Road scene modeling method based on real road surface data

Abstract

The invention relates to a road scene modeling method based on real road surface data, belongs to the technical field of road modeling, and solves the problems that existing road scene modeling is low in efficiency and cannot fit real road surface conditions. Comprising the steps of collecting continuous road scene data according to sampling frequency, and obtaining attributes of each sampling point; according to the attribute of each sampling point, selecting a segmentation point to segment the road scene data to obtain a plurality of scene primitives; performing geometric feature classification on each scene element according to the pavement type and the average attribute value of each scene element to obtain a plurality of geometric element sets; performing multi-dimensional feature clustering on each geometric primitive set according to the multi-dimensional attribute features of each scene primitive to obtain a plurality of subdivided primitive sets; and selecting a plurality of scene primitives from each subdivided scene primitive set according to received modeling demand information, and connecting the selected scene primitives to obtain a road scene model. And the road scene rapid modeling of highly restoring a real road surface is realized.

Description

Technical Field

[0001] The present invention relates to the technical field of road modeling, and in particular to a road scene modeling method based on real road surface data. Background Art

[0002] As a vital part of the modern transportation system, roads have different types in different scenarios, that is, different roads have different characteristic attributes. During the driving process of the vehicle, the various attributes of the road have an impact on the performance of the vehicle. In the simulation process, in order to make the simulation effect more consistent with the real effect, it is necessary to consider the various characteristic attributes of the road and model them.

[0003] In the existing method, the cost of the road primitive is calculated to select the road segment for modeling. This method requires the user to explicitly specify the required characteristic parameters of each dimension of each road primitive segment, and then match the most similar scene primitive from the primitive library according to the required characteristic parameters.

[0004] This existing method is only applicable to small-scale specific road scene modeling, because if the road scene to be modeled is too long, the required feature parameters are huge, and it is difficult for users to accurately specify the type, shape, resistance coefficient and other attribute characteristics of a large number of road segments in the actual modeling process. In addition, although the road scene model generated by this method retains the real microscopic attribute characteristics of each road point and meets the specified requirements of the user, it cannot consider the coupling characteristics and distribution characteristics between multiple attributes, making it difficult to ensure that the attributes of a large number of scene primitives are still similar to those of the real road after reorganization. Summary of the invention

[0005] In view of the above analysis, an embodiment of the present invention aims to provide a road scene modeling method based on real road surface data, so as to solve the problem that the existing road scene modeling is inefficient and cannot be applied to large-scale road scene modeling and cannot fit the real road conditions.

[0006] An embodiment of the present invention provides a road scene modeling method based on real road surface data, comprising the following steps:

[0007] Collect continuous road scene data according to the sampling frequency to obtain the attributes of each sampling point; select segmentation points according to the attributes of each sampling point to segment the road scene data to obtain multiple scene primitives;

[0008] Classify the geometric features of each scene primitive according to the road surface type and average attribute value of each scene primitive to obtain multiple geometric primitive sets;

[0009] According to the multidimensional attribute characteristics of each scene primitive, each geometric primitive set is clustered by multidimensional characteristics to obtain multiple subdivided primitive sets;

[0010] According to the received modeling requirement information, a number of scene primitives are selected from each subdivided scene primitive set, and the selected scene primitives are connected to obtain a road scene model.

[0011] Based on the further improvement of the above method, the geometric features of each scene primitive are classified according to the road surface type and average attribute value of each scene primitive, and multiple geometric primitive sets are obtained, including:

[0012] First, divide the road surface according to its type to obtain the primitive set corresponding to each road surface type;

[0013] Then, according to the average curvature and average slope of all sampling points contained in each scene primitive, the primitive set corresponding to each road surface type is divided by geometric features to obtain the curve primitive set, ramp primitive set and straight primitive set corresponding to each road surface type, which are respectively regarded as a geometric primitive set.

[0014] Based on the further improvement of the above method, the multidimensional attribute characteristics of each scene primitive are obtained by calculating the average and variance of the curvature, slope, rolling resistance coefficient, steering resistance coefficient and road roughness of all sampling points contained in each scene primitive.

