Laser calibration method, device and system for rotary dining table and medium
By setting geometric feature marking blocks on the rotating dining table and adjusting the lidar coordinate system, the problems of complex calibration, high hardware requirements and limited accuracy in the prior art are solved, and accurate calibration and action recognition of the rotating dining table are achieved.
Patent Information
- Application Number
- CN202411383615.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-30
- Publication Date
- 2024-12-27
AI Technical Summary
The existing linear laser profile instrument point cloud calibration method is complex, has high hardware requirements, is limited in accuracy and is susceptible to the environment, resulting in the inability to accurately identify the movements on the dining table and the inability to achieve accurate calibration.
Set marking blocks with geometric features on the edge of the rotating dining table. Point cloud data is collected through lidar, the raised trajectory of the marking block is identified, the lidar coordinate system is adjusted, and it is aligned with the dining table coordinate system is automatically corrected to ensure accurate identification of the dining table. on the action.
The calibration process is simplified, the hardware cost is reduced, the calibration accuracy and stability is improved, and the lidar can accurately identify the movements on the dining table and adapt to different environments.
Smart Images
Figure CN119199807A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of data processing technology, and in particular to a laser calibration method, device, system and medium for a rotating dining table. Background Art
[0002] With the rapid development of science and technology, line laser profilers have been widely used in industrial automation, quality inspection and other fields. However, since the horizontality of the laser emitted by the laser is reduced after amplification, and there are theoretically uneliminable distortions in the transmitting lens and the receiving lens, there are large errors in the target point cloud and low detection accuracy. In order to solve this problem, a line laser profiler point cloud calibration method and system based on a plane calibration block have appeared in the prior art. However, although this method improves the detection accuracy to a certain extent, it still has the following disadvantages.
[0003] The calibration process is complicated: The point cloud calibration method of the line laser profiler based on the plane calibration block requires multiple steps for calibration, including adjusting the level of the line laser profiler, collecting the height calibration data and X-direction calibration data of the calibration block, calculating the row pixel position information of the light strip and the pixel equivalent of each row, etc. These steps are not only cumbersome, but also require professional operation, which increases the difficulty and cost of operation.
[0004] High hardware requirements: This method requires the use of a specific plane calibration block, and the upper and lower parts of the calibration block need to have different colors or texture features to facilitate the line laser profiler to identify and collect data. This specific calibration block increases the hardware cost and limits the scope of application of this method.
[0005] Limited calibration accuracy: Although the point cloud calibration method of the line laser profiler based on the plane calibration block can improve the detection accuracy to a certain extent, its calibration accuracy is still limited due to factors such as laser distortion and lens error. In applications requiring high-precision detection, this method may not meet the requirements.
[0006] Susceptible to environmental influences: During the calibration process, changes in environmental factors such as temperature, humidity, and light may affect the calibration results. Especially in industrial production environments, the changes in these environmental factors are more complex and unpredictable, which may lead to reduced stability and reliability of the calibration results.
[0007] Therefore, it is necessary to solve the problem that the movements on the dining table cannot be accurately identified due to differences in installation height or tilt angle, resulting in inaccurate calibration. Summary of the invention
[0008] In view of this, the purpose of the embodiments of the present invention is to provide a laser calibration method, device, system and medium for a rotating dining table to solve one or more technical problems existing in the prior art and provide at least one beneficial option or create conditions.
[0009] On the one hand, an embodiment of the present invention provides a laser calibration method for a rotating dining table, the method comprising the following steps: A marking block with geometric features is arranged at the edge of the rotating dining table, and the marking block is used as a reference point of the laser radar during the rotation of the dining table; Starting the rotation function of the rotating dining table to make the marking block rotate synchronously with the edge of the rotating dining table; The automatic calibration function is started, and the point cloud data of the marker block during the rotation process is collected by the laser radar to form a corresponding three-dimensional space point set; Processing the point cloud data to identify the raised track formed by the marker block to determine the relative spatial position between the laser radar and the marker block; According to the relative spatial position, adjusting the coordinate system of the laser radar to align it with the coordinate system of the rotating dining table; The LiDAR is automatically calibrated to ensure accurate recognition of movements at the dining table.
[0010] Optionally, the processing of the point cloud data to identify a raised track formed by the marker block to determine a relative spatial position between the laser radar and the marker block comprises: De-noising and removing outliers from the point cloud data acquired by the laser radar to obtain a height threshold of the pre-processed point cloud data; Based on the height threshold of the preprocessed point cloud data, the point cloud data is divided into those less than the height threshold and those greater than the height threshold; A transformation matrix of at least two frames of continuous point cloud data is obtained, and a position of the marking block is updated according to the transformation matrix.
[0011] Optionally, adjusting the coordinate system of the laser radar according to the relative spatial position to align it with the coordinate system of the rotating dining table includes: Extracting the contour of the detected bulge to obtain the boundary information of the marked block; The center point position of the marking block is obtained by calculating the average value or the centroid of all points on the convex contour; Perform principal component analysis based on the points on the convex contour to calculate the direction of its principal axis; output two principal component vectors, the major axis v1 and the minor axis v2; The angles between the major axis v1 and the minor axis v2 of the two output principal component vectors and the X' axis and the Y' axis are used to represent the posture of the marker block.
