CN115713600A - Method and device for generating digital elevation model of automatic driving scene - Google Patents

Abstract

The method comprises the steps of dividing terrain points into corresponding slices, generating slice units according to the slices, and recording the elevation values of all the terrain points in the corresponding slices in each slice unit, so that the digital elevation model only comprises the elevation values of all the terrain points and does not comprise the plane position information of all the terrain points, and the occupation of a storage space during storage of the digital elevation model is effectively reduced. In addition, since the storage sequence of the elevation values of the topographic points in the same slicing unit is associated with the positions of the topographic points in the slice, the plane coordinate information of the topographic points can be restored based on the storage sequence of the elevation values of the topographic points in the slicing unit, so that the complete spatial information of the topographic points can be acquired.

Description

Method and device for generating digital elevation model of automatic driving scene

technical field

The present disclosure relates to the technical field of automatic driving, and in particular to a method and device for generating a digital elevation model of an automatic driving scene.

Background technique

With the development of autonomous driving technology, the hardware parameters of lidar are getting better and better, and the cost is getting lower and lower. LiDAR based on vehicle, airborne or other vehicles can obtain high-density and high-precision point cloud data of the target area at low cost and high efficiency. The collected point cloud data can be used to generate a digital elevation model, thereby providing basic terrain data support for high-precision maps, terrain analysis, decision-making planning, etc. in autonomous driving scenarios. However, the digital elevation model in the related art includes the plane position information and the elevation value of each point, which occupies a large storage space.

Contents of the invention

In view of this, the embodiments of the present disclosure provide a method and device for generating a digital elevation model of an automatic driving scene.

The first aspect of the embodiments of the present disclosure provides a method for generating a digital elevation model of an autonomous driving scene. The method includes: acquiring point cloud data of a target operating area of an autonomous driving vehicle, and determining the point cloud data based on the point cloud data. Plane position information and elevation values of multiple topographic points in the target operation area; based on the planar position information of each topographic point, determine the slice to which the corresponding topographic point belongs in the multiple pre-divided slices, and different slices correspond to different plane position ranges ; Generate the digital elevation model of the target operation area based on the elevation value of each topographic point and the slice to which each topographic point belongs, and store the digital elevation model; the digital elevation model includes a plurality of slice units, each slice A unit corresponds to a slice, which is used to record the elevation value of each topographic point in the corresponding slice; the storage order of the elevation value of each topographic point in the same slice unit in the slice unit is related to the position of each topographic point in the slice Associated.

The second aspect of the embodiments of the present disclosure provides a device for generating a digital elevation model of an automatic driving scene, the device includes: a first determination module, configured to obtain point cloud data of the target operation area of the automatic driving vehicle, based on The point cloud data determines the plane position information and elevation values of multiple topographic points in the target operation area; the second determination module is used to determine the corresponding topographic points in multiple pre-divided slices based on the plane position information of each topographic point Different slices correspond to different plane position ranges; the storage module is used to generate the digital elevation model of the target operation area based on the elevation value of each topographic point and the slice to which each topographic point belongs, and perform a digital elevation model on the digital Elevation model is stored; The digital elevation model includes a plurality of slice units, and each slice unit corresponds to a slice, which is used to record the elevation value of each topographic point in the corresponding slice; the elevation value of each topographic point in the same slice unit is in the The storage order in the slice unit is associated with the position of each terrain point in the slice.

A third aspect of the embodiments of the present disclosure provides a computer-readable storage medium on which a computer program is stored, and when the program is executed by a processor, the method of the above-mentioned first aspect is implemented.

The fourth aspect of the embodiments of the present disclosure provides an electronic device, including a memory, a processor, and a computer program stored in the memory and operable on the processor. When the processor executes the program, the above-mentioned first aspects of the method.

The above-mentioned at least one technical solution adopted by the embodiments of the present disclosure can achieve the following beneficial effects: by dividing the topographic points into corresponding slices, and generating slice units according to the slices, recording the information of each topographic point in the corresponding slice in each slice unit In this way, the digital elevation model only includes the elevation value of each topographic point, and does not include the plane position information of each topographic point, thereby effectively reducing the storage space occupied by the digital elevation model during storage. In addition, because the storage order of the elevation values of each topographic point in the same slice unit in the slice unit is associated with the position of each topographic point in the slice, therefore, based on the storage order of the elevation values of the topographic points in the slice unit The plane coordinate information of the terrain points is sequentially recovered, so that the complete spatial information of each terrain point can be obtained based on the recovered plane coordinate information and the stored elevation value. That is, the embodiment of the present disclosure only needs to store the elevation value of the topographic point in the digital elevation model, and can obtain the same effect as simultaneously storing the topographic point plane position information and the elevation value.

Description of drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure, the following will briefly introduce the drawings that need to be used in the embodiments or the description of the prior art. Obviously, the drawings in the following description are only of the present disclosure For some embodiments, those skilled in the art can also obtain other drawings based on these drawings without creative efforts.

Fig. 1 is a schematic diagram of an application scenario in an embodiment of the present disclosure.

FIG. 2 is a flowchart of a method for generating a digital elevation model of an automatic driving scene in an embodiment of the present disclosure.

