. A sensor visualization calibration method based on Qt and ROS as claimed in claim 1, characterized in that: The S300 includes: S301, pre-processing point cloud data and laser scanning data, integrating PCL library for data loading, processing and saving; The preprocessing of the point cloud data includes: standardizing and normalizing the point cloud data, and using the PCL library to store and manage the point cloud data to ensure efficient access and update of the data; The preprocessing of the laser scanning data includes: converting the original laser scanning data into a point cloud format and merging the data from multiple sensors into a unified point cloud representation; receiving, converting and fusing the laser scanning data; S302, using a point cloud radius filtering algorithm to remove noise and outliers; S303, identifying and extracting key geometric features from the point cloud data using a point cloud feature extraction algorithm; The point cloud feature extraction algorithm includes: preprocessing of point cloud data, geometric feature extraction, topological feature extraction, shape feature extraction, feature description and feature matching recognition, so as to facilitate subsequent point cloud analysis and processing.

5. A sensor visualization calibration method based on Qt and ROS as claimed in claim 4, characterized in that: The step S302, using a point cloud radius filtering algorithm to remove noise and outliers, includes: S3.1, set the filter radius radius and the neighborhood point set threshold K; S3.2, based on the set radius radius and the neighborhood point set threshold K, read a certain point cloud data, and determine the number of neighboring points within the set radius: when the number of neighboring points is less than the minimum number of neighboring points in the neighborhood point set threshold K, the point cloud data is marked as a noise point; conversely, if the number of neighboring points is greater than the minimum number of neighboring points in the neighborhood point set threshold K, it is marked as a valid point; S3.3, filter out noise points, retain valid points, and output the filtered point cloud.

6. A sensor visualization calibration method based on Qt and ROS as claimed in claim 1, characterized in that: The S400 includes: S401, based on the filtered point cloud data, integrates the Eigen library for efficient mathematical operations; S402, realizing the calculation of the affine transformation matrix, including translation, rotation and scaling operations; S403: Provide an interface to allow the user to change transformation parameters through the user interface and automatically calculate the corresponding affine transformation matrix.

7. A sensor visual calibration method based on Qt and ROS as claimed in claim 6, characterized in that: The step S402, implementing calculation of an affine transformation matrix, including translation, rotation and scaling operations, comprises: S4.

1. Add a scroll bar control in the user interface to adjust key parameters of the point cloud and laser scanning data; the key parameters include the rotation matrix value R and the translation vector T to adjust the position of the point cloud; S4.

2. Obtain the matrix Rx rotating around the X axis respectively: in The matrix Ry for rotation around the Y axis: in And the matrix Rz of rotation around the Z axis: in Then the total rotation matrix is ​​obtained: R = R z R y R x , and the translation vector: S4.

3. Confirm the affine transformation matrix based on the total rotation matrix R and translation vector T 8. The sensor visualization calibration method based on Qt and ROS as claimed in claim 1, characterized in that: The S500 comprises: S501, displaying the transformation parameters input by the user through the user interface, and updating the point cloud data in real time based on the calculation of the transformation parameters and the affine transformation matrix; S502. Use PCL visualization tools to create a dynamic point cloud view; S503: Based on the interactive operation of the point cloud view, the user can observe the point cloud data from different angles.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps in the sensor visualization calibration method based on Qt and ROS as described in any one of claims 1 to 8 are implemented.

10. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the steps in the sensor visualization calibration method based on Qt and ROS as described in any one of claims 1 to 9 are implemented.

Images