CN115077515A

CN115077515A - Data generation method and device, electronic equipment and computer program product

Info

Publication number: CN115077515A
Application number: CN202210999419.7A
Authority: CN
Inventors: 王成墨
Original assignee: Autonavi Software Co Ltd
Current assignee: Autonavi Software Co Ltd
Priority date: 2022-08-19
Filing date: 2022-08-19
Publication date: 2022-09-20
Anticipated expiration: 2042-08-19
Also published as: CN115077515B

Abstract

The embodiment of the disclosure discloses a data generation method, a data generation device, an electronic device and a computer program product, wherein the method comprises the following steps: acquiring side wall initial data of a side wall of a sinking road; the side wall initial data comprises a bottom end lane line associated with a sinking road, an initial side wall associated with the bottom end lane line and an initial top end line associated with the initial side wall; merging initial side walls belonging to the same sinking road based on the bottom lane line to form a merged side wall; determining a target top lane line based on the initial top line associated with the merged side wall; the target top lane line is an edge lane line of the top road associated with the initial side wall; and generating a target side wall of the sinking road based on the bottom lane line and the target top lane line. The technical scheme can enhance the display effect of the sinking road modeling rendering.

Description

Data generation method and device, electronic equipment and computer program product

Technical Field

The present disclosure relates to the field of geographic information technology, and in particular, to a data generation method, apparatus, electronic device, and computer program product.

Background

The high-precision map abstracts spatial ground feature elements of the real world and logically expresses the spatial ground feature elements in a semantic mode. Map elements expressed in the high-precision map can be more than hundreds of types, and the map elements comprise road facilities such as roads, lanes, sunken road side walls, green belts and the like. The sinking road side wall is an important road element in high-precision map data. If the expression of the side wall in the high-precision map is lacked, cavities at two sides of a sinking road can be caused, and the map surface effect of the map is influenced. Therefore, a solution is needed to be provided, which is used for modeling a side wall of a sinking road in a high-precision map, so that the sinking road is better expressed in the high-precision map, and the rendering effect of the side wall of the sinking road in the high-precision map is improved.

Disclosure of Invention

The embodiment of the disclosure provides a data generation method, a data generation device, electronic equipment and a computer program product.

In a first aspect, an embodiment of the present disclosure provides a data generation method, where the method includes:

acquiring side wall initial data of a side wall of a sinking road; the side wall initial data comprises a bottom end lane line associated with a sinking road, an initial side wall associated with the bottom end lane line and an initial top end line associated with the initial side wall;

merging initial side walls belonging to the same sinking road based on the bottom lane line to form a merged side wall;

determining a target top lane line based on the initial top line associated with the merged side wall; the target top lane line is an edge lane line of the top road associated with the initial side wall;

and generating a target side wall of the sinking road based on the bottom lane line and the target top lane line.

Further, merge the initial side walls belonging to the same sinking road based on the bottom lane line to form a merged side wall, comprising:

determining one or more bottom end lane lines which belong to the same sinking road and are connected in front and at the back in the side wall initial data;

determining initial side walls associated with the one or more bottom lane lines connected in front and back;

and combining the initial side walls according to the front-back connection sequence of the one or more bottom end lane lines connected in front-back manner to obtain combined side walls.

Further, determining a target top lane line based on the initial top line associated with the merged side wall comprises:

determining a second point on the bottom end lane line, wherein the second point is the smallest in plane distance with any first point on the initial top end line;

determining at least one candidate top lane line which is within a preset distance range from a plane of any first point on the initial top line and is positioned at the edge of the top road;

determining a third point on the candidate top lane line, which is closest to the plane distance of any first point on the initial top line;

determining a target top lane line based on the candidate top lane lines meeting preset conditions; wherein the preset conditions include:

the minimum plane distance between the candidate top lane line and the initial top line is smaller than a preset distance threshold;

the difference between the heights of the third point and the second point is greater than or equal to a preset height threshold value;

and the direction included angle between the candidate top lane line and the initial top line is less than or equal to a preset angle threshold value.

Further, the initial side walls comprise tunnel inner middle section side walls related to a sinking road, front section side walls and rear section side walls, wherein the tunnel outer front section side walls and the rear section side walls are located at two ends of the middle section side walls; the candidate top end lane lines comprise a front section top end lane line corresponding to the front section side wall and a rear section top end lane line corresponding to the rear section side wall; the bottom lane line comprises a front section bottom lane line, a middle section bottom lane line and a rear section bottom lane line which correspond to the front section side wall.

Determining a target top lane line based on the candidate top lane lines satisfying a preset condition, including:

determining a middle section broken line based on the front section top end lane line and the rear section top end lane line, and the front section bottom end lane line, the middle section bottom end lane line and the rear section bottom end lane line in the candidate top end lane lines meeting preset conditions;

and determining the top end line of the target lane of the target side wall based on the front section top end lane line, the rear section top end lane line and the middle section folding line.

Further, based on the front section top lane line and the rear section top lane line in the candidate top lane line satisfying the preset condition, and the front section bottom lane line, the middle section bottom lane line and the rear section bottom lane line determining the middle section broken line, include:

determining a first offset vector of a tail end point of the front section top lane line relative to a tail end point of the front section bottom lane line, and determining a second offset vector of a head end point of the rear section top lane line relative to a head end point of the rear section bottom lane line;

and performing linear interpolation between a tail end point of the front section top lane line and a head end point of the rear section top lane line based on the first offset vector, the second offset vector and position coordinates of each point on the middle section bottom lane line to obtain the middle section broken line.

Further, based on the first offset vector, the second offset vector, and the position coordinates of each point on the middle section bottom lane line, performing linear interpolation between the tail end point of the front section top lane line and the head end point of the rear section top lane line to obtain the middle section broken line, including:

performing vector decomposition on the first offset vector in the direction of a broken line of a tail end point of the front section top end lane line and the direction of a vertical broken line to obtain a first horizontal offset component and a first vertical offset component, and performing vector decomposition on the second offset vector in the direction of a broken line of a head end point of the rear section top end lane line and the direction of a vertical broken line to obtain a second horizontal offset component and a second vertical offset component;

calculating the length ratio of the length from each point on the lane line at the bottom end of the middle section to one end point of the lane line at the bottom end of the middle section to the total length of the lane line at the bottom end of the middle section;

performing linear interpolation of the length between the tail end point of the front section top lane line and the tail end point of the rear section top lane line based on the length proportion and the first horizontal offset component, the first vertical offset component, the second horizontal offset component and the second vertical offset component to obtain offset lengths of interpolation points corresponding to the points on the middle section bottom lane line;

determining a third offset vector of the interpolation point and each point corresponding to the interpolation point on the middle section bottom end lane line based on the offset lengths of each point on the middle section bottom end lane line in the broken line direction and the vertical broken line direction of the middle section bottom end lane line;

determining the position coordinates of the interpolation point based on the third offset vector and the position coordinates of each point corresponding to the interpolation point on the lane line at the bottom end of the middle section;

and determining the middle section broken line based on the tail end point of the front section top end lane line, the head end point of the rear section top end lane line and the position coordinates of the interpolation points.

Further, generating a target side wall of the sinking road based on the bottom end lane line and the target top end lane line includes:

determining position coordinates of each point on a bottom corner line based on plane coordinates of each point on the target top end lane line and height coordinates of a point on the bottom end lane line which is closest to each point on the target top end lane line on a horizontal plane;

generating a bottom surface of the target side wall based on the bottom corner line and the bottom end lane line;

and generating a vertical wall surface of the target side wall based on the target top lane line and the bottom corner line.

