CN113656529B

CN113656529B - Road precision determination method and device and electronic equipment

Info

Publication number: CN113656529B
Application number: CN202111089482.9A
Authority: CN
Inventors: 何淑辉; 杜坤
Original assignee: Beijing Baidu Netcom Science and Technology Co Ltd
Current assignee: Beijing Baidu Netcom Science and Technology Co Ltd
Priority date: 2021-09-16
Filing date: 2021-09-16
Publication date: 2023-01-17
Anticipated expiration: 2041-09-16
Also published as: CN113656529A

Abstract

The disclosure provides a road precision determination method, a road precision determination device and electronic equipment, and relates to the technical field of maps. The specific implementation scheme is as follows: when determining the road precision of the road to be detected in the map road data, the true value road data and the map road data corresponding to the road to be detected can be obtained first; determining a plurality of characteristic point pairs positioned on a lane line in the road to be detected from the truth value road data and the map road data corresponding to the road to be detected; and determining the road precision of the road to be detected in the map data by combining the true value road data and the map road data corresponding to the plurality of characteristic point pairs. In view of the way of adopting lane-level linear elements of a plurality of characteristic point pairs, the road information of the road to be detected can be better described, so that the road precision of the road to be detected in the map data can be accurately determined according to the true value road data and the map road data corresponding to the plurality of characteristic point pairs, and the accuracy of the determined road precision is improved.

Description

Road precision determination method and device and electronic equipment

Technical Field

The present disclosure relates to the field of data processing technologies, and in particular, to a method and an apparatus for determining road accuracy, and an electronic device, and in particular, to the field of map technologies.

Background

The high-precision map is an important component for realizing automatic driving, and particularly the precision of the high-precision map is very important for realizing automatic driving.

In the prior art, the accuracy of map data is generally estimated by adopting a point element mode; however, by using the dot-shaped elements, the elements such as lane lines and guardrails in the map data cannot be accurately evaluated, resulting in poor accuracy of the determined road precision.

Disclosure of Invention

The disclosure provides a road precision determination method, a road precision determination device and electronic equipment, and improves the accuracy of the determined road precision.

According to a first aspect of the present disclosure, there is provided a method for determining map road accuracy, which may include:

and acquiring true value road data and map road data corresponding to the road to be detected.

Determining a plurality of characteristic point pairs positioned on a lane line in the road to be detected from the truth value road data and the map road data corresponding to the road to be detected; each feature point pair includes a first feature point determined in the true value road data and a second feature point determined in the map road data, and the positions of the first feature points and the positions of the second feature points are matched one by one.

And determining the road precision of the road to be detected in the map road data according to the true value road data and the map road data corresponding to the plurality of characteristic point pairs.

According to a second aspect of the present disclosure, there is provided a map road accuracy determination device, which may include:

and the acquisition unit is used for acquiring true value road data and map road data corresponding to the road to be detected.

The determining unit is used for determining a plurality of characteristic point pairs positioned on a lane line in the road to be detected from the true value road data and the map road data corresponding to the road to be detected; wherein each feature point pair includes a first feature point determined in the true-value road data and a second feature point determined in the map road data, and the positions of the first feature point and the second feature point are matched one by one.

And the processing unit is used for determining the road precision of the road to be detected in the map road data according to the true value road data and the map road data corresponding to the plurality of characteristic point pairs.

According to a third aspect of the present disclosure, there is provided an electronic device, which may include:

at least one processor; and

a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,

the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of determining map road accuracy of the first aspect.

According to a fourth aspect of the present disclosure, there is provided a non-transitory computer-readable storage medium storing computer instructions for causing the computer to execute the method for determining map road precision of the first aspect.

According to a fifth aspect of the present disclosure, there is provided a computer program product comprising: a computer program, stored in a readable storage medium, from which at least one processor of an electronic device can read the computer program, execution of the computer program by the at least one processor causing the electronic device to perform the method of the first aspect.

According to the technical scheme, the accuracy of the determined road precision is improved.

It should be understood that the statements in this section do not necessarily identify key or critical features of the embodiments of the present disclosure, nor do they limit the scope of the present disclosure. Other features of the present disclosure will become apparent from the following description.

Drawings

The drawings are included to provide a better understanding of the present solution and are not to be construed as limiting the present disclosure. Wherein:

FIG. 1 is a schematic diagram of a road to be evaluated according to an embodiment of the disclosure;

fig. 2 is a flowchart illustrating a method for determining map road accuracy according to a first embodiment of the disclosure;

fig. 3 is a schematic view of a road to be detected according to an embodiment of the disclosure;

fig. 4 is a schematic diagram of 7 pairs of feature points determined on a lane line in a road to be detected according to an embodiment of the present disclosure;

fig. 5 is a flowchart illustrating a method for determining map road accuracy according to a second embodiment of the present disclosure;

FIG. 6 is a schematic diagram of an absolute accuracy error provided by an embodiment of the present disclosure;

FIG. 7 is a schematic diagram of a relative accuracy error provided by an embodiment of the present disclosure;

FIG. 8 is a schematic illustration of a longitudinal slope accuracy error provided by an embodiment of the present disclosure;

FIG. 9 is a schematic diagram of curvature accuracy error provided by an embodiment of the present disclosure;

FIG. 10 is a schematic view of a course angle accuracy error provided by an embodiment of the present disclosure;

fig. 11 is a schematic diagram of a frequency-to-ratio distribution diagram corresponding to an absolute accuracy error according to an embodiment of the present disclosure;

fig. 12 is a schematic structural diagram of a map road accuracy determination apparatus provided according to a third embodiment of the present disclosure;

fig. 13 is a schematic block diagram of an electronic device provided by an embodiment of the disclosure.

Detailed Description

Exemplary embodiments of the present disclosure are described below with reference to the accompanying drawings, in which various details of the embodiments of the disclosure are included to assist understanding, and which are to be considered as merely exemplary. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the disclosure. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.

In embodiments of the present disclosure, "at least one" means one or more, "a plurality" means two or more. "and/or" describes the access relationship of the associated object, meaning that there may be three relationships, e.g., A and/or B, which may mean: a exists alone, A and B exist simultaneously, and B exists alone, wherein A and B can be singular or plural. In the description of the text of the present disclosure, the character "/" generally indicates that the former and latter associated objects are in an "or" relationship. In addition, in the embodiments of the present disclosure, "first", "second", "third", "fourth", "fifth", and "sixth" are only used to distinguish the contents of different objects, and have no other special meaning.

The technical scheme provided by the embodiment of the disclosure can be applied to scenes such as high-precision map precision evaluation, automatic driving track precision evaluation, high-precision acquisition track precision evaluation, combined navigation track precision evaluation and the like. The high-precision map is an important component for realizing automatic driving, and particularly the precision of the high-precision map is very important for realizing automatic driving. Currently, the accuracy of map data is generally estimated by using a dot-shaped element method.

For example, as shown in fig. 1, fig. 1 is a schematic diagram of a road to be evaluated according to an embodiment of the present disclosure, when evaluating road accuracy in the road to be evaluated in map data, a dot-like element may be used to perform dotting on a lane line in the road to be evaluated, for example, feature points A, B, C, D, E shown in fig. 1 may use true value data and map data of feature point a, evaluate road accuracy of a lane dotted line L2 to which feature point a belongs, use true value data and map data of feature point B, evaluate road accuracy of a lane dotted line to which feature point B belongs, use true value data and map data of feature point C, evaluate road accuracy of a road arrow L3 to which feature point C belongs, use true value data and map data of feature point D, evaluate road accuracy of a lane line to which feature point D belongs, and evaluate road accuracy of a lane line L1 to which feature point E by using true value data and map data of feature point E.

