WO2022213580A1

WO2022213580A1 - Map generation method and apparatus, and electronic device and storage medium

Info

Publication number: WO2022213580A1
Application number: PCT/CN2021/126211
Authority: WO
Inventors: 张永乐
Original assignee: 阿波罗智联(北京)科技有限公司
Priority date: 2021-04-09
Filing date: 2021-10-25
Publication date: 2022-10-13
Also published as: CN113155141A

Abstract

A map generation method and apparatus, and an electronic device and a storage medium, which relate to the technical field of intelligent traffic, and in particular relate to the technical field of map data fusion. The method comprises: acquiring a first map data set and a second map data set, wherein the first map data set contains all first trajectory point coordinates corresponding to each lane, and the second map data set contains all second trajectory point coordinates corresponding to each road, and road information (101); according to the degree of matching between all the first trajectory point coordinates corresponding to each lane and all the second trajectory point coordinates corresponding to each road, determining a road that matches each lane (102); and generating a fused map data set on the basis of all the first trajectory point coordinates corresponding to each lane and the road information corresponding to the road that matches each lane (103). A fused map data set that contains both a lane and road information of a road can be obtained, thereby enriching map data.

Description

Map generation method, device, electronic device and storage medium

CROSS-REFERENCE TO RELATED APPLICATIONS

This disclosure requires the priority of the Chinese patent application number "202110385330.7" for the invention titled "Map Generation Method, Device, Electronic Device and Storage Medium" submitted by Apollo Zhilian (Beijing) Technology Co., Ltd. on April 9, 2021 right.

technical field

The present disclosure relates to the technical field of intelligent transportation, in particular to the technical field of map data fusion, and in particular to a method, device, electronic device and storage medium for generating a map.

Background technique

The realization of intelligent transportation is inseparable from the support of map data. In order to enable every traveler to obtain accompanying traffic travel services, the map needs to fully connect all road elements.

However, at present, the high-precision maps used in intelligent transportation contain less map data and cannot provide rich map element information.

SUMMARY OF THE INVENTION

The present disclosure provides a method, device, electronic device and storage medium for generating a map.

According to an aspect of the present disclosure, a method for generating a map is provided, comprising:

Obtain a first map data set and a second map data set, wherein the first map data set includes coordinates of each first track point corresponding to each lane, and the second map data set includes each first track point corresponding to each road. 2. Track point coordinates and road information;

According to the degree of matching between the coordinates of each first trajectory point corresponding to each of the lanes and the coordinates of each second trajectory point corresponding to each of the roads, determine a road that matches each of the lanes;

Based on the coordinates of each first track point corresponding to each of the lanes, and road information corresponding to the road matching each of the lanes, a fused map dataset is generated.

According to another aspect of the present disclosure, an apparatus for generating a map is provided, comprising:

The acquisition module is used to acquire a first map data set and a second map data set, wherein the first map data set contains coordinates of each first track point corresponding to each lane, and the second map data set contains each Coordinates and road information of each second track point corresponding to the road;

a matching module, configured to determine a road matching each of the lanes according to the degree of matching between the coordinates of each first trajectory point corresponding to each of the lanes and the coordinates of each of the second trajectory points corresponding to each of the roads;

The generating module is configured to generate a fused map data set based on the coordinates of each first track point corresponding to each of the lanes and the road information corresponding to the road matched with each of the lanes.

According to another aspect of the present disclosure, there is provided an electronic device, comprising:

at least one processor; and

a memory communicatively coupled to the at least one processor; wherein,

The memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to execute the map according to the embodiment of the above aspect. Generate method.

According to another aspect of the present disclosure, there is provided a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to cause the computer to perform the generation of the map according to the embodiments of the above aspect method.

According to another aspect of the present disclosure, there is provided a computer program product, including a computer program, which, when executed by a processor, implements the method for generating a map according to the embodiments of the above-mentioned aspect.

The map generation method, device, electronic device and storage medium provided by the present disclosure, by acquiring the first map data set and the second map data set, according to the coordinates of each first track point of each lane in the first map data set and the second The matching degree between the coordinates of each second track point of each road in the map data set determines the road matching each lane, and then based on the coordinates of each first track point corresponding to each lane and the corresponding road corresponding to each lane The fused map data set is generated, and the fused map data set containing both the lane and the road information of the road is obtained, which enriches the map data.

It should be understood that what is described in this section is not intended to identify key or critical features of embodiments of the disclosure, nor is it intended to limit the scope of the disclosure. Other features of the present disclosure will become readily understood from the following description.

Description of drawings

The accompanying drawings are used for better understanding of the present solution, and do not constitute a limitation to the present disclosure. in:

1 is a schematic flowchart of a method for generating a map according to an embodiment of the present disclosure;

2 is a schematic flowchart of a method for generating a map according to another embodiment of the present disclosure;

3 is an example diagram of the positional relationship between each first trajectory point corresponding to a lane and a candidate road;

4 is a schematic structural diagram of an apparatus for generating a map according to an embodiment of the present disclosure;

5 is a schematic structural diagram of an apparatus for generating a map according to another embodiment of the present disclosure;

6 is a schematic structural diagram of an apparatus for generating a map according to another embodiment of the present disclosure;

FIG. 7 is a block diagram of an electronic device used to implement the method for generating a map according to an embodiment of the present disclosure.

