CN117671173A

CN117671173A - Road modeling method and device based on laser point cloud and electronic equipment

Info

Publication number: CN117671173A
Application number: CN202311565483.5A
Authority: CN
Inventors: 马浩; 张攀科; 毛明楷; 吴垒; 张富杰; 朱万凯
Original assignee: Beijing Geo Vision Tech Co ltd
Current assignee: Beijing Geo Vision Tech Co ltd
Priority date: 2023-11-22
Filing date: 2023-11-22
Publication date: 2024-03-08

Abstract

The embodiment of the application provides a road modeling method and device based on laser point cloud and electronic equipment, and relates to the field of three-dimensional reconstruction. Acquiring three-dimensional point cloud data of a road, wherein the three-dimensional point cloud data comprises elevation values of a scanning line and a plurality of laser points; calculating the change rate of the elevation value of each laser point and the adjacent elevation value based on the scanning line to obtain a plurality of elevation change rates, and comparing each elevation change rate with a preset change rate threshold to obtain a laser point set, wherein the adjacent elevation value is the elevation value of the adjacent node of each laser point; clustering is carried out on the basis of the laser point set to obtain a plurality of point blocks, and filtering and vector processing are carried out on each point block to obtain a plurality of roadside vectors; constructing a road surface geometric model according to each road edge vector; and constructing textures of the road surface geometric model to generate a road model. The unstructured point cloud data can be quickly generated into a high-precision road model.

Description

Road modeling method and device based on laser point cloud and electronic equipment

Technical Field

The application relates to the technical field of three-dimensional reconstruction, in particular to a road modeling method and device based on laser point cloud and electronic equipment.

Background

Along with the continuous expansion of the scale of road traffic infrastructure, the problems of management and maintenance of road assets are increasingly prominent, and the problems of difficult data acquisition, limited data coverage, single expression mode, untimely data updating and the like, which restrict the effective management of road assets, cannot meet the requirements of maintenance management in the traditional management mode and technical means. With the development of mobile laser measurement technology, the vehicle-mounted laser measurement system can be used for rapidly acquiring three-dimensional point cloud space data of a road and a peripheral area. How to quickly generate a high-precision road model from unstructured point cloud data is important to realize three-dimensional reconstruction of a large-scale road traffic infrastructure.

Disclosure of Invention

The application provides a road modeling method, a device, electronic equipment and a readable storage medium based on laser point cloud, which can quickly generate a high-precision road model from unstructured point cloud data.

The technical scheme of the embodiment of the application is as follows:

in a first aspect, an embodiment of the present application provides a road modeling method based on a laser point cloud, where the method includes:

Acquiring three-dimensional point cloud data of a road, wherein the three-dimensional point cloud data comprises elevation values of a scanning line and a plurality of laser points;

calculating the change rate of the elevation value of each laser point and the adjacent elevation value based on the scanning line to obtain a plurality of elevation change rates, and comparing each elevation change rate with a preset change rate threshold to obtain a laser point set, wherein the adjacent elevation value is the elevation value of the adjacent node of each laser point;

clustering is carried out on the basis of the laser point set to obtain a plurality of point blocks, and filtering and vector processing are carried out on each point block to obtain a plurality of roadside vectors;

constructing a road surface geometric model according to each road edge vector;

and constructing textures of the road surface geometric model to generate a road model.

In the technical scheme, three-dimensional point cloud data of a road are firstly obtained, the three-dimensional point cloud data comprise elevation values of scanning lines and a plurality of laser points, and data support is provided for subsequent generation of a high-precision road model by obtaining the three-dimensional point cloud data; based on the scanning lines, calculating the change rates of the elevation values of the laser points and the adjacent elevation values to obtain a plurality of elevation change rates, and comparing the elevation change rates with a preset change rate threshold to obtain a laser point set, wherein the adjacent elevation values are the elevation values of the adjacent nodes of the laser points, so that the subsequent clustering treatment is facilitated; clustering processing is carried out on the basis of the laser point set to obtain a plurality of point blocks, filtering and vector processing are carried out on each point block to obtain a plurality of road edge vectors, noise points can be removed, fine extraction is carried out, and the subsequent generation of a high-precision road model is facilitated; constructing a road surface geometric model according to each road boundary vector; and carrying out texture construction on the road surface geometric model to generate a road model, and carrying out texture construction to enable the road model to be more vivid and generate a high-precision road model.

In some embodiments of the present application, the calculating, based on the scan lines, the change rate of the elevation value and the adjacent elevation value of each laser point to obtain a plurality of elevation change rates includes:

based on the scanning line, calculating the change rate of the elevation value and the adjacent elevation value of each laser point by using a preset change rate algorithm to obtain a plurality of elevation change rates;

wherein the rate of change algorithm is expressed as:

wherein Z is _i And X _i Z and x values, Z, of a laser scanning local coordinate system, denoted as laser spot _i+1 And X _i+1 The z and x values of the laser scanning local coordinate system of adjacent laser spots, denoted as laser spot, dz is denoted as the elevation change rate.

In the technical scheme, the position relation of the laser points can be reflected by calculating the elevation change rate, so that accurate road information is obtained.

