CN115757674A

CN115757674A - Map processing method, map processing device, map processing equipment and storage medium

Info

Publication number: CN115757674A
Application number: CN202211493588.XA
Authority: CN
Inventors: 李旭红; 李福樑
Original assignee: Apollo Intelligent Connectivity Beijing Technology Co Ltd; Apollo Zhixing Technology Guangzhou Co Ltd
Current assignee: Apollo Intelligent Connectivity Beijing Technology Co Ltd; Apollo Zhixing Technology Guangzhou Co Ltd
Priority date: 2022-11-25
Filing date: 2022-11-25
Publication date: 2023-03-07

Abstract

The present disclosure provides a map processing method, apparatus, device and storage medium, which relate to the technical field of artificial intelligence, and in particular to the technical fields of intelligent transportation, smart cities, traffic simulation, traffic digital management, and the like. The specific implementation scheme is as follows: the method comprises the steps of establishing a mapping relation between map elements in a first map and a second map, wherein the precision of the first map is higher than that of the second map, integrating map data corresponding to the map elements with the mapping relation in the first map and the second map according to a preset semantic road network protocol to obtain a target map, wherein the preset semantic road network protocol corresponds to at least two spatial scales, each spatial scale corresponds to at least one preset map layer, and an incidence relation exists between different preset map layers. By adopting the technical scheme, the map meeting the requirement of the preset semantic road network protocol is quickly generated on the basis of considering the drawing cost, and the consistency of the calculation results of different spatial scales is kept.

Description

Map processing method, map processing device, map processing equipment and storage medium

Technical Field

The present disclosure relates to the field of artificial intelligence technology, and more particularly to the field of intelligent transportation, smart cities, traffic simulation, and traffic digital management.

Background

In the urban traffic industry, road network data is the basis of various systems such as intelligent traffic management systems and traffic simulation systems.

At present, the road network data of each system mainly comes from developed and mature maps, such as navigation maps or high-precision maps, or maps constructed in a manual hand-drawing manner, and relevant processing such as traffic perception, model calculation, traffic deduction and the like can be performed by using the adopted maps.

Disclosure of Invention

The disclosure provides a map processing method, a map processing device, a map processing apparatus and a storage medium.

According to an aspect of the present disclosure, there is provided a map processing method including:

establishing a mapping relation between map elements in a first map and a second map, wherein the precision of the first map is higher than that of the second map;

and integrating map data corresponding to map elements with the mapping relationship in the first map and the second map according to a preset semantic road network protocol to obtain a target map meeting the requirement of the preset semantic road network protocol, wherein the preset semantic road network protocol corresponds to at least two spatial scales, each spatial scale corresponds to at least one preset map layer, and an association relationship exists between different preset map layers.

According to another aspect of the present disclosure, there is provided a map processing apparatus including:

the map relation establishing module is used for establishing a map relation of map elements in a first map and a second map, wherein the precision of the first map is higher than that of the second map;

and the data integration module is used for integrating the map data corresponding to the map elements with the mapping relation in the first map and the second map according to a preset semantic road network protocol to obtain a target map meeting the requirements of the preset semantic road network protocol, wherein the preset semantic road network protocol corresponds to at least two spatial scales, each spatial scale corresponds to at least one preset map layer, and an association relation exists between different preset map layers.

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

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 to cause the at least one processor to perform the method of the embodiments of the present disclosure.

According to another aspect of the present disclosure, there is provided a non-transitory computer readable storage medium having stored thereon computer instructions for causing the computer to perform the method of the embodiments of the present disclosure.

According to another aspect of the present disclosure, a computer program product is provided, comprising a computer program which, when executed by a processor, implements the method of any of the embodiments of the present disclosure.

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

Drawings

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

FIG. 1 is a flow chart of a map processing method provided in accordance with an embodiment of the present disclosure;

FIG. 2 is a schematic diagram of a visual display interface provided in accordance with an embodiment of the present disclosure;

fig. 3 is a macro scale schematic provided in accordance with an embodiment of the present disclosure;

FIG. 4 is a schematic view of a mesoscale provided in accordance with an embodiment of the present disclosure;

FIG. 5 is a micro-scale schematic provided in accordance with an embodiment of the present disclosure;

FIG. 6 is a flow chart of yet another map processing method provided in accordance with an embodiment of the present disclosure;

FIG. 7 is a flow chart diagram of a line element matching process provided according to an embodiment of the present disclosure;

FIG. 8 is a flow chart of another map processing method provided in accordance with an embodiment of the present disclosure;

FIG. 9 is a schematic structural diagram of a map processing apparatus provided in accordance with an embodiment of the present disclosure;

fig. 10 is a block diagram of an electronic device for implementing a map processing method according to an embodiment of the present disclosure.

Detailed Description

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

Fig. 1 is a flowchart of a map processing method according to an embodiment of the present disclosure, which is applicable to a case of constructing a map across spatial scales, where the constructed map may be applied to various systems in the urban Transportation industry, such as an intelligent traffic management system, traffic simulation systems with various spatial scales, an urban signal lamp control system, an urban traffic brain, an urban twin traffic system, and a traffic operation monitoring and scheduling Center (TOCC). The method can be executed by a map processing apparatus, which can be implemented by hardware and/or software and can be configured in an electronic device. Referring to fig. 1, the method specifically includes the following steps:

s101, establishing a mapping relation between map elements in a first map and map elements in a second map, wherein the precision of the first map is higher than that of the second map;

s102, according to a preset semantic road network protocol, integrating map data corresponding to map elements with the mapping relation in the first map and the second map to obtain a target map meeting the requirement of the preset semantic road network protocol, wherein the preset semantic road network protocol corresponds to at least two spatial scales, each spatial scale corresponds to at least one preset map layer, and an association relation exists between different preset map layers.

