CN114111813A - High-precision map element updating method and device, electronic equipment and storage medium - Google Patents

High-precision map element updating method and device, electronic equipment and storage medium Download PDF

Info

Publication number
CN114111813A
CN114111813A CN202111210659.6A CN202111210659A CN114111813A CN 114111813 A CN114111813 A CN 114111813A CN 202111210659 A CN202111210659 A CN 202111210659A CN 114111813 A CN114111813 A CN 114111813A
Authority
CN
China
Prior art keywords
information
map
scene
description information
determining
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202111210659.6A
Other languages
Chinese (zh)
Inventor
王浩
张瀚天
赵祖轩
周尧
彭亮
白宇
万国伟
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Apollo Intelligent Technology Beijing Co Ltd
Original Assignee
Apollo Intelligent Technology Beijing Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Apollo Intelligent Technology Beijing Co Ltd filed Critical Apollo Intelligent Technology Beijing Co Ltd
Priority to CN202111210659.6A priority Critical patent/CN114111813A/en
Publication of CN114111813A publication Critical patent/CN114111813A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
    • G01C21/28—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network with correlation of data from several navigational instruments
    • G01C21/30—Map- or contour-matching
    • G01C21/32—Structuring or formatting of map data
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/38—Electronic maps specially adapted for navigation; Updating thereof
    • G01C21/3804—Creation or updating of map data

Abstract

The invention provides a high-precision map element updating method and device, electronic equipment and a storage medium, and relates to the technical field of computers, in particular to the technical field of artificial intelligence such as automatic driving and big data processing. The specific implementation scheme is as follows: the method comprises the steps of determining reference attribute information of a map element, acquiring a scene image, analyzing the scene image to obtain scene description information, analyzing the scene description information to obtain element description information corresponding to the map element according to the reference attribute information, determining target space position information of the map element mapped in a scene according to the element description information, and updating the map element according to the target space position information.

Description

High-precision map element updating method and device, electronic equipment and storage medium
Technical Field
The present disclosure relates to the field of computer technologies, and in particular, to the field of artificial intelligence technologies such as autopilot and big data processing, and in particular, to a method and an apparatus for updating high-precision map elements, an electronic device, and a storage medium.
Background
Artificial intelligence is the subject of research that makes computers simulate some human mental processes and intelligent behaviors (such as learning, reasoning, thinking, planning, etc.), both at the hardware level and at the software level. Artificial intelligence hardware technologies generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing, and the like; the artificial intelligence software technology mainly comprises a computer vision technology, a voice recognition technology, a natural language processing technology, a machine learning technology, a deep learning technology, a big data processing technology, a knowledge map technology and the like.
The high-precision map is also called as a high-precision map and is used for an automatic driving automobile. The high-precision map has accurate vehicle position information and abundant road element data information, can help an automobile to predict road surface complex information such as gradient, curvature, course and the like, and can better avoid potential risks. The method for updating map elements in a high-precision map usually depends on high-precision point cloud data, so that the map element updating cost is high, the updating period is long, and the updating efficiency is not high.
Disclosure of Invention
The present disclosure provides a high-precision map element updating method, apparatus, electronic device, storage medium, and computer program product.
According to a first aspect of the present disclosure, there is provided a high-precision map element updating method, including: determining reference attribute information of the map element; acquiring a scene image, and analyzing the scene image to obtain scene description information; analyzing the scene description information to obtain element description information corresponding to the map element according to the reference attribute information; determining target space position information of the map elements mapped in the scene according to the element description information; and updating the map element according to the target space position information.
According to a second aspect of the present disclosure, there is provided a high-precision map element updating apparatus including: a first determination module for determining reference attribute information of a map element; the system comprises an acquisition module, a processing module and a display module, wherein the acquisition module is used for acquiring a scene image and analyzing the scene image to obtain scene description information; the analysis module is used for analyzing the scene description information to obtain element description information corresponding to the map elements according to the reference attribute information; the second determining module is used for determining the target space position information of the map element mapped in the scene according to the element description information; and the updating module is used for updating the map element according to the target space position information.
According to a third aspect of the present disclosure, there is provided an electronic device comprising: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the high-precision map element updating method of the embodiments of the present disclosure.
According to a fourth aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions for causing a computer to execute the high-precision map element updating method of the embodiments of the present disclosure is presented.
According to a fifth aspect of the present disclosure, a computer program product is presented, comprising a computer program which, when executed by a processor, implements the steps of the high precision map element updating method of an embodiment of the present disclosure.
