CN114595238A

CN114595238A - Vector-based map processing method and device

Info

Publication number: CN114595238A
Application number: CN202210212156.0A
Authority: CN
Inventors: 张钰玺; 贾俊
Original assignee: Autonavi Software Co Ltd
Current assignee: Autonavi Software Co Ltd
Priority date: 2022-03-04
Filing date: 2022-03-04
Publication date: 2022-06-07

Abstract

The embodiment of the specification provides a map processing method and a map processing device based on vectors, wherein the method comprises the steps of matching an initial vector and an updated vector of a target map according to a preset matching rule, and determining a vector matching pair; determining a pose adjustment parameter of the update vector and a repositioning parameter of each vector point in the update vector according to the vector matching pair; adjusting the update vector according to the pose adjustment parameter and the repositioning parameter to obtain an adjusted update vector; determining the confidence coefficient of the updated vector according to the matching distance between the initial vector and the updated vector in the vector matching pair and the incidence relation between the initial vector and the adjusted updated vector; and determining whether the target map changes or not according to the vector matching pairs, the pose adjustment parameters and/or the confidence degrees of the updated vectors.

Description

Vector-based map processing method and device

Technical Field

The embodiment of the specification relates to the technical field of computers, in particular to a vector-based map processing method.

Background

The high-precision map accurately describes the information of the position, the attribute, the geometry and the like of various road elements (such as stop boards, road signs and the like) in the real world, and is one of data sources of the automatic driving technology. Most automatic driving or auxiliary driving vehicles in the market rely on high-precision maps to help complete tasks such as perception, positioning and planning. This requires that the high-precision map accurately reflect the actual state of the road elements in real time. Namely, the present change in the high-precision map needs to be accurately found, so that the high-precision map is updated in time.

At present, the situation change in the high-precision map is generally artificially checked in a carpet manner to determine whether a certain road element changes, and then after the position of the change of the road element is manually determined, the on-site measurement, the quantity collection and the like are carried out to update the high-precision map; by the method, the present change of the road elements in the high-precision map can not be acquired in time, and the method is manually realized, so that the processing period is long, the cost is high, and the accuracy is poor.

Disclosure of Invention

In view of this, the embodiments of the present specification provide a vector-based map processing method. One or more embodiments of the present specification also relate to a vector-based map processing apparatus, a computing device, a computer-readable storage medium, and a computer program, so as to solve technical deficiencies in the prior art.

According to a first aspect of embodiments herein, there is provided a vector-based map processing method, including:

matching the initial vector and the updated vector of the target map according to a preset matching rule to determine a vector matching pair;

determining a pose adjustment parameter of the update vector and a repositioning parameter of each vector point in the update vector according to the vector matching pair;

adjusting the update vector according to the pose adjustment parameter and the repositioning parameter to obtain an adjusted update vector;

determining the confidence coefficient of the updated vector according to the matching distance between the initial vector and the updated vector in the vector matching pair and the incidence relation between the initial vector and the adjusted updated vector;

and determining whether the target map changes or not according to the vector matching pairs, the pose adjustment parameters and/or the confidence degrees of the updated vectors.

According to a second aspect of embodiments of the present specification, there is provided a vector-based map processing apparatus including:

the vector matching module is configured to match the initial vector and the updated vector of the target map according to a preset matching rule and determine a vector matching pair;

a parameter calculation module configured to determine a pose adjustment parameter of the update vector and a repositioning parameter of each vector point in the update vector according to the vector matching pair;

the vector adjusting module is configured to adjust the update vector according to the pose adjusting parameter and the repositioning parameter to obtain an adjusted update vector;

a confidence coefficient determining module configured to determine a confidence coefficient of the update vector according to a matching distance between an initial vector and an update vector in the vector matching pair and an association relationship between the initial vector and the adjusted update vector;

a change determination module configured to determine whether the target map has changed according to the confidence of the vector matching pairs, the pose adjustment parameters, and/or the update vectors.

According to a third aspect of embodiments herein, there is provided a computing device comprising:

a memory and a processor;

the memory is configured to store computer-executable instructions and the processor is configured to execute the computer-executable instructions, which when executed by the processor, implement the steps of the vector-based map processing method described above.

According to a fourth aspect of embodiments herein, there is provided a computer-readable storage medium storing computer-executable instructions that, when executed by a processor, implement the steps of the above-described vector-based map processing method.

According to a fifth aspect of embodiments herein, there is provided a computer program, wherein the computer program, when executed in a computer, causes the computer to perform the steps of the above-described vector-based map processing method.

One embodiment of the present specification implements a vector-based map processing method and apparatus, wherein the method includes matching an initial vector and an update vector of a target map according to a preset matching rule, and determining a vector matching pair; determining a pose adjustment parameter of the update vector and a repositioning parameter of each vector point in the update vector according to the vector matching pair; adjusting the update vector according to the pose adjustment parameter and the repositioning parameter to obtain an adjusted update vector; determining the confidence coefficient of the updated vector according to the matching distance between the initial vector and the updated vector in the vector matching pair and the incidence relation between the initial vector and the adjusted updated vector; determining whether the target map changes or not according to the vector matching pairs, the pose adjustment parameters and/or the confidence degrees of the update vectors; specifically, the vector-based map processing method can timely and accurately detect the change of the real world based on the initial vector data and the updated vector data of the target map, and maintain the timeliness of the data in the target map.

Drawings

Fig. 1 is a flowchart of a vector-based map processing method according to an embodiment of the present specification;

fig. 2 is a flowchart of obtaining vector matching pairs in a vector-based map processing method according to an embodiment of the present specification;

fig. 3 is a flowchart illustrating updating of vector point coordinates of an update vector in a vector-based map processing method according to an embodiment of the present disclosure;

fig. 4 is a flowchart illustrating the obtaining of confidence levels of update vectors in a vector-based map processing method according to an embodiment of the present disclosure;

fig. 5 is a flowchart illustrating a determination of whether a target map is changed in a vector-based map processing method according to an embodiment of the present disclosure;

fig. 6 is a schematic structural diagram of a vector-based map processing apparatus according to an embodiment of the present specification;

fig. 7 is a block diagram of a computing device according to an embodiment of the present disclosure.

Detailed Description

In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present description. This description may be implemented in many ways other than those specifically set forth herein, and those skilled in the art will appreciate that the present description is susceptible to similar generalizations without departing from the scope of the description, and thus is not limited to the specific implementations disclosed below.

The terminology used in the description of the one or more embodiments is for the purpose of describing the particular embodiments only and is not intended to be limiting of the description of the one or more embodiments. As used in one or more embodiments of the present specification and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and/or" as used in one or more embodiments of the present specification refers to and encompasses any and all possible combinations of one or more of the associated listed items.