Detailed ways

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

At present, the high-precision maps used in intelligent transportation contain less map data, and can only provide lane-level information, but cannot provide rich map element information, and need to collect a large amount of road information (such as speed limit information, road names, Points of interest, etc.) can be used to make high-precision maps, which results in a very large workload for making high-precision maps, resulting in a long online cycle for high-precision maps and low production efficiency.

Compared with high-precision maps, traditional navigation maps can provide road-level road information. In order to expand map information and enrich the application of map data, the high-precision map road network can be bound to the ordinary navigation map road network and data fusion can be performed.

In the related art, the binding and fusion of map data are mainly realized in two ways. One is to perform data fusion manually, which is inefficient; the other is to perform data fusion by manual + machine method. First, manually bind high-precision maps and navigation maps, and then realize data fusion through algorithms. This method is still It cannot be fully automated, and the technical difficulty is the binding of high-precision maps and navigation maps.

In view of the above problems, the present disclosure provides a map generation method, device, electronic device and storage medium. By acquiring the first map data set and the second map data set, according to the first map data set of each lane The matching degree between the coordinates of the track points and the coordinates of the second track points of each road in the second map data set determines the road that matches each lane, and then based on the coordinates of the first track points corresponding to each lane and the coordinates of the first track points corresponding to each lane. The road information corresponding to the roads matched with the lanes is used to generate a fused map dataset, thereby obtaining a fused map dataset that includes both lanes and road information of the road, which enriches the map data. Matching to obtain road information corresponding to the road and lane information for map data fusion, no need to manually collect road information, and no need to manually bind lanes and roads, which not only reduces the difficulty of generating high-precision maps, but also realizes the map road network. The automatic processing of automatic matching and map data fusion improves the efficiency of map generation.

The method, apparatus, electronic device, and storage medium for generating a map provided by the embodiments of the present disclosure will be described in detail below with reference to the accompanying drawings.

FIG. 1 is a schematic flowchart of a method for generating a map according to an embodiment of the present disclosure. As shown in FIG. 1 , the method for generating a map may include the following steps:

Step 101: Obtain a first map data set and a second map data set, wherein the first map data set contains coordinates of each first track point corresponding to each lane, and the second map data set contains each second map data set corresponding to each road. Track point coordinates and road information.

The road information may include, but is not limited to, road names, speed limit information, points of interest (POI), and the like.

In the embodiment of the present disclosure, the first map data set and the second map data set may be maps containing different map information. For example, the first map data set may be a high-precision map that provides lane level information, and the second map data set Can be a navigation map that provides road-level information.

Step 102: Determine a road matching each lane according to the degree of matching between the coordinates of each first track point corresponding to each lane and the coordinates of each second track point corresponding to each road.

In the embodiment of the present disclosure, for each lane in the first map data set, it needs to be matched with the road in the second map data set, according to the coordinates of each first track point corresponding to each lane and the corresponding The matching degree between the coordinates of the second track point to obtain the matching road.

As an example, the matching degree can be represented by the distance between the first trajectory point and the corresponding second trajectory point. The closer the distance is, the higher the matching degree between the first trajectory point and the corresponding second trajectory point is. . The distance between the first trajectory point and the second trajectory point can be obtained by calculating the Euclidean distance according to the coordinates of the first trajectory point and the corresponding coordinates of the second trajectory point. For any lane in the first map data set, after calculating the distance between the coordinates of each first track point corresponding to the lane and the coordinates of each second track point corresponding to each road, it can be determined according to the calculated distance. This lane matches the road. For example, a distance threshold can be preset, and among the coordinates of the second track points corresponding to each road, the distance between the coordinates of the first track points corresponding to the lane is not less than the preset distance threshold. The target second track point The road that contains the most target second trajectory points is determined as the road matching the lane.

As another example, the matching degree can be represented by the transition probability and emission probability of each first trajectory point corresponding to the lane to each road, and determine the transition probability and emission probability of each first trajectory point corresponding to the lane to each road according to the The matching degree between the lane and each road, and then determine the road matching the lane according to the matching degree. It should be noted that this manner will be described in detail in subsequent embodiments, and will not be repeated here.

Step 103: Generate a fused map data set based on the coordinates of each first track point corresponding to each lane and the road information corresponding to the road matching each lane.

In the embodiment of the present disclosure, after the road matching each lane in the first map data set is determined, the road information of the road matching each lane can be obtained from the second map data set, and then based on the first map data set corresponding to each lane The coordinates of the track points and the road information corresponding to the road matched with each lane are stored in association with the coordinates of each first track point corresponding to the lane and the road information corresponding to the road matched with each lane to generate a fused map data set. Therefore, the application based on the fused map dataset can obtain richer map information, including not only the lane-level information, but also the road name, POI, speed limit information, etc.