In some embodiments of the present application, comparing each of the elevation change rates with a preset change rate threshold value to obtain a laser point set includes:

under the condition that the elevation change rate is larger than the change rate threshold, adding laser points corresponding to the elevation change rate into a preset initial point set;

under the condition that the elevation change rate is smaller than or equal to the change rate threshold value, the laser points corresponding to the elevation change rate are not added into a preset initial point set;

And taking the initial point set as the laser point set.

In the technical scheme, the elevation change rate is compared with the preset change rate threshold value, and unimportant laser points are removed, so that a laser point set is obtained, and the follow-up generation of a more accurate road model is facilitated.

In some embodiments of the present application, the clustering processing based on the laser point set to obtain n point blocks includes:

creating a first empty point block, and storing a first point in the laser point set into the first empty point block to obtain a first point block; performing distance calculation on a second point in the laser point set and each laser point in the first point block to obtain a distance value;

creating a second empty point block under the condition that the distance value is larger than a preset distance threshold value, and adding a second point in the laser point set into the second empty point block to obtain a second point block;

adding a second point in the laser point set into the first empty point block under the condition that the distance value is smaller than or equal to a preset distance threshold value;

and constructing the first point block and the second point block into a plurality of point blocks.

In the technical scheme, the laser point sets are classified, so that the subsequent generation of a plurality of roadside line vectors is facilitated.

In some embodiments of the present application, the filtering and vector processing are performed on each of the point blocks to obtain a plurality of curbs vectors, including:

in each point block, calculating a plane included angle between a current node and an adjacent node adjacent to the current node in the point block, and comparing the plane included angle with a preset first angle threshold value to obtain a filtering node;

and vectorizing the filtering nodes to obtain a plurality of roadside vectors.

In the technical scheme, the points larger than the first angle threshold value are removed, so that the subsequent generation of the high-precision road model is facilitated.

In some embodiments of the present application, the plurality of curbs vectors are two curbs, each having a plurality of vector points;

the construction of the road surface geometric model according to each road edge vector comprises the following steps:

comparing the lengths of the two curbs, and determining a first curbs and a second curbs, wherein the length of the first curbs is greater than that of the second curbs;

homogenizing the vector points of the first route edge to obtain a first uniform route edge;

homogenizing the vector points of the second curb based on the number of the vector points of the first uniform curb to obtain a second uniform curb;

The vector points of the first uniform road edge and the vector points of the second uniform road edge are in one-to-one correspondence to obtain corresponding vector points of the first road edge and corresponding vector points of the second road edge;

and connecting the corresponding vector points on the first roadside with the corresponding vector points on the second roadside to form a plurality of triangles, and forming the road surface geometric model by the triangles.

In the technical scheme, the points on the first roadside line and the second roadside line are homogenized and correspond to each other one by one to form the road surface geometric model, so that the road surface geometric model can be generated quickly.

In some embodiments of the present application, the performing a one-to-one correspondence between the vector point of the first uniform road edge and the vector point of the second uniform road edge to obtain a corresponding vector point of the first road edge and a corresponding vector point of the second road edge includes:

calculating the included angles of the current node of the first uniform road edge, the first adjacent node of the current node and the second adjacent node of the current node to obtain an included angle value;

inserting a first vector point between the current node and the first adjacent node and inserting a second vector point between the current node and the second adjacent node when the included angle value is larger than a preset second angle threshold value;

Inserting a third vector point at a position corresponding to the position between the current node and the first adjacent node in the second uniform road edge, and inserting a fourth vector point at a position corresponding to the position between the current node and the second adjacent node;

and taking all nodes of the first uniform road edge as corresponding vector points of the first road edge, and taking all nodes of the second uniform road edge as corresponding vector points of the second road edge.

In the technical scheme, interpolation is carried out on the first uniform road edge line and the second uniform road edge line, so that one-to-one correspondence is realized, and the subsequent rapid generation of the road surface geometric model is facilitated.

In a second aspect, embodiments of the present application provide a road modeling apparatus based on a laser point cloud, the apparatus including: the data acquisition module is used for acquiring three-dimensional point cloud data of a road, wherein the three-dimensional point cloud data comprises elevation values of a scanning line and a plurality of laser points;

the first processing module is used for calculating the change rate of the elevation value of each laser point and the adjacent elevation value based on the scanning line to obtain a plurality of elevation change rates, and comparing each elevation change rate with a preset change rate threshold value to obtain a laser point set, wherein the adjacent elevation value is the elevation value of the adjacent node of each laser point;

The second processing module is used for carrying out clustering processing based on the laser point set to obtain a plurality of point blocks, and carrying out filtering and vector processing on each point block to obtain a plurality of roadside vectors;

the geometric construction module is used for constructing a pavement geometric model according to each roadside line vector;

and the generation module is used for carrying out texture construction on the road surface geometric model to generate a road model.

In a third aspect, an embodiment of the present application provides an electronic device, including a processor, a memory, a user interface, and a network interface, where the memory is configured to store instructions, and the user interface and the network interface are configured to communicate with other devices, and the processor is configured to execute the instructions stored in the memory, so that the electronic device performs the method provided in any one of the first aspect above.

In a fourth aspect, embodiments of the present application provide a computer-readable storage medium storing instructions that, when executed, perform the method of any one of the first aspects provided above.

