Wheel three-dimensional point cloud measurement and wheel set size method and system

Abstract

The application discloses a kind of based on wheel three-dimensional point cloud measurement and wheel set size method and system, it is related to wheel dynamic detection technical field, including: obtaining point cloud data, and based on point cloud data is carried out wheel outer side surface fitting processing, to fit wheel outer side surface;Extract wheel tread and the junction of wheel outer side surface corner point set;Corner point set is projected to wheel outer side surface and is carried out projection point conversion, to fit plane circle;Determine rolling axis based on the normal vector of wheel outer side surface and the center coordinates of projection point;The center coordinates of projection point is translated along the normal vector direction of wheel outer side surface, to obtain rolling circle data point set;Wheel section contour line is extracted based on rolling axis and rolling circle data point set, to obtain rim parameter.The application can improve the measurement accuracy, and solve the problem that wheel section contour point is unevenly distributed and exists breakpoint.

Description

Technical Field

[0001] This invention belongs to the field of wheel dynamic detection technology, specifically relating to a method and system for measuring wheel three-dimensional point cloud and wheelset dimensions. Background Technology

[0002] During railway vehicle operation, wheelsets rub against and collide with rails and brakes, and are corroded by rainwater and oil, making them prone to wear and defects. When dimensional deformation exceeds limits, it can cause safety hazards, increase wheel-rail noise, and affect passenger comfort. Therefore, it is necessary to regularly inspect wheel dimensions and promptly maintain and repair wheelsets that exceed limits to prevent serious accidents.

[0003] Train wheel dynamic detection can be completed in real time during low-speed or high-speed operation, which is fast and efficient, reducing maintenance workload and lowering the risk of failure. In the point cloud registration stage, traditional registration methods face two major challenges when processing wheel point clouds: first, the symmetry of the wheel as a rotating body makes registration prone to getting trapped in local optima; second, the mismatch rate is high when the point cloud overlap rate is low. Although the Super 4PCS algorithm improves speed through affine invariance, its adaptability to symmetrical point clouds is still insufficient, and it relies on manual parameter adjustment, resulting in poor robustness. In the wheel size parameter measurement stage, traditional wheel diameter measurement relies on rolling circle fitting, but the coverage angle of a single frame point cloud varies, leading to large errors in circle center positioning. In wheel flange parameter measurement, the direct section intersection method is prone to breakpoints due to the discreteness of the point cloud, while polynomial curve fitting has poor adaptability to complex contours and cannot meet the high-precision measurement requirements of various tread types.

[0004] Therefore, there is an urgent need to provide a solution to improve the above problems. Summary of the Invention

[0005] The purpose of this invention is to provide a method and system for measuring wheel dimensions and wheel set dimensions based on three-dimensional point cloud measurement, which can solve the problems of low measurement accuracy and uneven distribution of wheel cross-sectional contour points with discontinuities in the existing technology.

[0006] To solve the above-mentioned technical problems, the present invention is implemented as follows:

[0007] In a first aspect, embodiments of the present invention provide a method for measuring wheel dimensions and wheelset size based on three-dimensional point cloud measurements, the method comprising:

[0008] Acquire point cloud data and perform wheel outer surface fitting processing based on the point cloud data to fit the wheel outer surface;

[0009] Extract the set of corner points at the junction of the wheel tread and the outer side of the wheel;

[0010] The corner point set is projected onto the outer surface of the wheel and the projection points are transformed to fit a planar circle;

[0011] The rolling axis is determined based on the normal vector of the outer side of the wheel and the center coordinates of the projection point.

[0012] The center coordinates of the projection point are translated along the direction of the normal vector on the outer side of the wheel to obtain the set of rolling circle data points.

[0013] The wheel cross-sectional profile is extracted based on the data points of the rolling axis and rolling circle to obtain the wheel flange parameters.