It should be understood that the statements in this section do not necessarily identify key or critical features of the embodiments of the present disclosure, nor do they limit the scope of the present disclosure. Other features of the present disclosure will become apparent from the following description.
Drawings
The drawings are included to provide a better understanding of the present solution and are not to be construed as limiting the present disclosure. Wherein:
FIG. 1 is a schematic diagram according to a first embodiment of the present disclosure;
FIG. 2 is a schematic diagram according to a second embodiment of the present disclosure;
FIG. 3 is a schematic diagram according to a third embodiment of the present disclosure;
FIG. 4 is a schematic diagram according to a fourth embodiment of the present disclosure;
FIG. 5 is a schematic diagram according to a fifth embodiment of the present disclosure;
FIG. 6 is a schematic diagram according to a sixth embodiment of the present disclosure;
fig. 7 shows a schematic block diagram of an example electronic device for implementing the high precision map element update method of an embodiment of the present disclosure.
Detailed Description
Exemplary embodiments of the present disclosure are described below with reference to the accompanying drawings, in which various details of the embodiments of the disclosure are included to assist understanding, and which are to be considered as merely exemplary. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present disclosure. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.
Fig. 1 is a schematic diagram according to a first embodiment of the present disclosure.
It should be noted that the main execution body of the high-precision map element updating method of this embodiment is a high-precision map element updating apparatus, which may be implemented in a software and/or hardware manner, and the apparatus may be configured in an electronic device, and the electronic device may include, but is not limited to, a terminal, a server, and the like.
The embodiment of the disclosure relates to the technical field of computers, in particular to the technical field of artificial intelligence such as automatic driving and big data processing.
Wherein, Artificial Intelligence (Artificial Intelligence), english is abbreviated as AI. The method is a new technical science for researching and developing theories, methods, technologies and application systems for simulating, extending and expanding human intelligence.
The big data processing refers to a process of analyzing and processing large-scale data in an artificial intelligence mode, and the big data can be summarized into 5V, and has large data Volume (Volume), high speed (Velocity), multiple types (Velocity), Value (Value) and authenticity (Veracity).
The autopilot is a technology of sensing the surrounding environment by using various technologies such as radar, laser, ultrasonic, Global Positioning System (GPS), odometer, computer vision and the like, identifying obstacles and various signboards by an advanced calculation and control System, and planning a proper path to control the vehicle to run.
As shown in fig. 1, the high-precision map element updating method includes:
s101: reference attribute information of the map element is determined.
The elements used for describing the map may be referred to as map elements, and the map elements may be, for example, roads, traffic signs, lane lines, speed-limiting boards, and the like, which is not limited thereto.
The map element may have some related attribute information, the attribute information may be referred to as reference attribute information, the reference attribute information may be, for example, a type of the map element, and the type of the map element may be, for example, a road type, a lane line type, a signal lamp type, a speed limit board type, and the like, which is not limited to this.
The determining of the reference attribute information of the map element may be acquiring a high-precision map, then determining types of the map elements corresponding to the plurality of map elements in the high-precision map, and using the types of the map elements as the reference attribute information of the map elements.
For example, when the local graphic element is a speed limit sign, the reference attribute information of the map element may be, for example, a speed limit sign type (e.g., a highest speed limit type, a lowest speed limit type), which is not limited to this.
S102: and acquiring a scene image, and analyzing the scene image to obtain scene description information.
The image used for describing the scene corresponding to the map (and the scene corresponding to the map may be understood as the scene belonging to the geographic location corresponding to the map) may be referred to as a scene image, the number of the scene images may be one or more, the image may be obtained by shooting the scene corresponding to the map from multiple angles or multiple shooting parameters through a camera device such as a mobile phone or a camera, or the image may be obtained by parsing from a video stream, for example, the image may be a partial video frame image including the scene extracted from the video stream, which is not limited thereto.
The scene image may have some related description information, which may be referred to as scene description information, and the scene description information may specifically be, for example, pixel information of the scene image, feature information of the scene image, parameter information of the scene image, and the like, which is not limited thereto.
In the embodiment of the present disclosure, the acquiring of the scene image may be performed by acquiring the scene image corresponding to the map by using an image acquisition device with Real Time Kinematic (RTK) technology to obtain a plurality of scene images, where the plurality of scene images may form an ordered scene image sequence: i ═ Ii}。
The above method can carry corresponding positioning equipment while acquiring the scene image, and based on the solution information given by the RTK, integrate an Inertial Measurement Unit (IMU) and a Global Positioning System (GPS), analyze the scene image to obtain a parameter sequence of an image acquisition device of the RTK: p { (R)i,Ti,Ki) In which R isiAs an image IiRotation matrix of, TiAs an image IiTranslation matrix, KiAs an image IiThe internal reference matrix of (2).