As can be seen from fig. 1, the lane dotted line L2 to which the feature point a belongs, the lane dotted line to which the feature point B belongs, and the road arrow L3 to which the feature point C belongs are all road segments with short lengths, and the accuracy of the road can be evaluated by using dot-shaped elements. However, for a road segment with a long length, for example, the lane line L1 to which the feature point E belongs or the lane line to which the feature point D belongs, since high-order information such as the course, the state, the gradient, and the like of the road cannot be accurately determined by using the point-like elements for the evaluation, the accuracy of the road to which the feature point E belongs or the lane line to which the feature point D belongs in the map data cannot be accurately evaluated by using the point-like element evaluation, and thus the accuracy of the determined road accuracy is poor.

In order to accurately determine the road precision of the map data, it may be considered that real-valued road data of a road to be detected in the real world is collected by an intra-industry high-precision collection device, a lane-level linear element mode is adopted, a plurality of characteristic point pairs are selected from a lane line in the road to be detected, the road precision of the road to be detected in the map data is jointly evaluated by combining the real-valued road data and the map road data corresponding to the plurality of characteristic point pairs, and in view of the lane-level linear element mode adopting the plurality of characteristic point pairs, the road information of the road to be detected can be better described.

Based on the technical concept, the embodiment of the present disclosure provides a method for determining map road accuracy, and the method for determining map road accuracy provided by the present disclosure will be described in detail through specific embodiments. It is to be understood that the following detailed description may be combined with other embodiments, and that the same or similar concepts or processes may not be repeated in some embodiments.

Example one

Fig. 2 is a flowchart illustrating a method for determining map road accuracy according to a first embodiment of the present disclosure, where the method may be performed by software and/or a hardware device, for example, the hardware device may be a terminal or a server. For example, referring to fig. 2, the method for determining the accuracy of the map road may include:

s201, true value road data and map road data corresponding to the road to be detected are obtained.

For example, the road to be detected may be a road determined based on a set of same-name points, and the road segments between the set of same-name points are determined as the road to be detected. The homonymous point is a point where the true value road data and the map road data are the same.

For example, as shown in fig. 3, fig. 3 is a schematic view of a road to be detected provided by the embodiment of the present disclosure, when the road to be detected is determined, the same road surface feature position, such as a ground arrow, a diversion area, a dotted line and an isocenter, may be selected as a same-name point, and the whole set of lane lines are broken in parallel and level, and the lane lines therein are intercepted as the road to be detected. Referring to fig. 3, the starting point selects the front sharp corner of the ground arrow to be flush and break the whole set of lane lines; similarly, the end point selects the parallel and level of the corner point of the diversion area to break the whole group of lane lines, so that the road between two homonymous points can be determined as the road to be detected, and the road to be detected can be determined.

For example, when the truth value road data corresponding to the road to be detected is obtained, the truth value road data of the road to be detected may be collected by using high-precision collection equipment in the industry, or the truth value road data of the road to be detected may be obtained by using other methods, which may be specifically set according to actual needs, and the embodiment of the present disclosure is not particularly limited.

After the truth-value road data and the map road data corresponding to the road to be detected are acquired through S201, a plurality of feature point pairs are determined from a lane line in the road to be detected in a lane-level linear element manner, so that the road precision of the road to be detected in the map data can be jointly evaluated by combining the collected truth-value road data and the map road data corresponding to the plurality of feature point pairs, that is, the following S202 and S203 are executed:

s202, determining a plurality of characteristic point pairs on a lane line in a road to be detected from true value road data and map road data corresponding to the road to be detected; each feature point pair includes a first feature point determined in the truth value road data and a second feature point determined in the map road data, and the positions of the first feature points and the positions of the second feature points are matched one by one.

For example, when determining a plurality of feature point pairs on a lane line in a road to be detected, a preset dotting rule, for example, a dotting rule with the same interval distance, may be adopted to perform batch processing and statistical analysis of a program, and a plurality of feature points on a lane line in a road to be detected are determined from truth-value road data corresponding to the road to be detected and may be recorded as first feature points; and performing batch processing and statistical analysis on the program by adopting the same dotting rule, determining a plurality of characteristic points on a lane line in the road to be detected from the map road data corresponding to the road to be detected, wherein the characteristic points can be marked as second characteristic points, and marking two first characteristic points and the second characteristic points which are matched in position as first characteristic point pairs, thereby determining a plurality of characteristic point pairs on the lane line in the road to be detected. It should be noted that, in the embodiment of the present disclosure, in the following description, a lane line in a road to be detected in the true value road data may be marked as a lane line corresponding to the true value road data, and a lane line in a road to be detected in the map road data may be marked as a lane line corresponding to the map road data.

For example, as shown in fig. 4, fig. 4 is a schematic diagram of 7 feature point pairs determined on a lane line in a road to be detected according to an embodiment of the present disclosure, it should be noted that fig. 4 only illustrates 7 feature point pairs as an example, and in an actual application process, the number of the determined feature point pairs is much greater than 7, it can be seen that each feature point pair includes two feature points, one of the feature points is a first feature point determined on the lane line corresponding to the true value road data, and the other feature point is a second feature point on the lane line corresponding to the map road data. It is understood that, in general, the greater the number of the determined feature point pairs, the higher the accuracy of the determined road precision is based on the true road data and the map road data corresponding to the feature point pairs, that is, the number of the feature point pairs is in direct proportion to the accuracy of the determined road precision.

S203, determining the road precision of the road to be detected in the map road data according to the corresponding true value road data and the map road data of the plurality of characteristic point pairs.

It can be seen that, in the embodiment of the present disclosure, when determining the road precision of the road to be detected in the map road data, the true value road data and the map road data corresponding to the road to be detected may be obtained first; determining a plurality of characteristic point pairs positioned on a lane line in the road to be detected from true value road data and map road data corresponding to the road to be detected; and determining the road precision of the road to be detected in the map data by combining the true value road data and the map road data corresponding to the plurality of characteristic point pairs. In view of the way of adopting lane-level linear elements of a plurality of characteristic point pairs, the road information of the road to be detected can be better described, so that the road precision of the road to be detected in the map data can be accurately determined according to the true value road data and the map road data corresponding to the plurality of characteristic point pairs, and the accuracy of the determined road precision is improved.

Based on the above embodiment shown in fig. 1, in order to facilitate understanding how to determine the road precision of the road to be detected in the map road data according to the corresponding true value road data and the map road data of the plurality of feature point pairs in the above S203, a detailed description will be given below by using a second embodiment shown in fig. 5.

Example two

Fig. 5 is a flowchart illustrating a method for determining map road accuracy according to a second embodiment of the present disclosure, where the method may be performed by software and/or a hardware device, for example, the hardware device may be a terminal or a server. For example, referring to fig. 5, the method for determining the accuracy of the map road may include:

and S501, acquiring a true value coordinate of a first feature point in each feature point pair according to the true value road data corresponding to each feature point pair, and acquiring a map coordinate of a second feature point in each feature point pair according to the map road data corresponding to each feature point pair.

The truth coordinate may refer to a coordinate of the first feature point in the truth road data, and the map coordinate may refer to a coordinate of the second feature point in the map road data.

It is understood that, in general, the true-value road data corresponding to a feature point pair includes other data besides the true-value coordinate of the first feature point in the feature point pair, so that the true-value coordinate of the first feature point in the feature point pair can be extracted from the true-value road data according to the true-value road data corresponding to the feature point pair; similarly, the map road data corresponding to the feature point pair includes the true value coordinate of the second feature point in the feature point pair, and also includes other data, so that the true value coordinate of the second feature point in the feature point pair can be extracted from the map road data according to the map road data corresponding to the feature point pair, thereby obtaining the true value coordinate of the first feature point in the feature point pair and the map coordinate of the second feature point.

