CN116578891B

CN116578891B - Road information reconstruction method, terminal and storage medium

Info

Publication number: CN116578891B
Application number: CN202310861532.3A
Authority: CN
Inventors: 徐显杰; 赵伟亭; 刘�东
Original assignee: Suoto Hangzhou Automotive Intelligent Equipment Co Ltd; Tianjin Soterea Automotive Technology Co Ltd
Current assignee: Suoto Hangzhou Automotive Intelligent Equipment Co Ltd; Tianjin Soterea Automotive Technology Co Ltd
Priority date: 2023-07-14
Filing date: 2023-07-14
Publication date: 2023-10-03
Anticipated expiration: 2043-07-14
Also published as: CN116578891A

Abstract

The invention provides a road information reconstruction method, a terminal and a storage medium, wherein the method comprises the following steps: dividing a target road into a plurality of sub-road sections based on a first preset length, and determining aggregate track data of each sub-road section, wherein for each sub-road section, the aggregate track data is used for representing a sampling point set for collecting geographic position information when a plurality of vehicles run on the sub-road section; for each sub-road section, carrying out road trend analysis based on the aggregate track data of the sub-road section, and determining a target coordinate system of the sub-road section; and fitting the aggregate track data of the sub-road section in the target coordinate system of the sub-road section, and determining a plurality of standard sampling points of the sub-road section according to the fitting result, wherein the standard sampling points of each sub-road section jointly form the standard sampling points of the target road. The invention can improve the reconstruction precision of the road information.

Description

Road information reconstruction method, terminal and storage medium

Technical Field

The present invention relates to the field of intelligent driving technologies, and in particular, to a road information reconstruction method, a terminal, and a storage medium.

Background

The pre-acquisition of road information is of great importance for various driving scenarios, for example, PACC (predictive adaptive cruise control system, predictive adaptive cruise control) is based on ADAS (Advanced Driver Assistance System, advanced driving assistance system) map and ACC (Adaptive Cruise Control, adaptive cruise), and by acquiring road information of a road ahead and performing terrain matching, the engine and the gearbox are controlled according to an optimal algorithm, and optimal control of vehicle speed, gear and the like is actively achieved.

PACC needs to rely on ADAS maps to return forward road information, but many roads, especially roads other than expressways such as national roads, provinces, etc., have no corresponding road information. For roads without an ADAS map, the information of the target road is usually obtained by a road information reconstruction method, but the accuracy of road information reconstruction in the related art is low because of the complex form of most roads.

Disclosure of Invention

In view of the above, the present invention provides a road information reconstruction method, a terminal and a storage medium, which can solve the problem of low accuracy of road information reconstruction in the related art.

In a first aspect, an embodiment of the present invention provides a road information reconstruction method, including:

dividing a target road into a plurality of sub-road sections based on a first preset length, and determining aggregate track data of each sub-road section, wherein for each sub-road section, the aggregate track data is used for representing a sampling point set for collecting geographic position information when a plurality of vehicles run on the sub-road section;

for each sub-road section, carrying out road trend analysis based on the aggregate track data of the sub-road section, and determining a target coordinate system of the sub-road section;

and fitting the aggregate track data of the sub-road section in the target coordinate system of the sub-road section, and determining a plurality of standard sampling points of the sub-road section according to the fitting result, wherein the standard sampling points of each sub-road section jointly form the standard sampling points of the target road.

In one possible implementation manner, for each sub-road segment, the road trend analysis is performed based on the aggregate track data of the sub-road segment, and determining the target coordinate system of the sub-road segment includes:

for each sub-road section, carrying out principal component analysis on the aggregate track data of the sub-road section, and taking the direction of the maximum principal component as the direction of an independent variable coordinate axis;

and constructing a target coordinate system of the sub-road section based on the direction of the independent variable coordinate axis and a preset coordinate origin.

In one possible implementation manner, for each sampling point in the aggregate track data, the sampling point includes a longitude value and a latitude value, the fitting is performed on the aggregate track data of the sub-road segment in the target coordinate system of the sub-road segment, and determining the plurality of standard sampling points of the sub-road segment according to the fitting result includes:

fitting is carried out on the basis of a first preset fitting function according to the coordinate value of each sampling point in the aggregate track data of the sub-road section in the target coordinate system of the sub-road section, and a first fitting curve of the sub-road section is obtained;

and sampling the first fitting curve, determining a plurality of standard sampling points of the sub-road section, and determining a longitude value and a latitude value of each standard sampling point.

In one possible implementation, for each sampling point in the aggregate trajectory data, the sampling point further includes a height value, and after the sampling the first fitted curve to determine a plurality of standard sampling points for the sub-segment, the method further includes:

fitting is carried out on the basis of a second preset fitting function according to the coordinate value of each sampling point in the aggregate track data of the sub-road section in the target coordinate system of the sub-road section and the height value of each sampling point, so that a second fitting curve of the sub-road section is obtained;

determining a height value of each standard sampling point of the sub-road section based on a plurality of standard sampling points of the sub-road section and the second fitting curve;

and determining the gradient value and the curvature radius value of each standard sampling point according to the longitude value, the latitude value and the altitude value of each standard sampling point on the target road.

In one possible implementation, determining whether a first target vehicle is traveling on the target road;

if the first target vehicle runs on the target road, determining the running direction of the first target vehicle on the target road according to the geographical position information of the first target vehicle at a plurality of moments and the position relation of a preset first standard sampling point in the standard sampling points of the target road;

Determining a standard sampling point within a preset distance in front of the first target vehicle according to the running direction of the first target vehicle on the target road, the geographic position of the first target vehicle at the current moment and the standard sampling point of the target road;

and performing intelligent driving control on the first target vehicle based on the longitude value, the latitude value, the gradient value and the curvature radius value of the standard sampling point within the preset distance in front of the first target vehicle.

In one possible implementation, the preset area is divided into a plurality of blocks, each block uniquely corresponding to one coding block, and the determining whether the first target vehicle travels on the target road includes:

determining a coding block to which the first target vehicle belongs as a target coding block according to the geographic position of the first target vehicle at the current moment;

determining at least one target road corresponding to the target coding block according to the target coding block;

acquiring standard sampling points of each target road in the at least one target road;

based on the positional relationship of the first target vehicle and the standard sampling point of each target road in the at least one target road, whether the vehicle runs on one target road is determined.