Wherein R is as defined abovei,Ti,KiNamely can be called asThe scene image corresponds to the scene description information, which is not limited in this respect.
It should be noted that, in the embodiments of the present disclosure, the processes of acquiring, processing, and storing the scene image all conform to the regulations of the relevant laws and regulations, and do not violate the customs of the public order.
S103: and analyzing the scene description information to obtain element description information corresponding to the map elements according to the reference attribute information.
After the reference attribute information of the map element is determined, the element description information corresponding to the map element can be obtained by analyzing the scene description information according to the reference attribute information.
The information for describing the map element may be referred to as map description information, and the map element description information may specifically be, for example, location description information of the map element, parameter description information of the map element, semantic description information of the map element, and the like, which is not limited thereto.
In some embodiments, the element description information corresponding to the map element is obtained by parsing from the scene description information according to the reference attribute information, where the scene description information corresponding to the map element is obtained by matching from the scene description information according to the reference attribute information, and is used as the element description information corresponding to the map element, or any other possible manner may be adopted to obtain the description information corresponding to the map element by parsing from the scene description information, for example, a model matching processing manner, a mathematical algorithm manner, an engineering manner, and the like, which is not limited thereto.
S104: and determining the spatial position information of the target mapped in the scene by the map element according to the element description information.
After the element description information corresponding to the map element is obtained by parsing from the scene description information according to the reference attribute information, the spatial position information of the map element mapped in the scene may be determined according to the element description information, where the spatial position information may be referred to as target spatial position information, and the target spatial position information may specifically be, for example, a three-dimensional position coordinate or a multi-dimensional position coordinate of a space, which is not limited to this.
In some embodiments, the target spatial position information of the map element mapped in the scene is determined according to the element description information, which may be determining a coordinate position of the map element in a coordinate system of the map according to the element description information, then mapping the coordinate position of the map element in the coordinate system of the map into a coordinate system of the scene, determining a coordinate position of the map element in the coordinate system of the scene, and using the coordinate position as the target spatial position information.
Alternatively, any other possible method may be adopted to determine the spatial position information of the target mapped in the scene by the map element according to the element description information, for example, a matching algorithm manner, a projection processing manner, and the like, which is not limited in this regard.
S105: and updating the map elements according to the target space position information.
After determining the spatial location information of the target mapped in the scene according to the element description information, the map element may be updated according to the spatial location information of the target.
That is to say, in the embodiments of the present disclosure, the map elements in the high-precision map may be updated according to the target spatial position information, and in some other embodiments, the present disclosure also supports updating the map elements in the element library.
In some application scenarios, when a loaded map is displayed on a device, current location information is usually determined, and then one or more map elements corresponding to the current location information are extracted from an element library and loaded into the map, so as to implement loading and displaying of the map.
In some embodiments, the updating of the map element according to the target spatial position information may be updating the spatial position information of the map element to the target spatial position information when the spatial position information of the map element is inconsistent with the target spatial position information, or directly using the spatial position information of the map element as the target spatial position information when the spatial position information of the map element is consistent with the target spatial position information.
In other embodiments, the map element may be updated according to the target spatial position information, or the map element in the high-precision map may be deleted when the target spatial position information indicates that the position information corresponding to the target spatial position information does not exist in the high-precision map (if the position information corresponding to the target spatial position information does not exist in the high-precision map, it indicates that the map element corresponding to the target spatial position information does not exist in the high-precision map), which is not limited herein.
In the embodiment, reference attribute information of the map element is determined, the scene image is acquired, the scene image is analyzed to obtain scene description information, element description information corresponding to the map element is analyzed from the scene description information according to the reference attribute information, target spatial position information of the map element mapped in the scene is determined according to the element description information, and the map element is updated according to the target spatial position information.
Fig. 2 is a schematic diagram according to a second embodiment of the present disclosure.
As shown in fig. 2, the high-precision map element updating method includes:
s201: reference attribute information of the map element is determined.
S202: and acquiring a scene image, and analyzing the scene image to obtain scene description information.
The descriptions of S201-S202 may specifically participate in the above embodiments, and are not described herein again.
S203: according to the reference attribute information, a plurality of corresponding element images are respectively identified from the plurality of scene images, and the element images are local images corresponding to map elements in the corresponding scene images.
After the reference attribute information of the map element is determined, a plurality of corresponding element images can be respectively identified from a plurality of scenes according to the reference attribute information.
The partial image corresponding to the map element in the scene image may be referred to as an element image.