The first map and the second map may be existing maps with different accuracies, for example, the first map may be a high-accuracy map, and the second map may be a navigation map. The high-precision map is also called a high-precision map, can be understood as a high-precision and fine defined map, the precision of the high-precision map can generally reach the purpose of distinguishing each lane, various traffic elements in a traffic scene are stored according to the specified protocol in a standardized manner, the high-precision map can be applied to automatic driving, the high-precision map comprises the geometric linear aspects of longitudinal slopes, transverse slopes, curvature and the like of roads and the fine traffic semantic level, but the high-precision map lacks information related to the road level with large scale. The navigation map can also be called as a traditional map, the precision of the navigation map generally reflects the elements of important intersections, main roads and other levels, the connectivity of the road is emphasized, the geometric linear aspects such as longitudinal slopes, transverse slopes and curvatures of the road and the fine traffic semantic level are lacked, the traffic semantics are few, and more road detail information and other related traffic elements are lacked.

For various systems in the urban traffic industry, maps with different levels of detail are often used according to different application scenarios. For example, an application scene focusing on a city-level road running situation requires a map which is similar to a navigation map and embodies the road space scale of elements such as important intersections and main roads; for another example, a lane-level spatial scale high-precision map is needed for application scenes such as urban traffic light management, lane construction, road equipment facility management and maintenance, road traffic restrictions and the like; for another example, in an application scenario for deducing a traffic congestion state, the traffic congestion state of an urban road network needs to be perceived and predicted from a macroscopic perspective, and a more detailed traffic state deduction needs to be performed on perceived key roads and intersections from a microscopic perspective, so that an all-around data support is provided for a traffic control decision. At present, each system adopts a navigation map to perform corresponding calculation on a macro scale, adopts a high-precision map to perform corresponding calculation on a micro scale, is independent from the macro scale to the micro scale, and cannot form effective linkage, so that deduction conclusions obtained from different scales are often contradictory, the deduction conclusions are difficult to be reasonably applied, and the application of the corresponding system is influenced.

In the embodiment of the disclosure, in order to support different application scenarios of each system in the urban traffic industry, a set of road network protocols capable of facing traffic management is constructed, that is, the preset semantic road network protocol in the embodiment of the disclosure. The preset semantic road network protocol can be understood as a preset description protocol for describing traffic information with different spatial scales, the preset semantic road network protocol corresponds to at least two spatial scales (also can be understood as spatial resolution), each spatial scale corresponds to at least one preset map layer, the preset map layer can be understood as a preset map layer, and data such as spatial geometric information, road topological information, traffic semantic information and the like can be stored in the preset map layer. The correlation relationship exists between different preset layers, so that in the process of performing correlation calculation on the basis of the map meeting the preset semantic road network protocol, data contents in the corresponding preset layers can be acquired according to a required spatial scale to participate in calculation, and the data contents in the related preset layers are acquired according to the correlation relationship between the preset layers to participate in auxiliary calculation, that is, the data contents in the different preset layers can be shared and can be converted with each other during calculation, instead of using two sets of independent maps such as a traditional map and a high-precision map to separately calculate in the related art, the traffic objects with different spatial scales are described by using the idea of data layering, and the traffic objects with different spatial scales are correlated in the same set of map, so that lossless data and smooth state transition of mutual conversion in the calculation process aiming at different spatial scales are facilitated.

Illustratively, in the process of constructing the target map meeting the requirements of the preset semantic road network protocol, the unified traffic semantic map meeting the requirements of the preset semantic road network protocol can be quickly generated by using the data in the existing maps with different accuracies, so as to obtain the target map applied to each system in the traffic management industry, and effectively save the drawing cost. Specifically, a mapping relationship of map elements in the first map and the second map may be established. The map elements may include geometric elements such as point elements and line elements, and are used to describe different types of road information, such as intersections and roads. The mapping relationship may include a mapping relationship of a point element in the first map and a point element in the second map, and may further include a mapping relationship of a line element in the first map and a line element in the second map. The establishing method of the mapping relationship is not limited, and for example, the mapping relationship may be established by matching based on the geometric relationship and/or name similarity between map elements, and matching successfully matched map elements.

In the embodiment of the disclosure, after the mapping relationship of the map elements is established, according to a preset semantic road network protocol, map data corresponding to the map elements having the mapping relationship in the first map and the second map are integrated to obtain a target map meeting the requirement of the preset semantic road network protocol. The specific format of the target map is not limited, and may be json format, for example. For example, each preset map layer in the preset semantic road network protocol may include a plurality of fields, where different fields are used to describe different traffic information, and the description of the traffic information may be understood as traffic semantics, and corresponding map data may be obtained from the first map and the second map according to the meaning of the fields and filled in the corresponding fields, so as to obtain the target map.