[0012] Optionally, performing principal component analysis based on the points on the convex contour to calculate the principal axis direction includes: Establish the transformation equation between the radar coordinate system and the dining table coordinate system, where T is the coordinate translation matrix and R is the rotation matrix; According to the coordinates of the center point of the marker block in the radar coordinate system and the dining table coordinate system, as well as the obtained marker block posture information, the parameters in the translation matrix T and the rotation matrix R are solved, so as to adjust the coordinate system of the lidar to align it with the coordinate system of the rotating dining table.
[0013] Optionally, the conversion equation between the radar coordinate system and the dining table coordinate system is established, where T is the coordinate translation matrix and R is the rotation matrix, including: Establish radar coordinate system and dining table coordinate system; The radar coordinate system takes the emission center of the laser radar as the origin O, the laser emission direction as the Z axis, the direction perpendicular to the emission plane as the X axis, and the Y axis is determined by the right-hand rule; wherein any point P in the radar coordinate system is represented by the coordinates (x, y, z); The table coordinate system has the center of the table as the origin O', the plane of the table as the XY' plane, and the direction perpendicular to the plane of the table as the Z' axis; wherein any point P' in the table coordinate system is represented by the coordinates (x', y', z').
[0014] Optionally, the step of obtaining the center point position of the marker block by calculating the average value or the centroid of all points on the convex contour comprises: Calculate the average coordinates of all points on the outline of the marker block to obtain the coordinates of the center point of the marker block (x c ,y c ,z c ); Calculate any two non-collinear vectors on the marker block contour to obtain the cross product of the two non-collinear vectors to obtain the normal vector n of the marker block; The normal vector n is converted into a unit vector and its three components in the radar coordinate system (n x ,n y ,n z ) to represent the posture of the marker block.
[0015] Optionally, solving the parameters in the translation matrix T and the rotation matrix R includes: If the coordinates of the origin O of the radar coordinate system in the dining table coordinate system are (t x ,t y ,t z ), then the coordinate translation matrix T is expressed as: ; Through the translation matrix T, any point P(x, y, z) in the radar coordinate system is transformed to the corresponding point P'(x', y', z') in the table coordinate system, that is: ; If the radar coordinate system rotates by angle α around the X-axis, by angle β around the Y-axis, and by angle γ around the Z-axis, then the corresponding rotation matrix R x , R y , R z They are: ; Combining the coordinate translation matrix T and the rotation matrix R, the conversion equation between the radar coordinate system and the dining table coordinate system is obtained: .
[0016] On the other hand, an embodiment of the present invention provides a laser calibration device for a rotating dining table, comprising: The first module is used to set a marking block with geometric features on the edge of the rotating dining table, and the marking block is used as a reference point of the laser radar during the rotation of the dining table; The second module is used to start the rotation function of the rotating table, so that the marking block rotates synchronously with the edge of the rotating table; The third module is used to start the automatic calibration function, collect the point cloud data of the marker block during the rotation process through the laser radar, and form a corresponding three-dimensional space point set; A fourth module is used to process the point cloud data and identify the raised track formed by the marker block to determine the relative spatial position between the laser radar and the marker block; A fifth module is used to adjust the coordinate system of the laser radar according to the relative spatial position so as to align it with the coordinate system of the rotating dining table; The sixth module is used to automatically calibrate the laser radar to ensure accurate recognition of actions on the dining table.
[0017] On the other hand, an embodiment of the present invention provides a laser calibration system for a rotating dining table, comprising: at least one processor; at least one memory for storing at least one program; When the at least one program is executed by the at least one processor, the at least one processor implements any of the above-mentioned laser calibration methods for a rotating dining table.
[0018] On the other hand, an embodiment of the present invention provides a computer-readable storage medium, in which a program executable by a processor is stored. When the program executable by the processor is executed by the processor, it is used to execute any of the laser calibration methods for a rotating dining table described above.
[0019] The embodiment of the present invention sets a marker block with geometric features on the edge of a rotating dining table, and the marker block is used as a reference point for the laser radar during the rotation of the dining table; starts the rotating table rotation function and the automatic calibration function, so that the laser radar collects point cloud data during the synchronous rotation of the marker block and the edge of the rotating dining table to form a corresponding three-dimensional space point set; processes the point cloud data, identifies the raised track formed by the marker block, so as to determine the relative spatial position between the laser radar and the marker block; adjusts the coordinate system of the laser radar according to the relative spatial position to align it with the coordinate system of the rotating dining table; and automatically corrects the laser radar to ensure that the actions on the dining table can be accurately identified. The present invention can solve the technical problem that the actions on the dining table cannot be accurately identified, resulting in the inability to accurately calibrate, and simplifies the calibration process to achieve accurate calibration of the rotating dining table. BRIEF DESCRIPTION OF THE DRAWINGS
[0020] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.