In this way, when the true value coordinate of the first feature point and the map coordinate of the second feature point in each feature point pair are obtained, and the accuracy error corresponding to each feature point pair is determined, that is, the following S502 is executed to determine the road accuracy according to the accuracy error corresponding to each feature point pair.

And S502, determining the corresponding precision error of each characteristic point pair according to the true value coordinate of the first characteristic point and the map coordinate of the second characteristic point in each characteristic point pair.

For example, since the evaluation index of the road accuracy generally includes at least one of absolute accuracy, relative accuracy, slope accuracy, curvature accuracy, or heading angle accuracy, in the embodiment of the present disclosure, when determining the accuracy error corresponding to the characteristic point pair, the accuracy error corresponding to the characteristic point pair may include at least one of absolute accuracy error, relative accuracy error, slope accuracy error, curvature accuracy error, or heading angle accuracy error. It can be understood that, when determining the road precision based on the corresponding precision errors of the feature point pairs, the more the selected evaluation index of the precision error is, the more the accuracy of the corresponding determined road precision is.

The precision error is taken as an absolute precision error, wherein the absolute precision error can be determined by using the distance difference between the first feature point and the second feature point at the same position. When determining the absolute accuracy error corresponding to each feature point pair according to the true value coordinate of the first feature point in each feature point pair and the map coordinate of the second feature point, it can be understood that, in view of the similarity of the determination methods of the absolute accuracy error corresponding to each feature point pair, in order to avoid redundant description, how to determine the absolute accuracy error corresponding to each of the feature point pairs will be described below by taking the determination of the accuracy error corresponding to any one of the feature point pairs as an example.

For example, when determining the absolute accuracy error corresponding to the feature point pair according to the true value coordinate of the first feature point in the feature point pair and the map coordinate of the second feature point, referring to fig. 6, where fig. 6 is a schematic diagram of an absolute accuracy error provided in the embodiment of the present disclosure, a difference between the true value coordinate of the first feature point and the map coordinate of the second feature point may be calculated, and the difference is determined as the absolute accuracy error corresponding to the feature point pair, so as to obtain the absolute accuracy error corresponding to the feature point pair, so that the road accuracy of the road to be detected in the map data may be subsequently evaluated based on the determined absolute accuracy error corresponding to the feature point pair.

Taking the accuracy error as an example of a relative accuracy error, the relative accuracy error may be determined by using a difference between a distance between two feature points or feature contour points on the map and an actual distance corresponding to the distance. When determining the relative accuracy error corresponding to each feature point pair according to the true value coordinate of the first feature point in each feature point pair and the map coordinate of the second feature point, it can be understood that, in view of the similarity of the determination methods of the relative accuracy error corresponding to each feature point pair, in order to avoid redundant description, how to determine the relative accuracy error corresponding to each of the plurality of feature point pairs will be described below by taking the determination of the relative accuracy error corresponding to any one of the feature point pairs as an example. It should be noted that, two feature points or feature contour points may be feature points selected on the lane line, or may also be other feature points, for example, a road sign, and may be specifically set according to actual needs.

For example, when determining the relative accuracy error corresponding to the feature point pair according to the true value coordinate of the first feature point in the feature point pair and the map coordinate of the second feature point, a first distance between two first feature points may be determined according to the true value coordinate of the first feature point in the feature point pair and the true value coordinate of the first feature point in the first other feature point pair; determining a second distance between two second feature points according to the map coordinates of the second feature points in the feature point pair and the map coordinates of the second feature points in the first other feature point pair; wherein the first other characteristic point pair is another characteristic point pair except the characteristic point pair in the plurality of characteristic point pairs; and determining the difference between the first distance and the second distance as the corresponding relative error precision of the characteristic point pair.

For example, referring to fig. 7, fig. 7 is a schematic diagram of relative accuracy errors provided in the embodiment of the present disclosure, and it can be seen that a first feature point in a feature point pair and a first feature point in a first other feature point pair are points on two lane lines, a first distance between the two first feature points may be understood as a width of two lane lines corresponding to true road data, and a second distance between a second feature point in the feature point pair and a second feature point in the first other feature point pair may be understood as a width of two lane lines corresponding to map road data, a difference between the two widths, Δ d = Dn-Dn (n =1,2,3), is a relative accuracy error of a lane line, so as to obtain the relative accuracy error corresponding to the feature point pair, so that a subsequent point pair may evaluate the road accuracy of a road to be detected in the map data based on the determined relative accuracy error corresponding to the feature point pair.

Taking the precision error as the longitudinal slope precision error as an example, wherein the slope precision error can be determined by using the difference value between the actual longitudinal slope and the actual longitudinal slope of the feature point on the lane line. For example, if the longitudinal slope of the feature point determined based on the true value road data is i, and the longitudinal slope of the feature point determined based on the map road data is i + Δ i, the longitudinal slope accuracy error is determined using the distribution of Δ i. Referring to fig. 8, fig. 8 is a schematic diagram of a longitudinal slope precision error provided by an embodiment of the present disclosure, where a ratio of a height difference h between two feature points of the same slope segment on a road longitudinal section to a horizontal distance L thereof is expressed by a percentage, and is generally expressed by a letter "i", and the following formula can be referred to:

the percentage is converted to an angle, usually denoted by "θ", θ = arctan (i) in units of: radian, 1 radian = 180/pi degrees.

When determining the longitudinal slope precision error corresponding to each feature point pair according to the true value coordinate of the first feature point in each feature point pair and the map coordinate of the second feature point, it can be understood that, in view of the similarity of the determination methods of the longitudinal slope precision error corresponding to each feature point pair, in order to avoid redundancy, how to determine the longitudinal slope precision error corresponding to each of the feature point pairs will be described below by taking the determination of the longitudinal slope precision error corresponding to any one of the feature point pairs as an example.

For example, when determining the longitudinal slope precision error corresponding to a feature point pair according to the true value coordinate of a first feature point in the feature point pair and the map coordinate of a second feature point in the feature point pair, a first height difference and a first horizontal distance between two first feature points may be determined according to the true value coordinate of the first feature point in the feature point pair and the true value coordinate of the first feature point in a second other feature point pair; determining a second height difference and a second horizontal distance between two second feature points according to the map coordinates of the second feature points in the feature point pair and the map coordinates of the second feature points in a second other feature point pair; wherein the second other characteristic point pair is a characteristic point pair other than the characteristic point pair in the plurality of characteristic point pairs; and determining the longitudinal slope precision error corresponding to the characteristic point pair according to the first height difference, the first horizontal distance, the second height difference and the second horizontal distance.

For example, when determining the longitudinal slope precision error corresponding to the feature point pair according to the first height difference, the first horizontal distance, the second height difference, and the second horizontal distance, a first ratio between the first height difference and the first horizontal distance and a second ratio between the second height difference and the second horizontal distance may be determined first; and determining the difference value between the first ratio and the second ratio as the longitudinal slope precision error corresponding to the characteristic point pair, thereby obtaining the longitudinal slope precision error corresponding to the characteristic point pair, and then subsequently evaluating the road precision of the road to be detected in the map data based on the determined longitudinal slope precision error corresponding to the characteristic point pair.

Taking the precision error as the curvature precision error as an example, the curvature precision error may be determined by using an error distribution of a curvature value of a feature point on the lane line and a true curvature value of the point on the actual road. For example, if the true curvature value of the feature point determined based on the true value road data is k and the curvature value of the feature point determined based on the map road data is k + Δ k, the curvature accuracy error is determined using the distribution of Δ k. Referring to fig. 9, fig. 9 is a schematic diagram of a curvature accuracy error provided by an embodiment of the present disclosure, when determining a curvature accuracy corresponding to a feature point 2 in a feature point pair, it may be determined as a previous feature point 1 and a subsequent feature point 3, and a triangle is constructed based on the three feature points, assuming that the triangle is Δ ABC, and three sides are a, b, and c, respectively, and a radius R of a circle circumscribed by the triangle may be represented by the following formula:

wherein the content of the first and second substances,

the curvature k =1/R and the curvature k =1/R,

thereby determining the curvature accuracy corresponding to the feature point 2.

