CN111897906A

CN111897906A - Method, device, equipment and storage medium for processing map data

Info

Publication number: CN111897906A
Application number: CN202010760935.5A
Authority: CN
Inventors: 朱晓玲
Original assignee: Beijing Didi Infinity Technology and Development Co Ltd
Current assignee: Beijing Didi Infinity Technology and Development Co Ltd
Priority date: 2020-07-31
Filing date: 2020-07-31
Publication date: 2020-11-06

Abstract

The present disclosure relates to a method, apparatus, device, and storage medium for processing map data. The method described herein includes determining a target road region in map data corresponding to a geographic region based on road semantic information associated with the geographic region, the road semantic information identifying roads in the geographic region, and missing from the map data coordinate information for at least one target location within a target segment of the target road region. The method also includes selecting coordinate information for a plurality of reference locations for the target segment from the map data, and determining coordinate information for at least one target location within the target segment based at least on the coordinate information for the plurality of reference locations. By the scheme, the coordinate information missing in the map data can be determined more quickly and accurately.

Description

Method, device, equipment and storage medium for processing map data

Technical Field

The present disclosure relates generally to the field of maps, and more particularly, to methods, apparatuses, devices, and computer-readable storage media for processing map data.

Background

Map data, particularly high-precision point cloud maps, are commonly used in application scenarios such as object perception, automatic driving, and the like. Map data for a particular geographic area may be collected by way of laser scanning. However, due to interference of obstacles during the acquisition process, such as occlusion of static objects or interference of vehicles, pedestrians, etc., it is necessary to remove the obstacles from the acquired data. This can cause "holes" in the map data, i.e., information for corresponding locations is missing from the map data. Incomplete map data will be detrimental to the execution of subsequent applications. Therefore, completion of map data is an urgent problem to be solved.

Disclosure of Invention

According to some embodiments of the present disclosure, a scheme for processing map data is provided.

In a first aspect of the disclosure, a method of processing map data is provided. The method includes determining a target road region in map data corresponding to a geographic region based on road semantic information associated with the geographic region, the road semantic information identifying roads in the geographic region, the map data lacking coordinate information for at least one target location within a target segment of the target road region. The method also includes selecting coordinate information for a plurality of reference locations for the target segment from the map data, and determining coordinate information for at least one target location within the target segment based at least on the coordinate information for the plurality of reference locations.

In a second aspect of the present disclosure, an apparatus for processing map data is provided. The device includes: a region determination module configured to determine a target road region in map data corresponding to a geographic region based on road semantic information associated with the geographic region, the road semantic information identifying roads in the geographic region, the map data lacking coordinate information for at least one target location within a target segment of the target road region; a selection module configured to select coordinate information for a plurality of reference locations for a target segment from map data; and an information determination module configured to determine coordinate information of at least one target location within the target segment based at least on the coordinate information of the plurality of reference locations.

In a third aspect of the present disclosure, there is provided an electronic device comprising one or more processors and memory for storing computer-executable instructions for execution by the one or more processors to implement a method according to the first and/or second aspect of the present disclosure.

In a fourth aspect of the present disclosure, a computer-readable storage medium is provided having computer-executable instructions stored thereon, wherein the computer-executable instructions, when executed by a processor, implement a method according to the first aspect of the present disclosure.

This summary is provided to introduce a selection of concepts in a simplified form that are further described below in the detailed description. This summary is not intended to identify key features or essential features of the disclosure, nor is it intended to be used to limit the scope of the disclosure.

Drawings

Features, advantages and other aspects of exemplary embodiments of the present disclosure will become more apparent by referring to the following detailed description when taken in conjunction with the accompanying drawings. Several embodiments of the present disclosure are illustrated herein by way of example, and not by way of limitation, in the figures of the accompanying drawings and in which:

FIG. 1 illustrates a block diagram of an example environment in which embodiments of the present disclosure can be implemented;

fig. 2A and 2B illustrate example map data to be complemented;

FIG. 3 illustrates a flow diagram of a process of processing map data according to some embodiments of the present disclosure;

FIG. 4 illustrates a schematic diagram of map data in which road regions are identified, in accordance with some embodiments of the present disclosure;

fig. 5A and 5B illustrate schematic diagrams of a target segment of an extended road region, according to some embodiments of the present disclosure;

FIG. 6 illustrates an example of map data completion, according to some embodiments of the present disclosure;

FIG. 7 illustrates a block diagram of an apparatus for processing map data, in accordance with some embodiments of the present disclosure; and

FIG. 8 illustrates a block diagram of a computing device/server in which one or more embodiments of the present disclosure may be implemented.

Detailed Description

Some example embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While certain embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.