[0015] Based on the further improvement of the above method, according to the multidimensional attribute characteristics of each scene primitive, the improved K-means clustering algorithm is used to perform multidimensional feature clustering on each geometric primitive set, and each geometric primitive set is clustered into multiple subdivided primitive sets.

[0016] Based on the further improvement of the above method, the distance between each scene primitive and the cluster center in the geometric primitive set is calculated by the following formula in the improved K-means clustering algorithm:

[0017]

[0018] Among them, Dis(γ j ,μ i ) represents the distance between the jth scene primitive and the i-th cluster center in the current geometric primitive set; γ j (q) and μ i (q) represents the q-th dimension attribute of the j-th scene primitive and the i-th cluster center; Q represents the total dimension of the attribute feature; δ q Represents the distance weight of the q-th dimension attribute.

[0019] Based on further improvements to the above method, the modeling requirement information includes: the total length of the road and the proportion of the road length of each road surface type.

[0020] Based on the further improvement of the above method, several scene primitives are selected from each subdivided scene primitive set, including:

[0021] According to the modeling requirement information, the average length of the scene primitives corresponding to each road surface type and the proportion of the number of scene primitives in each geometric primitive set in each road surface type, the number of geometric primitive sets to be selected in each road surface type is obtained;

[0022] According to the number of to-be-selected geometric primitive sets of each set, and according to the proportion of the number of scene primitives in each subdivided primitive set, the number of to-be-selected primitive sets of each set is obtained;

[0023] A scene primitive is randomly selected from each subdivided primitive set according to the number of primitives to be selected, thereby obtaining a selected scene primitive.

[0024] Based on the further improvement of the above method, several selected scene primitives are connected to obtain a road scene model, including:

[0025] The end slope of the previous scene primitive and the start slope of the next adjacent scene primitive in the selected scene primitive are calculated in sequence; the rotation angle of the next scene primitive is calculated according to the two slopes and the direction vectors of the end and the start;

[0026] Taking the first sampling point of the next scene primitive as the center, after rotating all the sampling points contained in the next scene primitive according to the rotation angle, all the sampling points of the next scene primitive are translated so that the first sampling point of the next scene primitive coincides with the last sampling point of the previous scene primitive, thus completing the connection of the two selected scene primitives;

[0027] After several selected scene primitives are connected in sequence, a road scene model is obtained.

[0028] Based on the further improvement of the above method, the rotation angle of the next scene primitive is calculated according to the two slopes and the direction vectors of the end and the start, including:

[0029] Calculate the difference between the arc tangent value of the starting slope of the next scene primitive and the arc tangent value of the ending slope of the previous scene primitive to obtain a first angle;

[0030] Calculate the dot product of the direction vectors of the end and the start. If the dot product is negative, add 180 degrees to the first angle to get the rotation angle; otherwise, the first angle is the rotation angle.

[0031] Based on the further improvement of the above method, segmentation points are selected according to the attributes of each sampling point to segment the road scene data to obtain multiple scene primitives. The segmentation points are selected according to the road surface type, curvature and slope of each sampling point, and the road scene data is segmented according to the segmentation points to obtain multiple road segments, from which road segments with a length greater than or equal to a length threshold are extracted as each scene primitive.

[0032] Compared with the prior art, the present invention can achieve at least one of the following beneficial effects:

[0033] 1. First, the geometric features of each scene primitive are classified based on road type, curvature and slope, and then multi-dimensional feature clustering is performed for each category considering the coupling characteristics and distribution characteristics of multi-dimensional attributes at the same time, so as to better understand the characteristics of different scene primitives, capture real road characteristics, and better model various complex road scenes.

[0034] 2. Simplify the modeling requirement information, improve user experience, improve modeling efficiency, and be suitable for dynamic modeling of large-scale road scenes; determine the number of selections according to the distribution ratio of each sub-category, and ensure that all selected scene primitives are consistent with the real road scene in terms of the mutual coupling characteristics and distribution characteristics of multi-dimensional attributes, thereby improving the authenticity of the road scene model.

[0035] 3. Accurately rotate and translate the scene primitives according to their geometric features at the beginning and end to achieve smooth transition of the scene primitives, improve connection quality, and achieve better dynamic modeling effects.