When determining the curvature precision error corresponding to each feature point pair according to the true value coordinate of the first feature point in each feature point pair and the map coordinate of the second feature point, it can be understood that, in view of the similarity of the determination methods of the curvature precision error corresponding to each feature point pair, in order to avoid redundant description, how to determine the curvature precision error corresponding to each of the feature point pairs will be described below by taking the determination of the curvature precision error corresponding to any one of the feature point pairs as an example.

For example, when determining the curvature accuracy error corresponding to the characteristic point pair, a previous characteristic point pair and a next characteristic point pair of the characteristic point pair may be determined from the plurality of characteristic point pairs according to respective positions of the plurality of characteristic point pairs; determining a first radius of a triangle circumscribed circle formed by the three first feature points according to the true value coordinate of the first feature point in the previous feature point pair, the true value coordinate of the first feature point in the feature point pair and the true value coordinate of the first feature point in the next feature point pair; determining a second radius of a triangle circumscribed circle formed by the three second feature points according to the map coordinate of the second feature point in the previous feature point pair, the map coordinate of the second feature point in the feature point pair and the map coordinate of the second feature point in the next feature point pair; and determining the curvature precision error corresponding to the characteristic point pair according to the first radius and the second radius.

For example, when determining the accuracy error of the curvature corresponding to the feature point pair according to the first radius and the second radius, a first curvature corresponding to the first radius and a second curvature corresponding to the second radius may be determined first; and determining the difference value between the first curvature and the second curvature as the curvature precision error corresponding to the characteristic point pair, thereby obtaining the curvature precision error corresponding to the characteristic point pair, and then subsequently evaluating the road precision of the road to be detected in the map data based on the determined curvature precision error corresponding to the characteristic point pair.

Taking the accuracy error as the accuracy error of the heading angle as an example, wherein the accuracy error of the heading angle can be determined by adopting an included angle theta between the tangential direction of the lane line and the tangential direction of the actual lane line. As shown in fig. 10, fig. 10 is a schematic view of a course angle accuracy error provided by the embodiment of the present disclosure, when the course angle accuracy error corresponding to a feature point pair is determined, a first feature point in the feature point may be marked as a feature point a as a tangent point, and a first tangent line of a lane line to which the feature point a belongs is drawn from the feature point a; and a second characteristic point in the characteristic points can be marked as a characteristic point A 'to serve as a tangent point, a second tangent line of the lane line to which the second characteristic point belongs is led out from the characteristic point A', and a theta value is calculated according to an included angle between vectors of the two tangent lines, wherein the theta value can be obtained by referring to the following formula, so that the course angle precision error corresponding to the characteristic point pair is determined according to the included angle theta.

When determining the course angle accuracy error corresponding to each feature point pair according to the true value coordinate of the first feature point in each feature point pair and the map coordinate of the second feature point, it can be understood that, in view of the similarity of the determination methods of the course angle accuracy error corresponding to each feature point, in order to avoid redundancy, the following will describe how to determine the course angle accuracy error corresponding to each of the plurality of feature point pairs by taking the determination of the course angle accuracy error corresponding to any one of the feature point pairs as an example.

For example, when determining the accuracy error of the course angle corresponding to each feature point pair according to the coordinates of each feature point pair, determining a first tangent line of the lane line by taking the true value coordinate of the first feature point in the feature point pair as the tangent point; determining a second tangent of the lane line by taking the map coordinate of a second feature point in the feature point pair as a tangent point; and determining the course angle precision error corresponding to the characteristic point pair according to the first tangent and the second tangent.

For example, when determining the course angle precision error corresponding to the feature point pair according to the first tangent line and the second tangent line, an included angle between the first tangent line and the second tangent line may be determined first, and the included angle is determined as the course angle precision error corresponding to the feature point pair, so as to obtain the course angle precision error corresponding to the feature point pair, and thus, the road precision of the road to be detected in the map data may be evaluated subsequently based on the determined course angle precision error corresponding to the feature point pair.

It is understood that the embodiments of the present disclosure are only illustrated by examples that the precision error may include at least one of an absolute precision error, a relative precision error, a slope precision error, a curvature precision error, or a heading angle precision error, but the embodiments of the present disclosure are not limited thereto.

After the accuracy error corresponding to each feature point pair is determined in S502, the road accuracy may be determined based on the accuracy error corresponding to each feature point pair, that is, the following S503 is executed:

and S503, determining the road precision according to the corresponding precision errors of the characteristic point pairs.

For example, when determining the road precision according to the precision error corresponding to each feature point pair, an initial frequency corresponding to each precision error may be determined according to the precision error corresponding to each feature point pair; and determining the road precision according to the initial frequency corresponding to each precision error.

The initial frequency corresponding to a certain precision error can be understood as the frequency of the precision error occurring in the precision errors corresponding to a plurality of feature points. For example, if the number of the plurality of feature point pairs is 1000 times, the accuracy error corresponding to each of the plurality of feature point pairs is calculated, and 1000 accuracy errors are obtained, and if a certain accuracy error is 0.6 and 0.6 out of the 1000 accuracy errors occurs 86 times, the initial frequency corresponding to the accuracy error 0.6 is 86 times.

Illustratively, when determining the road precision according to the initial frequency corresponding to each precision error, determining the initial frequency corresponding to the precision error and the sum of the initial frequency corresponding to each precision error smaller than the precision error for each precision error, and determining the sum as the target frequency corresponding to the precision error; and determining the road precision according to the target frequency corresponding to each precision error.

The target frequency corresponding to a certain precision error can be understood as the initial frequency corresponding to the precision error, and the total frequency of the initial frequencies corresponding to the precision errors smaller than the precision error. For example, if the number of the plurality of feature point pairs is 1000, then the precision errors corresponding to the plurality of feature point pairs are calculated, and 1000 precision errors are obtained, and if a certain precision error is 0.6 and 0.6 of the 1000 precision errors occurs 86 times, the initial frequency corresponding to the precision error 0.6 is 86 times; the precision errors smaller than the precision error 0.6 are respectively 0.3 and 0.4, wherein the initial frequency corresponding to the precision error 0.3 is 100, the initial frequency corresponding to the precision error 0.4 is 300, and the target frequency corresponding to the precision error 0.6 is 486.

For example, when determining the road precision according to the target frequency corresponding to each precision error, the target frequency corresponding to each precision error and the ratio between the number of the characteristic point pairs may be determined, and the frequency ratio corresponding to each precision error may be obtained according to the ratio; determining the target error precision corresponding to the preset standard deviation according to the frequency ratio corresponding to each precision error and the preset frequency ratio corresponding to the preset standard deviation; and the target error precision corresponding to the preset standard deviation is used for indicating the road precision.

In order to facilitate understanding of how to determine the road precision according to the precision error corresponding to each feature point pair in the embodiment of the present disclosure, the following will describe in detail how to determine the road precision according to the precision error corresponding to each feature point pair, taking the precision error as an absolute precision error as an example.

Assuming that the number of feature point pairs of the above structure is 15245, the absolute accuracy error corresponding to each feature point pair can be calculated in S502, and assuming that the obtained absolute accuracy errors respectively include 0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9, 1, 1.1, and 1.2, where the initial frequency corresponding to the absolute accuracy error 0.1 is 6424, the initial frequency corresponding to the absolute accuracy error 0.2 is 1869, the initial frequency corresponding to the absolute accuracy error 0.3 is 2846, the initial frequency corresponding to the absolute accuracy error 0.4 is 1503, the initial frequency corresponding to the absolute accuracy error 0.5 is 1186, the initial frequency corresponding to the absolute accuracy error 0.6 is 610, the initial frequency corresponding to the absolute accuracy error 0.7 is 273, the initial frequency corresponding to the absolute accuracy error 0.8 is 131, the initial frequency corresponding to the absolute accuracy error 0.9 is 239, the absolute accuracy corresponding to the absolute frequency error 1.1, and the initial frequency corresponding to the absolute accuracy error 1.11.