It will be understood that, although the terms first, second, etc. may be used herein in one or more embodiments to describe various information, these information should not be limited by these terms. These terms are only used to distinguish one type of information from another. For example, a first can also be referred to as a second and, similarly, a second can also be referred to as a first without departing from the scope of one or more embodiments of the present description. The word "if" as used herein may be interpreted as "at … …" or "when … …" or "in response to a determination", depending on the context.

First, the noun terms to which one or more embodiments of the present specification relate are explained.

High-precision maps: high-precision maps for autonomous driving.

Differential changes found: the differences between the single-shot map and the surface features in the real world are compared.

Vector: and various high-precision map elements consisting of points containing information such as three-dimensional coordinates, attributes and the like.

And (3) bottoming vector: the map, vector elements to be updated, have been made.

Updating the vector: map vectors currently made, not mapped.

In specific implementation, the map database can be updated after the area where the feature is changed is measured in the field and data is collected, and the present change in the map can be accurately found by the method, but on one hand, carpet type investigation is needed, the time period is long, and the cost is high; on the other hand, the position of the change of the map elements needs to be determined manually, and the accuracy is low.

And the updating of the earth surface and the ground objects of the high-precision map on a smaller spatial scale can be realized based on the high-resolution remote sensing image classification. The method can efficiently update the ground features with obvious geometric features, but is limited by image resolution, image classification technology and the like, and can not accurately identify road elements with unobvious geometric features such as rods, plates, lane lines and the like in the high-precision map.

In addition, a crowd-sourced map updating scheme based on a visual technology can be adopted, mass data are used for updating the high-precision map, and the cost is low. However, the scheme requires a large amount of data for model training, and the accuracy is low in a scene with a small data amount.

In view of this, in the present specification, there is provided a vector-based map processing method, and the present specification relates to a vector-based map processing apparatus, a computing device, a computer-readable storage medium, and a computer program, which are described in detail one by one in the following embodiments.

Referring to fig. 1, fig. 1 is a flowchart illustrating a method for processing a vector-based map according to an embodiment of the present disclosure, which specifically includes the following steps.

Step 102: and matching the initial vector and the updated vector of the target map according to a preset matching rule to determine a vector matching pair.

The preset matching rule can be set according to practical application, and the embodiment of the specification is not limited; the target map can be understood as any type and any range of maps, such as any type of world map, country map, city map, high-precision map and the like; the initial vector of the target map can be understood as a backing vector, namely a vector element which is already made into a map and is to be updated, wherein the vector can be understood as a road element (a rod, a plate, a lane line and the like) of various high-precision maps consisting of points containing information such as three-dimensional coordinates, attributes and the like; the update vector of the target map can be understood as a map vector currently produced and not shown.

Specifically, after the target map and the initial vector and the update vector of the target map are obtained, the vector points in the initial vector and the vector points in the update vector may be matched through a preset matching rule, so as to accurately obtain the vector matching pairs of the initial vector and the update vector. The specific implementation mode is as follows:

the matching the initial vector and the updated vector of the target map according to the preset matching rule to determine the vector matching pair comprises the following steps:

obtaining an initial vector and an update vector of a target map, and respectively determining the geometric types of road elements corresponding to vector points in the initial vector and the update vector;

fitting the initial vector and the updated vector respectively through a preset fitting algorithm according to the geometric type to obtain road geometric elements of the initial vector and the updated vector;

and determining a vector matching pair according to the initial vector, the updating vector, the road geometric element of the initial vector and the road geometric element of the updating vector.

The road elements include, but are not limited to, bars, tiles, lane lines, etc., and the geometric type of the road elements may be understood as the types of the bars, the tiles, the lane lines, etc., for example, the type of the bars is points, the type of the tiles is planes, the type of the lane lines is straight lines, etc.

In practical application, the initial vector and the updated vector both comprise a plurality of vector points, each vector point comprises information such as three-dimensional coordinates and attributes, and the vector points are fitted according to a preset fitting algorithm, so that the road elements in the initial vector and the updated vector can be obtained.

Specifically, a target map (such as a high-precision map for determining whether a road element change occurs) and a base vector and an update vector of the target map are obtained; determining the geometric types (such as straight lines, points, planes and the like) of the road elements corresponding to the vector points in the initial vectors and updating the geometric types (such as straight lines, points, planes and the like) of the road elements corresponding to the vector points in the vectors; fitting the initial vector and the updated vector through a preset fitting algorithm according to each geometric type, wherein the geometric types are different, and the preset fitting algorithms adopted when fitting the initial vector and the updated vector can also be different, for example, the geometric type is a straight line, and a least square method can be adopted to fit the straight line; and after fitting the initial vector and the updated vector according to the geometric type through a preset fitting algorithm, obtaining road geometric elements (such as line elements, surface elements or point elements) of the initial vector and the updated vector respectively.

And determining a vector matching pair of the initial vector and the update vector according to the initial vector, the update vector, the road geometric element of the initial vector and the road geometric element of the update vector.

In specific implementation, when acquiring the road geometric elements of the initial vector and the updated vector, the initial road geometric elements of the initial vector and the updated vector need to be acquired first through a fitting algorithm, and then the accurate road geometric elements of the final initial vector and the updated vector are determined after other processing is performed on the initial road geometric elements of the initial vector and the updated vector. The specific mode is as follows:

the fitting the initial vector and the updated vector according to the geometric type by a preset fitting algorithm to obtain the road geometric elements of the initial vector and the updated vector comprises the following steps:

determining a fitting algorithm corresponding to the initial vector and the updated vector according to the geometric type;

obtaining the initial road geometric elements of the initial vector according to the fitting algorithm corresponding to the initial vector;

obtaining the initial road geometric elements of the update vector according to the fitting algorithm corresponding to the update vector;

and adjusting the initial road geometric elements of the initial vector and the initial road geometric elements of the updated vector according to a preset calculation rule to obtain the road geometric elements of the initial vector and the updated vector.

Wherein the fitting algorithm includes, but is not limited to, least squares.

In specific implementation, the fitting algorithms corresponding to different geometric types may be different, for example, a plane corresponds to one fitting algorithm, a straight line corresponds to another fitting algorithm, and the like. Firstly, determining a fitting algorithm corresponding to an initial vector and a fitting algorithm corresponding to an updated vector according to geometric types, then obtaining initial road geometric elements of the initial vector according to the fitting algorithm corresponding to the initial vector, and obtaining initial road geometric elements of the updated vector according to the fitting algorithm corresponding to the updated vector; and subsequently, adjusting the initial road geometric elements of the initial vector and the initial road geometric elements of the updated vector according to a preset calculation rule to obtain the road geometric elements of the initial vector and the updated vector so as to ensure the accuracy of the road geometric elements of the initial vector and the updated vector.