FIG. 3 is a schematic diagram of slices in one embodiment of the present disclosure.

FIG. 4 is a schematic diagram of a digital elevation model in an embodiment of the present disclosure.

FIG. 5 is a schematic diagram of an incremental update process in an embodiment of the present disclosure.

Fig. 6 is a block diagram of a device for generating a digital elevation model of an automatic driving scene in an embodiment of the present disclosure.

FIG. 7 is a schematic diagram of an electronic device in an embodiment of the present disclosure.

Detailed ways

Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, the same numerals in different drawings refer to the same or similar elements unless otherwise indicated. The implementations described in the following exemplary examples do not represent all implementations consistent with the present disclosure. Rather, they are merely examples of apparatuses and methods consistent with aspects of the present disclosure as recited in the appended claims.

The terminology used in the present disclosure is for the purpose of describing particular embodiments only, and is not intended to limit the present disclosure. As used in this disclosure and the appended claims, the singular forms "a", "the", and "the" are intended to include the plural forms as well, unless the context clearly dictates otherwise. It should also be understood that the term "and/or" as used herein refers to and includes any and all possible combinations of one or more of the associated listed items.

It should be understood that although the terms first, second, third, etc. may be used in the present disclosure to describe various information, the information should not be limited to these terms. These terms are only used to distinguish information of the same type from one another. For example, without departing from the scope of the present disclosure, first information may also be called second information, and similarly, second information may also be called first information. Depending on the context, the word "if" as used herein may be interpreted as "at" or "when" or "in response to a determination."

With the development of the autonomous driving industry, LiDAR based on vehicles, airborne or other vehicles can obtain high-density and high-precision point cloud data of target areas at low cost and high efficiency. The collected point cloud data can be used to generate a digital elevation model (Digital Elevation Model, DEM). The digital elevation model realizes the digital simulation of the terrain surface or the digital representation of the terrain surface form through the limited terrain elevation. Surface and record the elevation value of each grid point to characterize terrain features. Digital elevation models can provide basic terrain data support for high-precision maps, terrain analysis, and decision-making planning in autonomous driving scenarios.

Referring to FIG. 1 , it is a schematic diagram of an application scenario of an embodiment of the present disclosure. The self-driving vehicle 101 operating in the target operation area R (for example, a mining area) can travel between the loading point S1 and the unloading point S2 along the pre-planned driving route tr, so as to transport the coal mine at the loading point S1 to the unloading point S2 for further processing. uninstall. A laser radar 101a can be installed on the autonomous vehicle 101, and the laser radar 101a can collect point cloud data of the target operation area R during the movement of the autonomous vehicle 101, and the point cloud data can include any point H within the sensing range of the laser radar 101a. Three-dimensional coordinate information, the arbitrary point H includes but not limited to the ground point on the travel route tr, the point on the tree 102 in the target operation area R, the point on the pedestrian 103 in the target operation area R, and the coal mine pile 104 at the loading point S1 The above point and so on. A processing unit may be deployed on the self-driving vehicle 101, and the processing unit may generate a digital elevation model of the target operation area R based on the point cloud data collected by the laser radar 101a. Alternatively, the point cloud data collected by the lidar 101 a may also be sent by the autonomous vehicle 101 to the cloud, so as to generate a digital elevation model of the target operation area R on the cloud based on the received point cloud data. It can be understood that the above application scenarios are only illustrative and not intended to limit the present disclosure. In addition to the above scenarios, the solutions of the embodiments of the present disclosure may also be used in other application scenarios.

In related technologies, the digital elevation model includes not only the plane position information of each point in the target operation area R, but also the elevation value of each point, and the amount of data is relatively large, thus occupying a large amount of storage space. Based on this, the present disclosure provides a method for generating a digital elevation model of an automatic driving scene. The method in the embodiment of the present disclosure will be described below with reference to the application scenario shown in FIG. 1 . Referring to Figure 2, the method includes:

Step S201: Obtain the point cloud data C of the target operation area R of the autonomous vehicle 101, and determine the plane position information and elevation values of multiple terrain points H in the target operation area R based on the point cloud data C;

Step S202: Based on the plane position information of each topographic point H, determine the slice to which the corresponding topographic point H belongs in the multiple pre-divided slices, and different slices correspond to different plane position ranges;

Step S203: Generate a digital elevation model DEM of the target operation area R based on the elevation value of each topographic point H and the slice to which each topographic point H belongs, and store the digital elevation model DEM.

In step S201 , the point cloud data C can be collected by the laser radar 101 a on the autonomous vehicle 101 . The point cloud data C may include three-dimensional coordinate information of multiple terrain points H, based on the three-dimensional coordinate information of the terrain point, the plane position information and elevation value of the terrain point can be determined, where the plane position information can be recorded as (x, y) , which is used to characterize the location information of terrain points on the terrain surface, x represents the horizontal coordinate of the plane, and y represents the vertical coordinate of the plane. The elevation value refers to the distance from the topographic point to the absolute base along the plumb line, which can be recorded as z.