[0014] Optionally, the specific process of projecting the corner point set onto the outer surface of the wheel and transforming the projection points to fit a planar circle includes:

[0015] S1. Project all points in the corner point set onto the fitting plane of the outer surface to obtain the projection point set;

[0016] S2. Select two orthogonal unit vectors on the outer surface of the wheel, and establish a two-dimensional coordinate system with the two orthogonal unit vectors as the origin to obtain the two-dimensional point set of the plane circle fitting.

[0017] S3. Randomly select three points from the two-dimensional point set to obtain the perpendicular bisector circle;

[0018] S4. Calculate the distance from all points in the two-dimensional point set to the perpendicular bisector circle to obtain the scale of the interior points;

[0019] S5. Repeat steps S3 to S4, select the point with the highest proportion of interior points and its interior points as the final set of points for fitting the plane circle, and use the least squares method to refit to obtain the coordinates of the center of the target two-dimensional circle.

[0020] S6. Transform the two-dimensional center coordinates of the target circle again to obtain the three-dimensional center target of the target circle, and fit the plane circle.

[0021] Optionally, the specific steps for extracting the wheel cross-sectional profile include:

[0022] S1. Randomly select a cross section and project all wheel point clouds onto the cross section to obtain a point set;

[0023] S2. Divide the wheel point cloud into multiple intervals starting from the outer side along the rolling axis direction, and select the highest point in each interval as the contour point of that interval to obtain the wheel cross-section contour point set.

[0024] S3. Assign a parameter value to each data point in the wheel cross-section contour point set to generate a node vector;

[0025] S4. Initialize the control points and their corresponding weights, and define the error function based on the node vectors and control points;

[0026] S5. Repeat step S4. Stop iterating when the error function reaches the convergence condition or the current iteration number reaches the maximum iteration number, so as to obtain the wheel cross-section profile.

[0027] Optionally, the set of projection points includes the coordinates of multiple projection points, and the mathematical expression for the coordinates of the projection points is:

[0028] ;

[0029] in, Represents the coefficient. Represents the coordinates of all points in the corner point set. Indicates the coordinates of the projection point;

[0030] The two-dimensional point set fitted to a plane circle includes multiple two-dimensional point coordinates, and the mathematical expression for the two-dimensional point coordinates is:

[0031] ;

[0032] in, and Indicates in and Projection components in the direction, This represents the coordinates of the projection of the corner point onto the outer surface of the wheel. This represents any point on the outer surface of the wheel. and Indicates in direction and The projection components in the direction are orthogonal unit vectors;

[0033] The mathematical expression for the proportion of interior points is:

[0034] ;

[0035] ;

[0036] in, Represents the two-dimensional projection point to the circle distance, Represents a circle radius, This indicates the preset distance threshold. Indicates the scale of interior points. Indicates the number of two-dimensional projection points. and Representing circles respectively The x-coordinate and y-coordinate of the center of the circle. and Representing circles respectively The x and y coordinates of any point on the graph;

[0037] The specific steps for transforming the two-dimensional coordinates of the target circle's center to obtain the three-dimensional target circle's center, and then fitting the planar circle, include:

[0038] ;

[0039] in, Represents a plane circle. Represents the three-dimensional coordinates of the reference point. and These represent the x-coordinate and y-coordinate of the center of the target's three-dimensional circle, respectively.

[0040] Optionally, the mathematical expression for the node vector is:

[0041] ;

[0042] in, Represents a node vector, the first Set each node to 0, then... Each node is set to 1 to ensure that the curve passes through the beginning and end points;

[0043] The mathematical expression for the error function is:

[0044] ;

[0045] in, Represents the error function. Indicates the NURBS curve in terms of parameters The calculation point at that location, This indicates the number of two-dimensional projection points.

[0046] Secondly, embodiments of the present invention provide a system for measuring wheel three-dimensional point cloud and wheelset dimensions, the system comprising:

[0047] The point cloud data acquisition module is used to acquire point cloud data;

[0048] The wheel outer surface fitting module is used to perform wheel outer surface fitting processing based on point cloud data to fit the outer surface of the wheel.

