CN114693836A

CN114693836A - Method and system for generating road element vector

Info

Publication number: CN114693836A
Application number: CN202210233930.6A
Authority: CN
Inventors: 彭益堂; 陈岳
Original assignee: Autonavi Software Co Ltd
Current assignee: Autonavi Software Co Ltd
Priority date: 2022-03-09
Filing date: 2022-03-09
Publication date: 2022-07-01

Abstract

The invention discloses a method and a system for generating a road element vector. Wherein, the method comprises the following steps: acquiring point cloud data and an original image acquired in the same area; projecting the point cloud data to a two-dimensional plane to obtain a target image corresponding to the point cloud data; respectively carrying out semantic segmentation on road elements in the original image and the target image to obtain semantic segmentation results; and vectorizing the road elements based on the point cloud data and the semantic segmentation result to obtain a road element vector. The invention solves the technical problem of larger generation error of the road element vector in the related technology.

Description

Method and system for generating road element vector

Technical Field

The invention relates to the field of intelligent navigation, in particular to a method and a system for generating a road element vector.

Background

In order to realize digitalization of various road elements (such as lane lines, stop lines, zebra crossings and the like) in the real world, a high-precision map can be manufactured by using data acquired by unmanned vehicles and high-precision map acquisition vehicles. However, due to the limitations of the data acquisition precision and the acquisition angle, the generation error of the conventional road element vector is large, and the accuracy requirement of a high-precision map is not met.

In view of the above problems, no effective solution has been proposed.

Disclosure of Invention

The embodiment of the invention provides a method and a system for generating a road element vector, which at least solve the technical problem of larger generation error of the road element vector in the related technology.

According to an aspect of the embodiments of the present invention, there is provided a method for generating a road element vector, including: acquiring point cloud data and an original image acquired in the same area; projecting the point cloud data to a two-dimensional plane to obtain a target image corresponding to the point cloud data; respectively carrying out semantic segmentation on road elements in the original image and the target image to obtain semantic segmentation results; and vectorizing the road elements based on the point cloud data and the semantic segmentation result to obtain a road element vector.

According to another aspect of the embodiments of the present invention, there is also provided a method for generating a road element vector, including: the cloud server receives point cloud data and an original image which are collected in the same area; the cloud server projects the point cloud data to a two-dimensional plane to obtain a target image corresponding to the point cloud data; the cloud server performs semantic segmentation on road elements in the original image and the target image respectively to obtain semantic segmentation results; vectorizing the road elements by the cloud server based on the point cloud data and the semantic segmentation result to obtain a road element vector; the cloud server outputs the road element vector.

According to another aspect of the embodiments of the present invention, there is also provided a storage medium including a stored program, wherein the apparatus in which the storage medium is controlled to execute the method of generating a road element vector in the above-described embodiments when the program runs.

According to another aspect of the embodiments of the present invention, there is also provided an electronic terminal, including: a memory; and a processor connected to the memory, the processor being configured to execute a program, wherein the program executes the method for generating a road element vector in the above-described embodiment.

According to another aspect of the embodiments of the present invention, there is also provided a system for generating a road element vector, including: a processor; and a memory connected to the processor for providing the processor with instructions for processing the method for generating the road element vector in the above embodiment.

In the embodiment of the invention, after point cloud data and an original image in the same area are obtained, the point cloud data can be projected to a two-dimensional plane to obtain a target image, and the original image and the target image are subjected to semantic segmentation respectively to obtain a semantic segmentation result, so that the aim of road element vectorization can be achieved based on the point cloud data and the semantic segmentation result. It is easy to notice that the point cloud data is projected into a two-dimensional plane image, and then semantic segmentation is performed to extract road elements, so that the road element vector has three-dimensional information, the problem of road element loss caused by objective factors such as shielding and observation limitation of an original image can be avoided, the precision requirement of a high-precision map is met, the technical effects of ensuring the integrity of the road element vector, increasing data redundancy and improving the generation precision of the road element vector are achieved, and the technical problem of large generation error of the road element vector in the related technology is solved.

Drawings

The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the invention and together with the description serve to explain the invention without limiting the invention. In the drawings:

fig. 1 is a block diagram of a hardware configuration of a computer terminal for implementing a method of generating a road element vector according to an embodiment of the present invention;

FIG. 2 is a flow chart of a method of generating a road element vector according to an embodiment of the present invention;

FIG. 3 is a flow chart of a method of generating a stop-line vector according to an embodiment of the present invention;

FIG. 4 is a flow chart of a method of generating a lane line vector according to an embodiment of the present invention;

fig. 5 is a flow chart of a method of stop-line vectoring according to an embodiment of the present invention;

fig. 6 is a flow chart of a lane line vectoring method according to an embodiment of the present invention;

FIG. 7 is a flowchart of another method of generating a road element vector according to an embodiment of the present invention;

FIG. 8 is a schematic diagram of an apparatus for generating a road element vector according to an embodiment of the present invention;

fig. 9 is a schematic diagram of another road element vector generation apparatus according to an embodiment of the present invention;

fig. 10 is a block diagram of a computer terminal according to an embodiment of the present invention.

Detailed Description

In order to make the technical solutions of the present invention better understood, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.

It should be noted that the terms "first," "second," and the like in the description and claims of the present invention and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the invention described herein are capable of operation in sequences other than those illustrated or described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

First, some terms or terms appearing in the description of the embodiments of the present application are applicable to the following explanations:

vehicle is gathered to high accuracy: the professional collection equipment for the unmanned high-precision map comprises a laser radar, a camera, a GNSS (Global Navigation Satellite System) receiver, an IMU (Inertial Measurement Unit), a DMI (Distance Measuring Instrument), a control storage Unit and a vehicle.

Grid graph: the method may be a grid map composed of individual grids, and a two-dimensional grid map may be obtained by meshing three-dimensional laser point cloud data.

Lane marking: the lane line may be a boundary line for distinguishing the lane, and may be a white dotted line, a white solid line, a yellow double-dotted line, or the like, which indicates the vehicle travel position.

Stopping the line: can be a traffic sign at a signal lamp intersection and can be a white solid line which represents a position where a vehicle waits to pass for parking.