The term "include" and variations thereof as used herein is meant to be inclusive in an open-ended manner, i.e., "including but not limited to". Unless specifically stated otherwise, the term "or" means "and/or". The term "based on" means "based at least in part on". The terms "one example embodiment" and "one embodiment" mean "at least one example embodiment". The term "another embodiment" means "at least one additional embodiment". The terms "first," "second," and the like may refer to different or the same object. Other explicit and implicit definitions are also possible below.

FIG. 1 illustrates a block diagram of an example environment 100 in which embodiments of the present disclosure can be implemented. As shown in FIG. 1, environment 100 includes a map acquisition device 110 and a map processing device 120. It should be understood that the description of the structure and function of environment 100 is for exemplary purposes only and does not imply any limitation as to the scope of the disclosure. For example, embodiments of the present disclosure may also be applied to environments other than environment 100.

The map capture device 110 may include, but is not limited to, a capture cart or other device for capturing map data. For example, a lidar may be mounted on the map acquisition device 110 for acquiring data for a particular geographic area. Map capture device 110 may move within a particular geographic area during a capture period (e.g., daytime) to capture data used to make a map. Data collected by lidar and like devices is sometimes referred to as "point cloud data". The "point cloud data" as referred to herein refers to data information of respective points of an object surface returned when a laser beam is irradiated on the object surface, including coordinate information of each point (for example, coordinate values in a three-dimensional coordinate system) and a laser reflection intensity (also referred to as a "reflection value"). The map acquisition device 110 may generate map data 115 (also referred to as a "point cloud map" or "high precision map") about a particular geographic area based on the acquired data.

Due to interference from an obstacle, such as a block of a static object or interference from a vehicle, a pedestrian, or the like, the map collecting apparatus 110 may not be able to collect the road surface interfered by the obstacle. Since the map data is mainly information of the road surface, obstacles are removed from the collected data. This results in data loss, also referred to as "point cloud holes," in the acquired map data 115. Fig. 2A and 2B illustrate some examples of map data 115 in which "point cloud holes" exist. In the example of FIG. 2A, there are void regions 210-1, 210-2 in the map data 115 due to occlusion by static objects such as a lot of road greens at the roadside. In the example of FIG. 2B, there are void regions 220-1, 220-2, 220-3 in the map data 115 due to occlusion by static vehicles.

The map data 115 for a particular geographic area may be used to provide subsequent tasks, such as tasks like automated driving in a particular geographic area. The loss of data in a certain portion may result in an impact on the performance of subsequent tasks. For example, in an object detection process in an automatic driving process, ground information in a geographic area is required as a reference, otherwise a target object on a hollow area cannot be accurately detected. Therefore, it is desirable to be able to complement data, particularly coordinate information, missing in the map data 115.

To complement the missing data, the map data 115 may be provided to the map processing device 120. The map processing device 120 may complement the missing data in the map data 115, resulting in complemented map data 125.

In some schemes, since the collected map data relates to a large geographic range, the edges of the hole areas in the map data need to be labeled manually. Patch data is then regenerated for addition to the map data. However, such a scheme has disadvantages in terms of both processing efficiency and accuracy.

Embodiments of the present disclosure propose a scheme for processing map data. According to this solution, the road region to which the map data relates, in particular the road region having one or more sections missing coordinate information, is determined by means of the road semantic information. For a given segment, coordinate information for a plurality of reference locations is selected from the map data, and coordinate information missing in the segment is determined based on the coordinate information for the reference locations.

According to the scheme, the road regions in the map data can be automatically and quickly divided through the road semantic information, so that the positions to be repaired can be positioned more quickly, and the inefficiency and inaccuracy of manual marking are avoided. Because the road semantic information is usually information which needs to be generated when a complete high-precision map is constructed, the additional information acquisition overhead of the map data completion process cannot be increased. In addition, the missing coordinate information can be determined more quickly and accurately depending on the coordinate information of the existing reference position in the map data.

Some example embodiments of the disclosure will now be described with continued reference to the accompanying drawings.

Fig. 3 shows a schematic diagram of a process 300 for processing map data, in accordance with some embodiments of the present disclosure. For ease of discussion, the process of processing map data is discussed with reference to fig. 1 and 2. The process 300 may be performed, for example, at the map processing device 120 shown in fig. 1. It should be understood that process 300 may also include blocks not shown and/or may omit blocks shown. The scope of the present disclosure is not limited in this respect.

At block 310, the map processing device 120 determines a target road region in the map data 115 corresponding to the geographic region based on the road semantic information associated with the geographic region. The road semantic information can identify roads in a particular geographic area. Road semantic information may be extracted from a semantic map constructed for the corresponding geographic region. Semantic maps, similar to traditional digital maps, are used to annotate ground elements in a geographic area within a certain coordinate system, and may in particular contain road semantic information identifying various roads in the geographic area.

The map processing device 120 may label one or more road regions in the map data 115 with road semantic information. In the map data completion, data completion of a road region is mainly focused on, and other regions such as green belts between roads are generally not focused on. The road semantic information may assist the map processing device 120 in quickly dividing various regions of the entire map data.