According to the technical scheme provided by the embodiment of the disclosure, the mapping relation between map elements in a first map and a second map is established, wherein the precision of the first map is higher than that of the second map, and according to a preset semantic road network protocol, map data corresponding to the map elements with the mapping relation in the first map and the second map are integrated to obtain a target map meeting the requirement of the preset semantic road network protocol, wherein the preset semantic road network protocol corresponds to at least two spatial scales, each spatial scale corresponds to at least one preset map layer, and an association relation exists between different preset map layers. By adopting the technical scheme, the unified target map which meets the requirements of the preset semantic road network protocol and can be applied to each system in the traffic management industry is quickly generated by utilizing the data in the existing maps with different accuracies, the drawing cost is effectively saved, the preset semantic road network protocol adopts the map description idea of data layering, so that the calculation capability of different spatial scales is realized in the process of performing related calculation based on the obtained target map, and the information in different layers can be shared and mutually converted due to the fact that the calculation is performed by depending on the same set of map, so that the calculation results of different spatial scales can be kept consistent.

In an alternative embodiment said predetermined semantic road network protocols correspond to at least three spatial scales, said at least three spatial scales comprising a macro scale, at least one meso scale and a micro scale. The method has the advantages that more spatial scales are set, and smooth conversion among data of different spatial scales is facilitated while richer application scenes are met.

In an alternative embodiment, the macro scale includes road intersections and roads; the mesoscopic scale comprises road breaking points and road sections, the road breaking points are used for representing the number of lanes and/or the positions of lane lines in the same road, and the road sections take the road intersections and/or the road breaking points as end points; the microscopic scale includes a lane. The advantage of such an arrangement is that traffic objects contained in different spatial scales are reasonably divided, and at the same time, existing navigation map data and high-precision map data can be better compatible.

For example, point elements in map elements can be regarded as nodes, and the nodes are divided into two types, one type is a road intersection, and the other type is a road breaking point, and the nodes belong to different preset map layers. A road intersection can be understood as a physical intersection (junction), which is a road bifurcation point and has an area for traffic flow exchange; a road break point (zipper) may be understood as a non-physical intersection where there is a change in the number of lanes and/or lane lines and there is no interchange of traffic flow in conflicting directions. Optionally, in order to embody more detailed traffic information, the road breaking point may be determined according to a preset road breaking rule. The preset road breaking rules may include, for example: the position where the number of the lanes changes is broken; there is an advance right turn break; breaking the pedestrian zebra crossing in the middle of the road; the confluence and diversion positions of the main road and the auxiliary road of the road and the ramp are broken; the turning part in the middle of the road is broken; and the broken line of the lane in the preset range of the road intersection is changed into the broken line of the lane in the solid line, and the like.

Illustratively, a road (road) on a macro scale is located between intersections, i.e., the two endpoints that are the start and end of the road are intersections, and the road typically contains no detail. The road is broken into a plurality of sections according to a preset road breaking rule, each section can be called a road section (roadseg) and belongs to a mesoscopic scale, and the end points of the road sections can be a road intersection and a road breaking point or can be road breaking points. The road and the road section can have a plurality of lanes (lane) which can embody the road details and belong to the microscale, and in addition, the lane lines in the road intersection and the road breaking point also belong to the microscale.

For example, the storing the related information of each object included in each spatial scale in different preset layers may include: the map comprises a road intersection map layer, a road breaking point map layer, a macroscopic road map layer, a road section line map layer and a lane line map layer.

Optionally, on the basis of the above objects, more objects may be set to describe the traffic information more comprehensively. For example, a portion where a road inside a road intersection is linked with a road may be referred to as a road connector (roadConnector), corresponding to a road connector layer; the link part between the road segment inside the road breaking point and the road segment can be called a road segment connector (roadsegConnector), and corresponds to the road segment connector map layer; inside the intersection and the road break point, the linked part between the lanes may be called a lane connector (laneConnector), and corresponds to the lane connector layer.

Optionally, the preset semantic road network protocol may also support visual display, may include point objects on the road surface, such as street lamps, signs, and the like, may store corresponding three-dimensional model data in a corresponding preset layer (such as a layer marked as a road point object layer), and may be loaded when visualization is to be performed. For the preset layers each including the point object and the line object, corresponding preset layers including a surface object may be respectively set, and relevant data required for visual rendering may be stored in the preset layers, for example, the data may be respectively recorded as a road intersection surface layer, a road break point surface layer, a macro road surface layer, a lane surface layer, a road connector surface layer, a lane connector surface layer, and a road surface object (such as an object to which a texture needs to be added) layer.

As an example, the following may be understood with reference to fig. 2 to 5, taking a road intersection as an example. Fig. 2 is a schematic diagram of a visual display interface provided according to an embodiment of the present disclosure, where detailed information of the intersection, specifically, a visual display of a high-precision map, may be displayed in a page; fig. 3 is a macro scale schematic diagram provided in accordance with an embodiment of the present disclosure, and fig. 3 shows a representation of a road intersection at a road-level spatial scale, including road intersections in the form of points and roads in the form of lines; fig. 4 is a schematic view of a mesoscale provided according to an embodiment of the present disclosure, and fig. 4 shows an expression form of a road intersection at a road segment scale, including a road intersection in the form of a point, a road breaking point and a road segment in the form of a line; fig. 5 is a schematic diagram at a microscopic scale provided according to an embodiment of the present disclosure, and fig. 5 shows a representation form of the intersection at a lane-level spatial scale, including the intersection and the road breaking point in the form of points and the lane in the form of lines.