[0049] The corner point set acquisition module is used to extract the corner point set at the junction of the wheel tread and the outer side of the wheel;

[0050] The planar circle fitting module is used to project the corner point set onto the outer surface of the wheel and perform projection point transformation to fit a planar circle;

[0051] The rolling axis generation module is used to determine the rolling axis based on the normal vector of the outer side of the wheel and the center coordinates of the projection point;

[0052] The rolling circle data point set generation module is used to translate the center coordinates of the projected points along the normal vector direction of the outer side of the wheel to obtain the rolling circle data point set.

[0053] The wheel flange parameter generation module is used to extract the wheel cross-sectional profile based on the set of rolling axis and rolling circle data points to obtain wheel flange parameters.

[0054] Thirdly, embodiments of the present invention provide an electronic device including a processor, a memory, and a program or instructions stored in the memory and executable on the processor, wherein the program or instructions, when executed by the processor, implement the steps of the method as described in the first aspect.

[0055] Fourthly, embodiments of the present invention provide a readable storage medium on which a program or instructions are stored, and when the program or instructions are executed by a processor, the steps of the method as described in the first aspect are implemented.

[0056] Compared with existing technologies, the beneficial effects of the method for measuring wheel three-dimensional point cloud and wheelset dimensions provided by this invention are as follows:

[0057] First, this invention improves the Super 4PCS algorithm during the research of coarse registration algorithms, and compared with traditional algorithms, the registration accuracy and robustness are significantly improved.

[0058] Secondly, in the measurement of wheel diameter parameters, this invention proposes a planar circle fitting algorithm based on the outer corner point of the wheel rim, which significantly improves the measurement accuracy compared with planar circle fitting based on rolling circle cloud and single frame point cloud.

[0059] Third, this invention studies a projection-based interval sampling method combined with the NURBS curve fitting algorithm in the measurement of wheel flange parameters, which solves the problem of uneven distribution of wheel cross-sectional profile points and the existence of discontinuities. Attached Figure Description

[0060] Figure 1 This is a flowchart of a method for measuring wheel dimensions based on three-dimensional point cloud data of a wheel, provided in the first embodiment of the present invention;

[0061] Figure 2 This invention provides a schematic diagram for calculating the center of a circle, as shown in the first embodiment.

[0062] Figure 3 This is a schematic diagram of the sampling interval of the wheel cross-section contour line provided in the first embodiment of the present invention;

[0063] Figure 4 This diagram illustrates the internal structure of a wheel three-dimensional point cloud measurement and wheelset size system provided in the second embodiment of the present invention. Detailed Implementation

[0064] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0065] The terms "first," "second," etc., used in the specification and claims of this invention are used to distinguish similar objects and are not used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that embodiments of the invention can be implemented in orders other than those illustrated or described herein. Furthermore, in the specification and claims, "and / or" indicates at least one of the connected objects, and the character " / " generally indicates that the preceding and following objects are in an "or" relationship.

[0066] The following description, in conjunction with the accompanying drawings, details a method and system for measuring wheel dimensions based on three-dimensional point cloud data, through specific embodiments and application scenarios.

[0067] Example 1

[0068] Please see Figure 1 This represents a flowchart of a method for measuring wheel dimensions and wheelset size based on three-dimensional point cloud of a wheel provided by the present invention, including steps S1 to S6.

[0069] S1: Acquire point cloud data and perform wheel outer surface fitting processing based on the point cloud data to fit the wheel outer surface.

[0070] Specifically, the outer side of the wheel is a point on the tread surface h-70mm inward from the outer side of the wheel. The complete wheel point cloud data is obtained through point cloud registration. ;

[0071] Furthermore, this invention divides the point cloud registration scheme into five different schemes. Schemes two and four, for coarse registration, use the invention's novel algorithm. To verify the feasibility of the algorithm, evaluation metrics are used to measure the five proposed point cloud registration schemes.

[0072] Root mean square error and mean absolute error are generally used to measure the error in the correspondence between the source point cloud and the true points after the estimated motion parameter transformation.