In summary, one or more technical solutions provided in the embodiments of the present application at least have the following technical effects or advantages:

1. The method adopts the technical means that the elevation value is used as a judging condition, clustering, filtering and vector processing are carried out, a geometric model is obtained by construction, and then the geometric model is constructed by texture, so that the road model is generated, and the problem that unstructured point cloud data cannot be quickly generated into a high-precision road model in the related technology is effectively solved. According to the embodiment of the application, the road model is generated by performing coarse extraction and then fine extraction and performing texture construction, so that the high-precision road model can be quickly generated by unstructured point cloud data, and the three-dimensional reconstruction of the road traffic infrastructure in a large range is realized.

2. By calculating the elevation change rate, the position relation of the laser points can be reflected, and accurate road information can be obtained.

3. And the points larger than the first angle threshold value are removed, so that the subsequent generation of the high-precision road model is facilitated.

4. The points on the road side line are homogenized and correspond to each other one by one, so that a road surface geometric model can be quickly generated.

Drawings

FIG. 1 is a flow chart of a road modeling method based on laser point clouds according to one embodiment of the present application;

FIG. 2 is a schematic flow chart showing a sub-step of step S200 in FIG. 1;

FIG. 3 is a schematic flow chart of a sub-step of step S300 in FIG. 1;

FIG. 4 is a pipeline filtering schematic diagram of a laser point cloud-based road modeling method provided in one embodiment of the present application;

FIG. 5 is a schematic flow chart of a sub-step of step S400 in FIG. 1;

FIG. 6 is a schematic flow chart showing a sub-step of step S440 in FIG. 5;

FIG. 7 is an insertion vector point schematic diagram of a laser point cloud-based road modeling method provided by one embodiment of the present application;

FIG. 8 is a schematic diagram of a road surface set model of a road modeling method based on laser point clouds according to one embodiment of the present application;

FIG. 9 is a schematic structural diagram of a road modeling apparatus based on laser point clouds according to an embodiment of the present application;

fig. 10 is a schematic structural diagram of an electronic device according to an embodiment of the present application.

Detailed Description

In order to make those skilled in the art better understand the technical solutions in the present specification, the technical solutions in the embodiments of the present specification will be clearly and completely described below with reference to the drawings in the embodiments of the present specification, and it is obvious that the described embodiments are only some embodiments of the present application, but not all embodiments.

In the description of embodiments of the present application, words such as "for example" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described herein as "such as" or "for example" should not be construed as preferred or advantageous over other embodiments or designs. Rather, the use of words such as "or" for example "is intended to present related concepts in a concrete fashion.

In the description of the embodiments of the present application, the term "plurality" means two or more. For example, a plurality of systems means two or more systems, and a plurality of screen terminals means two or more screen terminals. Furthermore, the terms "first," "second," and the like, are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating an indicated technical feature. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include one or more such feature. The terms "comprising," "including," "having," and variations thereof mean "including but not limited to," unless expressly specified otherwise.

The embodiment of the application provides a road modeling method, a device, electronic equipment and a readable storage medium based on laser point cloud, wherein the road modeling method based on the laser point cloud firstly acquires three-dimensional point cloud data of a road, the three-dimensional point cloud data comprises scanning lines and elevation values of a plurality of laser points, and data support is provided for subsequent generation of a high-precision road model by acquiring the three-dimensional point cloud data; based on the scanning lines, calculating the change rates of the elevation values of the laser points and the adjacent elevation values to obtain a plurality of elevation change rates, and comparing the elevation change rates with a preset change rate threshold to obtain a laser point set, wherein the adjacent elevation values are the elevation values of the adjacent nodes of the laser points, so that the subsequent clustering treatment is facilitated; clustering processing is carried out on the basis of the laser point set to obtain a plurality of point blocks, filtering and vector processing are carried out on each point block to obtain a plurality of road edge vectors, noise points can be removed, fine extraction is carried out, and the subsequent generation of a high-precision road model is facilitated; constructing a road surface geometric model according to each road boundary vector; and carrying out texture construction on the road surface geometric model to generate a road model, and carrying out texture construction to enable the road model to be more vivid and generate a high-precision road model. Compared with the prior art that the unstructured point cloud data cannot be quickly generated into the high-precision road model, the method and the device can quickly generate the unstructured point cloud data into the high-precision road model through coarse extraction and then fine extraction and texture construction.

The road modeling method based on the laser point cloud can be applied to the construction of road scenes in unmanned driving, such as the rapid construction of models of planar elements of sidewalks, green belts, safety islands, intersections and the like, and can rapidly generate high-precision road models from unstructured point cloud data.

The technical scheme provided by the embodiment of the application is further described below with reference to the accompanying drawings.

Referring to fig. 1, fig. 1 is a flow chart of a road modeling method based on laser point cloud according to an embodiment of the present application. The laser point cloud-based road modeling method is applied to a laser point cloud-based road modeling apparatus, and is executed by an electronic device or a processor in a readable storage medium, and includes steps S100, S200, S300, S400, and S500.

Step S100, three-dimensional point cloud data of a road are obtained, wherein the three-dimensional point cloud data comprise elevation values of a scanning line and a plurality of laser points.

In an embodiment, a plurality of laser radars are installed in an unmanned vehicle, road information is collected through each laser radar, and collected data comprises elevation values of a scanning line and a plurality of laser points, and further comprises a point cloud density, a time stamp, position information in space of each point and the like. The scanning line is a reference for scanning a plurality of points and provides aspects for calculation among the points; the elevation value is the elevation value of each point relative to the reference plane, reflects the position of the point in the vertical direction, and is convenient for constructing a road model according to each laser point and the elevation value of the laser point. And reading data acquired by the laser radar through a preset interface, processing and converting the acquired data to obtain three-dimensional point cloud data of the road, and providing data support for the construction of a subsequent road model. Wherein the pre-set interface may be a read function provided by the pyntcloud library.