The traditional scheme for extracting road elements by using laser point clouds and panoramic photos mainly depends on the observation of the photos, and the extracted road element vectors are often incomplete or missing due to the problems of photo shielding, camera observation range limitation and the like; the computer vision scheme for extracting road elements by using images and tracks depends on the precision of the tracks and the observation of a camera, and the obtained vector error is extremely large and often does not meet the precision requirement of a high-precision map.

In order to solve the problem that unmanned vehicles and high-precision map collecting vehicles automatically generate high-precision map road element vectors, the application provides a method for automatically generating the high-precision map road element vectors.

Example 1

In accordance with an embodiment of the present invention, there is provided a method of generating a road element vector, it being noted that the steps illustrated in the flowchart of the drawings may be performed in a computer system such as a set of computer-executable instructions and that, although a logical order is illustrated in the flowchart, in some cases, the steps illustrated or described may be performed in an order different than that presented herein.

The method provided by the first embodiment of the present application may be executed in a mobile terminal, a computer terminal, or a similar computing device. Fig. 1 shows a hardware configuration block diagram of a computer terminal (or mobile device) for implementing a road element vector generation method. As shown in fig. 1, the computer terminal 10 (or mobile device 10) may include one or more processors (shown as 102a, 102b, … …, 102n in the figures) which may include, but are not limited to, a processing device such as a microprocessor MCU or a programmable logic device FPGA, a memory 104 for storing data, and a transmission module 106 for communication functions. Besides, the method can also comprise the following steps: a display, an input/output interface (I/O interface), a Universal Serial BUS (USB) port (which may be included as one of the ports of the BUS), a network interface, a power source, and/or a camera. It will be understood by those skilled in the art that the structure shown in fig. 1 is only an illustration and is not intended to limit the structure of the electronic device. For example, the computer terminal 10 may also include more or fewer components than shown in FIG. 1, or have a different configuration than shown in FIG. 1.

It should be noted that the one or more processors and/or other data processing circuitry described above may be referred to generally herein as "data processing circuitry". The data processing circuitry may be embodied in whole or in part in software, hardware, firmware, or any combination thereof. Further, the data processing circuit may be a single stand-alone processing module, or incorporated in whole or in part into any of the other elements in the computer terminal 10 (or mobile device). As referred to in the embodiments of the application, the data processing circuit acts as a processor control (e.g. selection of a variable resistance termination path connected to the interface).

The memory 104 may be used to store software programs and modules of application software, such as program instructions/data storage devices corresponding to the method for generating a road element vector in the embodiment of the present invention, and the processor executes various functional applications and data processing by running the software programs and modules stored in the memory 104, so as to implement the method for generating a road element vector. The memory 104 may include high speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include memory located remotely from the processor, which may be connected to the computer terminal 10 via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.

The transmission device 106 is used for receiving or transmitting data via a network. Specific examples of the network described above may include a wireless network provided by a communication provider of the computer terminal 10. In one example, the transmission device 106 includes a Network adapter (NIC) that can be connected to other Network devices through a base station to communicate with the internet. In one example, the transmission device 106 can be a Radio Frequency (RF) module, which is used to communicate with the internet in a wireless manner.

The display may be, for example, a touch screen type Liquid Crystal Display (LCD) that may enable a user to interact with a user interface of the computer terminal 10 (or mobile device).

It should be noted here that in some alternative embodiments, the computer device (or mobile device) shown in fig. 1 described above may include hardware elements (including circuitry), software elements (including computer code stored on a computer-readable medium), or a combination of both hardware and software elements. It should be noted that fig. 1 is only one example of a particular specific example and is intended to illustrate the types of components that may be present in the computer device (or mobile device) described above.

Under the above operating environment, the present application provides a method of generating a road element vector as shown in fig. 2. Fig. 2 is a flowchart of a method for generating a road element vector according to an embodiment of the present invention. As shown in fig. 2, the method may include the steps of:

step S202, point cloud data and an original image collected in the same area are obtained.

The point cloud data in the steps can be laser point cloud acquired by unmanned vehicles and high-precision map acquisition vehicles through laser radars, and the point cloud data has the advantages of depth information and high distance measurement precision; the original image can be an image acquired by an unmanned vehicle and a high-precision map acquisition vehicle through a camera, and has the advantages of dense perception and long range. The same area in the above steps may be an area where a high-precision map needs to be generated, and the area may be set in advance by a user.

In order to improve the generation precision of the road element vector, in the embodiment of the application, the point cloud data and the original image may be fused to generate the road element vector by combining the advantages of the point cloud data and the original image. In an optional embodiment, data acquisition can be performed in the area through an unmanned vehicle and a high-precision map acquisition vehicle, so that point cloud data and an original image acquired in the same area can be acquired; in another optional embodiment, data acquisition can be performed in different areas through an unmanned vehicle and a high-precision map acquisition vehicle, and then the point cloud data and the original image are associated, so that the point cloud data and the original image in the same area are extracted.

In order to improve the accuracy and efficiency in the subsequent processing process, after point cloud data and an original image are obtained, preprocessing can be carried out, and wrong point clouds or images which are low in precision and irrelevant to road elements are removed.

And step S204, projecting the point cloud data to a two-dimensional plane to obtain a target image corresponding to the point cloud data.

The target image in the above step may be a two-dimensional grid image, and the size of each grid and the number of grids in the image may be preset by a user.

In order to fuse the point cloud data and the original data, in an optional embodiment, an initial raster image is first generated according to user settings, and then the point cloud data is projected to a two-dimensional plane corresponding to the initial raster image based on a spatial position relationship, so that a corresponding two-dimensional raster image can be obtained.

It should be noted that the projection process is a process of converting three-dimensional point cloud data into a two-dimensional image, and therefore, it may be considered that depth information in the three-dimensional point cloud data is discarded, and then information in other two dimensions is associated with each grid in the two-dimensional grid image based on spatial coordinates in other two dimensions.

And step S206, performing semantic segmentation on the road elements in the original image and the target image respectively to obtain semantic segmentation results.

The road elements in the above steps may be elements for generating a high-precision map, and may include: the present invention relates to a vehicle, and more particularly, to a vehicle, a vehicle. The semantic segmentation result in the above step may be a result of labeling the road element in the original image and the target image, where the labeling may refer to pixel-level labeling, that is, determining whether each pixel in the two images belongs to the road element, and therefore, the result obtained by performing semantic segmentation on the original image may be represented by an original image Mask, and the result obtained by performing semantic segmentation on the target image may be represented by a target image Mask.

