CN114625828A

CN114625828A - Lane-level data matching method and device, electronic equipment and storage medium

Info

Publication number: CN114625828A
Application number: CN202210350275.2A
Authority: CN
Inventors: 肖宁; 闫伟; 储超
Original assignee: Tencent Technology Shenzhen Co Ltd
Current assignee: Tencent Technology Shenzhen Co Ltd
Priority date: 2022-04-02
Filing date: 2022-04-02
Publication date: 2022-06-14

Abstract

The embodiment of the invention discloses a lane-level data matching method, a lane-level data matching device, electronic equipment and a storage medium; the embodiment of the invention can be applied to scenes such as intelligent traffic, Internet of vehicles and the like, can obtain the vehicle position of a target vehicle, determine the high-precision data of a local lane corresponding to at least one lane of a road where the vehicle position is located, thin the figure points in the high-precision data of the local lane based on the position relation between the figure points to obtain lane-level thinning data corresponding to each lane, predict the positioning area of the target vehicle in each lane based on the thinned figure points of each lane according to the position of the thinned figure points and the vehicle position, determine the distance from the vehicle position to a figure point line segment formed by two adjacent figure points in the positioning area, and determine the matching result of the target vehicle in the high-precision data of the local lane based on the distance; the method can keep the vehicle positioning precision, reduce the calculation cost, improve the vehicle positioning efficiency and realize the quick matching of the vehicle position and the lane high-precision data.

Description

Lane-level data matching method and device, electronic equipment and storage medium

Technical Field

The invention relates to the technical field of map navigation, in particular to a lane-level data matching method and device, electronic equipment and a storage medium.

Background

With the rapid development of information acquisition technology, data currently used in the map navigation field is being converted from traditional common road data into high-precision road data with more accurate and rich information.

Because the shape points of the high-precision data are dense, and the road is provided with a plurality of lanes, the shape point processing mode in the traditional common road data is adopted to process the high-precision data, the requirement on the calculation performance of equipment is high, a large amount of calculation resources are occupied, and the vehicle positioning efficiency is low.

Disclosure of Invention

The embodiment of the invention provides a lane-level data matching method, a lane-level data matching device, electronic equipment and a storage medium, which can keep the vehicle positioning precision, reduce the calculation overhead, improve the vehicle positioning efficiency and realize the rapid matching of the vehicle position and lane high-precision data.

The embodiment of the invention provides a lane-level data matching method, which comprises the following steps:

acquiring a vehicle position of a target vehicle;

determining local lane high-precision data corresponding to at least one lane of a road where the vehicle is located, wherein one piece of local lane high-precision data comprises at least two shape points of one lane, and the shape points are used for indicating the trend of the lane;

based on the position relation among the shape points, thinning the shape points in the local lane high-precision data to obtain lane-level thinning data corresponding to each lane, wherein the curve formed by the shape points in the lane-level thinning data is matched with the curve formed by the starting points in the local lane high-precision data in trend;

predicting a positioning area of the target vehicle in each lane based on the shape-drawing points of each lane according to the position of the shape-drawing points and the position of the vehicle;

and determining the distance from the vehicle position to a shape point line segment formed by two adjacent shape points in the positioning area, and determining the matching result of the target vehicle in the local lane high-precision data based on the distance.

Optionally, an embodiment of the present invention provides a lane-level data matching apparatus, including:

a position acquisition unit for acquiring a vehicle position of a target vehicle;

the data determining unit is used for determining local lane high-precision data corresponding to at least one lane of a road where the vehicle is located, wherein one local lane high-precision data comprises at least two shape points of one lane, and the shape points are used for indicating the trend of the lane;

the data thinning unit is used for thinning the shape points in the local lane high-precision data based on the position relation among the shape points to obtain lane-level thinning data corresponding to each lane, and the curve formed by the shape points in the lane-level thinning data is matched with the curve formed by the starting points in the local lane high-precision data in trend;

the region prediction unit is used for predicting a positioning region of the target vehicle in each lane based on the shape-drawing points of each lane according to the positions of the shape-drawing points and the vehicle position;

and the result determining unit is used for determining the distance from the vehicle position to a shape point line segment formed by two adjacent shape points in the positioning area, and determining the matching result of the target vehicle in the local lane high-precision data based on the distance.

Optionally, the shape points include end shape points and intermediate shape points located between the end shape points, and the data thinning unit is configured to determine a thinned back shape point for keeping the lane direction in the intermediate shape points based on a position relationship between the intermediate shape points and the end shape points at both ends;

and determining the post-thinning points for keeping the lane trend in the adjacent end point points based on the position relationship between the intermediate form points between the adjacent end point points and the adjacent end point points by taking the post-thinning points as new end point form points to obtain lane-level thinning data consisting of the post-thinning points.

Optionally, the data thinning unit is configured to determine, based on the shape point positions of the shape points, a maximum distance between a straight line formed by the middle shape point and the two end shape points;

if the maximum distance is larger than a preset distance threshold value, taking the middle shape point corresponding to the maximum distance as a shape point after the thinning;

taking the shape point after thinning as a new end shape point, and dividing a curve formed by the shape points into two sub-curves;

determining the maximum distance between the middle shape point on the sub-curve and the end shape point of the sub-curve;

if the maximum distance is larger than a preset distance threshold value, taking the middle shape point corresponding to the maximum distance as a new shape point after thinning;

and taking the new post-thinning point as a new end point, dividing the sub-curve where the new post-thinning point is located into two new sub-curves, executing the step of determining the maximum distance between the middle point on the sub-curve and the end point of the sub-curve until no new post-thinning point exists on the sub-curve, and obtaining lane-level thinning data formed by the post-thinning points.

Optionally, the area prediction unit is configured to determine a first reference shape point in the thinned shaping points according to a first shape point and a second shape point in the thinned shaping points when the number of the thinned shaping points is greater than a preset number of area shape points;

determining a second reference shape point in the shape point after the suction and the thin according to the first reference shape point and the second shape point;

calculating a first distance between the target vehicle and the first reference shape point and a second distance between the target vehicle and the second reference shape point based on the vehicle position, the shape point position of the first reference shape point and the shape point position of the second reference shape point;

if the first distance is smaller than the second distance, taking the second reference shape point as a new second shape point;

and if the number of the thinned shape points between the first shape point and the new second shape point is not more than the number of the area shape points, taking the first shape point, the new second shape point and the thinned shape point between the first shape point and the new second shape point as positioning areas.

Optionally, the result determining unit is configured to determine, according to the vehicle position and the shape point positions of any two adjacent shape points in the positioning region of each lane, positions of candidate positioning points of the target vehicle on the lanes;

calculating the line segment distance between the vehicle position and the position of each candidate positioning point, and taking the line segment distance as the distance from the vehicle position to a shape point line segment formed by two adjacent shape points in the positioning area;

determining a target positioning point of the target vehicle from the candidate positioning points based on the distance;

and taking the two adjacent shape points corresponding to the target positioning point as a matching result of the target vehicle in the local lane high-precision data.

Optionally, the result determining unit is configured to calculate, according to the vehicle position and shape point positions of any two adjacent shape points in the positioning area of each lane, a position relationship indicating parameter between a candidate positioning point of the target vehicle on each lane and a shape point line segment formed by the two shape points;

and when the position relation indicating parameter is within a preset parameter range, calculating the position of the candidate positioning point of the target vehicle on each lane according to the shape point positions of the two shape points and the position relation indicating parameter.

Optionally, the lane-level data matching device provided in the embodiment of the present invention further includes a driving weight calculation unit, configured to obtain vehicle speed data and vehicle heading data of the target vehicle;

calculating a running weight parameter of the target vehicle based on the vehicle speed data, the vehicle course data and a preset weight mapping relation;

the result determination unit is used for determining a distance weight parameter of the target vehicle based on the distance;

calculating a positioning parameter between the target vehicle and the candidate positioning point according to the distance weight parameter and the driving weight parameter;

determining a target localization point of the target vehicle from the candidate localization points based on the localization parameters.

Optionally, the weight mapping relationship includes a speed weight mapping relationship and an angle weight mapping relationship, and the driving weight calculating unit is configured to calculate a speed weight parameter of the target vehicle based on the vehicle speed data and the speed weight mapping relationship;

determining the running angle of the target vehicle according to a preset angle coordinate system and the vehicle heading data;

determining the line segment angle of each shape point line segment according to the angle coordinate system and the shape point line segment formed by two adjacent shape points in each positioning area;

calculating an angle weight parameter of the target vehicle based on the driving angle, the line segment angle and the angle weight mapping relation;

and calculating a running weight parameter of the target vehicle based on the speed weight parameter and the angle weight parameter.

