CN112565387B

CN112565387B - Method and device for updating high-precision map

Info

Publication number: CN112565387B
Application number: CN202011383175.7A
Authority: CN
Inventors: 范昌诗; 吴伟
Original assignee: Beijing Rockwell Technology Co Ltd
Current assignee: Beijing Rockwell Technology Co Ltd
Priority date: 2020-12-01
Filing date: 2020-12-01
Publication date: 2023-07-07
Anticipated expiration: 2040-12-01
Also published as: CN112565387A

Abstract

The application discloses a method and a device for updating a high-precision map, and relates to the technical field of high-precision maps. The method comprises the following steps: acquiring driving data corresponding to a plurality of target vehicles, wherein the driving data corresponding to the target vehicles are acquired when the target vehicles pass through a target road section in a target time period, and the driving data corresponding to the target vehicles comprise: the method comprises the steps of driving route information corresponding to a target vehicle, driving video corresponding to the target vehicle and camera calibration files corresponding to the target vehicle; determining a plurality of target pavement element position information acquired and obtained by each target vehicle according to the driving route information, the driving video and the camera calibration file corresponding to each target vehicle; and updating the high-precision map according to the acquired position information of the plurality of target road surface elements of each target vehicle. The method and the device are suitable for the process of updating the high-precision map.

Description

Method and device for updating high-precision map

Technical Field

The application relates to the technical field of high-precision maps, in particular to a method and a device for updating a high-precision map.

Background

With the continuous development of science and technology, the automatic driving technology is also rapidly developed. The high-precision map is a foundation for realizing automatic driving, and specifically comprises traffic signs, traffic lights, street lamp poles and other elements for automatic driving vehicle navigation. Due to the reasons of road construction and the like, the positions of the traffic signs, the positions of the traffic lights and the positions of the street lamp poles in the road are changed, so that the positions of the traffic signs, the positions of the traffic lights and the positions of the street lamp poles in the high-precision map are required to be updated in time in order to ensure the driving safety of an automatic driving vehicle.

At present, a centralized drawing mode is generally adopted to update the position of a traffic sign board, the position of a traffic lamp and the position of a street lamp post in a high-precision map, namely, a manufacturer of the high-precision map acquires the position information of the traffic sign board, the position information of the traffic lamp and the position information of the street lamp post of a target road section through a self-refitted data acquisition vehicle, and then updates the high-precision map through the position information of the traffic sign board, the position information of the traffic lamp and the position information of the street lamp post acquired by the data acquisition vehicle. However, the problem arises that the cost of updating the high-precision map is high due to the high cost of retrofitting the data acquisition vehicle.

Disclosure of Invention

The embodiment of the application provides a method and a device for updating a high-precision map, which mainly aim to reduce the cost for updating the high-precision map on the basis of ensuring that the position of a traffic sign board, the position of a traffic light and the position of a street light pole in the high-precision map are updated in time.

In order to solve the technical problems, the embodiment of the application provides the following technical scheme:

in a first aspect, the present application provides a method of updating a high-precision map, the method comprising:

acquiring driving data corresponding to a plurality of target vehicles, wherein the driving data corresponding to the target vehicles are acquired when the target vehicles pass through a target road section in a target time period, and the driving data corresponding to the target vehicles comprise: the driving route information corresponding to the target vehicle, the driving video corresponding to the target vehicle and the camera calibration file corresponding to the target vehicle;

Determining a plurality of target pavement element position information acquired and obtained by each target vehicle according to the driving route information, the driving video and the camera calibration file corresponding to each target vehicle, wherein the target pavement element position information is the position information of a target traffic sign board, a target traffic light or a target street light pole in the target road section in a high-precision map;

and updating the high-precision map according to the acquired position information of the plurality of target pavement elements of each target vehicle.

Optionally, the determining, according to the driving route information, the driving video and the camera calibration file corresponding to each target vehicle, the position information of the plurality of target road surface elements acquired by each target vehicle includes:

extracting multi-frame driving images from driving videos corresponding to the target vehicles, wherein the driving images comprise target pavement elements, and the target pavement elements are specifically target traffic signboards, target traffic lights or target street lamp poles;

determining positioning information corresponding to each frame of the driving image according to driving video and driving route information corresponding to the target vehicle, wherein the positioning information corresponding to the driving image is the position information of the target vehicle in the high-precision map when the target vehicle shoots the driving image;

And determining the position information of a plurality of target pavement elements acquired by the target vehicle according to the camera calibration file corresponding to the target vehicle, the multi-frame driving image and the positioning information corresponding to each frame of driving image.