Further, the method further comprises:

acquiring a bottom lane line associated with the initial side wall based on the initial data of the side wall, and forming an initial lane line set;

taking one bottom lane line in the initial lane line set as a search lane line corresponding to the current initial side wall;

taking out candidate bottom lane lines which are communicated with the search lane line in front and back from the initial lane line set;

when the candidate bottom lane line belongs to the initial lane line set or the lane line attribute of the candidate bottom lane line includes a tunnel wall, adding the candidate bottom lane line into a target bottom lane line set, determining the candidate bottom lane line as a next search lane line, skipping to a step of taking out the candidate bottom lane line which is connected with the search lane line from the initial lane line set, repeating the execution until a search stop condition is met, and then skipping to a step of determining a plurality of candidate bottom lane lines which are connected with each other in the target bottom lane line set in the front-back direction as the bottom lane line which is associated with the current target side wall;

determining a length of the candidate bottom lane line when the candidate bottom lane line does not belong to the initial set of lane lines and a lane line attribute of the candidate bottom lane line does not include a tunnel wall;

when the length of the candidate bottom lane line is smaller than a preset length allowable threshold value, adding the candidate bottom lane line into a target bottom lane line set, subtracting the length of the candidate bottom lane line from the preset length allowable threshold value, determining the candidate bottom lane line as a next search lane line, skipping to a step of taking out candidate bottom lane lines which are communicated with the search lane line from the initial lane line set, repeating the step until a search stop condition is met, and skipping to a step of determining a plurality of candidate bottom lane lines which are communicated with each other from front to back in the target bottom lane line set as bottom lane lines associated with a current target side wall;

determining a plurality of candidate bottom lane lines which are communicated back and forth in the target bottom lane line set as bottom lane lines associated with the current target side wall;

and when the initial lane line set is not empty, skipping to a step of taking one bottom lane line in the initial lane line set as a search lane line, and searching the bottom lane line associated with the next initial side wall.

In a second aspect, the present disclosure provides a high-precision map generation method, which generates a target side wall associated with a sinking road in a high-precision map by using the method of the first aspect.

In a third aspect, an embodiment of the present disclosure provides a data generating apparatus, including:

the system comprises a first acquisition module, a second acquisition module and a third acquisition module, wherein the first acquisition module is configured to acquire side wall initial data of a side wall of a sinking road; the side wall initial data comprises a bottom end lane line associated with a sinking road, an initial side wall associated with the bottom end lane line and an initial top end line associated with the initial side wall;

a merging module configured to merge initial side walls belonging to the same sinking road based on the bottom lane line to form merged side walls;

a first determination module configured to determine a target top lane line based on the initial top line of the merged side wall association; the target top lane line is an edge lane line of the top road associated with the initial side wall;

a first generation module configured to generate a target side wall of the sinking road based on the bottom lane line and the target top lane line.

The functions can be realized by hardware, and the functions can also be realized by executing corresponding software by hardware. The hardware or software includes one or more modules corresponding to the above-described functions.

In one possible design, the apparatus includes a memory configured to store one or more computer instructions that enable the apparatus to perform the corresponding method, and a processor configured to execute the computer instructions stored in the memory. The apparatus may also include a communication interface for the apparatus to communicate with other devices or a communication network.

In a fourth aspect, the disclosed embodiments provide an electronic device comprising a memory, a processor, and a computer program stored on the memory, wherein the processor executes the computer program to implement the method of any of the above aspects.

In a fifth aspect, the disclosed embodiments provide a computer-readable storage medium for storing computer instructions for any one of the above apparatuses, which when executed by a processor, are configured to implement the method of any one of the above aspects.

In a sixth aspect, the disclosed embodiments provide a computer program product comprising computer instructions for implementing the method of any one of the above aspects when executed by a processor.

The technical scheme provided by the embodiment of the disclosure can have the following beneficial effects:

in the embodiment of the disclosure, for a side wall of a sinking road, a bottom lane line associated with the sinking road, an initial side wall associated with the sinking road and an initial top line associated with the initial side wall which are already in side wall initial data are obtained, and the initial side walls belonging to the same sinking road are merged by using the bottom lane line to form a merged side wall; and then determining a target top lane line based on the initial top line associated with the merged side wall, and generating a target side wall of the sinking road based on the bottom lane line and the target top lane line. By the mode, the side walls of the sinking part and the rising part of the same sinking road can be combined into a whole, so that the display effect of modeling and rendering of the sinking road is enhanced; meanwhile, the method overcomes the defects that the side wall is not tightly attached to the road and the side wall of the sinking part and the side wall of the rising part of the sinking road are separated due to the fact that the side wall initial data are directly adopted to generate the sinking road in the prior art.

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.

Drawings

Other features, objects, and advantages of the present disclosure will become more apparent from the following detailed description of non-limiting embodiments when taken in conjunction with the accompanying drawings. The following is a description of the drawings.

Fig. 1 shows a flow diagram of a data generation method according to an embodiment of the present disclosure.

Fig. 2 illustrates a side wall initial data effect diagram of a sinking road side wall according to an embodiment of the present disclosure.

Fig. 3 shows a schematic view of the effect after the lane line is segmented according to an embodiment of the present disclosure.

Fig. 4 shows a block diagram of a data generation apparatus according to an embodiment of the present disclosure.

Fig. 5 is a schematic structural diagram of an electronic device suitable for implementing a data generation method and/or a high-precision map generation method according to an embodiment of the present disclosure.

Detailed Description

Hereinafter, exemplary embodiments of the present disclosure will be described in detail with reference to the accompanying drawings so that those skilled in the art can easily implement them. Also, for the sake of clarity, parts not relevant to the description of the exemplary embodiments are omitted in the drawings.

In the present disclosure, it is to be understood that terms such as "including" or "having," etc., are intended to indicate the presence of the disclosed features, numbers, steps, actions, components, parts, or combinations thereof, and do not preclude the possibility that one or more other features, numbers, steps, actions, components, parts, or combinations thereof are present or added.

It should be further noted that the embodiments and features of the embodiments in the present disclosure may be combined with each other without conflict. The present disclosure will be described in detail below with reference to the accompanying drawings in conjunction with embodiments.

The details of the embodiments of the present disclosure are described in detail below with reference to specific embodiments.

Fig. 1 shows a flow diagram of a data generation method according to an embodiment of the present disclosure. As shown in fig. 1, the data generation method includes the steps of:

in step S101, side wall initial data of a side wall of a sinking road is obtained; the side wall initial data comprises a bottom end lane line associated with a sinking road, an initial side wall associated with the bottom end lane line and an initial top end line associated with the initial side wall;

in step S102, merging initial side walls belonging to the same sinking road based on the bottom lane line to form a merged side wall;

in step S103, determining a target top lane line based on the initial top line associated with the merged side wall; the target top lane line is an edge lane line of the top road associated with the initial side wall;

in step S104, a target side wall of the sinking road is generated based on the bottom end lane line and the target top end lane line.

In this embodiment, the data generation method may be executed in a server or a cloud. The initial data of the side wall of the sinking road can be obtained by processing collected data, wherein the collected data can comprise image data, point cloud data and the like collected by collecting equipment on collecting vehicles running on the road. The side wall initial data of the side wall of the sinking road may include a bottom lane line of the sinking road, an initial side wall associated with the bottom lane line, an initial top line associated with the initial side wall, and the like. It should be noted that the initial side wall is a plane where the bottom lane line and the initial top line are located, and the initial top line is not a lane line on the top lane.