Step 200, calculating the change rates of the elevation values and the adjacent elevation values of the laser points based on the scanning lines to obtain a plurality of elevation change rates, and comparing each elevation change rate with a preset change rate threshold to obtain a laser point set, wherein the adjacent elevation values are the elevation values of the adjacent nodes of each laser point.

In an embodiment, the adjacent elevation values are elevation values of adjacent nodes of each laser point, the elevation values and the adjacent elevation values of each laser point are calculated based on a scanning line to obtain a plurality of elevation change rates, the elevation values and the adjacent elevation values of each laser point are calculated based on the scanning line by using a preset change rate algorithm to obtain a plurality of elevation change rates, and the calculation of the elevation change rates is beneficial to the subsequent acquisition of a laser point set for clustering.

Wherein the rate of change algorithm is expressed as:

In another embodiment, the preset change rate threshold is obtained by setting by a professional according to experience, and the elevation change of adjacent laser points on the pavement and the pavement is small, so that the elevation change rate is low; the x values of adjacent laser points on the curb are very close, and the elevation change rate is large. As shown in fig. 2, the elevation change rates are compared with a preset change rate threshold value to obtain a laser point set, including but not limited to the following steps:

Step S210, adding laser points corresponding to the elevation change rate into a preset initial point set under the condition that the elevation change rate is larger than a change rate threshold.

In some possible embodiments of the present application, when the elevation change rate is greater than the change rate threshold, it indicates that the greater the elevation change rate, the closer the position of the laser point is, the laser point with the greater elevation change rate is selected, the laser point corresponding to the elevation change rate is added to a preset initial point set, and the laser points meeting the conditions are sequentially added, so that the laser point set is beneficial to subsequent acquisition.

In step S220, under the condition that the elevation change rate is less than or equal to the change rate threshold, the laser points corresponding to the elevation change rate are not added into the preset initial point set.

In some possible embodiments of the present application, when the elevation change rate is less than or equal to the change rate threshold, the smaller the elevation change rate is, the farther the laser point is located, the laser point corresponding to the elevation change rate is not added to the preset initial point set, and the laser point can be added to other point sets.

In step S230, the initial point set is used as the laser point set.

In some possible embodiments of the present application, according to step S210 and step S220, the laser points satisfying the condition are added into the initial point set, and the initial point set is used as the laser point set, so as to facilitate subsequent clustering of the laser point set.

Step S300, clustering processing is carried out based on the laser point set to obtain a plurality of point blocks, and filtering and vector processing are carried out on each point block to obtain a plurality of curbstone vectors.

In an embodiment, the point blocks are represented in a list or tuple form, the points with a relatively close distance are classified into a category based on the laser point set according to the driving direction, the points are added into one point block, then pipeline filtering processing is carried out on each laser point in each point block, noise points are removed, vectorization is carried out on each point block, and a plurality of roadside vectors are obtained, so that the subsequent construction of a geometric model is facilitated.

As shown in fig. 3, the clustering process is performed based on the laser point set to obtain n point blocks, including but not limited to the following steps:

step S310, a first empty point block is created, and a first point in the laser point set is stored in the first empty point block to obtain a first point block.

In some possible embodiments of the present application, a null point block is first created, which may be represented as a list or tuple. And selecting one point from the laser point set as a first point, storing the first point in the laser point set into a first empty point block in a list or tuple form to obtain a first point block, and facilitating the subsequent construction of the road edge vector according to the point block. The selecting of one point from the laser point set as the first point may be random, or the laser points in the laser point set may be ordered and selected in sequence.

Step S320, calculating the distance between the second point in the laser point set and each laser point in the first point block to obtain a distance value.

In some possible embodiments of the present application, the set of laser points has a plurality of laser points, one point is selected from the set of laser points as a second point, and the second point is calculated from the distance between each laser point in the first point block to obtain a distance value. The method comprises the following steps: and carrying out difference calculation on the x and y values of the second point and all points in each laser point in the first point block, representing the difference as delta x and delta y, and selecting the minimum difference value from all the difference values to obtain a distance value, thereby being beneficial to clustering according to the distance value. One point can be selected from the laser point set as a second point, or the laser points in the laser point set can be selected randomly, or the laser points in the laser point set can be ordered and selected according to the sequence.

Step S330, under the condition that the distance value is larger than the preset distance threshold value, creating a second empty point block, and adding a second point in the laser point set into the second empty point block to obtain a second point block.

In some possible embodiments of the present application, the preset distance threshold includes a threshold of x and a threshold of y, and in a case where the distance value is greater than the preset distance threshold, that is, Δx is greater than the threshold of x or Δy is greater than the threshold of y, a second null point block is created, which may be represented as a list or tuple. And adding a second point in the laser point set into the second empty point block in the form of a list or a tuple to obtain a second point block. The road edge vector is beneficial to the subsequent construction according to the point blocks.

In step S340, if the distance value is less than or equal to the preset distance threshold, adding the second point in the laser point set to the first empty point block.