Specifically, the adjusting the initial road geometric element of the initial vector and the initial road geometric element of the update vector according to a preset calculation rule to obtain the road geometric elements of the initial vector and the update vector includes:

calculating first fitting residual errors of vector points in the initial vector according to the initial road geometric elements of the initial vector, and calculating root mean square, mean value and standard deviation of the first fitting residual errors according to the first fitting residual errors;

calculating a second fitting residual of a vector point in the updated vector according to the initial road geometric element of the updated vector, and calculating the root mean square, the mean value and the standard deviation of the second fitting residual according to the second fitting residual;

adjusting the initial road geometric elements of the initial vector according to the root mean square, the mean value and the standard deviation of the first fitting residual error to obtain the road geometric elements of the initial vector;

and adjusting the initial road geometric elements of the updated vector according to the root mean square, the mean value and the standard deviation of the second fitting residual error to obtain the road geometric elements of the updated vector.

In practical application, after the initial road geometric elements of the initial vector and the updated vector are respectively determined, a first fitting residual error of each vector point of the initial vector and a second fitting residual error of each vector point of the updated vector are respectively calculated according to the initial road geometric elements of the initial vector and the updated vector. Then calculating according to the first fitting residual of each vector point of the initial vector to obtain the root mean square, the mean value and the standard deviation of the first fitting residual, and calculating according to the second fitting residual of each vector point of the updated vector to obtain the root mean square, the mean value and the standard deviation of the second fitting residual; and subsequently, according to the root mean square, the mean value and the standard deviation of the first fitting residual errors, adjusting the initial road geometric elements of the initial vectors to obtain the road geometric elements of the initial vectors, and meanwhile, according to the root mean square, the mean value and the standard deviation of the second fitting residual errors, adjusting the initial road geometric elements of the updated vectors to obtain the road geometric elements of the updated vectors.

The method comprises the steps of adjusting initial road geometric elements of an initial vector, wherein outliers deviating from twice standard deviation of the mean value of a first fitting residual are marked according to the root mean square, the mean value and the standard deviation of the first fitting residual, the marked outliers are removed under the condition that the root mean square of the first fitting residual does not meet preset requirements (such as a preset distance threshold, 3 centimeters, 5 centimeters and the like), the initial road geometric elements of the initial vector are obtained through a fitting algorithm repeatedly, the initial road geometric elements of the initial vector are adjusted according to the preset calculation rule, and the adjustment is finished until the root mean square of the first fitting residual meets the preset requirements, so that the road geometric elements of the initial vector are determined; similarly, the determination of the road geometric element of the update vector may refer to the determination manner of the road geometric element of the initial vector, and is not described herein again.

Taking the geometric types of the road elements corresponding to the vector points in the initial vector and the updated vector as examples, when the straight line and the plane in the initial vector and the updated vector are fitted through a fitting algorithm, the calculated fitting residual means that (taking the updated vector as an example) n vector points are fitted with a straight line L, then the residual between the n points and the straight line L is calculated, namely the coordinate (x0, y0) of the vector point is substituted into the straight line equation of L, and (x0, y1) is obtained, wherein r is y1-y0, and r is the fitting residual. Since there are n points, n R will be obtained, defined as set R. Then solving the root mean square error of R, namely fitting residual rms, simultaneously calculating the mean value and standard deviation of R, and then removing outliers, thereby obtaining the accurate road geometric elements after the initial vector and the updated vector are adjusted. The purpose of deleting the outliers is to remove abnormal gross errors as much as possible and ensure the accuracy of fitting. Of course, if the outliers are rejected too much, then the vector fit failure is flagged.

After the road geometric elements of the initial vector and the updated vector are determined, the vector matching pair between the initial vector and the updated vector can be quickly and accurately calculated. The specific implementation mode is as follows:

determining a vector matching pair according to the initial vector, the update vector, the road geometric element of the initial vector and the road geometric element of the update vector, comprising:

calculating the distance error between the vector point of the updated vector and the road geometric element of the initial vector, and determining an initial vector matching pair according to the distance error;

determining attribute information of vector points of the updated vectors in the initial vector matching pairs and attribute information of vector points of corresponding initial vectors;

and under the condition that the attribute information of the two is the same, calculating an included angle between the road geometric element of the updated vector in the initial vector matching pair and the road geometric element of the initial vector, and determining the vector matching pair according to the included angle.

Specifically, the distance error between each vector point in the update vector and each road geometric element in the initial vector is calculated, the priming vector with the distance error larger than a preset distance threshold is deleted, so that the road geometric elements of the initial vector corresponding to each vector point in the update vector are screened out, and the vector pairs meeting the requirements are recorded. For example, if the distance errors between four vector points in the update vector and the surface element in the road geometric element of the initial vector are all less than or equal to a preset distance threshold, it means that the four vector points and the surface element in the road geometric element of the initial vector form an initial vector matching pair.

And then determining attribute information of each vector point in the initial vector matching pair, calculating an included angle between the road geometric element of the updated vector in the initial vector matching pair and the road geometric element of the initial vector under the condition that the attribute information of the two vector points is consistent, recording the vector pair meeting the requirement under the condition that the included angle is less than or equal to a preset angle threshold value, and taking the vector pair as a final vector matching pair.

In practical application, when calculating the distance error, for line elements (line elements in road geometric elements), calculating the distance error between each vector point in the updated vector and each line element in the initial vector one by one, eliminating the initial vector with the distance error larger than a preset distance threshold, and recording the vector pair meeting the requirement; and for the surface elements (surface elements in the road geometric elements), calculating the distance error between each vector point in the updated vector and each surface element in the initial vector one by one, eliminating the initial vector with the distance error larger than a preset distance threshold value, and recording the vector pairs meeting the requirements.

Specifically, when calculating the distance error between the vector point of the update vector and the road geometric element of the initial vector, the bottoming vector is already fitted into a straight line or a plane, and the update vector is a pile of vector scatter points. Taking a straight line after bottoming vector fitting as an example, setting n vector points of an update vector, calculating the distance between the n points and the straight line after bottoming vector fitting one by one to obtain a set R, calculating the rms (root mean square) of the R, and judging whether the two straight lines have a corresponding relation according to the rms. In actual application, the calculation methods of different elements have certain differences, which are determined according to actual application.

And judging whether the attributes of the vector points of the initial vector and the vector points of the updated vector are consistent or not in the vector pairs which meet the requirements, if not, continuously utilizing all the vector points in the updated vector and the initial vector to fit line elements or surface elements and the like by a least square method. And if the two geometric factors are consistent, calculating an included angle between the road geometric element of the updated vector in the initial vector matching pair and the road geometric element of the initial vector.