In an optional implementation manner, a data structure corresponding to the preset map layer includes a field for representing a static traffic semantic and/or a dynamic traffic semantic. The method has the advantages that the target map can contain richer traffic semantic information, and different application requirements in the system are supported.

For example, the static traffic semantics may be understood as semantic information of a traffic object whose change frequency is lower than a first preset frequency, where the first preset frequency may be, for example, once a year, that is, a traffic object that cannot be easily changed, such as a road, a road section, a central point of a road intersection, and the like; the dynamic traffic semantics can be understood as semantic information of a traffic object with a change frequency higher than a second preset frequency, where the second preset frequency is generally lower than the first preset frequency, and may be, for example, once a day or once a month, and the like, that is, the traffic object is easy to change, such as a change of an arrow, such as a left turn of a road, a speed limit, a guideboard for issuing information, a traffic direction of a lane in different time periods, and the like.

For example, the predetermined semantic network protocol may include 18 predetermined layers, and an alternative embodiment of the layer names, meanings, and included fields may be as shown in table 1 below.

Table 1 preset map layers in a preset semantic network protocol

For example, the preset semantic network protocol can support the related calculation of the urban road network traffic model and the visualization of a front-end webpage (web), and can also support the editing requirement of the road visualization. For example, a modification operation of a user based on a surface layer is received in a visualization page, and then data in a corresponding layer is modified according to an association relationship between the surface layer and a line graph layer and a point graph layer.

Fig. 6 is a flowchart of another map processing method provided according to an embodiment of the present disclosure, and this embodiment proposes an alternative scheme based on the foregoing optional embodiments, and further describes the establishment of the mapping relationship. Referring to fig. 6, the method includes:

s601, converting the first map and the second map into the same preset coordinate system.

For example, the first map and the second map may be uniformly converted into a GWS84 coordinate System or a WGS coordinate System, specifically, a geocentric coordinate System, a rectangular spatial coordinate System, and a coordinate System adopted by a Global Positioning System (GPS), in which an origin coincides with a centroid of the earth.

S602, establishing a first mapping relation of point elements based on the distance relation of the point elements in the first map and the second map in a preset coordinate system.

The map elements include point elements including intersections and line elements including roads and road segments.

For example, the meaning of the point element in the two map elements is relatively clear, and the point element may be matched first to establish the mapping relationship of the point element. Taking the coordinates of the central point of the intersection in the first map as the center, taking a preset length (the specific numerical value is not limited, such as 10-20 meters) as the radius to make a circle outwards, judging whether the coordinates of the central point of each intersection in the second map fall into the circle, and if so, establishing a mapping relation between the intersection in the first map and the intersection to which the coordinates of the central point of the intersection falling into the circle belong.

Specifically, the method comprises the steps of traversing a road intersection h in the high-precision map, generating a circle by taking a center point of the road intersection h as a circle center and a radius R, traversing a road intersection l in the traditional map, and if l is in the circle, aligning the road intersection h and the road intersection l to form a first mapping relation.

S603, determining whether the end points of the line elements are matched based on the first mapping relation for the line elements in the first map and the second map, and establishing a second mapping relation of the line elements according to the determination result.

Illustratively, the basic structure of an urban road network is points and lines, and the starting point and the ending point of each road route are definite road intersections, so that the mapping relationship of line elements can be constructed by comparing whether the starting point and the ending point of two roads are the same or not.

In an alternative embodiment, S603 may specifically include: for a first line element in the second map, searching a target line element with a first mapping relation at a starting point and/or an end point in the first map; determining the target line element and the line elements in the second map, which have a capping relationship and/or a communicating relationship with the target line element, as second line elements; establishing a second mapping relationship of the first line element and the second line element. The advantage of this arrangement is that line elements with corresponding relationships can be found comprehensively.

For example, a start point and an end point corresponding to a first line element in a second map may be determined according to a capping relationship and/or attribute information in the second map, then each element to be matched in the first map is traversed, a start point and an end point corresponding to the element to be matched are determined according to the capping relationship and/or attribute information in the second map, whether a first mapping relationship exists between the start point corresponding to the first line element and the start point corresponding to the element to be matched, and whether a first mapping relationship exists between the end point corresponding to the first line element and the end point corresponding to the element to be matched, if the first mapping relationship exists, the start points may be the same or the end points may be the same, because the first map and the second map may have different defining manners for roads, for example, there are XX roads in the conventional map, the start point and the end point are intersection a and B, while there are XX roads and XX south roads in the high-precision map, the start point of the XX road is the north road, the start point of the XX road is the intersection 1, the south road, the intersection is 2, the XX road and the intersection, and the intersection may have a mapping relationship between the first and the second intersection, and the intersection corresponding to the first intersection B. In addition, if an XX middle road between an XX north road and an XX south road exists in the high-precision map, a second mapping relationship between the XX road and the XX middle road may also be established, so that a line element to be matched, of which a point and/or an end point has a first mapping relationship, is marked as a target line element, and the target line element and a line element in the second map, of which a capping relationship and a communicating relationship exist with the target line element, are determined as second line elements and are used for establishing a second mapping relationship with the first line elements.

In the electronic map, the capping relationship between roads may be a level crossing road (called a level crossing road for short), where the level crossing road refers to two actually crossing roads, and the crossing position is a start point or an end point, so that the start point and the end point of a road may be determined by the capping relationship, and whether the roads are communicated or not may also be determined. Further, in the electronic map, it is also possible to record attribute information of map elements such as a connection attribute of a point element and a line element, a connection attribute between line elements, and the like, and it is possible to determine a start point and an end point of a line element, and whether or not the line elements are connected based on the attribute information.