In one possible implementation manner, the dividing the target road into a plurality of sub-road segments and determining the aggregate track data of each sub-road segment based on the first preset length includes:

taking sampling points of a second target vehicle which runs on the target road once and collects geographic position information as reference track data, and sequencing the sampling points in the reference track data according to the collection time;

determining a starting point of the target road according to the reference track data, and sequentially calculating the distance between each sampling point and the starting point;

dividing the target road into a plurality of sub-road sections based on the first preset length according to the distance between each sampling point and the starting point, determining the sampling point belonging to the sub-road section in the reference track data for each sub-road section, and determining the longitude and latitude range of the sub-road section according to the sampling point belonging to the sub-road section in the reference track data;

and for each sub-road section, determining sampling points when other vehicles run on the sub-road section based on the longitude and latitude range of the sub-road section, and obtaining the aggregate track data of the sub-road section.

In one possible implementation manner, the aggregate track data of each sub-road segment together form the aggregate track data of the target road, and before the road trend analysis is performed on each sub-road segment based on the aggregate track data of the sub-road segment, the method further includes:

Determining a mapping relation between a length value and a fitting goodness value according to the aggregate track data of the target road, wherein in the mapping relation, for any length value, the fitting goodness value uniquely corresponding to the length value is used for representing the average value of the fitting goodness value of the first preset fitting function corresponding to each sub-road section when the length of each sub-road section is the length value, and the fitting goodness value is the evaluation value of the first preset fitting function;

according to the mapping relation, determining a length value corresponding to the maximum value of the goodness-of-fit value as a second preset length;

and dividing the target road into a plurality of sub-road sections again based on the second preset length and the aggregate track data of the target road, and determining the aggregate track data of each sub-road section.

In a second aspect, embodiments of the present invention provide a terminal comprising a memory, a processor and a computer program stored in the memory and executable on the processor, the processor implementing the steps of the method as described above in the first aspect or any one of the possible implementations of the first aspect when the computer program is executed.

In a third aspect, embodiments of the present invention provide a computer readable storage medium storing a computer program which, when executed by a processor, implements the steps of the method as described above in the first aspect or any one of the possible implementations of the first aspect.

Compared with the prior art, the embodiment of the invention has the beneficial effects that:

when the road information of the target road is reconstructed, the target road is divided into a plurality of sub-road sections, and the aggregate track data of each sub-road section is determined. The road trend of each sub-road section is analyzed based on the aggregate track data of the sub-road section, a target coordinate system corresponding to the sub-road section is established, the aggregate track of the sub-road section is fitted under the target coordinate system of the sub-road section, the establishment of a fitting function can be ensured, the fitting precision is improved, and the sub-road section is resampled based on the fitting result of each sub-road section, so that the standard sampling point of the target road section is obtained. The method provided by the embodiment of the invention can improve the reconstruction accuracy of the road information.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed in the embodiments or the description of the prior art will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.

Fig. 1 is a flowchart of an implementation of a road information reconstruction method according to an embodiment of the present invention;

FIG. 2 is a schematic diagram of a relationship between a road trend and a coordinate system according to an embodiment of the present invention;

FIG. 3 is a schematic diagram of a first fitting curve and a second fitting curve obtained by fitting an aggregation function of a sub-road segment according to an embodiment of the present invention;

FIG. 4 is a schematic diagram of calculating a standard sampling point gradient value according to an embodiment of the present invention;

fig. 5 is a schematic diagram of a fitting result of fitting aggregated track data of a sub-section based on a cubic polynomial according to an embodiment of the present invention;

FIG. 6 is a schematic diagram of a mapping relationship between a length value and a goodness-of-fit value according to an embodiment of the present invention;

fig. 7 is a schematic structural diagram of a road information reconstruction device according to an embodiment of the present invention;

fig. 8 is a schematic diagram of a terminal according to an embodiment of the present invention.

Detailed Description

In the following description, for purposes of explanation and not limitation, specific details are set forth such as the particular system architecture, techniques, etc., in order to provide a thorough understanding of the embodiments of the present invention. It will be apparent, however, to one skilled in the art that the present invention may be practiced in other embodiments that depart from these specific details. In other instances, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present invention with unnecessary detail.

For the purpose of making the objects, technical solutions and advantages of the present invention more apparent, the following description will be made by way of specific embodiments with reference to the accompanying drawings.

The method provided by the embodiment of the invention can be applied to passenger vehicles and commercial vehicles. Referring to fig. 1, a flowchart of an implementation of a road information reconstruction method provided by an embodiment of the present invention is shown, and details are as follows:

in step 101, based on the first preset length, the target road is divided into a plurality of sub-road segments, and aggregate track data of each sub-road segment is determined, where for each sub-road segment, the aggregate track data is used to represent a set of sampling points for collecting geographic location information when a plurality of vehicles travel on the sub-road segment.

In the embodiment of the invention, in the process of reconstructing the target road information, because the reconstruction is required based on the historical driving track of the vehicle on the target road, the road length is generally longer, the road shape is continuously changed, and in order to improve the reconstruction accuracy, in the embodiment of the invention, the target road is optionally divided into a plurality of sub-road sections based on the first preset length.

The first preset length may be determined based on a target road to be reconstructed, for example, the target road has a higher complexity, there are multiple turns and multiple uphill and downhill sections, and the first preset length is smaller, such as 1km, and if the target road has a lower complexity, such as a relatively straight national road or province road, the first preset length is larger, such as 2km. The embodiment of the invention does not limit the specific value of the first preset length.

In the embodiment of the invention, when a vehicle with the intelligent equipment runs on a road, vehicle position coordinates and altitude data are acquired in real time, wherein the position coordinates comprise longitude and latitude information of each sampling point. A plurality of vehicles travel on the same road a plurality of times, so that a large number of sampling points can be accumulated, and the sampling points are used as aggregate track data of the target road. Based on the segmentation of step 101, aggregate trajectory data for each sub-segment may be acquired.

Optionally, in an embodiment of the present invention, the reference coordinate system adopts a geographic coordinate system, where the geographic coordinate system is a coordinate system that uses a three-dimensional sphere to define the earth surface location, so as to implement referencing to earth surface points through longitude and latitude. Other coordinate systems may be used as the reference coordinate system, which is not limited in the embodiment of the present invention, and the relative position of the reference coordinate system and the target road is fixed after the reference coordinate system is set.