In the embodiment of the present disclosure, the plurality of corresponding element images are respectively identified from the plurality of scene images according to the reference attribute information, and may be a plurality of partial images corresponding to a plurality of map elements in the scene images are identified by using an image detection algorithm according to the reference attribute information of the map elements, and the plurality of partial images are used as the plurality of element images, which is not limited thereto.
For example, a sequence of scene images may be identified using an image detection algorithm based on reference attribute information of map elements: i ═ IiAnd (4) taking a plurality of speed limit card images obtained by recognition as a plurality of element images.
S204: a plurality of element image information corresponding to the plurality of element images, respectively, is determined.
The plurality of element images may have some related image information, which may be referred to as element image information, and the element image information may specifically be, for example, an index value corresponding to the element image, a description value of the element image, and the like, which is not limited herein.
For example, when the element image is a speed-limit sign image, the plurality of element image information may be, for example, an index value corresponding to the speed-limit sign image, a speed-limit sign speed-limit value, or the like, which is not limited thereto.
The above-described determination of the plurality of elemental image information corresponding to the plurality of elemental images may be performed after the corresponding plurality of elemental images are recognized from the plurality of scene images, respectively, based on the reference attribute information.
That is, after a plurality of speed limit sign images are recognized from a plurality of scene images, and the plurality of speed limit sign images are treated as a plurality of element images,a plurality of element image information sets respectively corresponding to the plurality of speed limit board images can be determined: n { (C)i,j,Li,j) In which C isi,jRepresenting a sequence of images of a scene: i ═ IiIn the ith image, the speed limit board with the index value of j, Li,jAnd the speed limit value of the speed limit card of the ith image is shown.
In the embodiment of the disclosure, when a plurality of element image information sets corresponding to a plurality of speed limit board images are determined: n { (C)i,j,Li,j) After that, the element image information set N may be clustered to obtain a corresponding clustering result: mi＝{Mi,jIn which M isi,jAnd e.g. N, wherein i is the index of the clustering result, and j is the index value of the speed limit board belonging to the clustering center.
S205: and analyzing the corresponding scene description information according to the element image information to obtain the corresponding element description information.
Optionally, in some embodiments, the corresponding element description information is obtained by parsing from the corresponding scene description information according to the element image information, or the corresponding element description information is obtained by determining the element position of the corresponding map element in the scene image according to the element image information, and then the corresponding element description information is obtained by parsing from the corresponding scene description information according to the element position, so as to realize that the element position in the scene image is firstly identified, and then the corresponding element description information is obtained by parsing from the scene description information according to the element position, because the element position can be used for expressing the spatial position condition of the element in the real scene corresponding to the map element (if the map element is assumed to be a speed limit board, the element in the real scene is the speed limit board body in the real scene), when the element description information is resolved based on the spatial position condition, the analysis method is more targeted, noise interference caused by similar or similar interference elements in a scene is avoided, the consumption of computing resources required by denoising is reduced, the analysis efficiency of the element description information is improved, the accuracy of the analysis of the element description information is guaranteed, and the element description information can more accurately express the characteristics of corresponding map elements.
The position of the map element corresponding to the scene image may be referred to as an element position, and the element position may specifically be, for example, a position coordinate of the element, which is not limited to this.
In the embodiment of the disclosure, when a plurality of element image information sets corresponding to a plurality of speed limit board images are determined: n { (C)i,j,Li,j) After that, the element image information set N may be clustered to obtain a corresponding clustering result: mi＝{Mi,jAnd the clustering result is: mi＝{Mi,jCorresponding as map elements to element positions in the scene image.
Wherein M isi,jAnd e.g. N, wherein i is the index of the clustering result, and j is the index value of the speed limit board belonging to the clustering center.
At the element-obtaining position Mi＝{Mi,jAnd after the element description information is analyzed, the corresponding element description information can be obtained from the corresponding scene description information according to the element position.
In the embodiment of the disclosure, the element position M is obtainedi＝{Mi,jAfter, from the scene description information P { (R), it is possible to determine the position of the element from the scene description information P { (R)i,Ti,Ki) In the method, corresponding element description information is obtained through analysis, namely for any Mi,je.M, corresponding (R, T, K) exists in the scene description information, and the (R, T, K) is the element description information.
Alternatively, any other possible manner may also be adopted, and according to the element image information, corresponding element description information is obtained by parsing from the corresponding scene description information, for example, a model parsing manner, a matching algorithm manner, and the like, which is not limited herein.