In some possible embodiments of the present application, according to step S330, when the distance value is smaller than or equal to the preset distance threshold, that is, Δx is smaller than or equal to the threshold of x or Δy is smaller than or equal to the threshold of y, the first point in the set of laser points is stored in the second empty point block in the form of a list or tuple, so as to obtain a first point block, which is favorable for obtaining a roadside vector according to the subsequent point block construction.

And S350, constructing a plurality of point blocks by the first point block and the second point block.

In some possible embodiments of the present application, two or more dot blocks are formed by obtaining a first dot block and a second dot block. It should be noted that, a third dot block may also be formed, for example, a distance value is obtained by performing distance calculation on a third dot in the laser dot set and each laser dot in the first dot block, and when the distance value is greater than a preset distance threshold, a distance value is obtained by performing distance calculation on the third dot in the laser dot set and each laser dot in the second dot block, and when the distance value is greater than the preset distance threshold, a third empty dot block is created, and when the second dot in the laser dot set is added into the third empty dot block in the form of a list or a tuple, a third dot block is obtained. The first dot block, the second dot block, and the third dot block are configured into a plurality of dot blocks. More dot blocks can be formed, and the construction method is similar to that described above, and is not repeated here. By forming a plurality of point blocks, the subsequent construction is facilitated to obtain the roadside vector.

In an embodiment, in case of two curbs, the construction of the two curbs vectors is performed from the first point block and the second point block. Filtering and vector processing are performed on each point block to obtain a plurality of curbside vectors, including but not limited to: in each point block, calculating a plane included angle between a current node and an adjacent node adjacent to the current node in the point block, wherein the adjacent node adjacent to the current node is a previous node of the current node and a next node of the current node, and the plane included angle is an included angle formed by an edge formed by the current node and the previous node and an edge formed by the current node and the next node. Comparing the plane included angle with a preset first angle threshold value, performing difference calculation on the plane included angle and 180 degrees to obtain a difference value, and indicating that the plane included angle is close to 180 degrees and retaining the current node under the condition that the difference value is smaller than or equal to the first angle threshold value; and under the condition that the difference value is larger than the first angle threshold value, the plane included angle is far away from 180 degrees, and the current node is deleted. The nodes in each point block are filtered in sequence to obtain filtering nodes, so that the method is beneficial to forming a more accurate road model subsequently.

As shown in FIG. 4, each clustered point block has a plurality of nodes, the current node is m1, adjacent nodes adjacent to the current node are m2 and m3, and a plane included angle is obtained according to an angle formed by the edge m1m2 and the edge m1m 3. The preset first angular threshold may be 5 degrees, 10 degrees, etc., which will not be described herein. Comparing the plane included angle with a preset first angle threshold value, performing difference calculation on the plane included angle and 180 degrees to obtain a difference value, and indicating that the plane included angle is close to 180 degrees and retaining the current node under the condition that the difference value is smaller than or equal to the first angle threshold value; and under the condition that the difference value is larger than the first angle threshold value, the plane included angle is far away from 180 degrees, and the current node is deleted. The nodes in each point block are filtered in sequence to obtain filtering nodes, so that the method is beneficial to forming more accurate road models subsequently. The closer the plane included angle is to 180 degrees, the straighter the curb line is.

In another embodiment, the filtering node is vectorized, specifically: and (3) reserving two nodes, namely a first node and a last node, at each filtering node in each point block, setting a point at a certain distance d in the middle, and outputting the point even if the distance d is short at a place with a corner, so as to form a roadside line vector. And obtaining a plurality of roadside vectors according to the plurality of point blocks in the vector mode, so that the geometrical model can be constructed according to the roadside vectors.

Step S400, constructing a pavement geometric model according to each roadside line vector.

In one embodiment, the plurality of curbs vectors are two curbs, each having a plurality of vector points. As shown in fig. 5, constructing a geometric model of a road surface from a curbside vector includes, but is not limited to, the steps of:

in step S410, the lengths of the two curbs are compared to determine a first curbs and a second curbs, wherein the length of the first curbs is greater than the length of the second curbs.

In one embodiment, the lengths of two curbs are calculated, with the longer curbs being denoted as the first curbs, denoted as s1, and the shorter curbs being denoted as the second curbs, denoted as s2. The longer road edge can be used as a second road edge, and the shorter road edge can be used as a first road edge, so that the construction of the road surface geometric model is not influenced.

Step S420, homogenizing the vector points of the first route edge to obtain a first uniform route edge.

In an embodiment, according to the first route determined in step S410, the vector points are set at intervals of a preset length, for example, one vector point is set at intervals of 5 meters, and according to the length S1 of the first route, there are N vector points on the route, where n=ceil (S1/5) +1. And uniformly dividing the first route edge according to the N vector points to obtain a first uniform route edge, which is beneficial to the subsequent route edge correspondence.

Step S430, homogenizing the vector points of the second uniform curb based on the number of the vector points of the first uniform curb to obtain the second uniform curb.

In an embodiment, N vector points are obtained according to the homogenization of the first route edge, and for convenience, the number of vector points of the second route edge is also N, so the distance between the vector points is d=s2/(N-1). And homogenizing the second curb according to the interval D to obtain a second uniform curb, which is beneficial to the subsequent curb correspondence.

Step S440, vector points of the first uniform road edge and vector points of the second uniform road edge are in one-to-one correspondence, and corresponding vector points of the first road edge and corresponding vector points of the second road edge are obtained.