In one possible implementation manner, sampling points for collecting geographic position information once the second target vehicle runs on the target road are used as reference track data, and the sampling points in the reference track data are ordered according to the collecting time; determining a starting point of a target road according to the reference track data, and sequentially calculating the distance between each sampling point and the starting point; dividing a target road into a plurality of sub-road sections based on a first preset length according to the distance between each sampling point and a starting point, determining the sampling point belonging to the sub-road section in the reference track data for each sub-road section, and determining the longitude and latitude range of the sub-road section according to the sampling point belonging to the sub-road section in the reference track data; and for each sub-road section, determining sampling points when other vehicles run on the sub-road section based on the longitude and latitude range of the sub-road section, and obtaining the aggregate track data of the sub-road section.

The track data of one vehicle traveling at a time has a strict time sequence compared with the aggregate track data formed by a plurality of vehicles traveling at a plurality of times. Therefore, in the embodiment of the invention, one vehicle is selected as the second target vehicle, and the sampling point data which is collected once and sequenced according to the time sequence and is used as the reference track data of the target road. Alternatively, the expression form of the reference trajectory data is shown in table 1 below. The second target vehicle is an arbitrarily selected one of the travel locus data-related vehicles.

TABLE 1

A sampling Point sequence number	B vehicle	C device ID	Time D	E longitude value	F latitude value	G altitude	H adjacent point distance	I cumulative distance
									1	Second target vehicle	915*****010	2022/11/6 21:20:40	117.969908	24.397458	8	0	0
2	Second target vehicle	915*****010	2022/11/6 21:20:41	117.969859	24.397597	8	16.178619	16.178619
									3	Second target vehicle	915*****010	2022/11/6 21:20:42	117.969814	24.397736	8	16.058607	32.237227
4	Second target vehicle	915*****010	2022/11/6 21:20:43	117.96977	24.397876	8	16.136482	48.373708
									5	Second target vehicle	915*****010	2022/11/6 21:20:44	117.969725	24.398017	8	16.271117	64.644825
6	Second target vehicle	915*****010	2022/11/6 21:20:45	117.969679	24.398158	8	16.299863	80.944689
									7	Second target vehicle	915*****010	2022/11/6 21:20:46	117.96963	24.398296	9	16.073241	97.01793
8	Second target vehicle	915*****010	2022/11/6 21:20:47	117.96958	24.39843	9	15.685005	112.702934
									9	……	……	……	……	……	……	……	……

In table 1, each row represents a sample point and is sorted according to time sequence information, as in column D of table 1 above, and optionally, after time sorting, each sample point is numbered sequentially, as in column a of table 1 above.

The first sampling point in the reference track data, i.e. the sampling point with the sampling point serial number of 1 in the above table 1, is marked as the starting point of the target road. For convenience of description, a sampling point corresponding to the start point is denoted as sampling point 1.

And according to the longitude and latitude of each sampling point in the reference track data, calculating the distance between each sampling point and the adjacent last sampling point in sequence according to the E column and the F column of the table 1, and obtaining the data of the H column of the table 1. Based on the distance between two adjacent points, the distance between each sampling point and the starting point, i.e. sampling point 1, can be calculated, resulting in the data of column I in table 1 above.

According to the last data of the I column, the accumulated distance of the sampling points in the reference track data can be obtained. According to the method, the target road is segmented, and if the first preset length is 2000 meters, the standard segmentation interval is: the upper and lower limits of each interval represent the distance range between the sampling point and the starting point, i.e. the range of values of column I in Table 1 above.

After the sampling points obtained by other vehicles driving on the target road are obtained, the distribution of the sampling points of other vehicles on each sub-road section can be determined based on the longitude and latitude range of each sub-road section, and then the aggregate track data of each sub-road section is obtained. Compared with the reference track data, the aggregate track data contains more sampling points, and the result of road fitting based on the aggregate track data is more in accordance with the real road form.

In step 102, for each sub-link, a road trend analysis is performed based on the aggregate track data for that sub-link, and a target coordinate system for that sub-link is determined.

In the embodiment of the invention, the road fitting is carried out on each sub-road section by using a related fitting algorithm based on the aggregate track data of the sub-road section. Alternatively, a cubic polynomial is used for fitting. The process of fitting by using a cubic polynomial is to use a shape such asFitting each sampling point in the aggregate trajectory data based on the longitude and latitude coordinates of each sampling point, thereby enabling the morphology of the road to be represented by a smooth, continuous function. However, it is possible that each sub-section of the actual target road has a different trend. If a reference coordinate system, such as a geographic coordinate system, is used, the fitting may not be successful by a related fitting algorithm, i.e., if the reference coordinate system is used, the functional relationship may be caused to be not established. FIG. 2 is a schematic view showing the relationship between the road trend and the coordinate system according to the embodiment of the present invention, in FIG. 2, usingxoyRepresenting a reference coordinate system, if a form is used>Fitting the sub-section by a polynomial of degree three, from which function it is known that one xThe value can only correspond to oneyValues. If in the reference coordinate system, fix the east-west direction asxThe axis is in the north-south directionyThe axis, then for the road as shown in fig. 2, the functional relationship does not hold, and the direct fit cannot succeed.

Based on this, in the embodiment of the present invention, the road trend of the sub-link is analyzed based on the aggregate track data of the sub-link, and a target coordinate system corresponding to the sub-link is determinedxThe direction of the axis, as shown in FIG. 2, determines the target coordinate systemxThe axis being in figure 2Axis, object coordinate systemxAfter the axis is determined, the axis can be based on the target coordinate systemxThe axis being defined perpendicular theretoyAnd (5) an axis, thereby establishing a target coordinate system corresponding to the sub-road section.

By adopting the method provided by the embodiment of the invention, for each sub-road section, a target coordinate system corresponding to the sub-road section is independently determined according to the road trend of the sub-road section, and the setting basis of the target coordinate system corresponding to the sub-road section is that the target coordinate system of the sub-road section enables the distribution state of the aggregate track data of the sub-road section to be consistent with a fitting function, namely, under the target coordinate system of the sub-road section, the sub-road is subjected to a preset fitting functionThe aggregate track data of the segments are fitted, so that the establishment of the function relation of a preset fitting function can be ensured. For example, in accordance with a related fitting function, e.g. fitting function as a shape, e.g. The distribution relation of the aggregate track data of the sub-section in the sub-section target coordinate system satisfies onexThe value uniquely corresponds to oneyValues.