In some embodiments, the road semantic information may specifically include an identification of a plurality of road boundaries in a particular geographic area. The map processing device 120 may determine one or more road regions defined by a plurality of road boundaries from the map data 115. With the aid of the road semantic information, the map processing device 120 can quickly divide different road regions from the complete map data 115.

In fig. 4, the division of the road area of the map data is schematically illustrated by taking the map data 115 illustrated in fig. 2A as an example. Note that the map data shown in fig. 2A may be a part or all of the map data 115 collected by the map collection device 110. In fig. 4, some necessary elements in the map data 115 are presented in simple line formation for ease of illustration. In FIG. 4, there are hole regions 210-1, 210-2 (collectively or individually referred to as hole regions 210) in the map data 115, the boundaries of which are shown by dotted lines, but note that there is no specific identification of hole boundaries in actual map data.

The map processing device 120 matches the road boundaries 402-1, 402-2, 402-3, and 402-4 (collectively or individually referred to as road boundaries 402) indicated by the road semantic information into the map data 115 so that the

road regions

410, 420, and 430 defined by these road boundaries can be determined. Each road region may be defined by a left road boundary and a right road boundary.

Further, the map processing device 120 may determine which road region or regions divided from the map data 115 have data missing. Under normal circumstances, the map data 115 may include coordinate information of various locations in a geographic area, as well as other auxiliary information such as intensity information, color information, reflectivity information, and the like, through collection by the map collection device 110. The presence of voids results from the removal of the obstruction. Thus, for some locations, the map data 115 may correspond to a lack of coordinate information and other ancillary information. In the embodiments of the present disclosure, completion of missing coordinate information is mainly focused on.

The coordinate information is used for positioning purposes, which may be represented by coordinate values of the corresponding position in three-dimensional space. The coordinate information may specifically include a height value in the vertical direction and a horizontal coordinate value in the horizontal direction. In the embodiment of the present disclosure, the height value of a location within a road region in the map data 115 refers to the ground height of the location. If a three-dimensional space is modeled in a (x, y, z) three-dimensional coordinate system, the horizontal coordinate values in the horizontal direction include a pair of coordinate values on both the x and y coordinate axes, and the height values in the vertical direction include a coordinate value on the z coordinate axis.

In some examples, the horizontal coordinate values may indicate longitude and latitude (e.g., x-axis coordinate values and y-axis coordinate values) of the corresponding location, and the height values may indicate an altitude of the corresponding location relative to sea level. In some examples, the three-dimensional coordinate system may also be constructed by setting a reference origin such that the horizontal coordinate values may indicate horizontal distances of the corresponding locations relative to the reference origin on x and y coordinate axes, and the height values may indicate differences in height of the corresponding locations relative to the reference origin on a z coordinate axis. Coordinate information for a location (corresponding to a point in space) may also be represented by other means, including height values and horizontal coordinate values. Embodiments of the present disclosure are not limited in this respect.

In some embodiments, after dividing the road region, the map processing device 120 determines that there are one or more road regions where the coordinate information is missing as the target road region to be completed. In the example of fig. 4, the

road areas

410 and 420 are target road areas because the

road areas

410 and 420 include the hole areas 210-1 and 210-2, respectively, in which the coordinate information of the respective positions is complemented. In some embodiments, there is a lack of coordinate information for at least one section of the target road region. A section in which there is a lack of coordinate information is referred to herein as a "target section".

In some embodiments, since road regions typically extend over greater distances and the total area of the entire region is greater, the map processing device 120 also divides the target road region into a plurality of road segments in order to more accurately determine the missing coordinate information at a particular location. The map processing device 120 can determine, segment by segment, whether there is a lack of coordinate information therein. A section in which there is a lack of coordinate information is referred to herein as a "target section".

In some embodiments, the map processing device 120 may divide the target road region into a plurality of segments by dividing the road boundaries defining the target road region. For example, the map processing apparatus 120 may divide the road boundary by a predetermined length. As such, each section may include a polygonal area defined at least by the corresponding road boundary. Of course, it is understood that the division of the sections is configurable, and the lengths of the road boundaries corresponding to different sections may be the same or different. The target road region may be divided in any other manner than by road boundary.

As an example, in FIG. 4, the map processing device 120 divides the target road region 410 into sections 412-1, 412-2, 41-3 (collectively or individually referred to as section 412), and divides the target road region 420 into sections 422-1, 422-2 (collectively or individually referred to as section 422). Each section 412, 422 may form a polygonal area defined at least by the road boundary 402. In the example of FIG. 4, each section 412, 422 includes a portion of a void region 210-1, 210-2, as void regions 210-1 and 210-2 are continuous regions extending along the road boundary. The map processing device 120 determines these sections as target sections to be completed.