[0036] In the present invention, the above-mentioned technical solutions can also be combined with each other to achieve more preferred combination solutions. Other features and advantages of the present invention will be described in the subsequent description, and some advantages can become obvious from the description, or can be understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained through the contents particularly pointed out in the description and the drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] The drawings are only for the purpose of illustrating particular embodiments and are not to be considered limiting of the present invention. Like reference symbols denote like components throughout the drawings.

[0038] Figure 1 The present invention is a flow chart of a road scene modeling method based on real road surface data in an embodiment of the present invention. DETAILED DESCRIPTION

[0039] The preferred embodiments of the present invention are described in detail below in conjunction with the accompanying drawings, wherein the accompanying drawings constitute a part of this application and are used together with the embodiments of the present invention to illustrate the principles of the present invention, but are not used to limit the scope of the present invention.

[0040] A specific embodiment of the present invention discloses a road scene modeling method based on real road surface data. Figure 1 As shown, the following steps are included:

[0041] S1. Collect continuous road scene data according to the sampling frequency to obtain the attributes of each sampling point; select segmentation points according to the attributes of each sampling point to segment the road scene data to obtain multiple scene primitives.

[0042] It should be noted that by arranging sensors such as cameras and radars on the vehicle and allowing the vehicle to continuously drive on the corresponding road, data from each sampling point is collected and stored according to the sampling frequency to obtain continuous road scene data.

[0043] The data of each sampling point are analyzed to obtain the properties of each sampling point, including: calculating the curvature, slope and road roughness of each sampling point; constructing an extended Kalman filter or unscented Kalman filter model based on the vehicle dynamics model, and estimating the rolling resistance coefficient and steering resistance coefficient of each sampling point according to the motor torque on the left and right sides of the vehicle, the longitudinal vehicle speed and the yaw angular velocity.

[0044] Furthermore, the road surface type of each sampling point is obtained by passing the image captured by the camera into the trained classification neural network, and the road surface type includes but is not limited to: paved road, gravel road and undulating dirt road.

[0045] In this step, segmentation points are selected from each sampling point according to the attributes of each sampling point to segment the collected continuous road scene data, and the continuous road data is segmented into scene primitive segments with as simple attributes as possible.

[0046] Specifically, the segmentation points are selected in a variety of ways according to the road surface type, curvature and slope of each sampling point, including:

[0047] ① From the continuous sampling points, the sampling points where the road surface type changes suddenly are taken as the segmentation points.

[0048] For example, the road surface types of the first 10 sampling points are all paved roads, and the road surface type of the 11th sampling point is a gravel road, and the 11th sampling point is used as a segmentation point.

[0049] ② Divide the continuous road scene data into multiple road sections according to the preset length; calculate the curvature change and slope change of the sampling points in each road section respectively. If the curvature change exceeds the curvature change threshold, or the slope change exceeds the slope change threshold, the first sampling point in the road section is used as the segmentation point.

[0050] Segmentation points obtained in various ways are summarized, and the collected continuous road scene data is segmented using the segmentation points to obtain multiple road segments; considering the uncertainty of the sensor during data collection, there will be a certain amount of data jitter, resulting in a large redundancy in the segmentation points obtained above, and the road segments segmented according to the segmentation points are too fragmented. Therefore, in order to improve the availability of road segments, road segments with a length less than the length threshold are discarded, and only road segments with a length greater than or equal to the length threshold are retained as the primitives of each scene.

[0051] S2. Classify the geometric features of each scene primitive according to the road surface type and average attribute value of each scene primitive to obtain multiple geometric primitive sets.

[0052] It should be noted that the road surface type of each sampling point in each scene primitive obtained in step S1 is consistent. In this step, the primitive set corresponding to each road surface type is obtained by first dividing the primitives according to the road surface type, that is, the primitive set S corresponding to the road surface type t t For example, the primitive set S1 corresponds to the paved road, the primitive set S2 corresponds to the gravel road, and the primitive set S3 corresponds to the undulating dirt road.

[0053] Then, according to the average curvature and average slope of all sampling points contained in each scene primitive, the primitive set corresponding to each road surface type is divided by geometric features to obtain the curve primitive set, ramp primitive set and straight primitive set corresponding to each road surface type, which are respectively regarded as a geometric primitive set.