In an alternative implementation manner, for each sub-road section, performing principal component analysis on the aggregate track data of the sub-road section, and taking the direction of the maximum principal component as the direction of the independent variable coordinate axis; and constructing a target coordinate system of the sub-road section based on the direction of the independent variable coordinate axis and a preset coordinate origin.

Principal component analysis (Principal Component Analysis, PCA) is a statistical method. In the embodiment of the invention, for the aggregated track data of each sub-section, the direction of the first principal component in the aggregated track data, that is, the direction with the largest variance, is determined by a principal component analysis method, and the direction is taken as the target coordinate system of the sub-sectionxThe shaft can ensure that the function relationship is established when the aggregate track data of one sub-road section is fitted through a preset fitting function, such as a cubic polynomial function.

As shown in fig. 2, for a sub-link, the trend of the aggregate track data of the sub-link in the road is as shown in the road in fig. 2, and the target coordinate system corresponding to the sub-link is determined by a principal component analysis method The axis, i.e. +.in FIG. 2>Axis, determination->An axis, based on a preset origin, establishing and +.>Axial phaseVertical->An axis, namely obtaining the target coordinate system of the sub-section。

In step 103, in the target coordinate system of the sub-link, fitting is performed on the aggregate track data of the sub-link, and a plurality of standard sampling points of the sub-link are determined according to the fitting result, where the plurality of standard sampling points of each sub-link together form a standard sampling point of the target link.

In the embodiment of the invention, for each sub-road section, based on the target coordinate system of the sub-road section, the aggregate track data of the sub-road section is fitted to obtain a fitting result, and the fitting result is a smooth continuous curve which can be represented by a specific function. And resampling the fitting result under the target coordinate system of the sub-road section to obtain resampled points in a plurality of target coordinate systems, and restoring the resampled points to the reference coordinate system based on the mapping relation between the target coordinate system of the sub-road section and the reference coordinate system to obtain a plurality of standard sampling points of the sub-road section in the reference coordinate system.

With reference to fig. 2, assuming that the road in fig. 2 corresponds to the sub-link 3 in the target road, determining that the x-axis of the target coordinate system corresponding to the sub-link 3 is in fig. 2 by performing principal component analysis on the aggregate track data of the sub-link 3 An axis, based on a preset origin, establishing and +.>Perpendicular to the axis->The axis, the target coordinate system of sub-section 3 is obtained>In sub-section 3 target coordinate system +.>And fitting the aggregate track data of the sub-section 3 to obtain a continuous and smooth curve which can be expressed by a function. By resampling, a plurality of resampled points are obtained on the curve, based on the target coordinate system +.>And a reference coordinate system->And mapping the resampled points into a reference coordinate system to obtain a plurality of standard sampling points and coordinate values of each standard sampling point in the reference coordinate system.

In the embodiment of the present invention, the target road is divided into n sub-road segments by step 101, where n is a positive integer greater than or equal to 2. Through step 102, a target coordinate system uniquely corresponding to each sub-road section can be obtained, and the aggregate track data of the sub-road section is fitted in the target coordinate system corresponding to the sub-road section, so that the fitting precision is higher. The n sub-segments correspond to n fitting functions, and optionally, the fitting functions are cubic polynomial functions. Each curve fitted to the method is continuous and smooth, so that resampling can be performed at any preset interval, and noise influence of original sampling points, namely sampling points in the aggregate track data, is reduced.

The plurality of standard sampling points of each sub-road section jointly form the standard sampling point of the target road. The standard sampling point of the target road is in a reference coordinate system, and the coordinate information of the sampling point is represented by longitude and latitude.

In one possible implementation manner, for each sampling point in the aggregate track data, the sampling point includes a longitude value and a latitude value, and according to the coordinate value of each sampling point in the aggregate track data of the sub-road section in the target coordinate system of the sub-road section, fitting is performed based on a first preset fitting function, so as to obtain a first fitting curve of the sub-road section; and sampling the first fitting curve, determining a plurality of standard sampling points of the sub-road section, and determining a longitude value and a latitude value of each standard sampling point.

The first preset fitting function is a function for determining coordinate values of sampling points in a target coordinate system based on longitude values and latitude values of the sampling points, and fitting a curve to which the road segment belongs based on the coordinate values of each sampling point in the target coordinate system, namely two-dimensional fitting of the curve to which the road segment belongs. Optionally, the function form of the first preset fitting function is:

in the method, in the process of the invention,、/>respectively representing the sampling points in the polymerization track data in the target coordinate system +. >Shaft(s)>The value of the axis, i.e.)>Is about->Is a third order polynomial of (c). />、/>、/>、/>The values of (2) are learned by a fitting algorithm.

The first fitting curve refers to a representation of a curve to which a road section belongs, that is, a two-dimensional representation of the curve to which the road section belongs, based on coordinate values of each sampling point in the aggregate track data in the target coordinate system.

After the first fitting curve is obtained, a plurality of standard sampling points of the sub-road section are determined through resampling on the first fitting curve, and according to the coordinate value of each standard sampling point in the target coordinate system of the sub-road section and the mapping relation between the target coordinate system and the reference coordinate system, the longitude value and the latitude value of each standard sampling point in the reference coordinate system, namely the geographic coordinate system, can be determined.

In one possible implementation manner, for each sampling point in the aggregate track data, the sampling point further includes a height value, and fitting is performed based on a second preset fitting function according to the coordinate value of each sampling point in the aggregate track data of the sub-road section in the target coordinate system of the sub-road section and the height value of each sampling point, so as to obtain a second fitting curve of the sub-road section; determining a height value of each standard sampling point of the sub-road section based on a plurality of standard sampling points of the sub-road section and a second fitting curve; and determining the gradient value and the curvature radius value of each sampling point according to the longitude value, the latitude value and the altitude value of each standard sampling point on the target road.

The second preset fitting function is a function for fitting the curve of the road segment based on the coordinate value and the height value of the sampling point in the target coordinate system, namely, three-dimensional fitting of the curve of the road segment.

The second fitting curve refers to a representation of a curve to which the road segment belongs, that is, a three-dimensional representation of the curve to which the road belongs, based on the coordinate value and the height value of each sampling point in the aggregated track data.