[0021] Figure 1 This is a rendering of a rotating dining table and a laser radar provided by an embodiment of the present invention; Figure 2 It is a schematic flow chart of the steps of a laser calibration method for a rotating dining table provided by an embodiment of the present invention; Figure 3 yes Figure 2 Specific step flow diagram of step S500 Figure 4 yes Figure 3 Schematic diagram of the specific steps of step S520 Figure 5 It is a structural block diagram of a laser calibration method system for a rotating dining table provided by an embodiment of the present invention; Figure 6 The present invention is a block diagram of a laser calibration method for a rotating dining table provided in an embodiment of the present invention. DETAILED DESCRIPTION
[0022] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.
[0023] It should be noted that, although the functional modules are divided in the device schematic diagram and the logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in a different order than the module division in the device or the order in the flowchart. The terms "first", "second", etc. in the specification, claims and the above drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence.
[0024] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application and are not intended to limit this application.
[0025] In addition, described feature, structure or characteristic can be combined in one or more embodiments in any suitable manner. In the following description, many specific details are provided to provide a full understanding of the embodiments of the present application. However, those skilled in the art will appreciate that the technical scheme of the present application can be put into practice without one or more of the specific details, or other methods, components, devices, steps, etc. can be adopted. In other cases, known methods, devices, realizations or operations are not shown or described in detail to avoid blurring the various aspects of the application.
[0026] The block diagrams shown in the accompanying drawings are only functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities can be implemented in software form, or in one or more hardware charging modules or integrated circuits, or in different networks and / or processor devices and / or microcontroller devices.
[0027] The flowcharts shown in the accompanying drawings are only exemplary and do not necessarily include all the contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps can be decomposed, and some operations / steps can be combined or partially combined, so the actual execution order may change according to actual conditions.
[0028] See also Figure 1 , where 1 is the laser radar; 2 is the area covered by the laser radar; 3 is the rotatable device of the rotating dining table; 4 is the non-rotatable device of the rotating dining table; and 5 is the marking block.
[0029] Specifically, taking a rectangular block as an example, a rectangular block is placed on the rotating edge of the rotating dining table as a mark. Start the rotation function of the rotating dining table so that the rotating disk drives the rectangular block to rotate together. At the same time, start the automatic calibration program to control the area array laser radar to collect data during the rotation process. The laser radar will collect the point cloud data of the rectangular block and the desktop data to form a series of three-dimensional space point sets. By identifying and analyzing this circle of protrusions, the relative position relationship between the laser radar and the rectangular block is determined. According to the collected data, the central coordinate system of the radar is calibrated. By calculating the translation and rotation matrices, the radar coordinate system is accurately aligned with the dining table coordinate system. After the coordinate alignment is completed, a verification test is performed. Through actual operation and observation, check whether the radar can accurately identify the actions on the dining table, and make fine adjustments as needed.
[0030] See also Figure 2 , Figure 3 and Figure 4 As shown, an embodiment of the present invention provides a laser calibration method for a rotating dining table, the method comprising the following steps: S100, setting a marking block with geometric features at the edge of the rotating dining table, wherein the marking block is used as a reference point for the laser radar during the rotation of the dining table; Specifically, the marker blocks have unique and easily identifiable geometric features, such as triangles, rectangles or crosses. These shapes are easily distinguished and detected by the laser radar. In addition, the surface of the marker blocks can be made of highly reflective materials, and multiple marker blocks can be evenly distributed on the edge of the dining table. The relative position relationship of these marker blocks can provide richer positioning information. It helps the laser radar capture the signal of the marker block more clearly, thereby improving the accuracy of positioning.
[0031] S200, starting the rotation function of the rotating dining table to make the marking block rotate synchronously with the edge of the rotating dining table; Specifically, the marking block is fixed to the edge of the rotating dining table to ensure that the marking block is always within the field of view of the laser radar during the rotation of the dining table.
[0032] S300, starting the automatic calibration function, collecting point cloud data of the marker block during the rotation process through the laser radar, and forming a corresponding three-dimensional space point set; Specifically, the system starts the automatic calibration mode of the laser radar. In this mode, the laser radar will continuously scan the rotating dining table and collect point cloud data of the marker block in real time. During the rotation of the dining table, the laser radar will capture the reflection points of the marker block at different positions and angles to generate a series of point cloud data. These point cloud data will contain the position information of the marker block in three-dimensional space. The point cloud data collected by the laser radar is processed to generate a three-dimensional space point set of the marker block during the rotation process. These point sets can be represented as a series of three-dimensional coordinate points, reflecting the movement trajectory of the marker block during the rotation process. The generated three-dimensional space point set is fitted with a trajectory to identify the movement path of the marker block. By comparing the actual path with the ideal path, calibration can be performed to correct the parameters of the laser radar to ensure that it accurately detects the position of the marker block during the rotation process.
[0033] S400, processing the point cloud data, identifying the raised track formed by the marker block, so as to determine the relative spatial position between the laser radar and the marker block; Specifically, the collected point cloud data is denoised to filter out abnormal points and noise points, and the point cloud data that truly reflects the surface of the marker block is retained. If the amount of point cloud data is too large, downsampling can be performed to reduce the computational burden while retaining key feature points. By analyzing the height changes of the point cloud data, the convex part between the surface of the marker block and the surrounding environment is identified. This can be achieved by calculating the normal vector or curvature of the local neighborhood in the point cloud.