In some embodiments, the point cloud data C may be obtained by preprocessing the original point cloud data of the target operation area R collected by the lidar 101a. Wherein, the preprocessing may include but not limited to at least one of the following: voxelization filtering, noise filtering, and non-topographic point filtering. Various preprocessing methods are illustrated below with examples.

Among them, voxel filtering refers to filtering the original point cloud data by voxelizing the grid, that is, downsampling the point cloud data to reduce the density of the point cloud unit distance, thereby reducing the number of point cloud data while maintaining Shape features of point cloud data. For example, the point cloud space can be divided into a certain number and size of voxelized grids (for example, cubes), and the barycenter point of the voxelized grid can be used to approximate all other points in the voxelized grid to achieve simplification Effects on point cloud data. The original point cloud data may be voxelized and filtered based on the target resolution of the digital elevation model DEM, that is, the size of the voxelized grid is determined based on the target resolution of the digital elevation model DEM. Generally speaking, in order to ensure the accuracy of the digital elevation model DEM, the side length parameter of the voxelized grid can be set to a value not lower than the target resolution. The target resolution of digital elevation model DEM can be set based on actual needs. The smaller the value of the target resolution, the higher the target resolution, the higher the accuracy of the digital elevation model DEM, and the larger the amount of data. Therefore, the accuracy and data volume of the digital elevation model DEM can be considered at the same time when determining the target resolution.

In one embodiment, assuming that the target resolution of the digital elevation model DEM is 0.1 meters, the side length parameter of the voxelized grid can also be set to 0.1 meters. In this way, the data volume of point cloud data can be effectively reduced while retaining the geometric characteristics and accuracy requirements of space objects, and the processing and calculation efficiency of point cloud data can be improved.

Noise filtering refers to filtering various noise points such as dust, moving scattered points, isolated points, abnormal high points, abnormal low points, and abnormal far points in the original point cloud data through one or more filtering algorithms. A complete set of filtering algorithms can be used to filter the noise of the original point cloud data, including but not limited to histogram filtering, statistical filtering, radius filtering, etc. Histogram filtering can count the number of points in different coordinate ranges, thereby filtering out abnormal high points, abnormal low points, abnormal far points and other noise points. Statistical filtering and radius filtering can determine the density of point cloud data in different areas, thereby filtering out noise such as dust, moving scattered points, and isolated points. Various filtering algorithms can be performed serially. By performing noise filtering, various noise points can be effectively filtered out, thereby reducing calculation errors in the process of generating a digital elevation model DEM.

Non-topographic point filtering refers to identifying the semantic information of point cloud data through semantic segmentation of point cloud data, so as to filter out various non-topographic points such as vehicles, houses, pedestrians, roadblocks, and traffic signs in the original point cloud data. Only topographic points such as roads, hillsides, isolation retaining walls, and steps in the original point cloud data are used to participate in the generation of the digital elevation model DEM, thereby reducing the impact of non-topographic points on the digital elevation model DEM and improving the accuracy of the digital elevation model DEM. Semantic segmentation of point cloud data can be achieved using pattern recognition, machine learning algorithms, or a combination of the two.

In step S202, unified slice organization rules and data structures may be set. As shown in FIG. 3 , the plane position range may be pre-divided into multiple slices, and different slices correspond to different plane position ranges (including different plane abscissa ranges and/or different plane ordinate ranges). For example, the plane abscissa range of a slice is [x1,x2], the plane ordinate range is [y1,y2]; the plane abscissa range of the adjacent slice in the same row as the slice is [x2,x3], the plane The vertical coordinate range is [y1,y2]; the horizontal coordinate range of the adjacent slice in the same column as the slice is [x1,x2], and the horizontal vertical coordinate range is [y2,y3], where x1, x2 and x3 are real numbers that are not equal to each other, and y1, y2 and y3 are real numbers that are not equal to each other.

The size of each slice can be the same or different. For the convenience of description, the description below takes the same size of each slice as an example. The row side length RL and the column side length CL of the slice can be set based on data management efficiency and flexibility, wherein the row side length RL and the column side length CL can be the same or different. Optionally, both the row side length RL and the column side length CL can be set to 10 meters.

In some embodiments, a fixed reference point B0 may be set based on the area of the target operation region R, as shown in FIG. 3 , the coordinates of the reference point are (-10000, 10000). After the reference point is determined, the slice with the reference point B0 as the upper left corner point can be used as the slice at row 0 and column 0, so as to obtain the row number and column number of each slice.

You can use the row and column coordinates of the slice to identify each slice. For example, use {0,0} to identify the slice at row 0 and column 0, and use {0,1} to identify the slice at row 0 and column 1. And so on. Alternatively, slice numbers may also be used to identify each slice. For example, each slice is numbered by row, assuming that each row includes u slices, the number of each slice in the first row can be recorded as 0, 1, 2, ..., u-1 in turn; each row in the second row The numbers of the slices can be sequentially recorded as u, u+1, u+2, ..., 2u-1; and so on.