Optionally, the lane-level data matching device provided in the embodiment of the present invention further includes a driving planning unit, configured to determine, according to a matching result of the target vehicle in the local lane high-precision data, a target lane corresponding to the target vehicle;

acquiring lane observation data of each lane in a road where the vehicle is located;

and generating a lane-level driving plan of the target vehicle according to the lane observation data of the target lane and the lane observation data of other lanes.

Optionally, the lane-level data matching device provided in the embodiment of the present invention further includes a driving data obtaining unit, configured to obtain vehicle speed data and vehicle heading data of the target vehicle;

the result determining unit is used for calculating the estimated positioning position of the target vehicle according to the vehicle position, the vehicle speed data and the vehicle course data;

and determining the distance from the pre-estimated positioning position to a shape point line segment formed by two adjacent shape points in the positioning area.

Optionally, the lane-level data matching device provided in the embodiment of the present invention further includes a second data thinning unit, configured to obtain lane flow data of each lane on a road where the vehicle is located;

determining a new preset distance threshold corresponding to the original lane level data according to the lane flow data of each lane;

and executing the step of determining the maximum distance between the straight line formed by the middle point and the two end point points based on the shape point positions of the shape points based on the new preset distance threshold.

Correspondingly, the embodiment of the invention also provides the electronic equipment, which comprises a memory and a processor; the memory stores an application program, and the processor is used for running the application program in the memory to execute any step of the lane-level data matching method provided by the embodiment of the invention.

Accordingly, the embodiment of the present invention further provides a computer-readable storage medium, where a plurality of instructions are stored, and the instructions are suitable for being loaded by a processor to perform any of the steps in the lane-level data matching method provided by the embodiment of the present invention.

Furthermore, the embodiment of the present invention further provides a computer program product, which includes a computer program or instructions, and the computer program or instructions, when executed by a processor, implement the steps in any lane-level data matching method provided by the embodiment of the present invention.

By adopting the scheme of the embodiment of the invention, the vehicle position of a target vehicle can be obtained, the local lane high-precision data corresponding to at least one lane of a road where the vehicle position is located is determined, one local lane high-precision data comprises at least two shape points of one lane, the shape points are used for indicating the direction of the lane, the shape points in the local lane high-precision data are thinned based on the position relation among the shape points to obtain lane-level thinned data corresponding to each lane, the curve formed by the shape points in the lane-level thinned data is matched with the curve formed by the starting points in the local lane high-precision data, the positioning area of the target vehicle in each lane is predicted based on the thinned shape points of each lane according to the position of the thinned shape points and the vehicle position, the distance from the vehicle position to the shape point line segment formed by two adjacent shape points in the positioning area is determined, determining a matching result of the target vehicle in the local lane high-precision data based on the distance; according to the embodiment of the invention, the high-precision local lane high-precision data is thinned to obtain the thinned shape points, and the positioning area of the target vehicle in each lane is predicted on the basis of the thinned shape points, so that when lane-level positioning is carried out, the lane and/or shape points matched with the target vehicle in the local lane high-precision data can be determined according to the thinned shape points in the positioning area, the vehicle positioning precision can be maintained, the calculation cost is reduced, the vehicle positioning efficiency is improved, and the rapid matching of the vehicle position and the lane high-precision data is realized.

Drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.

Fig. 1 is a scene schematic diagram of a lane-level data matching method according to an embodiment of the present invention;

FIG. 2 is a flow chart of a lane-level data matching method provided by an embodiment of the invention;

FIG. 3 is a schematic diagram of a thinning process provided by an embodiment of the present invention;

fig. 4 is a schematic diagram of a positioning area determining process provided in an embodiment of the present invention;

FIG. 5 is a schematic diagram of a relationship between vehicle coordinates and shape point line segments provided by an embodiment of the present invention;

FIG. 6 is a schematic diagram of a projection calculation process provided by an embodiment of the invention;

FIG. 7 is a schematic view of a target vehicle angle relationship provided by an embodiment of the present invention;

FIG. 8 is another flow chart of a lane-level data matching method according to an embodiment of the present invention;

FIG. 9 is a schematic diagram of a lane-level data matching system provided by an embodiment of the invention;

fig. 10 is a schematic structural diagram of a lane-level data matching apparatus provided in an embodiment of the present invention;

fig. 11 is another schematic structural diagram of the lane-level data matching apparatus according to the embodiment of the present invention;

fig. 12 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.

Detailed Description

The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be obtained by a person skilled in the art without inventive step based on the embodiments of the present invention, are within the scope of protection of the present invention.

The embodiment of the invention provides a lane-level data matching method and device, electronic equipment and a computer-readable storage medium. In particular, embodiments of the present invention provide a lane-level data matching method suitable for a lane-level data matching apparatus, which may be integrated in an electronic device.

The electronic device may be a terminal or other devices, including but not limited to a mobile terminal and a fixed terminal, for example, the mobile terminal includes but is not limited to a smart phone, a smart watch, a tablet computer, a notebook computer, a vehicle-mounted terminal, a smart vehicle, and the like, wherein the fixed terminal includes but is not limited to a desktop computer, a smart television, and the like.

The electronic device may also be a server or other devices, where the server may be an independent physical server, a server cluster or a distributed system formed by multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud service, a cloud database, cloud computing, a cloud function, cloud storage, Network service, cloud communication, middleware service, domain name service, security service, CDN (Content Delivery Network), and a big data and artificial intelligence platform, but is not limited thereto.

The lane-level data matching method can be realized by the terminal, and can also be realized by the terminal and the server together.

The following describes the method by taking an example in which the terminal and the server implement the lane-level data matching method together.

As shown in fig. 1, the lane-level data matching system provided by the embodiment of the present invention includes a terminal 10, a server 20, and the like; the terminal 10 and the server 20 are connected via a network, such as a wired or wireless network connection.

Among them, the terminal 10 may exist as a terminal that transmits the vehicle position of the target vehicle to the server 20.

The server 20 may be configured to obtain a vehicle position of a target vehicle, and determine local lane high-precision data corresponding to at least one lane of a road where the vehicle position is located, where one local lane high-precision data includes at least two shape points of one lane, and the shape points are used to indicate a direction of the lane; and (3) thinning the shape points in the local lane high-precision data based on the position relation between the shape points to obtain lane-level thinning data corresponding to each lane, wherein the curve formed by the shape points in the lane-level thinning data is matched with the curve formed by the starting points in the local lane high-precision data in trend.

The server 20 can predict a positioning area of the target vehicle in each lane based on the thinned-out points of each lane according to the positions of the thinned-out points and the vehicle position, determine the distance from the vehicle position to a point line segment formed by two adjacent points in the positioning area, and determine the matching result of the target vehicle in the local lane high-precision data based on the distance.

It is to be understood that the step of matching the lane-level data performed by the server 20 may also be performed by the terminal 10, which is not limited by the embodiment of the present invention.

The following are detailed descriptions. It should be noted that the following description of the embodiments is not intended to limit the preferred order of the embodiments.

Embodiments of the present invention will be described in terms of a lane-level data matching device, which may be specifically integrated in a server or a terminal.

As shown in fig. 2, a specific flow of the lane-level data matching method of the present embodiment may be as follows:

201. the vehicle position of the target vehicle is acquired.

The target vehicle may be an intelligent vehicle that needs to be located, or the target vehicle may be a vehicle where a terminal capable of being located is located.

For example, the target vehicle may be an unmanned vehicle, or the target vehicle may be a vehicle equipped with an in-vehicle navigation terminal, or the like.

In an embodiment of the present invention, the vehicle position may be expressed in latitude and longitude, for example, the vehicle position may be 22 degrees 32 minutes north latitude and 114 degrees 3 minutes east longitude.

Alternatively, each geographic area may be divided into n sub-areas, each sub-area has a landmark position (e.g., the position of a landmark building or the position of the center point of the area), and when the vehicle position is represented, the sub-area where the target vehicle is located and the relative coordinates between the target vehicle and the landmark position may be used for representation.

For example, the vehicle location may be (3, 114, -22), indicating that the target vehicle is located in the 3 rd sub-zone, 114 meters east, 22 meters north, etc. in the landmark location.