In the embodiment of the disclosure, because the corresponding multiple element images are respectively identified from the multiple scene images according to the reference attribute information, the multiple element image information respectively corresponding to the multiple element images is determined, and the corresponding element description information is obtained by analyzing from the corresponding scene description information according to the element image information, the identification of the element image information in the scene images can be realized first, and then the corresponding element description information is obtained by analyzing from the scene description information based on the element image information, because the element image information can be used for describing the element in the real scene corresponding to the map element (the map element is assumed to be the speed limit sign, the element in the real scene is the speed limit sign body in the real scene), when the analysis of the element description information is assisted based on the element image information, the analysis method can be more targeted, the representation capability of the element description information is effectively improved based on the element image information, the accuracy of the analysis of the element description information is effectively guaranteed, and therefore the execution of a subsequent map element method can be effectively assisted based on the element description information.
S206: and generating external reference description information corresponding to the map elements according to the element description information.
Among them, information for describing an external reference corresponding to a map element may be referred to as external reference description information.
In the embodiment of the present disclosure, the external reference description information corresponding to the map element is generated according to the element description information, which may be an element position M corresponding to the map element is generated according to the element description informationi,jCorresponding external reference (R)k，Tk，Kk) And will be (R)k，Tk，Kk) As external reference description information.
S207: and determining initial spatial position information of the map element mapped in the scene according to the external reference description information.
The information describing the spatial position may be referred to as spatial position information, and the spatial position information may specifically be, for example, a spatial coordinate, which is not limited to this.
After generating the external reference description information corresponding to the map element according to the element description information, the spatial position information of the map element mapped in the scene may be determined according to the external reference description information, where the spatial position information may be referred to as initial spatial position information, and the initial spatial position information may specifically be, for example, a three-dimensional spatial position coordinate, which is not limited to this.
In the embodiment of the present disclosure, the above-mentioned generation corresponds to the map elementExternal reference description information (R)k，Tk，Kk) Then, the three-dimensional space position information H of the map elements mapped in the scene can be solved by using an overdetermined linear equation and combining a multi-view geometric technologyiAnd the three-dimensional space position information H is obtainediAs initial spatial location information.
S208: and determining target spatial position information from the plurality of initial spatial position information according to the external reference description information and the element position.
After the initial spatial position information is determined, corresponding spatial position information can be determined from the plurality of initial spatial position information according to the external reference description information combined with the element position, the spatial position information can be called as target spatial position information, and the target spatial position information is determined from the plurality of initial spatial position information according to the external reference description information combined with the element position, so that when the target spatial position information is determined in an auxiliary manner based on the external reference description information, interference caused by information difference to the determination of the target spatial position information can be avoided, the accuracy of the target spatial position information can be effectively guaranteed, and meanwhile, the reasonability of the target spatial position information determination process can be effectively improved.
In some embodiments, the target spatial position information is determined from the multiple pieces of initial spatial position information according to the external reference description information in combination with the element position, or the multiple pieces of initial spatial position information may be subjected to a filtering process according to the external reference description information in combination with the element position, that is, spatial position information meeting a preset condition is selected from the multiple pieces of initial spatial position information, and the spatial position information is used as the target spatial position information, which is not limited herein.
Alternatively, any other possible manner may be adopted, and the target spatial position information is determined from the multiple initial spatial position information according to the external description information and the element position, for example, a model prediction manner, a feature matching manner, and the like, which is not limited herein.
S209: and updating the map elements according to the target space position information.
For the description of S209, reference may be made to the above embodiments specifically, and details are not repeated here.
In the embodiment, reference attribute information of a map element is determined, a scene image is acquired, the scene image is analyzed to obtain scene description information, a plurality of corresponding element images are respectively identified from the plurality of scene images according to the reference attribute information, a plurality of element image information respectively corresponding to the element images is determined, the corresponding element description information is analyzed from the corresponding scene description information according to the element image information, when the element description information is analyzed in an auxiliary manner based on the element image information, the analyzing method can be more targeted, the representation capability of the element description information is effectively improved based on the element image information, the accuracy of analyzing the element description information is effectively guaranteed, and the execution of a subsequent map element method can be effectively assisted based on the element description information, according to the element description information, generating external reference description information corresponding to the map elements, determining target space position information from a plurality of initial space position information according to the external reference description information and combining element positions, and updating the map elements according to the target space position information, so that when the target space position information is determined in an auxiliary mode based on the external reference description information, interference caused by information difference to the determination of the target space position information can be avoided, the accuracy of the target space position information can be effectively guaranteed, meanwhile, the rationality of the determination process of the target space position information is effectively improved, and the updating effect of the map elements is effectively improved.
Fig. 3 is a schematic diagram according to a fourth embodiment of the present disclosure.
As shown in fig. 3, the high-precision map element updating method includes:
s301: reference attribute information of the map element is determined.