It can be understood that the above slice organization rules are only illustrative. For example, in addition to the reference point shown in the figure, a point at other coordinate positions can also be used as the reference point B0. For another example, a slice with the reference point B0 as the lower left corner, the lower right corner, or the upper right corner may be taken as a slice at row 0 and column 0, so as to obtain the row number and column number of each slice. Appropriate slice organization rules and data structures can be selected according to actual conditions, which will not be listed in this disclosure. Through the above method, the elevation value of the topographic point is associated and bound with the row number and column number of the slice to which the topographic point belongs, and the simple and efficient organization and management of the digital elevation model based on the row number and column number are realized. For ease of description, the scheme of the embodiment of the present disclosure will be described below by taking the slice tissue rule shown in FIG. 3 as an example.

On the basis of the above slice organization rules, the slice to which the topographic point H belongs can be determined based on the planar position information of the topographic point H, the planar position information of the preset reference point B0, and the size of each slice. Wherein, the plane position information can include the plane abscissa x and the plane ordinate y, and the size of the slice can be represented by the row side length RL and the column side length CL of the slice. When the shape of the slice is a square, the size of the slice is also It can be represented by the area of the slice or the length of the diagonal of the slice.

Specifically, the row number of the slice to which the topographic point H belongs may be determined based on the plane ordinate of the topographic point H, the plane ordinate of the reference point B0, and the row side lengths of each slice. The column number of the slice to which the topographic point H belongs may also be determined based on the plane abscissa of the topographic point H, the plane abscissa of the reference point B0, and the column side lengths of each slice. In the embodiment shown in FIG. 3 , assuming that the row side lengths of each slice are both CL and the column side lengths of each slice are RL, the distance between the plane ordinate of the reference point and the plane ordinate of the topographic point H can be obtained. For the first difference, determine a first ratio between the first difference and the column side length RL of the slice, and round down the first ratio to obtain the row number m of the slice to which the terrain point H belongs. It is also possible to obtain the second difference between the plane abscissa of the topographic point H and the plane abscissa of the reference point, determine the second ratio of the second difference to the line length CL of the slice, and calculate the second ratio. Round down to get the column number n of the slice to which the topographic point H belongs. In some embodiments, the calculation formula of the row number m and column number n of the slice to which the terrain point H belongs can be written as:

Among them, B0.x and B0.y represent the plane abscissa and plane ordinate of the reference point B0 respectively, H.x and H.y represent the plane abscissa and plane ordinate of the terrain point H respectively, and floor represents the rounding down operation. In the case where the reference point B0 is the lower left corner of the slice at row 0 and column 0, the floor in the above formula (1.1) can be replaced with Ceiling, that is, an upward rounding operation. In other embodiments, the row number m and column number n of the slice to which the topographic point H belongs can be adjusted according to actual conditions, and will not be listed here. After obtaining the row number m and column number n of the slice to which the topographic point H belongs, the row number m and the column number n may also be converted into the number of the slice to which the topographic point H belongs. Still assuming that each row in the slice organization rule shown in FIG. 3 includes u slices, the number of the slice to which the topographic point H belongs can be recorded as u*m+n.

In step S203, a digital elevation model DEM may be generated based on the elevation value of each topographic point H and the slice to which each topographic point belongs. Since the generated digital elevation model only includes the elevation value of each topographic point, and does not include the plane position information of each topographic point, the data volume of the digital elevation model is effectively reduced, thereby effectively reducing the storage time of the digital elevation model. space occupation.

The elevation value of each topographic point H included in the digital elevation model DEM can be organized according to the slice to which the topographic point H belongs. Specifically, the digital elevation model DEM may include a plurality of slice units, each slice unit corresponds to a slice, and is used to record the elevation value of each topographic point in the corresponding slice. For example, referring to Fig. 4, when the number of slices is v, the number of slice units is also v, and each slice is respectively marked as slice 1, slice 2, ..., slice v, and each slice unit is respectively marked as slice unit 1 , slice unit 2, ..., slice unit v. Among them, slice unit 1 corresponds to slice 1 and is used to record the elevation value of each topographic point in slice 1; slice unit 2 corresponds to slice 2 and is used to record the elevation value of each topographic point in slice 2; and so on.

In some embodiments, the plane position information of the feature points of the corresponding slice is recorded in each slice unit, and the identification information of each slice unit is based on the identification information of the slice corresponding to the slice unit (ie, the row number and column number of the slice, or slice number) to determine. For example, each slice unit may be organized into a slice file, and the identification information of the slice corresponding to each slice file may be used as the file name of the slice file. In this way, the slice corresponding to the slice unit can be determined based on the identification information of the slice unit.

In some other embodiments, each slice unit records the plane position information of the feature points of the corresponding slice and the elevation value of each terrain point in the corresponding slice. Wherein, the feature point of the slice may be a corner point of the slice (for example, an upper left corner point of the slice), a center point of the slice, or a midpoint of a side of the slice, and the like. Take the feature point as the upper left corner of the slice as an example, as shown in Figure 3, the feature point of the slice at row m and column n (the slice corresponding to the gray area in the figure) is shown as feature point B in the figure. In this way, the plane position information of the feature point B (including the plane abscissa and plane ordinate) of the feature point B can be recorded in the slice unit corresponding to the slice in the mth row and nth column, and each of the slices in the mth row and nth column The elevation value of the topographic point.