The map processing device 120 may determine the coordinate information missing therein on a target section-by-target section basis. With continued reference back to the process 300 of fig. 3, at block 320, the map processing device 120 selects coordinate information for multiple reference locations for the target segment from the map data 115. In an embodiment of the present disclosure, the determination of missing coordinate information in a target segment is facilitated by utilizing coordinate information already in map data 115. At block 330, the map processing device 120 determines coordinate information for at least one target location within the target segment based at least on the coordinate information for the plurality of reference locations.

Typically, a location within a section in a road region corresponds to the road surface of the section. In some embodiments, to complement the coordinate information of certain locations in the target segment, the road surface of the target segment may be fitted by way of a plane fitting based on the known coordinate information of the reference locations. The specific manner of plane fitting will be discussed in detail below. Typically, coordinate information for three locations can be fitted to a plane. However, to achieve a better fit, more coordinate information for the location may be selected.

In some embodiments, the manner in which the reference location is selected may also depend on the road type. Specifically, the map processing device 120 may determine a road type of the target road region, and select coordinate information of a plurality of reference positions for the target section from the map data based on the road type. The road type may be divided according to a road setting rule in a general traffic environment. For example, the road type may include a motorway and a non-motorway. The vehicle lane may also divide the primary vehicle lane and the auxiliary vehicle lane.

Since the map collecting device 110 may move along the lane of the vehicle, particularly the main lane of the vehicle, while collecting data, data collection for other lanes may be disturbed by more obstacles. For example, in some cases obstacles such as road greenbelts, barriers, etc. may be disposed between lanes, resulting in a continuous large area of data missing in lanes other than the lane in which the map-collecting device 110 is moving. For example, in the example of fig. 2A and 4, void areas 210-1, 210-2 that extend continuously along the roadway may be due to green belts or fences between

roadway areas

410 and 430 and

roadway areas

420 and 430. For such road areas where there may be a large area data loss, the map processing apparatus 120 may ensure the accuracy of the coordinate information for the determined target position by selecting more reference positions from areas other than the target section.

In some embodiments, the road type may be preset. If the map processing device 120 determines that the road type of the target road region is the predetermined road type, the map processing device 120 may determine to expand the target section of the target road region, resulting in an expanded section. The map processing device 120 may select coordinate information of a plurality of reference positions from the expanded area for determining coordinate information of the target position to be complemented.

In some embodiments, the predetermined road type for which expansion of the target zone needs to be performed may comprise a non-motorised lane, since, as described above, the void area resulting from the obstruction of the non-motorised lane by an obstacle may be larger. For example, in the example of fig. 4,

target road regions

410 and 420 are bicycle lanes, and thus each target section 412, 422 may be determined to be expanded. In some embodiments, the predetermined road type may also include an auxiliary vehicle lane, as there may also be large void areas in the auxiliary vehicle lane in the map data 115. The predetermined road type may also include other types of roads, such as other lanes in addition to the lane in which the map-acquisition device 110 is moving.

In some embodiments, the map processing device 120 may perform the expansion for each target segment in the target road region. Alternatively, the map processing device 120 may determine whether to expand the target section in the target road region based on the size of the "hole" area in the target section. For example, in the target road region, the region where the coordinate information is missing in some target sections is small, and the missing coordinate information can be determined by selecting a reference position in the section. In some examples, if the size of the "hole" region in the target section is large (e.g., greater than a threshold size), this means that the number of target locations for which coordinate information is missing is large (e.g., greater than a threshold number). In this case, the map processing device 120 may determine that the target section is to be expanded. For the size of the "hole" area in the target section, the map processing device 120 may determine by determining known coordinate information about the hole area, for example, by measuring the size of the "hole" area by the difference in horizontal coordinate values of the x-axis and the y-axis in the coordinate information.

In some embodiments, the map processing device 120 may not determine the type of road region, but may calculate the size of a "hole" region of a target section therein and determine whether the size of the "hole" region is greater than a threshold size for each target road region. For target segments with large "hole" areas, the map processing device 120 may ensure that there are sufficient reference locations to select by expanding the target segments.

In performing the target section expansion, the map processing device 120 may expand the target section toward a road area adjacent to the target road area such that the expanded section includes at least a portion of the adjacent road area. Since the map processing device 120 can determine the respective road regions in the map data 115 from the road semantic information, the road regions adjacent to the target road region can be determined accordingly. For example, in the example of fig. 4, the target section 412 or 422 may be extended to an adjacent road region 430. Note that the adjacent road area refers to an adjacent road area that is closer to the target road area than other road areas, but other isolation spaces may exist between the target road area and its adjacent road area, for example, greenbelts, isolation barriers, and the like may exist. In some embodiments, the map processing device 120 may choose to expand the target segment to an adjacent road region or non-road region that does not have a void region or a void region that is small.