Specifically, S603 may include: for a first line element in the second map, determining whether a starting point and an end point of a first line element to be determined in the first map have the first mapping relation with the first line element; determining the first line element to be determined as a second line element if the starting point of the first line element to be determined and the first line element have the first mapping relationship and the end point of the first line element to be determined and the first mapping relationship; if the starting point of the first line element to be determined and the first line element have the first mapping relationship, but the end point of the first line element to be determined and the end point of the first line element do not have the first mapping relationship, searching a second line element to be determined, which has a capping relationship and/or a communicating relationship with the first line element to be determined, if the end point of the second line element to be determined and the end point of the first line element have the first mapping relationship, determining the first line element to be determined and the second line element to be determined as target line elements, and determining the target line element and the line element in the second map, which has the capping relationship and/or the communicating relationship with the target line element, as second line elements; if the starting point of the first line element to be determined does not have the first mapping relationship with the first line element, but the end point of the first line element to be determined does have the first mapping relationship with the end point of the first line element, searching a third line element to be determined, which has a capping relationship and/or a communicating relationship with the first line element, if the starting point of the third line element to be determined has the first mapping relationship with the first line element, determining the first line element to be determined and the third line element to be determined as target line elements, and determining the target line element and the line element in the second map, which has the capping relationship and/or the communicating relationship with the target line element, as second line elements; a second mapping relationship of the first line element and the second line element is established. The method has the advantages that the next line element to be judged can be quickly found according to the connection attribute of the line elements in the first map, and the mapping relation between a certain line element in the second map and a plurality of line elements in the first map is further established.

Fig. 7 is a schematic flow chart of a line element matching process according to an embodiment of the present disclosure, and as shown in fig. 7, a line element j of a conventional map is traversed, start-stop intersections of the line element j are determined according to a capping relationship and/or attribute information and are respectively denoted as t _ s and t _ e, then a line element i in a high-precision map is traversed, and start-stop intersections of the line element i are determined according to the capping relationship and/or attribute information and are respectively denoted as h _ s and h _ e. If t _ s and h _ s have a first mapping relationship and t _ e and h _ e have the first mapping relationship, i.e., t _ s = h _ s and t _ e = h _ e, the line j and the line i are paired, i.e., a second mapping relationship is established. If t _ s = h _ s, t _ e! H _ e (there is no first mapping relationship between t _ e and h _ e), finding subsequent line object i + n (n is a positive integer greater than or equal to 1, and n takes a value of 1 when first determined) according to the capping relationship and/or attribute information (specifically, connectivity attribute of line element) of line i, determining the end intersection of i + n, and marking as h _ e _ i + n, if t _ e = h _ e _ i + n, establishing a second mapping relationship between line j and line i to line i + n, if t _ e = |)! h _ e _ i + n, adding the current line i + n into the intermediate line set hn, increasing n incrementally, namely continuously searching the next subsequent line element according to the gland relation and/or the attribute information on the basis of the current line i + n, namely re-determining the line i + n until finding the line i + n with the first mapping relation at the terminal intersection, and pairing the line j with the line i, the line elements in the intermediate line set hn and the last line i + n. If t _ s! If = h _ s, t _ e = h _ e, finding a predecessor line object i-m (m is a positive integer greater than or equal to 1, and m takes a value of 1 when first determined) according to the capping relationship and/or attribute information (specifically, connectivity attribute of a line element) of the line i, determining an intersection of the starting point of the line object i-m, and marking as h _ s _ i-m, if t _ s = h _ s _ i-m, establishing a second mapping relationship between the line j and a line object set composed of the line i to the line i-m, and if t _ s! = h _ s _ i-m, the current line i-m is added to the set of intermediate lines hm, and m is incremented, and so on. If t _ s! = h _ s, t _ e! And if h _ e is not reached, finding a new line object i in the high-precision map until the traversal is finished.

In an optional implementation, the establishing the second mapping relationship between the first line element and the second line element may specifically include: establishing an initial mapping relationship of the first line element and the second line element; and verifying the initial mapping relation based on a preset verification strategy, and determining the verified initial mapping relation as a second mapping relation of the line element. The method has the advantages that some line element pairs with mismatching conditions can be filtered out in a mode of verifying the initial mapping relation, and the accuracy of data in the target map is guaranteed.

In an optional implementation manner, the verifying the initial mapping relationship based on a preset verification policy, and determining the verified initial mapping relationship as the second mapping relationship of the line element includes: and for the line element pair with the initial mapping relation, determining whether a preset verification index is successfully matched, if so, determining that the line element pair passes the verification, and determining the verified initial mapping relation as a second mapping relation of the line element, wherein the preset verification index comprises at least one of the length of the line element, the distance of the line element, the azimuth angle of the line element and the name of the line element. The method has the advantages that line element pairs with mismatching conditions can be accurately filtered, and the accuracy of data in the target map is further ensured.

For example, if the matching is not successful, it is determined that the line element is not verified, and the initial mapping relationship which is not verified is not the second mapping relationship of the line element.

For example, for the length of the line element, it may be determined whether a length difference and/or a length difference ratio of the line element pair having the second mapping relationship is smaller than a preset threshold, and if so, the verification is considered to be passed.