In the method for generating a map according to the embodiment of the present disclosure, by acquiring a first map data set and a second map data set, the first map data set includes coordinates of each first track point corresponding to each lane, and the second map data set includes each The coordinates and road information of each second track point corresponding to the road, according to the degree of matching between the coordinates of each first track point corresponding to each lane and the coordinates of each second track point corresponding to each road, determine the road that matches each lane , based on the coordinates of each first track point corresponding to each lane and the road information corresponding to the road matching each lane, a fused map data set is generated, thereby obtaining a road information including both lanes and roads. The map dataset is fused to enrich the map data, and the road information corresponding to the road is obtained by matching the lane with the road and the lane information is merged with the map data, without the need to manually collect the road information and manually bind the lane to the road. It not only reduces the difficulty of generating high-precision maps, but also realizes automatic matching of map road networks and automatic processing of map data fusion, which improves the efficiency of map generation.

In a possible implementation manner of the embodiment of the present disclosure, the matching degree may be represented by the transition probability and emission probability of each first trajectory point corresponding to the lane to each road, and by calculating the transition probability matrix and the emission probability matrix of each road, according to The corresponding transition probability matrix and emission probability matrix of each road are used to determine the road matching each lane. This process will be described in detail below in conjunction with FIG. 2 .

FIG. 2 is a schematic flowchart of a method for generating a map according to another embodiment of the present disclosure. As shown in FIG. 2 , on the basis of the embodiment shown in FIG. 1 , step 102 may include the following steps:

Step 201: Acquire a plurality of candidate roads corresponding to any lane and the coordinates of each second track point corresponding to each candidate road from the second map data set.

In the embodiment of the present disclosure, for any lane in the first map data set, a plurality of candidate roads corresponding to the lane may be obtained from the second map data set, and the coordinates of each second track point corresponding to each candidate road may be obtained .

Wherein, when acquiring a plurality of candidate roads corresponding to any lane, the candidate roads can be acquired in different ways, and the following examples are used for description.

As an example, the coordinates of each second track point of each road may be compared with the coordinates of each first track point corresponding to any lane, and the statistics of the coordinates of each second track point corresponding to each road and any lane may be calculated. The number of second track points with the same coordinates of each first track point, and the roads are arranged in descending order of the number, and the first n roads are selected as candidate roads. Among them, n is a positive integer, and the value of n can be preset.

As an example, the distance between the coordinates of each second track point of each road and the coordinates of each first track point corresponding to any lane may be calculated, and for each road, the second track point whose distance reaches a preset distance threshold is calculated. The number of track points accounts for the proportion of the total number of second track points corresponding to the road, and a road whose proportion reaches a preset value is determined as a candidate road.

As an example, a plurality of candidate roads near any lane may be searched from the second map dataset based on the spatial index. Obtaining candidate roads through spatial index can effectively improve the search efficiency of candidate roads.

It should be noted that the above method of obtaining a plurality of candidate roads is only used as an example to explain the present disclosure, and cannot be used as a limitation of the present disclosure, and other solutions that can obtain candidate roads other than the above method should also belong to the content of the present disclosure .

In the embodiment of the present disclosure, after obtaining multiple candidate roads corresponding to any lane from the second map data set, the coordinates of each second track point corresponding to each candidate road may be further obtained from the second map data set.

Step 202: Calculate the transition probability matrix and the emission probability matrix corresponding to each candidate road according to the coordinates of each first trajectory point corresponding to any lane and the coordinates of each second trajectory point corresponding to each candidate road.

In the embodiment of the present disclosure, for each candidate road, the transition probability matrix and the emission probability corresponding to the candidate road may be calculated according to the coordinates of each first trajectory point corresponding to any lane and the coordinates of each second trajectory point corresponding to the candidate road matrix. Among them, each element in the transition probability matrix represents the transition probability from each first trajectory point corresponding to the lane to the candidate road; each element in the emission probability matrix represents each first trajectory point corresponding to the lane to the candidate road emission probability. That is to say, the number of elements of the transition probability matrix and the emission probability matrix is determined by the number of first trajectory points corresponding to any lane.

In a possible implementation manner of the embodiment of the present disclosure, when calculating the transition probability matrix corresponding to each candidate road, each adjacent first trajectory point may be calculated according to the coordinates of each first trajectory point on any lane. Then, according to the coordinates of each second trajectory point corresponding to each candidate road, determine the coordinates of each projection point on each candidate road corresponding to each first trajectory point on any lane. The coordinates of each projection point on each candidate road, determine the length of the second trajectory between every two adjacent projection points on each candidate road, and then according to the length of each first trajectory corresponding to any lane and the corresponding length on each candidate road The ratio between the lengths of the second tracks determines the transition probability matrix corresponding to each candidate road. When calculating the emission probability matrix corresponding to each candidate road, the distance between each first trajectory point on any lane and the corresponding projection point can be determined first, and then according to the distance between each first trajectory point and the corresponding projection point on any lane Distance, determine the Gaussian distribution corresponding to each candidate road, and determine the emission probability matrix corresponding to each candidate road according to the Gaussian distribution corresponding to each candidate road.

The coordinates of each projection point on each candidate road corresponding to each first trajectory point on any lane may be determined according to the coordinates of each second trajectory point corresponding to each candidate road. For each first trajectory point on any lane, draw a vertical line from the first trajectory point to the candidate road. The intersection of the vertical line and the candidate road is the projection point corresponding to the first trajectory point on the candidate road. If The projected point overlaps with a certain second trajectory point of the candidate road, and the coordinates of the second trajectory point are the coordinates of the projected point. If the projected point falls between two second trajectory points, the The coordinates of the two second track points determine the coordinates of the projection point. For example, the mean value of the coordinates of the two second track points can be determined as the coordinates of the projection point, or the coordinates of the second track points that are close to each other can be determined as the coordinates of the projection point. The coordinates are determined to be the coordinates of the projected point, and so on.