When the included angle is calculated, for line elements (line elements in road geometric elements), calculating the included angle between each line element in the updated vector and each line element in the initial vector one by one in the initial vector matching pair, and if the included angle is less than or equal to a preset angle threshold value, recording the vector pair meeting the requirement; and for the surface elements (surface elements in the road geometric elements), calculating an included angle of a normal vector between each surface element in the update vector and each surface element in the initial vector one by one, recording a vector pair meeting the requirement if the included angle is less than or equal to a preset angle threshold value, and taking the vector pair as a final vector matching pair. If the included angle is greater than the preset angle threshold, the matching relation does not exist, for example, if the included angle of the two straight lines exceeds a certain threshold, the two straight lines are not corresponding.

Taking the straight line elements of the ground lane lines as an example, if the straight line equation of the fitted base vector is: ax + By + C is 0;

the vector points of the update vector are: p (x0, y0), then the point-to-line distance is calculated by equation 1:

a, B, C are undetermined parameters of a linear equation; x and Y are the X and Y coordinates, respectively, of the straight-line equation.

Taking the face element of the card as an example, if the plane equation of the fitted base vector is: ax + By + Cz + D ═ 0;

the vector point of the update vector is p (x0, y0, z0), then the point-to-plane distance is calculated by equation 2:

for the surface elements, vector points of the base vector generally consist of n angular points, and if rectangular points are taken as an example, n is 4;

the gravity center point of the current plane can be calculated from 4 corner points, see formula 3:

then, the update vector also has corresponding n +1 points, and after the sequence alignment, the distances between the points are calculated respectively, see the public

Formula 4:

then 5 distances d are obtained and the rms (root mean square) of the 5 distances d is calculated, i.e. the distance of the final point plane.

When the method is used specifically, the calculation method of formula 2 is used for preliminary screening, and then the calculation methods of formula 3 and formula 4 are used as final basis.

Referring to fig. 2, fig. 2 is a flowchart illustrating the obtaining of vector matching pairs in a vector-based map processing method according to an embodiment of the present specification, and specifically includes the following steps.

Step 202, determining the element types of the base vector and the update vector respectively.

The prime vector may be understood as the initial vector of the above embodiment, and the element type may be understood as the geometric type of the road element corresponding to the vector point in the prime vector and the update vector of the above embodiment.

The element type includes a line element and a plane element as an example.

Step 204: and for the base vector and the update vector, respectively obtaining line elements of the base vector and the update vector by least square fitting by using all vector points.

Step 206: and for the base vector and the update vector, respectively obtaining the surface elements of the base vector and the update vector by least square fitting by using all vector points.

Step 208: and performing linear robust fitting, attribute consistency check, angle consistency check and linear distance check calculation on the line elements.

Specifically, straight line robust fitting: calculating a fitting residual error of each vector point in the backing vector and the updating vector aiming at line elements of the backing vector or the updating vector, calculating an rms, a mean value and a standard deviation of the fitting residual error, and marking outliers deviating from the mean value of the fitting residual error by 2 times of the standard deviation; and under the condition that the rms of the fitting residual does not meet the preset requirement, removing outliers, repeating the steps 204 to 206 until the rms of the fitting residual meets the preset requirement, and determining the line elements of the final bottoming vector or the updating vector.

Checking the linear distance: calculating the distance error between each vector point in the updated vector and the line element in the priming vector one by one, eliminating the priming vector with the distance error larger than a threshold value, and recording the vector pair meeting the requirement.

Checking attribute consistency: and judging whether the attributes of the update vector and the backing vector in the satisfactory vector pair determined by the linear distance check are consistent, if not, indicating that the vector pair is not matched, and if so, carrying out angle consistency check on the vector pair to obtain the final satisfactory vector pair.

Checking the angle consistency: calculating the included angle between each line element in the updated vector and the line element in the bottoming vector in the vector pair meeting the linear distance check and the attribute consistency check one by one, and under the condition that the included angle exceeds a preset angle threshold value, indicating that the vector pair is not matched; and under the condition that the included angle does not exceed the preset angle threshold value, taking the included angle as a vector pair meeting the requirement.

Step 210: and carrying out normal vector angle inspection, plane distance inspection, plane robust fitting and attribute consistency inspection calculation on the surface elements.

Specifically, planar robust fitting: calculating a fitting residual error of each vector point in the backing vector and the updating vector aiming at the surface elements of the backing vector or the updating vector, calculating an rms, a mean value and a standard deviation of the fitting residual error, and marking outliers deviating from the mean value of the fitting residual error by 2 times of the standard deviation; and under the condition that the rms of the fitting residual does not meet the preset requirement, removing outliers, repeating the steps 204 to 206 until the rms of the fitting residual meets the preset requirement, and determining the line element of the final bottoming vector or the updating vector.

Checking the plane distance: calculating the distance error between each vector point in the updated vector and the surface element in the backing vector one by one, eliminating the backing vector with the distance error larger than a threshold value, and recording the vector pair meeting the requirement.

Checking a normal vector angle: calculating an included angle between each surface element in an updating vector in a vector pair meeting the requirements of plane distance check and attribute consistency check and a normal vector of a surface element in a bottoming vector one by one, and under the condition that the included angle exceeds a preset angle threshold value, indicating that the vector pair is not matched; and under the condition that the included angle does not exceed the preset angle threshold value, taking the included angle as a vector pair meeting the requirement.

In this embodiment, the matched vector pair of the priming vector and the update vector can be obtained quickly and accurately according to the above steps 202 to 210.

Step 104: and determining the pose adjustment parameters of the update vector and the repositioning parameters of each vector point in the update vector according to the vector matching pairs.

Specifically, the determining, according to the vector matching pair, a pose adjustment parameter of the update vector and a repositioning parameter of each vector point in the update vector includes:

constructing a Kalman filter according to the vector matching pair and the matching distance between the bottoming vector and the updating vector in the vector matching pair;

calculating a pose adjustment parameter of the update vector according to the Kalman filter;

and determining the repositioning parameters of each vector point in the updating vector according to the pose adjusting parameters and the current coordinates of the vector points in the updating vector.

The Kalman filtering is an algorithm that performs optimal estimation on the system state by using a linear system state equation and outputting observation data through the system input.

Specifically, all vector matching pairs are used as observation, the matching distance between a bottoming vector and an updating vector in each vector matching pair is used as an observed quantity, a pose adjustment parameter at the previous moment is used as a state prediction value (if the pose adjustment parameter does not exist, the state prediction value is set to be 0), and a Kalman filter (namely an observation equation and a state equation of the Kalman filter are constructed, wherein the observation equation and the state equation of the Kalman filter are fixed filter structures, the observation equation refers to external observation, and the state equation describes time domain change of a parameter to be estimated).

And calculating pose adjustment parameters (such as pose correction numbers) of the update vector according to the constructed Kalman filter, and determining repositioning parameters (graph repositioning residual errors) of each vector point in the update vector according to the pose adjustment parameters and the current coordinates of the vector points in the update vector.