In the embodiment of the present invention, for each sub-link, the target coordinate system of the sub-link is a three-dimensional coordinate system based on the same segmentation criteria, that is, based on the segmentation criteria of step 101, includingPerpendicular to plane->The length of the shaft, optionally,the plane is used to represent sea level +.>The value is the altitude value of the sampling point, optionally the altitude value of the sampling point.

At the position ofAnd in the coordinate system, fitting the aggregate track data of the sub-road section.

Optionally, the second preset fitting function is a slope fitting function, and the function form is:

in the method, in the process of the invention,、/>、/>respectively representing the sampling points in the polymerization track data in the target coordinate system +.>Shaft(s)>Shaft(s)>Values of axes. I.e.)>Concerning (/ ->) In the formula, < ->To->The weight is preset and can be learned by a fitting algorithm. Fig. 3 is a schematic diagram of a first fitting curve and a second fitting curve obtained by fitting an aggregation function of a sub-road section according to an embodiment of the present invention. As shown in fig. 3, the upper curve is the second fitted curve, and the lower curve is the first fitted curve.

Based on the second fitting curve, substituting each standard sampling point into a second fitting function corresponding to the second fitting curve, so that the height value of each standard sampling point can be obtained, and optionally, the altitude value of each standard sampling point can be obtained. At this time, the longitude value, latitude value, and altitude value of each standard sampling point are determined. A complete standard sample point consisting of longitude, latitude and altitude is obtained as shown in table 2 below:

TABLE 2

A standard sampling point sequence number	B longitude value	C latitude value	Elevation D	E curvature	F grade value	G cumulative distance
							1	117.969908	24.397458	8	C1	S1	0
2	117.969859	24.397597	8	C2	S2	16.178619
							3	117.969814	24.397736	8	C3	S3	32.237227
4	117.96977	24.397876	8	C4	S4	48.373708
							5	117.969725	24.398017	8	C5	S5	64.644825
6	117.969679	24.398158	8	C6	S6	80.944689
							7	117.96963	24.398296	9	C7	S7	97.01793
8	117.96958	24.39843	9	C8	S8	112.702934
							9	……	……	……	……	……	……

And determining the gradient value and the curvature radius value of each sampling point according to the longitude value, the latitude value and the height value of each standard sampling point on the target road. Table 2 is merely an example of one data structure of a standard sampling point, and the embodiment of the present invention does not limit the data structure of the standard sampling point.

In an alternative implementation manner, any three standard sampling points on the target road can uniquely determine a circle, the radius of the circle is the radius of curvature r of the standard sampling point, and the inverse of the radius of curvature is the curvature corresponding to the standard sampling point.

In one possible implementation, after the standard sampling points of the target road are obtained, as shown in table 2, the cumulative distance between each standard sampling point and the first standard sampling point may be obtained, for one standard sampling point a, one standard sampling point B located a preset distance before the standard sampling point and one standard sampling point C located a preset distance after the standard sampling point may be obtained, a circle may be uniquely determined based on the standard sampling point A, B, C, and the curvature of the standard sampling point a may be calculated according to the radius of the circle. Alternatively, a circle can be uniquely determined by two sampling points adjacent to the standard sampling point a, and the curvature of the standard sampling point a can be determined by the radius of the circle. The curvature corresponding to each standard sampling point may also be determined in other manners, which are not limiting in the embodiments of the present invention.

In an alternative implementation, the difference in elevation/difference in elevation between the current standard sampling point and the next sampling point on the target road is divided by the horizontal distance, and the obtained result is substituted into the arctangent function, and the obtained angle value is the gradient value of the current position. Fig. 4 is a schematic diagram showing a calculation of a gradient value of a standard sampling point according to an embodiment of the present invention, and in combination with fig. 4, an attribute point N is a current standard sampling point, an attribute point n+1 is a standard sampling point located at a later stage of the current standard sampling point, and a calculated value of an angle α is a gradient value of the current standard sampling point.

By the above method, the curvature and gradient of each standard sampling point can be calculated, resulting in columns E and F as shown in table 2 above.

In the embodiment of the invention, the standard sampling points are obtained based on resampling of the fitting function, and the curvature and gradient of each standard sampling point are calculated based on the height value, the longitude and latitude value and the like of the standard sampling points, so that noise in data can be filtered more than the original sampling points, namely sampling points in an aggregate track, are directly used for calculation. In addition, the fitting process of the function uses the sampling data of a plurality of vehicles, so that the standard deviation sampling points obtained by the method can reflect the real condition of the road.

In one possible implementation manner, fig. 5 is a schematic diagram of a fitting result of fitting to sub-section aggregate trajectory data based on a cubic polynomial according to an embodiment of the present invention. Wherein, the points represent sampling points in the aggregated track data, and the curve represents the fitting result. The purpose of the fitting is to bring the fitted curve as close as possible to all the sampling points, and the "degree of approach" can be represented by an evaluation index, which is the "goodness of fit". The value range of the fitting goodness is 0 to 1, and the closer the value of the fitting goodness is to 1, the better the fitting degree of the obtained fitting curve to the sampling points is.

In an alternative implementation, the aggregate track data of each sub-link together form the aggregate track data of the target link, and before for each sub-link, the method further includes, before performing the link trend analysis based on the aggregate track data of the sub-link: determining a mapping relation between a length value and a fitting goodness value according to the aggregate track data of a target road, wherein in the mapping relation, for any length value, the fitting goodness value uniquely corresponding to the length value is used for representing the average value of the fitting goodness value of a first preset fitting function corresponding to each sub-road section when the length of each sub-road section is the length value, and the fitting goodness value is the evaluation value of the first preset fitting function; according to the mapping relation, determining a length value corresponding to the maximum value of the fitting goodness value as a second preset length; and dividing the target road into a plurality of sub-road segments again based on the second preset length and the aggregate track data of the target road, and determining the aggregate track data of each sub-road segment.

Optionally, the first preset fitting function is a function for determining coordinate values of the sampling points in the target coordinate system based on longitude values and latitude values of the sampling points, and fitting the curve to which the road segment belongs based on the coordinate values of each sampling point in the target coordinate system, that is, two-dimensional fitting of the curve to which the road segment belongs. Optionally, the function form of the first preset fitting function is:

In the method, in the process of the invention,、/>respectively representing the sampling points in the polymerization track data in the target coordinate system +.>Shaft(s)>The value of the axis, i.e.)>Is about->Is a third order polynomial of (c). />、/>、/>、/>The values of (2) are learned by a fitting algorithm.