In some embodiments, the map processing device 120 may perform the expansion of the road region by moving the road boundary of the target section in the direction of the adjacent road region. Specifically, the map processing apparatus 120 may expand by a predetermined distance in a normal direction of a road boundary of the target section, and particularly, move two vertex positions of the target section corresponding to the road boundary by a predetermined distance in the normal direction. The normal direction is perpendicular to the extending direction of the road boundary, and may be determined by rotating the extending direction by 90 degrees clockwise. The predetermined distance may be configured as is practical to ensure that the distance is greater than an obstacle such as a median between road zones.

Fig. 5A and 5B schematically show the expansion of the target section. In the example of fig. 5A and 5B, the target section 412 of the target road region 410 in fig. 4 is explained as an example of expansion. The target sections 412, one section 432 of the road area 430 and the road boundaries of these target sections are schematically shown in the figure. As shown in fig. 5A, between the target section 412 and the section 432, there is a greenery isolation zone 510 that shares the road boundary 402-2 with the target section 412 and the road boundary 502 with the section 432. More coordinate information of the target section 412 is missing in the map data 115 due to the presence of the green-planted isolation region 510. Therefore, the map processing apparatus 120 determines to expand the target section 412 when performing the map data completion.

Fig. 5B shows an expansion of the target zone 412. The map processing apparatus 120 moves the two

vertices

501 and 503 of the road boundary 402-2 corresponding to the target section 412 by a predetermined distance along the normal direction 505, thereby expanding the target section 412 to a partial area 520 including the section 432. As can be seen in fig. 5B, the extended section of the target section 412 includes the target section 412, the green implant isolation region 510, and the region 520.

After obtaining the expanded segment, the mapping device 120 may select sufficient coordinate information of the reference location from the expanded segment for determining the missing coordinate information in the target segment 412. The map processing device 120 may perform coordinate information in selecting the reference position from the portion of the adjacent road area included in the extended section. Additionally, the map processing device 120 may also select coordinate information of a known reference location from the target segment 412.

As mentioned above, the coordinate information of the unknown target position may be determined by way of plane fitting using the coordinate information of the reference position. The coordinate information of each reference position includes a height value and a horizontal coordinate value in the horizontal direction. The map processing device 120 may fit the road surface of the target section based on the height value and the horizontal coordinate value of the reference position, thereby obtaining a fitting relationship in which the position within the target section conforms in the three-dimensional space. The fit relationship to which the position on each three-dimensional plane conforms can be expressed as a fit equation: ax + by + cz + d is 0, where x and y represent horizontal coordinate values of a position, z represents a height value of the position, and a, b, c, and d are parameters of the fitting relationship. The fitting relationship may be determined by solving the fitting equation using the coordinate information of the known reference location. The mapping device 120 may select coordinate information for more than three reference locations and may utilize some optimization algorithms to make the determined fit relationship more accurate.

For example only, determining a road-to-road fit relationship for a target segment using a random sampling consistency algorithm is described herein. The map processing apparatus 120 may randomly select coordinate information of three reference positions from the coordinate information of the selected reference positions, and calculate a, b, c, and d in the fitting equation. Setting a position to the fitted distance threshold to the road surface as the currently calculated d. And substituting the height value and the horizontal coordinate value into the currently calculated fitting equation according to the coordinate information of the selected reference position to obtain the distance from each reference position to the currently fitted road surface. And considering the reference position with the distance from the reference position to the currently fitted road surface smaller than d as an in-local point, and considering the reference position with the distance larger than d as an out-local point. For the currently determined fitting equation, the map processing device 120 counts the number n of the local internal points in all the reference positions. The map processing device 120 may repeatedly perform the determination of the fitting equation, re-calculate the fitting equation again by randomly selecting the coordinate information of the three reference positions, and count the number n of the local points again for the newly calculated fitting equation. The mapping device 120 may repeat the above process until a threshold number of iterations is reached. The map processing device 120 may determine a fitting equation corresponding to the number of maximum local points as a fitting relationship to which the position within the target section conforms in the three-dimensional space.

It should be appreciated that the map processing device 120 may utilize other optimization algorithms, such as least squares, in addition to the random sampling consistency algorithm, to determine a fit relationship that the locations within the target segment conform to in three-dimensional space. Embodiments of the present disclosure are not limited in this respect.