It can be understood that each element in the determined transition probability matrix corresponding to each candidate road is the ratio between the length of the first track point and the length of the corresponding second track point. For example, FIG. 3 is an example diagram of the positional relationship between each first trajectory point corresponding to the lane and the candidate road. As shown in Figure 3, point A is the projection point corresponding to the first trajectory point 01, and point B is the projection point corresponding to the first trajectory point 02, then the length of the first trajectory point between 01 and 02 is the same as the difference between A and B. The ratio between the lengths of the second track points between , is an element in the transition probability matrix corresponding to the candidate road R1.

It should be noted that the transition probability can also be represented by curvature, angle, etc. The embodiment of the present disclosure only uses the ratio between the trajectory lengths as the transition probability as an example to explain the present disclosure, rather than limiting the present disclosure.

In the embodiment of the present disclosure, by calculating the first trajectory length between every two adjacent first trajectory points, and calculating the second trajectory length between every adjacent two projected points on each candidate road, according to any lane The ratio between the corresponding first trajectory lengths and the corresponding second trajectory lengths on each candidate road, determine the transition probability matrix corresponding to each candidate road, according to the relationship between each first trajectory point on any lane and the corresponding projection point The distance between each candidate road is determined, and the Gaussian distribution corresponding to each candidate road is determined, and then the emission probability matrix corresponding to each candidate road is determined according to the Gaussian distribution corresponding to each candidate road. The similarity of , uses the emission probability matrix to reflect the proximity between the lane and the candidate road, which provides conditions for determining the road matching the lane according to the transition probability matrix and the emission probability matrix.

Step 203 , according to the transition probability matrix and the emission probability matrix corresponding to each candidate road, determine a target road matching any lane from each candidate road.

As a possible implementation, according to the transition probability matrix and emission probability matrix corresponding to each candidate road, determine the target road matching any lane from each candidate road, including: from the transition probability of each candidate road In the matrix and the emission probability matrix, the first transition probability and the first emission probability corresponding to each first trajectory point are obtained; according to the product of the first transition probability and the first emission probability corresponding to each first trajectory point, each The first similarity value corresponding to the first track point; the second similarity value corresponding to each candidate road is determined according to each first similarity value corresponding to each first track point in each candidate road; the largest second similarity value The corresponding candidate road is determined as the target road.

Wherein, when acquiring the second similarity value corresponding to each candidate road, the first similarity values of the first trajectory points corresponding to the same candidate road may be added to obtain the second similarity value of the candidate road; Among the first similarity values of the first trajectory points corresponding to the same candidate road, the largest first similarity value is determined as the second similarity value of the candidate road, which is not limited in the present disclosure.

By obtaining the first transition probability and the first emission probability corresponding to each first trajectory point from the transition probability matrix and the emission probability matrix of each candidate road, and according to the first transition probability corresponding to each first trajectory point and The product of the first emission probability determines the first similarity value corresponding to each first trajectory point, and determines the first similarity value corresponding to each candidate road according to the first similarity values corresponding to each first trajectory point in each candidate road. Then, the candidate road corresponding to the largest second similarity value is determined as the target road, thereby realizing the automatic matching between the lanes in the first map data set and the roads in the second map data set, and improving the binding efficiency of the road network .

As a possible implementation, according to the transition probability matrix and emission probability matrix corresponding to each candidate road, determine the target road matching any lane from each candidate road, including: according to the transition probability of each candidate road For each transition probability in the matrix, determine the first candidate road corresponding to the maximum transition probability; according to each transmission probability in the transmission probability matrix of each candidate road, determine the second candidate road corresponding to the maximum transmission probability; When the second candidate road is the same, the first candidate road is determined as the target road.

The transition probability indicates the similarity between the lane and the road, and the emission probability indicates the proximity between the lane and the road. The first candidate road determined according to the maximum transition probability is the road most similar to the lane, and the second candidate determined according to the maximum emission probability The road is the road closest to the lane, then when the first candidate road and the second candidate road are the same road, the road is the target road that best matches the lane, thus realizing the automatic binding between the lane and the road , which improves the accuracy of lane-to-road matching.

Further, in a possible implementation manner of the embodiment of the present disclosure, when the first candidate road is different from the second candidate road, a third similarity value corresponding to each first track point is determined, and the third similarity value is The product of the transition probability and the emission probability corresponding to each first trajectory point obtained from the transition probability matrix and the emission probability matrix of the first candidate road; determine the fourth similarity value corresponding to each first trajectory point, the fourth similarity value is the product of the transition probability and the emission probability corresponding to each first trajectory point obtained from the transition probability matrix and the emission probability matrix of the second candidate road; it is determined from each third similarity value and each fourth similarity value. Maximum similarity value; the candidate road corresponding to the maximum similarity value is determined as the target road.