[0054] Specifically, the primitive set corresponding to each road surface type is taken out in turn, and when the primitive set corresponding to the current road surface type is divided into geometric features, if the average curvature of all sampling points contained in the scene primitives in this primitive set is greater than the set curvature threshold, then this scene primitive is considered to be a curve, and it is added to the curve primitive set corresponding to the current road surface type; if the average slope of all sampling points contained in the remaining scene primitives in this primitive set is greater than the set slope threshold, then this scene primitive is a ramp, and it is added to the ramp primitive set corresponding to the current road surface type; finally, the remaining scene primitives in this primitive set are straight roads, and they are added to the straight road primitive set corresponding to the current road surface type; each of the obtained curve primitive set, ramp primitive set, and straight road primitive set is a geometric primitive set S t,k , where k represents the type of geometric feature, namely: curve, ramp and straight road.

[0055] For example, the primitive set S1 corresponding to the paved road is further divided into the curve primitive set S 1,1 , ramp primitive set S 1,2 and the straight line primitive set S 1,3 .

[0056] It should be noted that this embodiment further divides the scene primitives of each road type into curves, ramps and straight roads, extracts more accurate geometric feature information of the road, facilitates meeting the user's various modeling needs, and makes the modeled road scene closer to the real road data.

[0057] S3. Perform multidimensional feature clustering on each geometric primitive set according to the multidimensional attribute features of each scene primitive, to obtain multiple subdivided primitive sets.

[0058] It should be noted that when there are a large number of scene primitives, each geometric primitive set obtained in step S2 will still contain many scene primitives. Therefore, when modeling road scenes, in order to accurately select scene primitives and ensure that the selected scene primitives are similar to the properties of the real road after modeling, this step further clusters and subdivides each geometric primitive set according to multi-dimensional attribute characteristics.

[0059] Specifically, the multidimensional attributes include: curvature ρ, slope α, rolling resistance coefficient f r , steering resistance coefficient f t and road roughness f f For each scene primitive, a statistical analysis is performed on the multidimensional attributes of all the sampling points it contains, and the average value of each attribute is calculated. and variance Multidimensional attribute features as scene primitives Among them, the mean value is used to represent the coupling characteristics of each attribute in the scene primitive; the variance is used to represent the distribution characteristics of each attribute in the scene primitive.

[0060] According to the multidimensional attribute characteristics of each scene primitive, the improved K-means clustering algorithm is used to perform multidimensional feature clustering on each geometric primitive set, and each geometric primitive set is clustered into multiple subdivided primitive sets.

[0061] Specifically, select the primitive set S corresponding to the road type t t A set of geometric primitives S under t,k , which contains m scene primitives [γ1,γ2,γ3,…,γ m ] as the input sample of the clustering algorithm. According to the number of categories n to be divided, samples are randomly selected as the initial cluster centers [μ1,μ2,…,μ n ], according to each input sample γ j The multidimensional attribute characteristics of the cluster are assigned to the category to which the nearest cluster center belongs.

[0062] It should be noted that the distance between each scene primitive in the geometric primitive set and the cluster center is calculated by the following formula:

[0063]

[0064] Among them, Dis(γ j ,μ i ) represents the distance between the jth scene primitive and the i-th cluster center in the current geometric primitive set; γ j (q) and μ i (q) represents the q-th dimension attribute of the j-th scene primitive and the i-th cluster center; Q represents the total dimension of the attribute feature; δ q It represents the distance weight of the q-th dimension attribute, which can be pre-set according to the actual situation to indicate the different influences of each dimension feature in the clustering process.

[0065] When a clustering iteration is completed, that is, all scene primitives are assigned, the mean of the attribute features of each dimension of all scene primitives in each category is calculated as the multidimensional attribute feature of the new cluster center for the next clustering iteration. When the maximum number of iterations is reached, the clustering process of a geometric primitive set is completed. Geometric primitive set S t,k It is clustered into n subdivision primitive sets, and the dth subdivision primitive set is represented as S t,k,d (d=1,2,…,n).

[0066] S4. According to the received modeling requirement information, select a number of scene primitives from each segmented scene primitive set, connect the selected scene primitives, and obtain a road scene model.