Based on the initial frequency corresponding to each absolute accuracy error, the target frequency corresponding to each absolute accuracy error can be determined, wherein the target frequency corresponding to an absolute accuracy error of 0.1 is 6424, the target frequency corresponding to an absolute accuracy error of 0.2 is 6424, that is, the target frequency corresponding to an absolute accuracy error of 0.3 is 8293, the target frequency corresponding to an absolute accuracy error of 0.3 is 12642, the target frequency corresponding to an absolute accuracy error of 0.4 is 12642, the target frequency corresponding to an absolute accuracy error of 0.5 is 6424, and the initial frequency corresponding to an accuracy error of 0.2 is 1869, that is, the target frequency corresponding to an absolute accuracy error of 0.3 is 11139, similarly, the target frequency corresponding to an absolute accuracy error of 0.4 is 1269, the target frequency corresponding to an absolute accuracy error of 0.5 is 3228, the target frequency corresponding to an absolute accuracy error of 0.6 is 3236, the target frequency corresponding to an absolute accuracy error of 0.1 is 3236, the target frequency corresponding to an absolute accuracy error of 379, and the target frequency corresponding to an absolute accuracy error of 379 is 3260.1, and an absolute accuracy of 379.

After the target frequency corresponding to each absolute accuracy error is determined, the frequency ratio corresponding to each absolute accuracy error can be determined according to the ratio of the target frequency to the number 15245 of the feature point pairs, and the following table 1 can be referred to:

TABLE 1

Absolute accuracy error	Target frequency	Ratio of frequency to frequency
			0.1	6424	42.14％
0.2	8293	54.40％
			0.3	11139	73.07％
0.4	12642	82.93％
			0.5	13828	90.71％
0.6	14438	94.71％
			0.7	14711	96.50％
0.8	14842	97.36％
			0.9	15081	98.93％
1	15168	99.50％
			1.1	15234	99.93％
1.2	15245	100％

As can be seen from table 1, the frequency occupancy corresponding to the absolute accuracy error 0.1 is 42.14%, the frequency occupancy corresponding to the absolute accuracy error 0.2 is 54.40%, the frequency occupancy corresponding to the absolute accuracy error 0.3 is 73.07%, the frequency occupancy corresponding to the absolute accuracy error 0.4 is 82.93%, the frequency occupancy corresponding to the absolute accuracy error 0.5 is 90.71%, the frequency occupancy corresponding to the absolute accuracy error 0.6 is 94.71%, the frequency occupancy corresponding to the absolute accuracy error 0.7 is 96.50%, the frequency occupancy corresponding to the absolute accuracy error 0.8 is 97.36%, the frequency occupancy corresponding to the absolute accuracy error 0.9 is 98.93%, the frequency occupancy corresponding to the absolute accuracy error 1 is 99.50%, the frequency occupancy corresponding to the absolute accuracy error 1.1 is 99.93%, and the frequency occupancy corresponding to the absolute accuracy error 1.2 is 100%.

Based on the frequency ratio shown in table 1, a frequency ratio distribution graph corresponding to an absolute accuracy error can be obtained correspondingly, as shown in fig. 11, fig. 11 is a schematic diagram of a frequency ratio distribution graph corresponding to an absolute accuracy error provided in the embodiment of the present disclosure, and based on table 1 or fig. 11, in view of that, in a normal case, the preset standard deviations for estimating the road accuracy are respectively 1-fold standard deviation, 2-fold standard deviation, and 3-fold standard deviation, and the preset frequency ratio corresponding to 1-fold standard deviation is 68.26%, the preset frequency ratio corresponding to 2-fold standard deviation is 95.44%, and the preset frequency ratio corresponding to 3-fold standard deviation is 99.73%, based on the preset frequency ratios corresponding to 1-fold standard deviation, 2-fold standard deviation, and 3-fold standard deviation, it can be determined that, in the road accuracy evaluation scenario, the target accuracy error under the 1-fold standard deviation is 3238 zft 3238-fold standard deviation, and the target accuracy error under the 1-fold standard deviation is 3262 zft, as shown in the following table 1.2:

TABLE 2

With reference to table 2, after a target precision error of 0.3,2 times of standard deviation and a target precision error of 1.1 3 times of standard deviation, which correspond to the absolute precision error, are respectively determined, the road precision of the road to be detected in the map data can be determined through a target precision error of 0.3,2 times of standard deviation and a target precision error of 0.8 times of standard deviation and a target precision error of 1.1 times of standard deviation, which correspond to the absolute precision error, so that the road precision of the road to be detected in the map data can be accurately determined, and the accuracy of the determined road precision is improved.

It should be noted that, the above is only described by taking the absolute accuracy error corresponding to each feature point pair as an example to determine the road accuracy, and when the road accuracy is determined according to other accuracy errors corresponding to each feature point pair, for example, a relative accuracy error, a slope accuracy error, a curvature accuracy error, or a heading angle accuracy error, an implementation manner of determining the road accuracy is similar to that of determining the road accuracy according to the absolute accuracy error corresponding to each feature point pair, and reference may be made to the absolute accuracy error corresponding to each feature point pair to determine a relevant description of the road accuracy, and here, the embodiment of the present disclosure is not described in detail again.

It can be seen that, in the embodiment of the present application, when determining the road precision of a road to be detected in map road data, the true value coordinates of the first feature point in each feature point pair may be obtained first, and the map coordinates of the second feature point in each feature point pair may be obtained according to the map road data corresponding to each feature point pair; and determining the corresponding precision error of each characteristic point pair according to the true value coordinate of the first characteristic point in each characteristic point pair and the map coordinate of the second characteristic point, and determining the road precision according to the corresponding precision error of each characteristic point pair. In this way, the road information of the road to be detected can be better described by adopting the lane-level linear elements of the plurality of characteristic point pairs, so that the road precision of the road to be detected in the map data can be accurately determined, and the accuracy of the determined road precision is improved.

EXAMPLE III

Fig. 12 is a schematic structural diagram of a map road accuracy determining apparatus 120 according to a third embodiment of the present disclosure, for example, please refer to fig. 12, where the map road accuracy determining apparatus 120 may include:

the obtaining unit 1201 is configured to obtain true value road data and map road data corresponding to the road to be detected.

A determining unit 1202, configured to determine, from the true value road data and the map road data corresponding to the road to be detected, a plurality of feature point pairs located on a lane line in the road to be detected; each feature point pair includes a first feature point determined in the truth road data and a second feature point determined in the map road data, and the positions of the first feature points and the positions of the second feature points are matched one by one.

The processing unit 1203 is configured to determine road precision of a road to be detected in the map road data according to the true value road data and the map road data corresponding to the plurality of feature point pairs.

Optionally, the processing unit 1203 includes a first processing module, a second processing module, and a third processing module.

And the first processing module is used for acquiring the true value coordinates of the first characteristic points in each characteristic point pair according to the true value road data corresponding to each characteristic point pair, and acquiring the map coordinates of the second characteristic points in each characteristic point pair according to the map road data corresponding to each characteristic point pair.

And the second processing module is used for determining the corresponding precision error of each characteristic point pair according to the true value coordinate of the first characteristic point in each characteristic point pair and the map coordinate of the second characteristic point.

And the third processing module is used for determining the road precision according to the precision errors corresponding to the characteristic point pairs.

Optionally, the third processing module includes a first processing sub-module and a second processing sub-module.