Fig. 2 is a schematic view illustrating side wall initial data effect of a sinking road side wall according to an embodiment of the present disclosure. As shown in fig. 2, the two sides of the sinking road are top roads, the sinking road and the top roads are connected through side walls, the sinking road has a certain height difference relative to the top roads, and the height difference is the height of the side walls. The bottom edge line of the side wall in the side wall initial data is the bottom lane line, while the top end line of the side wall is not usually the edge lane line on the top road, and the top end line is a line closer to the edge lane line. As can be seen from fig. 2, the sinking portion of the sinking road extends to one end of the tunnel, while the rising portion of the sinking road, opposite to the sinking portion, extends from the other end of the tunnel.

In the initial data of the side walls of the sinking road, the sinking portion and the rising portion of the same sinking road are expressed separately, that is, the side walls of the same sinking road are expressed as a plurality of initial side walls in the initial data of the side walls, each initial side wall corresponds to a respective initial top end line, and the initial top end lines related to the initial side walls of the same sinking road are disconnected and discontinuous at least in the tunnel part. Therefore, in the embodiment of the present disclosure, the initial side walls belonging to the same sinking road are searched by associating the bottom lane lines with the same sinking road, and the initial side walls are merged to form a complete merged side wall, which is the complete side wall of the same sinking road seen in the real world. Then, a corresponding continuous target top lane line is found based on the complete side wall and the discontinuous initial top line.

It can be understood that the top roads corresponding to the sinking roads are continuous in the tunnel portion, so that the sinking portion and the rising portion of a target top lane line on the same sinking road can be found to be located at the top of the side wall, and are closer to the initial top line, so that after the entry top lane line is found, the entry top lane line can be used as the top line of the merged side wall, and the bottom lane line associated with the merged side wall can be used as the bottom line of the merged side wall to generate the target side wall. In some embodiments, the target side wall may lie in a plane connecting the target top lane line and the target bottom lane line.

In the embodiment of the disclosure, for a side wall of a sinking road, a bottom lane line associated with the sinking road, an initial side wall associated with the sinking road and an initial top line associated with the initial side wall which are already in side wall initial data are obtained, and the initial side walls belonging to the same sinking road are merged by using the bottom lane line to form a merged side wall; and then determining a target top lane line based on the initial top line associated with the merged side wall, and generating a target side wall of the sinking road based on the bottom lane line and the target top lane line. By the method, the side walls of the sinking part and the rising part of the same sinking road can be combined into a whole, so that the display effect of modeling and rendering of the sinking road is enhanced; meanwhile, the method overcomes the defects that the side wall is not tightly attached to the road and the side wall of the sinking part and the side wall of the rising part of the sinking road are separated due to the fact that the side wall initial data are directly adopted to generate the sinking road in the prior art.

In an optional implementation manner of this embodiment, in step S102, that is, the step of combining the initial side walls belonging to the same sinking road based on the bottom lane line to form a combined side wall further includes the following steps:

In this optional implementation, all bottom lane lines belonging to the same sinking road may be found from the side wall initial data, so that all bottom lane lines are sequentially connected to form a continuous complete bottom lane line based on the extending direction of the sinking road. And all the initial side walls associated with the complete bottom lane line can also be combined in sequence according to the connection sequence of the bottom lane line to form combined side walls.

In an optional implementation manner of this embodiment, in step S103, the step of determining a target top lane line based on the initial top line associated with the merged side wall further includes the following steps:

determining a second point on the bottom end lane line, which is the smallest plane distance from any first point on the initial top end line;

determining candidate top lane lines which are within a preset distance range from the plane of any first point on the initial top line and are positioned at the edge of the top road;

In this alternative implementation, when determining the target top lane line, a point (referred to as a second point herein) closest to the plane on the corresponding bottom lane line is calculated according to each point (referred to as a first point herein for distinguishing from points on other lines thereafter) on the initial top line associated with each of the initial side walls in the merged side walls, and the height of the second point is recorded as Z0.

And calculating candidate top lane lines with the plane distance within the preset distance range and positioned at the edge of the top road according to each first point on the initial top line, calculating a point (referred to as a third point) with the closest plane distance from the first point to each candidate top lane line, and recording the height Zi of the third point.

Selecting a candidate top lane line closest to the initial top line from candidate top lane lines simultaneously satisfying the following three conditions, and determining the candidate top lane line closest to the initial top line as the top lane line associated with each initial side wall in the merged side walls:

1) the closest distance to the plane of the initial tip line is less than a distance threshold.

2) Zi-Z0 is not less than a preset height threshold.

3) The included angle between the direction of the candidate top lane line and the direction of the candidate bottom lane line is not more than a preset angle threshold value.

A target top lane line is determined based on the top lane lines associated with each of the initial side walls.

In an optional implementation manner of this embodiment, the initial side wall includes a tunnel inner middle section side wall associated with a sinking road, a front section side wall and a rear section side wall, which are located outside the tunnel at two ends of the middle section side wall; the candidate top end lane lines comprise a front section top end lane line corresponding to the front section side wall and a rear section top end lane line corresponding to the rear section side wall; the bottom end lane line comprises a front section bottom end lane line, a middle section bottom end lane line and a rear section bottom end lane line which correspond to the front section side wall;

the step of determining a target top lane line based on the candidate top lane lines satisfying a preset condition further includes the steps of:

In this optional implementation, in order to find an edge lane line that is closer to the sinking road on the top road associated with the sinking road, the edge lane line is used as a target top lane line, so as to model a target side wall of the sinking road, and the merged side wall may be segmented. As described above, the sinking road may include a sinking portion outside the tunnel, a rising portion, and a portion inside the tunnel. The side walls associated with the sinking road section in the tunnel need not be represented in the high-precision map as they are covered by the top road at the tunnel. The side walls of the ascending portion and the descending portion of the sinking road need to be expressed in a high-precision map, and in order to form the ascending portion and the descending portion of the sinking road into a whole effect in a visual sense, a top end line connecting the two side walls needs to be found, and the top end line can be expressed through an edge lane line on the side of the sinking road on the top road.

To find the edge lane line, i.e., the target top lane line mentioned above, the merged side wall is divided into a front section side wall and a rear section side wall at both ends of the tunnel, and the front section and the rear section can be determined based on a sinking portion and a rising portion of the sinking road, for example, the sinking portion of the sinking road is the front section side wall, the rising portion is the rear section side wall, and the inside of the tunnel is the middle section side wall. Correspondingly, the bottom lane line and the initial top line are also segmented according to the mode, the sinking part corresponding to the sinking road is a front section bottom lane line and a front section initial top line, the rising part corresponding to the sinking road is a rear section bottom lane line and a rear section initial top line, and the part in the tunnel is a middle section bottom lane line and a middle section initial top line.

It is understood that the initial top line associated with the initial side wall included in the side wall initial data of the sinking road side wall includes only the initial top lines associated with the side walls associated with the sinking portion and the rising portion of the sinking road, and the initial top line associated with the side wall within the tunnel is not expressed; the top lane line found based on the initial top line associated with the initial side wall also only includes a front section top lane line and a rear section top lane line, and a middle section top lane line corresponding to the tunnel portion does not exist, so that a middle section broken line between the front section top lane line and the rear section top lane line is determined based on the existing front section top lane line, the rear section top lane line, the front section bottom lane line, the middle section bottom lane line and the rear section top lane line, the head and the tail sections of the middle section broken line are respectively connected with the front section top lane line and the rear section top lane line, and the deviation between the plane position of each point on the middle section broken line and the plane position of each corresponding point on the middle section bottom lane line is consistent, and the broken line direction of each point on the middle section broken line and the broken line direction of each corresponding point on the middle section bottom lane line are consistent, and the height difference between each point on the middle section broken line and each corresponding point on the middle section bottom line is on the broken line The first height difference between the point (which is a known point, namely the tail end point of the front section top lane line) and the head end point of the middle section bottom lane line, and the second height difference between the middle section tail end point (which is a known point, namely the head end point of the rear section top lane line) and the tail end point of the middle section bottom lane line are uniformly distributed. It should be noted that, each point on the middle segment folding line and the corresponding point on the middle segment bottom lane line can be understood as a one-to-one correspondence relationship on the vertical plane of the target side wall.