For example, as to the distance of the line element, it may be determined whether a distance value of the line element pair having the second mapping relation is smaller than a preset distance threshold, and if so, the verification is considered to be passed, where a calculation manner of the distance value is not specifically limited, and may be, for example, a bidirectional huffman (Hausdorff) distance H (a, B).

For example, for the azimuth angle of the line element, it may be determined whether a difference between the azimuth angles of the line element pair having the second mapping relation is smaller than a preset angle threshold, and if so, the verification is considered to be passed. The azimuth angle may be a course angle or a road direction, and the road direction is divided into: the eight directions of east, south, west, north, southeast, southwest, northeast and northwest. The course angle is the included angle between the road route and the true north direction. If the angle error range of the two lines is within plus or minus 5 degrees, the course angles are considered to be the same, and the verification is passed.

For example, for the names of the line elements, fuzzy matching may be performed on the names of the line element pairs having the second mapping relationship in a text analysis manner, and if matching is successful, the verification is considered to be passed.

S604, according to a preset semantic road network protocol, integrating map data corresponding to map elements with a first mapping relation and a second mapping relation in the first map and the second map to obtain a target map meeting the requirement of the preset semantic road network protocol.

The preset semantic road network protocol corresponds to at least three spatial scales, the at least three spatial scales comprise a macro scale, at least one mesoscopic scale and a micro scale, each spatial scale corresponds to at least one preset layer, and incidence relations exist between different preset layers.

The map processing method provided by the embodiment of the disclosure converts the existing maps with different accuracies into the same coordinate system, establishes the first mapping relationship of the intersection of the middle road of the point element, and further establishes the second mapping relationship of the road in the line element based on the first mapping relationship, so as to accurately associate the map elements in the first map and the second map, and further accurately fill the map data with the mapping relationship into the preset semantic road network protocol, so as to quickly and accurately generate the target map meeting the requirements of the preset semantic road network protocol, further improve the accuracy of the target map, and further support the application of each system in the urban traffic industry better.

Fig. 8 is a flowchart of another map processing method according to an embodiment of the present disclosure, and this embodiment provides an alternative scheme based on the foregoing optional embodiments, and further describes an integration process of map data.

Referring to fig. 8, the method includes:

s801, converting the first map and the second map into the same preset coordinate system.

S802, establishing a first mapping relation of point elements based on the distance relation of the point elements in the first map and the second map in a preset coordinate system.

And S803, for the first line element in the second map, searching a target line element with a first mapping relation between the starting point and/or the end point from the first map.

S804, determining the target line element and the line elements in the second map, which have a covering relationship and/or a communicating relationship with the target line element, as second line elements.

S805, establishing an initial mapping relation of the first line element and the second line element.

S806, for the line element pair with the initial mapping relation, determining whether the preset verification index is successfully matched, if so, determining that the line element pair passes the verification, and determining the initial mapping relation passing the verification as a second mapping relation of the line element pair.

S807, fields to be filled in the preset semantic network protocol are determined, and map data corresponding to the fields to be filled, of the map elements with the mapping relation, are obtained from the first map and the second map.

For example, the fields to be filled in the preset semantic network protocol may refer to the relevant contents in table 1. Specifically, the corresponding relationship between each field to be filled and the first field in the first map protocol corresponding to the first map and the corresponding relationship between each field to be filled and the first field in the first map protocol corresponding to the second map may be pre-established, and for the current field to be filled, corresponding map data may be searched for in the first map and/or the second map according to the corresponding relationship and acquired.

S808, filling the acquired map data into a field to be filled; and/or calculating the acquired map data according to a preset calculation mode, and filling the calculation result into the field to be filled.

Illustratively, for a field to be filled currently, if the acquired map data is matched with the data content to be filled, the field to be filled currently can be directly filled with the acquired map data; if the obtained map data is not matched with the data content to be filled, the map data can be calculated in a preset calculation mode, for example, for some fields to be filled with the mesoscopic scale, the map data obtained from the high-precision map can be subjected to aggregation calculation, and then the data to be filled can be obtained.

And S809, generating a target map meeting the requirement of the preset semantic road network protocol according to the filling result.

According to the map processing method provided by the embodiment of the disclosure, after the mapping relation between the map elements of the first map and the second map is established, corresponding data is pertinently acquired from the first map and the second map for each field to be filled in the preset semantic network protocol, and filling is performed by adopting a direct filling mode or a filling mode after calculation, so that a target map can be quickly and accurately generated.

Fig. 9 is a schematic structural diagram of a map processing apparatus provided according to an embodiment of the present disclosure, where the embodiment of the present disclosure is applicable to a case where a map across spatial scales is constructed. The device can be realized by hardware and/or software and can be configured in electronic equipment. Referring to fig. 9, the map processing apparatus 900 includes:

a mapping relationship establishing module 901, configured to establish a mapping relationship between map elements in a first map and a second map, where accuracy of the first map is higher than accuracy of the second map;

a data integration module 902, configured to integrate, according to a preset semantic road network protocol, map data corresponding to map elements in the first map and the second map that have the mapping relationship, so as to obtain a target map that meets requirements of the preset semantic road network protocol, where the preset semantic road network protocol corresponds to at least two spatial scales, each spatial scale corresponds to at least one preset map layer, and an association relationship exists between different preset map layers.

The map processing device provided by the embodiment of the disclosure uses data in existing maps with different accuracies to quickly generate a unified target map which meets the requirements of a preset semantic road network protocol and can be applied to each system in the traffic management industry, thereby effectively saving the drawing cost.