[0067] It should be noted that the modeling requirement information input by the user includes: the total length of the road and the proportion of the road length of each road surface type. There is no need for the user to input the required attribute feature values ​​of each scene primitive, which improves the user experience and modeling efficiency, and is suitable for dynamic modeling of large-scale road scenes.

[0068] First, according to the modeling requirement information and the average length of the scene primitives corresponding to each road surface type, the number of to-be-selected roads corresponding to each road surface type is obtained by the following formula:

[0069]

[0070] Among them, N t represents the number of road surface type t to be selected, that is, from the primitive set S t The number of scene primitives to be selected in ; L represents the total length of the road; P represents the proportion of the road length of road type t; Represents the average length of the scene primitives corresponding to the road type t, that is, the primitive set S t The average length of all scene primitives in .

[0071] Then, according to the proportion of scene primitives in each geometric primitive set in each road type, the number of to-be-selected geometric primitive sets N is obtained. t,k, that is, the number of straight roads, ramps and curved roads in each road type is obtained.

[0072] It should be noted that if the user has specific requirements for the number of straight roads, ramps or curved roads in a certain road type, the corresponding number should be added in the modeling requirement information. At the same time, the number of straight roads, ramps and curved roads in each road type can be obtained based on the proportion of the number of scene primitives in each geometric primitive set and the specified number.

[0073] Next, according to the number of geometric primitives to be selected in each set, and the proportion of the number of scene primitives in each subdivided primitive set, the number of subdivided primitive sets to be selected N is obtained. t,k,d ;

[0074] Finally, according to the number of primitives to be selected in each subdivided primitive set, a scene primitive is randomly selected to obtain a selected scene primitive. The indexes of the selected scene primitives are concatenated to obtain a scene primitive index sequence.

[0075] This embodiment classifies scene primitives at different levels through steps S2 and S3. In this step, the number of elements to be selected is obtained layer by layer according to the proportion of each category in each layer, thereby obtaining the number of elements to be selected for each subdivided primitive set, ensuring that all selected scene primitives are consistent with the real road scene in terms of the mutual coupling characteristics and distribution characteristics of multi-dimensional attributes, thereby improving the authenticity of the modeling scene.

[0076] The indexes of the selected scene primitives are spliced ​​together in an order set according to the actual situation or in a random order to obtain a selected scene primitive index sequence. According to the scene primitive index sequence, the adjacent next scene primitive is connected on the basis of the previous scene primitive in sequence, and after the selected scene primitives are connected in sequence, a road scene model is obtained.

[0077] That is to say, the coordinates of the first scene primitive in the scene primitive index sequence remain unchanged, and it is used as the previous scene primitive to connect to its adjacent next scene primitive. After the connection, the newly connected scene primitive is used as the new previous scene primitive to continue connecting to its adjacent next scene primitive until all connections are completed.

[0078] Specifically, the process of connecting the latter scene primitive with the former scene primitive includes:

[0079] ① Calculate the end slope of the previous scene primitive and the starting slope of the adjacent next scene primitive in the selected scene primitive in sequence; calculate the rotation angle of the next scene primitive based on the two slopes and the direction vectors of the end and the starting end.

[0080] It should be noted that, according to the preset number of sampling points Num, the last Num sampling points of the previous scene primitive are taken as the end, and the first Num sampling points of the next scene primitive are taken as the beginning. The end slope k is obtained by fitting a linear function according to the coordinates of the sampling points contained in the end and the beginning respectively. after and the initial slope k before .

[0081] The difference between the arc tangent value of the starting slope of the next scene primitive and the arc tangent value of the ending slope of the previous scene primitive is calculated, and the first angle θ is obtained by the following formula:

[0082] θ=arctan(k after )-arctan(k before ) Formula (3)

[0083] Here, arctan(·) represents the inverse tangent function.

[0084] It should be noted that if the rotation angle is calculated only based on the slope, the directions of connection of the two scene primitives may be opposite. Therefore, the direction vector of the end is further calculated based on the coordinates of the last sampling point and the Num-th sampling point from the end of the previous scene primitive; the direction vector of the starting end is calculated based on the coordinates of the Num-th sampling point and the first sampling point of the next scene primitive; and the dot product of the direction vectors of the end and the starting end is calculated. If the dot product is negative, the first angle is added with 180 degrees to obtain the rotation angle; otherwise, the first angle is the rotation angle.