Optionally, the determining, according to the camera calibration file corresponding to the target vehicle, the multi-frame driving image, and the positioning information corresponding to each frame of the driving image, the position information of the plurality of target road surface elements acquired by the target vehicle includes:

acquiring the actual size corresponding to each target pavement element from the high-precision map;

determining the image size and the image position corresponding to each target pavement element according to a preset perception recognition algorithm and a plurality of frames of the driving images, wherein the image size corresponding to the target pavement element is the size of the target pavement element in the corresponding driving image, and the image position corresponding to the target pavement element is the position of the target pavement element in the corresponding driving image;

substituting the actual size, the image size and the image position corresponding to each target pavement element into a preset similar triangle algorithm to calculate and obtain a first position corresponding to each target pavement element, wherein the first position corresponding to the target pavement element is the position of the target pavement element relative to a preset camera of the target vehicle;

Determining a second position corresponding to each target pavement element according to the first position corresponding to each target pavement element and the camera calibration file, wherein the second position corresponding to each target pavement element is the position of the target pavement element relative to the target vehicle;

and determining a plurality of pieces of target pavement element position information acquired and obtained by the target vehicle according to the second position corresponding to each target pavement element and the positioning information corresponding to each driving image.

Optionally, the updating the high-precision map according to the plurality of target pavement element position information acquired by each target vehicle includes:

grouping the position information of a plurality of target pavement elements corresponding to each target pavement element so as to divide the position information of the target pavement elements corresponding to each target pavement element and at the same position into the same set;

determining the position information of the target pavement element in the set with the largest number of elements in the sets corresponding to each target pavement element as the position of the pavement element to be updated corresponding to each target pavement element;

and updating the high-precision map by using the positions of the road surface elements to be updated corresponding to each target road surface element.

acquiring the position of an original pavement element corresponding to each target pavement element from the high-precision map;

comparing the position information of a plurality of target pavement elements corresponding to each target pavement element with the position of an original pavement element corresponding to each target pavement element to obtain a plurality of deviation pavement element positions corresponding to each target pavement element;

if the proportion of the number of the plurality of deviation pavement element positions corresponding to the target pavement element to the number of the plurality of target pavement element position information corresponding to the target pavement element is larger than a preset proportion threshold value, determining the pavement element position to be updated corresponding to the target pavement element according to the plurality of deviation pavement element positions corresponding to the target pavement element;

and updating the high-precision map by using the position of the road surface element to be updated corresponding to the target road surface element.

Optionally, before the acquiring the driving data corresponding to the plurality of target vehicles, the method further includes:

Receiving driving data sent by each target vehicle;

and storing the driving data sent by each target vehicle into a local storage space.

Optionally, the target vehicle is a common vehicle provided with a preset camera and a GPS sensor.

In a second aspect, the present application further provides an apparatus for updating a high-precision map, the apparatus comprising:

the system comprises an acquisition unit, a control unit and a control unit, wherein the acquisition unit is used for acquiring driving data corresponding to a plurality of target vehicles, the driving data corresponding to the target vehicles are acquired when the target vehicles pass through a target road section in a target time period, and the driving data corresponding to the target vehicles comprise: the driving route information corresponding to the target vehicle, the driving video corresponding to the target vehicle and the camera calibration file corresponding to the target vehicle;

the determining unit is used for determining a plurality of target pavement element position information acquired and obtained by each target vehicle according to the driving route information, the driving video and the camera calibration file corresponding to each target vehicle, wherein the target pavement element position information is the position information of a target traffic sign board, a target traffic light or a target street light pole in the target road section in a high-precision map;

And the updating unit is used for updating the high-precision map according to the acquired position information of the plurality of target road surface elements of each target vehicle.

Optionally, the determining unit includes:

the extraction module is used for extracting multi-frame driving images from driving videos corresponding to the target vehicles, wherein the driving images contain target pavement elements, and the target pavement elements are specifically target traffic signboards, target traffic lights or target street lamp poles;

the first determining module is used for determining positioning information corresponding to the driving image of each frame according to driving video and driving route information corresponding to the target vehicle, wherein the positioning information corresponding to the driving image is the position information of the target vehicle in the high-precision map when the target vehicle shoots the driving image;

and the second determining module is used for determining a plurality of pieces of target pavement element position information acquired and obtained by the target vehicle according to the camera calibration file corresponding to the target vehicle, the multi-frame driving image and the positioning information corresponding to each frame of driving image.

Optionally, the second determining module includes:

the obtaining submodule is used for obtaining the actual size corresponding to each target pavement element in the high-precision map;

The first determining submodule is used for determining the image size and the image position corresponding to each target pavement element according to a preset perception recognition algorithm and a plurality of frames of driving images, wherein the image size corresponding to the target pavement element is the size of the target pavement element in the corresponding driving image, and the image position corresponding to the target pavement element is the position of the target pavement element in the corresponding driving image;

substituting a sub-module, configured to substitute the actual size, the image size and the image position corresponding to each target pavement element into a preset similar triangle algorithm to calculate and obtain a first position corresponding to each target pavement element, where the first position corresponding to the target pavement element is a position of the target pavement element relative to a preset camera of the target vehicle;

the second determining submodule is used for determining a second position corresponding to each target pavement element according to the first position corresponding to each target pavement element and the camera calibration file, wherein the second position corresponding to each target pavement element is the position of the target pavement element relative to the target vehicle;

And the third determining submodule is used for determining a plurality of pieces of target pavement element position information acquired and obtained by the target vehicle according to the second position corresponding to each target pavement element and the positioning information corresponding to each driving image frame.