And the first processing submodule is used for determining the initial frequency corresponding to each precision error according to the precision error corresponding to each characteristic point pair.

And the second processing submodule is used for determining the road precision according to the initial frequency corresponding to each precision error.

Optionally, the second processing sub-module is specifically configured to determine, for each precision error, an initial frequency corresponding to the precision error, and a sum of the initial frequency corresponding to each precision error smaller than the precision error, and determine the sum as a target frequency corresponding to the precision error; and determining the road precision according to the target frequency corresponding to each precision error.

Optionally, the second processing sub-module is specifically configured to determine a ratio between the target frequency corresponding to each precision error and the number of the feature point pairs, and obtain a frequency ratio corresponding to each precision error according to the ratio; determining target error precision corresponding to the preset standard deviation according to the frequency ratio corresponding to each precision error and the preset frequency ratio corresponding to the preset standard deviation; and the target error precision corresponding to the preset standard deviation is used for indicating the road precision.

Optionally, the precision error is an absolute precision error, and the second processing module includes a third processing submodule and a fourth processing submodule.

And the third processing submodule is used for determining the corresponding difference value of each characteristic point pair according to the true value coordinate of the first characteristic point in each characteristic point pair and the map coordinate of the second characteristic point.

And the fourth processing submodule is used for determining the corresponding difference value of each characteristic point pair as the corresponding absolute precision error of each characteristic point pair.

Optionally, the precision error is a relative precision error, and the second processing module further includes a fifth processing submodule and a sixth processing submodule.

A fifth processing submodule, configured to determine, for each pair of feature points, a first distance between two first feature points according to a true value coordinate of a first feature point in the pair of feature points and a true value coordinate of a first feature point in a first other pair of feature points; determining a second distance between two second feature points according to the map coordinates of the second feature point in the feature point pair and the map coordinates of the second feature point in the first other feature point pair; wherein the first other characteristic point pair is a characteristic point pair other than the characteristic point pair among the plurality of characteristic point pairs.

And the sixth processing submodule is used for determining the difference value between the first distance and the second distance as the corresponding relative error precision of the characteristic point pair.

Optionally, the precision error is a longitudinal slope precision error, and the second processing module further includes a seventh processing submodule and an eighth processing submodule.

The seventh processing submodule is used for determining a first height difference and a first horizontal distance between two first characteristic points according to the true value coordinate of the first characteristic point in the characteristic point pair and the true value coordinate of the first characteristic point in a second other characteristic point pair aiming at each characteristic point pair; determining a second height difference and a second horizontal distance between two second feature points according to the map coordinates of the second feature point in the feature point pair and the map coordinates of the second feature point in a second other feature point pair; wherein the second other characteristic point pair is a characteristic point pair other than the characteristic point pair among the plurality of characteristic point pairs.

And the eighth processing submodule is used for determining the longitudinal slope precision error corresponding to the characteristic point pair according to the first height difference, the first horizontal distance, the second height difference and the second horizontal distance.

Optionally, the eighth processing sub-module is specifically configured to determine a first ratio between the first height difference and the first horizontal distance, and a second ratio between the second height difference and the second horizontal distance, respectively; and determining the difference between the first ratio and the second ratio as the longitudinal slope precision error corresponding to the characteristic point pair.

Optionally, the precision error is a curvature precision error, and the second processing module further includes a ninth processing sub-module, a tenth processing sub-module, an eleventh processing sub-module, and a twelfth processing sub-module.

And a ninth processing submodule, configured to determine, for each characteristic point pair, a preceding characteristic point pair and a succeeding characteristic point pair of the characteristic point pair from the plurality of characteristic point pairs according to respective positions of the plurality of characteristic point pairs.

And the tenth processing submodule is used for determining the first radius of a triangle circumscribed circle formed by the three first characteristic points according to the true value coordinate of the first characteristic point in the previous characteristic point pair, the true value coordinate of the first characteristic point in the characteristic point pair and the true value coordinate of the first characteristic point in the next characteristic point pair.

And the eleventh processing submodule is used for determining a second radius of a triangle circumscribed circle formed by the three second characteristic points according to the map coordinate of the second characteristic point in the previous characteristic point pair, the map coordinate of the second characteristic point in the characteristic point pair and the map coordinate of the second characteristic point in the next characteristic point pair.

And the twelfth processing submodule is used for determining the curvature precision error corresponding to the characteristic point pair according to the first radius and the second radius.

Optionally, the twelfth processing sub-module is specifically configured to determine a first curvature corresponding to the first radius and a second curvature corresponding to the second radius, respectively; and determining the difference value between the first curvature and the second curvature as the curvature precision error corresponding to the characteristic point pair.

Optionally, the accuracy error is a heading angle accuracy error, and the second processing module includes a thirteenth processing submodule and a fourteenth processing submodule.

The thirteenth processing submodule is used for determining a first tangent of the lane line by taking the true value coordinate of the first characteristic point in the characteristic point pair as a tangent point aiming at each characteristic point pair; and determining a second tangent of the lane line by taking the map coordinate of the second feature point in the feature point pair as a tangent point.

And the fourteenth processing submodule is used for determining the course angle precision error corresponding to the characteristic point pair according to the first tangent line and the second tangent line.

Optionally, the fourteenth processing sub-module is specifically configured to determine an included angle between the first tangent line and the second tangent line; and determining the included angle as the accuracy error of the corresponding course angle of the characteristic point pair.

The map road accuracy determining apparatus 120 provided in the embodiment of the present disclosure may implement the technical solution of the map road accuracy determining method shown in any one of the embodiments, and the implementation principle and the beneficial effect of the map road accuracy determining apparatus are similar to those of the map road accuracy determining method, and reference may be made to the implementation principle and the beneficial effect of the map road accuracy determining method, which are not described herein again.

The present disclosure also provides an electronic device, a readable storage medium, and a computer program product according to embodiments of the present disclosure.

According to an embodiment of the present disclosure, the present disclosure also provides a computer program product comprising: a computer program, stored in a readable storage medium, from which at least one processor of the electronic device can read the computer program, and the at least one processor executes the computer program to make the electronic device execute the solution of the method for determining map road precision provided by any one of the above embodiments.

Fig. 13 is a schematic block diagram of an electronic device 130 provided by an embodiment of the disclosure. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be examples only, and are not intended to limit implementations of the disclosure described and/or claimed herein.

As shown in fig. 13, the apparatus 130 includes a computing unit 1301 that can perform various appropriate actions and processes according to a computer program stored in a Read Only Memory (ROM) 1302 or a computer program loaded from a storage unit 1308 into a Random Access Memory (RAM) 1303. In the RAM 1303, various programs and data necessary for the operation of the device 130 can also be stored. The calculation unit 1301, the ROM 1302, and the RAM 1303 are connected to each other via a bus 1304. An input/output (I/O) interface 1305 is also connected to bus 1304.

A number of components in device 130 connect to I/O interface 1305, including: an input unit 1306 such as a keyboard, a mouse, or the like; an output unit 1307 such as various types of displays, speakers, and the like; storage unit 1308, such as a magnetic disk, optical disk, or the like; and a communication unit 1309 such as a network card, modem, wireless communication transceiver, etc. The communication unit 1309 allows the device 130 to exchange information/data with other devices through a computer network such as the internet and/or various telecommunication networks.

Computing unit 1301 may be a variety of general and/or special purpose processing components with processing and computing capabilities. Some examples of computing unit 1301 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various computing units running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, and so forth. The calculation unit 1301 executes the respective methods and processes described above, such as the determination method of the map road accuracy. For example, in some embodiments, the determination of map road accuracy may be implemented as a computer software program tangibly embodied on a machine-readable medium, such as storage unit 1308. In some embodiments, part or all of the computer program may be loaded and/or installed onto device 130 via ROM 1302 and/or communications unit 1309. When the computer program is loaded into the RAM 1303 and executed by the computing unit 1301, one or more steps of the determination method of map road accuracy described above may be performed. Alternatively, in other embodiments, the computing unit 1301 may be configured in any other suitable manner (e.g., by means of firmware) to perform the determination method of map road accuracy.

Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuitry, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), system on a chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs that are executable and/or interpretable on a programmable system including at least one programmable processor, which may be special or general purpose, receiving data and instructions from, and transmitting data and instructions to, a storage system, at least one input device, and at least one output device.

Program code for implementing the methods of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the program codes, when executed by the processor or controller, cause the functions/operations specified in the flowchart and/or block diagram to be performed. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine or entirely on the remote machine or server.

In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which a user may provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form, including acoustic, speech, or tactile input.

The systems and techniques described here can be implemented in a computing system that includes a back-end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back-end, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), and the Internet.

The computer system may include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The Server can be a cloud Server, also called a cloud computing Server or a cloud host, and is a host product in a cloud computing service system, so as to solve the defects of high management difficulty and weak service expansibility in the traditional physical host and VPS service ("Virtual Private Server", or simply "VPS"). The server may also be a server of a distributed system, or a server incorporating a blockchain.

It should be understood that various forms of the flows shown above may be used, with steps reordered, added, or deleted. For example, the steps described in the present disclosure may be executed in parallel, sequentially, or in different orders, as long as the desired results of the technical solutions disclosed in the present disclosure can be achieved, and the present disclosure is not limited herein.

The above detailed description should not be construed as limiting the scope of the disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may be made in accordance with design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present disclosure should be included in the scope of protection of the present disclosure.

Claims

1. A method for determining map road accuracy comprises the following steps:

acquiring true value road data and map road data corresponding to a road to be detected, wherein the road to be detected is a road segment between a group of same-name points, and the same-name points are points with the same true value road data and the same map road data;

determining a plurality of characteristic point pairs positioned on a lane line in the road to be detected from the truth value road data and the map road data corresponding to the road to be detected; each characteristic point pair comprises a first characteristic point determined in the truth value road data and a second characteristic point determined in the map road data, and the positions of the first characteristic points are matched with the positions of the second characteristic points one by one; the interval distance dotting rule used for determining the first characteristic points in the truth value road data is the same as the interval distance dotting rule used for determining the second characteristic points in the map road data;

acquiring a truth value coordinate of a first characteristic point in each characteristic point pair according to the truth value road data corresponding to each characteristic point pair, and acquiring a map coordinate of a second characteristic point in each characteristic point pair according to the map road data corresponding to each characteristic point pair;

determining the corresponding precision error of each characteristic point pair according to the true value coordinate of the first characteristic point in each characteristic point pair and the map coordinate of the second characteristic point;

determining the road precision according to the precision errors corresponding to the characteristic point pairs;

the determining the precision error corresponding to each feature point pair according to the true value coordinate of the first feature point and the map coordinate of the second feature point in each feature point pair includes:

for each feature point pair, determining a first height difference and a first horizontal distance between two first feature points according to the true value coordinate of the first feature point in the feature point pair and the true value coordinate of the first feature point in a second other feature point pair; determining a second height difference and a second horizontal distance between two second feature points according to the map coordinates of the second feature point in the feature point pair and the map coordinates of the second feature point in the second other feature point pair; wherein the second other characteristic point pair is a characteristic point pair other than the characteristic point pair among the plurality of characteristic point pairs;

determining a first ratio between the first height difference and the first horizontal distance and a second ratio between the second height difference and the second horizontal distance, respectively;

and determining the difference between the first ratio and the second ratio as the longitudinal slope precision error corresponding to the characteristic point pair.

2. The method of claim 1, wherein the determining the road precision from the precision error corresponding to the characteristic point pair comprises:

determining the initial frequency corresponding to each precision error according to the precision error corresponding to each characteristic point pair;

and determining the road precision according to the initial frequency corresponding to each precision error.

3. The method of claim 2, wherein said determining the road precision according to the initial frequency corresponding to each precision error comprises:

aiming at each precision error, determining an initial frequency corresponding to the precision error, and determining the sum of the initial frequency corresponding to each precision error smaller than the precision error as a target frequency corresponding to the precision error;

and determining the road precision according to the target frequency corresponding to each precision error.

4. The method of claim 3, wherein the determining the road precision according to the target frequency corresponding to each precision error comprises:

respectively determining the target frequency corresponding to each precision error and the ratio of the target frequency to the number of the characteristic point pairs, and obtaining the frequency ratio corresponding to each precision error according to the ratio;

determining target error precision corresponding to a preset standard deviation according to the frequency ratio corresponding to each precision error and a preset frequency ratio corresponding to a preset standard deviation; and the target error precision corresponding to the preset standard deviation is used for indicating the road precision.

5. The method according to any one of claims 1 to 4, wherein the accuracy error is an absolute accuracy error, and the determining the accuracy error corresponding to each feature point pair according to the true coordinates of the first feature point and the map coordinates of the second feature point in each feature point pair comprises:

determining the corresponding difference value of each characteristic point pair according to the true value coordinate of the first characteristic point in each characteristic point pair and the map coordinate of the second characteristic point;

and determining the difference value corresponding to each characteristic point pair as the absolute precision error corresponding to each characteristic point pair.

6. The method according to any one of claims 1 to 4, wherein the accuracy error is a relative accuracy error, and the determining the accuracy error corresponding to each feature point pair according to the true coordinates of the first feature point and the map coordinates of the second feature point in each feature point pair comprises:

for each feature point pair, determining a first distance between two first feature points according to the true value coordinate of the first feature point in the feature point pair and the true value coordinate of the first feature point in a first other feature point pair; determining a second distance between two second feature points according to the map coordinates of the second feature point in the feature point pair and the map coordinates of the second feature point in the first other feature point pair; wherein the first other characteristic point pair is a characteristic point pair other than the characteristic point pair among the plurality of characteristic point pairs;

and determining the difference between the first distance and the second distance as the corresponding relative error precision of the characteristic point pair.

7. The method according to any one of claims 1 to 4, wherein the accuracy error is a curvature accuracy error, and the determining the accuracy error corresponding to each feature point pair according to the true coordinates of the first feature point and the map coordinates of the second feature point in each feature point pair comprises:

for each pair of characteristic points, determining a preceding characteristic point pair and a succeeding characteristic point pair of the pair of characteristic points from the plurality of pairs of characteristic points according to respective positions of the plurality of pairs of characteristic points;

determining a first radius of a triangle circumscribed circle formed by the three first characteristic points according to the true value coordinate of the first characteristic point in the previous characteristic point pair, the true value coordinate of the first characteristic point in the characteristic point pair and the true value coordinate of the first characteristic point in the next characteristic point pair;

determining a second radius of a triangle circumscribed circle formed by the three second feature points according to the map coordinate of the second feature point in the previous feature point pair, the map coordinate of the second feature point in the feature point pair and the map coordinate of the second feature point in the next feature point pair;

and determining the curvature precision error corresponding to the characteristic point pair according to the first radius and the second radius.

8. The method of claim 7, wherein the determining the curvature accuracy error corresponding to the pair of feature points from the first radius and the second radius comprises:

respectively determining a first curvature corresponding to the first radius and a second curvature corresponding to the second radius;

and determining the difference between the first curvature and the second curvature as the curvature precision error corresponding to the characteristic point pair.

9. The method according to any one of claims 1 to 4, wherein the accuracy error is a heading angle accuracy error, and the determining the accuracy error corresponding to each feature point pair according to the coordinates of each feature point pair includes:

aiming at each characteristic point pair, determining a first tangent of a lane line by taking the true value coordinate of a first characteristic point in the characteristic point pair as a tangent point; determining a second tangent of the lane line by taking the map coordinate of a second feature point in the feature point pair as a tangent point;

and determining the course angle precision error corresponding to the characteristic point pair according to the first tangent and the second tangent.