[0085] ② Taking the first sampling point of the next scene primitive as the center, rotate all the sampling points contained in the next scene primitive according to the rotation angle.

[0086] It should be noted that the first sampling point (x0, y0) of the next scene primitive is taken as the center, and all sampling points contained in the next scene primitive are rotated in the XY two-dimensional plane according to the rotation angle, and the rotated XY coordinates are calculated by the following formula:

[0087]

[0088] Among them, (x e ,y e ) and (x_rot e ,y_ro e ) represent the XY coordinates of the e-th sampling point in the next scene primitive before and after rotation. Since the first sampling point is the rotation center, the coordinates remain unchanged before and after rotation.

[0089] This step smoothly connects primitives of different scenes through rotation, improves the connection quality, and achieves better dynamic modeling effect.

[0090] ③Translate all sampling points of the next scene primitive so that the first sampling point of the next scene primitive coincides with the last sampling point of the previous scene primitive, thus completing the connection between the two selected scene primitives.

[0091] It should be noted that translation is based on the last sampling point of the previous scene primitive and is performed according to the relative position of each sampling point in the next scene primitive and its first sampling point. The formula is as follows:

[0092]

[0093] Among them, (x_re e ,y_re e ,z_re e ) represents the coordinates of the e-th sampling point in the next scene primitive after translation; z e Indicates the Z coordinate of the e-th sampling point in the next scene primitive before translation, z0 indicates the Z coordinate of the first sampling point in the next scene before translation, (x_before end ,y_before end ,z_before end ) represents the XYZ coordinates of the last sampled point in the previous scene primitive.

[0094] From the above connection process, it can be seen that in the process of connecting scene primitives, only the coordinates of each sampling point are changed, and each sampling point still maintains its original multi-dimensional attributes. When connecting the selected scene primitives, the multi-dimensional attributes of each sampling point contained in it can be seamlessly spliced ​​without making any changes, and the complete attribute information of the modeled road scene can be obtained.

[0095] Compared with the prior art, the road scene modeling method based on real road surface data provided in this embodiment first classifies the geometric features of each scene primitive from the perspective of road surface type, curvature and slope, and then performs multi-dimensional feature clustering for each category while considering the coupling features and distribution features of multi-dimensional attributes, so as to better understand the characteristics of different scene primitives, capture real road features, and better model various complex road scenes; simplify modeling requirement information, improve user experience, improve modeling efficiency, and be suitable for dynamic modeling of large-scale road scenes; determine the number of scenes to be selected according to the distribution ratio of each sub-category, ensure that all selected scene primitives are consistent with the real road scene in terms of the mutual coupling characteristics and distribution characteristics of multi-dimensional attributes, and improve the authenticity of the road scene model; accurately rotate and translate according to the geometric features of the start and end of the scene primitives, realize smooth transition of the scene primitives, improve connection quality, and achieve better dynamic modeling effect.

[0096] Those skilled in the art will appreciate that all or part of the processes of the above-mentioned embodiments can be implemented by instructing related hardware through a computer program, and the program can be stored in a computer-readable storage medium, wherein the computer-readable storage medium is a disk, an optical disk, a read-only storage memory, or a random access memory, etc.

[0097] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily conceived by any technician familiar with the technical field within the technical scope disclosed by the present invention should be covered within the protection scope of the present invention.

Claims

1. A road scene modeling method based on real road surface data, characterized in that: The following steps are involved: Collect continuous road scene data according to the sampling frequency to obtain the attributes of each sampling point; select segmentation points according to the attributes of each sampling point to segment the road scene data to obtain multiple scene primitives; Classify the geometric features of each scene primitive according to the road surface type and average attribute value of each scene primitive to obtain multiple geometric primitive sets; According to the multidimensional attribute characteristics of each scene primitive, each geometric primitive set is clustered by multidimensional characteristics to obtain multiple subdivided primitive sets; According to the received modeling requirement information, a number of scene primitives are selected from each subdivided scene primitive set, and the selected scene primitives are connected to obtain a road scene model.