In an embodiment, since more vector points are needed to represent the shape of the curved road, the vector points of the first uniform road edge and the vector points of the second uniform road edge are in one-to-one correspondence, so that the calculation amount is reduced, the road surface geometric model is generated quickly, and the constructed road surface model is smoother and is more attached to a real road surface. As shown in fig. 6, the vector points of the first uniform road edge and the vector points of the second uniform road edge are in one-to-one correspondence to obtain the corresponding vector points of the first road edge and the corresponding vector points of the second road edge, including but not limited to the following steps:

in step S441, the included angle between the current node of the first uniform road edge, the first neighboring node of the current node, and the second neighboring node of the current node is calculated, so as to obtain the included angle value.

In some embodiments of the present application, according to the first uniform road edge, one node of the first uniform road edge is selected as a current node, denoted as p12, a previous node of the current node is a first neighboring node of the current node, denoted as p11, a next node of the current node is a second neighboring node of the current node, denoted as p13. And calculating an included angle formed by an edge p11p12 formed by the current node and the first adjacent node and an edge p12p13 formed by the current node and the second adjacent node to obtain an included angle value. The vector points are inserted according to the included angle values in the follow-up process, and one-to-one correspondence is conducted.

In step S442, a first vector point is inserted between the current node and the first neighboring node, and a second vector point is inserted between the current node and the second neighboring node when the included angle value is greater than a preset second angle threshold.

In some embodiments of the present application, the preset second angular threshold is empirically set by a practitioner. The included angle value is larger than a preset second angle threshold value, so that the bending degree of the first uniform road edge is larger, a first vector point is inserted between the current node and the first adjacent node, and a second vector point is inserted between the current node and the second adjacent node, so that the line is smoother, and the generated road model is more accurate. It should be noted that, all nodes are traversed until the included angle value formed by all vector points is smaller than the preset second angle threshold value.

In other embodiments of the present application, when the included angle value is less than or equal to the preset second angle threshold value, it indicates that the first uniform road edge has a smaller degree of curvature at this point, and the route is smoother without inserting vector points.

In step S443, a third vector point is inserted at a position corresponding to the position between the current node and the first neighboring node, and a fourth vector point is inserted at a position corresponding to the position between the current node and the second neighboring node in the second uniform road edge.

In some embodiments of the present application, according to the vector inserted in the first uniform roadside at step S442, since the number of vector points in the second uniform roadside is the same as the data of vector points in the first uniform roadside and is also uniformly distributed at the interval D, the current node, the first neighboring node, and the second neighboring node in the first uniform roadside have corresponding points on the second uniform roadside. Then, in the second uniform roadside, a vector point is also inserted at a position corresponding to between the current node and the first neighboring node, which is a third vector point, and a fourth vector point is also inserted at a position corresponding to between the current node and the second neighboring node, so that the vector points on the first uniform roadside and the second uniform roadside are in one-to-one correspondence. Through carrying out the one-to-one correspondence with two curb lines, not only can reduce the calculated amount, can also make the road surface model of constructing comparatively smooth. Correspondingly, when the first uniform road edge is inserted into the vector points, the vector points are also inserted into the corresponding positions of the second uniform road edge, so that all the vector points are in one-to-one correspondence.

In step S444, all nodes of the first uniform road edge are used as corresponding vector points of the first road edge, and all nodes of the second uniform road edge are used as corresponding vector points of the second road edge.

In some embodiments of the present application, according to steps S441 to S443, all nodes of the first uniform road edge are used as corresponding vector points of the first road edge, and all nodes of the second uniform road edge are used as corresponding vector points of the second road edge, so that the vector points on the first road edge and the second road edge are in one-to-one correspondence, and the calculation amount can be reduced.

As shown in fig. 7, the first uniform road edge is homogenized to obtain a first uniform road edge, and the first uniform road edge includes vector points p11, p12, p13, and p14. Homogenizing the second curb to obtain a second uniform curb, wherein the second uniform curb comprises vector points p21, p22, p23 and p24. On the first uniform roadside line, the current node is p12, the first adjacent node is p11, the second adjacent node is p13, the two sides are p11p12 and p12p13, an included angle formed by the two sides is alpha, and under the condition that alpha is larger than a preset second angle threshold value, the node p1x1 is inserted between the p11 and the p12, and the node p1x2 is inserted between the p12 and the p 13. Correspondingly, the node p2x1 is inserted between the p21 and the p22, and the node p2x2 is inserted between the p22 and the p23, so that the first uniform curb line and the second uniform curb line are in one-to-one correspondence, and the calculation amount of the subsequent construction of the set model is reduced.

Step S450, connecting the corresponding vector point on the first roadside with the corresponding vector point on the second roadside to form a plurality of triangles, and forming the road surface geometric model by the plurality of triangles.

In an embodiment, a first point of the corresponding vector points on the first roadside is connected with a first point of the corresponding vector points on the second roadside, then the first point of the corresponding vector points on the second roadside is connected with a second point of the corresponding vector points on the first roadside, the second point of the corresponding vector points on the first roadside is connected with a second point of the corresponding vector points on the second roadside, the second point of the corresponding vector points on the second roadside is connected with a third point of the corresponding vector points on the first roadside, the corresponding vector points are sequentially connected according to the mode, so that a plurality of triangles are formed, and the plurality of sequentially continuous triangles form a road geometric model, so that the road model is generated according to the geometric model.