Optionally, the updating unit includes:

the grouping module is used for grouping the plurality of target pavement element position information corresponding to each target pavement element so as to divide the target pavement element position information corresponding to each target pavement element and at the same position into the same set;

the third determining module is used for determining the position information of the target pavement element in the set with the largest number of elements in the sets corresponding to each target pavement element as the position of the pavement element to be updated corresponding to each target pavement element;

and the first updating module is used for updating the high-precision map by using the pavement element positions to be updated corresponding to each target pavement element.

Optionally, the updating unit includes:

the acquisition module is used for acquiring the original pavement element position corresponding to each target pavement element from the high-precision map;

the comparison module is used for comparing the position information of the plurality of target pavement elements corresponding to each target pavement element with the original pavement element position corresponding to each target pavement element so as to obtain a plurality of deviation pavement element positions corresponding to each target pavement element;

A fourth determining module, configured to determine, when a ratio of the number of the plurality of deviation pavement element positions corresponding to the target pavement element to the number of the plurality of target pavement element position information corresponding to the target pavement element is greater than a preset ratio threshold, a pavement element position to be updated corresponding to the target pavement element according to the plurality of deviation pavement element positions corresponding to the target pavement element;

and the second updating module is used for updating the high-precision map by using the position of the road surface element to be updated corresponding to the target road surface element.

Optionally, the apparatus further includes:

the receiving unit is used for receiving the driving data sent by each target vehicle before the obtaining unit obtains the driving data corresponding to the plurality of target vehicles;

and the storage unit is used for storing the driving data sent by each target vehicle into a local storage space.

In a third aspect, an embodiment of the present application provides a storage medium, where the storage medium includes a stored program, where the program, when executed, controls a device where the storage medium is located to execute the method for updating a high-precision map according to the first aspect.

In a fourth aspect, embodiments of the present application provide an apparatus for updating a high-precision map, the apparatus comprising a storage medium; and one or more processors coupled to the storage medium, the processors configured to execute the program instructions stored in the storage medium; the program instructions, when executed, perform the method of updating a high-precision map of the first aspect.

By means of the technical scheme, the technical scheme provided by the application has the following advantages:

compared with the prior art that the traffic sign board position, the traffic light position and the street light pole position in the high-precision map are updated in a centralized drawing mode, the method and the device can acquire driving data acquired when a plurality of target vehicles travel through a target road section in a target time period (namely driving videos acquired through a preset camera, driving route information recorded through a GPS sensor and camera calibration files corresponding to the preset camera) through a cloud server, and then the cloud server determines the target road surface element position information corresponding to each target traffic sign board acquired and/or the target road surface element position information corresponding to each target traffic light by each target vehicle according to the driving route information acquired and driving videos and camera calibration files acquired by each target vehicle, and/or the target road surface element position information corresponding to each target traffic sign board and/or the target road surface element position information corresponding to each target street light pole, and then the cloud server updates the high-precision map according to the target road surface element position information corresponding to each target traffic sign board acquired and/or the target road surface element position information corresponding to each target street light pole. Because the target vehicle is a common vehicle provided with the preset camera and the GPS sensor, and after the target vehicle acquires the driving data, the driving data acquired by the target vehicle can be uploaded to the cloud server, so that the cloud server can reduce the cost of updating the high-precision map on the basis of ensuring timely updating of the traffic sign position, the traffic light position and the street light pole position in the high-precision map.

The foregoing description is only an overview of the technical solutions of the present application, and may be implemented according to the content of the specification in order to make the technical means of the present application more clearly understood, and in order to make the above-mentioned and other objects, features and advantages of the present application more clearly understood, the following detailed description of the present application will be given.

Drawings

The above, as well as additional purposes, features, and advantages of exemplary embodiments of the present application will become readily apparent from the following detailed description when read in conjunction with the accompanying drawings. Several embodiments of the present application are illustrated by way of example and not by way of limitation in the figures of the accompanying drawings, in which like reference numerals refer to similar or corresponding parts and in which:

fig. 1 shows a flowchart of a method for updating a high-precision map according to an embodiment of the present application;

FIG. 2 shows a flowchart of another method for updating a high-precision map provided by an embodiment of the present application;

FIG. 3 shows a block diagram of an apparatus for updating a high-precision map according to an embodiment of the present application;

fig. 4 shows a block diagram of another apparatus for updating a high-precision map according to an embodiment of the present application.

Detailed Description

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

It is noted that unless otherwise indicated, technical or scientific terms used herein should be given the ordinary meaning as understood by one of ordinary skill in the art to which this application belongs.

The embodiment of the application provides a method for updating a high-precision map, as shown in fig. 1, the method comprises the following steps:

101. and acquiring driving data corresponding to the plurality of target vehicles.

The target vehicle is a vehicle passing through a target road section in a target time period, and specifically is a common vehicle provided with a preset camera and a GPS sensor; the driving data corresponding to the target vehicle is acquired when the target vehicle passes through a target road section in a target time period, and the method specifically comprises the following steps: the method comprises the steps of driving route information corresponding to a target vehicle, driving video corresponding to the target vehicle and camera calibration files corresponding to the target vehicle; the target road section comprises a plurality of target traffic signs, and/or a plurality of target traffic lights, and/or a plurality of target street lamp poles.