[0073] ;

[0074] ;

[0075] in, This represents the root mean square error. Let R represent the mean absolute error, and R be the rotation matrix, a 3x3 orthogonal matrix that describes the rotation transformation from the source coordinate system to the target coordinate system. Let represent the set of all point pairs, and t be the translation vector (3*1), describing the translation transformation from the source coordinate system to the target coordinate system. Points in the source point cloud and points in the target point cloud One-to-one correspondence.

[0076] Rotational error E R Translation error E t It is generally used to measure the difference between the estimated value and the true value of the transformation matrix, and is mostly used when the true value of the transformation matrix is ​​known.

[0077] ;

[0078] ;

[0079] in, Represents the actual translation vector. R represents the estimated translation vector. t Let R represent the actual rotation matrix. e This represents the estimation of the rotation matrix. Since the rotation matrix is ​​an orthogonal matrix, the formula in the calculation... It can also be used Replacement.

[0080] Interior point ratio is generally used to measure the effective correspondence ratio of a point cloud pair, and its mathematical expression is:

[0081] ;

[0082] in, Indicates the scale of interior points. Indicates the first The coordinates of the source point cloud, Indicates the first The coordinates of the target point cloud, N represents the total number of point pairs, and 1 [ ] represents Iverson brackets, which take the value 1 when the value inside the brackets is true, and 0 otherwise. This is the distance threshold.

[0083] Based on the above point cloud registration evaluation metrics, it can be concluded that, compared with other algorithms, using the SIFT-based Super 4PCS improved algorithm for coarse registration, although the time is slightly longer than that of traditional algorithms, all evaluation metrics are improved. When using the ISS-based Super 4PCS improved algorithm for coarse registration, the registration time is almost the same as that of traditional algorithms, and the registration accuracy and robustness are superior to other schemes. Therefore, the registration scheme selected in this invention is to use the ISS-based Super 4PCS improved algorithm for coarse registration, combined with the ICP algorithm for fine registration, to achieve the final wheel point cloud registration.

[0084] S2: Extract the point set at the corner where the wheel tread meets the outer side of the wheel.

[0085] Specifically, this invention extracts the corner point set at the junction of the wheel tread and the outer surface, and selects the corner point set at the junction of the tread and the outer surface that is basically unaffected by wear for curve fitting. The resulting corner point set is then obtained. .

[0086] S3: Project the corner point set onto the outer surface of the wheel and transform the projection points to fit a planar circle.

[0087] Specifically, this invention performs planar circle fitting based on the corner points of the outer side of the rim, and the steps are as follows:

[0088] S3-1, Set the corner points All points are projected onto the fitting plane of the outer surface to obtain Given the coordinates before projection and plane equations Calculate the coordinates of the projection point using the following formula. The mathematical expression is:

[0089] ;

[0090] S3-2. Select two orthogonal unit vectors on the fitting plane of the outer surface. A two-dimensional coordinate system is established with the intersection of the two vectors as the origin. The projected points are then converted into two-dimensional coordinates to obtain a two-dimensional point set for subsequent planar circle fitting. The coordinates are calculated as shown in the following formula:

[0091] ;

[0092] in, and yes exist and Projection components in the direction, Corner point The coordinates of the projection point on the fitting plane of the outer surface. To fit any point on the plane to the outer surface of the plane, and This represents two orthogonal unit vectors.

[0093] S3-3, From a two-dimensional point set Three points were randomly selected from the middle. Calculate separately as well as perpendicular bisector and The equation states that the intersection of the two lines is the center of the circle, and the radius is... The circle formed by the center and the radius is called a circle. .

[0094] S3-4 Calculating Two-Dimensional Point Sets All points to circles distance Distance less than threshold The point is the interior point, and then the scale of the interior point is calculated. .