As shown in fig. 8, the corresponding vector points on the first roadside are q11, q12, q13, q14, q15, q16 and q17, respectively, the corresponding vector points on the second roadside are q21, q22, q23, q24, q25, q26 and q27, respectively, q11 is connected with q21, q21 is connected with q12, q12 is connected with q22, q22 is connected with q23, and so on, to form a plurality of triangles, and the triangles form a road surface set model, so that the road model can be generated according to the geometric model.

And S500, performing texture construction on the road surface geometric model to generate a road model.

In an embodiment, a preset texture picture is obtained, and the texture picture is a prepared road picture, and the picture is directly read through a data reading interface. And placing the texture picture above the pavement aggregate model, and constructing textures to generate a road model. The road model generation method can be used for modeling on sidewalks, green belts, safety islands, intersections and the like according to the road model generation method, is beneficial to simulating real road intersections and realizes three-dimensional reconstruction of road traffic infrastructures in a large range.

As shown in fig. 9, an embodiment of the present application provides a road modeling apparatus 100 based on laser point cloud, where the apparatus 100 obtains three-dimensional point cloud data of a road through a data obtaining module 110, the three-dimensional point cloud data includes elevation values of a plurality of laser points and a scan line, and provides data support for subsequent generation of a high-precision road model by obtaining the three-dimensional point cloud data; then, calculating the change rate of the elevation value of each laser point and the adjacent elevation value based on the scanning line by the first processing module 120 to obtain a plurality of elevation change rates, and comparing each elevation change rate with a preset change rate threshold value to obtain a laser point set, wherein the adjacent elevation value is the elevation value of the adjacent node of each laser point, which is beneficial to the subsequent clustering; clustering is carried out based on the laser point set; clustering is performed on the basis of the laser point set through the second processing module 130 to obtain a plurality of point blocks, filtering and vector processing are performed on each point block to obtain a plurality of road edge vectors, noise points can be removed, fine extraction is performed, and subsequent generation of a high-precision road model is facilitated; a geometric construction module 140 is utilized to construct a pavement geometric model according to each roadside line vector; and finally, the road surface geometric model is subjected to texture construction by using the generating module 150 to generate a road model, and the road model is more vivid by the texture construction, so that a high-precision road model is generated.

It should be noted that the data acquisition module 110 is connected to the first processing module 120, the first processing module 120 is connected to the second processing module 130, the second processing module 130 is connected to the geometry building module 140, and the geometry building module 140 is connected to the generating module 150. The road modeling method based on the laser point cloud is applied to the road modeling device 100 based on the laser point cloud, the road modeling device 100 based on the laser point cloud uses elevation values as judgment conditions, clustering, filtering and vector processing are performed, coarse extraction is performed first, fine extraction is performed, a geometric model is obtained through construction, texture construction is performed on the geometric model, and the road model can be generated by generating the road model, so that unstructured point cloud data can be quickly generated into a high-precision road model.

Also to be described is: in the device provided in the above embodiment, when implementing the functions thereof, only the division of the above functional modules is used as an example, in practical application, the above functional allocation may be implemented by different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules, so as to implement all or part of the functions described above. In addition, the embodiments of the apparatus and the method provided in the foregoing embodiments belong to the same concept, and specific implementation processes of the embodiments of the method are detailed in the method embodiments, which are not repeated herein.

The application also discloses electronic equipment. Referring to fig. 10, fig. 10 is a schematic structural view of an electronic device according to the disclosure of the embodiment of the present application. The electronic device 500 may include: at least one processor 501, at least one network interface 504, a user interface 503, a memory 505, at least one communication bus 502.

Wherein a communication bus 502 is used to enable connected communications between these components.

The user interface 503 may include a Display screen (Display) and a Camera (Camera), and the optional user interface 503 may further include a standard wired interface and a standard wireless interface.

The network interface 504 may optionally include a standard wired interface, a wireless interface (e.g., WI-FI interface), among others.

Wherein the processor 501 may include one or more processing cores. The processor 501 connects various parts throughout the server using various interfaces and lines, performs various functions of the server and processes data by executing or executing instructions, programs, code sets, or instruction sets stored in the memory 505, and invoking data stored in the memory 505. Alternatively, the processor 501 may be implemented in hardware in at least one of digital signal processing (Digital Signal Processing, DSP), field programmable gate array (Field-Programmable Gate Array, FPGA), programmable logic array (Programmable Logic Array, PLA). The processor 501 may integrate one or a combination of several of a central processing unit (Central Processing Unit, CPU), an image processor (Graphics Processing Unit, GPU), and a modem, etc. The CPU mainly processes an operating system, a user interface, an application program and the like; the GPU is used for rendering and drawing the content required to be displayed by the display screen; the modem is used to handle wireless communications. It will be appreciated that the modem may not be integrated into the processor 501 and may be implemented by a single chip.

The Memory 505 may include a random access Memory (Random Access Memory, RAM) or a Read-Only Memory (Read-Only Memory). Optionally, the memory 505 comprises a non-transitory computer readable medium (non-transitory computer-readable storage medium). Memory 505 may be used to store instructions, programs, code sets, or instruction sets. The memory 505 may include a stored program area and a stored data area, wherein the stored program area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playing function, an image playing function, etc.), instructions for implementing the above-described various method embodiments, etc.; the storage data area may store data or the like involved in the above respective method embodiments. The memory 505 may also optionally be at least one storage device located remotely from the processor 501. Referring to fig. 10, an operating system, a network communication module, a user interface module, and an application program of a road modeling method based on a laser point cloud may be included in a memory 505 as a computer storage medium.