Wherein, the plane position information of the feature points of the slice may be determined based on the preset plane position information of the reference point B0, the position information of the slice in the plurality of slices, and the size of each slice. In the embodiment shown in FIG. 3 , assuming that the row side lengths of each slice are both CL and the column side lengths of each slice are RL, the first product of the column number of the slice and the row side length of the slice can be obtained, based on the The sum of the first product and the plane abscissa of the reference point determines the plane abscissa B.x of the feature point B of the slice. The second product of the row number of the slice and the column side length of the slice may also be obtained, and the plane ordinate B.y of the feature point B of the slice is determined based on the difference between the plane ordinate of the reference point and the second product. In some embodiments, the calculation formulas of the plane abscissa B.x and the plane ordinate B.y of the feature point B of the slice in the mth row and the nth column can be respectively written as:

In the case where the feature point B is the center point of the slice of the mth row and the nth column, the plane abscissa B.x of the feature point B can increase the offset of CL/2 on the basis of the formula (1.2), and the feature point B’s The plane ordinate B.y can increase the offset of RL/2 on the basis of formula (1.2). In other embodiments, the calculation formulas of the plane abscissa B.x and the plane ordinate B.y of the feature point B can be adjusted according to the actual situation, and will not be listed here.

In some embodiments, the storage order of the elevation values of each terrain point in the same slice unit in the slice unit is associated with the position of each terrain point in the slice to which it belongs. For example, a slice can be divided into multiple sub-slices based on the target resolution of the digital elevation model DEM, each sub-slice is a grid on a certain row and column in the slice, and the position of a topographic point in the slice can be determined by the The sub-slice to which the terrain point belongs is represented by the row number and column number in the corresponding slice. For example, the grid at row 0 and column 0 in the slice is a sub-slice, and the grid at row 0 and column 1 in the slice is another sub-slice. Multiple terrain points can be included in each sub-slice. Based on the row number and column number of each sub-slice in the corresponding slice, the storage order of the elevation values of each topographic point in the slice in the corresponding slice unit can be determined.

As shown in FIG. 4 , elevation values of topographic points in each sub-slice may be recorded row by row in a slice unit. Specifically, for each slice unit, the elevation value of each terrain point H(row0, col0) in the sub-slice of row 0 and column 0 can be recorded first, and then the terrain in the sub-slice of row 0 and column 1 can be recorded The elevation value of point H(row0, col1), and so on, until the elevation value of each terrain point in the sub-slice in the last column of row 0 is recorded. Then, record the elevation value of each topographic point H(row1, col0) in the sub-slice of row 1, column 0, and the elevation value of each topographic point H(row1, col1) in the sub-slice of row 1, column 1 , and so on, until the elevation value of each terrain point in the sub-slice of the first row and the last column is recorded. The elevation values of the topographic points in each sub-slice are recorded line by line in the above manner until all the elevation values of the topographic points in all sub-slices in the same slice are recorded.

Since the density of point cloud data is usually high, the number of terrain points actually collected in a sub-slice may be greater than 1, and one terrain point can also be filtered from each sub-slice, or based on multiple terrain points included in the sub-slice A terrain point is fitted, and each terrain point in the corresponding sub-slice is represented by the filtered or fitted terrain point. Since the sub-slices are divided according to the target resolution of the digital elevation model DEM, screening or fitting a topographic point for each sub-slice in this way can not only reduce the amount of data, but also meet the requirements of the digital elevation model DEM. Target resolution requirements. The filtered or fitted terrain points may be called grid points corresponding to sub-slices. On this basis, the elevation value of each topographic point recorded in the slice unit may only include the elevation value of each grid point in the corresponding slice.

Further, the elevation values of multiple topographic points in the same sub-slice may also be fused, and the fused elevation value may be used as the elevation value of each topographic point in the sub-slice. Specifically, the elevation values of multiple neighborhood topographic points of the grid point of the sub-slice can be determined, and the elevation value of each neighborhood topographic point can be weighted and averaged by using the inverse distance weighting algorithm to obtain the elevation value of the grid point. Wherein, the topographic point in the neighborhood of the grid point refers to the topographic point whose distance to the grid point is smaller than a preset neighborhood radius.

Through the above method, the plane coordinate information of the terrain points can be recovered based on the storage order of the elevation values of the terrain points in the slice unit, so that the complete spatial information of each terrain point can be obtained based on the restored plane coordinate information and the stored elevation values. That is, the embodiment of the present disclosure only needs to store the elevation value of the topographic point in the digital elevation model, and can obtain the same effect as simultaneously storing the topographic point plane position information and the elevation value.