If the length of each sub-road section is too short, each sub-road section approximates a straight line, and the morphological characteristics of the local road are difficult to obtain in a road fitting mode. If the length of each sub-segment is too long, the complexity of the sub-segment may exceed the complexity of the fitting function itself, resulting in a low degree of fitting, or failure of fitting. In the embodiment of the invention, a mapping relation between the length value and the goodness-of-fit value is established, and optionally, a series of length values, such as 200 meters, 400 meters, 600 meters … … meters, 2200 meters, etc., are set from small to large according to a preset step length, and for each length, the length value is used as a segmentation basis, i.e. the length of each sub-road section is the length value. By the method of steps 102 to 103, the aggregate track data of each sub-road section is fitted through a first fitting function, a fitting goodness value of each sub-road section is obtained, an average fitting goodness value is calculated and is used as the fitting goodness value corresponding to the length value, each length value is sequentially used as a segmentation basis, the fitting goodness value corresponding to the length value is determined, and the mapping relation between the length value and the fitting goodness value is determined.

Fig. 6 is a schematic diagram of a mapping relationship between a length value and a goodness-of-fit value according to an embodiment of the present invention. Referring to fig. 6, the abscissa is the length of the fit window, i.e., the length value, and the ordinate is the goodness of fit, and fig. 6 is the mapping relationship between the length value and the goodness of fit value, which is established by analyzing a certain target road, for which the goodness of fit value is maximum when the length of the fit window, i.e., the length of each sub-road section, is about 2000, for the target road, referring to fig. 6. Accordingly, a second preset length value=2000 meters may be set, the target road is subdivided into a plurality of sub-segments based on the second preset length and the aggregate track data of the target road, and the aggregate track data of each sub-segment is determined. Steps 102 and 103 are then performed based on the aggregate trajectory data for each sub-segment to further improve the fitting accuracy.

In one possible implementation, after determining the standard sampling points of the target road and the longitude, latitude, altitude, gradient, curvature and other data of each standard sampling point, the reconstruction of the target road information is completed. Based on the reconstructed target road, in a possible implementation manner, the method provided by the embodiment of the invention further includes: determining whether the first target vehicle is traveling on the target road; if the first target vehicle runs on the target road, determining the running direction of the first target vehicle on the target road according to the position relation between the geographic position information of the first target vehicle at a plurality of moments and a first standard sampling point preset in standard sampling points of the target road; determining a standard sampling point in a preset distance in front of the first target vehicle according to the running direction of the first target vehicle on the target road, the geographic position of the first target vehicle at the current moment and the standard sampling point of the target road; and performing intelligent driving control on the first target vehicle based on the longitude value, the latitude value, the gradient value and the curvature radius value of the standard sampling point within the preset distance in front of the first target vehicle.

Alternatively, the first target vehicle may be the same as the second target vehicle, or may be another vehicle other than the second target vehicle, which is not limited in the embodiment of the present invention.

After the information of the target road is acquired, the information of the target road can be used as an ADAS map to realize the PACC function of the vehicle.

In an optional implementation manner, according to the geographic position of the first target vehicle at the current moment, determining a coding block to which the first target vehicle belongs as a target coding block; determining at least one target road corresponding to the target coding block according to the target coding block; acquiring standard sampling points of each target road in at least one target road; based on the position relation between the first target vehicle and the standard sampling point of each target road in at least one target road, whether the vehicle runs on one target road is determined. By the method, the matching efficiency of the vehicle and the target road can be improved, and the calculated amount can be reduced.

For example, according to the map, the target area is divided into a plurality of non-overlapping blocks, each block uniquely corresponding to one code block, and for the target road, the target road corresponds to at least one code block. After the road information of the multi-item target road is obtained, a database is established, wherein the database comprises standard sampling point information of each item of target road and information of at least one coding block corresponding to the target road.

In order to determine the road on which the vehicle is traveling during the traveling process of the vehicle, optionally, according to the geographic position information of the current moment of the vehicle, determining the block to which the vehicle belongs on the map, determining the coding block corresponding to the block, and according to the coding block, indexing in a database to obtain at least one target road corresponding to the coding block and the standard sampling point of each target road.

Optionally, calculating the position relationship between the current position of the vehicle and each standard sampling point on at least one standard road in turn, and if the distance between the current position of the vehicle and at least one standard sampling point is smaller than the preset distance, determining that the vehicle is located on the target road to which the standard sampling point belongs.

For ease of understanding, the following description is provided in connection with a specific example:

first, it is determined whether the vehicle is on a target road.

Through the steps, the code block to which the vehicle belongs is determined to be the target code block, the target code block corresponds to an item of target road, and the target road is marked as a target road 1. It is determined whether the vehicle is on the target road 1. The standard sampling points of the target link 1 are shown in table 2 above.

When the vehicle runs, the vehicle-mounted equipment can acquire the current position information of the vehicle, such as longitude and latitude coordinates, and meanwhile, the distance between the current vehicle coordinates and each standard sampling point of the target road in the table 2 can be calculated. And is defined as follows:

(1) When the distance between the current coordinate of the vehicle and any one standard sampling point is smaller than X meters, the vehicle is considered to run on the target road;

(2) When the distances between the current coordinates and all the standard sampling points are greater than X meters, the vehicle is regarded as not running on the target road;

optionally, X is a preset distance value, and may be set according to practical applications, for example, x=10 meters.

By calculation, when it is judged that the vehicle is traveling on the target road, the standard sampling point nearest to the vehicle is regarded as the position of the vehicle on the target road, simply referred to as "vehicle position".

Second, judging the traveling direction of the vehicle on the target road

The standard sampling points shown in table 2 above are arranged in order. For convenience of description below, a direction in which sample No. 1 is regarded as a start point is defined as a "forward direction", and a direction in which sample No. 1 is regarded as an end point is defined as an "reverse direction".