[0095] ;

[0096] ;

[0097] in, Represents the two-dimensional projection point to the circle distance, Represents a circle radius, This indicates the preset distance threshold. Indicates the scale of interior points. Indicates the number of two-dimensional projection points. and Representing circles respectively The x-coordinate and y-coordinate of the center of the circle. and Representing circles respectively The x and y coordinates of any point on the graph;

[0098] S3-5. Repeat steps S3-3 to S3-4, selecting the point with the highest proportion of interior points and its interior points as the final set of points for fitting the plane circle, and then refitting using the least squares method to obtain the final coordinates of the circle center. ;

[0099] S3-6. Transform the two-dimensional center of the circle back into three-dimensional space. The three-dimensional coordinates of the center are: The calculation formula is:

[0100] ;

[0101] in, Represents a plane circle. Represents the three-dimensional coordinates of the reference point. and These represent the x-coordinate and y-coordinate of the center of the target's three-dimensional circle, respectively.

[0102] S4: Determine the rolling axis based on the normal vector of the outer side of the wheel and the center coordinates of the projection point.

[0103] Specifically, this invention determines the rolling axis using the outer surface normal vector and the coordinates of the projection point center. The mathematical expression for the rolling axis is:

[0104] ;

[0105] in, This represents the normal vector of the outer surface.

[0106] S5: Translate the center coordinates of the projection points along the direction of the normal vector on the outer side of the wheel to obtain the set of rolling circle data points;

[0107] Specifically, in this invention, the center C of the rolling circle is obtained by translating 0 along the normal vector direction of the outer surface. A rolling circle cross-section parallel to the outer surface is drawn through the center C. The intersection of the rolling circle cross-section and the wheel point cloud is the rolling circle data point set. ;

[0108] S6: Extract the wheel cross-sectional profile based on the data point set of the rolling axis and rolling circle to obtain the wheel flange parameters.

[0109] Specifically, in the process of obtaining wheel flange parameters, this invention uses a projection-based interval sampling method combined with a NURBS curve fitting algorithm to extract the wheel cross-sectional profile. The main steps include:

[0110] S6-1. After randomly selecting a cross-section A3x+B3y+C3z+D3=0, project all wheel point clouds onto this plane to obtain a point set. After projection, as shown in Figure 3, the wheel point cloud is divided into multiple intervals starting from the outer side along the rolling axis. The mathematical expression is:

[0111] ;

[0112] in, Indicates the interval width. Represents the interval number. Representing the rim width, the highest point of each interval is selected as the profile point of that interval, ultimately resulting in the set of profile points for the wheel cross-section. ,in, These are key points selected from the original point set, used as initial control points for NURBS curve fitting.

[0113] S6-2. Set a parameter value based on the chord length parameterization, and generate a node vector based on the parameter value. The mathematical expression for the parameter value is:

[0114] ;

[0115] ;

[0116] ;

[0117] in, Indicates the first The coordinates of each data point Indicates the first The coordinates of each data point This represents the sum of the square roots of the distances between all adjacent points. , Each node vector represents a different node vector.

[0118] The mathematical expression for the node vector is:

[0119] ;

[0120] Among them, the former Set each node to 0, then... Each node is set to 1 to ensure that the curve passes through the beginning and end points.

[0121] S6-3. Initialize control points and their corresponding weights. Initial control points can be simply set as a subset of data points or obtained initially through some interpolation method, and the initial weights can be set to 1.

[0122] S6-4. Define the error function and minimize it by adjusting the control point positions and weights using an optimization algorithm.

[0123] Specifically, the mathematical expression for the error function is:

[0124] ;

[0125] in, Represents the error function. Indicates the NURBS curve in terms of parameters The calculation point at that location, This indicates the number of two-dimensional projection points.

[0126] S6-10. Repeat step S6-4 until the error function is complete. The iteration stops when the convergence condition or the maximum number of iterations is reached.

[0127] Furthermore, the specific steps for obtaining the rim parameters include: via the rolling axis Construct a plane pm3, and obtain the wheel cross-section contour data points using a projection-based interval extraction algorithm. .

[0128] Furthermore, the data points of the wheel cross-section profile... The NURBS curve fitting algorithm was used to obtain the profile curve of the wheel section.