[0034] Exemplarily, the feature points of the marker block at different positions are connected to form a continuous raised track. The formed track is smoothed to eliminate small fluctuations caused by vibration or other interference during rotation, making the track more continuous and stable. Based on the fitted raised track, the relative spatial position of the marker block at different positions and the laser radar is calculated. This includes calculating the distance and angle between the center position of the marker block and the laser radar. If the laser radar and the marker block are in different coordinate systems, a coordinate transformation is required to transform the position of the marker block into the coordinate system of the laser radar to determine their relative position.
[0035] S500, adjusting the coordinate system of the laser radar according to the relative spatial position so as to align it with the coordinate system of the rotating dining table; Specifically, the LiDAR usually has its own three-dimensional coordinate system (X, Y, Z), where the Z axis may be aligned with the vertical direction of the device, and the X and Y axes are aligned with the horizontal plane. The rotating table also has its own coordinate system, where X', Y' are horizontal plane coordinates and Z' is the vertical axis, and the Z' axis usually coincides with the rotation axis. Based on the relative spatial position calculated previously, determine the translation vector between the LiDAR and the marker block (i.e., the reference point of the rotating table). This represents the distance between the origin of the LiDAR coordinate system and the origin of the rotating table coordinate system. Identify the rotation angle between the LiDAR coordinate system and the rotating table coordinate system. Usually, it is necessary to calculate three Euler angles (Pitch, Roll, Yaw) or use a rotation matrix to represent the rotation relationship between the coordinate systems. Translate the LiDAR coordinate system to align with the origin of the rotating table coordinate system. This step eliminates the displacement difference between the two. Apply the calculated rotation transformation to align the coordinate axes of the LiDAR with the coordinate axes of the rotating table. This step ensures that the coordinate systems of the two are completely aligned in direction. By collecting the point cloud data of the marker block again, check the alignment of the laser radar coordinate system and the coordinate system of the rotating dining table. In some embodiments, the trajectory of the marker block in the laser radar coordinate system should be consistent with the motion path of the rotating dining table; if a deviation is found in the alignment result, the alignment effect can be further optimized by adjusting the translation vector or rotation matrix. After the alignment is completed, the laser radar coordinate system can be directly used to track the movement of the rotating dining table to ensure accurate detection and control of the position and posture of the dining table during rotation. Through the above steps, the laser radar coordinate system can be accurately aligned with the coordinate system of the rotating dining table, providing a solid foundation for subsequent automatic control, real-time tracking and data analysis.
[0036] S600, automatically calibrates the laser radar to ensure accurate recognition of actions on the dining table.
[0037] Specifically, based on the detected errors, the LiDAR parameters (e.g., scanning angle, laser intensity, or sensitivity) are automatically adjusted to compensate for the deviations in the recognition process. During daily use, the LiDAR continuously monitors the reference points and real-time motion data, and automatically makes fine adjustments to adapt to factors such as environmental changes or equipment aging.
[0038] When a large error or anomaly is identified, the system will automatically trigger the correction procedure and provide feedback information to the operator in real time to ensure timely adjustments during operation.
[0039] Optionally, the processing of the point cloud data to identify a raised track formed by the marker block to determine a relative spatial position between the laser radar and the marker block comprises: De-noising and removing outliers from the point cloud data acquired by the laser radar to obtain a height threshold of the pre-processed point cloud data; Based on the height threshold of the preprocessed point cloud data, the point cloud data is divided into those less than the height threshold and those greater than the height threshold; A transformation matrix of at least two frames of continuous point cloud data is obtained, and a position of the marking block is updated according to the transformation matrix.
[0040] Specifically, noise removal involves filtering the original point cloud data to remove noise points introduced by environmental interference or sensor errors. Common methods include statistical filtering or distance-based filtering to ensure that the remaining point cloud data is more accurate.
[0041] Outlier removal involves identifying and removing outliers, which are usually points that do not conform to the geometry of the marked block or are too far away from other points. Through algorithms such as density clustering or neighborhood analysis, outliers are removed to obtain more reliable point cloud data.
[0042] After denoising and removing outliers, a threshold is set based on the height distribution of the point cloud data. The threshold is used to distinguish the marker block from the background environment. The height threshold should be able to effectively distinguish the marker block from other parts, such as the point cloud data of the desktop or environmental objects.
[0043] Exemplarily, based on the preprocessed point cloud data, the point cloud data is divided into two categories: one is point cloud data with a height less than a threshold (possibly corresponding to the background or desktop), and the other is point cloud data with a height greater than the threshold (corresponding to the marker block).
[0044] Marker block extraction: Focus on data greater than the height threshold, which may contain the main features of the marker block. Through further shape analysis or clustering methods, the outline and position of the marker block are extracted.