When the vehicle runs on the target road, the accumulated distance between the position of the vehicle and the No. 1 sampling point can be obtained in real time, and the following judgment can be made:

the accumulated distance between the position of the vehicle and the No. 1 sampling point gradually increases, and the vehicle moves in a positive direction;

the accumulated distance between the position of the vehicle and the sampling point No. 1 is gradually decreased, and the vehicle moves in the reverse direction;

Third, return predictive information to the vehicle

After confirming the direction in which the vehicle is traveling on the target road, taking the vehicle traveling in the "forward direction" as an example, the following information is output to the vehicle in real time:

the current position of the vehicle is measured according to the accumulated distance between the position of the vehicle and the sampling point No. 1;

curvature and gradient of the road in the range of 100-200 meters in front of the current vehicle;

a typical example is as follows:

the current vehicle travels in the positive direction, the position is 100 meters;

at the position of 200 meters, the curvature is 0, and the gradient is 0;

at the 210 meter position, the curvature is 0.003 and the gradient is 0.3;

……

at 300 meters, the curvature is 0.002 and the gradient is 0.2;

according to the above information, the vehicle-side device can learn:

the vehicle travels in a direction taking the sampling point No. 1 as a starting point, and the current position is 100 meters away from the starting point;

at a position 200 meters from the start point, i.e., a position 200-100=100 meters in front of the vehicle, the curvature is 0, and the gradient is 0;

at a position 210 m from the start point, i.e., 210-100=110 m in front of the vehicle, the curvature is 0.003, and the gradient is 0.3;

……

at a position 300 m from the start point, i.e., 300-100=200 m in front of the vehicle, the curvature is 0.002, and the gradient is 0.2;

The subsequent PACC module takes the information as input, if an ascending slope with a larger gradient appears in front, the rotation speed of the vehicle engine is increased in advance to speed up the vehicle, and excessive oil consumption in the ascending slope process is avoided; if a downhill slope with a larger gradient or a curve with a larger curvature appears in front, the rotation speed of the engine of the vehicle is reduced in advance to reduce the speed of the vehicle, so that the downhill slope and the turning speed are prevented from being too fast to ensure the running safety, and meanwhile, the vehicle is prevented from reducing the speed and generating unnecessary oil consumption after entering the downhill slope or the curve.

It should be understood that the sequence number of each step in the foregoing embodiment does not mean that the execution sequence of each process should be determined by the function and the internal logic, and should not limit the implementation process of the embodiment of the present invention.

The following are device embodiments of the invention, for details not described in detail therein, reference may be made to the corresponding method embodiments described above.

Fig. 7 is a schematic structural diagram of a road information reconstruction device according to an embodiment of the present invention, and for convenience of explanation, only a portion related to the embodiment of the present invention is shown, and the details are as follows:

as shown in fig. 7, the road information reconstruction device 7 includes: a dividing module 71, a first determining module 72 and a second determining module 73;

The dividing module 71 is configured to divide the target road into a plurality of sub-road segments based on a first preset length, and determine aggregate track data of each sub-road segment, where for each sub-road segment, the aggregate track data is used to represent a set of sampling points for collecting geographic location information when a plurality of vehicles travel on the sub-road segment;

a first determining module 72, configured to, for each sub-link, perform a road trend analysis based on the aggregate track data of the sub-link, and determine a target coordinate system of the sub-link;

the second determining module 73 is configured to fit the aggregate track data of the sub-road segment in the target coordinate system of the sub-road segment, determine a plurality of standard sampling points of the sub-road segment according to the fitting result, where the plurality of standard sampling points of each sub-road segment together form a standard sampling point of the target road.

In one possible implementation, the first determining module 72 is further configured to:

In one possible implementation, the second determining module 73 is configured to:

In one possible implementation, the second determining module 73 is further configured to:

determining a height value of each standard sampling point of the sub-road section based on a plurality of standard sampling points of the sub-road section and a second fitting curve;

And determining the gradient value and the curvature radius value of each sampling point according to the longitude value, the latitude value and the altitude value of each standard sampling point on the target road.

determining whether the first target vehicle is traveling on the target road;

if the first target vehicle runs on the target road, determining the running direction of the first target vehicle on the target road according to the position relation between the geographic position information of the first target vehicle at a plurality of moments and a first standard sampling point preset in standard sampling points of the target road;

determining a standard sampling point in a preset distance in front of the first target vehicle according to the running direction of the first target vehicle on the target road, the geographic position of the first target vehicle at the current moment and the standard sampling point of the target road;

acquiring standard sampling points of each target road in at least one target road;

based on the position relation between the first target vehicle and the standard sampling point of each target road in at least one target road, whether the vehicle runs on one target road is determined.

In one possible implementation, the partitioning module 71 is configured to:

taking sampling points which are used for collecting geographic position information when a second target vehicle runs on a target road once as reference track data, and sequencing the sampling points in the reference track data according to the collecting time;

determining a starting point of a target road according to the reference track data, and sequentially calculating the distance between each sampling point and the starting point;

dividing a target road into a plurality of sub-road sections based on a first preset length according to the distance between each sampling point and a starting point, determining the sampling point belonging to the sub-road section in the reference track data for each sub-road section, and determining the longitude and latitude range of the sub-road section according to the sampling point belonging to the sub-road section in the reference track data;

In one possible implementation, the partitioning module 71 is further configured to:

determining a mapping relation between a length value and a fitting goodness value according to the aggregate track data of a target road, wherein in the mapping relation, for any length value, the fitting goodness value uniquely corresponding to the length value is used for representing the average value of the fitting goodness value of a first preset fitting function corresponding to each sub-road section when the length of each sub-road section is the length value, and the fitting goodness value is the evaluation value of the first preset fitting function;

according to the mapping relation, determining a length value corresponding to the maximum value of the fitting goodness value as a second preset length;

and dividing the target road into a plurality of sub-road segments again based on the second preset length and the aggregate track data of the target road, and determining the aggregate track data of each sub-road segment.

The road information reconstruction device provided in this embodiment may be used to execute the above-mentioned road information reconstruction method embodiment, and its implementation principle and technical effects are similar, and this embodiment will not be repeated here.

Fig. 8 is a schematic diagram of a terminal according to an embodiment of the present invention. As shown in fig. 8, the terminal 8 of this embodiment includes: a processor 80, a memory 81 and a computer program 82 stored in the memory 81 and executable on the processor 80. The processor 80, when executing the computer program 82, implements the steps of the respective road information reconstruction method embodiments described above, such as steps 101 to 103 shown in fig. 1. Alternatively, the processor 80, when executing the computer program 82, performs the functions of the modules/units of the apparatus embodiments described above, such as the functions of the modules 71 to 73 shown in fig. 7.