In an optional embodiment, the original image and the target image may be processed by using a semantic segmentation algorithm provided in the related art, and the road element information may be extracted from the original image and the road element information may be extracted from the target image, for example, in this embodiment, the original image and the target image are processed by using a pre-trained semantic segmentation model.

And S208, vectorizing the road elements based on the point cloud data and the semantic segmentation result to obtain a road element vector.

In an alternative embodiment, the point cloud data is discrete data points in three-dimensional space, and the road elements are linear or nonlinear elements, often straight or curved lines. In addition, semantic segmentation results respectively represent pixel ranges of road elements in the original image, the target image and the point cloud data, and on the basis, point clouds of the pixel ranges in the point cloud data can be clustered and fitted to achieve the vectorization purpose, so that a road element vector is obtained.

For example, the method for generating the stop-line vector shown in fig. 3 is taken as an example, and as shown in fig. 3, the method may include the following steps:

step S302, a high-precision map acquisition vehicle acquires point cloud data and an original image, and carries out preprocessing to associate the point cloud data and the original image;

step S304, projecting the point cloud data in a certain range (namely the same area) to a plane to obtain a two-dimensional grid map (namely the target image);

s306, extracting stop line element information in the original image and the two-dimensional grid image respectively through a semantic segmentation model to obtain a semantic segmentation result;

and S308, clustering point cloud data according to the semantic segmentation result, and carrying out lane line vectorization to obtain a stop line vector.

For example, a method for generating a lane line vector as shown in fig. 4 is taken as an example, and as shown in fig. 4, the method may include the following steps:

s402, acquiring point cloud data and an original image by a high-precision map acquisition vehicle, preprocessing, and associating the point cloud data and the original image;

step S404, projecting the point cloud data in a certain range (namely the same area) to a plane to obtain a two-dimensional grid map (namely the target image);

step S406, respectively extracting lane line element information in the original image and the two-dimensional grid image through a semantic segmentation model to obtain a semantic segmentation result;

and step S408, carrying out lane line vectorization according to the point cloud data and the semantic segmentation result to obtain a lane line vector.

According to the scheme provided by the embodiment of the application, after the point cloud data and the original image in the same area are obtained, the point cloud data can be projected to a two-dimensional plane to obtain a target image, and the original image and the target image are subjected to semantic segmentation respectively to obtain a semantic segmentation result, so that the aim of road element vectorization can be achieved based on the point cloud data and the semantic segmentation result. It is easy to notice that the point cloud data is projected into a two-dimensional plane image, and then semantic segmentation is performed to extract road elements, so that the road element vector has three-dimensional information, the problem of road element loss caused by objective factors such as shielding and observation limitation of an original image can be avoided, the precision requirement of a high-precision map is met, the technical effects of ensuring the integrity of the road element vector, increasing data redundancy and improving the generation precision of the road element vector are achieved, and the technical problem of large generation error of the road element vector in the related technology is solved.

In the above embodiments of the present application, the semantic segmentation result may include: the method comprises the following steps of obtaining a first result corresponding to an original image and a second result corresponding to a target image, wherein the road element is vectorized based on point cloud data and a semantic segmentation result to obtain a road element vector, and the vectorization comprises the following steps: respectively carrying out pixel clustering on the first result and the second result to obtain a first pixel range and a second pixel range corresponding to the road element; clustering the point cloud data based on the first pixel range and the second pixel range respectively to obtain a first point cloud and a second point cloud corresponding to the road elements; and fitting the first point cloud and the second point cloud to generate a road element vector.

In an optional embodiment, distances may be respectively performed on road element pixels in the first result and the second result, pixel ranges corresponding to road elements in different images are determined, point cloud data is then respectively projected to the first result and the second result, point clouds falling within the pixel ranges are determined, clustering is performed according to a spatial relationship, and finally, the clustered road element point clouds are fitted to generate a road element vector.

For the linear elements, the vectorization of the linear elements requires that the point cloud data is fitted to a curve, and in an optional embodiment, the original images and the target images may be processed respectively, the original images are clustered, and a linear element vector is fitted, and at the same time, the target images are clustered, and a linear element vector is also fitted, and curve fitting is performed on a plurality of linear element vectors in the same range, so as to obtain a unique linear element vector.

For the non-linear elements, the vectorization of the non-linear elements also requires that point cloud data is fitted to a curve, in an optional embodiment, the original image and the target image can be processed respectively, the original image is clustered to obtain a clustered point cloud set, meanwhile, the target image is clustered to obtain a clustered point cloud set, the two point cloud sets are directly fused into a point cloud set and fitted, the vertex coordinates of a bounding box of the non-linear elements can be extracted, and the non-linear element vector is formed based on the coordinates.

In the above embodiments of the present application, clustering point cloud data based on a first pixel range and a second pixel range respectively to obtain a first point cloud and a second point cloud corresponding to a road element includes: respectively projecting the point cloud data to a first result and a second result to obtain a first projection image and a second projection image; determining a first target pixel in the first pixel range in the first projection image and a second target pixel in the second pixel range in the second projection image; and clustering the point cloud corresponding to the first target pixel and the point cloud corresponding to the second target pixel respectively based on the spatial relationship to obtain the first point cloud and the second point cloud.

In an alternative embodiment, the original image and the target image are different, but the whole processing flow is the same, so that the two images can be processed respectively in the same processing mode to obtain two corresponding results. The clustering process of the point cloud data comprises the following steps: and projecting the point cloud data on a semantic segmentation result (namely the first result or the second result), namely a Mask image, marking the point clouds falling in the pixel range of the road element, and clustering according to the spatial relationship to obtain the clustered road element point cloud (namely the first point cloud or the second point cloud). In the method, all pixels in the road element pixel range in the projection image (i.e. the first projection image or the second projection image) may be determined first, and due to the correspondence between the point cloud data and the projection image, the point clouds corresponding to all pixels in the road element pixel range may be determined, and the point clouds falling in the road element pixel range may be obtained.