[0129] To significantly improve registration accuracy and robustness, the first embodiment of this invention also provides a new algorithm that improves upon the original Super 4PCS algorithm in the coarse registration stage of point clouds. Specifically, after the train passes through the track area equipped with a depth camera, the partial point clouds collected by the depth camera are stitched together to form a complete wheel point cloud. The technical approach includes point cloud data preprocessing, feature point extraction, point cloud feature point descriptors, coarse point registration, and fine point cloud registration. In the coarse point cloud registration stage, when the point cloud has symmetry, errors are easily made in point pair recognition. Especially for rotating bodies like wheel point clouds, the original Super 4PCS algorithm is not stable enough, so a Super 4PCS algorithm based on key points is proposed.

[0130] Specifically, a keypoint-based Super 4PCS algorithm includes the following steps:

[0131] Step 1: Extract key points from the source and target point clouds using ISS (Interface Separation and Reference Spectrum) to preserve the main features of the point clouds while avoiding strong symmetry and reducing the impact of point cloud noise on the registration results.

[0132] Step 2: Use the extracted ISS key points as the input point cloud for the Super 4PCS algorithm. This eliminates the need to traverse all point pairs in the point cloud, thus speeding up the retrieval process and making the matching results more accurate.

[0133] Step 3: The set of transformation matrices obtained from the registration of keypoint pairs using Super 4PCS. , each After being applied to the source point cloud P, the following is obtained: ,calculate Each of them The nearest point in the target point cloud Q distance And form corresponding point pairs, if Then the pair of points is considered as interior points and assigned to the interior point set. If it is in the middle, otherwise it is considered an exterior point and belongs to the exterior point set. Finally, as shown in the formula The proportion of interior points under each transformation is calculated, and the transformation matrix with the highest proportion of interior points is selected as the final transformation matrix.

[0134] Example 2

[0135] Please see Figure 4 This diagram illustrates the internal structure of a wheel-based three-dimensional point cloud measurement and wheelset dimensional system according to a second embodiment of the present invention, comprising:

[0136] Point cloud data acquisition module 100 is used to acquire point cloud data;

[0137] The wheel outer surface fitting module 200 is used to perform wheel outer surface fitting processing based on point cloud data to fit the wheel outer surface.

[0138] Corner point set acquisition module 300 is used to extract the corner point set at the junction of the wheel tread and the outer side of the wheel.

[0139] The planar circle fitting module 400 is used to project the corner point set onto the outer surface of the wheel and perform projection point transformation to fit a planar circle.

[0140] The rolling axis generation module 500 is used to determine the rolling axis based on the normal vector of the outer side of the wheel and the center coordinates of the projection point;

[0141] The rolling circle data point set generation module 600 is used to translate the center coordinates of the projected points along the normal vector direction of the outer side of the wheel to obtain the rolling circle data point set.

[0142] The rim parameter generation module 700 is used to extract the wheel cross-sectional profile based on the set of rolling axis and rolling circle data points to obtain the rim parameters.

[0143] The wheel 3D point cloud measurement and wheelset size system in this embodiment of the invention can be a device, or a component, integrated circuit, or chip in a terminal. The device can be a mobile electronic device or a non-mobile electronic device. For example, mobile electronic devices can refer to mobile phones, tablets, laptops, PDAs, in-vehicle electronic devices, wearable devices, ultra-mobile personal computers (UMPCs), netbooks, or personal digital assistants (PDAs), etc., while non-mobile electronic devices can refer to servers, network attached storage (NAS), personal computers (PCs), televisions (TVs), ATMs, or self-service machines, etc. This embodiment of the invention does not impose specific limitations.

[0144] The wheel three-dimensional point cloud measurement and wheelset size system in this embodiment of the invention can represent a device with an operating system. This operating system can represent Android, iOS, or other possible operating systems; this embodiment of the invention does not impose specific limitations.

[0145] The present invention provides a system for measuring wheel dimensions and measuring wheel set dimensions based on three-dimensional point cloud data. Figures 1 to 3 The various processes implemented in the method embodiment based on the three-dimensional point cloud measurement of wheels and the wheelset size method will not be described again here to avoid repetition.