By way of example, the computer program 82 may be partitioned into one or more modules/units that are stored in the memory 81 and executed by the processor 80 to complete the present invention. The one or more modules/units may be a series of computer program instruction segments capable of performing the specified functions, which instruction segments are used for describing the execution of the computer program 82 in the terminal 8.

The terminal 8 may be a computing device such as a desktop computer, a notebook computer, a palm computer, a cloud server, etc. The terminal 8 may include, but is not limited to, a processor 80, a memory 81. It will be appreciated by those skilled in the art that fig. 8 is merely an example of the terminal 8 and is not intended to limit the terminal 8, and may include more or fewer components than shown, or may combine certain components, or different components, e.g., the terminal may further include input-output devices, network access devices, buses, etc.

The processor 80 may be a central processing unit (Central Processing Unit, CPU), but may also be other general purpose processors, digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), field programmable gate arrays (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.

The memory 81 may be an internal storage unit of the terminal 8, such as a hard disk or a memory of the terminal 8. The memory 81 may also be an external storage device of the terminal 8, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card) or the like, which are provided on the terminal 8. Further, the memory 81 may also include both an internal storage unit and an external storage device of the terminal 8. The memory 81 is used for storing the computer program and other programs and data required by the terminal. The memory 81 may also be used to temporarily store data that has been output or is to be output.

It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-described division of the functional units and modules is illustrated, and in practical application, the above-described functional distribution may be performed by different functional units and modules according to needs, i.e. the internal structure of the apparatus is divided into different functional units or modules to perform all or part of the above-described functions. The functional units and modules in the embodiment 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, where the integrated units may be implemented in a form of hardware or a form of a software functional unit. In addition, the specific names of the functional units and modules are only for distinguishing from each other, and are not used for limiting the protection scope of the present application. The specific working process of the units and modules in the above system may refer to the corresponding process in the foregoing method embodiment, which is not described herein again.

In the foregoing embodiments, the descriptions of the embodiments are emphasized, and in part, not described or illustrated in any particular embodiment, reference is made to the related descriptions of other embodiments.

Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.

In the embodiments provided in the present invention, it should be understood that the disclosed apparatus/terminal and method may be implemented in other manners. For example, the apparatus/terminal embodiments described above are merely illustrative, e.g., the division of the modules or units is merely a logical function division, and there may be additional divisions when actually implemented, e.g., 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 may be an indirect coupling or communication connection via interfaces, devices or units, which may be in electrical, mechanical or other forms.

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 on 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 the embodiments of the present invention 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 modules/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 storage medium. Based on such understanding, the present invention may implement all or part of the flow of the method of the above embodiment, or may be implemented by instructing related hardware by a computer program, where the computer program may be stored in a computer readable storage medium, and the computer program may implement the steps of each of the road information reconstruction method embodiments described above when executed by a processor. Wherein the computer program comprises computer program code which may be in source code form, object code form, executable file or some intermediate form etc. The computer readable medium may include: any entity or device capable of carrying the computer program code, a recording medium, a U disk, a removable hard disk, a magnetic disk, an optical disk, a computer Memory, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), an electrical carrier signal, a telecommunications signal, a software distribution medium, and so forth.

The above embodiments are only for illustrating the technical solution of the present invention, and not for limiting the same; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention, and are intended to be included in the scope of the present invention.

Claims

1. A road information reconstruction method, characterized by comprising:

dividing a target road into a plurality of sub-road sections based on a first preset length, and determining aggregate track data of each sub-road section, wherein for each sub-road section, the aggregate track data is used for representing a sampling point set for collecting geographic position information when a plurality of vehicles run on the sub-road section, and the sampling points comprise longitude values, latitude values and altitude values;

Sampling the first fitting curve, determining a plurality of standard sampling points of the sub-road section, and determining a longitude value and a latitude value of each standard sampling point;

fitting is carried out on the basis of a second preset fitting function according to the coordinate value of each sampling point in the aggregate track data of the sub-road section in the target coordinate system of the sub-road section and the height value of each sampling point, so that a second fitting curve of the sub-road section is obtained; determining a height value of each standard sampling point of the sub-road section based on a plurality of standard sampling points of the sub-road section and the second fitting curve;

and determining the gradient value and the curvature radius value of each standard sampling point according to the longitude value, the latitude value and the height value of each standard sampling point on the target road, wherein a plurality of standard sampling points of each sub-road section jointly form the standard sampling point of the target road.

2. The method of claim 1, wherein for each sub-link, performing a link trend analysis based on the aggregate trajectory data for the sub-link, determining the target coordinate system for the sub-link comprises:

3. The method of claim 1, wherein after determining the slope value and the radius of curvature value for each standard sampling point based on the longitude value, the latitude value, and the altitude value for each standard sampling point on the target road, the method further comprises:

determining whether a first target vehicle is traveling on the target road;

4. A method according to claim 3, wherein the predetermined area is divided into a plurality of blocks, each block uniquely corresponding to one of the encoded blocks, and wherein determining whether the first target vehicle is traveling on the target road comprises:

5. The method of any one of claims 1 to 4, wherein dividing the target road into a plurality of sub-segments and determining aggregate trajectory data for each sub-segment based on the first preset length comprises:

taking sampling points of a second target vehicle as reference track data, and sequencing the sampling points in the reference track data according to acquisition time; the sampling points are obtained by acquiring geographic position information when the second target vehicle runs on the target road at any time;

6. The method of claim 1, wherein the aggregate track data for each sub-link collectively comprises aggregate track data for the target link, and wherein prior to said for each sub-link performing a link strike analysis based on the aggregate track data for that sub-link, the method further comprises:

determining a mapping relation between a length value and a fitting goodness value according to the aggregate track data of the target road, wherein in the mapping relation, for any length value, the fitting goodness value uniquely corresponding to the length value is used for representing the average value of the fitting goodness value of a first preset fitting function corresponding to each sub-road section when the length of each sub-road section is the length value, and the fitting goodness value is the evaluation value of the first preset fitting function;

7. A terminal comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that the processor implements the steps of the method according to any of the preceding claims 1 to 6 when the computer program is executed.

8. A computer readable storage medium storing a computer program, characterized in that the computer program when executed by a processor implements the steps of the method according to any of the preceding claims 1 to 6.