In the above embodiments of the present application, in a case where the road element includes a nonlinear element, fitting the first point cloud and the second point cloud to generate a road element vector, includes: fusing the first point cloud and the second point cloud based on the spatial relationship to obtain a target point cloud; fitting the target point cloud to obtain the bounding box coordinates of the nonlinear elements; a road element vector is generated based on the bounding box coordinates.

The non-linear elements in the above steps may be road elements that cannot be represented by straight lines or curved lines in the map, for example, the non-linear elements may be stop lines, zebra stripes, turning arrows, etc., but are not limited thereto, and for the non-linear elements, corresponding non-linear element vectors may be generated through bounding boxes of the non-linear elements. The bounding box coordinates in the above step may refer to coordinates of vertices of the bounding box, and the bounding box is usually rectangular, and thus, the bounding box coordinates may be coordinates of four vertices of the rectangle.

In an optional embodiment, for the non-linear elements, the first point cloud and the second point cloud obtained by clustering may be fused to obtain a target point cloud, that is, the target point cloud may be obtained by solving a union set of the first point cloud and the second point cloud. Then, the target point cloud can be fitted through a RANSAC point cloud plane segmentation method, the vertex coordinates of the enclosing frame are extracted, and the nonlinear element vector is formed on the basis of the vertex coordinates of the enclosing frame.

For example, the stop-line vectorization method shown in fig. 5 is taken as an example for explanation, and as shown in fig. 5, the method may include the following steps:

step S502, clustering stop line pixels in the original image semantic segmentation Mask and the raster image semantic segmentation Mask respectively, and marking a pixel range corresponding to the stop line;

step S504, projecting the point cloud data to an original image semantic segmentation Mask and a grid image semantic segmentation Mask, marking the point cloud falling in the stop line pixel range, and clustering according to the spatial relationship;

and S506, fusing the clustered point clouds of the stop line, fitting the fused point clouds, and extracting fixed point coordinates of a surrounding frame of the stop line to form a vector.

It should be noted that, before step S506, denoising may also be performed on the clustered stop-line point cloud, and fitting may be performed on the denoised stop-line point cloud.

In the above embodiments of the present application, in a case where the road element includes a line type element, fitting the first point cloud and the second point cloud to generate a road element vector includes: fitting the first point cloud and the second point cloud respectively to generate a plurality of central line vectors of the line type elements; and according to the spatial position relationship, performing curve fitting on the multiple central line vectors at the same position to obtain a road element vector.

The line type elements in the above steps may be road elements that can be represented by straight lines or curved lines in the map, and for example, the line type elements may be lane lines, but not limited thereto, and for the line type elements, a road element vector may be generated by a set of curved lines.

In an optional embodiment, for the line type elements, curve fitting may be performed on the first point cloud and the second point cloud obtained through clustering respectively by using a least square method, a RANSAC method, and other fitting methods, so as to obtain a center line vector corresponding to the first point cloud and a center line vector corresponding to the second point cloud, that is, to obtain a plurality of center line vectors, and then curve fitting is performed on the plurality of center line vectors at the same position, that is, curve fitting is performed on the center line vector corresponding to the first point cloud and the center line vector corresponding to the second point cloud, so as to obtain a unique line type element vector.

For example, the lane line vectorization method shown in fig. 6 is taken as an example for explanation, and as shown in fig. 6, the method may include the following steps:

step S602, clustering lane line pixels in the original image semantic segmentation Mask and the raster image semantic segmentation Mask respectively, and marking the pixel range corresponding to the lane line;

step S604, projecting the point cloud data to original image semantic segmentation Mask and raster image semantic segmentation Mask, marking the point cloud falling in the lane line pixel range, and clustering according to the spatial relationship;

step S606, respectively fitting the clustered lane line point clouds and extracting a lane line center line vector;

and step S608, fusing a plurality of lane line vectors at the same position according to the spatial position relationship, and performing curve fitting to obtain a unique lane line vector.

In the above embodiment of the present application, semantic segmentation is performed on road elements in an original image and a target image respectively to obtain semantic segmentation results, which includes: and respectively carrying out semantic segmentation on the original image and the target image through a semantic segmentation model to obtain a semantic segmentation result.

The semantic segmentation model in the above steps may be a model provided in the related art, or a model trained according to the recognition requirement of the road element. In an actual use scene, the selection setting can be carried out according to the requirements of different users.

In an optional embodiment, the semantic segmentation model may perform semantic segmentation on the original image to obtain a first result corresponding to the original image, and the semantic segmentation model may perform semantic segmentation on the target image to obtain a second result corresponding to the target image, so that the first result and the second result form the semantic segmentation result. By using the semantic segmentation model to perform semantic segmentation, the effect of improving the semantic segmentation efficiency and accuracy can be achieved.

In the above embodiment of the present application, the method further includes: segmenting the point cloud data to obtain a plurality of point cloud blocks; extracting point cloud blocks containing road elements from the plurality of point cloud blocks to obtain target point cloud blocks; and projecting the target point cloud block to a two-dimensional plane to obtain a target image.

In an optional embodiment, because the data volume of the point cloud data is large, the problems of low processing efficiency and low accuracy exist in the operations of directly mapping, clustering, fitting and the like on the point cloud data. In order to solve the problem, after point cloud data is obtained, the point cloud data can be segmented according to the requirements of customers on processing efficiency and accuracy to obtain a plurality of point cloud blocks, the point cloud blocks which do not contain road elements in the plurality of point cloud blocks are deleted, only the point cloud blocks which contain the road elements are reserved to obtain target point cloud blocks, and at the moment, the number of the target point cloud blocks is far smaller than that of the point cloud data. And then, the point cloud data contained in the target point cloud block can be projected to a two-dimensional plane to obtain a two-dimensional grid map.

In the above embodiment of the present application, after vectorizing the road element based on the point cloud data and the semantic segmentation result to obtain a road element vector, the method further includes: and generating a target map based on the road element vector.

The target map in the above step may be a high-precision map, and the precision of the map may be set by the user.

In an alternative embodiment, an available high-precision map may be generated based on the generated road element vector. For example, taking the example that the road element vector includes the stop line vector, the method may further include the steps of: and generating an available high-precision map based on the fitted vertex coordinates of the bounding box of the stop line. For another example, taking the example that the road element vector includes a lane line vector, the method may further include the steps of: and based on the fitted lane line vector, generating an available high-precision map by calculating information such as curvature and gradient of the lane line.