The preset semantic road network protocol corresponds to at least three spatial scales, wherein the at least three spatial scales comprise a macro scale, at least one meso scale and a micro scale.

In an alternative embodiment, the macro scale includes road intersections and roads; the mesoscopic scale comprises road breaking points and road sections, the road breaking points are used for indicating the number of lanes and/or the positions of lane lines in the same road, and the road sections take the road intersections and/or the road breaking points as end points; the microscopic scale includes a lane.

In an optional implementation manner, a data structure corresponding to the preset map layer includes a field for representing a static traffic semantic and/or a dynamic traffic semantic.

In an alternative embodiment, the map element comprises a point element comprising the intersection and a line element comprising the road;

wherein, the mapping relationship establishing module comprises:

the coordinate conversion unit is used for converting the first map and the second map into the same preset coordinate system;

a first mapping relationship establishing unit, configured to establish a first mapping relationship of the point elements based on a distance relationship between the point elements in the first map and the second map in the preset coordinate system;

and the second mapping relation establishing unit is used for determining whether the end points of the line elements are matched or not based on the first mapping relation for the line elements in the first map and the second map, and establishing a second mapping relation of the line elements according to a determination result.

In an optional implementation manner, the second mapping relationship establishing unit includes:

a target line element determining subunit, configured to, for a first line element in the second map, find, from the first map, a target line element for which a starting point and/or an end point has the first mapping relationship;

a second line element determination subunit, configured to determine the target line element and the line elements in the second map that have a capping relationship and/or a connectivity relationship with the target line element as second line elements;

a mapping relationship establishing subunit, configured to establish a second mapping relationship between the first line element and the second line element.

In an optional implementation, the mapping relationship establishing subunit includes:

an initial relationship establishing subunit, configured to establish an initial mapping relationship between the first line element and the second line element;

and the relationship verification subunit is configured to determine, for the line element pair having the initial mapping relationship, whether a preset verification index is successfully matched, if the matching is successful, determine that the line element pair passes the verification, and determine the verified initial mapping relationship as a second mapping relationship of the line element pair, where the preset verification index includes at least one of a length of the line element, a distance of the line element, an azimuth of the line element, and a name of the line element pair.

In an alternative embodiment, the data integration module includes:

the data acquisition unit is used for determining fields to be filled in a preset semantic network protocol and acquiring map data, corresponding to the fields to be filled, of the map elements with the mapping relation from the first map and the second map;

the data filling unit is used for filling the acquired map data into the field to be filled; and/or calculating the acquired map data according to a preset calculation mode, and filling a calculation result into the field to be filled;

and the map generation unit is used for generating a target map meeting the requirement of the preset semantic road network protocol according to the filling result.

In the technical scheme of the disclosure, the collection, storage, use, processing, transmission, provision, disclosure and the like of the personal information of the related user all accord with the regulations of related laws and regulations, and do not violate the common customs of public order.

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

FIG. 10 shows a schematic block diagram of an example electronic device 1000 that can 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, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be examples only, and are not intended to limit implementations of the disclosure described and/or claimed herein.

As shown in fig. 10, the apparatus 1000 includes a computing unit 1001 that can perform various appropriate actions and processes according to a computer program stored in a Read Only Memory (ROM) 1002 or a computer program loaded from a storage unit 1008 into a Random Access Memory (RAM) 1003. In the RAM 1003, various programs and data necessary for the operation of the device 1000 can also be stored. The calculation unit 1001, the ROM1002, and the RAM 1003 are connected to each other by a bus 1004. An input/output (I/O) interface 1005 is also connected to bus 1004.

A number of components in device 1000 are connected to I/O interface 1005, including: an input unit 1006 such as a keyboard, a mouse, and the like; an output unit 1007 such as various types of displays, speakers, and the like; a storage unit 1008 such as a magnetic disk, an optical disk, or the like; and a communication unit 1009 such as a network card, a modem, a wireless communication transceiver, or the like. The communication unit 1009 allows the device 1000 to exchange information/data with other devices through a computer network such as the internet and/or various telecommunication networks.

Computing unit 1001 may be a variety of general and/or special purpose processing components with processing and computing capabilities. Some examples of the computing unit 1001 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various dedicated Artificial Intelligence (AI) computing chips, various computing units running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, and so forth. The calculation unit 1001 executes the respective methods and processes described above, such as the map processing method. For example, in some embodiments, the map processing method may be implemented as a computer software program tangibly embodied in a machine-readable medium, such as the storage unit 1008. In some embodiments, part or all of the computer program may be loaded and/or installed onto device 1000 via ROM1002 and/or communications unit 1009. When the computer program is loaded into the RAM 1003 and executed by the computing unit 1001, one or more steps of the map processing method described above may be performed. Alternatively, in other embodiments, the computing unit 1001 may be configured to perform the map processing method in any other suitable manner (e.g., by means of firmware).

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

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

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

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

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

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

Artificial intelligence is the subject of research that makes computers simulate some human mental processes and intelligent behaviors (such as learning, reasoning, thinking, planning, etc.), both at the hardware level and at the software level. Artificial intelligence hardware technologies generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing, and the like; the artificial intelligence software technology mainly comprises a computer vision technology, a voice recognition technology, a natural language processing technology, a machine learning/deep learning technology, a big data processing technology, a knowledge map technology and the like.