After the middle section broken line is determined, the front section top end lane line, the middle section broken line and the rear section top end lane line can be connected end to obtain a target top end lane line. The front section top lane line, the middle section broken line, the rear section top lane line, the front section bottom lane line, the middle section bottom lane line and the rear section bottom lane line are shown in fig. 3.

In an optional implementation manner of this embodiment, the step of determining a target top lane line based on the candidate top lane line meeting a preset condition further includes the following steps:

and performing linear interpolation between a tail end point of the front section top lane line and a head end point of the rear section top lane line based on the first offset vector, the second offset vector and position coordinates of each point on the middle section bottom lane line to obtain the middle section folding line.

In this alternative implementation, as described above, the plane positions of the points on the middle-section folding line (i.e., the positions in the direction of X, Y) are offset from the plane positions of the corresponding points on the middle-section bottom lane line, the folding line direction of the points on the middle-section folding line is identical to the folding line direction of the corresponding points on the middle-section bottom lane line, and the height differences between the points on the middle-section folding line and the corresponding points on the middle-section bottom lane line are uniformly distributed between the first height difference between the first end point (which is a known point, i.e., the tail end point of the front-section top lane line) and the first end point of the middle-section bottom lane line, and the second height difference between the tail end point (which is a known point, i.e., the first end point of the rear-section top lane line) and the tail end point of the middle-section bottom lane line. Therefore, when determining the position coordinates of each point on the middle segment broken line, the plane position offset and the broken line direction of each point relative to the corresponding point on the bottom lane line can be determined firstly.

For this purpose, in the embodiment of the present disclosure, first, a first offset vector in the polyline direction and the vertical polyline direction of a tail end point of a front section top lane line (the tail end point also corresponds to a head end point of a middle section polyline) relative to a tail end point of a front section bottom lane line is determined, and a second offset vector in the polyline direction and the vertical polyline direction of a head end point of a rear section top lane line (the head end point corresponds to a tail end point of a middle section polyline) relative to a head end point of a rear section bottom lane line is determined, and a middle section polyline is obtained by performing linear interpolation between the tail end point of the front section top lane line and the head end point of the rear section top lane line based on the first offset vector, the second offset vector and position coordinates of each point on the middle section bottom lane line; the deviation of each point on the middle section broken line obtained by linear interpolation relative to each corresponding point on the middle section bottom lane line in the broken line direction and the vertical broken line direction is related to a first deviation vector and a second deviation vector, the broken line direction of each point on the middle section broken line is consistent with the broken line direction of each corresponding point on the middle section bottom lane line (namely the broken line direction of each point on the middle section bottom lane line), and the height difference between each point on the middle section broken line and each corresponding point on the middle section bottom lane line is also related to the first deviation vector and the second deviation vector, so that each point between the head end point and the tail end point of the middle section broken line can be obtained by linear interpolation based on the first deviation vector, the second deviation vector and the position coordinates of each point on the middle section bottom lane line.

In an optional implementation manner of this embodiment, based on the first offset vector, the second offset vector, and position coordinates of each point on the middle section bottom lane line, performing linear interpolation between a tail end point of the front section top lane line and a head end point of the rear section top lane line to obtain the middle section broken line includes:

In this alternative implementation, as described above, the two end points of the middle section broken line include the tail end point of the front section top lane line and the head end point of the rear section top lane line, and the broken line direction of each point on the middle section broken line is consistent with the broken line direction of the corresponding point on the middle section bottom lane line. In order to obtain other points on the middle section broken line except for two end points, offset vectors of interpolation points corresponding to the points on the middle section bottom end lane line relative to the points can be found. In order to find the position of the interpolation point more accurately, the embodiment of the present disclosure decomposes the offset vector of the interpolation point and each corresponding point on the middle section bottom end lane line into two components in the polyline direction and the vertical polyline direction. The direction of the fold line is a direction along the middle fold line, and the direction of the vertical fold line is a direction perpendicular to the direction of the fold line.

The offset vectors of two end points of the middle section broken line relative to two end points of the middle section bottom lane line are a first offset vector and a second offset vector, vector decomposition can be firstly carried out on the broken line direction and the vertical broken line direction of the first offset vector and the second offset vector to obtain a first horizontal offset component and a first vertical offset component corresponding to the first offset vector, and a second horizontal offset component and a second vertical offset component corresponding to the second offset vector.

Because the interpolation points correspond to each point on the middle section bottom lane line, the length distribution of each point on the middle section bottom lane line is consistent with the length distribution of each interpolation point on the middle section broken line, so that the length proportion of each point can be calculated firstly based on the length of each point on the middle section bottom lane line from one end point (which can be a head end point or a tail end point) of the middle section bottom lane line and the total length of the middle section bottom lane line, and the length proportion can express the length distribution information of each point on the middle section bottom lane line.

Based on the length scale of each point and the first horizontal offset component, the first vertical offset component, the second horizontal offset component, and the second vertical offset component, linear interpolation of the length can be carried out between the tail end point of the front section top lane line and the tail end point of the rear section top lane line to obtain the offset lengths of interpolation points corresponding to the points on the middle section bottom lane line in the broken line direction and the vertical broken line direction, and further determining a third offset vector of the interpolation point relative to corresponding points on the lane line at the bottom end of the middle section based on the offset lengths in the broken line direction and the vertical broken line direction, and based on the third offset vector and the position coordinates of the corresponding points on the lane line of the bottom vehicle at the bottom end of the middle section, the position coordinates of each interpolation point can be determined, and then the middle segment broken line is obtained by connecting two end points on the middle segment broken line with each interpolation point.

The following is a detailed description of one implementation example.

As described above, by searching and processing the side wall initial data of the side wall of the sinking road, the following 5 lane lines can be obtained: a front section bottom end lane line, a middle section bottom end lane line, a rear section bottom end lane line, a front section top end lane line and a rear section top end lane line of the side wall; and the middle-segment broken line (expressed by the middle-segment broken line because it is not a lane line) between the front-segment top-end lane line and the rear-segment top-end lane line is unknown, so the embodiment of the present disclosure proposes the following method for calculating the middle-segment broken line between the front-segment top-end lane line and the rear-segment top-end lane line:

1. each of the points of the known 5 lane lines (each lane line is described by each point on the lane line in the side wall initial data) was connected in series to form 1 fold line, and the direction of the fold line was made to coincide with the direction of the lane line.

2. Obtaining 2 tail end points of the front section top end lane line and the front section bottom end lane line, and 2 head end points of the rear section top end lane line and the rear section bottom end lane line, respectively calculating the offsets of the corresponding points in three directions of X, Y, Z, and recording as a first Offset vector Offset0 and a second Offset vector Offset 1.

3. With the middle bottom lane line as a reference, the 2 Offset vectors Offset0 and Offset1 are used as the whole head-to-tail Offset vectors. The head-to-tail integral offset vectors are subjected to vector decomposition in the directions of the head and tail points of the polyline respectively, and a first vertical offset component ValueH0, a first horizontal offset component ValueV0, a second vertical offset component ValueH1 and a second horizontal offset component ValueV1 along the direction of the polyline and the direction of the vertical polyline are calculated. The horizontal offset component is an offset component in the direction of the polygonal line, and the vertical offset component is an offset component in the direction of the vertical polygonal line.