On the basis of the fitting relationship, the map processing device 120 may also determine the horizontal coordinate value of the target position by referring to the horizontal coordinate value of the position. In general, at the time of acquisition of the map data 115, scanning is performed at a predetermined resolution in the horizontal direction, and therefore the horizontal coordinate values of the respective positions in the target section in the horizontal direction are changed at a predetermined resolution. The map processing device 120 may move the horizontal coordinate value of one reference position in the x-coordinate axis direction and the y-coordinate axis direction at a predetermined resolution, thereby determining the horizontal coordinate value of each target position. The reference position for determining the horizontal coordinate value may be an arbitrary reference position, or the reference position closest to the hole region may be selected for convenience of calculation. For example, if the predetermined resolution is 8 centimeters, the map processing apparatus 120 may slide the coordinate axes of the reference position in the x-coordinate-axis direction and the y-coordinate-axis direction at intervals of 8 centimeters, thereby determining the horizontal coordinate values of the respective target positions.

In the case where the horizontal coordinate value of each target position is determined, the map processing device 120 may determine the height value of each target position based on a fitting relationship, for example, a fitting equation ax + by + cz + d of 0. Finally, the map processing device 120 may determine all coordinate information of the target locations missing in the target section.

For each target road region and each target segment in the map data 115, the map processing device 120 may utilize the processes discussed above to determine coordinate information for the missing target location. Through this process, the map processing device 120 may determine the complemented map data 125 to which the map data 115 corresponds. FIG. 6 shows that the map data 115 of FIG. 2A is complemented to obtain the map data 125, wherein the hole areas 210-1 and 210-2 are filled with the corresponding coordinate information. It is to be understood that the completion can be performed in a similar manner to the map data 115 in fig. 2B.

Fig. 7 illustrates a schematic block diagram of an apparatus 700 for processing map data according to some embodiments of the present disclosure. The apparatus 700 may be implemented as or included in the map processing apparatus 120.

As shown, the apparatus 700 includes an area determination module 710 configured to determine a target road area in map data corresponding to a geographic area based on road semantic information associated with the geographic area. The road semantic information identifies roads in the geographic area. Coordinate information of at least one target position within a target segment of a target road region is missing from the map data. The apparatus 700 further comprises a selection module 720 configured to select coordinate information for a plurality of reference positions for the target segment from the map data. The apparatus 700 further comprises an information determining module 730 configured to determine coordinate information of at least one target location within the target segment based on at least the coordinate information of the plurality of reference locations.

In some embodiments, the road semantic information includes an identification of a plurality of road boundaries in the geographic area. In some embodiments, the region determination module 710 includes: a road region determination module configured to determine at least one road region defined by a plurality of road boundaries from map data; and a target road region determination module configured to determine, as a target road region, a road region in which coordinate information of at least one position is missing from among the at least one road region.

In some embodiments, the apparatus 700 further comprises: a segment dividing module configured to divide the target road region into a plurality of segments by dividing a road boundary defining the target road segment, the plurality of road segments including the target segment.

In some embodiments, the selection module 720 includes: a type determination module configured to determine a road type of a target road region; and a type-based selection module configured to select coordinate information of a plurality of reference positions for the target section from the map data based on the road type.

In some embodiments, the type determination module comprises a semantic information based determination module configured to determine the road type of the target road region based on the road semantic information.

In some embodiments, the type-based selection module comprises: an expansion module configured to expand the target section in the map data to obtain an expanded section if the road type is a predetermined road type; and an extension-based selection module configured to select coordinate information of the plurality of reference locations from the extension segment.

In some embodiments, the expansion module includes an adjacent expansion module configured to expand the target segment toward a road region in the map data adjacent to the target road region such that the expanded segment includes at least a portion of the adjacent road region.

In some embodiments, the predetermined road type includes at least one of a non-motorized lane and an auxiliary motorized lane.

In some embodiments, the coordinate information of the plurality of reference positions includes a height value in a vertical direction and a horizontal coordinate value in a horizontal direction of each of the plurality of reference positions. In some embodiments, the information determination module 730 includes: the fitting module is configured to fit the road surface of the target section based on the height values and the horizontal coordinate values of the multiple reference positions to obtain a fitting relation which accords with the position in the target section in a three-dimensional space; a horizontal coordinate value determination module configured to determine a horizontal coordinate value of each of the at least one target position based on a horizontal coordinate value of at least one reference position among the plurality of reference positions and a predetermined resolution of the map data in a horizontal direction; and a height value determination module configured to determine a respective height value of the at least one target location based on the fitting relationship and the respective horizontal coordinate value of the at least one target location, respectively.

Fig. 8 illustrates a block diagram that illustrates a computing device/server 800 in which one or more embodiments of the disclosure may be implemented. It should be understood that the computing device/server 800 illustrated in fig. 8 is merely exemplary and should not be construed as limiting in any way the functionality and scope of the embodiments described herein. The computing device/server 800 shown in fig. 8 may be used to implement the map processing device 120 of fig. 1.

As shown in fig. 8, computing device/server 800 is in the form of a general purpose computing device. Components of computing device/server 800 may include, but are not limited to, one or more processors or processing units 810, memory 820, storage 830, one or more communication units 840, one or more input devices 850, and one or more output devices 860. The processing unit 810 may be a real or virtual processor and can perform various processes according to programs stored in the memory 820. In a multiprocessor system, multiple processing units execute computer-executable instructions in parallel to improve the parallel processing capability of computing device/server 800.