In the above embodiment, the sub-slice to which the topographic point belongs may be jointly determined based on the planar position information of the topographic point, the planar position information of the feature points of the slice to which the topographic point belongs, and the target resolution of the digital elevation model. Wherein, the sub-slice to which the terrain point belongs may be identified by the row number and the column number of the sub-slice in the corresponding slice, or may be identified by the serial number of the sub-slice in the corresponding slice. In the embodiment where the sub-slice is identified by its row number and column number, the third difference between the plane ordinate of the corner point of the slice to which the sub-slice belongs and the plane ordinate of the terrain point in the sub-slice can be obtained , determine the row number of the sub-slice based on the ratio of the third difference to the target resolution of the digital elevation model, and obtain the distance between the plane abscissa of the terrain point in the sub-slice and the plane abscissa of the corner point of the slice to which the sub-slice belongs The column number of the sub-slice is determined based on the ratio of the fourth difference to the target resolution of the digital elevation model. In some embodiments, the formulas for calculating the row numbers and column numbers of sub-slices can be written as:

Assuming that the number of sub-slices in each row in a slice is w, the number of a sub-slice in the corresponding slice can be written as w*row+col.

After the digital elevation model DEM is generated, the plane position information of each topographic point can be recovered from the digital elevation model DEM through certain processing, and the elevation value of each topographic point can be extracted from the digital elevation model DEM. Then, based on the plane position information and elevation values of each topographic point, a visualized topographic map can be rendered, or topographic factors of the target operation area R can be calculated, such as accuracy, latitude, altitude, height, aspect, slope, surface Roughness, terrain relief, slope shape, etc. It is also possible to generate a high-precision map based on the plane position information and elevation values of each terrain point, and/or perform path planning and decision-making control on the automatic driving process of the automatic driving vehicle 101 . The method for recovering the planar position information of the topographic point is illustrated below with an example.

In some embodiments, the target slice unit of the digital elevation model DEM can be read; the sub-slice to which the target topographic point belongs is determined based on the recording sequence of the target topographic point in the target slice unit; based on the sub-slice to which the target topographic point belongs, the target slice The plane position information of the feature points in the unit and the target resolution of the digital elevation model DEM determine the plane position information of the target terrain point.

Wherein, the target slice unit may be any slice unit included in the digital elevation model DEM. The target terrain point may be any terrain point in the target slice unit, or a grid point in any sub-slice included in the slice corresponding to the target slice unit. Since each topographic point and grid point is recorded in the slice unit sequentially, the sub-slice to which the target topographic point belongs can be determined based on the recording sequence index of the target topographic point.

Specifically, the total number of columns sum_col of sub-slices in the slice can be determined based on the row width of the slice and the target resolution of the digital elevation model DEM, specifically expressed as:

sum_col=CL/resolution(2.1)

Then, determine the row number row and column number col of the target terrain point in the corresponding slice based on the record sequence index of the target terrain point in the slice unit and the total column number sum_col of the sub-slice. Specifically, the ratio of the record sequence index of the target terrain point in the slice unit to the total column number sum_col of the sub-slice can be obtained, and the ratio is rounded down to obtain the row number row of the target terrain point. It is also possible to take the remainder of the record sequence index of the target terrain point in the slice unit to the total column number sum_col of the sub-slice, and determine the column number col of the target terrain point based on the remainder. The calculation formula of the row number and column number of the target topographic point can be written as:

Then, the third product of the line number of the target topographic point and the target resolution of the digital elevation model DEM can be determined, based on the third product and the sum of the plane abscissa of the feature point B of the slice where the target topographic point is located to determine the target topographic point plane abscissa. It is also possible to determine the fourth product of the column number of the target topographic point and the target resolution of the digital elevation model DEM, and determine the plane of the target topographic point based on the difference between the plane abscissa of the feature point B of the slice where the target topographic point is located and the fourth product Y-axis. The calculation formulas for recovering the plane abscissa and plane ordinate of the target terrain point can be written as:

In some embodiments, when the updated point cloud data is collected, the slice to which the updated point cloud data belongs (referred to as the slice to be updated) can also be determined, and the elevation value in the slice unit corresponding to the slice to be updated is calculated. renew. For example, referring to Fig. 5, in the case that the slice to be updated to which the point cloud data belongs includes the slice of the mth row and the nth column, the updating of each topographic point in the slice of the mth row and the nth column can be determined based on the updated point cloud data Elevation value, and update the elevation value in the slice unit corresponding to the slice at row m and column n based on the updated elevation value. The above update process is called incremental update. In the embodiments of the present disclosure, by associating and binding the elevation value of the topographic point with the slice where the topographic point is located, incremental update can be performed based on the row number and column number of the slice, which improves the efficiency and accuracy of incremental update.

It is not difficult to understand that the solutions described in the above embodiments can be freely combined to obtain a new solution if there is no conflict, and due to space reasons, no further introduction is given here.

The following are device embodiments of the present disclosure, which can be used to implement the method embodiments of the present disclosure. For details not disclosed in the disclosed device embodiments, please refer to the disclosed method embodiments.

Fig. 6 is a schematic structural diagram of an apparatus for generating a digital elevation model of an automatic driving scene according to an embodiment of the present disclosure. As shown in Figure 6, the device includes:

The first determination module 601 is configured to acquire point cloud data of the target operation area of the self-driving vehicle, and determine plane position information and elevation values of multiple terrain points in the target operation area based on the point cloud data;

The second determining module 602 is configured to determine the slices to which the corresponding topographic points belong in the pre-divided multiple slices based on the plane position information of each topographic point, and different slices correspond to different plane position ranges;

A storage module 603, configured to generate a digital elevation model of the target operation area based on the elevation value of each topographic point and the slice to which each topographic point belongs, and store the digital elevation model;

The digital elevation model includes a plurality of slice units, each slice unit corresponds to a slice, and is used to record the elevation value of each topographic point in the corresponding slice;

The storage order of the elevation values of each topographic point in the same slice unit in the slice unit is associated with the position of each topographic point in the slice to which it belongs.