In the embodiment of the present specification, the pose correction number and the repositioning residual of the update vector may be calculated according to a kalman filter, and subsequently, the coordinates of the vector points in the update vector may be adjusted according to the pose correction number and the repositioning residual of the update vector, so that the coordinates of the vector points in the update vector are accurate.

In practical application, when the data volume of the target map is large, the target map may be segmented according to a preset segmentation rule, and then the present change of each segment of the map is determined according to the segmentation result. The specific implementation mode is as follows:

before the constructing of the kalman filter according to the vector matching pair and the matching distance between the priming vector and the update vector in the vector matching pair, the method further comprises:

segmenting the target map according to preset segmentation rules to obtain a plurality of segmented maps;

and sequentially taking each segmented map as a target segmented map, and determining an initial vector and an updating vector corresponding to the target segmented map and a vector matching pair in the target segmented map.

The preset segmentation rule may be set according to actual application, for example, the target map is divided according to a certain spatial range and a certain time range, so as to obtain a plurality of segmented maps.

And then, taking each segmented map as a target segmented map once, and acquiring the corresponding initial vector and the corresponding updated vector in the target segmented map and the vector matching pair in the target segmented map. And subsequently, the present change of the target segmented map can be judged according to the corresponding initial vector and the corresponding updated vector in the target segmented map and the vector matching pair in the target segmented map.

Step 106: and adjusting the update vector according to the pose adjustment parameter and the repositioning parameter to obtain an adjusted update vector.

Specifically, the adjusting the update vector according to the pose adjustment parameter and the repositioning parameter to obtain an adjusted update vector includes:

and under the condition that the repositioning parameters meet chi-square verification, adjusting the coordinates of each vector point in the updating vector according to the repositioning parameters and the pose adjusting parameters to obtain an adjusted updating vector.

The chi-square check is the deviation degree between the actual observed value and the theoretical inferred value of the statistical sample, the deviation degree between the actual observed value and the theoretical inferred value determines the size of the chi-square value, and if the chi-square value is larger, the deviation degree between the actual observed value and the theoretical inferred value is larger; otherwise, the smaller the deviation of the two is; if the two values are completely equal, the chi-square value is 0, which indicates that the theoretical values completely meet.

During specific implementation, post-test residual error analysis is performed on the relocation parameters of each vector point in the update vector, whether the post-test residual errors of all the vector points meet chi-square verification or not is judged, if yes, the coordinates of each vector point in the update vector are adjusted according to the relocation parameters and the pose adjustment parameters, and the adjusted update vector is obtained.

If the Ka-square verification fails, a normalized standard normal distribution residual sequence is constructed, variance expansion is carried out on vectors except for the standard deviation of 3 times, a Kalman filter is reconstructed, and pose adjustment parameters and repositioning parameters of updated vectors are calculated.

Referring to fig. 3, fig. 3 is a flowchart illustrating updating the vector point coordinates of the update vector in a vector-based map processing method according to an embodiment of the present specification, which specifically includes the following steps.

Specifically, the example of updating the vector point coordinates of the update vector in the target segment map is described.

Step 302: and determining a base vector, an update vector and a matching relation of the base vector and the update vector of the target map.

Step 304: and carrying out region segmentation on the target map to obtain a target segmented map.

Specifically, the specific implementation manner of performing region segmentation on the target map to obtain the target segmented map may be referred to in the above embodiments.

Step 306: and determining a base vector, an update vector and a vector matching pair of the target segmented map.

Step 308: and acquiring the pose correction number of the last segment.

Step 310: and constructing a Kalman filter according to the bottoming vector, the updating vector and the vector matching pair of the target segmented map and the pose correction number of the last segment.

Specifically, all matched vector matching pairs in the target segmented map are used as observation, the matching distance between a bottoming vector and an updating vector in the matching pairs is used as an observed quantity, and an observation equation of the Kalman filter is constructed; and taking the pose correction number of the last segment as a state prediction value to construct a state equation of the Kalman filter.

Step 312: and calculating the pose correction number of the updated vector in the target segmented map according to the Kalman filter.

Specifically, the calculation of the pose correction number of the update vector in the target segmented map according to the kalman filter can be understood as the calculation of the pose correction number of the update vector in the target segmented map according to the observation equation of the kalman filter and the state equation of the kalman filter.

Step 314: and calculating to obtain the repositioning residual error of each vector point in the update vector in the target segmented map according to the pose correction number of the update vector in the target segmented map.

Step 316: residual error analysis is carried out on the relocation residual error of each vector point in the updated vector in the target segmented map, whether the relocation residual error of each vector point meets chi-square verification or not is judged, if yes, step 318 is executed, and if not, step 320 is executed.

Wherein the relocation residual is understood to be the residual of the matching distance of the base vector and the update vector.

Firstly, carrying out chi-square distribution test on the residuals, wherein chi-square distribution refers to that if a set obeys normal distribution, the squares of elements in the set and the chi-square distribution are carried out, and the squares of all the elements should be smaller than a certain threshold value; if the chi-square distribution does not pass, then a normalized standard normal distribution, i.e., (r-mean)/std, is calculated, mean being the mean and std being the standard deviation. Then, variance expansion is carried out on a part of P { (r-mean)/std } >0.997, namely variance expansion, namely, each observation value has a priori variance which represents the precision of the observation value, and the observation value is found to be inaccurate by testing, so that the variance is amplified to a certain extent, and the precision of the observation value is represented to be unreliable.

Step 318: and outputting the pose correction number of the update vector in the target segmented map and the repositioning residual error of each vector point in the update vector in the target segmented map, and recalculating the coordinate of the update vector according to the pose correction number and the repositioning residual error.

Step 320: and constructing a normalized standard normal distribution residual sequence, performing variance expansion on vector points which are not 3 times of the standard deviation, and continuing to execute the step 310.

In the embodiment of the specification, the coordinate of the vector point of the update vector in the target segmented map is adjusted through the pose correction number and the repositioning residual error, and the accuracy of the coordinate of the vector point of the update vector in the target map can be ensured subsequently, so that whether the target map is subjected to the present change or not is judged more accurately.

Step 108: and determining the confidence coefficient of the updated vector according to the matching distance between the initial vector and the updated vector in the vector matching pair and the incidence relation between the initial vector and the adjusted updated vector.

Specifically, if the target map is not segmented, the confidence of the update vector is determined directly according to the matching distance between the initial vector and the update vector in the vector matching pair and the incidence relation between the initial vector and the adjusted update vector.