4. And calculating the length of each point from the head end point of the middle-section bottom lane line along the broken line in the middle-section bottom lane line, and dividing the length by the whole length of the middle-section bottom lane line to be used as the length Ratio of the current point on the middle-section bottom lane line.

5. According to the length proportion of each point of middle section bottom lane line, with the linear interpolation of the length along broken line direction, perpendicular broken line direction of the head and the tail point of middle section bottom lane line, obtain offset length ValueHi, ValueVi along broken line direction, perpendicular broken line direction of each point as following calculation:

ValueHi = ValueH0 * (1 - Ratio) + ValueH1 * Ratio

ValueVi = ValueV0 * (1 - Ratio) + ValueV1 * Ratio

6. calculating the direction Hi along the broken line and the direction Vi along the vertical broken line of each point of the lane line at the bottom end of the middle section, and calculating a third Offset vector Offset _ i of each point of the lane line at the bottom end of the middle section according to the Offset lengths ValueHi and ValueVi along the broken line and the direction of the vertical broken line as follows:

Offset_i = Hi * ValueHi + Vi * ValueVi

7. and calculating the position of each point on the lane line at the top end of the middle section according to the third offset vector of each point of the lane line at the bottom end of the middle section and the original position of each point of the lane line at the bottom end of the middle section.

In an optional implementation manner of this embodiment, the step S104 of generating a target side wall of the sinking road based on the bottom lane line and the target top lane line includes:

determining position coordinates of each point on a bottom corner line based on the plane coordinates of each point on the target top end lane line and the height coordinates of the point on the bottom end lane line which is closest to each point on the target top end lane line on a horizontal plane;

generating a bottom surface of the target side wall based on the bottom corner line and the bottom lane line;

In the optional implementation mode, in order to enhance the display effect of modeling rendering, the target side wall is generated in a mode that the single side wall is split into the bottom surface and the vertical side surface, so that the rendering effect of the generated target side wall is more stereoscopic, and gaps and holes cannot occur between the target side wall and a sinking road.

In some embodiments, each point on the target top lane line is calculated as the closest point to the bottom lane line on a two-dimensional plane (which may be understood as a horizontal plane, i.e., an XY plane), and the height of the closest point to the bottom lane line (i.e., the closest point to each point on the target top lane line on the horizontal plane) is obtained. And combining the plane coordinates of the point on the top lane line of the target and the height of the closest point on the bottom lane line of the target to generate a new coordinate point, wherein the new coordinate point is used as the point of the bottom corner line of the target side wall.

The bottom lane lines and bottom corner lines create horizontal planes as the bottom surfaces of the target side walls, while the target top lane lines and bottom corner lines create vertical planes as the vertical wall surfaces of the target side walls.

In an optional implementation manner of this embodiment, the method further includes the following steps:

taking one bottom lane line in the initial lane line set as a current search lane line corresponding to the initial side wall;

when the length of the candidate bottom lane line is smaller than a preset length allowable threshold, adding the candidate bottom lane line into a target bottom lane line set, subtracting the length of the candidate bottom lane line from the preset length allowable threshold, determining the candidate bottom lane line as a next search lane line, skipping to a step of taking out the candidate bottom lane line which is connected with the search lane line from the initial lane line set, repeating the execution until a search stop condition is met, and skipping to a step of determining a plurality of candidate bottom lane lines which are connected with each other from front to back in the target bottom lane line set as the bottom lane line which is associated with the current target side wall;

In this alternative implementation, in the side wall initial data of the sinking road side wall, a complete side wall is expressed in a segmented manner, for example, the complete side wall is expressed by being divided into a sinking portion and a rising portion, but this manner may cause a phenomenon such as misalignment between the sinking portion and the rising portion after rendering. In the present disclosure, the sinking portion and the rising portion of the sinking road are combined to form a whole, and then an integral side wall is regenerated. The step of merging the sinking road-related data may be performed before step S102.

In order to generate the whole side wall of the sinking road, the embodiment of the disclosure finds all bottom lane lines from the side wall initial data of the side wall of the sinking road, forms an initial bottom lane line set, and sets a preset length allowable threshold. The purpose of setting the predetermined length tolerance threshold is to avoid a break in the middle of the originally same complete side wall due to the side wall initial data representation. And searching bottom lane lines related to the same side wall from the initial bottom lane line set to form a target bottom lane line set, wherein one target bottom lane line set corresponds to one complete side wall.

In some embodiments, the search stop condition comprises: the candidate bottom lane lines which are communicated front and back are not unique, the initial bottom lane line set is empty, or the length of the candidate bottom lane line is greater than or equal to a preset length allowable threshold value.

The search process is described in detail below:

starting searching by using a first initial bottom lane line (which can be any one) in the initial bottom lane line set, searching candidate bottom lane lines which are communicated with the bottom lane line in front and back, and judging whether the searched candidate bottom lane lines meet any one of the following conditions:

1) in the initial set of bottom lane lines.

2) The lane line attribute is a tunnel wall.

In the first case, if the candidate bottom lane line having the front-rear connection relationship is unique and satisfies any one of the above conditions, the candidate bottom lane line is recorded to the target bottom lane line set in the front-rear connection relationship, and a new search is started with the candidate bottom lane line.

In the second case, if the candidate bottom lane line with the front-back connection relation is unique but does not satisfy any of the above conditions, the length of the candidate bottom lane line is calculated, if the length does not exceed the preset length allowable threshold, the length of the candidate lane line is subtracted from the preset length allowable threshold to serve as a new preset length allowable threshold, the candidate bottom lane line is recorded to the target bottom lane line according to the front-back connection relation, and the front-back search is continued by the candidate bottom lane line. And if the length exceeds the preset length allowable threshold, stopping the current search, wherein the front-back communicated bottom lane lines in the target bottom lane line set are all bottom lane lines associated with the side wall corresponding to the current search.

And if the candidate bottom lane lines with the front-back connection relation are not unique, stopping the current search, wherein the front-back connected bottom lane lines in the target bottom lane line set are all bottom lane lines associated with the side wall corresponding to the current search.

If the initial bottom lane line set is not empty, starting the next search with the first initial bottom lane line in the remaining initial bottom lane line set, that is, generating a target bottom lane line set including all bottom lane lines associated with the next side wall.

After the initial bottom lane line set is empty or the above-mentioned condition for stopping the search is satisfied, one or more target bottom lane line sets may be obtained, each of which corresponds to a complete target side wall. Therefore, a plurality of candidate bottom lane lines which are connected in the front-rear direction in one target bottom lane line set can be connected according to the sequence relation to be determined as the bottom lane line associated with the corresponding initial side wall.

In addition, since the preset allowable length threshold is set, a situation that a bottom lane line which is not associated with the current initial side wall may exist at the head and tail parts in the searched target bottom lane line set, therefore, the minimum and maximum lane line indexes meeting the above conditions 1) or 2) can be calculated for all the lane lines connected in front and at the back in the target bottom lane line set, the lane line with the index between the minimum and maximum indexes is reserved, and the lane lines except the minimum and maximum indexes introduced at the head and tail parts due to the setting of the preset allowable length threshold are excluded.

In addition, non-sinking road side walls, such as those of viaducts, may be excluded. If there is no lane line of the tunnel wall attribute in the continuous lane lines of the target bottom lane line set, it may be determined that the target bottom lane line set corresponds to a non-sinking road, and therefore, the target bottom lane line set may be excluded.