In the embodiment of the present application, the execution subject in each step is a cloud server. When any target vehicle runs through a target road section in a target time period, driving data acquired in the driving process (namely driving video shot by a preset camera, driving route information recorded by a GPS sensor and a camera calibration file corresponding to the preset camera) are sent to a cloud server, so that when a preset updating moment is reached, the cloud server can acquire the driving data acquired when a plurality of target vehicles pass through the target road section in the target time period, wherein the preset updating moment can be but is not limited to: daily 00:00: 00. daily 12:00:00, the target time period may be, but is not limited to being: 24 hours before the preset update time, 48 hours before the preset update time, 36 hours before the preset update time, and so on.

102. And determining the position information of a plurality of target pavement elements acquired and obtained by each target vehicle according to the driving route information, the driving video and the camera calibration file corresponding to each target vehicle.

In this embodiment of the present application, after acquiring driving data acquired when a plurality of target vehicles pass through a target road segment in a target time period, the cloud server may determine, according to driving data (driving route information, driving video and camera calibration file) acquired by each target vehicle, a plurality of target road surface element position information acquired by each target vehicle, that is, according to driving route information, driving video and camera calibration file acquired by each target vehicle, determine, according to target road surface element position information corresponding to each target traffic sign acquired by each target vehicle, and/or target road surface element position information corresponding to each target traffic lamp, and/or target road surface element position information corresponding to each target street lamp post, where the target road surface element position information corresponding to the target traffic sign is position information of the target traffic sign in the high-precision map, and the target road surface element position information corresponding to the target traffic lamp is position information of the target traffic lamp in the high-precision map.

103. And updating the high-precision map according to the acquired position information of the plurality of target road surface elements of each target vehicle.

In this embodiment of the present application, after determining, according to driving data (driving route information, driving video, and camera calibration file) acquired by each target vehicle, a cloud server may update the high-precision map according to the plurality of target road surface element position information acquired by each target vehicle, that is, according to the target road surface element position information corresponding to each target traffic sign acquired by each target vehicle, and/or the target road surface element position information corresponding to each target traffic lamp, and/or the target road surface element position information corresponding to each target street lamp post.

Compared with the prior art that the traffic sign board position, the traffic light position and the street light pole position in the high-precision map are updated in a centralized drawing mode, the method for updating the high-precision map can acquire driving data acquired when a plurality of target vehicles travel through a target road section in a target time period (namely driving videos acquired through a preset camera, driving route information recorded through a GPS sensor and camera calibration files corresponding to the preset camera) at a cloud server, and then the cloud server determines the target road surface element position information corresponding to each target traffic sign board acquired by each target vehicle and/or the target road surface element position information corresponding to each target traffic light and/or the target road surface element position information corresponding to each target street light pole according to driving route information acquired through the preset camera, driving route information recorded through the GPS sensor and the camera calibration files corresponding to each target traffic sign board, and then the cloud server updates the high-precision map according to the target road surface element position information corresponding to each target traffic sign board acquired by each target vehicle and/or the target road surface element position information corresponding to each target street light pole. Because the target vehicle is a common vehicle provided with the preset camera and the GPS sensor, and after the target vehicle acquires the driving data, the driving data acquired by the target vehicle can be uploaded to the cloud server, so that the cloud server can reduce the cost of updating the high-precision map on the basis of ensuring timely updating of the traffic sign position, the traffic light position and the street light pole position in the high-precision map.

For more detailed description below, another method for updating a high-precision map is provided in the embodiments of the present application, specifically as shown in fig. 2, the method includes:

201. and receiving the driving data sent by each target vehicle, and storing the driving data sent by each target vehicle into a local storage space.

In the embodiment of the application, when each target vehicle runs through a target road section in a target time period, driving data (namely driving video shot by a preset camera, driving route information recorded by a GPS sensor and a camera calibration file corresponding to the preset camera) acquired in the driving process are sent to a cloud server; after the cloud server receives the driving data sent by each target vehicle, the driving data sent by each target vehicle are stored in the local storage space, so that when a preset updating moment is reached, the cloud server can acquire the driving data acquired when each target vehicle passes through a target road section in a target time period from the local storage space.

202. And acquiring driving data corresponding to the plurality of target vehicles.

Regarding step 202, the obtaining of driving data corresponding to the plurality of target vehicles may refer to the description of the corresponding portion of fig. 1, and the embodiments of the present application will not be repeated here.

203. And determining the position information of a plurality of target pavement elements acquired and obtained by each target vehicle according to the driving route information, the driving video and the camera calibration file corresponding to each target vehicle.

In the embodiment of the application, after acquiring the driving data acquired when a plurality of target vehicles pass through the target road section in the target time period, the cloud server can determine the position information of a plurality of target road surface elements acquired by each target vehicle according to the driving data (driving route information, driving video and camera calibration file) acquired by each target vehicle.