10. The method of claim 9, wherein determining the heading angle accuracy error corresponding to the pair of feature points from the first tangent and the second tangent comprises:

determining an included angle between the first tangent and the second tangent;

and determining the included angle as the course angle precision error corresponding to the characteristic point pair.

11. A map road accuracy determining apparatus, comprising:

the device comprises an acquisition unit, a processing unit and a processing unit, wherein the acquisition unit is used for acquiring true value road data and map road data corresponding to a road to be detected, the road to be detected is a road segment between a group of same-name points, and the same-name points refer to points at which the true value road data and the map road data are the same;

the determining unit is used for determining a plurality of characteristic point pairs positioned on a lane line in the road to be detected from the true value road data and the map road data corresponding to the road to be detected; each feature point pair comprises a first feature point determined in the truth-value road data and a second feature point determined in the map road data, and the positions of the first feature points and the positions of the second feature points are matched one by one; the interval distance dotting rule used for determining the first characteristic points in the truth value road data is the same as the interval distance dotting rule used for determining the second characteristic points in the map road data;

the processing unit is used for determining the road precision of the road to be detected in the map road data according to the true value road data and the map road data corresponding to the plurality of characteristic point pairs;

the processing unit comprises a first processing module, a second processing module and a third processing module;

the first processing module is configured to obtain a true value coordinate of a first feature point in each feature point pair according to the true value road data corresponding to each feature point pair, and obtain a map coordinate of a second feature point in each feature point pair according to the map road data corresponding to each feature point pair;

the second processing module is configured to determine, according to the true value coordinate of the first feature point in each feature point pair and the map coordinate of the second feature point, a precision error corresponding to each feature point pair;

the third processing module is configured to determine the road precision according to the precision error corresponding to each feature point pair;

the precision error is a longitudinal slope precision error, and the second processing module further comprises a seventh processing submodule and an eighth processing submodule;

the seventh processing submodule is configured to determine, for each pair of feature points, a first height difference and a first horizontal distance between two first feature points according to a true-value coordinate of a first feature point in the pair of feature points and a true-value coordinate of a first feature point in a second other pair of feature points; determining a second height difference and a second horizontal distance between two second feature points according to the map coordinates of the second feature points in the feature point pair and the map coordinates of the second feature points in the second other feature point pair; wherein the second other characteristic point pair is a characteristic point pair other than the characteristic point pair among the plurality of characteristic point pairs;

the eighth processing submodule is configured to determine a longitudinal slope precision error corresponding to the feature point pair according to the first height difference, the first horizontal distance, the second height difference, and the second horizontal distance;

the eighth processing sub-module is specifically configured to determine a first ratio between the first height difference and the first horizontal distance, and a second ratio between the second height difference and the second horizontal distance, respectively; and determining the difference between the first ratio and the second ratio as the longitudinal slope precision error corresponding to the characteristic point pair.

12. The apparatus of claim 11, wherein the third processing module comprises a first processing sub-module and a second processing sub-module;

the first processing submodule is used for determining the initial frequency corresponding to each precision error according to the precision error corresponding to each characteristic point pair;

13. The apparatus of claim 12, wherein,

the second processing submodule is specifically configured to determine, for each precision error, an initial frequency corresponding to the precision error, a sum of the initial frequency corresponding to each precision error smaller than the precision error, and determine the sum as a target frequency corresponding to the precision error; and determining the road precision according to the target frequency corresponding to each precision error.

14. The apparatus of claim 13, wherein,

the second processing submodule is specifically configured to determine a ratio between the target frequency corresponding to each precision error and the number of the feature point pairs, and obtain a frequency ratio corresponding to each precision error according to the ratio; determining target error precision corresponding to a preset standard deviation according to the frequency ratio corresponding to each precision error and a preset frequency ratio corresponding to a preset standard deviation; and the target error precision corresponding to the preset standard deviation is used for indicating the road precision.

15. The apparatus of any one of claims 11-14, wherein the precision error is an absolute precision error, the second processing module comprising a third processing sub-module and a fourth processing sub-module;

the third processing submodule is used for determining corresponding difference values of the characteristic point pairs according to the true value coordinate of the first characteristic point in each characteristic point pair and the map coordinate of the second characteristic point;

and the fourth processing submodule is configured to determine the difference corresponding to each feature point pair as an absolute precision error corresponding to each feature point pair.

16. The apparatus of any one of claims 11-14, wherein the precision error is a relative precision error, the second processing module further comprising a fifth processing sub-module and a sixth processing sub-module;

the fifth processing submodule is configured to determine, for each pair of feature points, a first distance between two first feature points according to a true-value coordinate of a first feature point in the pair of feature points and a true-value coordinate of a first feature point in a first other pair of feature points; determining a second distance between two second feature points according to the map coordinates of the second feature point in the feature point pair and the map coordinates of the second feature point in the first other feature point pair; wherein the first other characteristic point pair is a characteristic point pair other than the characteristic point pair among the plurality of characteristic point pairs;

and the sixth processing submodule is configured to determine a difference between the first distance and the second distance as a relative error precision corresponding to the feature point pair.

17. The apparatus of any one of claims 11-14, wherein the precision error is a curvature precision error, the second processing module further comprising a ninth processing sub-module, a tenth processing sub-module, an eleventh processing sub-module, and a twelfth processing sub-module;

the ninth processing sub-module is configured to determine, for each of the characteristic point pairs, a preceding characteristic point pair and a succeeding characteristic point pair of the characteristic point pair from among the plurality of characteristic point pairs according to respective positions of the plurality of characteristic point pairs;

the tenth processing submodule is configured to determine a first radius of a triangle circumscribed circle formed by the three first feature points according to the true value coordinate of the first feature point in the previous feature point pair, the true value coordinate of the first feature point in the feature point pair, and the true value coordinate of the first feature point in the next feature point pair;

the eleventh processing submodule is configured to determine a second radius of a triangle circumscribed circle formed by the three second feature points according to the map coordinate of the second feature point in the previous feature point pair, the map coordinate of the second feature point in the feature point pair, and the map coordinate of the second feature point in the next feature point pair;

18. The apparatus of claim 17, wherein,

the twelfth processing submodule is specifically configured to determine a first curvature corresponding to the first radius and a second curvature corresponding to the second radius, respectively; and determining the difference between the first curvature and the second curvature as the curvature precision error corresponding to the characteristic point pair.

19. The apparatus of any one of claims 11-14, wherein the accuracy error is a heading angle accuracy error, the second processing module comprising a thirteenth processing sub-module and a fourteenth processing sub-module;

the thirteenth processing submodule is configured to determine, for each feature point pair, a first tangent line of the lane line by using the true value coordinate of the first feature point in the feature point pair as a tangent point; determining a second tangent of the lane line by taking the map coordinate of a second feature point in the feature point pair as a tangent point;

and the fourteenth processing submodule is used for determining the course angle precision error corresponding to the characteristic point pair according to the first tangent and the second tangent.

20. The apparatus of claim 19, wherein,

the fourteenth processing submodule is specifically configured to determine an included angle between the first tangent and the second tangent; and determining the included angle as the course angle precision error corresponding to the characteristic point pair.

21. An electronic device, comprising:

at least one processor; and

the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of determining map road accuracy of any one of claims 1-10.

22. A non-transitory computer-readable storage medium storing computer instructions for causing a computer to execute the method for determining map road accuracy according to any one of claims 1 to 10.

23. A computer program product comprising a computer program which, when executed by a processor, carries out the steps of the map road accuracy determination method of any one of claims 1 to 10.