When the first candidate road and the second candidate road are not the same road, calculate the product of the transition probability and the emission probability corresponding to each first trajectory point of the first candidate road to obtain a plurality of third similarity values, and calculate the second The product of the transition probability and the emission probability corresponding to each first trajectory point of the candidate road is obtained to obtain a plurality of fourth similarity values, and then each third similarity value and each fourth similarity value are compared, and the largest similarity value is selected from them. The candidate road corresponding to the value is determined as the target road. Therefore, it is only necessary to calculate the similarity value of the two candidate roads, which reduces the amount of calculation and is beneficial to improve the speed and efficiency of lane-to-road matching.

In the method for generating a map according to the embodiment of the present disclosure, a plurality of candidate roads corresponding to any lane and the coordinates of each second track point corresponding to each candidate road are obtained from the second map data set, according to the first map data set corresponding to any lane. The trajectory point coordinates and the coordinates of each second trajectory point corresponding to each candidate road are calculated, and the transition probability matrix and emission probability matrix corresponding to each candidate road are calculated, and then according to the transition probability matrix and emission probability matrix corresponding to each candidate road, from each candidate road. The target road that matches any lane is determined from the candidate roads, thereby realizing the automatic matching of lanes and roads without manual processing, improving the efficiency of road network matching, and helping to shorten the online cycle of the map.

Since the product lines and coordinate systems used by different map datasets are usually inconsistent, in order to facilitate road network binding and improve the accuracy of road network binding, in a possible implementation manner of the embodiment of the present disclosure, according to The degree of matching between the coordinates of each first track point corresponding to each lane and the coordinates of each second track point corresponding to each road, before determining the road matching each lane, the first map data set and the second map The datasets are migrated to the same coordinate system. By unifying the coordinate system of the first map data set and the second map data set, it is convenient to call data when the subsequent lanes and roads are matched, and it is beneficial to improve the accuracy of the lane-to-road matching.

In order to realize the above embodiments, the present disclosure also provides a map generating apparatus. FIG. 4 is a schematic structural diagram of an apparatus for generating a map according to an embodiment of the present disclosure. As shown in FIG. 4 , the apparatus 40 for generating a map includes an acquiring module 410 , a matching module 420 and a generating module 430 .

The obtaining module 410 is configured to obtain a first map data set and a second map data set, wherein the first map data set includes coordinates of each first track point corresponding to each lane, and the second map data set It includes the coordinates of each second track point corresponding to each road and road information.

In a possible implementation manner of the embodiment of the present disclosure, the first map data set is a high-precision map, and the second map data set is a navigation map.

The matching module 420 is configured to determine a road matching each of the lanes according to the degree of matching between the coordinates of each of the first trajectory points corresponding to each of the lanes and the coordinates of each of the second trajectory points corresponding to each of the roads.

The generating module 430 is configured to generate a fused map data set based on the coordinates of each first track point corresponding to each of the lanes and the road information corresponding to the road matching each of the lanes.

Further, in a possible implementation manner of the embodiment of the present disclosure, as shown in FIG. 5 , on the basis of the embodiment shown in FIG. 4 , the matching module 420 includes:

The obtaining unit 421 is configured to obtain, from the second map data set, a plurality of candidate roads corresponding to any one of the lanes and the coordinates of each second track point corresponding to each of the candidate roads.

The calculation unit 422 is configured to calculate the transition probability matrix corresponding to each candidate road and the emission probability matrix.

In a possible implementation manner of the embodiment of the present disclosure, the calculating unit 422 is specifically configured to: calculate the first trajectory between every two adjacent first trajectory points according to the coordinates of each first trajectory point on any of the lanes length; according to the coordinates of each second trajectory point corresponding to each of the candidate roads, determine the coordinates of each projection point on each candidate road corresponding to each first trajectory point on any of the lanes; according to each The coordinates of each projection point on the candidate road, determine the second trajectory length between every two adjacent projection points on each candidate road; according to the length of each first trajectory corresponding to any lane and each determine the transition probability matrix corresponding to each candidate road; determine the distance between each first trajectory point and the corresponding projection point on the any lane; According to the distance between each first trajectory point and the corresponding projection point on any lane, the Gaussian distribution corresponding to each candidate road is determined; according to the Gaussian distribution corresponding to each candidate road, the corresponding The emission probability matrix of .

The matching unit 423 is configured to determine a target road that matches any of the lanes from the candidate roads according to the transition probability matrix and the emission probability matrix corresponding to each candidate road.

In a possible implementation manner of the embodiment of the present disclosure, the matching unit 423 is specifically configured to: obtain the first transition corresponding to each first trajectory point from the transition probability matrix and the emission probability matrix of each candidate road probability and first emission probability; determine the first similarity value corresponding to each first trajectory point according to the product of the first transition probability corresponding to each first trajectory point and the first emission probability; each first similarity value corresponding to each first trajectory point in the candidate road, to determine the second similarity value corresponding to each candidate road; the candidate road corresponding to the largest second similarity value is determined as the target road .

In a possible implementation manner of the embodiment of the present disclosure, the matching unit 423 is specifically configured to: determine the first candidate road corresponding to the maximum transition probability according to each transition probability in the transition probability matrix of each candidate road; For each emission probability in the emission probability matrix of each candidate road, determine the second candidate road corresponding to the maximum emission probability; if the first candidate road is the same as the second candidate road, the A candidate road is determined as the target road.