Specifically, in this embodiment of the present application, for any one target vehicle, the cloud server may determine, according to the driving route information, the driving video, and the camera calibration file corresponding to the target vehicle, a plurality of target road surface element position information acquired by the target vehicle in the following manner:

(1) And extracting multi-frame driving images from driving videos corresponding to the target vehicles.

The driving video corresponding to the target vehicle consists of multiple frames of images, the driving image corresponding to the target vehicle is specifically an image containing target pavement elements, and the target pavement elements are specifically target traffic signs in a target road section, target traffic lights in the target road section or target street lamp posts in the target road section.

(2) And determining positioning information corresponding to each frame of driving image according to the driving video and the driving route information corresponding to the target vehicle.

The positioning information corresponding to any driving image is the position information of the target vehicle in the high-precision map when the target vehicle shoots the driving image.

In the embodiment of the application, after the cloud server extracts the multi-frame driving image from the driving video corresponding to the target vehicle, the positioning information corresponding to each frame of driving image can be determined according to the driving video corresponding to the target vehicle and the driving route information. Specifically, in this step, the cloud server may align the timestamp sequence corresponding to the driving route information with the multi-frame image included in the driving video, thereby determining the positioning information corresponding to each frame of image included in the driving video, and then determine the positioning information corresponding to each frame of driving image according to the positioning information corresponding to each frame of image included in the driving video, but is not limited thereto.

(3) And determining the position information of a plurality of target pavement elements acquired by the target vehicle according to the camera calibration file corresponding to the target vehicle, the multi-frame driving image and the positioning information corresponding to each frame driving image.

In the embodiment of the application, after determining the positioning information corresponding to each frame of driving image according to the driving video and the driving route information corresponding to the target vehicle, the cloud server can determine a plurality of pieces of target pavement element position information acquired and obtained by the target vehicle according to the camera calibration file corresponding to the target vehicle, the multi-frame driving image and the positioning information corresponding to each frame of driving image.

Specifically, in this step, the cloud server may determine, according to the camera calibration file corresponding to the target vehicle, the multi-frame driving image, and the positioning information corresponding to each frame of driving image, the position information of the plurality of target road surface elements acquired by the target vehicle in the following manner: firstly, acquiring an actual size corresponding to each target pavement element in a high-precision map, wherein the actual size corresponding to each target pavement element (a target traffic sign board, a target traffic light or a target street lamp post) in a target road section is recorded in the high-precision map; then, determining the image size and the image position corresponding to each target pavement element according to a preset perception recognition algorithm and a multi-frame driving image, wherein the image size corresponding to the target pavement element is the size of the target pavement element in the corresponding driving image, the image position corresponding to the target pavement element is the position of the target pavement element in the corresponding driving image, the preset perception recognition algorithm can be specifically any existing deep learning recognition algorithm, and the embodiment of the application is not specifically limited to the above; secondly, substituting the actual size, the image size and the image position corresponding to each target pavement element into a preset similar triangle algorithm, so as to calculate and obtain a first position corresponding to each target pavement element, wherein the first position corresponding to the target pavement element is the position of the target pavement element relative to a preset camera of the target vehicle; thirdly, determining a second position corresponding to each target pavement element according to a first position corresponding to each target pavement element and a camera calibration file, wherein the second position corresponding to each target pavement element is the position of the target pavement element relative to a target vehicle, the camera calibration file is specifically an external parameter calibration file, and the second position corresponding to the target pavement element can be determined according to the position of the target pavement element relative to a preset camera of the target vehicle (namely, the first position corresponding to the target pavement element) and the external parameter calibration file; and finally, determining the position information of a plurality of target pavement elements acquired by the target vehicle according to the second position corresponding to each target pavement element and the positioning information corresponding to each frame of driving image.

204. And updating the high-precision map according to the acquired position information of the plurality of target road surface elements of each target vehicle.

In this embodiment of the present application, after determining the position information of a plurality of target road surface elements acquired and obtained by each target vehicle according to the driving data (driving route information, driving video and camera calibration file) acquired and obtained by each target vehicle, the cloud server may update the high-precision map according to the position information of a plurality of target road surface elements acquired and obtained by each target vehicle.

Specifically, in the embodiment of the present application, the cloud server may update the high-precision map according to the position information of a plurality of target road surface elements acquired and obtained by each target vehicle in the following two ways:

(1) Firstly, grouping a plurality of target pavement element position information corresponding to each target pavement element to divide the target pavement element position information corresponding to each target pavement element and at the same position into the same set; secondly, determining the position information of the target pavement elements in the set with the largest number of elements in the sets corresponding to each target pavement element as the position of the pavement element to be updated corresponding to each target pavement element; and finally, updating the high-precision map by using the positions of the road surface elements to be updated corresponding to each target road surface element. For example, when a target road surface element is specifically a certain target traffic sign board in a target road section, first, a plurality of target road surface element position information corresponding to the target traffic sign board is subjected to grouping processing, so that the target road surface element position information corresponding to the target traffic sign board and at the same position is divided into the same set; secondly, determining the position information of the target road surface element in the set with the largest element number in the sets corresponding to the target traffic sign as the position of the road surface element to be updated corresponding to the target traffic sign; and finally, updating the high-precision map by using the position of the road surface element to be updated corresponding to the target traffic sign board.