[0146] Optionally, embodiments of the present invention also provide an electronic device, including a processor, a memory, and a program or instructions stored in the memory and executable on the processor. When the program or instructions are executed by the processor, they implement the various processes of the above-described embodiment of a method for measuring wheel three-dimensional point cloud and wheelset dimensions, and can achieve the same technical effect. To avoid repetition, further details are omitted here.

[0147] This invention also provides a readable storage medium storing a program or instructions. When the program or instructions are executed by a processor, they implement the various processes of the above-described embodiment of a method for measuring wheel three-dimensional point cloud and wheelset dimensions, and achieve the same technical effect. To avoid repetition, this will not be elaborated further here.

[0148] The processor refers to the processor in the electronic device described in the above embodiments. The readable storage medium includes computer-readable storage media, such as computer read-only memory (ROM), random access memory (RAM), magnetic disk, or optical disk.

[0149] It should be noted that, in this invention, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element. Furthermore, it should be noted that the scope of the methods and apparatus in the embodiments of this invention is not limited to performing functions in the order shown or discussed, but may also include performing functions substantially simultaneously or in the reverse order, depending on the functions involved. For example, the described methods may be performed in a different order than described, and various steps may be added, omitted, or combined. Additionally, features described with reference to certain examples may be combined in other examples.

[0150] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal (which may be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in the various embodiments of the present invention.

[0151] The embodiments of the present invention have been described above with reference to the accompanying drawings. However, the present invention is not limited to the specific embodiments described above. The specific embodiments described above are merely illustrative and not restrictive. Those skilled in the art can make many other forms under the guidance of the present invention without departing from the spirit and scope of the claims, and all of these forms are within the protection scope of the present invention.

Claims

1. A method for measuring wheel dimensions and determining wheelset size based on three-dimensional point cloud measurements, characterized in that, include: Acquire point cloud data and perform wheel outer surface fitting processing based on the point cloud data to fit the wheel outer surface. Extract the set of corner points at the junction of the wheel tread and the outer side of the wheel; The corner point set is projected onto the outer surface of the wheel and the projection points are transformed to fit a planar circle; The rolling axis is determined based on the normal vector of the outer surface of the wheel and the center coordinates of the projection point; The center coordinates of the projection point are translated along the normal vector direction of the outer side of the wheel to obtain the set of rolling circle data points. The wheel cross-sectional profile is extracted based on the rolling axis and the set of rolling circle data points to obtain the wheel flange parameters.

2. The method for measuring wheel dimensions and determining wheelset size based on three-dimensional point cloud of a wheel according to claim 1, characterized in that, The specific process of projecting the corner point set onto the outer surface of the wheel and performing projection point transformation to fit a planar circle includes: S1. Project all points in the corner point set onto the fitting plane of the outer surface to obtain the set of projection points; S2. Select two orthogonal unit vectors on the outer surface of the wheel, and establish a two-dimensional coordinate system with the two orthogonal unit vectors as the origin to obtain a two-dimensional point set for plane circle fitting; S3. Randomly select three points from the two-dimensional point set to obtain the perpendicular bisector circle; S4. Calculate the distance from all points in the two-dimensional point set to the perpendicular bisector circle to obtain the inner point ratio; S5. Repeat steps S3 to S4, select the point with the highest proportion of interior points and its interior points as the final set of points for fitting the plane circle, and use the least squares method to refit to obtain the coordinates of the center of the target two-dimensional circle. S6. The coordinates of the two-dimensional center of the target circle are transformed again to obtain the three-dimensional center of the target circle, so as to fit the plane circle.