In the above-described embodiments of the present application, in a case where the road element includes a line-type element, generating the target map based on the road element vector includes: determining physical parameter information of the road element vector; and generating a target map based on the road element vector and the physical parameter information.

The physical parameter information in the above step may be information such as curvature and gradient of the line type element, but is not limited thereto.

In an alternative embodiment, after the line element vector is generated, the physical parameter information such as curvature and gradient of the line element vector may be calculated, and a usable high-precision map may be generated.

It should be noted that, for simplicity of description, the above-mentioned method embodiments are described as a series of acts or combination of acts, but those skilled in the art will recognize that the present invention is not limited by the order of acts, as some steps may occur in other orders or concurrently in accordance with the invention. Further, those skilled in the art should also appreciate that the embodiments described in the specification are preferred embodiments and that the acts and modules referred to are not necessarily required by the invention.

Through the above description of the embodiments, those skilled in the art can clearly understand that the method according to the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but the former is a better implementation mode in many cases. Based on such understanding, the technical solutions of the present invention may be embodied in the form of a software product, which is stored in a storage medium (e.g., ROM/RAM, magnetic disk, optical disk) and includes instructions for enabling a terminal device (e.g., a mobile phone, a computer, a server, or a network device) to execute the method according to the embodiments of the present invention.

Example 2

There is also provided, in accordance with an embodiment of the present invention, a method of generating a road element vector, it being noted that the steps illustrated in the flowchart of the figure may be performed in a computer system such as a set of computer-executable instructions and that, although a logical order is illustrated in the flowchart, in some cases the steps illustrated or described may be performed in an order different than that presented herein.

Fig. 7 is a flowchart of another road element vector generation method according to an embodiment of the present invention. As shown in fig. 7, the method may include the steps of:

step S702, a cloud server receives point cloud data and an original image which are collected in the same area;

step S704, the cloud server projects the point cloud data to a two-dimensional plane to obtain a target image corresponding to the point cloud data;

step S706, the cloud server performs semantic segmentation on the road elements in the original image and the target image respectively to obtain semantic segmentation results;

step S708, vectorizing the road elements by the cloud server based on the point cloud data and the semantic segmentation result to obtain a road element vector;

in step S710, the cloud server outputs the road element vector.

In an alternative embodiment, the cloud server may send the road element vector to the client, and the client displays the road element vector to the client for viewing, so that the client can confirm the road element vector and ensure the accuracy of the subsequently generated high-precision map.

In the above embodiment of the present application, the semantic segmentation result may include: the method comprises the following steps of obtaining a first result corresponding to an original image and a second result corresponding to a target image, wherein the road element is vectorized based on point cloud data and a semantic segmentation result to obtain a road element vector, and the vectorization comprises the following steps: respectively carrying out pixel clustering on the first result and the second result to obtain a first pixel range and a second pixel range corresponding to the road element; clustering the point cloud data based on the first pixel range and the second pixel range respectively to obtain a first point cloud and a second point cloud corresponding to the road elements; and fitting the first point cloud and the second point cloud to generate a road element vector.

In the above embodiments of the present application, in a case that the road element includes a non-linear element, fitting the first point cloud and the second point cloud to generate a road element vector, including: fusing the first point cloud and the second point cloud based on the spatial relationship to obtain a target point cloud; fitting the target point cloud to obtain the bounding box coordinates of the nonlinear elements; a road element vector is generated based on the bounding box coordinates.

In the above embodiments of the present application, semantic segmentation is performed on road elements in an original image and a target image respectively to obtain semantic segmentation results, including: and respectively carrying out semantic segmentation on the original image and the target image through a semantic segmentation model to obtain a semantic segmentation result.

In the above embodiment of the present application, the method further includes: the cloud server divides the point cloud data to obtain a plurality of point cloud blocks; the cloud server extracts point cloud blocks containing road elements from the plurality of point cloud blocks to obtain target point cloud blocks; and the cloud server projects the cloud blocks of the target point to a two-dimensional plane to obtain a target image.

In the above embodiment of the present application, after vectorizing the road element based on the point cloud data and the semantic segmentation result to obtain a road element vector, the method further includes: the cloud server generates a target map based on the road element vector; the cloud server outputs the target map.

It should be noted that the preferred embodiments described in the above examples of the present application are the same as the schemes, application scenarios, and implementation procedures provided in example 1, but are not limited to the schemes provided in example 1.

Example 3

According to an embodiment of the present invention, there is also provided an apparatus for generating a road element vector for implementing the method for generating a road element vector in embodiment 1 described above, as shown in fig. 8, the apparatus 800 including: an acquisition module 802, a projection module 804, a semantic segmentation module 806, and a vectorization module 808.

The obtaining module 802 is configured to obtain point cloud data and an original image collected in the same area; the projection module 804 is used for projecting the point cloud data to a two-dimensional plane to obtain a target image corresponding to the point cloud data; the semantic segmentation module 806 is configured to perform semantic segmentation on the road elements in the original image and the target image respectively to obtain a semantic segmentation result; the vectorization module 808 is configured to perform vectorization on the road element based on the point cloud data and the semantic segmentation result to obtain a road element vector.

It should be noted here that the obtaining module 802, the projecting module 804, the semantic segmentation module 806, and the vectorization module 808 correspond to steps S202 to S208 in embodiment 1, and the four modules are the same as the corresponding steps in the implementation example and the application scenario, but are not limited to the disclosure in embodiment 1. It should be noted that the above modules may be operated in the computer terminal 10 provided in embodiment 1 as a part of the apparatus.

In the above embodiments of the present application, the semantic segmentation result may include: a first result corresponding to the original image and a second result corresponding to the target image, wherein the vectorization module includes: the device comprises a pixel clustering unit, a point cloud clustering unit and a fitting unit.

The pixel clustering unit is used for respectively carrying out pixel clustering on the first result and the second result to obtain a first pixel range and a second pixel range corresponding to the road element; the point cloud clustering unit is used for clustering the point cloud data based on the first pixel range and the second pixel range respectively to obtain a first point cloud and a second point cloud corresponding to the road elements; and the fitting unit is used for fitting the first point cloud and the second point cloud to generate a road element vector.