In an optional implementation manner of this embodiment, before the step S102 of merging initial side walls belonging to the same sinking road based on the bottom lane line to form a merged side wall, the method further includes the following steps:

searching all front section bottom end lane lines determined from the side wall initial data of the side wall of the sinking road forward along the front section bottom end lane lines, and searching all rear section bottom end lane lines determined from the side wall initial data of the side wall of the sinking road backward along the front section bottom end lane lines, wherein the search stopping condition comprises:

firstly, the distance from the current search point to the flow guide belt does not exceed a distance threshold value; the diversion belt is closest to the current bottom lane line direction;

the second, the distance searched forward or backward exceeds the preset distance;

thirdly, other bottom end lane lines connected with the front section bottom end lane line or the rear section bottom end lane line are not searched forwards or backwards;

if the first condition is met, merging the searched bottom lane line into a front section bottom lane line or a rear section bottom lane line;

and if the second and/or third stripes are satisfied, the currently searched bottom lane line is an invalid lane line.

In an optional implementation manner of this embodiment, before the step of determining a target top lane line based on the candidate top lane line meeting a preset condition, the method further includes the following steps:

selecting a target top lane line closest to the direction of the top line of the initial side wall from all target top lane lines determined by using the initial top line as an initial top lane line for searching, and recording the current initial top lane line to a target top line set;

searching the associated candidate top lane line forwards or backwards along the two ends of the initial top lane line respectively, and stopping searching if one of the following conditions is met:

after the target top lane lines with the virtual line attributes are removed, the residual quantity in all the target top lane lines related to the current single direction is not equal to 1;

the searched unique target top lane line is recorded in the target top line set;

the range of the searched unique target top end lane line in the head-tail direction of the target top end lane line is not intersected with the range of the original initial top end line in the head-tail direction;

and if the search stopping condition is not met, taking the searched unique target top lane line as the next initial top lane line, and continuing searching and recording until the search is stopped.

It should be noted that the target top lane line may also be detected in a manner of extending the front-back search of the bottom lane line in the foregoing, so as to merge the target top lane lines belonging to the same side wall.

According to the high-precision map generation method, the target side wall related to the sinking road in the high-precision map is generated by the data generation method.

In this embodiment, the high-precision map generation method may be executed on a server, and when the collection vehicle runs on a road, the collection vehicle collects the collection data such as image data and point cloud data of the sinking road and the side wall of the sinking road from the collection point, and transmits the collection data and the corresponding collection point to the server for processing. The server may extract side wall initial data of the side wall of the sinking road from the collected data, the side wall initial data including a bottom lane line of the sinking road, an initial side wall associated with the bottom lane line, an initial top line associated with the initial side wall, and the like.

After the initial data of the side walls of the sinking road are processed by the data generation method, the target side walls related to the sinking road can be obtained, and the target side walls as a whole express the side walls at two sides of the sinking road. The specific details of the data generation method can be referred to the above description, and are not repeated herein. The target side wall of the sunken road may be made in high-precision map data that may be applied in location-based services, especially in intelligent driving of vehicles.

The following are embodiments of the disclosed apparatus that may be used to perform embodiments of the disclosed methods.

Fig. 4 shows a block diagram of a data generation apparatus according to an embodiment of the present disclosure. The apparatus may be implemented as part or all of an electronic device through software, hardware, or a combination of both. As shown in fig. 4, the data generation apparatus includes:

a first obtaining module 401 configured to obtain side wall initial data of a side wall of a sinking road; the side wall initial data comprises a bottom end lane line associated with a sinking road, an initial side wall associated with the bottom end lane line and an initial top end line associated with the initial side wall;

a merging module 402 configured to merge initial side walls belonging to the same sinking road based on the bottom lane line to form a merged side wall;

a first determining module 403 configured to determine a target top lane line based on the initial top line of the merged side wall association; the target top lane line is an edge lane line of the top road associated with the initial side wall;

a first generating module 404 configured to generate a target side wall of the sinking road based on the bottom lane line and the target top lane line.

In this embodiment, the data generation apparatus may be executed in a server or a cloud. The initial data of the side wall of the sinking road can be obtained by processing collected data, wherein the collected data can comprise image data, point cloud data and the like collected by collecting equipment on collecting vehicles running on the road. The side wall initial data of the side wall of the sinking road may include a bottom lane line of the sinking road, an initial side wall associated with the bottom lane line, an initial top line associated with the initial side wall, and the like. It should be noted that the initial side wall is a plane where the bottom lane line and the initial top line are located, and the initial top line is not a lane line on the top road.

In an optional implementation manner of this embodiment, the merging module includes:

the first determining submodule is configured to determine one or more bottom end lane lines which belong to the same sinking road and are connected in a front-back mode in the side wall initial data;

a second determining submodule configured to determine initial side walls associated with the one or more bottom lane lines of the front-to-back connection;

and the merging submodule is configured to merge the initial side wall according to the front-back connection sequence of the one or more bottom end lane lines connected in front-back to obtain a merged side wall.

and the direction included angle between the candidate top lane line and the initial top line is less than or equal to a preset angle threshold value. The first determining module includes:

a third determination submodule configured to determine a second point on the bottom end lane line that is a minimum planar distance from any first point on the initial top end line;

a fourth determination submodule configured to determine at least one candidate top lane line that is within a preset distance range from a plane of any first point on the initial top lane and is at the top lane edge;

a fifth determination submodule configured to determine a third point on the candidate top end lane line that is closest to a plane distance of any first point on the initial top end line;

a sixth determination submodule configured to determine a target top lane line based on the candidate top lane line satisfying a preset condition; wherein the preset conditions include:

And calculating candidate top lane lines with the plane distance within a preset distance range and positioned at the edge of the top road according to each first point on the initial top lane line, calculating a point (referred to as a third point) with the plane distance from the first point to each candidate top lane line being the nearest, and recording the height Zi of the third point.

2) Zi-Z0 is not less than a preset height threshold.

the sixth determination submodule includes:

a seventh determination sub-module configured to determine a middle section broken line based on the front section top end lane line and the rear section top end lane line, and the front section bottom end lane line, the middle section bottom end lane line, and the rear section bottom end lane line, of the candidate top end lane lines satisfying a preset condition;

an eighth determination submodule configured to determine a target lane top line of the target side wall based on the front section top lane line, the rear section top lane line, and the middle section broken line.

In this optional implementation, in order to find an edge lane line that is closer to the sinking road on the top road associated with the sinking road, the edge lane line is used as a target top lane line, so as to model a target side wall of the sinking road, and the merged side wall may be segmented. As described above, the sinking road may include a sinking portion outside the tunnel, a rising portion, and a portion inside the tunnel. The side wall related to the sinking road part in the tunnel is covered by the top road at the tunnel, so that the side wall does not need to be expressed in a high-precision map. The side walls of the ascending portion and the descending portion of the sinking road need to be expressed in a high-precision map, and in order to form the ascending portion and the descending portion of the sinking road into a whole effect in a visual sense, a top end line connecting the two side walls needs to be found, and the top end line can be expressed through an edge lane line on the side of the sinking road on the top road.

In an optional implementation manner of this embodiment, the seventh determining sub-module includes:

a ninth determining submodule configured to determine a first offset vector of a trailing end point of the leading section top lane line relative to a trailing end point of the leading section bottom lane line, and to determine a second offset vector of a leading end point of the trailing section top lane line relative to a leading end point of the trailing section bottom lane line;

a first interpolation sub-module configured to perform linear interpolation between a tail end point of the front section top lane line and a head end point of the rear section top lane line based on the first offset vector, the second offset vector, and position coordinates of each point on the middle section bottom lane line, to obtain the middle section broken line.