Computing device/server 800 typically includes a number of computer storage media. Such media may be any available media that is accessible by computing device/server 800 and includes, but is not limited to, volatile and non-volatile media, removable and non-removable media. The memory 820 may be volatile memory (e.g., registers, cache, Random Access Memory (RAM)), non-volatile memory (e.g., Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory), or some combination thereof. Storage device 830 may be a removable or non-removable medium and may include a machine-readable medium, such as a flash drive, a magnetic disk, or any other medium that may be capable of being used to store information and/or data (e.g., training data for training) and that may be accessed within computing device/server 800.

Computing device/server 800 may further include additional removable/non-removable, volatile/nonvolatile storage media. Although not shown in FIG. 8, a magnetic disk drive for reading from and writing to a removable, non-volatile magnetic disk (e.g., a "floppy disk") and an optical disk drive for reading from or writing to a removable, non-volatile optical disk may be provided. In these cases, each drive may be connected to a bus (not shown) by one or more data media interfaces. Memory 820 may include a computer program product 825 having one or more program modules configured to perform the various methods or acts of the various embodiments of the disclosure.

Communication unit 840 enables communication with other computing devices over a communication medium. Additionally, the functionality of the components of computing device/server 800 may be implemented in a single computing cluster or multiple computing machines capable of communicating over a communications connection. Thus, computing device/server 800 may operate in a networked environment using logical connections to one or more other servers, network Personal Computers (PCs), or another network node.

The input device 850 may be one or more input devices such as a mouse, keyboard, trackball, or the like. The output device(s) 860 may be one or more output devices such as a display, speakers, printer, or the like. Computing device/server 800 may also communicate with one or more external devices (not shown), such as storage devices, display devices, etc., as desired, through communication unit 840, with one or more devices that enable a user to interact with computing device/server 800, or with any device (e.g., network card, modem, etc.) that enables computing device/server 800 to communicate with one or more other computing devices. Such communication may be performed via input/output (I/O) interfaces (not shown).

According to an exemplary implementation of the present disclosure, a computer-readable storage medium having stored thereon computer-executable instructions is provided, wherein the computer-executable instructions are executed by a processor to implement the above-described method. According to an exemplary implementation of the present disclosure, there is also provided a computer program product, tangibly stored on a non-transitory computer-readable medium and comprising computer-executable instructions, which are executed by a processor to implement the method described above.

Various aspects of the present disclosure are described herein with reference to flowchart illustrations and/or block diagrams of methods, apparatus, devices and computer program products implemented in accordance with the disclosure. It will be understood that each block of the flowchart illustrations and/or block diagrams, and combinations of blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer-readable program instructions.

These computer-readable program instructions may be provided to a processing unit of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processing unit of the computer or other programmable data processing apparatus, create means for implementing the functions/acts specified in the flowchart and/or block diagram block or blocks. These computer-readable program instructions may also be stored in a computer-readable storage medium that can direct a computer, programmable data processing apparatus, and/or other devices to function in a particular manner, such that the computer-readable medium storing the instructions comprises an article of manufacture including instructions which implement the function/act specified in the flowchart and/or block diagram block or blocks.

The computer readable program instructions may be loaded onto a computer, other programmable data processing apparatus, or other devices to cause a series of operational steps to be performed on the computer, other programmable apparatus or other devices to produce a computer implemented process such that the instructions which execute on the computer, other programmable apparatus or other devices implement the functions/acts specified in the flowchart and/or block diagram block or blocks.

The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various implementations of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of instructions, which comprises one or more executable instructions for implementing the specified logical function(s). In some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

The foregoing has described implementations of the present disclosure, and the above description is illustrative, not exhaustive, and not limited to the implementations disclosed. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described implementations. The terminology used herein was chosen in order to best explain the principles of various implementations, the practical application, or improvements to the technology in the marketplace, or to enable others of ordinary skill in the art to understand various implementations disclosed herein.

Claims

1. A method of processing map data, comprising:

determining a target road region in map data corresponding to a geographic region based on road semantic information associated with the geographic region, the road semantic information identifying roads in the geographic region, coordinate information for at least one target location within a target segment of the target road region being missing from the map data;

selecting coordinate information for a plurality of reference locations for the target segment from the map data; and

determining the coordinate information of the at least one target location within the target segment based at least on the coordinate information of the plurality of reference locations.

2. The method of claim 1, wherein the road semantic information includes an identification of a plurality of road boundaries in the geographic area, the determining the target road region comprising:

determining from the map data at least one road region defined by the plurality of road boundaries; and

determining the target road region from the at least one road region.