For the implementation process of the functions and effects of each module in the above-mentioned device, please refer to the implementation process of the corresponding steps in the above-mentioned method for details, and details will not be repeated here.

Fig. 7 is a schematic structural diagram of an electronic device according to an embodiment of the present disclosure. As shown in FIG. 7 , the electronic device 70 of this embodiment includes: a processor 701 , a memory 702 , and a computer program 703 stored in the memory 702 and capable of running on the processor 701 . When the processor 701 executes the computer program 703, the steps in the foregoing method embodiments are implemented. Alternatively, when the processor 701 executes the computer program 703, the functions of the modules/units in the foregoing device embodiments are realized.

Exemplarily, the computer program 703 can be divided into one or more modules/units, and one or more modules/units are stored in the memory 702 and executed by the processor 701 to complete the present disclosure. One or more modules/units may be a series of computer program instruction segments capable of accomplishing specific functions, and the instruction segments are used to describe the execution process of the computer program 703 in the electronic device 70 .

The electronic device 70 may be electronic devices such as desktop computers, notebooks, palmtop computers, and cloud servers. The electronic device 70 may include but not limited to a processor 701 and a memory 702 . Those skilled in the art can understand that FIG. 7 is only an example of the electronic device 70, and does not constitute a limitation to the electronic device 70. It may include more or less components than shown in the figure, or combine some components, or different components. , for example, an electronic device may also include an input and output device, a network access device, a bus, and the like.

The processor 701 may be a central processing unit (Central Processing Unit, CPU), or other general-purpose processors, digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), on-site Field-Programmable Gate Array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor, or the processor may be any conventional processor, or the like.

The storage 702 may be an internal storage unit of the electronic device 70 , for example, a hard disk or a memory of the electronic device 70 . The memory 702 can also be an external storage device of the electronic device 70, for example, a plug-in hard disk equipped on the electronic device 70, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash memory card ( FlashCard), etc. Further, the memory 702 may also include both an internal storage unit of the electronic device 70 and an external storage device. The memory 702 is used to store computer programs and other programs and data required by the electronic device. The memory 702 can also be used to temporarily store data that has been output or will be output.

Those skilled in the art can clearly understand that for the convenience and brevity of description, only the division of the above-mentioned functional units and modules is used for illustration. In practical applications, the above-mentioned functions can be assigned to different functional units, Completion of modules means that the internal structure of the device is divided into different functional units or modules to complete all or part of the functions described above. Each functional unit and module in the embodiment may be integrated into one processing unit, or each unit may exist separately physically, or two or more units may be integrated into one unit, and the above-mentioned integrated units may adopt hardware It can also be implemented in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the protection scope of the present disclosure. For the specific working process of the units and modules in the above system, reference may be made to the corresponding process in the foregoing method embodiments, and details will not be repeated here.

In the above-mentioned embodiments, the descriptions of each embodiment have their own emphases, and for parts that are not detailed or recorded in a certain embodiment, refer to the relevant descriptions of other embodiments.

Those skilled in the art can appreciate that the units and algorithm steps of the examples described in conjunction with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed by hardware or software depends on the specific application and design constraints of the technical solution. Skilled artisans may implement the described functionality using different methods for each particular application, but such implementation should not be considered beyond the scope of the present disclosure.

In the embodiments provided in the present disclosure, it should be understood that the disclosed device/electronic equipment and method may be implemented in other ways. For example, the device/electronic device embodiments described above are only illustrative. For example, the division of modules or units is only a logical function division. In actual implementation, there may be other division methods. Multiple units or components can be Incorporation may either be integrated into another system, or some features may be omitted, or not implemented. In another point, the mutual coupling or direct coupling or communication connection shown or discussed may be through some interfaces, and the indirect coupling or communication connection of devices or units may be in electrical, mechanical or other forms.

A unit described as a separate component may or may not be physically separated, and a component displayed as a unit may or may not be a physical unit, that is, it may be located in one place, or may be distributed to multiple network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

In addition, each functional unit in each embodiment of the present disclosure may be integrated into one processing unit, each unit may exist separately physically, or two or more units may be integrated into one unit. The above-mentioned integrated units can be implemented in the form of hardware or in the form of software functional units.

If an integrated module/unit is realized in the form of a software function unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present disclosure realizes all or part of the processes in the methods of the above embodiments, and can also be completed by instructing related hardware through computer programs. The computer programs can be stored in computer-readable storage media, and the computer programs can be processed. When executed by the controller, the steps in the above-mentioned method embodiments can be realized. A computer program may include computer program code, which may be in source code form, object code form, executable file, or some intermediate form or the like. The computer readable medium may include: any entity or device capable of carrying computer program code, recording medium, U disk, removable hard disk, magnetic disk, optical disk, computer memory, read-only memory (Read-Only Memory, ROM), random access Memory (Random Access Memory, RAM), electrical carrier signal, telecommunication signal, and software distribution medium, etc. It should be noted that the content contained in computer readable media may be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, computer readable media may not Including electrical carrier signals and telecommunication signals.