In the above embodiment of the present application, the point cloud clustering unit is further configured to perform the following steps: respectively projecting the point cloud data to a first result and a second result to obtain a first projection image and a second projection image; determining a first target pixel in the first pixel range in the first projection image and a second target pixel in the second pixel range in the second projection image; and clustering the point cloud corresponding to the first target pixel and the point cloud corresponding to the second target pixel respectively based on the spatial relationship to obtain the first point cloud and the second point cloud.

In the above embodiment of the present application, in the case that the road element includes a non-linear element, the point cloud clustering unit is further configured to perform the following steps: fusing the first point cloud and the second point cloud based on the spatial relationship to obtain a target point cloud; fitting the target point cloud to obtain the bounding box coordinates of the nonlinear elements; a road element vector is generated based on the bounding box coordinates.

In the above embodiment of the present application, in the case that the road element includes a line type element, the point cloud clustering unit is further configured to perform the following steps: fitting the first point cloud and the second point cloud respectively to generate a plurality of central line vectors of the line type elements; and according to the spatial position relation, performing curve fitting on the multiple centerline vectors at the same position to obtain a road element vector.

In the above embodiment of the present application, the semantic segmentation module is further configured to perform semantic segmentation on the original image and the target image respectively through a semantic segmentation model to obtain a semantic segmentation result.

In the above embodiment of the present application, the apparatus further includes: the device comprises a point cloud segmentation module and an extraction module.

The point cloud segmentation module is used for segmenting point cloud data to obtain a plurality of point cloud blocks; the extraction module is used for extracting point cloud blocks containing road elements from the plurality of point cloud blocks to obtain target point cloud blocks; the projection module is also used for projecting the target point cloud blocks to a two-dimensional plane to obtain a target image.

In the above embodiment of the present application, the apparatus further includes: and a map generation module.

The map generation module is used for carrying out vectorization on the road elements based on the point cloud data and the semantic segmentation result to obtain a road element vector, and then generating a target map based on the road element vector.

In the above-described embodiment of the present application, in a case where the road element includes a line type element, the map generation module includes: a determining unit and a generating unit.

The determining unit is used for determining physical parameter information of the road element vector; the generation unit is used for generating a target map based on the road element vector and the physical parameter information.

It should be noted that the preferred embodiments described in the foregoing examples of the present application are the same as the schemes, application scenarios, and implementation procedures provided in example 1, but are not limited to the schemes provided in example 1.

Example 4

According to an embodiment of the present invention, there is also provided an apparatus for generating a road element vector for implementing the method for generating a road element vector in embodiment 2, the apparatus being located in a cloud server, as shown in fig. 9, the apparatus 900 including: an acquisition module 902, a projection module 904, a semantic segmentation module 906, a vectorization module 908, and an output module 910.

The acquisition module 902 is configured to acquire point cloud data and an original image acquired in the same area; the projection module 904 is configured to project the point cloud data to a two-dimensional plane to obtain a target image corresponding to the point cloud data; the semantic segmentation module 906 is configured to perform semantic segmentation on the road elements in the original image and the target image respectively to obtain semantic segmentation results; the vectorization module 908 is configured to vectorize the road element based on the point cloud data and the semantic segmentation result to obtain a road element vector; the output module 910 is configured to output the road element vector.

It should be noted here that the above-mentioned obtaining module 902, projecting module 904, semantic dividing module 906, vectorizing module 908 and output module 910 correspond to steps S702 to S710 in embodiment 2, and the five modules are the same as the examples and application scenarios realized by the corresponding steps, but are not limited to what is disclosed in the above-mentioned embodiment 2. It should be noted that the above modules may be operated in the computer terminal 10 provided in embodiment 1 as a part of the apparatus.

The pixel clustering unit is used for respectively carrying out pixel clustering on the first result and the second result to obtain a first pixel range and a second pixel range corresponding to the road elements; the point cloud clustering unit is used for clustering the point cloud data based on the first pixel range and the second pixel range respectively to obtain a first point cloud and a second point cloud corresponding to the road elements; the fitting unit is used for fitting the first point cloud and the second point cloud to generate a road element vector.

In the above embodiment of the present application, in the case that the road element includes a line type element, the point cloud clustering unit is further configured to perform the following steps: fitting the first point cloud and the second point cloud respectively to generate a plurality of central line vectors of the line type elements; and according to the spatial position relationship, performing curve fitting on the multiple central line vectors at the same position to obtain a road element vector.

In the above embodiment of the present application, the semantic segmentation module is further configured to perform semantic segmentation on the original image and the target image respectively through a semantic segmentation model, so as to obtain a semantic segmentation result.

The map generation module is used for carrying out vectorization on road elements based on the point cloud data and the semantic segmentation result to obtain a road element vector, and then generating a target map based on the road element vector; the output module is also used for outputting the target map.

Example 5

According to an embodiment of the present invention, there is also provided a system for generating a road element vector, including:

a processor; and

and the memory is connected with the processor and used for providing the processor with instructions for processing the generation method of the road element vector in the embodiment.

Example 6

The embodiment of the invention can provide a computer terminal which can be any computer terminal device in a computer terminal group. Optionally, in this embodiment, the computer terminal may also be replaced with a terminal device such as a mobile terminal.

Optionally, in this embodiment, the computer terminal may be located in at least one network device of a plurality of network devices of a computer network.

In this embodiment, the computer terminal may execute the program code of the following steps in the method for generating a road element vector: acquiring point cloud data and an original image acquired in the same area; projecting the point cloud data to a two-dimensional plane to obtain a target image corresponding to the point cloud data; respectively carrying out semantic segmentation on road elements in the original image and the target image to obtain semantic segmentation results; and vectorizing the road elements based on the point cloud data and the semantic segmentation result to obtain a road element vector.

Alternatively, fig. 10 is a block diagram of a computer terminal according to an embodiment of the present invention. As shown in fig. 10, the computer terminal a may include: one or more processors 1002 (only one of which is shown), and memory 1004.