If the target map is segmented, the absolute accuracy and the relative accuracy of the target segmented map and the confidence of the relative accuracy of the update vector in the target segmented map need to be calculated according to the segmentation result. The specific implementation mode is as follows:

determining the confidence of the updated vector according to the matching distance between the initial vector and the updated vector in the vector matching pair and the incidence relation between the initial vector and the adjusted updated vector, wherein the determining comprises:

taking the matching distance between the initial vector and the updated vector in the vector matching pair in the target segmented map as a first set;

taking the distance between the updating vector and the initial vector in the target segmented map as a second set;

taking the distance between the road geometric element of the update vector and the road geometric element of the initial vector in the target segmented map as a third set;

respectively sampling the first set, the second set and the third set, and calculating a sampling sample mean value and a sampling sample variance according to sampling results;

and determining the confidence of absolute precision and relative precision of the vector points in the updating vector according to the mean value and the variance of the sampling samples.

Specifically, before repositioning (i.e. before adjusting the coordinates of each vector point in the update vector according to the repositioning parameters and the pose adjustment parameters), the absolute distance between all vector matching pairs in the target segment map is taken as a first set P₁After the relocation, the distances between all the vector points of the update vector in the target segment map and all the matching vector points of all the vector points of the initial vector are taken as a second set P₂After the relocation, the distance between the road geometric element of the update vector in the target segment map and the road geometric element of the initial vector is taken as a third set P₃Separately for sets P₁、P₂、P₃Randomly sampling, calculating the average value of samples sampled each time, and respectively recording the average value set of samples corresponding to each set as Q₁、Q₂、Q₃(ii) a Calculating Q₁、Q₂、Q₃And designing an interval to be detected according to the requirement, and carrying out hypothesis test to obtain a probability value, wherein the probability value is the confidence coefficient of the segmentation absolute precision, the segmentation relative precision and the vector relative precision. The absolute accuracy of the segment means the degree of deviation between the obtained vector and the road elements in the real world, and the relative accuracy meansRelative degree of deviation. The absolute accuracy, the relative accuracy and the relative accuracy of the vector of the segment respectively correspond to Q1, Q2 and Q3, and the calculation modes are the same; the interval to be detected can be designed according to actual requirements, such as 10cm transverse lane lines, 10cm longitudinal traffic lights, 30cm transverse traffic lights, 40cm high traffic lights and the like.

The confidence of the absolute accuracy and the relative accuracy of the vector point in the update vector can be understood as the degree of deviation between the vector point in the update vector and the road element in the real world, that is, the smaller the degree of deviation, the road element in the target map is not changed, and the larger the degree of deviation, the road element in the target map is changed.

Referring to fig. 4, fig. 4 is a flowchart illustrating obtaining of confidence of an update vector in a vector-based map processing method according to an embodiment of the present specification, which specifically includes the following steps.

Step 402: and calculating the pose correction number of the update vector according to the update vector, the backing vector and the matching relation between the update vector and the backing vector.

Specifically, a region to be detected (such as the target map mentioned above) is divided according to a certain spatial range and a certain time range to obtain a plurality of segments, and for each segment, an update vector, a priming vector, and a vector matching relationship (vector matching pair) in the segment are respectively read.

Taking all vector matching pairs in the segments as observation, taking the matching distance between the bottoming vector and the updating vector as observation quantity, and constructing an observation equation of the Kalman filter; and under the condition that the pose correction number of the previous segment exists, the pose correction number of the previous segment is used as a state prediction value, and a state equation of the Kalman filter is constructed.

And calculating the pose correction number of the current segment according to the constructed Kalman filter (the observation equation of the Kalman filter and the state equation of the Kalman filter), and calculating the repositioning residual error of each vector point in the update vector according to the pose correction number of the current segment and the current coordinate of each vector point in the update vector.

Performing post-test residual analysis according to the obtained repositioning residual, and firstly judging whether the post-test residual of all vectors meets chi-square test; if yes, outputting repositioning residual errors and pose correction numbers, and recalculating the coordinates of the updated vector.

If the data do not pass the chi-square test, a normalized standard normal distribution residual sequence is constructed, variance expansion is carried out on vectors except for 3 times of standard deviation, and the steps are repeated until all data are processed.

Step 404: acquiring the relative distance of the vectors in the whole area before pose correction, the relative distance of the vectors in the whole area after pose correction and the relative distance of the vectors in the single area after pose correction; and randomly sampling and calculating a sampling average value of the obtained relative distance of the vectors in the whole area before the pose correction, the relative distance of the vectors in the whole area after the pose correction and the relative distance of the single vector after the pose correction to obtain the sampling average value.

Specifically, the absolute distance between all the matching vector pairs in a certain segment before relocation is taken as a set P₁(ii) a The distance between all the matching vectors in a certain segment after relocation is taken as a set P₂(ii) a The distance between a certain matching vector after relocation is taken as a set P₃。

Respectively to the set P₁、P₂、P₃Randomly sampling, calculating the average value of samples sampled each time, and respectively recording the average value set of samples corresponding to each set as Q₁、Q₂、Q₃(ii) a Calculating Q₁、Q₂、Q₃Sample mean and variance of (c).

Step 406: and calculating the confidence degrees of the absolute precision, the relative precision and the relative precision of the vector of the segment according to the sampling mean value, and carrying out change marking on the changed vector points in the updated vector according to the confidence degrees.

Specifically, calculate Q₁、Q₂、Q₃And designing an interval to be detected according to the requirement, and carrying out hypothesis test to obtain a probability value, wherein the probability value is the confidence coefficient of the segmentation absolute precision, the segmentation relative precision and the vector relative precision. And according to confidenceAnd judging whether the vector is subjected to the change of the current situation.

Step 110: and determining whether the target map changes or not according to the vector matching pairs, the pose adjustment parameters and/or the confidence degrees of the updated vectors.

Specifically, after determining the vector matching pair, the pose adjustment parameter of the update vector, and the confidence of the update vector, it may be determined whether the road element in the target map has changed according to the parameters.

In practical application, there are various specific implementation manners for determining whether the road elements in the target map change according to the vector matching pairs, the pose adjustment parameters of the update vectors and the confidence degrees of the update vectors, which are described in two ways below. The specific implementation mode is as follows:

determining whether the target map changes according to the vector matching pairs, the pose adjustment parameters and/or the confidence degrees of the update vectors, including:

determining that the target map changes under the condition that any one vector point in the updated vector does not have a matching relation according to the vector matching pair; or

Determining that the target map changes under the condition that the confidence coefficient of the updating vector is determined not to meet a preset confidence coefficient threshold; or

And under the condition that the pose adjustment parameter is determined not to meet the preset precision threshold value, determining that the target map changes.

Namely, when the fact that any vector point in the updating vector does not have a matching relation is determined according to the vector matching pair, the fact that the road elements of the target map are changed can be determined; for example, when a certain vector point exists in the initial vector and does not exist in the update vector, it may be determined that the vector point is deleted in the update vector; when a certain vector point exists in the update vector but does not exist in the initial vector, it can be determined that the vector point is added in the update vector.