(2) Firstly, acquiring an original pavement element position corresponding to each target pavement element from a high-precision map, wherein the original pavement element position corresponding to the target pavement element is position information recorded in the high-precision map and corresponding to the target pavement element; then, comparing the position information of a plurality of target pavement elements corresponding to each target pavement element with the position of an original pavement element corresponding to each target pavement element to obtain a plurality of deviation pavement element positions corresponding to each target pavement element, wherein if the position information of a certain target pavement element corresponding to a certain target pavement element is the same as the position of the original pavement element corresponding to the target pavement element, the position information of the target pavement element is determined to be the position of a non-deviation pavement element corresponding to the target pavement element, and if the position information of a certain target pavement element corresponding to a certain target pavement element is different from the position of the original pavement element corresponding to the target pavement element, the position information of the target pavement element is determined to be the position of the deviation pavement element corresponding to the target pavement element; secondly, for any one target pavement element, if the proportion of the number of the plurality of deviation pavement element positions corresponding to the target pavement element to the number of the plurality of target pavement element position information corresponding to the target pavement element is greater than a preset proportion threshold, determining the pavement element position to be updated corresponding to the target pavement element according to the plurality of deviation pavement element positions corresponding to the target pavement element, specifically, determining the average value of the plurality of deviation pavement element positions corresponding to the target pavement element as the pavement element position to be updated corresponding to the target pavement element, but not limited to, where the preset proportion threshold may be: 30%, 40%, 50%, etc.; and finally, after obtaining the position of the road surface element to be updated corresponding to a certain target road surface element, updating the high-precision map by using the position of the road surface element to be updated corresponding to the target road surface element. For example, when the target road surface element is specifically a certain target traffic light in the target road section, firstly, the original road surface element position corresponding to the target traffic light is obtained from a high-precision map; then, comparing the position information of a plurality of target road surface elements corresponding to the target traffic light with the original road surface element positions corresponding to the target traffic light to obtain a plurality of deviation road surface element positions corresponding to the target traffic light; secondly, if the proportion of the number of the plurality of deviation pavement element positions corresponding to the target traffic light to the number of the plurality of target pavement element position information corresponding to the target traffic light is larger than a preset proportion threshold value, determining the pavement element position to be updated corresponding to the target traffic light according to the plurality of deviation pavement element positions corresponding to the target traffic light, namely determining the average value of the plurality of deviation pavement element positions corresponding to the target traffic light as the pavement element position to be updated corresponding to the target traffic light; and finally, updating the high-precision map by using the road surface element position to be updated corresponding to the target traffic light.

In order to achieve the above object, according to another aspect of the present application, an embodiment of the present application further provides a storage medium, where the storage medium includes a stored program, and when the program runs, the device where the storage medium is controlled to execute the method for updating the high-precision map described above.

To achieve the above object, according to another aspect of the present application, there is also provided an apparatus for updating a high-precision map, the apparatus including a storage medium; and one or more processors coupled to the storage medium, the processors configured to execute the program instructions stored in the storage medium; and executing the method for updating the high-precision map when the program instructions run.

Further, as an implementation of the method shown in fig. 1 and fig. 2, another embodiment of the present application further provides a device for updating a high-precision map. The embodiment of the device corresponds to the embodiment of the method, and for convenience of reading, details of the embodiment of the method are not repeated one by one, but it should be clear that the device in the embodiment can correspondingly realize all the details of the embodiment of the method. The device is applied to on guaranteeing in time to update traffic sign board position, traffic light position and street lamp pole position in the high-definition map on the basis, reduces the cost of updating the high-definition map, and specifically as shown in fig. 3, and the device includes:

The acquiring unit 31 is configured to acquire driving data corresponding to a plurality of target vehicles, where the driving data corresponding to the target vehicles is acquired when the target vehicles pass through a target road section in a target time period, and the driving data corresponding to the target vehicles includes: the driving route information corresponding to the target vehicle, the driving video corresponding to the target vehicle and the camera calibration file corresponding to the target vehicle;

a determining unit 32, configured to determine, according to driving route information, driving video, and camera calibration files corresponding to each target vehicle, a plurality of target road surface element position information acquired and obtained by each target vehicle, where the target road surface element position information is position information of a target traffic sign board, a target traffic light, or a target street light post in the target road section in a high-precision map;

and an updating unit 33, configured to update the high-precision map according to the plurality of target road surface element position information acquired and obtained by each of the target vehicles.

Further, as shown in fig. 4, the determination unit 32 includes:

the extracting module 321 is configured to extract a plurality of frame driving images from a driving video corresponding to the target vehicle, where the driving images include target pavement elements, and the target pavement elements are specifically target traffic signs, target traffic lights or target street lamp posts;

A first determining module 322, configured to determine positioning information corresponding to the driving image of each frame according to driving video and driving route information corresponding to the target vehicle, where the positioning information corresponding to the driving image is position information of the target vehicle in the high-precision map when the target vehicle shoots the driving image;

the second determining module 323 is configured to determine, according to a camera calibration file corresponding to the target vehicle, a multi-frame driving image, and positioning information corresponding to each frame of driving image, a plurality of target pavement element position information acquired by the target vehicle.