In the electronic device 500 shown in fig. 10, the user interface 503 is mainly used for providing an input interface for a user, and acquiring data input by the user; and the processor 501 may be configured to invoke an application program in the memory 505 that stores a laser point cloud based road modeling method, which when executed by the one or more processors 501, causes the electronic device 500 to perform the method as in one or more of the embodiments described above. It should be noted that, for simplicity of description, the foregoing method embodiments are all expressed as a series of action combinations, but it should be understood by those skilled in the art that the present application is not limited by the order of actions described, as some steps may be performed in other order or simultaneously in accordance with the present application. Further, those skilled in the art will also appreciate that the embodiments described in the specification are all preferred embodiments, and that the acts and modules referred to are not necessarily required in the present application.

In the foregoing embodiments, the descriptions of the embodiments are emphasized, and for parts of one embodiment that are not described in detail, reference may be made to related descriptions of other embodiments.

In the several embodiments provided herein, it should be understood that the disclosed apparatus may be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative, such as a division of units, merely a division of logic functions, and there may be additional divisions in actual implementation, such as multiple units or components may be combined or integrated into another system, or some features may be omitted, or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be through some service interface, device or unit indirect coupling or communication connection, electrical or otherwise.

The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed over a plurality of 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.

In addition, each functional unit in each embodiment of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.

The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable memory. Based on such understanding, the technical solution of the present application may be embodied in essence or a part contributing to the prior art or all or part of the technical solution in the form of a software product stored in a memory, including several instructions for causing a computer device (which may be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the methods of the embodiments of the present application. And the aforementioned memory includes: various media capable of storing program codes, such as a U disk, a mobile hard disk, a magnetic disk or an optical disk.

The above are merely exemplary embodiments of the present disclosure and are not intended to limit the scope of the present disclosure. That is, equivalent changes and modifications are contemplated by the teachings of this disclosure, which fall within the scope of the present disclosure. Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure.

This application is intended to cover any adaptations, uses, or adaptations of the disclosure following, in general, the principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a scope and spirit of the disclosure being indicated by the claims.

Claims

1. A road modeling method based on a laser point cloud, the method comprising:

constructing a road surface geometric model according to each road edge vector;

2. The method of claim 1, wherein calculating the change rate of the elevation value and the adjacent elevation value of each laser point based on the scan line to obtain a plurality of elevation change rates includes:

wherein the rate of change algorithm is expressed as:

3. The method of claim 1, wherein comparing each of the elevation change rates with a preset change rate threshold value to obtain a set of laser points comprises:

And taking the initial point set as the laser point set.

4. The method according to claim 1, wherein the clustering based on the laser point set to obtain n point blocks includes:

5. The method of claim 1, wherein said filtering and vector processing each of said blocks of points to obtain a plurality of curbside vectors, comprising:

And vectorizing the filtering nodes to obtain a plurality of roadside vectors.

6. The method of claim 1, wherein a plurality of said curbs vectors are two curbs, each said curbs having a plurality of vector points;

7. The method of claim 6, wherein the performing one-to-one correspondence between the vector points of the first uniform road edge and the vector points of the second uniform road edge to obtain the corresponding vector points of the first road edge and the corresponding vector points of the second road edge comprises:

inserting a third vector point at a position corresponding to the position between the current node and the first adjacent node in the second uniform road edge, and inserting a fourth vector point at a position corresponding to the position between the current node and the second adjacent node; and taking all nodes of the first uniform road edge as corresponding vector points of the first road edge, and taking all nodes of the second uniform road edge as corresponding vector points of the second road edge.

8. A laser point cloud based road modeling apparatus, the apparatus comprising:

a data acquisition module (110) for acquiring three-dimensional point cloud data of a road, wherein the three-dimensional point cloud data comprises elevation values of a scanning line and a plurality of laser points;

the first processing module (120) is configured to calculate, based on the scan lines, a change rate of each elevation value of the laser points and an adjacent elevation value, so as to obtain a plurality of elevation change rates, and compare each elevation change rate with a preset change rate threshold value, so as to obtain a laser point set, where the adjacent elevation value is an elevation value of an adjacent node of each laser point;

the second processing module (130) is used for carrying out clustering processing based on the laser point set to obtain a plurality of point blocks, and carrying out filtering and vector processing on each point block to obtain a plurality of roadside vectors;

a geometric construction module (140) for constructing a road surface geometric model according to each of the road edge vectors;

and the generation module (150) is used for carrying out texture construction on the road surface geometric model to generate a road model.

9. An electronic device comprising a processor (501), a memory (505), a user interface (503), a communication bus (502) and a network interface (504), the processor (501), the memory (505), the user interface (503) and the network interface (504) being respectively connected to the communication bus (502), the memory (505) being for storing instructions, the user interface (503) and the network interface (504) being for communicating to other devices, the processor (501) being for executing the instructions stored in the memory (505) for causing the electronic device (500) to perform the method according to any of claims 1-7.

10. A computer readable storage medium storing instructions which, when executed, perform the method of any one of claims 1-7.