Or when the confidence of the update vector does not meet the preset confidence threshold, the target map can be determined to be changed; or determining that the target map changes under the condition that the pose adjustment parameter of the update vector does not meet the preset precision threshold. The preset confidence threshold and the preset precision threshold may be set according to actual applications, and are not limited herein.

In addition, in another mode, whether the target map changes or not can be accurately judged in a layer-by-layer progressive mode. The specific implementation mode is as follows:

under the condition that the matching relation exists between each vector point in the updating vector according to the vector matching pair, judging whether the confidence coefficient of the updating vector meets a preset confidence coefficient threshold value or not,

if so, judging whether the pose adjusting parameters meet a preset precision threshold value,

if not, determining that the target map changes.

Specifically, whether a matching relation exists in each vector point in the update vector is determined according to a vector matching pair is judged, if yes, whether the confidence coefficient of the update vector meets a preset confidence coefficient threshold value is judged, if not, the target map is determined to be changed, if yes, whether the pose adjustment parameter meets a preset precision threshold value is continuously judged, if not, the target map is determined to be changed, and if yes, the target map is determined not to be changed.

Referring to fig. 5, fig. 5 is a flowchart illustrating a determination process for determining whether a target map has changed in a vector-based map processing method according to an embodiment of the present disclosure, which specifically includes the following steps.

Step 502: and judging the matching relationship.

Specifically, whether a matching relationship exists between the update vector and the initial vector is determined according to the vector matching pair, if so, step 504 is executed, and if not, step 506 is executed.

Step 504: and (5) judging the confidence degree.

Specifically, the absolute accuracy confidence of the segment, the relative accuracy confidence of the segment, and the relative accuracy confidence of the vector are obtained, and whether the absolute accuracy confidence of the segment, the relative accuracy confidence of the segment, and the relative accuracy confidence of the vector meet a preset accuracy threshold is judged, if yes, step 508 is executed, and if not, step 510 is executed.

Step 506: and deleting the vector.

Specifically, vector deletion may be understood as that if there is a vector in the base vector, but there is no vector in the currently acquired update vector, so that the vector may disappear in the real world and be marked as deleted.

Step 508: and (5) judging the pose correction number.

Specifically, it is determined whether the pose correction number of the update vector matches the prior precision provided by the trajectory, if yes, step 510 is executed, and if no, step 512 is executed.

Specifically, the prior accuracy may be understood as the positioning accuracy of the current segmentation area (target segmentation map) on the trajectory of the collection vehicle, for example, the positioning accuracy of x, y and z is 5cm, 5cm and 10cm, and it is conceivable that the pose correction number in this interval should be almost of this order, and if the calculated pose correction number is 5m, 5m and 10m, it is certainly problematic.

Step 510, vector position changes.

Step 512: the vector position does not change.

The map processing method based on the vector provided by the embodiment of the specification can timely and accurately detect the change of the real world based on the initial vector data and the updated vector data of the target map, and maintain the timeliness of the data in the target map.

Specifically, the map processing method based on the vector provided by the embodiment of the present specification can automatically detect the change of the real world based on the vector data such as the initial vector data and the update vector data of the target map, and maintain the timeliness of the map data. Compared with manual operation, the production efficiency is greatly improved, and the production cost is reduced; because the vector data is composed of vector points, various traffic elements such as lane lines, traffic lights, traffic signs and the like can be accurately described, and the coverage of all the elements of the road can be realized. In addition, compared with remote sensing images and visual pictures, the vector data has more definite three-dimensional coordinate information, and can accurately describe the position and the change degree of the change of the real world.

Meanwhile, by means of the high-precision map difference finding method based on vector data (namely a vector-based map processing method), the change detection of the real world can be completed by means of a mathematical statistics method depending on a vector with accurate position information, and the method is high in precision, efficiency and reliability and convenient to achieve. In addition, technical innovation is made on error processing of vector matching and vector repositioning in the embodiment of the specification, a robust estimation method in the surveying and mapping field is used for reference, gross errors in observed data can be accurately distinguished and removed, and accuracy of pose correction numbers is finally guaranteed. By combining filtering estimation, a central limit theorem, a hypothesis testing method and the like, a series of testing quantities are constructed by utilizing the matching residual errors before and after relocation, finally, the real world change can be accurately judged through the testing quantities, and the reliability of the change finding result is described through a mathematical method.

Corresponding to the above method embodiment, the present specification further provides an embodiment of a vector-based map processing apparatus, and fig. 6 shows a schematic structural diagram of a vector-based map processing apparatus provided in an embodiment of the present specification. As shown in fig. 6, the apparatus includes:

the vector matching module 602 is configured to match the initial vector and the updated vector of the target map according to a preset matching rule, and determine a vector matching pair;

a parameter calculation module 604 configured to determine pose adjustment parameters of the update vector and repositioning parameters of each vector point in the update vector according to the vector matching pairs;

a vector adjusting module 606 configured to adjust the update vector according to the pose adjustment parameter and the repositioning parameter, so as to obtain an adjusted update vector;

a confidence determination module 608 configured to determine a confidence of the updated vector according to a matching distance between an initial vector and an updated vector in the vector matching pair and an association relationship between the initial vector and the adjusted updated vector;

a change determining module 610 configured to determine whether the target map has changed according to the confidence of the vector matching pair, the pose adjustment parameter, and/or the update vector.

Optionally, the vector matching module 602 is further configured to:

Optionally, the vector matching module 602 is further configured to include:

calculating a first fitting residual of a vector point in the initial vector according to the initial road geometric elements of the initial vector, and calculating a root mean square, a mean value and a standard deviation of the first fitting residual according to the first fitting residual;

Optionally, the vector matching module 602 is further configured to:

Optionally, the parameter calculating module 604 is further configured to:

Optionally, the vector adjusting module 606 is further configured to:

Optionally, the apparatus further comprises:

a segmentation module configured to:

Optionally, the confidence determination module 608 is further configured to:

Optionally, the change determining module 610 is further configured to:

if not, determining that the target map changes.

The map processing device based on the vector provided by the embodiment of the specification can timely and accurately detect the change of the real world based on the initial vector data and the updated vector data of the target map, and maintain the timeliness of the data in the target map.

The above is a schematic scheme of a vector-based map processing apparatus of the present embodiment. It should be noted that the technical solution of the vector-based map processing apparatus belongs to the same concept as that of the vector-based map processing method described above, and details of the technical solution of the vector-based map processing apparatus, which are not described in detail, can be referred to the description of the technical solution of the vector-based map processing method described above.

FIG. 7 illustrates a block diagram of a computing device 700 provided in accordance with one embodiment of the present description. The components of the computing device 700 include, but are not limited to, memory 710 and a processor 720. Processor 720 is coupled to memory 710 via bus 730, and database 750 is used to store data.