3. The method of claim 2, further comprising:

dividing the target road region into a plurality of segments by dividing a road boundary defining the target road segment, the plurality of road segments including the target segment.

4. The method of claim 1, wherein selecting coordinate information for a plurality of reference locations comprises:

determining a road type of the target road area; and

selecting, from the map data, coordinate information for the plurality of reference locations for the target segment based on the road type.

5. The method of claim 4, wherein determining a road type of the target road region comprises:

determining the road type of the target road region based on the road semantic information.

6. The method of claim 4, wherein selecting the plurality of reference locations from the map data based on the road type comprises:

if the road type is a preset road type, expanding the target section in the map data to obtain an expanded section; and

selecting coordinate information of the plurality of reference positions from the extended section.

7. The method of claim 6, wherein expanding the target segment comprises:

expanding the target segment toward a road region in the map data that is adjacent to the target road region such that the expanded segment includes at least a portion of the adjacent road region.

8. The method of claim 6, wherein the predetermined road type comprises at least one of a non-motorized lane and an auxiliary motorized lane.

9. The method of claim 1, wherein the coordinate information of the plurality of reference locations comprises height values in a vertical direction and horizontal coordinate values in a horizontal direction for each of the plurality of reference locations, and wherein determining the coordinate information of the at least one target location within the target segment comprises:

fitting the road surface of the target section based on the height values and the horizontal coordinate values of the multiple reference positions to obtain a fitting relation which is met by the positions in the target section in a three-dimensional space;

determining a horizontal coordinate value of each of the at least one target position based on the horizontal coordinate value of at least one of the plurality of reference positions and a predetermined resolution of the map data in a horizontal direction; and

and respectively determining the height value of each target position based on the fitting relation and the horizontal coordinate value of each target position.

10. An apparatus for processing map data, the apparatus comprising:

a region determination module configured to determine a target road region in map data corresponding to a geographic region based on road semantic information associated with the geographic region, the road semantic information identifying roads in the geographic region, coordinate information for at least one target location within a target segment of the target road region being missing from the map data;

a selection module configured to select coordinate information for a plurality of reference locations for the target segment from the map data; and

an information determination module configured to determine the coordinate information of the at least one target location within the target segment based at least on the coordinate information of the plurality of reference locations.

11. The apparatus of claim 10, wherein the road semantic information includes an identification of a plurality of road boundaries in the geographic area, the area determination module comprising:

a road region determination module configured to determine at least one road region defined by the plurality of road boundaries from the map data; and

a target road region determination module configured to determine, from the at least one road region, a road region in which coordinate information of at least one location is missing, as the target road region.

12. The apparatus of claim 11, further comprising:

a segment dividing module configured to divide the target road region into a plurality of segments by dividing a road boundary defining the target road segment, the plurality of road segments including the target segment.

13. The apparatus of claim 10, wherein the selection module comprises:

a type determination module configured to determine a road type of the target road region; and

a type-based selection module configured to select coordinate information of the plurality of reference locations for the target segment from the map data based on the road type.

14. The apparatus of claim 13, wherein the type determination module comprises:

a semantic information based determination module configured to determine the road type of the target road region based on the road semantic information.

15. The apparatus of claim 13, wherein the type-based selection module comprises:

an expansion module configured to expand the target section in the map data to obtain an expanded section if the road type is a predetermined road type; and

an extension-based selection module configured to select coordinate information of the plurality of reference locations from the extended section.

16. The apparatus of claim 15, wherein the expansion module comprises:

an adjacent expansion module configured to expand the target segment toward a road region in the map data adjacent to the target road region such that the expanded segment includes at least a portion of the adjacent road region.

17. The apparatus of claim 15, wherein the predetermined road type comprises at least one of a non-motorized lane and an auxiliary motorized lane.

18. The apparatus of claim 10, wherein the coordinate information of the plurality of reference locations comprises height values in a vertical direction and horizontal coordinate values in a horizontal direction for each of the plurality of reference locations, and wherein the information determination module comprises:

a fitting module configured to fit a road surface of the target section based on the height values and the horizontal coordinate values of the respective plurality of reference positions, resulting in a fitting relationship in which positions within the target section conform in a three-dimensional space;

a horizontal coordinate value determination module configured to determine a horizontal coordinate value of each of the at least one target position based on the horizontal coordinate value of at least one of the plurality of reference positions and a predetermined resolution of the map data in a horizontal direction; and

a height value determination module configured to determine a respective height value of the at least one target location based on the fitted relationship and the respective horizontal coordinate value of the at least one target location, respectively.

19. An electronic device, comprising:

one or more processors; and

a memory storing computer-executable instructions that, when executed by the one or more processors, cause the electronic device to implement the method of any of claims 1-9.

20. A computer-readable storage medium having computer-executable instructions stored thereon, wherein the computer-executable instructions, when executed by a processor, implement the method of any one of claims 1 to 9.