It is understood that after the lane-level positioning of the target vehicle is achieved, the driving of the target vehicle may be planned according to the lane in which the target vehicle is located. In some optional embodiments, the lane-level data matching method provided in the embodiments of the present invention may further include:

determining a target lane corresponding to the target vehicle according to a matching result of the target vehicle in the local lane high-precision data;

And the target lane is the determined lane where the target vehicle is located. The lane observation data may include, but is not limited to, traffic data and/or lane width data for each lane, and the like.

For example, in the embodiment of the present invention, it may be planned whether the target vehicle can perform operations such as lane change or the like according to the traffic data of the target lane and the traffic data of other lanes.

202. And determining local lane high-precision data corresponding to at least one lane of a road where the vehicle is located, wherein one piece of local lane high-precision data comprises at least two shape points of one lane, and the shape points are used for indicating the trend of the lane.

The road on which the vehicle is located generally includes at least one lane. For example, a road may include two lanes in both directions, or a road may include a straight lane, a left-turn lane, a right-turn lane, etc.

Specifically, when determining the local lane high-accuracy data, lane high-accuracy data of a local range corresponding to the vehicle position may be determined as the local lane high-accuracy data from among lane high-accuracy data stored in advance according to the vehicle position. For example, the vehicle position is 22 degrees north latitude 32 minutes and 114 degrees east longitude 3 minutes, and the acquired high-precision data of the local lane of the vehicle can be lane high-precision data in the range from 22 degrees north latitude 30 to 22 degrees north latitude 34 minutes, and 114 degrees east longitude 1 to 114 degrees east longitude 5 minutes.

Alternatively, the high-accuracy data of the local lane in the local range corresponding to the vehicle position may be determined based on the road position corresponding to the vehicle position.

The lane High-precision data may be High-precision road (HD) data, or may be data that is richer than general road data (SD) data information and does not meet the High-precision road data Standard.

For example, the high-precision road data may include road lane line equations/shape point coordinates, lane type, lane speed limits, lane marking type, pole coordinates, guidepost position, camera/traffic light position, and the like. The lane high-precision data may be high-precision road data, or may be data only retaining part of information in the high-precision road data, for example, the lane high-precision data may only include lane line equations/shape point coordinates, lane types, lane speed limits, lane marking types, lane topology information, and the like.

203. And (3) thinning the shape points in the local lane high-precision data based on the position relation between the shape points to obtain lane-level thinning data corresponding to each lane, wherein the curve formed by the shape points in the lane-level thinning data is matched with the curve formed by the starting points in the local lane high-precision data in trend.

The thinning means that the number of data points is reduced under the condition that the curve shape or the broken line shape is unchanged as much as possible when data are processed.

Specifically, when thinning the shape points, a step-size compression algorithm can be adopted, that is, one point is extracted at a certain step-size interval along a continuous curve, the rest points are all compressed, and then the adjacent extracted points are approximated by linear continuity or curve fitting. Alternatively, a line segment filtering algorithm may be used, that is, when the length of a line segment is smaller than a preset filtering value, the midpoint of the line segment is used to replace the segment.

Or, in the embodiment of the present invention, the high-precision data of the local lane may be thinned according to the position relationship between the various points. The method includes the steps of extracting shape points in the high-precision data of the local lane based on the position relationship between the shape points to obtain lane-level extraction data corresponding to each lane, wherein the shape points may include end shape points and intermediate shape points located between the end shape points, and the method specifically includes the following steps:

determining a thinning-out figure point used for reserving the lane trend in the middle figure point based on the position relation between the middle figure point and the end figure points at the two ends;

and determining the post-thinning points for keeping the lane trend in the intermediate points between the adjacent end point points based on the position relationship between the intermediate points between the adjacent end point points and the adjacent end point points to obtain lane-level thinning data consisting of the post-thinning points.

The end point is a shape point located at the starting position and the ending position of a certain part of the lane among shape points used for the trend of the lane.

And the middle shape point is the shape point except the end shape point in the local lane high-precision data.

In some examples, when determining the post-thinning point for keeping the lane direction, the slope of a straight line formed by the intermediate point and the end-thinning points at the two ends may be calculated based on the positional relationship between the intermediate point and the end-thinning points at the two ends, and the intermediate point having an absolute value of the slope greater than a preset threshold may be selected as the post-thinning point.

In other examples, the step of determining a post-thinning point for keeping the lane direction in the middle shape point based on the position relationship between the middle shape point and the end shape points at the two ends may specifically include:

determining the maximum distance between straight lines formed by the middle shape point and the shape points of the two end points based on the shape point positions of the shape points;

and if the maximum distance is greater than the preset distance threshold value, taking the middle shape point corresponding to the maximum distance as the shape point after the thinning.

The preset distance threshold may be defined according to actual requirements, for example, 1m, 0.8m, 0.5m, and the like.

For example, as shown in (1) in fig. 3, points 1 and 5 are end-shaped points, and points 2, 3, and 4 are intermediate-shaped points. The maximum distance between the straight lines formed by the points 1 and 5 is determined from the

points

2, 3 and 4, for example, the distance corresponding to the point 2 is 0.1, the distance corresponding to the point 3 is 0.7, and the distance corresponding to the point 4 is 0.5. And if the distance corresponding to the point 3 is greater than the preset distance threshold value 0.5, taking the point 3 as a post-form point of the rarefaction.

In order to improve the matching degree between the curve formed by the shape points in the lane-level thinning data and the curve formed by the starting points in the local lane high-precision data, the step "taking the thinned points as new end point shape points, determining the thinned points for keeping the lane direction in the adjacent end point shape points based on the position relationship between the intermediate shape points between the adjacent end point shape points and the adjacent end point shape points, and obtaining the lane-level thinning data formed by the thinned points" may specifically include:

and taking the new post-thinning points as new end point points, dividing the sub-curve where the new post-thinning points are located into two sections of new sub-curves, executing the step of determining the maximum distance from the middle points on the sub-curves to the end point points of the sub-curves until the new post-thinning points do not exist on the sub-curves, and obtaining lane-level thinning data formed by the post-thinning points.

At this time, as shown in (2) of fig. 3, the curve is divided into a sub-curve composed of

points

1, 2, and 3 with point 3 as a new end point, and a sub-curve composed of points 3, 4, and 5, point 5 is a point 4 as an intermediate point between the end point and the new end point (point 3), and the maximum distance between the straight line composed of point 4 and points 3 and 5 is calculated to be 0.6 and greater than a preset distance threshold, and point 4 may be set as a post-thinning point.

And if the point 1 is taken as the middle point of the end point shape point and the new end point shape point (point 3) as the point 2, the maximum distance between the straight line formed by the point 2 and the

points

1 and 3 is calculated to be 0.2 and is smaller than a preset distance threshold, the point 2 cannot be taken as the post-thinning shape point.

It can be understood that, because there may be data corresponding to a plurality of lanes in the local lane high-precision data, lane-level data corresponding to each lane may be processed separately in a synchronous or asynchronous manner, which is not limited in the embodiment of the present invention.

In the practical application process, the preset distance threshold value in the rarefaction process can be adjusted according to factors such as vehicle density and the like. In some optional embodiments, the lane-level data matching method provided in the embodiments of the present invention may further include:

acquiring lane flow data of each lane in a road where the vehicle is located;

and based on the new preset distance threshold, executing the step of determining the maximum distance between the straight line formed by the middle point and the two end point points based on the shape point positions of the shape points.

The lane flow data is data describing the flow of vehicles in the lane. For example, the lane traffic data may be 30 vehicles/minute, or 2 vehicles/second, etc. Specifically, the lane flow data may be obtained by a traffic flow observation device provided on or beside the road, or the lane flow data may be obtained based on the positioning information of each vehicle, and so on.

Specifically, when determining the new preset distance threshold, the determination may be performed according to a mapping relationship between preset lane flow data and the preset distance threshold, and lane flow data of each lane.

For example, before determining the new preset distance threshold, three different candidate distance thresholds may be preset, including a first candidate distance threshold, a second candidate distance threshold, and a third candidate distance threshold, where the first candidate distance threshold > the second candidate distance threshold > the third candidate distance threshold. In practical applications, the preset distance threshold may be defaulted as the second candidate distance threshold. The preset distance threshold may be modified to a first candidate distance threshold when the lane flow is greater than a first traffic flow threshold, and the preset distance threshold may be modified to a third candidate distance threshold when the lane flow is less than a second traffic flow threshold.