Computing device 700 also includes access device 740, access device 740 enabling computing device 700 to communicate via one or more networks 760. Examples of such networks include the Public Switched Telephone Network (PSTN), a Local Area Network (LAN), a Wide Area Network (WAN), a Personal Area Network (PAN), or a combination of communication networks such as the internet. Access device 740 may include one or more of any type of network interface, e.g., a Network Interface Card (NIC), wired or wireless, such as an IEEE802.11 Wireless Local Area Network (WLAN) wireless interface, a worldwide interoperability for microwave access (Wi-MAX) interface, an ethernet interface, a Universal Serial Bus (USB) interface, a cellular network interface, a bluetooth interface, a Near Field Communication (NFC) interface, and so forth.

In one embodiment of the present description, the above-described components of computing device 700, as well as other components not shown in FIG. 7, may also be connected to each other, such as by a bus. It should be understood that the block diagram of the computing device architecture shown in FIG. 7 is for purposes of example only and is not limiting as to the scope of the present description. Those skilled in the art may add or replace other components as desired.

Computing device 700 may be any type of stationary or mobile computing device, including a mobile computer or mobile computing device (e.g., tablet, personal digital assistant, laptop, notebook, netbook, etc.), mobile phone (e.g., smartphone), wearable computing device (e.g., smartwatch, smartglasses, etc.), or other type of mobile device, or a stationary computing device such as a desktop computer or PC. Computing device 700 may also be a mobile or stationary server.

Wherein the processor 720 is configured to execute computer-executable instructions that, when executed by the processor, implement the steps of the vector-based map processing method described above.

The above is an illustrative scheme of a computing device of the present embodiment. It should be noted that the technical solution of the computing device and the technical solution of the vector-based map processing method belong to the same concept, and details that are not described in detail in the technical solution of the computing device can be referred to the description of the technical solution of the vector-based map processing method.

An embodiment of the present specification also provides a computer-readable storage medium storing computer-executable instructions that, when executed by a processor, implement the steps of the vector-based map processing method described above.

The above is an illustrative scheme of a computer-readable storage medium of the present embodiment. It should be noted that the technical solution of the storage medium belongs to the same concept as that of the above-mentioned vector-based map processing method, and for details that are not described in detail in the technical solution of the storage medium, reference may be made to the description of the technical solution of the above-mentioned vector-based map processing method.

An embodiment of the present specification further provides a computer program, wherein when the computer program is executed in a computer, the computer program causes the computer to execute the steps of the vector-based map processing method.

The above is an illustrative scheme of a computer program of the present embodiment. It should be noted that the technical solution of the computer program is the same as the technical solution of the vector-based map processing method, and details that are not described in detail in the technical solution of the computer program can be referred to the description of the technical solution of the vector-based map processing method.

The foregoing description has been directed to specific embodiments of this disclosure. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims can be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.

The computer instructions comprise computer program code which may be in the form of source code, object code, an executable file or some intermediate form, or the like. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, usb disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM), Random Access Memory (RAM), electrical carrier wave signals, telecommunications signals, software distribution medium, and the like. It should be noted that the computer readable medium may contain content that is subject to appropriate increase or decrease as required by legislation and patent practice in jurisdictions, for example, in some jurisdictions, computer readable media does not include electrical carrier signals and telecommunications signals as is required by legislation and patent practice.

It should be noted that, for the sake of simplicity, the foregoing method embodiments are described as a series of acts, but those skilled in the art should understand that the present embodiment is not limited by the described acts, because some steps may be performed in other sequences or simultaneously according to the present embodiment. Further, those skilled in the art should also appreciate that the embodiments described in this specification are preferred embodiments and that acts and modules referred to are not necessarily required for an embodiment of the specification.

In the above embodiments, the descriptions of the respective embodiments have respective emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments.

The preferred embodiments of the present specification disclosed above are intended only to aid in the description of the specification. Alternative embodiments are not exhaustive and do not limit the invention to the precise embodiments described. Obviously, many modifications and variations are possible in light of the above teaching. The embodiments were chosen and described in order to best explain the principles of the embodiments and the practical application, to thereby enable others skilled in the art to best understand and utilize the embodiments. The specification is limited only by the claims and their full scope and equivalents.

Claims

1. A vector-based map processing method, comprising:

2. The method of claim 1, wherein the matching the initial vector and the updated vector of the target map according to the preset matching rule to determine a vector matching pair comprises:

3. The method of claim 2, wherein the fitting the initial vector and the updated vector according to the geometric type by a preset fitting algorithm to obtain the road geometric elements of the initial vector and the updated vector comprises:

4. The method according to claim 3, wherein the adjusting the initial road geometry of the initial vector and the initial road geometry of the updated vector according to a preset calculation rule to obtain the road geometry of the initial vector and the updated vector comprises:

5. The method of claim 2, said determining a vector matching pair from said initial vector, said update vector, said road geometry of said initial vector and said road geometry of said update vector, comprising:

6. The method according to claim 1 or 5, wherein the determining of the pose adjustment parameters of the update vector and the repositioning parameters of each vector point in the update vector according to the vector matching pairs comprises:

7. The method according to claim 6, wherein the adjusting the update vector according to the pose adjustment parameter and the repositioning parameter to obtain an adjusted update vector comprises:

8. The method of claim 6, further comprising, before constructing the Kalman filter according to the matching distance between the vector matching pair, the priming vector and the update vector in the vector matching pair:

segmenting the target map according to a preset segmentation rule to obtain a plurality of segmented maps;

9. The method of claim 8, wherein determining the confidence level of the update vector according to the matching distance between the initial vector and the update vector in the vector matching pair and the association relationship between the initial vector and the adjusted update vector comprises:

and determining the confidence coefficient of the absolute precision and the relative precision of the vector points in the updating vector according to the mean value and the variance of the sampling samples.

10. The method of claim 1, the determining whether the target map has changed according to the confidence of the vector matching pairs, the pose adjustment parameters, and/or the update vectors, comprising:

And determining that the target map changes under the condition that the pose adjustment parameter is determined not to meet a preset precision threshold.

11. The method of claim 1, the determining whether the target map has changed according to the confidence of the vector matching pairs, the pose adjustment parameters, and/or the update vectors, comprising:

if not, judging whether the pose adjusting parameter meets a preset precision threshold value,

if not, determining that the target map changes.

12. A vector-based map processing apparatus, comprising:

13. A computing device, comprising:

a memory and a processor;

the memory for storing computer-executable instructions, the processor for executing the computer-executable instructions, the computer-executable instructions when executed by the processor for performing the steps of the vector based map processing method of any of claims 1 to 11.

14. A computer-readable storage medium storing computer-executable instructions which, when executed by a processor, implement the steps of the vector-based map processing method of any one of claims 1-11.