S302: and acquiring a scene image, and analyzing the scene image to obtain scene description information.
S303: and analyzing the scene description information to obtain element description information corresponding to the map elements according to the reference attribute information.
S304: and determining initial spatial position information of the map element mapped in the scene according to the external reference description information.
For the description of S301 to S304, reference may be made to the above embodiments, which are not described herein again.
S305: and determining a plurality of position loss values respectively corresponding to the plurality of initial spatial position information according to the external reference description information and the element position.
The loss values corresponding to the plurality of initial spatial position information may be referred to as position loss values, and the position loss values may be used to assist in optimizing the initial spatial position information.
Optionally, in some embodiments, a plurality of position loss values respectively corresponding to a plurality of initial spatial position information are determined according to the external reference description information in combination with the element position, where the external reference description information, the element position, and the initial spatial position information are input into the target adjustment model to obtain a position loss value output by the target adjustment model and corresponding to the initial spatial position information.
The initial adjustment model is trained in advance according to sample external reference description information related to sample map elements, sample element positions and labeling space position information until the adjustment model converges, and the adjustment model obtained through training is used as a target adjustment model.
The adjustment model obtained at the initial stage of training may be referred to as an initial adjustment model, and the initial adjustment model may be an artificial intelligence model, specifically, for example, a neural network model or a machine learning model, or of course, any other possible artificial intelligence model capable of executing an adjustment task may be adopted, which is not limited thereto.
In other embodiments, the corresponding losses may be preconfigured for the target adjustment modelLoss function:
Figure BDA0003308824050000121
then, the extrinsic description information, the element position, and the initial spatial position information are used as input parameters of the loss function to obtain a loss value output by the loss function, and the loss value is used as a plurality of position loss values corresponding to the plurality of initial spatial position information, which is not limited herein.
S306: a target position loss value with the smallest value is determined from the plurality of position loss values.
After determining the plurality of position loss values corresponding to the plurality of pieces of initial spatial position information, the loss value having the smallest value among the plurality of position loss values may be determined, and the loss value may be referred to as a target position loss value.
S307: and taking the initial space position information corresponding to the target position loss value as target space position information.
Among the plurality of initial spatial position information, the initial spatial position information corresponding to the target position loss value may be referred to as target spatial position information.
After the target position loss value with the minimum value is determined from the plurality of position loss values, the initial spatial position information corresponding to the target position loss value can be determined, and the initial spatial position information is used as the target spatial position information, because the initial spatial position information with the minimum loss value is determined from the initial spatial position information and is used as the target spatial position information, the optimization of the initial spatial position information based on the position loss value can be realized, so that more accurate target spatial position information can be obtained, and because the data volume of the target spatial position information is smaller than that of the initial spatial position information, the consumption of computing resources can be reduced to a certain extent, and the updating efficiency of map elements can be effectively improved in an auxiliary mode.
S308: determining a plurality of correlation values between the reference attribute information and a plurality of candidate attribute information in an element library respectively, wherein the element library comprises: a plurality of candidate attribute information, and an existing map element corresponding to a portion of the candidate attribute information.
The map elements in the non-updated high-precision map may be referred to as existing map elements, and a plurality of existing map elements may form an element library.
The existing map elements may have some related attribute information, and the attribute information may be referred to as candidate attribute information.
Taking the map element as a speed limit sign as an example, the existing map element position in the element library may be represented as G ═ GiThe candidate attribute information may be expressed as W ═ WiAnd (c) this is not limiting.
Among them, the value for describing the correlation between the reference attribute information and the plurality of candidate attribute information in the element library, respectively, may be referred to as a correlation value.
In the embodiment of the present disclosure, determining a plurality of correlation values between the reference attribute information and a plurality of candidate attribute information in the element library may be performed on the candidate attribute information W ═ { W ═ WiCarry out clustering processing to obtain a clustering result Wi＝{Wi,jAnd for reference attribute information L ═ LiCarry out clustering processing to obtain a clustering result Li＝{Li,j}。
The clustering result L is obtainedi＝{Li,jW andi＝{Wi,jafter that, for any Li,jE.g. L, and Wi,jBelongs to W, if satisfy Li,j-Wi,j||2D is less than or equal to d (wherein d is a preset distance threshold), then LiAnd WiBy adding one, a plurality of correlation values between the reference attribute information and a plurality of candidate attribute information in the library of elements can be determined.
S309: and determining candidate attribute information corresponding to the maximum correlation value in the plurality of correlation values.