For another example, a continuous function relationship between the lane traffic data and the preset distance threshold may be established through the data model, and a new preset distance threshold corresponding to the original lane level data of each lane may be determined according to the lane traffic data and the continuous function relationship of each lane.

204. And predicting a positioning area of the target vehicle in each lane based on the drawn back point of each lane according to the position of the drawn back point and the position of the vehicle.

The positions of the geometric points after the thinning can be represented by longitude and latitude, each geographic area can be divided into n sub-areas, each sub-area is provided with a mark position, the sub-areas where the geometric points after the thinning are located and the relative coordinates between the geometric points after the thinning and the mark positions are used for representation, and the like.

Specifically, the description of the position of the rarefaction point may be the same as or different from the description of the vehicle position. For example, the thinned-out points and the vehicle position may be expressed in terms of latitude and longitude, or the thinned-out points may be expressed in terms of latitude and longitude, the vehicle position may be expressed based on relative coordinates with respect to the locations of the markers in the sub-area, and so on. If the two are described differently, a conversion may be made, for example, the vehicle position, expressed based on relative coordinates with respect to the locations of the markers in the sub-area, may be converted to latitude and longitude, and so on.

In the embodiment of the invention, the calculation amount can be further reduced by carrying out region screening on the thinning postformable point.

Specifically, when the positioning region is determined, the thinned shape points may be divided into N sub-regions, the distances between the shape points located in the middle sequence in each sub-region and the vehicle position are calculated, and the sub-region corresponding to the minimum distance and one or two adjacent sub-regions are used as the positioning region.

Alternatively, when determining the positioning area, step 203 may specifically include:

when the number of the shape points after the thinning is larger than the number of the preset area shape points, determining a first reference shape point in the shape points after the thinning according to a first shape point and a second shape point in the shape points after the thinning;

determining a second reference shape point in the shape points after the rarefaction according to the first reference shape point and the second shape point;

and if the number of the thinned shape points between the first shape point and the new second shape point is not more than the number of the area shape points, taking the first shape point, the new second shape point and the thinned shape points between the first shape point and the new second shape point as positioning areas.

The number of the area points can be a customized value, such as 80 points, 100 points and 200 points.

Specifically, when the first reference shape point is determined, an intermediate position of the first shape point and the second shape point may be calculated according to the positions of the first shape point and the second shape point, and a shape point closest to the intermediate position may be used as the first reference shape point.

Or, the shape points may be numbered according to the position relationship of the shape points in the positioning region, the first shape point may be the shape point corresponding to the first number, the second shape point may be the shape point corresponding to the last number, and the shape point corresponding to the middle value of the number is taken as the first reference shape point.

For example, as shown in fig. 4, assuming that the shape points after the current lane is sparse are P1, P2, …, PN, if N ═ the number of shape points in the region, then no calculation is needed, and the search interval is returned directly to [1, N ]. If N > the number of region shape points, P1 is taken as the first shape point and PN is taken as the second shape point.

Then, the first reference shape point may be PM, M ═ L + N)/2, and the second reference shape point may be PS, S ═ M + N)/2. And calculating the distances between the vehicle position and the PM and the PN to respectively obtain a first distance and a second distance.

And if the first distance is smaller than the second distance and N-S < (equal to the number of the area shape points), taking the PS-PN as a positioning area.

In some examples, when the first distance is smaller than the second distance, if the number of the thinned points between the first shape point and the new second shape point is greater than the number of the area shape points, the step of determining the first reference shape point of the thinned points according to the first shape point and the second shape point of the thinned points is performed by taking the first shape point, the new second shape point, and the shape point between the first shape point and the new second shape point as the new thinned points.

For example, if the distances between the vehicle position and the PM and the PN are calculated, a first distance and a second distance are obtained respectively; and if the first distance is smaller than the second distance and the number of the N-S region shape points is larger than the second distance, taking the PS-PN as a new thinning back shape point, and re-determining the first reference shape point and the second reference shape point from the PS-PN.

In other examples, when the first distance is not less than the second distance, the first reference centroid point is considered as a new first centroid point;

and if the number of the thinned shape points between the new first shape point and the new second shape point is not more than the number of the area shape points, taking the new first shape point, the new second shape point and the thinned shape point between the new first shape point and the new second shape point as the positioning areas.

For example, if the distances between the vehicle position and the PM and the PN are calculated, a first distance and a second distance are obtained respectively; and taking the PM-PN as a positioning area if the first distance is not less than the second distance and M-S < (equal to the number of area shape points).

In other examples, when the first distance is not less than the second distance, if the number of the thinned points between the new first shape point and the new second shape point is greater than the number of the area shape points, the new first shape point, the new second shape point, and the thinned points between the new first shape point and the new second shape point are used as the new thinned points, and the step of determining the first reference shape point in the thinned points according to the first shape point and the second shape point in the thinned points is performed.

For example, if the distances between the vehicle position and the PM and the PN are calculated, a first distance and a second distance are obtained respectively; and if the first distance is not less than the second distance and the number of M-S > region shape points is greater than the second distance, taking the PM-PN as a new thinning back shape point, and re-determining the first reference shape point and the second reference shape point from the PM-PN.

205. And determining the distance from the vehicle position to a shape point line segment formed by two adjacent shape points in the positioning area, and determining the matching result of the target vehicle in the local lane high-precision data based on the distance.

It can be understood that there are at least two shape points in the positioning area, and when calculating the distance, the distance from the vehicle position to each shape point line segment may be calculated sequentially, or the distance from the vehicle position to each shape point line segment may be calculated simultaneously.

Specifically, when the distance is calculated, a projection point corresponding to the vehicle position may be determined on the shape point line segment of each lane, and then the distance between the vehicle position and the projection point of each lane may be calculated to obtain the distance from the vehicle position to the shape point line segment, thereby determining the lane positioning point. That is, step 204 may include:

determining the position of a candidate positioning point of a target vehicle on each lane according to the position of the vehicle and the shape point positions of any two adjacent shape points in the positioning area of each lane;

And the candidate positioning points are projection points of the vehicle on each lane. Specifically, with the coordinates P of the current position of the vehicle and the positioning area of the lane i, P may be projected onto a line segment formed by two adjacent points in the positioning area, respectively, and it is determined whether the projected point of P falls within the line segment formed by two shape points, so as to find the optimal orthographic projection position, i.e., the candidate positioning point.

The target positioning point may be regarded as the determined actual position of the target vehicle, or may be regarded as a corresponding position in the lane determined by the local lane high-precision data.

In other examples, lane high-accuracy data of the lane corresponding to the target locating point may also be used as a matching result of the target vehicle in the local lane high-accuracy data. And taking the corresponding lane of the target positioning point in the local lane high-precision data as a matching result of the target vehicle in the local lane high-precision data.

In some optional embodiments, the step "determining the position of the candidate positioning point of the target vehicle on each lane according to the vehicle position and the shape point positions of any two adjacent shape points in the positioning region of each lane" may specifically include:

calculating a position relation indicating parameter between a candidate positioning point of the target vehicle on each lane and a shape point line segment formed by two shape points according to the position of the vehicle and the shape point positions of any two adjacent shape points in the positioning area of each lane;

and when the position relation indicating parameter is within the preset parameter range, calculating the position of the candidate positioning point of the target vehicle on each lane according to the shape point positions of the two shape points and the position relation indicating parameter.

The position relation indicating parameter is used for indicating the position relation between the candidate positioning point and a shape point line segment formed by two shape points.

Specifically, as shown in fig. 5, there may be three kinds of position relationships between the candidate localization point and the shape point line segment formed by two shape points. The position relation indication parameter can be calculated by the following formula:

where P denotes the vehicle positioning coordinates, A, B denotes any two continuous points on the lane center line, and M denotes the projection point of P to the line segment AB (positioning point candidate). When M is between A, B, r is more than or equal to 0 and less than or equal to 1.

After the position relation indicating parameter is obtained, the subsequent processing can be performed only when the position relation indicating parameter is within the preset parameter range (i.e. r is more than or equal to 0 and less than or equal to 1), otherwise, the AB is updated to be the next group of two adjacent shape points, and the calculation is continued. When the position relation indicating parameter is within the preset parameter range, the coordinate of M can be calculated by the following formula:

M.lon＝A.lon+r*(B.lon–A.lon)，

M.lat＝A.lat+r*(B.lat–A.lat)。

where m.lon is the longitude of M and m.lat represents the latitude of M. Lon is longitude of A, lat is latitude of A, Lon is longitude of B, and B.lon is latitude of B.