Further, in a possible implementation manner of the embodiment of the present disclosure, the matching unit 423 is specifically further configured to: determine each first trajectory when the first candidate road is different from the second candidate road the third similarity value corresponding to the point, where the third similarity value is the product of the transition probability and the emission probability corresponding to each first trajectory point obtained from the transition probability matrix and the emission probability matrix of the first candidate road; determine a fourth similarity value corresponding to each first trajectory point, where the fourth similarity value is a transition probability and emission probability corresponding to each first trajectory point obtained from the transition probability matrix and emission probability matrix of the second candidate road The product of probabilities; the maximum similarity value is determined from each third similarity value and each fourth similarity value; the candidate road corresponding to the maximum similarity value is determined as the target road.

In a possible implementation manner of the embodiment of the present disclosure, as shown in FIG. 6 , on the basis of the embodiment shown in FIG. 4 , the map generating apparatus 40 further includes:

The preprocessing module 400 is configured to migrate the first map data set and the second map data set to the same coordinate system.

It should be noted that, the foregoing explanations of the embodiments of the method for generating a map are also applicable to the apparatus for generating a map in this embodiment, and the implementation principles thereof are similar, which will not be repeated here.

The apparatus for generating a map according to the embodiment of the present disclosure obtains a first map data set and a second map data set, the first map data set includes coordinates of each first track point corresponding to each lane, and the second map data set includes each The coordinates and road information of each second track point corresponding to the road, according to the degree of matching between the coordinates of each first track point corresponding to each lane and the coordinates of each second track point corresponding to each road, determine the road that matches each lane , based on the coordinates of each first track point corresponding to each lane and the road information corresponding to the road matching each lane, a fused map data set is generated, thereby obtaining a road information including both lanes and roads. The map dataset is fused to enrich the map data, and the road information corresponding to the road is obtained by matching the lane with the road and the lane information is merged with the map data, without the need to manually collect the road information and manually bind the lane to the road. It not only reduces the difficulty of generating high-precision maps, but also realizes automatic matching of map road networks and automatic processing of map data fusion, which improves the efficiency of map generation.

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

FIG. 7 shows a schematic block diagram of an example electronic device 700 that may be used to implement embodiments of the present disclosure. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. Electronic devices may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are by way of example only, and are not intended to limit implementations of the disclosure described and/or claimed herein.

As shown in FIG. 7 , the electronic device 700 includes a computing unit 701, which can be loaded into a random access memory (Random Access Memory) according to a computer program stored in a read-only memory (Read-Only Memory, ROM) 702 or from a storage unit 708, A computer program in RAM) 703 to perform various appropriate actions and processes. In the RAM 703, various programs and data required for the operation of the electronic device 700 can also be stored. The computing unit 701, the ROM 702, and the RAM 703 are connected to each other through a bus 704. An Input/Output (I/O) interface 705 is also connected to the bus 704 .

Various components in the electronic device 700 are connected to the I/O interface 705, including: an input unit 706, such as a keyboard, a mouse, etc.; an output unit 707, such as various types of displays, speakers, etc.; a storage unit 708, such as a magnetic disk, an optical disk, etc. etc.; and a communication unit 709, such as a network card, modem, wireless communication transceiver, and the like. The communication unit 709 allows the electronic device 700 to exchange information/data with other devices through a computer network such as the Internet and/or various telecommunication networks.

Computing unit 701 may be various general-purpose and/or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 701 include, but are not limited to, a central processing unit (Central Processing Unit, CPU), a graphics processing unit (Graphic Processing Units, GPU), various dedicated artificial intelligence (Artificial Intelligence, AI) computing chips, various operating A computational unit, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, etc., for the algorithm of the machine learning model. The computing unit 701 executes the various methods and processes described above, such as a map generation method. For example, in some embodiments, the method of generating the map may be implemented as a computer software program tangibly embodied on a machine-readable medium, such as storage unit 708 . In some embodiments, part or all of the computer program may be loaded and/or installed on electronic device 700 via ROM 702 and/or communication unit 709 . When the computer program is loaded into the RAM 703 and executed by the computing unit 701, one or more steps of the map generation method described above may be performed. Alternatively, in other embodiments, the computing unit 701 may be configured to perform the method of generating the map by any other suitable means (eg, by means of firmware).

Various implementations of the systems and techniques described herein above can be implemented in digital electronic circuitry, integrated circuit systems, Field Programmable Gate Arrays (FPGAs), Application-Specific Integrated Circuits (ASICs) , Application Specific Standard Product (ASSP), System On Chip (SOC), Load Programmable Logic Device (CPLD), computer hardware, firmware, software, and/or implemented in their combination. These various embodiments may include being implemented in one or more computer programs executable and/or interpretable on a programmable system including at least one programmable processor that The processor, which may be a special purpose or general-purpose programmable processor, may receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device an output device.

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

In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in connection with the instruction execution system, apparatus or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. Machine-readable media may include, but are not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media would include one or more wire-based electrical connections, portable computer disks, hard disks, random access memory (RAM), read only memory (ROM), erasable programmable read only memory (Electrically Programmable Read-Only-Memory, EPROM) or flash memory, optical fiber, portable compact disk read-only memory (Compact Disc Read-Only Memory, CD-ROM), optical storage device, magnetic storage device, or a combination of the above any suitable combination.