The memory may be used to store software programs and modules, such as program instructions/modules corresponding to the method and apparatus for generating a road element vector in the embodiment of the present invention, and the processor executes various functional applications and data processing by running the software programs and modules stored in the memory, that is, implements the method for generating a road element vector. The memory may include high speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory may further include memory remotely located from the processor, and these remote memories may be connected to terminal a through a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.

The processor can call the information and application program stored in the memory through the transmission device to execute the following steps: acquiring point cloud data and an original image acquired in the same area; projecting the point cloud data to a two-dimensional plane to obtain a target image corresponding to the point cloud data; respectively carrying out semantic segmentation on road elements in the original image and the target image to obtain semantic segmentation results; and vectorizing the road elements based on the point cloud data and the semantic segmentation result to obtain a road element vector.

Optionally, the semantic segmentation result may include: the processor may further execute the program code for: respectively carrying out pixel clustering on the first result and the second result to obtain a first pixel range and a second pixel range corresponding to the road element; clustering the point cloud data based on the first pixel range and the second pixel range respectively to obtain a first point cloud and a second point cloud corresponding to the road elements; and fitting the first point cloud and the second point cloud to generate a road element vector.

Optionally, the processor may further execute the program code of the following steps: respectively projecting the point cloud data to a first result and a second result to obtain a first projection image and a second projection image; determining a first target pixel in a first pixel range in the first projection image and a second target pixel in a second pixel range in the second projection image; and clustering the point cloud corresponding to the first target pixel and the point cloud corresponding to the second target pixel respectively based on the spatial relationship to obtain the first point cloud and the second point cloud.

Optionally, the processor may further execute the program code of the following steps: under the condition that the road elements comprise nonlinear elements, fusing the first point cloud and the second point cloud based on the spatial relationship to obtain a target point cloud; fitting the target point cloud to obtain the bounding box coordinates of the nonlinear elements; a road element vector is generated based on the bounding box coordinates.

Optionally, the processor may further execute the program code of the following steps: under the condition that the road elements comprise line type elements, fitting the first point cloud and the second point cloud respectively to generate a plurality of central line vectors of the line type elements; and according to the spatial position relationship, performing curve fitting on the multiple central line vectors at the same position to obtain a road element vector.

Optionally, the processor may further execute the program code of the following steps: and respectively carrying out semantic segmentation on the original image and the target image through a semantic segmentation model to obtain a semantic segmentation result.

Optionally, the processor may further execute the program code of the following steps: segmenting the point cloud data to obtain a plurality of point cloud blocks; extracting point cloud blocks containing road elements from the plurality of point cloud blocks to obtain target point cloud blocks; and projecting the target point cloud block to a two-dimensional plane to obtain a target image.

Optionally, the processor may further execute the program code of the following steps: and after vectorizing the road elements based on the point cloud data and the semantic segmentation result to obtain a road element vector, generating a target map based on the road element vector.

Optionally, the processor may further execute the program code of the following steps: determining physical parameter information of the road element vector in the case where the road element includes a line type element; and generating a target map based on the road element vector and the physical parameter information.

The embodiment of the invention provides a road element vector generation scheme. The point cloud data is projected into a two-dimensional plane image, semantic segmentation is carried out to extract road elements, so that the road element vector has three-dimensional information, the problem of road element loss caused by objective factors such as shielding and observation limitation of an original image can be solved, the precision requirement of a high-precision map is met, the technical effects of ensuring the integrity of the road element vector, increasing data redundancy and improving the generation precision of the road element vector are achieved, and the technical problem of large generation error of the road element vector in the related technology is solved.

It can be understood by those skilled in the art that the structure shown in fig. 10 is only an illustration, and the computer terminal may also be a terminal device such as a smart phone (e.g., an Android phone, an iOS phone, etc.), a tablet computer, a palm computer, a Mobile Internet Device (MID), a PAD, etc. Fig. 10 is a diagram illustrating a structure of the electronic device. For example, the computer terminal 10 may also include more or fewer components (e.g., network interfaces, display devices, etc.) than shown in FIG. 10, or have a different configuration than shown in FIG. 10.

Those skilled in the art will appreciate that all or part of the steps in the methods of the above embodiments may be implemented by a program instructing hardware associated with the terminal device, where the program may be stored in a computer-readable storage medium, and the storage medium may include: flash disks, Read-Only memories (ROMs), Random Access Memories (RAMs), magnetic or optical disks, and the like.

Example 7

The embodiment of the invention also provides a storage medium. Alternatively, in this embodiment, the storage medium may be configured to store the program code executed by the method for generating a road element vector provided in the first embodiment.

Optionally, in this embodiment, the storage medium may be located in any one of computer terminals in a computer terminal group in a computer network, or in any one of mobile terminals in a mobile terminal group.

Optionally, in this embodiment, the storage medium is configured to store program code for performing the following steps: acquiring point cloud data and an original image acquired in the same area; projecting the point cloud data to a two-dimensional plane to obtain a target image corresponding to the point cloud data; respectively carrying out semantic segmentation on road elements in the original image and the target image to obtain semantic segmentation results; and vectorizing the road elements based on the point cloud data and the semantic segmentation result to obtain a road element vector.

Optionally, the semantic segmentation result may include: the storage medium is further configured to store program code for performing the steps of: respectively carrying out pixel clustering on the first result and the second result to obtain a first pixel range and a second pixel range corresponding to the road element; clustering the point cloud data based on the first pixel range and the second pixel range respectively to obtain a first point cloud and a second point cloud corresponding to the road elements; and fitting the first point cloud and the second point cloud to generate a road element vector.

Optionally, the storage medium is further configured to store program codes for performing the following steps: respectively projecting the point cloud data to a first result and a second result to obtain a first projection image and a second projection image; determining a first target pixel in the first pixel range in the first projection image and a second target pixel in the second pixel range in the second projection image; and clustering the point cloud corresponding to the first target pixel and the point cloud corresponding to the second target pixel respectively based on the spatial relationship to obtain the first point cloud and the second point cloud.

Optionally, the storage medium is further configured to store program codes for performing the following steps: under the condition that the road elements comprise nonlinear elements, fusing the first point cloud and the second point cloud based on the spatial relationship to obtain a target point cloud; fitting the target point cloud to obtain the bounding box coordinates of the nonlinear elements; a road element vector is generated based on the bounding box coordinates.