After determining a plurality of correlation values between the reference attribute information and a plurality of candidate attribute information in the element library, the candidate attribute information W corresponding to the maximum correlation value among the plurality of correlation values may be determinedi。
S310: and matching the map elements with the existing map elements in the element library according to the corresponding candidate attribute information and the target spatial position information to obtain a matching result.
S311: and updating the map elements according to the matching result.
In the embodiment of the disclosure, the map element is matched with the existing map element in the element library according to the candidate attribute information and the target spatial position information, and then the map element is updated according to the matching result, the candidate attribute information can be used for describing the element related attribute (if the map element is assumed to be a speed limit board, the element attribute in the real scene is the speed limit board type of the speed limit board) in the real scene corresponding to the map element, the target position information can be used for expressing the spatial position condition of the element (if the map element is assumed to be a speed limit board, the element in the real scene is the speed limit board body in the real scene) in the real scene corresponding to the map element, so that when the map element is updated based on the matching result, the map element can be updated in all directions based on two dimensions of the position information and the attribute information, therefore, the comprehensiveness and the accuracy of the map element updating are effectively improved.
Optionally, in some embodiments, as shown in fig. 4, fig. 4 is a schematic diagram according to a fourth embodiment of the present disclosure, and updating the map element according to the matching result includes:
s401: and if the existing map elements corresponding to the corresponding candidate attribute information do not exist in the element library, marking the map elements as new map elements.
Map elements that do not exist in the element library may be referred to as new map elements.
In the embodiment of the present disclosure, the candidate attribute information W may be obtainediSearching in the element library, if the existing map elements corresponding to the corresponding candidate attribute information do not exist in the element library, namely
Figure BDA0003308824050000141
The corresponding candidate attribute may be signaledInformation-dependent reference attribute information LiThe corresponding map element is marked as a new map element.
S402: and if the existing map elements corresponding to the corresponding candidate attribute information exist in the element library, and the Euclidean distance between the reference space position information of the corresponding existing map elements and the target space position information meets the set condition, marking the map elements as the existing map elements.
The spatial position information of the existing map element may be referred to as reference spatial position information.
In the embodiment of the present disclosure, if there is an existing map element corresponding to the corresponding candidate attribute information in the element library, that is, WiIf the map element is not an empty set and the euclidean distance between the reference spatial position information of the corresponding existing map element and the target spatial position information satisfies a set condition (wherein the set condition can be configured adaptively according to the actual service scene, and is not limited to this), the map element can be marked as the existing map element.
That is, in the candidate attribute information WiThe map element is not an empty set, existing map elements with the same attribute as the corresponding candidate attribute information exist in the element library, and when the Euclidean distance between the reference space position information of the corresponding existing map elements and the target space position information meets the set condition, the map elements can be marked as the existing map elements.
S403: and if the existing map elements corresponding to the corresponding candidate attribute information do not exist in the element library, and the Euclidean distance between any existing map element in the element library and the map element does not meet the set condition, marking the map element as a deleted map element.
Among them, a map element that needs to be deleted and updated among a plurality of map elements may be referred to as a deleted map element.
In the embodiment of the present disclosure, if there is no existing map element corresponding to the corresponding candidate attribute information in the element library, that is, WiIs not an empty set, and the Euclidean distance between the reference space position information of the corresponding existing map element and the target space position information does not meet the setAnd if the condition is determined (wherein the set condition can be configured adaptively according to the actual service scene, and is not limited to this), the map element can be marked as a deleted map element.
That is, in the candidate attribute information WiThe map element is not an empty set, and the existing map element with the same attribute as the corresponding candidate attribute information exists in the element library, but when the Euclidean distance between the reference space position information of the corresponding existing map element and the target space position information does not meet the set condition, the map element can be marked as a deleted map element.
In summary, in the embodiment of the present disclosure, when the reference attribute information respectively has a correlation with the candidate attribute information in the element library, the map element is updated according to the matching result between the map element and the existing map element in the element library, so that the change condition of the map element in the element library can be accurately and quickly found, the update of the map element can be efficiently realized based on the change condition of the map element, the freshness of the high-precision map is effectively improved, and the safety of vehicle driving in an actual driving scene can be effectively ensured.
S404: and if the reference attribute information is determined not to have correlation with the candidate attribute information in the element library respectively, marking the map element as a deleted map element.
In the embodiment of the present disclosure, if the reference attribute information L is determinediRespectively associated with a plurality of candidate attribute information W in the element libraryiThere is no correlation between them, then the element library can be associated with multiple candidate attribute information WiThe corresponding map element is marked as a deleted map element, which is not limited.