Further, as shown in fig. 4, the second determining module 323 includes:

an obtaining submodule 3231, configured to obtain an actual size corresponding to each target pavement element in the high-precision map;

a first determining submodule 3232, configured to determine, according to a preset perception recognition algorithm and a plurality of frames of driving images, an image size and an image position corresponding to each target road surface element, where the image size corresponding to the target road surface element is the size of the target road surface element in the corresponding driving image, and the image position corresponding to the target road surface element is the position of the target road surface element in the corresponding driving image;

Substituting sub-module 3233, configured to substitute the actual size, the image size and the image position corresponding to each target pavement element into a preset similar triangle algorithm, so as to calculate and obtain a first position corresponding to each target pavement element, where the first position corresponding to the target pavement element is a position of the target pavement element relative to a preset camera of the target vehicle;

a second determining submodule 3234, configured to determine a second position corresponding to each target road surface element according to the first position corresponding to each target road surface element and the camera calibration file, where the second position corresponding to each target road surface element is a position of the target road surface element relative to the target vehicle;

and a third determining submodule 3235, configured to determine, according to the second position corresponding to each target road surface element and the positioning information corresponding to each driving image frame, a plurality of target road surface element position information acquired and obtained by the target vehicle.

Further, as shown in fig. 4, the updating unit 33 includes:

the grouping module 331 is configured to perform grouping processing on the plurality of target pavement element position information corresponding to each target pavement element, so as to divide the target pavement element position information corresponding to each target pavement element and having the same position into the same set;

A third determining module 332, configured to determine, as a pavement element position to be updated corresponding to each target pavement element, target pavement element position information in a set with the largest number of elements in a plurality of sets corresponding to each target pavement element;

a first updating module 333, configured to update the high-precision map using the pavement element positions to be updated corresponding to each of the target pavement elements.

Further, as shown in fig. 4, the updating unit 33 includes:

an obtaining module 334, configured to obtain, from the high-precision map, an original pavement element position corresponding to each of the target pavement elements;

a comparison module 335, configured to compare the position information of multiple target pavement elements corresponding to each target pavement element with the position of the original pavement element corresponding to each target pavement element, so as to obtain multiple deviation pavement element positions corresponding to each target pavement element;

a fourth determining module 336, configured to determine, when a ratio of the number of the plurality of deviation road surface element positions corresponding to the target road surface element to the number of the plurality of target road surface element position information corresponding to the target road surface element is greater than a preset ratio threshold, a road surface element position to be updated corresponding to the target road surface element according to the plurality of deviation road surface element positions corresponding to the target road surface element;

And a second updating module 337, configured to update the high-precision map using the pavement element position to be updated corresponding to the target pavement element.

Further, as shown in fig. 4, the apparatus further includes:

a receiving unit 34, configured to receive driving data sent by each target vehicle before the obtaining unit 31 obtains driving data corresponding to a plurality of target vehicles;

and a storage unit 35, configured to store the driving data sent by each target vehicle into a local storage space.

Further, as shown in fig. 4, the target vehicle is a general vehicle equipped with a preset camera and a GPS sensor.

Compared with the prior art that the traffic sign position, the traffic light position and the street light pole position in the high-precision map are updated in a centralized drawing mode, the method and the device for updating the high-precision map can acquire driving data acquired when a plurality of target vehicles travel through a target road section in a target time period (namely driving videos acquired through preset cameras, driving route information recorded through GPS sensors and camera calibration files corresponding to the preset cameras) at a cloud server, and then the cloud server determines the target road surface element position information corresponding to each target traffic sign acquired by each target vehicle and/or the target road surface element position information corresponding to each target traffic light and/or the target road surface element position information corresponding to each target road lamp pole according to the driving route information acquired by each target vehicle, the driving route information recorded through the GPS sensors and the camera calibration files corresponding to the preset cameras, and then the cloud server updates the target road surface element position information corresponding to each target traffic sign and/or the target road surface element position information corresponding to each target road surface lamp pole. Because the target vehicle is a common vehicle provided with the preset camera and the GPS sensor, and after the target vehicle acquires the driving data, the driving data acquired by the target vehicle can be uploaded to the cloud server, so that the cloud server can reduce the cost of updating the high-precision map on the basis of ensuring timely updating of the traffic sign position, the traffic light position and the street light pole position in the high-precision map.

The device for updating the high-precision map comprises a processor and a memory, wherein the acquisition unit, the determination unit, the updating unit and the like are stored in the memory as program units, and the processor executes the program units stored in the memory to realize corresponding functions.

The processor includes a kernel, and the kernel fetches the corresponding program unit from the memory. The inner core can be provided with one or more than one, and the cost for updating the high-precision map is reduced on the basis of ensuring the timely updating of the traffic sign position, the traffic light position and the street light pole position by adjusting the inner core parameters.