2. The road scene modeling method based on real road surface data according to claim 1 is characterized in that: The geometric feature classification of each scene primitive is performed according to the road surface type and the average attribute value of each scene primitive to obtain multiple geometric primitive sets, including: First, divide the road surface according to its type and obtain the primitive set corresponding to each road surface type; Then, according to the average curvature and average slope of all sampling points contained in each scene primitive, the primitive set corresponding to each road surface type is divided by geometric features to obtain the curve primitive set, ramp primitive set and straight primitive set corresponding to each road surface type, which are respectively regarded as a geometric primitive set.

3. The road scene modeling method based on real road surface data according to claim 2 is characterized in that: The multi-dimensional attribute characteristics of each scene primitive are obtained by calculating the average value and variance of the curvature, slope, rolling resistance coefficient, steering resistance coefficient and road surface roughness of all sampling points contained in each scene primitive.

4. The road scene modeling method based on real road surface data according to claim 3 is characterized in that: According to the multidimensional attribute characteristics of each scene primitive, an improved K-means clustering algorithm is used to perform multidimensional feature clustering on each geometric primitive set, and each geometric primitive set is clustered into multiple subdivided primitive sets.

5. The road scene modeling method based on real road surface data according to claim 4 is characterized in that: In the improved K-means clustering algorithm, the distance between each scene primitive in the geometric primitive set and the cluster center is calculated by the following formula: Among them, Dis(γ j , μ i ) represents the distance between the jth scene primitive and the i-th cluster center in the current geometric primitive set; γ j (q) and μ i (q) represents the q-th dimension attribute of the j-th scene primitive and the i-th cluster center; Q represents the total dimension of the attribute feature; δ q Represents the distance weight of the q-th dimension attribute.

6. The road scene modeling method based on real road surface data according to claim 2, characterized in that: The modeling requirement information includes: the total length of the road and the proportion of the road length of each road surface type.

7. The road scene modeling method based on real road surface data according to claim 6 is characterized in that: The selecting a plurality of scene primitives from each subdivided scene primitive set includes: According to the modeling requirement information, the average length of the scene primitives corresponding to each road surface type and the proportion of the number of scene primitives in each geometric primitive set in each road surface type, the number of geometric primitive sets to be selected in each road surface type is obtained; According to the number of to-be-selected geometric primitive sets of each set, and according to the proportion of the number of scene primitives in each subdivided primitive set, the number of to-be-selected primitive sets of each set is obtained; A scene primitive is randomly selected from each subdivided primitive set according to the number of primitives to be selected, thereby obtaining a selected scene primitive.

8. The road scene modeling method based on real road surface data according to claim 1, characterized in that: The connecting of the selected plurality of scene primitives to obtain a road scene model comprises: The end slope of the previous scene primitive and the start slope of the adjacent next scene primitive in the selected scene primitive are calculated in sequence; the rotation angle of the next scene primitive is calculated according to the two slopes and the direction vectors of the end and the start; Taking the first sampling point of the next scene primitive as the center, after rotating all the sampling points contained in the next scene primitive according to the rotation angle, all the sampling points of the next scene primitive are translated so that the first sampling point of the next scene primitive coincides with the last sampling point of the previous scene primitive, thus completing the connection of the two selected scene primitives; After several selected scene primitives are connected in sequence, a road scene model is obtained.

9. The road scene modeling method based on real road surface data according to claim 8, characterized in that: The step of calculating the rotation angle of the next scene primitive according to the two slopes and the direction vectors of the end and the start includes: Calculate the difference between the arc tangent value of the starting slope of the next scene primitive and the arc tangent value of the ending slope of the previous scene primitive to obtain a first angle; The dot product of the direction vectors of the end and the start is calculated. If the dot product is a negative number, 180 degrees is added to the first angle to obtain the rotation angle; otherwise, the first angle is the rotation angle.

10. The road scene modeling method based on real road surface data according to claim 1, characterized in that: The method of selecting segmentation points according to the attributes of each sampling point to segment the road scene data to obtain multiple scene primitives is to select segmentation points according to the road surface type, curvature and slope of each sampling point, segment the road scene data according to the segmentation points to obtain multiple road segments, and extract road segments with a length greater than or equal to a length threshold as each scene primitive.

Images