[0045] Exemplarily, at least two frames of continuous point cloud data are obtained, and the transformation matrix between them is calculated. Common methods include ICP (Iterative Closest Point) algorithm or NDT (Normal Distributions Transform), etc., which are used to match the same points or features in continuous frames. Through registration, the rotation and displacement transformation matrices between the two frames of point cloud data are determined. Apply the transformation matrix to update the position of the marker block identified in the previous frame to the current frame. In this way, the accurate position of the marker block at different time points can be obtained to form a continuous motion trajectory. As time goes by, the position of the marker block is continuously updated, and its motion trajectory on the rotating dining table is tracked. Through this process, the relative position between the lidar and the marker block can be accurately calculated.
[0046] Optionally, adjusting the coordinate system of the laser radar according to the relative spatial position to align it with the coordinate system of the rotating dining table includes: S510, extracting the contour of the detected protrusion to obtain the boundary information of the marked block; Specifically, in the preprocessed point cloud data, the contour of the detected raised part of the marker block is extracted. The boundary points of the marker block are identified using an edge detection algorithm or a threshold-based contour extraction method. The extracted contour data should include all boundary points of the marker block, which will be used for the subsequent calculation of the center point and the main axis direction.
[0047] S520, obtaining the center point position of the marking block by calculating the average value or the centroid of all points on the convex contour; Specifically, all boundary points on the convex contour are calculated to obtain the average value or centroid position of these points. The centroid can be regarded as the center position of the marker block in three-dimensional space. The position of the centroid is the center point position of the marker block, which will be used as a reference point in the subsequent coordinate system alignment process.
[0048] S530, performing principal component analysis based on the points on the convex contour to calculate the principal axis direction; outputting two principal component vectors, the major axis v1 and the minor axis v2; The angles between the major axis v1 and the minor axis v2 of the two output principal component vectors and the X' axis and the Y' axis are used to represent the posture of the marker block.
[0049] Specifically, principal component analysis (PCA) is performed on all points on the raised contour. PCA is a statistical method that can find the principal axis direction of the data by calculating the covariance matrix of the data. Through PCA, two principal component vectors of the marker block contour points can be obtained: the major axis v1 and the minor axis v2. The major axis v1 represents the expansion of the point cloud data in the main direction, and the minor axis v2 represents the expansion in the secondary direction. The angles between the two principal component vectors (major axis v1 and minor axis v2) and the X' axis and Y' axis of the rotating dining table coordinate system are calculated. These angles can be used to describe the posture of the marker block relative to the dining table coordinate system. The calculated results of the angles can be used to represent the degree of rotation and tilt of the marker block in space, that is, the posture of the marker block.
[0050] Optionally, performing principal component analysis based on the points on the convex contour to calculate the principal axis direction includes: Establish the transformation equation between the radar coordinate system and the dining table coordinate system, where T is the coordinate translation matrix and R is the rotation matrix; According to the coordinates of the center point of the marker block in the radar coordinate system and the dining table coordinate system, as well as the obtained marker block posture information, the parameters in the translation matrix T and the rotation matrix R are solved, so as to adjust the coordinate system of the lidar to align it with the coordinate system of the rotating dining table.
[0051] Specifically, according to the calculated position and posture of the center point of the marker block, adjust the laser radar coordinate system so that its X' axis and Y' axis are aligned with the major axis v1 and minor axis v2 of the marker block respectively. After the alignment is completed, verify the position and posture of the marker block in the laser radar coordinate system to ensure that it is consistent with the coordinate system of the rotating dining table.
[0052] It can be understood that during the operation of the system, by continuously monitoring the posture and position of the marker block, the coordinate system of the lidar is dynamically adjusted to ensure that it is always aligned with the coordinate system of the rotating dining table.
[0053] Optionally, the conversion equation between the radar coordinate system and the dining table coordinate system is established, where T is the coordinate translation matrix and R is the rotation matrix, including: Establish radar coordinate system and dining table coordinate system; Specifically, we established two three-dimensional rectangular coordinate systems, one is the coordinate system of the lidar (referred to as the radar coordinate system), and the other is the coordinate system of the rotating dining table (referred to as the dining table coordinate system).
[0054] The radar coordinate system takes the emission center of the laser radar as the origin O, the laser emission direction as the Z axis, the direction perpendicular to the emission plane as the X axis, and the Y axis is determined by the right-hand rule; wherein any point P in the radar coordinate system is represented by the coordinates (x, y, z); Specifically, the origin O of the radar coordinate system is located at the emission center of the laser radar. The Z axis is along the emission direction of the laser radar, that is, the propagation direction of the laser beam. The X axis is perpendicular to the emission plane and perpendicular to the Z axis. Usually, the X axis can be selected to be parallel to the horizontal plane. The Y axis is determined according to the right-hand rule. Specifically, when the thumb of the right hand points to the Z axis and the index finger points to the X axis, the direction pointed by the middle finger is the Y axis. Any point P in the radar coordinate system can be represented by three-dimensional coordinates (x, y, z), where x is the projection distance of point P in the X axis direction; y is the projection distance of point P in the Y axis direction; and z is the projection distance of point P in the Z axis direction.