The above embodiments are only used to illustrate the technical solutions of the present disclosure, rather than to limit them; although the present disclosure has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: it can still be described in the foregoing embodiments Modifications to the technical solutions recorded, or equivalent replacements for some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present disclosure, and should be included in this disclosure. within the scope of protection.

The above embodiments are only used to illustrate the technical solutions of the present disclosure, rather than to limit them; although the present disclosure has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: it can still be described in the foregoing embodiments Modifications to the technical solutions recorded, or equivalent replacements for some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present disclosure, and should be included in this disclosure. within the scope of protection.

Claims (12)

1. A method of generating a digital elevation model of an autonomous driving scenario, the method comprising:

acquiring point cloud data of a target operation area of an automatic driving vehicle, and determining plane position information and elevation values of a plurality of topographic points in the target operation area based on the point cloud data;

determining slices of the corresponding topographic points in a plurality of pre-divided slices based on the plane position information of each topographic point, wherein different slices correspond to different plane position ranges;

generating a digital elevation model of the target operation area based on the elevation value of each topographic point and the slice to which each topographic point belongs, and storing the digital elevation model;

the digital elevation model comprises a plurality of slice units, each slice unit corresponds to one slice and is used for recording the elevation value of each topographic point in the corresponding slice;

the storage sequence of the elevation values of all topographic points in the same slice unit in the slice unit is related to the positions of all topographic points in the slice.

2. The method according to claim 1, wherein the determining a slice to which the corresponding topographic point belongs among the pre-divided slices based on the plane position information of the respective topographic point comprises:

and determining the slice to which the topographic point belongs based on the plane position information of the topographic point, the plane position information of a preset reference point and the size of each slice.

3. The method according to claim 1, wherein in each slice unit, plane position information of the feature point of the corresponding slice and elevation values of respective topographical points in the corresponding slice are recorded.

4. The method according to claim 3, wherein the plane position information of the feature point of the slice is determined based on the plane position information of a preset reference point, the position information of the slice in the plurality of slices, and the size of each slice.

5. The method according to claim 3 or 4, wherein each slice is divided into a plurality of sub-slices according to a target resolution of the digital elevation model; the slicing unit is used for recording the elevation values of the topographic points in each sub-slice of the corresponding slice line by line;

and determining the sub-slice to which the topographic points belong based on the plane position information of the topographic points, the plane position information of the characteristic points of the slice to which the topographic points belong and the target resolution of the digital elevation model.

6. The method of claim 5, further comprising:

reading a target slice unit of the digital elevation model;

determining a sub-slice to which the target topographic point belongs based on the recording sequence of the target topographic point in the target slice unit;

and determining the plane position information of the target topographic point based on the sub-slice to which the target topographic point belongs, the plane position information of the feature point in the target slice unit and the target resolution of the digital elevation model.

7. The method of claim 1, further comprising:

under the condition that updated point cloud data are collected, determining a slice to be updated to which the updated point cloud data belong, and determining an updated elevation value of each topographic point in the slice to be updated based on the updated point cloud data;

and updating the elevation value in the slice unit corresponding to the slice to be updated based on the updated elevation value of each topographic point in the slice to be updated.

8. The method of claim 1, further comprising:

preprocessing the original point cloud data of the target operation area to obtain the point cloud data; the pre-treatment comprises at least one of: voxelization filtering, noise filtering and non-topographical point filtering.

9. The method of claim 3, further comprising:

acquiring elevation values of a plurality of neighborhood topographic points of grid points of the sub-slices; the grid points of the sub-slice are used for fitting a plurality of topographic points in the sub-slice;

and fusing the elevation values of the plurality of neighborhood topographic points to obtain the elevation value of the grid point.

10. An apparatus for generating a digital elevation model of an autonomous driving scenario, the apparatus comprising:

the system comprises a first determination module, a second determination module and a third determination module, wherein the first determination module is used for acquiring point cloud data of a target operation area of an automatic driving vehicle and determining plane position information and elevation values of a plurality of topographic points in the target operation area based on the point cloud data;

the second determining module is used for determining slices of the corresponding topographic points in the pre-divided multiple slices based on the plane position information of each topographic point, and different slices correspond to different plane position ranges;

the storage module is used for generating a digital elevation model of the target operation area based on the elevation value of each topographic point and the slice to which each topographic point belongs, and storing the digital elevation model;

the digital elevation model comprises a plurality of slice units, each slice unit corresponds to one slice and is used for recording the elevation value of each topographic point in the corresponding slice;

the storage sequence of the elevation values of all topographic points in the same slice unit in the slice unit is related to the positions of all topographic points in the slice.

11. A computer-readable storage medium, on which a computer program is stored, which program, when being executed by a processor, is adapted to carry out the method of any one of claims 1 to 9.

12. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the method of any one of claims 1 to 9 when executing the program.

Images