Optionally, the storage medium is further configured to store program codes for performing the following steps: under the condition that the road elements comprise line type elements, fitting the first point cloud and the second point cloud respectively to generate a plurality of central line vectors of the line type elements; and according to the spatial position relationship, performing curve fitting on the multiple central line vectors at the same position to obtain a road element vector.

Optionally, the storage medium is further configured to store program codes for performing the following steps: and respectively carrying out semantic segmentation on the original image and the target image through a semantic segmentation model to obtain a semantic segmentation result.

Optionally, the storage medium is further configured to store program codes for performing the following steps: segmenting the point cloud data to obtain a plurality of point cloud blocks; extracting point cloud blocks containing road elements from the plurality of point cloud blocks to obtain target point cloud blocks; and projecting the target point cloud blocks to a two-dimensional plane to obtain a target image.

Optionally, the storage medium is further configured to store program codes for performing the following steps: and after vectorizing the road elements based on the point cloud data and the semantic segmentation result to obtain a road element vector, generating a target map based on the road element vector.

Optionally, the storage medium is further configured to store program codes for performing the following steps: determining physical parameter information of the road element vector in the case where the road element includes a line type element; and generating a target map based on the road element vector and the physical parameter information.

The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.

In the above embodiments of the present invention, the descriptions of the respective embodiments have respective emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments.

In the embodiments provided in the present application, it should be understood that the disclosed technology can be implemented in other ways. The above-described embodiments of the apparatus are merely illustrative, and for example, the division of the units is only one type of division of logical functions, and there may be other divisions when actually implemented, for example, a plurality of units or components may be combined or may be integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, units or modules, and may be in an electrical or other form.

The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.

In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit may be implemented in the form of hardware, or may also be implemented in the form of a software functional unit.

The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a removable hard disk, a magnetic or optical disk, and other various media capable of storing program codes.

The foregoing is only a preferred embodiment of the present invention, and it should be noted that, for those skilled in the art, various modifications and amendments can be made without departing from the principle of the present invention, and these modifications and amendments should also be considered as the protection scope of the present invention.

Claims

1. A method for generating a road element vector, comprising:

acquiring point cloud data and an original image acquired in the same area;

projecting the point cloud data to a two-dimensional plane to obtain a target image corresponding to the point cloud data;

respectively carrying out semantic segmentation on road elements in the original image and the target image to obtain semantic segmentation results;

and vectorizing the road elements based on the point cloud data and the semantic segmentation result to obtain a road element vector.

2. The method of claim 1, wherein the semantic segmentation results comprise: the first result corresponding to the original image and the second result corresponding to the target image, wherein vectorizing the road element based on the point cloud data and the semantic segmentation result to obtain a road element vector, includes:

respectively carrying out pixel clustering on the first result and the second result to obtain a first pixel range and a second pixel range corresponding to the road element;

clustering the point cloud data based on the first pixel range and the second pixel range respectively to obtain a first point cloud and a second point cloud corresponding to the road element;

and fitting the first point cloud and the second point cloud to generate the road element vector.

3. The method of claim 2, wherein clustering the point cloud data based on the first pixel range and the second pixel range, respectively, to obtain a first point cloud and a second point cloud corresponding to the road element comprises:

respectively projecting the point cloud data to the first result and the second result to obtain a first projection image and a second projection image;

determining a first target pixel in the first range of pixels in the first projection image and a second target pixel in the second range of pixels in the second projection image;

and clustering the point cloud corresponding to the first target pixel and the point cloud corresponding to the second target pixel respectively based on the spatial relationship to obtain the first point cloud and the second point cloud.

4. The method of claim 2, wherein fitting the first point cloud and the second point cloud to generate the road element vector if the road element comprises a nonlinear element comprises:

fusing the first point cloud and the second point cloud based on a spatial relationship to obtain a target point cloud;

fitting the target point cloud to obtain the bounding box coordinates of the nonlinear elements;

generating the road element vector based on the bounding box coordinates.

5. The method of claim 2, wherein fitting the first point cloud and the second point cloud to generate the road element vector if the road element comprises a line type element comprises:

fitting the first point cloud and the second point cloud respectively to generate a plurality of central line vectors of the line type elements;

and according to the spatial position relationship, performing curve fitting on the vectors of the plurality of central lines at the same position to obtain the road element vector.

6. The method according to claim 1, wherein performing semantic segmentation on the road elements in the original image and the target image respectively to obtain semantic segmentation results comprises:

and performing semantic segmentation on the original image and the target image respectively through a semantic segmentation model to obtain a semantic segmentation result.

7. The method of claim 1, further comprising:

segmenting the point cloud data to obtain a plurality of point cloud blocks;

extracting point cloud blocks containing the road elements from the plurality of point cloud blocks to obtain target point cloud blocks;

and projecting the target cloud block to the two-dimensional plane to obtain the target image.

8. The method according to any one of claims 1 to 7, wherein after vectorizing the road element based on the point cloud data and the semantic segmentation result to obtain a road element vector, the method further comprises:

and generating a target map based on the road element vector.

9. The method of claim 8, wherein generating a target map based on the road element vector in a case where the road element includes a line-type element comprises:

determining physical parameter information of the road element vector;

and generating the target map based on the road element vector and the physical parameter information.

10. A method for generating a road element vector, comprising:

the cloud server receives point cloud data and an original image which are collected in the same area;

the cloud server projects the point cloud data to a two-dimensional plane to obtain a target image corresponding to the point cloud data;

the cloud server performs semantic segmentation on the road elements in the original image and the target image respectively to obtain semantic segmentation results;

the cloud server vectorizes the road elements based on the point cloud data and the semantic segmentation result to obtain a road element vector;

the cloud server outputs the road element vector.

11. A storage medium characterized by comprising a stored program, wherein a device in which the storage medium is located is controlled to execute the method for generating a road element vector according to any one of claims 1 to 10 when the program is executed.

12. An electronic terminal, comprising: a memory; a processor connected to the memory, the processor being configured to run a program, wherein the program is configured to execute the method for generating a road element vector according to any one of claims 1 to 10 when running.

13. A system for generating a road element vector, comprising:

a processor; and

a memory, connected to the processor, for providing the processor with instructions to process the method for generating a road element vector according to any one of claims 1 to 10.