In an optional implementation manner of this embodiment, the first interpolation submodule includes:

a decomposition submodule configured to perform vector decomposition on the first offset vector in a polyline direction and a vertical polyline direction of a tail end point of the front section top lane line to obtain a first horizontal offset component and a first vertical offset component, and perform vector decomposition on the second offset vector in a polyline direction and a vertical polyline direction of a head end point of the rear section top lane line to obtain a second horizontal offset component and a second vertical offset component;

the calculation submodule is configured to calculate the length ratio of the length from each point on the middle section bottom end lane line to one end point of the middle section bottom end lane line to the total length of the middle section bottom end lane line;

a second interpolation submodule configured to perform linear interpolation of length between a tail end point of the front-section top lane line and a tail end point of the rear-section top lane line based on the length ratio and the first horizontal offset component, the first vertical offset component, the second horizontal offset component, and the second vertical offset component, to obtain offset lengths of interpolation points corresponding to points on the middle-section bottom lane line;

a tenth determination submodule configured to determine a third offset vector of the interpolation point and each point corresponding to the interpolation point on the middle section bottom end lane line based on the offset lengths of each point on the middle section bottom end lane line in a polyline direction and a vertical polyline direction of the middle section bottom end lane line;

an eleventh determination sub-module configured to determine position coordinates of the interpolation point based on the third offset vector and position coordinates of points corresponding to the interpolation point on the middle bottom lane line;

a twelfth determination submodule configured to determine the middle polyline based on position coordinates of a trailing end point of the front-section top lane line, a leading end point of the rear-section top lane line, and the interpolation point.

In this alternative implementation, as described above, the two end points of the middle section broken line include the tail end point of the front section top lane line and the head end point of the rear section top lane line, and the broken line direction of each point on the middle section broken line is consistent with the broken line direction of the corresponding point on the middle section bottom lane line. In order to obtain other points on the middle-segment broken line except for the two end points, offset vectors of interpolation points corresponding to the points on the bottom lane line of the middle segment relative to the points can be found. In order to find the position of the interpolation point more accurately, the embodiment of the present disclosure decomposes the offset vector of the interpolation point and each corresponding point on the middle section bottom end lane line into two components in the polyline direction and the vertical polyline direction. The direction of the fold line is a direction along the middle fold line, and the direction of the vertical fold line is a direction perpendicular to the direction of the fold line.

The offset vectors of two end points of the middle section broken line relative to two end points of the middle section bottom lane line are a first offset vector and a second offset vector, vector decomposition can be firstly carried out on the first offset vector, the second offset vector and the vertical broken line direction to obtain a first horizontal offset component and a first vertical offset component corresponding to the first offset vector and a second horizontal offset component and a second vertical offset component corresponding to the second offset vector.

Because the interpolation points correspond to each point on the middle section bottom lane line, the length distribution of each point on the middle section bottom lane line is consistent with the length distribution of each interpolation point on the middle section broken line, so that the length proportion of each point can be calculated based on the length of each point on the middle section bottom lane line from one end point (which can be a head end point or a tail end point) of the middle section bottom lane line and the total length of the middle section bottom lane line, and the length proportion can express the length distribution information of each point on the middle section bottom lane line.

This is explained in more detail below by means of an implementation example.

As described above, by searching and processing the side wall initial data of the side wall of the sinking road, the following 5 lane lines can be obtained: a front section bottom end lane line, a middle section bottom end lane line, a rear section bottom end lane line, a front section top end lane line and a rear section top end lane line of the side wall; and the middle broken line between anterior segment top end lane line and the back end lane line (because not lane line, so describe with the middle broken line) is unknown, so this disclosure embodiment has proposed the following device of calculating the middle broken line between anterior segment top end lane line and the back end lane line:

2. And acquiring 2 tail end points of the front section top lane line and the front section bottom lane line and 2 head end points of the rear section top lane line and the rear section bottom lane line, respectively calculating the offsets of the corresponding points in X, Y, Z three directions, and recording as a first Offset vector Offset0 and a second Offset vector Offset 1.

3. With the middle bottom lane line as a reference, the 2 Offset vectors Offset0 and Offset1 are used as the whole head-to-tail Offset vectors. The head-to-tail integral offset vectors are subjected to vector decomposition in the directions of the head and tail points of the polyline respectively, and a first vertical offset component ValueH0, a first horizontal offset component ValueV0, a second vertical offset component ValueH1 and a second horizontal offset component ValueV1 along the direction of the polyline and the direction of the vertical polyline are calculated. Note that the horizontal offset component is an offset component in the direction of the polygonal line, and the vertical offset component is an offset component in the direction of the vertical polygonal line.

4. And calculating the length of each point from the initial end point of the middle-section bottom lane line along the broken line in the middle-section bottom lane line, dividing the length by the whole length of the middle-section bottom lane line, and taking the length as the length Ratio of the current point on the middle-section bottom lane line.

ValueHi = ValueH0 * (1 - Ratio) + ValueH1 * Ratio

ValueVi = ValueV0 * (1 - Ratio) + ValueV1 * Ratio

6. calculating the direction Hi along the broken line and the direction Vi of the vertical broken line of each point of the middle section bottom lane line, and calculating a third Offset vector Offset _ i of each point of the middle section bottom lane line according to the Offset lengths ValueHi and ValueVi along the broken line and the direction of the vertical broken line as follows:

Offset_i = Hi * ValueHi + Vi * ValueVi

and generating a vertical wall surface of the target side wall based on the target top lane line and the bottom corner line. The first generation module includes:

a thirteenth determination submodule configured to determine position coordinates of each point on a bottom corner line based on plane coordinates of each point on the target top end lane line and height coordinates of a point on the bottom end lane line closest to each point on the target top end lane line on a horizontal plane;

a first generation submodule configured to generate a floor of the target side wall based on the floor angle line and the floor lane line;

a second generation submodule configured to generate a side of the target side wall based on the target top lane line and the base corner line.

In this optional implementation manner, in order to enhance the display effect of the modeling rendering, in this implementation, the target side wall is generated in a manner that a single side wall is split into two parts, namely, a bottom surface and a vertical side surface.

The bottom end lane lines and bottom corner lines create horizontal planes as the bottom surface of the target side wall, while the target top end lane lines and bottom corner lines create vertical planes as the vertical wall surfaces of the target side wall.

In an optional implementation manner of this embodiment, the apparatus further includes:

a second obtaining module configured to obtain a bottom lane line associated with an initial side wall based on the side wall initial data and form an initial lane line set;

a second determining module, configured to take one bottom lane line in the initial lane line set as a search lane line corresponding to the current initial side wall;

a third obtaining module configured to take out a candidate bottom lane line that is in front-to-back communication with the search lane line from the initial lane line set;

a first adding module configured to add the candidate bottom lane line to a target bottom lane line set when the candidate bottom lane line belongs to the initial lane line set or a lane line attribute of the candidate bottom lane line includes a tunnel wall, determine the candidate bottom lane line as a next search lane line, jump to the third acquiring module, repeat the execution until a search stop condition is satisfied, and jump to a fourth determining module;

a third determination module configured to determine a length of the candidate bottom lane line when the candidate bottom lane line does not belong to the initial set of lane lines and a lane line attribute of the candidate bottom lane line also does not include a tunnel wall;

a second adding module, configured to add the candidate bottom lane line to a target bottom lane line set when the length of the candidate bottom lane line is smaller than a preset length allowable threshold, subtract the length of the candidate bottom lane line from the preset length allowable threshold, determine the candidate bottom lane line as a next search lane line, jump to the third obtaining module, repeat the execution until a search stop condition is met, and jump to a fourth determining module;

a fourth determining module configured to determine a plurality of candidate bottom lane lines connected in tandem in the target bottom lane line set as a bottom lane line associated with a current target side wall;

and the skipping module is configured to search for the bottom lane line associated with the next initial side wall after skipping the second determining module when the initial lane line set is not empty.