The embodiment of the application provides a storage medium, which comprises a stored program, wherein when the program runs, equipment where the storage medium is located is controlled to execute the method for updating the high-precision map.

The storage medium may include volatile memory, random Access Memory (RAM) and/or nonvolatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM), among other forms in computer readable media, the memory including at least one memory chip.

The embodiment of the application also provides a device for updating the high-precision map, which comprises a storage medium; and one or more processors coupled to the storage medium, the processors configured to execute the program instructions stored in the storage medium; and executing the method for updating the high-precision map when the program instructions run.

The embodiment of the application provides equipment, which comprises a processor, a memory and a program stored on the memory and capable of running on the processor, wherein the processor executes the program to realize the following steps:

Further, the determining, according to the driving route information, the driving video and the camera calibration file corresponding to each target vehicle, the position information of the plurality of target road surface elements acquired by each target vehicle includes:

Further, the determining, according to the camera calibration file corresponding to the target vehicle, the multi-frame driving image, and the positioning information corresponding to each frame of driving image, the position information of the plurality of target road surface elements acquired by the target vehicle includes:

Further, the updating the high-precision map according to the plurality of target road surface element position information acquired by each target vehicle includes:

Further, before the driving data corresponding to the plurality of target vehicles are acquired, the method further includes:

receiving driving data sent by each target vehicle;

Further, the target vehicle is a common vehicle provided with a preset camera and a GPS sensor.

The present application also provides a computer program product adapted to perform, when executed on a data processing device, a program code initialized with the method steps of: acquiring driving data corresponding to a plurality of target vehicles, wherein the driving data corresponding to the target vehicles are acquired when the target vehicles pass through a target road section in a target time period, and the driving data corresponding to the target vehicles comprise: the driving route information corresponding to the target vehicle, the driving video corresponding to the target vehicle and the camera calibration file corresponding to the target vehicle; determining a plurality of target pavement element position information acquired and obtained by each target vehicle according to the driving route information, the driving video and the camera calibration file corresponding to each target vehicle, wherein the target pavement element position information is the position information of a target traffic sign board, a target traffic light or a target street light pole in the target road section in a high-precision map; and updating the high-precision map according to the acquired position information of the plurality of target pavement elements of each target vehicle.

It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.

The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

In one typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.

The memory may include volatile memory in a computer-readable medium, random Access Memory (RAM) and/or nonvolatile memory, etc., such as Read Only Memory (ROM) or flash RAM. Memory is an example of a computer-readable medium.

Computer readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of storage media for a computer include, but are not limited to, phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium, which can be used to store information that can be accessed by a computing device. Computer-readable media, as defined herein, does not include transitory computer-readable media (transmission media), such as modulated data signals and carrier waves.

It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article or apparatus that comprises an element.

It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.

The foregoing is merely exemplary of the present application and is not intended to limit the present application. Various modifications and changes may be made to the present application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc. which are within the spirit and principles of the present application are intended to be included within the scope of the claims of the present application.

Claims

1. A method of updating a high-precision map, comprising:

updating the high-precision map according to the position information of a plurality of target pavement elements acquired and obtained by each target vehicle;

determining the position information of a plurality of target pavement elements acquired and obtained by each target vehicle according to the driving route information, the driving video and the camera calibration file corresponding to each target vehicle, wherein the method comprises the following steps:

2. The method according to claim 1, wherein the determining the plurality of target pavement element position information acquired by the target vehicle according to the camera calibration file corresponding to the target vehicle, the multi-frame driving image, and the positioning information corresponding to each frame of the driving image includes:

3. The method according to claim 1, wherein updating the high-precision map based on the plurality of target road surface element position information acquired by each of the target vehicles includes:

4. The method according to claim 1, wherein updating the high-precision map based on the plurality of target road surface element position information acquired by each of the target vehicles includes:

5. The method of claim 1, wherein prior to the acquiring the driving data corresponding to the plurality of target vehicles, the method further comprises:

receiving driving data sent by each target vehicle;

6. The method of any one of claims 1-5, wherein the target vehicle is a regular vehicle equipped with a pre-set camera and GPS sensor.

7. An apparatus for updating a high-precision map, comprising:

The updating unit is used for updating the high-precision map according to the acquired position information of the plurality of target road surface elements of each target vehicle;

the determination unit includes:

8. The apparatus of claim 7, wherein the second determining module comprises:

9. The apparatus of claim 7, wherein the updating unit comprises:

10. The apparatus of claim 7, wherein the updating unit comprises:

11. The apparatus of claim 7, wherein the apparatus further comprises:

12. The apparatus according to any one of claims 7-11, wherein the target vehicle is a regular vehicle equipped with a preset camera and a GPS sensor.

13. A storage medium comprising a stored program, wherein the program, when run, controls a device in which the storage medium is located to perform the method of updating a high-precision map of any one of claims 1 to 6.

14. An apparatus for updating a high-precision map, the apparatus comprising a storage medium; and one or more processors coupled to the storage medium, the processors configured to execute the program instructions stored in the storage medium; the program instructions, when executed, perform the method of updating a high-precision map of any one of claims 1 to 6.