It is understood that after determining the line segment where the candidate anchor point is located, the distance from the vehicle position to the line segment of each shape point can be calculated without the position of the candidate anchor point, as shown in fig. 6, APB forms a triangle, where A, B is two adjacent shape points, and P is the vehicle position.

In some examples, the distance S from the vehicle position to each shape point line segment may be calculated by the following formula:

the vector representation can convert longitude and latitude representations of points into a representation of a two-dimensional plane coordinate system, and can utilize mercator projection or directly convert a difference value of the longitude and latitude into a difference value of an absolute distance meter.

Alternatively, the distance S from the vehicle position to each point line segment can be calculated by the following formula:

wherein a, b and c respectively represent the lengths of the line segments AP, AB and PB, and the lengths can be easily calculated by inputting longitude and latitude coordinates of two points.

In the practical application process, in order to improve the accuracy of vehicle positioning, factors such as the driving speed and the driving direction of the vehicle can be comprehensively considered when determining the lane positioning point. That is, in some optional embodiments, before the step "determining the lane locating point of the target vehicle from the candidate locating points based on the distance", the lane-level data matching method provided by the embodiments of the present invention may further include:

acquiring vehicle speed data and vehicle course data of a target vehicle;

and calculating the running weight parameter of the target vehicle based on the vehicle speed data, the vehicle course data and a preset weight mapping relation.

In the embodiment of the invention, the current speed and direction of the vehicle can be combined by the driving weight parameters, so that the positioning accuracy is further improved.

Correspondingly, the step "determining the lane locating point of the target vehicle from the candidate locating points based on the distance" may specifically include:

determining a distance weight parameter for the target vehicle based on the distance;

and determining the lane positioning point of the target vehicle from the candidate positioning points based on the positioning parameters.

Specifically, the distance weight parameter may be calculated by the following formula:

wherein eta is a self-defined constant and can be set according to the actual situation. And d (i) the distance from the vehicle position to a point line segment formed by two adjacent points in the positioning area.

It should be noted that the calculation formula of the distance weight parameter is only an example, and actually w_disThe definition of (1) is not limited as long as (1) is a symmetric function and (2) the value range is [0,1 ]](3) the smaller w is the d (i)_disThe larger the condition.

Specifically, in some optional examples, the weight mapping relationship may include a speed weight mapping relationship and an angle weight mapping relationship, and the step of "calculating the driving weight parameter of the target vehicle based on the vehicle speed data and the vehicle heading data and the preset weight mapping relationship" may specifically include:

calculating a speed weight parameter of the target vehicle based on the vehicle speed data and the speed weight mapping relation;

determining the running angle of the target vehicle according to a preset angle coordinate system and vehicle course data;

and calculating the running weight parameter of the target vehicle based on the speed weight parameter and the angle weight parameter.

Wherein the velocity weight parameter

Where spd is vehicle speed data.

The angle weight parameter cos (azidiff), specifically, azidiff | α - β |, as shown in fig. 7, α is the driving angle of the target vehicle, and β is the line segment angle of the shape point line segment.

The driving weight parameter can be calculated by the following formula:

wherein gamma, lambda and phi are constants which can be freely set,

it should be noted that the calculation formula of the driving weight parameter is only an example, and actually W_spd,The definition of (1) is not limited as long as (1) a symmetric function is satisfied, and (2) a value range is [0,1 ]]And (3) the condition that the result is smaller as the vehicle speed is larger when the angles are the same, and the result is smaller as the angle is larger when the vehicle speed is the same.

In some optional embodiments, before the step "determining a distance from the vehicle position to a shape point line segment formed by two adjacent shape points in the positioning area", the lane-level data matching method provided by the embodiment of the present invention may further include:

acquiring vehicle speed data and vehicle course data of a target vehicle;

determining the distance from the vehicle position to a shape point line segment formed by two adjacent shape points in the positioning area, wherein the distance comprises the following steps:

calculating the estimated positioning position of the target vehicle according to the vehicle position, the vehicle speed data and the vehicle course data;

Therefore, the actual vehicle position at the moment when the positioning result is obtained through calculation can be obtained by considering the prediction of the vehicle speed and the course, namely the estimated positioning position, and then the vehicle positioning is carried out. The real-time performance of vehicle positioning can be improved.

From the above, the embodiment of the invention can acquire the vehicle position of the target vehicle, determine the high-precision data of the local lane corresponding to at least one lane of the road where the vehicle position is located, wherein one piece of high-precision data of the local lane comprises at least two form points of one lane, the form points are used for indicating the trend of the lane, and based on the position relationship between the form points, thinning the figure points in the local lane high-precision data to obtain lane-level thinning data corresponding to each lane, matching the curve formed by the figure points in the lane-level thinning data with the curve formed by the starting points in the local lane high-precision data, according to the position of the shape point after thinning and the position of the vehicle, predicting a positioning area of the target vehicle in each lane based on the shape point after thinning of each lane, determining the distance from the position of the vehicle to a shape point line segment formed by two adjacent shape points in the positioning area, and determining a matching result of the target vehicle in the local lane high-precision data based on the distance; according to the embodiment of the invention, the high-precision local lane high-precision data is thinned to obtain the thinned shape points, and the positioning area of the target vehicle in each lane is predicted on the basis of the thinned shape points, so that when lane-level positioning is carried out, the lane and/or shape points matched with the target vehicle in the local lane high-precision data can be determined according to the thinned shape points in the positioning area, the vehicle positioning precision can be maintained, the calculation cost is reduced, the vehicle positioning efficiency is improved, and the rapid matching of the vehicle position and the lane high-precision data is realized.

The method according to the preceding embodiment is illustrated in further detail below by way of example.

In this embodiment, the system of fig. 1 will be explained.

As shown in fig. 8, the specific flow of the lane-level data matching method of this embodiment may be as follows:

801. the terminal determines the vehicle position of the target vehicle and determines the high-precision data of the local lane corresponding to at least one lane of the road where the vehicle position is located.

As shown in fig. 9, the terminal may determine the vehicle location of the target vehicle through a vehicle location module in the lane-level data matching system. The high-precision data of the local lane of each lane can be determined by the map data module.

The vehicle positioning module can collect historical state information of the vehicle in a historical positioning time period, wherein the historical state information includes but is not limited to global positioning system GPS information (which can be based on common GNSS positioning, PPP positioning and RTK positioning), vehicle control information, vehicle vision perception information, inertial measurement unit IMU information and the like. Finally, the module outputs positioning point information P (longitude and latitude coordinates of the vehicle position coordinates) at the current moment through a certain algorithm and rules. The positioning point information is used for acquiring local map data from the map data module and for lane matching, is an important input for lane-level positioning judgment and is also a reference point for lane-level adsorption/matching results.

The map data module is matched with the corresponding road position according to the positioning information of the vehicle positioning module, so that local map information of the current position is obtained, and here local lane level road information near the vehicle positioning module is obtained. The data comprises lane level information of a local area of a vehicle positioning point, including the total number of lanes and the lane center line form point coordinates of each lane.

Assuming that the map data returns a set of lane data, which is denoted as lanegagroup, the total number of lanes in each lanegagroup is consistent, the lane line type and color are also consistent, and different lanegagroup divisions may be due to different lane line types/colors or different lane numbers. The lane group data may include a lane topology relationship. The map data module returns the lanegagroup data information of the vehicle positioning point, and if the laneway group data information is empty, the area does not have required lane level data.

802. And the terminal thins the shape points in the local lane high-precision data based on the position relation among the shape points in the local lane high-precision data to obtain lane-level thinning data corresponding to each lane, and the curve formed by the shape points in the lane-level thinning data is matched with the curve formed by the starting points in the local lane high-precision data.

Specifically, when the geometric point is thinned, a step compression algorithm, a line segment filtering algorithm, and the like may be used, which is not limited in the embodiment of the present invention.

Through step 801, it is known that the vehicle is roughly within a laneGroup plane, and it is not known which lane is specifically within the plane, and which specific position in the lane. The form points of one laneGroup may be hundreds, thousands or even tens of thousands, with each lane having dense form points. In order to reduce the calculation amount of matching, the density of the shape points needs to be thinned, and the density of the points is reduced under the condition of ensuring no great loss of precision.