In this alternative implementation, in the side wall initial data of the sinking road side wall, a complete side wall is expressed in a segmented manner, for example, the complete side wall is expressed by being divided into a sinking portion and a rising portion, but this manner may cause a phenomenon such as misalignment between the sinking portion and the rising portion after rendering. In the present disclosure, the sinking portion and the rising portion of the sinking road are combined to form a whole, and then an integral side wall is regenerated. The above-described module of merging sink road-related data may be performed before the merging module.

In order to generate the whole side wall of the sinking road, the embodiment of the disclosure finds all bottom lane lines from the side wall initial data of the side wall of the sinking road, forms an initial bottom lane line set, and sets a preset length allowable threshold. The purpose of setting the predetermined length tolerance threshold is to avoid a break in the middle of the originally same complete sidewall due to the initial data representation of the sidewall. And searching bottom lane lines related to the same side wall from the initial bottom lane line set to form a target bottom lane line set, wherein one target bottom lane line set corresponds to one complete side wall.

The search process is described in detail below:

starting searching by using a first initial bottom lane line (which can be any one) in the initial bottom lane line set, searching candidate bottom lane lines which are connected with the bottom lane line in front and back, and judging whether the searched candidate bottom lane lines meet any one of the following conditions:

1) in the initial bottom lane line set.

2) The lane line attribute is a tunnel wall.

In addition, since the preset allowable length threshold is set, a situation that a bottom lane line which is not associated with the current initial side wall may exist in the head and tail part of the searched target bottom lane line set, so that the minimum and maximum lane line indexes meeting the above conditions 1) or 2) can be calculated for all the lane lines connected in front and at the back of the target bottom lane line set, the lane line with the index between the minimum and maximum indexes is reserved, and the lane lines except the minimum and maximum indexes introduced in the head and tail part due to the setting of the preset allowable length threshold are excluded.

In an optional implementation manner of this embodiment, before the merging module, the apparatus may further be implemented as:

if the first condition is met, merging the searched bottom lane line into a front section bottom lane line or the rear section bottom lane line;

In an optional implementation manner of this embodiment, before the sixth determining sub-module, the apparatus is further implemented to:

after the target top lane lines with the virtual line attributes are removed, the residual quantity in all the target top lane lines associated with the current single direction is not equal to 1;

the range of the searched unique target top lane line in the head-tail direction of the target top lane line is not intersected with the range of the original initial top lane line in the head-tail direction;

As shown in fig. 5, the electronic device 500 includes a processing unit 501, which may be implemented as a CPU, GPU, FPGA, NPU, or the like processing unit. The processing unit 501 may perform various processes in the embodiments of any one of the methods described above of the present disclosure according to a program stored in a Read Only Memory (ROM) 502 or a program loaded from a storage section 508 into a Random Access Memory (RAM) 503. In the RAM503, various programs and data necessary for the operation of the electronic apparatus 500 are also stored. The processing unit 501, the ROM502, and the RAM503 are connected to each other by a bus 504. An input/output (I/O) interface 505 is also connected to bus 504.

The following components are connected to the I/O interface 505: an input portion 506 including a keyboard, a mouse, and the like; an output portion 507 including a display such as a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and the like, and a speaker; a storage portion 508 including a hard disk and the like; and a communication section 509 including a network interface card such as a LAN card, a modem, or the like. The communication section 509 performs communication processing via a network such as the internet. The driver 510 is also connected to the I/O interface 505 as necessary. A removable medium 511 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on the drive 510 as necessary, so that a computer program read out therefrom is mounted into the storage section 508 as necessary.

In particular, according to embodiments of the present disclosure, any of the methods described above with reference to embodiments of the present disclosure may be implemented as a computer software program. For example, embodiments of the present disclosure include a computer program product comprising a computer program tangibly embodied on a machine-readable medium, the computer program comprising program code for performing any of the methods of embodiments of the present disclosure. In such an embodiment, the computer program may be downloaded and installed from a network through the communication section 509, and/or installed from the removable medium 511.

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 embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, 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 units or modules described in the embodiments of the present disclosure may be implemented by software or hardware. The units or modules described may also be provided in a processor, and the names of the units or modules do not in some cases constitute a limitation of the units or modules themselves.

As another aspect, the present disclosure also provides a computer-readable storage medium, which may be the computer-readable storage medium included in the apparatus in the above-described embodiment; or it may be a separate computer readable storage medium not incorporated into the device. The computer readable storage medium stores one or more programs for use by one or more processors in performing the methods described in the present disclosure.

The foregoing description is only exemplary of the preferred embodiments of the disclosure and is illustrative of the principles of the technology employed. It will be appreciated by those skilled in the art that the scope of the invention in the present disclosure is not limited to the specific combination of the above-mentioned features, but also encompasses other embodiments in which any combination of the above-mentioned features or their equivalents is possible without departing from the inventive concept. For example, the above features and (but not limited to) the features disclosed in this disclosure having similar functions are replaced with each other to form the technical solution.

Claims

1. A method of generating data, comprising:

acquiring side wall initial data of a side wall of a sinking road; the side wall initial data comprise a bottom lane line associated with a sinking road, an initial side wall associated with the bottom lane line and an initial top line associated with the initial side wall;

2. The method of claim 1, wherein merging initial side walls belonging to the same sinking road based on the bottom lane line to form a merged side wall comprises:

determining an initial side wall associated with the one or more bottom lane lines connected in tandem;

3. The method of claim 1 or 2, wherein determining a target headway line based on the initial headway line of the merged sidewall association comprises:

4. The method of claim 3, wherein the initial side walls include a mid-tunnel side wall in a sunken road connection, a front section side wall and a rear section side wall outside the tunnel at opposite ends of the mid-section side wall; the candidate top end lane lines comprise a front section top end lane line corresponding to the front section side wall and a rear section top end lane line corresponding to the rear section side wall; the bottom end lane line comprises a front section bottom end lane line, a middle section bottom end lane line and a rear section bottom end lane line which correspond to the front section side wall;

5. The method of claim 4, wherein determining a middle polyline based on the front section top lane line and the rear section top lane line, and the front section bottom lane line, the middle section bottom lane line, and the rear section bottom lane line of the candidate top lane lines satisfying a preset condition comprises:

6. The method of claim 5, wherein linearly interpolating between a trailing point of the leading section top lane line and a leading point of the trailing section top lane line based on the first offset vector, the second offset vector, and position coordinates of points on the middle section bottom lane line to obtain the middle section polyline comprises:

7. The method of any of claims 1-2, wherein generating the target side wall of the sinking road based on the bottom end lane line and the target top end lane line comprises:

8. The method according to any one of claims 1-2, wherein the method further comprises:

9. A high-precision map generation method, characterized in that the method is used for generating a target side wall related to a sinking road in a high-precision map by using the method of any one of claims 1 to 8.

10. A data generation apparatus, comprising:

11. An electronic device comprising a memory, a processor, and a computer program stored on the memory, wherein the processor executes the computer program to implement the method of any one of claims 1-9.

12. A computer program product comprising computer instructions, characterized in that the computer instructions, when executed by a processor, implement the method of any of claims 1-9.