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

The systems and techniques described herein may be implemented on a computing system that includes back-end components (eg, as a data server), or a computing system that includes middleware components (eg, an application server), or a computing system that includes front-end components (eg, a user's computer having a graphical user interface or web browser through which a user may interact with implementations of the systems and techniques described herein), or including such backend components, middleware components, Or any combination of front-end components in a computing system. The components of the system may be interconnected by any form or medium of digital data communication (eg, a communication network). Examples of communication networks include: Local Area Network (LAN), Wide Area Network (WAN), the Internet, and blockchain networks.

A computer system can include clients and servers. Clients and servers are generally remote from each other and usually interact through a communication network. The relationship of client and server arises by computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also known as a cloud computing server or a cloud host. It is a host product in the cloud computing service system to solve the problems existing in traditional physical hosts and VPS services (Virtual Private Server, virtual private server). The management is difficult and the business expansion is weak. The server can also be a server of a distributed system, or a server combined with a blockchain.

In order to implement the above embodiments, the present disclosure also provides a computer program product, including a computer program, which, when executed by a processor, implements the method for generating a map according to the foregoing embodiments.

It should be understood that steps may be reordered, added or deleted using the various forms of flow shown above. For example, the steps described in the present disclosure can be executed in parallel, sequentially, or in different orders. As long as the desired results of the technical solutions disclosed in the present disclosure can be achieved, there is no limitation herein.

The above-mentioned specific embodiments do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may occur depending on design requirements and other factors. Any modifications, equivalent replacements, and improvements made within the spirit and principles of the present disclosure should be included within the protection scope of the present disclosure.

Claims

A method for generating a map, including:

Obtain a first map data set and a second map data set, wherein the first map data set includes coordinates of each first track point corresponding to each lane, and the second map data set includes each first track point corresponding to each road. 2. Track point coordinates and road information;

According to the degree of matching between the coordinates of each first trajectory point corresponding to each of the lanes and the coordinates of each second trajectory point corresponding to each of the roads, determine a road that matches each of the lanes;

Based on the coordinates of each first track point corresponding to each of the lanes, and road information corresponding to the road matching each of the lanes, a fused map dataset is generated.
The method according to claim 1, wherein, according to the degree of matching between the coordinates of each first track point corresponding to each of the lanes and the coordinates of each second track point corresponding to each of the roads, determining the relationship with each lane The lanes match the roads, including:

Obtaining a plurality of candidate roads corresponding to any one of the lanes and the coordinates of each second track point corresponding to each of the candidate roads from the second map data set;

According to the coordinates of each first trajectory point corresponding to any one of the lanes and the coordinates of each second trajectory point corresponding to each of the candidate roads, calculate the transition probability matrix and the emission probability matrix corresponding to each of the candidate roads;

According to the transition probability matrix and the emission probability matrix corresponding to each candidate road, a target road matching any one of the lanes is determined from the candidate roads.
The method according to claim 2, wherein calculating each candidate road according to the coordinates of each first track point corresponding to any one of the lanes and the coordinates of each second track point corresponding to each of the candidate roads The corresponding transition probability matrix and emission probability matrix, including:

According to the coordinates of each first trajectory point on any of the lanes, calculate the first trajectory length between every two adjacent first trajectory points;

According to the coordinates of each second trajectory point corresponding to each of the candidate roads, determine the coordinates of each projection point on each of the candidate roads corresponding to each of the first trajectory points on the any lane;

According to the coordinates of each projection point on each candidate road, determine the second trajectory length between every two adjacent projection points on each candidate road;

determining a transition probability matrix corresponding to each candidate road according to the ratio between each first trajectory length corresponding to any of the lanes and each corresponding second trajectory length on each candidate road;

determining the distance between each first trajectory point on the any lane and the corresponding projection point;

Determine the Gaussian distribution corresponding to each candidate road according to the distance between each first trajectory point and the corresponding projection point on the any lane;

According to the Gaussian distribution corresponding to each candidate road, the emission probability matrix corresponding to each candidate road is determined.
The method according to claim 3, wherein, according to the transition probability matrix and the emission probability matrix corresponding to each of the candidate roads, the target road that matches the any one of the lanes is determined from the candidate roads ,include:

From the transition probability matrix and the emission probability matrix of each of the candidate roads, obtain the first transition probability and the first emission probability corresponding to each first trajectory point;

determining the first similarity value corresponding to each of the first trajectory points according to the product of the first transition probability and the first emission probability corresponding to each of the first trajectory points;

Determine the second similarity value corresponding to each candidate road according to each first similarity value corresponding to each first trajectory point in each candidate road;

The candidate road corresponding to the largest second similarity value is determined as the target road.
The method according to claim 3, wherein, according to the transition probability matrix and the emission probability matrix corresponding to each of the candidate roads, the target road that matches the any one of the lanes is determined from the candidate roads ,include:

According to each transition probability in the transition probability matrix of each candidate road, determine the first candidate road corresponding to the maximum transition probability;

According to each emission probability in the emission probability matrix of each candidate road, determine the second candidate road corresponding to the maximum emission probability;

When the first candidate road is the same as the second candidate road, the first candidate road is determined as the target road.
The method of claim 5, further comprising:

In the case where the first candidate road is different from the second candidate road, determine a third similarity value corresponding to each first track point, where the third similarity value is a transition probability from the first candidate road the product of the transition probability and the emission probability corresponding to each first trajectory point obtained in the matrix and the emission probability matrix;

Determine a fourth similarity value corresponding to each first trajectory point, where the fourth similarity value is obtained from the transition probability matrix and the emission probability matrix of the second candidate road corresponding to the transition probability of each first trajectory point and product of emission probabilities;

determining the maximum similarity value from each third similarity value and each fourth similarity value;

The candidate road corresponding to the maximum similarity value is determined as the target road.
The method according to any one of claims 1-6, wherein, according to the matching between the coordinates of each first track point corresponding to each of the lanes and the coordinates of each second track point corresponding to each of the roads degrees, before determining which road matches each of said lanes, also includes:

Migrating the first map dataset and the second map dataset into the same coordinate system.
The method according to any one of claims 1-6, wherein the first map data set is a high-precision map, and the second map data set is a navigation map.
A map generating device, comprising:

The acquisition module is used to acquire a first map data set and a second map data set, wherein the first map data set contains coordinates of each first track point corresponding to each lane, and the second map data set contains each Coordinates and road information of each second track point corresponding to the road;

a matching module, configured to determine a road matching each of the lanes according to the degree of matching between the coordinates of each first trajectory point corresponding to each of the lanes and the coordinates of each of the second trajectory points corresponding to each of the roads;

The generating module is configured to generate a fused map data set based on the coordinates of each first track point corresponding to each of the lanes and the road information corresponding to the road matched with each of the lanes.
The apparatus of claim 9, wherein the matching module comprises:

an obtaining unit, configured to obtain a plurality of candidate roads corresponding to any one of the lanes and the coordinates of each second track point corresponding to each of the candidate roads from the second map data set;

A calculation unit, configured to calculate the transition probability matrix and the emission probability corresponding to each candidate road according to the coordinates of each first trajectory point corresponding to any of the lanes and the coordinates of each second trajectory point corresponding to each of the candidate roads matrix;

A matching unit, configured to determine a target road matching any of the lanes from the candidate roads according to the transition probability matrix and the emission probability matrix corresponding to each candidate road.
The apparatus of claim 10, wherein the computing unit is specifically used for:

Calculate the length of the first track between every two adjacent first track points according to the coordinates of each first track point on any of the lanes;

According to the coordinates of each second trajectory point corresponding to each of the candidate roads, determine the coordinates of each projection point on each of the candidate roads corresponding to each of the first trajectory points on the any lane;

According to the coordinates of each projection point on each candidate road, determine the second trajectory length between every two adjacent projection points on each candidate road;

determining a transition probability matrix corresponding to each candidate road according to the ratio between each first trajectory length corresponding to any of the lanes and each corresponding second trajectory length on each candidate road;

determining the distance between each first trajectory point on the any lane and the corresponding projection point;

Determine the Gaussian distribution corresponding to each candidate road according to the distance between each first trajectory point and the corresponding projection point on the any lane;

According to the Gaussian distribution corresponding to each candidate road, the emission probability matrix corresponding to each candidate road is determined.
The device of claim 11, wherein the matching unit is specifically used for:

From the transition probability matrix and the emission probability matrix of each of the candidate roads, obtain the first transition probability and the first emission probability corresponding to each first trajectory point;

determining the first similarity value corresponding to each of the first trajectory points according to the product of the first transition probability and the first emission probability corresponding to each of the first trajectory points;

Determine the second similarity value corresponding to each candidate road according to each first similarity value corresponding to each first trajectory point in each candidate road;

The candidate road corresponding to the largest second similarity value is determined as the target road.
The device according to claim 11, wherein the matching unit is specifically used for:

According to each transition probability in the transition probability matrix of each candidate road, determine the first candidate road corresponding to the maximum transition probability;

According to each emission probability in the emission probability matrix of each candidate road, determine the second candidate road corresponding to the maximum emission probability;

When the first candidate road is the same as the second candidate road, the first candidate road is determined as the target road.
The device according to claim 13, wherein the matching unit is further used for:

In the case where the first candidate road is different from the second candidate road, determine a third similarity value corresponding to each first track point, where the third similarity value is a transition probability from the first candidate road the product of the transition probability and the emission probability corresponding to each first trajectory point obtained in the matrix and the emission probability matrix;

Determine a fourth similarity value corresponding to each first trajectory point, where the fourth similarity value is obtained from the transition probability matrix and the emission probability matrix of the second candidate road corresponding to the transition probability of each first trajectory point and product of emission probabilities;

determining the maximum similarity value from each third similarity value and each fourth similarity value;

The candidate road corresponding to the maximum similarity value is determined as the target road.
The apparatus of any one of claims 9-14, further comprising:

A preprocessing module, configured to migrate the first map data set and the second map data set to the same coordinate system.
The apparatus according to any one of claims 9-14, wherein the first map data set is a high-precision map, and the second map data set is a navigation map.
An electronic device comprising:

at least one processor; and

a memory communicatively coupled to the at least one processor; wherein,

The memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the execution of any of claims 1-8 how to generate the map described.
A non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to cause the computer to perform the method for generating a map according to any one of claims 1-8.
A computer program product comprising a computer program which, when executed by a processor, implements the method for generating a map according to any one of claims 1-8.