As shown in fig. 9, the terminal may perform thinning on the shape point in the local lane high-precision data through a data thinning module in the lane-level data matching system.

803. And the terminal predicts the positioning area of the target vehicle in each lane based on the sparse points of each lane according to the positions of the sparse points and the positions of the vehicles.

For example, it can be assumed that the shape points after the current lane thinning are P1, P2, …, PN, and if N < (equal to the number of area shape points), no calculation is needed, and the search interval is directly returned to [1, N ]. If N > the number of region shape points, P1 is taken as the first shape point and PN is taken as the second shape point.

Then, the first reference pattern point may be PM, (L + N)/2), and the second reference pattern point may be PS, (M + N)/2. And calculating the distances between the vehicle position and the PM and the PN to respectively obtain a first distance and a second distance.

As shown in fig. 9, the terminal may determine the localization area from the thinning-out point by an area determination module in the lane-level data matching system.

804. And the terminal calculates the position relation indicating parameter between the candidate positioning point of the target vehicle on each lane and the shape point line segment formed by two shape points according to the position of the vehicle and the shape point positions of any two adjacent shape points in the positioning area of each lane.

Specifically, as shown in fig. 6, the positional relationship indicating parameter

Where P denotes the vehicle positioning coordinates, A, B denotes any two continuous shape points on the lane center line, and M denotes the projection point of P to the line segment AB (positioning point candidate). When M is between A, B, 0 ≦ r ≦ 1.

805. And when the position relation indicating parameter is within the preset parameter range, calculating the position of the candidate positioning point of the target vehicle on each lane according to the shape point positions of the two shape points and the position relation indicating parameter.

Specifically, when r is greater than or equal to 0 and less than or equal to 1, the coordinate of M can be calculated by the following formula:

M.lon＝A.lon+r*(B.lon–A.lon)，

m.lat + r (b.lat-a.lat), where lon and lat may represent longitude and latitude, respectively.

806. And the terminal calculates the line segment distance between the vehicle position and the position of each candidate positioning point, and determines the lane positioning point of the target vehicle from the candidate positioning points based on the line segment distance.

Specifically, the terminal may use the candidate positioning point corresponding to the minimum line segment distance as the lane positioning point of the target vehicle.

In some optional embodiments, the lane-level data matching system provided in the embodiments of the present invention may further include a motion data module, which provides real-time vehicle speed information, IMU information (such as vehicle heading angle information), steering wheel angle information, and the like of the vehicle; and the image processing module is used for providing a processing result of the visual road information in front of the vehicle, the camera can acquire a road image in front of the vehicle for a monocular camera arranged on the vehicle (arranged on a windshield, a roof or the like), then the acquired image is analyzed and processed, and finally the identified lane line type and color information (which can be obtained by a machine learning method) around the vehicle (on the left side and the right side) and the confidence quality of the lane line information are output. Wherein lane line colors include, but are not limited to, yellow, white, blue, green, gray, black, and others; lane line types include, but are not limited to, single solid line, single dashed line, double solid line, double dashed line, left virtual right real, left real right virtual, guard rail, curb, road edge, among others.

The lane-level data matching system provided by the embodiment of the invention also comprises a laser radar module: and providing a 3D point cloud result of radar scanning for matching with a high-precision map. Ultrasonic radar: and the laser radar module provides radar measurement results to obtain position information of some markers for matching with a high-precision map. And other modules: such as looking around the cameras (the result of each camera can be taken as an observed value), the speed of the vehicle's four wheels, etc.

Therefore, the embodiment of the invention can acquire the vehicle position of the target vehicle, determine the high-precision data of the local lane corresponding to at least one lane of the road where the vehicle position is located, wherein one piece of high-precision data of the local lane comprises at least two shape points of one lane, the shape points are used for indicating the trend of the lane, and based on the position relationship among the shape points, thinning the figure points in the local lane high-precision data to obtain lane-level thinning data corresponding to each lane, matching the curve formed by the figure points in the lane-level thinning data with the curve formed by the starting points in the local lane high-precision data, according to the position of the shape point after thinning and the position of the vehicle, predicting a positioning area of the target vehicle in each lane based on the shape point after thinning of each lane, determining the distance from the position of the vehicle to a shape point line segment formed by two adjacent shape points in the positioning area, and determining a matching result of the target vehicle in the local lane high-precision data based on the distance; according to the embodiment of the invention, the high-precision local lane high-precision data is thinned to obtain the thinned shape points, and the positioning area of the target vehicle in each lane is predicted on the basis of the thinned shape points, so that when lane-level positioning is carried out, the lane and/or shape points matched with the target vehicle in the local lane high-precision data can be determined according to the thinned shape points in the positioning area, the vehicle positioning precision can be maintained, the calculation cost is reduced, the vehicle positioning efficiency is improved, and the rapid matching of the vehicle position and the lane high-precision data is realized.

In order to better implement the method, correspondingly, the embodiment of the invention also provides a lane-level data matching device.

Referring to fig. 10, the apparatus includes:

a position acquisition unit 1001 operable to acquire a vehicle position of a target vehicle;

the data determining unit 1002 may be configured to determine local lane high-precision data corresponding to at least one lane of a road where the vehicle is located, where one local lane high-precision data includes at least two shape points of one lane, and the shape points are used for indicating a trend of the lane;

a data thinning unit 1003, configured to thin the shape points in the local lane high-precision data based on the position relationship between the shape points to obtain lane-level thinning data corresponding to each lane, where a curve formed by the shape points in the lane-level thinning data matches a curve formed by the start points in the local lane high-precision data;

a region prediction unit 1004, which may be configured to predict a positioning region of the target vehicle in each lane based on the post-thinning point of each lane according to the position of the post-thinning point and the vehicle position;

the result determining unit 1005 may be configured to determine a distance from the vehicle position to a shape point line segment formed by two adjacent shape points in the positioning area, and determine a matching result of the target vehicle in the local lane high-precision data based on the distance.

In some optional embodiments, the shape points include end shape points and intermediate shape points located between the end shape points, and the data thinning unit 1003 is configured to determine a thinned shape point for keeping the lane direction in the intermediate shape points based on a position relationship between the intermediate shape point and the end shape points at both ends;

and determining the post-thinning points for keeping the trend of the lane in the adjacent end point points based on the position relation between the middle points and the adjacent end point points, and obtaining lane-level thinning data consisting of the post-thinning points.

In some optional embodiments, the data thinning unit 1003 is configured to determine a maximum distance between a straight line formed by the middle centroid point and the two end centroid points based on the centroid point positions of the centroid points;

if the maximum distance is larger than the preset distance threshold, taking the middle shaping point corresponding to the maximum distance as a new post-thinning shaping point;

In some optional embodiments, the region prediction unit 1004 may be configured to determine a first reference shape point of the thinned shape points according to a first shape point and a second shape point of the thinned shape points when the number of the thinned shape points is greater than a preset number of region shape points;

In some optional embodiments, the result determining unit 1005 may be configured to determine the position of the candidate positioning point of the target vehicle on each lane according to the vehicle position and the shape point positions of any two adjacent shape points in the positioning region of each lane;

and taking the two adjacent shape points corresponding to the target positioning point as a matching result of the target vehicle in the high-precision data of the local lane.

In some optional embodiments, the result determining unit 1005 may be configured to calculate, according to the vehicle position and the shape point positions of any two adjacent shape points in the positioning region of each lane, a position relationship indicating parameter between the candidate positioning point of the target vehicle on each lane and a shape point line segment formed by the two shape points;

In some optional embodiments, as shown in fig. 11, the lane-level data matching apparatus provided in the embodiment of the present invention may further include a driving weight calculation unit 1006, which may be configured to obtain vehicle speed data and vehicle heading data of the target vehicle;

calculating a driving weight parameter of the target vehicle based on the vehicle speed data, the vehicle course data and a preset weight mapping relation;

a result determination unit operable to determine a distance weight parameter of the target vehicle based on the distance;

and determining the target positioning point of the target vehicle from the candidate positioning points based on the positioning parameters.