[0055] The table coordinate system has the center of the table as the origin O', the plane of the table as the XY' plane, and the direction perpendicular to the plane of the table as the Z' axis; wherein any point P' in the table coordinate system is represented by the coordinates (x', y', z').
[0056] Specifically, the origin O' of the dining table coordinate system is located at the center of the dining table; XY' plane: the plane of the dining table is the XY' plane, that is, the plane where the surface of the dining table is located; Z' axis: the direction perpendicular to the plane of the dining table is the Z' axis in the dining table coordinate system, usually pointing above or below the dining table. X' axis and Y' axis: The X' axis and Y' axis are in the XY' plane. The X' axis is usually selected to be parallel to one side of the dining table, and the Y' axis is determined according to the right-hand rule. Any point P' in the dining table coordinate system can be expressed by three-dimensional coordinates (x', y', z'), where: x' is the projection distance of point P' in the X' axis direction; y' is the projection distance of point P' in the Y' axis direction; z' is the projection distance of point P' in the Z' axis direction.
[0057] It can be understood that in some embodiments, a point P(x, y, z) in the radar coordinate system is converted to a point P'(x', y', z') in the dining table coordinate system, or a point P'(x', y', z') in the dining table coordinate system is converted to a point P(x, y, z) in the radar coordinate system; the specific conversion relationship depends on the relative position and posture between the radar and the dining table.
[0058] Optionally, the step of obtaining the center point position of the marker block by calculating the average value or the centroid of all points on the convex contour comprises: S521, calculate the average coordinates of all points on the outline of the marker block to obtain the coordinates (x c ,y c ,z c ); Specifically, the coordinates of all points on the contour of the marker block are averaged, and the specific calculation method is as follows: ; ; ; Where N is the total number of points on the contour of the marker block, (x i ,y i ,z i ) is the coordinate of the i-th point. The calculated (x c ,y c ,z c ) are the center point coordinates of the marker block.
[0059] S522, calculating any two non-collinear vectors on the marker block contour to obtain the cross product of the two non-collinear vectors to obtain the normal vector n of the marker block; Specifically, from the set of points on the contour of the marker block, select any two non-collinear vectors, v1 as follows:
[0060] v2 looks like this:
[0061] Among them, (x1, y1, z1), (x2, y2, z2), and (x3, y3, z3) are three different points on the contour of the marker block.
[0062] S523, convert the normal vector n into a unit vector and use its three components (n x ,n y ,n z ) to represent the posture of the marker block.
[0063] Specifically, the cross product of these two vectors is calculated to obtain the normal vector n: The calculated n represents the normal vector of the marker block. The normal vector n is normalized to obtain the unit normal vector: in , is the modulus of the normal vector, i.e. .
[0064] The unit normal vector n unit The three components in the radar coordinate system (n x ,n y ,n z ) is used to represent the posture of the marker block. Among them:
[0065] These three components reflect the orientation of the marker block in the radar coordinate system. c ,y c ,z c ) and the three components of the unit normal vector (n x ,n y ,n z ), which can fully describe the position and attitude of the marker block in the radar coordinate system.
[0066] Optionally, solving the parameters in the translation matrix T and the rotation matrix R includes: If the coordinates of the origin O of the radar coordinate system in the dining table coordinate system are (t x ,t y ,t z ), then the coordinate translation matrix T is expressed as: ; Through the translation matrix T, any point P(x, y, z) in the radar coordinate system is transformed to the corresponding point P'(x', y', z') in the table coordinate system, that is: ; If the radar coordinate system rotates by angle α around the X-axis, by angle β around the Y-axis, and by angle γ around the Z-axis, then the corresponding rotation matrix R x , R y , R z They are: ; Combining the coordinate translation matrix T and the rotation matrix R, the conversion equation between the radar coordinate system and the dining table coordinate system is obtained: .
[0067] The embodiment of the present invention sets a marker block with geometric features on the edge of a rotating dining table, and the marker block is used as a reference point for a laser radar during the rotation of the dining table; starts the rotation function of the rotating dining table to make the marker block rotate synchronously with the edge of the rotating dining table; starts the automatic calibration function to collect point cloud data of the marker block during the rotation process through the laser radar to form a corresponding three-dimensional space point set; processes the point cloud data to identify the raised track formed by the marker block to determine the relative spatial position between the laser radar and the marker block; adjusts the coordinate system of the laser radar according to the relative spatial position to align it with the coordinate system of the rotating dining table; and automatically corrects the laser radar to ensure that the actions on the dining table can be accurately identified. The present invention can solve the technical problem that the actions on the dining table cannot be accurately identified, resulting in the inability to accurately calibrate, and simplifies the calibration process to achieve accurate calibration of the rotating dining table.
[0068] The present invention also has the following beneficial effects: The calibration process is simplified, human intervention is reduced, operation difficulty is lowered, and calibration efficiency is improved.
[0069] Only a rectangular block needs to be placed on the edge of the rotating table as a mark. There is no need to purchase or make special calibration tools, which reduces hardware costs.
[0070] By accurately calculating the translation and rotation matrices, the radar coordinate system is precisely aligned with the dining table coordinate system, thereby improving the accuracy and stability of the calibration.