Cloud computing (cloud computing) refers to a technology system that accesses a flexibly extensible shared physical or virtual resource pool through a network, where resources may include servers, operating systems, networks, software, applications, storage devices, and the like, and may be deployed and managed in a self-service manner as needed. Through the cloud computing technology, high-efficiency and strong data processing capacity can be provided for technical application and model training of artificial intelligence, block chains and the like.

It should be understood that various forms of the flows shown above may be used, with steps reordered, added, or deleted. For example, the steps described in this disclosure may be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solutions provided by this disclosure can be achieved, and are not limited herein.

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

Claims

1. A map processing method, comprising:

establishing a mapping relation of map elements in a first map and a second map, wherein the precision of the first map is higher than that of the second map;

2. The method of claim 1, wherein said predetermined semantic road network protocols correspond to at least three spatial scales comprising a macro scale, at least one meso scale and a micro scale.

3. The method of claim 2, wherein the macro scale includes intersections and roads; the mesoscopic scale comprises road breaking points and road sections, the road breaking points are used for representing the number of lanes and/or the positions of lane lines in the same road, and the road sections take the road intersections and/or the road breaking points as end points; the microscopic scale includes a lane.

4. The method according to claim 1, wherein a data structure corresponding to the preset map layer includes a field for representing static traffic semantics and/or dynamic traffic semantics.

5. The method of claim 3, wherein the map element comprises a point element comprising the intersection and a line element comprising the road; the establishing of the mapping relationship between the map elements in the first map and the second map comprises the following steps:

converting the first map and the second map into the same preset coordinate system;

establishing a first mapping relation of the point elements based on the distance relation of the point elements in the first map and the second map in the preset coordinate system;

and for the line elements in the first map and the second map, determining whether the end points of the line elements are matched or not based on the first mapping relation, and establishing a second mapping relation of the line elements according to the determination result.

6. The method of claim 5, wherein the determining, for the line element in the first map and the second map, whether the end points of the line element match based on the first mapping relationship and establishing a second mapping relationship of the line element according to the determination result comprises:

for a first line element in the second map, searching a target line element with a first mapping relation at a starting point and/or an end point in the first map;

determining the target line element and the line elements in the second map, which have a capping relationship and/or a communicating relationship with the target line element, as second line elements;

establishing a second mapping relationship of the first line element and the second line element.

7. The method of claim 6, wherein said establishing a second mapping relationship of said first line element and said second line element comprises:

establishing an initial mapping relationship of the first line element and the second line element;

and for the line element pair with the initial mapping relation, determining whether a preset verification index is successfully matched, if so, determining that the line element pair passes the verification, and determining the verified initial mapping relation as a second mapping relation of the line element, wherein the preset verification index comprises at least one of the length of the line element, the distance of the line element, the azimuth angle of the line element and the name of the line element.

8. The method according to claim 1, wherein the integrating map data corresponding to map elements in the first map and the second map having the mapping relationship according to a preset semantic road network protocol to obtain a target map meeting the requirement of the preset semantic road network protocol comprises:

determining fields to be filled in a preset semantic network protocol, and acquiring map data corresponding to the fields to be filled, of the map elements with the mapping relation from the first map and the second map;

filling the obtained map data into the field to be filled; and/or calculating the acquired map data according to a preset calculation mode, and filling a calculation result into the field to be filled;

and generating a target map meeting the requirements of the preset semantic road network protocol according to the filling result.

9. A map processing apparatus, comprising:

and the data integration module is used for integrating map data corresponding to map elements with the mapping relation in the first map and the second map according to a preset semantic road network protocol to obtain a target map meeting the requirement of the preset semantic road network protocol, wherein the preset semantic road network protocol corresponds to at least two spatial scales, each spatial scale corresponds to at least one preset map layer, and an association relation exists between different preset map layers.

10. The apparatus of claim 9, wherein said predetermined semantic road network protocol corresponds to at least three spatial scales including a macro scale, at least one meso scale and a micro scale.

11. The apparatus of claim 10, wherein the macro scale comprises road intersections and roads; the mesoscopic scale comprises road breaking points and road sections, the road breaking points are used for indicating the number of lanes and/or the positions of lane lines in the same road, and the road sections take the road intersections and/or the road breaking points as end points; the microscopic scale includes a lane.

12. The apparatus according to claim 9, wherein the data structure corresponding to the preset map layer includes a field for representing static traffic semantics and/or dynamic traffic semantics.

13. The apparatus of claim 11, wherein the map element comprises a point element comprising the intersection and a line element comprising the road;

wherein, the mapping relationship establishing module comprises:

14. The apparatus of claim 13, wherein the second mapping relationship establishing unit comprises:

15. The apparatus of claim 14, wherein the mapping relationship establishing subunit comprises:

and the relationship verification subunit is configured to determine, for a line element pair in which the initial mapping relationship exists, whether a preset verification index is successfully matched, if the matching is successful, determine that the verification passes, and determine the verified initial mapping relationship as a second mapping relationship of the line element, where the preset verification index includes at least one of a length of the line element, a distance of the line element, an azimuth of the line element, and a name of the line element.

16. The apparatus of claim 9, wherein the data integration module comprises:

17. 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 to enable the at least one processor to perform the method of any one of claims 1-8.

18. A non-transitory computer readable storage medium having stored thereon computer instructions for causing the computer to perform the method of any one of claims 1-8.