In some optional embodiments, the weight mapping relationship may include a speed weight mapping relationship and an angle weight mapping relationship, and the driving weight calculation unit 1006 may be configured to calculate a speed weight parameter of the target vehicle based on the vehicle speed data and the speed weight mapping relationship;

In some optional embodiments, the lane-level data matching apparatus provided in the embodiments of the present invention may further include a driving planning unit 1007, which may be configured to determine a target lane corresponding to the target vehicle according to a matching result of the target vehicle in the local lane high-precision data;

In some optional embodiments, the lane-level data matching apparatus provided in the embodiments of the present invention may further include a driving data obtaining unit 1008, which may be configured to obtain vehicle speed data and vehicle heading data of the target vehicle;

a result determination unit 1005 operable to calculate an estimated location of the target vehicle based on the vehicle location, and the vehicle speed data and the vehicle heading data;

In some optional embodiments, the lane-level data matching apparatus provided in the embodiment of the present invention may further include a data updating and thinning unit 1009, which may be configured to obtain lane flow data of each lane in a road where the vehicle is located;

and based on the new preset distance threshold, executing the step of determining the maximum distance between the middle shape point and a straight line formed by the original starting shape point and the original final shape point based on the shape point position of the shape point.

It can be known from the above that, by the lane-level data matching device, the vehicle position of the target vehicle can be obtained, the local lane high-precision data corresponding to at least one lane of the road where the vehicle position is located is determined, one local lane high-precision data includes at least two shape points of one lane, the shape points are used for indicating the direction of the lane, based on the position relationship between the shape points, the shape points in the local lane high-precision data are thinned, the lane-level thinned data corresponding to each lane is obtained, the curve formed by the shape points in the lane-level thinned data is matched with the curve direction formed by the starting points in the local lane high-precision data, the positioning area of the target vehicle in each lane is predicted based on the thinned shape points of each lane according to the position of the thinned shape points and the vehicle position, the distance from the vehicle position to the line segment of the shape points formed by two adjacent shape points in the positioning area is determined, determining a matching result of the target vehicle in the local lane high-precision data based on the distance; according to the embodiment of the invention, the high-precision local lane high-precision data is thinned to obtain the thinned shape points, and the positioning area of the target vehicle in each lane is predicted on the basis of the thinned shape points, so that when lane-level positioning is carried out, the lane and/or shape points matched with the target vehicle in the local lane high-precision data can be determined according to the thinned shape points in the positioning area, the vehicle positioning precision can be maintained, the calculation cost is reduced, the vehicle positioning efficiency is improved, and the rapid matching of the vehicle position and the lane high-precision data is realized.

In addition, an embodiment of the present invention further provides an electronic device, where the electronic device may be a terminal or a server, and as shown in fig. 12, a schematic structural diagram of the electronic device according to the embodiment of the present invention is shown, specifically:

the electronic device may include Radio Frequency (RF) circuitry 1201, memory 1202 including one or more computer-readable storage media, input unit 1203, display unit 1204, sensors 1205, audio circuitry 1206, Wireless Fidelity (WiFi) module 1207, processor 1208 including one or more processing cores, and power supply 1209. Those skilled in the art will appreciate that the electronic device configuration shown in fig. 12 does not constitute a limitation of the electronic device and may include more or fewer components than those shown, or some components may be combined, or a different arrangement of components. Wherein:

RF circuit 1201 may be used for receiving and transmitting signals during a message transmission or communication process, and in particular, for receiving downlink information from a base station and then processing the received downlink information by one or more processors 1208; in addition, data relating to uplink is transmitted to the base station. In general, RF circuitry 1201 includes, but is not limited to, an antenna, at least one Amplifier, a tuner, one or more oscillators, a Subscriber Identity Module (SIM) card, a transceiver, a coupler, a Low Noise Amplifier (LNA), a duplexer, and the like. In addition, RF circuitry 1201 may also communicate with networks and other devices via wireless communication. The wireless communication may use any communication standard or protocol, including but not limited to Global System for Mobile communications (GSM), General Packet Radio Service (GPRS), Code Division Multiple Access (CDMA), Wideband Code Division Multiple Access (WCDMA), Long Term Evolution (LTE), email, Short Message Service (SMS), and the like.

The memory 1202 may be used to store software programs and modules, and the processor 1208 performs various functional applications and data processing by operating the software programs and modules stored in the memory 1202. The memory 1202 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application program required by at least one function (such as a sound playing function, an image playing function, etc.), and the like; the storage data area may store data (such as audio data, a phonebook, etc.) created according to the use of the electronic device, and the like. Further, the memory 1202 may include high-speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid state storage device. Accordingly, the memory 1202 may also include a memory controller to provide access to the memory 1202 by the processor 1208 and the input unit 1203.

The input unit 1203 may be used to receive input numeric or character information and generate keyboard, mouse, joystick, optical or trackball signal inputs related to user settings and function control. In particular, in one particular embodiment, the input unit 1203 may include a touch-sensitive surface as well as other input devices. The touch-sensitive surface, also referred to as a touch display screen or a touch pad, may collect touch operations by a user (e.g., operations by a user on or near the touch-sensitive surface using a finger, a stylus, or any other suitable object or attachment) thereon or nearby, and drive the corresponding connection device according to a predetermined program. Alternatively, the touch sensitive surface may comprise two parts, a touch detection means and a touch controller. The touch detection device detects the touch direction of a user, detects a signal brought by touch operation and transmits the signal to the touch controller; the touch controller receives touch information from the touch sensing device, converts the touch information into touch point coordinates, sends the touch point coordinates to the processor 1208, and can receive and execute commands sent by the processor 1208. In addition, touch sensitive surfaces may be implemented using various types of resistive, capacitive, infrared, and surface acoustic waves. The input unit 1203 may include other input devices in addition to a touch-sensitive surface. In particular, other input devices may include, but are not limited to, one or more of a physical keyboard, function keys (such as volume control keys, switch keys, etc.), a trackball, a mouse, a joystick, and the like.

The display unit 1204 may be used to display information input by or provided to the user as well as various graphical user interfaces of the electronic device, which may be made up of graphics, text, icons, video, and any combination thereof. The Display unit 1204 may include a Display panel, and optionally, the Display panel may be configured in the form of a Liquid Crystal Display (LCD), an Organic Light-Emitting Diode (OLED), or the like. Further, the touch-sensitive surface may overlay the display panel, and when a touch operation is detected on or near the touch-sensitive surface, the touch operation is transmitted to the processor 1208 to determine the type of touch event, and the processor 1208 may provide a corresponding visual output on the display panel according to the type of touch event. Although in FIG. 12 the touch sensitive surface and the display panel are two separate components to implement input and output functions, in some embodiments the touch sensitive surface may be integrated with the display panel to implement input and output functions.

The electronic device can also include at least one sensor 1205, such as a light sensor, motion sensor, and other sensors. In particular, the light sensor may include an ambient light sensor that may adjust the brightness of the display panel according to the brightness of ambient light, and a proximity sensor that may turn off the display panel and/or the backlight when the electronic device is moved to the ear. As one of the motion sensors, the gravity acceleration sensor can detect the magnitude of acceleration in each direction (generally, three axes), can detect the magnitude and direction of gravity when the mobile phone is stationary, and can be used for applications of recognizing the posture of the mobile phone (such as horizontal and vertical screen switching, related games, magnetometer posture calibration), vibration recognition related functions (such as pedometer and tapping), and the like; as for other sensors such as a gyroscope, a barometer, a hygrometer, a thermometer, and an infrared sensor, which may be further configured to the electronic device, detailed descriptions thereof are omitted.

Audio circuitry 1206, a speaker, and a microphone may provide an audio interface between a user and the electronic device. The audio circuit 1206 can transmit the electrical signal converted from the received audio data to a loudspeaker, and the electrical signal is converted into a sound signal by the loudspeaker and output; on the other hand, the microphone converts a collected sound signal into an electric signal, converts the electric signal into audio data after being received by the audio circuit 1206, processes the audio data by the audio data output processor 1208, and transmits the audio data to, for example, another electronic device via the RF circuit 1201 or outputs the audio data to the memory 1202 for further processing. Audio circuitry 1206 may also include an earbud jack to provide communication of peripheral headphones with the electronic device.

WiFi belongs to short-range wireless transmission technology, and the electronic device can help the user send and receive e-mail, browse web pages, access streaming media, etc. through the WiFi module 1207, which provides wireless broadband internet access for the user. Although fig. 12 shows the WiFi module 1207, it is understood that it does not belong to the essential constitution of the electronic device, and may be omitted entirely as needed within the scope not changing the essence of the invention.