[0071] By optimizing the algorithm and adding filtering and denoising steps, the impact of environmental noise on the calibration results is reduced, and the adaptability and stability of the system in different environments are improved.
[0072] By realizing the function of stopping after picking up food, the intelligence level of the revolving dining table is improved, making the dining process more convenient and quick, and improving the user's dining experience. Figure 5 , an embodiment of the present invention provides a laser calibration device for a rotating dining table, comprising: The first module is used to set a marking block with geometric features on the edge of the rotating dining table, and the marking block is used as a reference point of the laser radar during the rotation of the dining table; The second module is used to start the rotation function of the rotating table, so that the marking block rotates synchronously with the edge of the rotating table; The third module is used to start the automatic calibration function, collect the point cloud data of the marker block during the rotation process through the laser radar, and form a corresponding three-dimensional space point set; A fourth module is used to process the point cloud data and identify the raised track formed by the marker block to determine the relative spatial position between the laser radar and the marker block; A fifth module is used to adjust the coordinate system of the laser radar according to the relative spatial position so as to align it with the coordinate system of the rotating dining table; The sixth module is used to automatically calibrate the laser radar to ensure accurate recognition of actions on the dining table.
[0073] The embodiment of the present invention sets a marker block with geometric features on the edge of a rotating dining table, and the marker block is used as a reference point for a laser radar during the rotation of the dining table; starts the rotation function of the rotating dining table to make the marker block rotate synchronously with the edge of the rotating dining table; starts the automatic calibration function to collect point cloud data of the marker block during the rotation process through the laser radar to form a corresponding three-dimensional space point set; processes the point cloud data to identify the raised track formed by the marker block to determine the relative spatial position between the laser radar and the marker block; adjusts the coordinate system of the laser radar according to the relative spatial position to align it with the coordinate system of the rotating dining table; and automatically corrects the laser radar to ensure that the actions on the dining table can be accurately identified. The present invention can solve the technical problem that the actions on the dining table cannot be accurately identified, resulting in the inability to accurately calibrate, and simplifies the calibration process to achieve accurate calibration of the rotating dining table.
[0074] See also Figure 6 , an embodiment of the present invention provides a laser calibration system for a rotating dining table, comprising: at least one processor; at least one memory for storing at least one program; When the at least one program is executed by the at least one processor, the at least one processor implements any of the above-mentioned laser calibration methods for a rotating dining table.
[0075] It can be seen that the contents of the above method embodiments are all applicable to the present system embodiments, the functions specifically implemented by the present system embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.
[0076] In addition, the embodiment of the present application also discloses a computer program product or a computer program, and the computer program product or the computer program is stored in a computer-readable storage medium. The processor of the computer device can read the computer program from the computer-readable storage medium, and the processor executes the computer program, so that the computer device performs the above method. Similarly, the contents in the above method embodiment are all applicable to the storage medium embodiment, and the functions specifically implemented by the storage medium embodiment are the same as those in the above method embodiment, and the beneficial effects achieved are also the same as those achieved by the above method embodiment.
[0077] The device embodiments described above are merely illustrative, and the units described as separate components may or may not be physically separated, that is, they may be located in one place or distributed on multiple network units. Some or all of the charging modules may be selected according to actual needs to achieve the purpose of the present embodiment.
[0078] Those skilled in the art will appreciate that all or some of the steps in the methods disclosed above, and the functional charging modules / units in the systems and devices may be implemented as software, firmware, hardware, or appropriate combinations thereof.
[0079] The terms "first", "second", "third", "fourth", etc. (if any) in the specification of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.
[0080] It should be understood that in this application, "at least one (item)" means one or more, and "plurality" means two or more. "And / or" is used to describe the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" can mean: only A exists, only B exists, and A and B exist at the same time, where A and B can be singular or plural. The character " / " generally indicates that the objects associated before and after are in an "or" relationship. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, c can be single or multiple.
[0081] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.
[0082] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
[0083] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.
[0084] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including multiple instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, referred to as ROM), random access memory (Random Access Memory, referred to as RAM), disk or optical disk and other media that can store programs.
[0085] The preferred embodiments of the present invention are described above with reference to the accompanying drawings, but the scope of the rights of the present invention is not limited thereto. Any modification, equivalent substitution and improvement made by a person skilled in the art without departing from the scope and essence of the present invention should be within the scope of the rights of the present invention.
Claims
1. A laser calibration method for a rotating dining table, characterized in that: The method comprises the following steps: A marking block with geometric features is arranged at the edge of the rotating dining table, and the marking block is used as a reference point of the laser radar during the rotation of the dining table; Starting the rotation function of the rotating dining table to make the marking block rotate synchronously with the edge of the rotating dining table; The automatic calibration function is started, and the point cloud data of the marker block during the rotation process is collected by the laser radar to form a corresponding three-dimensional space point set; Processing the point cloud data to identify the raised track formed by the marker block to determine the relative spatial position between the laser radar and the marker block; According to the relative spatial position, adjusting the coordinate system of the laser radar to align it with the coordinate system of the rotating dining table; The LiDAR is automatically calibrated to ensure accurate recognition of movements at the dining table.