3. The method for measuring wheel dimensions and wheelset size based on three-dimensional point cloud of a wheel according to claim 1, characterized in that, The specific steps for extracting the wheel cross-sectional contour line include: S1. Randomly select a cross section and project all wheel point clouds onto the cross section to obtain a point set; S2. Divide the wheel point cloud into multiple intervals starting from the outer side along the rolling axis direction, and select the highest point in each interval as the contour point of that interval to obtain the wheel cross-section contour point set. S3. Assign a parameter value to each data point in the wheel cross-section contour point set to generate a node vector; S4. Initialize the control points and their corresponding weights, and define an error function based on the node vectors and the control points; S5. Repeat step S4. Stop iterating when the error function reaches the convergence condition or the current iteration number reaches the maximum iteration number, so as to obtain the wheel cross-sectional profile.

4. The method for measuring wheel dimensions and wheelset size based on three-dimensional point cloud of a wheel according to claim 2, characterized in that, in, The set of projection points includes the coordinates of multiple projection points, and the mathematical expression for the coordinates of the projection points is: ； in, Represents the coefficient. Represents the coordinates of all points in the corner point set. Indicates the coordinates of the projection point; The two-dimensional point set fitted to the plane circle includes multiple two-dimensional point coordinates, and the mathematical expression for the two-dimensional point coordinates is: ； in, and Indicates in and Projection components in the direction, This represents the coordinates of the projection of the corner point onto the outer surface of the wheel. This represents any point on the outer surface of the wheel. and Indicates in direction and The projection components in the direction are orthogonal unit vectors; The mathematical expression for the ratio of the interior points is: ； ； in, Represents the two-dimensional projection point to the circle distance, Represents a circle radius, This indicates the preset distance threshold. Indicates the scale of interior points. Indicates the number of two-dimensional projection points. and Representing circles respectively The x-coordinate and y-coordinate of the center of the circle. and Representing circles respectively The x and y coordinates of any point on the graph; The specific steps of transforming the two-dimensional center coordinates of the target circle again to obtain the three-dimensional center target of the target circle, in order to fit the planar circle, include: ； in, Represents a plane circle. 'Represents the three-dimensional coordinates of the reference point, and These represent the x-coordinate and y-coordinate of the center of the target's three-dimensional circle, respectively.

5. The method for measuring wheel dimensions and wheelset size based on three-dimensional point cloud of a wheel according to claim 3, characterized in that, in, The mathematical expression for the node vector is: ； in, Represents a node vector. This represents the vector of the nth node. Represents the vector of the (k+1)th node, the previous Set each node to 0, then... Each node is set to 1 to ensure that the curve passes through the beginning and end points; The mathematical expression for the error function is: ； in, Represents the error function. This represents the coordinates of the i-th data point. Indicates the NURBS curve in terms of parameters The calculation point at that location, This indicates the number of two-dimensional projection points.

6. A system for measuring wheel dimensions and determining wheelset size based on three-dimensional point cloud data, characterized in that, include: The point cloud data acquisition module is used to acquire point cloud data; The wheel outer surface fitting module is used to perform wheel outer surface fitting processing based on the point cloud data to fit the wheel outer surface. The corner point set acquisition module is used to extract the corner point set at the junction of the wheel tread and the outer side of the wheel; The planar circle fitting module is used to project the corner point set onto the outer surface of the wheel and perform projection point transformation to fit a planar circle; A rolling axis generation module is used to determine the rolling axis based on the normal vector of the outer side of the wheel and the center coordinates of the projection point; The rolling circle data point set generation module is used to translate the center coordinates of the projection point along the normal vector direction of the outer side of the wheel to obtain the rolling circle data point set. The rim parameter generation module is used to extract the wheel cross-sectional profile based on the rolling axis and the rolling circle data point set to obtain the rim parameters.

7. An electronic device, characterized in that, It includes a processor, a memory, and a program or instructions stored in the memory and executable on the processor, wherein the program or instructions, when executed by the processor, implement the steps of a method for measuring wheel three-dimensional point cloud and wheelset dimensions as described in any one of claims 1-5.

8. A readable storage medium, characterized in that, The readable storage medium stores a program or instructions that, when executed by a processor, implement the steps of a method for measuring wheel three-dimensional point cloud and wheelset dimensions as described in any one of claims 1-5.

Images