The processor 1208 is a control center of the electronic device, connects various parts of the entire cellular phone using various interfaces and lines, and performs various functions of the electronic device and processes data by operating or executing software programs and/or modules stored in the memory 1202 and calling data stored in the memory 1202. Optionally, processor 1208 may include one or more processing cores; preferably, the processor 1208 may integrate an application processor, which mainly handles operating systems, user interfaces, application programs, etc., and a modem processor, which mainly handles wireless communications. It is to be appreciated that the modem processor described above may not be integrated into processor 1208.

The electronic device also includes a power supply 1209 (e.g., a battery) for powering the various components, which may preferably be logically coupled to the processor 1208 via a power management system that may be used to manage charging, discharging, and power consumption. The power supply 1209 may also include one or more dc or ac power sources, recharging systems, power failure detection circuitry, power converters or inverters, power status indicators, and any other components.

Although not shown, the electronic device may further include a camera, a bluetooth module, and the like, which are not described in detail herein. Specifically, in this embodiment, the processor 1208 in the electronic device loads an executable file corresponding to a process of one or more application programs into the memory 1202 according to the following instructions, and the processor 1208 runs the application programs stored in the memory 1202, so as to implement various functions as follows:

acquiring a vehicle position of a target vehicle;

determining local lane high-precision data corresponding to at least one lane of a road where the vehicle is located, wherein the local lane high-precision data comprises at least two shape points of the lane, and the shape points are used for indicating the trend of the lane;

predicting a positioning area of the target vehicle in each lane based on the shape-drawing points of each lane according to the positions of the shape-drawing points and the vehicle positions;

It will be understood by those skilled in the art that all or part of the steps of the methods of the above embodiments may be performed by instructions or by associated hardware controlled by the instructions, which may be stored in a computer readable storage medium and loaded and executed by a processor.

To this end, the present invention provides a computer-readable storage medium, in which a plurality of instructions are stored, and the instructions can be loaded by a processor to execute the steps in any lane-level data matching method provided by the present invention. For example, the instructions may perform the steps of:

acquiring a vehicle position of a target vehicle;

The above operations can be implemented in the foregoing embodiments, and are not described in detail herein.

Wherein the computer-readable storage medium may include: read Only Memory (ROM), Random Access Memory (RAM), magnetic or optical disks, and the like.

Since the instructions stored in the computer-readable storage medium can execute the steps in any lane-level data matching method provided in the embodiment of the present invention, the beneficial effects that can be achieved by any lane-level data matching method provided in the embodiment of the present invention can be achieved, which are detailed in the foregoing embodiments and will not be described herein again.

According to an aspect of the application, there is also provided a computer program product or a computer program comprising computer instructions stored in a computer readable storage medium. The processor of the electronic device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the electronic device executes the method provided in the various alternative implementations in the above embodiments.

The lane-level data matching method, device, electronic device and storage medium provided by the embodiments of the present invention are described in detail above, and a specific example is applied in the present disclosure to explain the principle and the implementation of the present invention, and the description of the above embodiments is only used to help understanding the method and the core idea of the present invention; meanwhile, for those skilled in the art, according to the idea of the present invention, the specific embodiments and the application range may be changed, and in summary, the content of the present specification should not be construed as limiting the present invention.

Claims

1. A lane-level data matching method, comprising:

acquiring a vehicle position of a target vehicle;

2. The lane-level data matching method according to claim 1, wherein the shape points include end shape points and intermediate shape points located between the end shape points;

the method for performing thinning on the shape points in the local lane high-precision data based on the position relationship among the shape points to obtain lane-level thinning data corresponding to each lane comprises the following steps:

and determining the post-thinning points for keeping the lane trend in the intermediate points between the adjacent end point points based on the position relationship between the intermediate points between the adjacent end point points and the adjacent end point points by taking the post-thinning points as new end point points to obtain lane-level thinning data consisting of the post-thinning points.

3. The lane-level data matching method according to claim 2, wherein the determining of the thinned-out points of the intermediate shape points for keeping the lane direction based on the positional relationship between the intermediate shape points and the end shape points at both ends comprises:

the method for obtaining lane-level rarefaction data formed by the rarefaction shaping points comprises the following steps of taking the rarefaction shaping points as new end shaping points, determining the rarefaction shaping points used for keeping the lane trend in the middle of the adjacent end shaping points based on the position relation between the middle shaping points and the adjacent end shaping points among the adjacent end shaping points, and obtaining the lane-level rarefaction data formed by the rarefaction shaping points, wherein the method comprises the following steps:

determining the maximum distance between the middle figure point on the sub-curve and the end figure point of the sub-curve;

and taking the new post-rarefaction figure point as a new end figure point, dividing the sub-curve where the new post-rarefaction figure point is located into two sections of new sub-curves, executing the step of determining the maximum distance from the middle figure point on the sub-curve to the end figure point of the sub-curve until no new post-rarefaction figure point exists on the sub-curve, and obtaining lane-level rarefaction data formed by the post-rarefaction figure points.

4. The lane-level data matching method according to claim 1, wherein the predicting a localization area of the target vehicle in each lane based on the thinned-out point of each lane according to the position of the thinned-out point and the vehicle position includes:

when the number of the shaping points after the thinning is larger than the number of the preset area shaping points, determining a first reference shaping point in the shaping points after the thinning according to a first shaping point and a second shaping point in the shaping points after the thinning;

5. The lane-level data matching method according to claim 1, wherein the determining of the distance from the vehicle position to a shape point line segment formed by two adjacent shape points in the positioning region, and the determining of the matching result of the target vehicle in the local lane high-precision data based on the distance comprises:

determining the position of the target vehicle at the candidate positioning point on each lane according to the vehicle position and the shape point positions of any two adjacent shape points in the positioning area of each lane;

6. The lane-level data matching method according to claim 5, wherein the determining positions of candidate positioning points of the target vehicle on the lanes according to the vehicle position and the shape point positions of any two adjacent shape points in the positioning region of each lane comprises:

calculating a position relation indicating parameter between a candidate positioning point of the target vehicle on each lane and a shape point line segment formed by two shape points according to the vehicle position and the shape point positions of any two adjacent shape points in the positioning area of each lane;

7. The lane-level data matching method according to claim 5, wherein before determining a target localization point of the target vehicle from the candidate localization points based on the distance, the method further comprises:

acquiring vehicle speed data and vehicle course data of the target vehicle;

the determining a target localization point of the target vehicle from the candidate localization points based on the distance comprises:

8. The lane-level data matching method according to claim 7, wherein the weight mapping relationship includes a speed weight mapping relationship and an angle weight mapping relationship, and the calculating of the driving weight parameter of the target vehicle based on the vehicle speed data and the vehicle heading data and a preset weight mapping relationship includes:

calculating a speed weight parameter of the target vehicle based on the vehicle speed data and the speed weight mapping relationship;

9. The lane-level data matching method according to claim 1, further comprising:

10. The lane-level data matching method according to claim 1, wherein before determining a distance from the vehicle position to a point line segment formed by two adjacent points in the positioning region, the method further comprises:

acquiring vehicle speed data and vehicle course data of the target vehicle;

the determining the distance from the vehicle position to a shape point line segment formed by two adjacent shape points in the positioning area comprises:

11. The lane-level data matching method according to claim 3, characterized in that the method further comprises:

acquiring lane flow data of each lane in a road where the vehicle is located;

12. A lane-level data matching apparatus, characterized by comprising:

the data determining unit is used for determining local lane high-precision data corresponding to at least one lane of a road where the vehicle is located, wherein one piece of local lane high-precision data comprises at least two form points of one lane, and the form points are used for indicating the trend of the lane;

the data thinning unit is used for thinning the figure points in the local lane high-precision data based on the position relation between the figure points to obtain lane-level thinning data corresponding to each lane, and a curve formed by the figure points in the lane-level thinning data is matched with a curve formed by the starting points in the local lane high-precision data in trend;

the region prediction unit is used for predicting a positioning region of the target vehicle in each lane based on the post-thinning point of each lane according to the position of the post-thinning point and the vehicle position;

13. An electronic device comprising a memory and a processor; the memory stores an application program, and the processor is configured to run the application program in the memory to execute the steps of the lane-level data matching method according to any one of claims 1 to 11.

14. A computer readable storage medium storing a plurality of instructions adapted to be loaded by a processor to perform the steps of the lane-level data matching method according to any one of claims 1 to 11.

15. A computer program product comprising a computer program or instructions, characterized in that the computer program or instructions, when executed by a processor, implement the steps of the lane-level data matching method according to any of claims 1 to 11.