2. The method according to claim 1, characterized in that The processing of the point cloud data and identifying the raised track formed by the marker block to determine the relative spatial position between the laser radar and the marker block comprises: De-noising and removing outliers from the point cloud data acquired by the laser radar to obtain a height threshold of the pre-processed point cloud data; Based on the height threshold of the preprocessed point cloud data, the point cloud data is divided into those less than the height threshold and those greater than the height threshold; A transformation matrix of at least two frames of continuous point cloud data is obtained, and a position of the marking block is updated according to the transformation matrix.
3. The method according to claim 2, characterized in that The adjusting the coordinate system of the laser radar according to the relative spatial position so as to align it with the coordinate system of the rotating dining table comprises: Extracting the contour of the detected bulge to obtain the boundary information of the marked block; The center point position of the marking block is obtained by calculating the average value or the centroid of all points on the convex contour; Perform principal component analysis based on the points on the raised contour to calculate the direction of its principal axis; output two principal component vectors, the major axis v1 and the minor axis v2; wherein the angles between the major axis v1 and the minor axis v2 of the two principal component vectors and the X' axis and the Y' axis respectively represent the posture of the marker block.
4. The method according to claim 3, characterized in that: The performing principal component analysis based on the points on the convex contour to calculate the principal axis direction thereof comprises: Establish the transformation equation between the radar coordinate system and the dining table coordinate system, where T is the coordinate translation matrix and R is the rotation matrix; According to the coordinates of the center point of the marker block in the radar coordinate system and the dining table coordinate system, as well as the obtained marker block posture information, the parameters in the translation matrix T and the rotation matrix R are solved, so as to adjust the coordinate system of the lidar to align it with the coordinate system of the rotating dining table.
5. The method according to claim 4, characterized in that The conversion equation between the radar coordinate system and the dining table coordinate system is established, including: Establish radar coordinate system and dining table coordinate system; The radar coordinate system takes the emission center of the laser radar as the origin O, the laser emission direction as the Z axis, the direction perpendicular to the emission plane as the X axis, and the Y axis is determined by the right-hand rule; wherein any point P in the radar coordinate system is represented by the coordinates (x, y, z); The table coordinate system has the center of the table as the origin O', the plane of the table as the XY' plane, and the direction perpendicular to the plane of the table as the Z' axis; wherein any point P' in the table coordinate system is represented by the coordinates (x', y', z').
6. The method according to claim 3, characterized in that The method of obtaining the center point position of the marker block by calculating the average value or the centroid of all points on the convex contour comprises: Calculate the average coordinates of all points on the outline of the marker block to obtain the coordinates of the center point of the marker block (x c ,y c ,z c ); Calculate any two non-collinear vectors on the marker block contour to obtain the cross product of the two non-collinear vectors to obtain the normal vector n of the marker block; The normal vector n is converted into a unit vector and its three components in the radar coordinate system (n x ,n y ,n z ) to represent the posture of the marker block.
7. The method according to claim 4, characterized in that Solving the parameters of the translation matrix T and the rotation matrix R includes: If the coordinates of the origin O of the radar coordinate system in the dining table coordinate system are (t x ,t y ,t z ), then the coordinate translation matrix T is expressed as: ； Through the translation matrix T, any point P(x, y, z) in the radar coordinate system is transformed to the corresponding point P'(x', y', z') in the table coordinate system, that is: ； If the radar coordinate system rotates by angle α around the X-axis, by angle β around the Y-axis, and by angle γ around the Z-axis, then the corresponding rotation matrix R x , R y , R z They are: ； Combining the coordinate translation matrix T and the rotation matrix R, the conversion equation between the radar coordinate system and the dining table coordinate system is obtained: 。 8. A laser calibration device for a rotating dining table, characterized in that: The device comprises: The first module is used to set a marking block with geometric features on the edge of the rotating dining table, and the marking block is used as a reference point of the laser radar during the rotation of the dining table; The second module is used to start the rotation function of the rotating table, so that the marking block rotates synchronously with the edge of the rotating table; The third module is used to start the automatic calibration function, collect the point cloud data of the marker block during the rotation process through the laser radar, and form a corresponding three-dimensional space point set; A fourth module is used to process the point cloud data and identify the raised track formed by the marker block to determine the relative spatial position between the laser radar and the marker block; A fifth module is used to adjust the coordinate system of the laser radar according to the relative spatial position so as to align it with the coordinate system of the rotating dining table; The sixth module is used to automatically calibrate the laser radar to ensure accurate recognition of actions on the dining table.
9. A laser calibration system for a rotating dining table, characterized in that: include: at least one processor; at least one memory for storing at least one program; When the at least one program is executed by the at least one processor, the at least one processor implements the laser calibration method for a rotating dining table as described in any one of claims 1-7.
10. A computer-readable storage medium storing a program executable by a processor, characterized in that: The processor-executable program is used to execute the laser calibration method for a rotating dining table as described in any one of claims 1-7 when executed by the processor.