Therefore, in the embodiment, because the map elements are updated according to the matching results between the map elements and the existing map elements in the element library when the reference attribute information respectively has correlation with the candidate attribute information in the element library, the change conditions of the map elements in the element library can be accurately and quickly found, the update of the map elements can be efficiently realized based on the change conditions of the map elements, the freshness of the high-precision map can be effectively improved, the safety of vehicle driving in an actual driving scene can be effectively guaranteed, because the map elements are directly marked as the map elements to be deleted when the reference attribute information respectively has no correlation with the candidate attribute information in the element library, the deletion update processing of the map elements can be directly realized based on the attribute dimensions of the map elements, therefore, the updating processing logic of the map elements can be effectively simplified, the waste of computing resources is effectively avoided, and the updating efficiency of the map elements is effectively improved while the updating effect of the map elements is effectively ensured.
In this embodiment, by determining reference attribute information of a map element, acquiring a plurality of scene images corresponding to scene description information, parsing the scene description information to obtain element description information corresponding to the map element according to the reference attribute information, determining initial spatial position information of the map element mapped in the scene according to the external description information, determining a plurality of position loss values corresponding to the plurality of initial spatial position information, respectively, according to the external description information in combination with element positions, determining initial spatial position information corresponding to a target position loss value, and using the initial spatial position information as the target spatial position information, since the initial spatial position information with the smallest loss value is determined from the initial spatial position information and is used as the target spatial position information, optimization of the initial spatial position information based on the position loss value can be achieved, the map element updating method comprises the steps of obtaining more accurate target space position information, wherein the data volume of the target space position information is smaller than that of initial space position information, so that the consumption of operation resources can be reduced to a certain extent, and the map element updating efficiency can be effectively improved in an auxiliary mode.
Fig. 5 is a schematic diagram according to a fifth embodiment of the present disclosure.
As shown in fig. 5, the high-precision map element updating apparatus 50 includes:
a first determining module 501, configured to determine reference attribute information of a map element;
an obtaining module 502, configured to obtain a scene image, and analyze the scene image to obtain scene description information;
the analyzing module 503 is configured to analyze the scene description information to obtain element description information corresponding to the map element according to the reference attribute information;
a second determining module 504, configured to determine, according to the element description information, spatial location information of a target of the map element mapped in the scene; and
and an updating module 505, configured to update the map element according to the target spatial location information.
In some embodiments of the present disclosure, as shown in fig. 6, fig. 6 is a schematic diagram according to a sixth embodiment of the present disclosure, and the high-precision map element updating apparatus 60 includes: the device comprises a first determining module 601, an obtaining module 602, an analyzing module 603, a second determining module 604 and an updating module 605, wherein the analyzing module 603 comprises:
an identifying sub-module 6031, configured to identify, according to the reference attribute information, a plurality of corresponding element images from the plurality of scene images, where an element image is a local image corresponding to a map element in a corresponding scene image;
a first determination sub-module 6032 for determining a plurality of elemental image information corresponding to the plurality of elemental images, respectively;
and the parsing sub-module 6033 is configured to parse the corresponding scene description information according to the element image information to obtain corresponding element description information.
In some embodiments of the present disclosure, the parsing sub-module 6033 is specifically configured to:
determining, from the element image information, a respective map element corresponding to an element position in the scene image;
and analyzing the corresponding scene description information according to the element position to obtain the corresponding element description information.
In some embodiments of the present disclosure, the second determining module 604 includes:
a generation submodule 6041 configured to generate, according to the element description information, external reference description information corresponding to the map element;
a second determining submodule 6042, configured to determine, according to the external reference description information, initial spatial position information of the map element mapped in the scene; and
and a third determining sub-module 6043, configured to determine, according to the external reference description information and the element position, target spatial position information from the multiple pieces of initial spatial position information.
In some embodiments of the present disclosure, among others, the third determining submodule 6043 includes:
a first determining unit 60431, configured to determine, according to the external reference description information in combination with the element position, a plurality of position loss values corresponding to the plurality of initial spatial position information, respectively;
a second determination unit 60432 configured to determine a target position loss value having a minimum value from among the plurality of position loss values;
a processing unit 60433, configured to use the initial spatial position information corresponding to the target position loss value as the target spatial position information.
In some embodiments of the present disclosure, the first determining unit 60431 is specifically configured to:
inputting the external reference description information, the element position and the initial spatial position information into a target adjustment model to obtain a position loss value which is output by the target adjustment model and corresponds to the initial spatial position information;
the initial adjustment model is trained in advance according to sample external reference description information related to sample map elements, sample element positions and labeling space position information until the adjustment model converges, and the adjustment model obtained through training is used as a target adjustment model.
In some embodiments of the present disclosure, among others, the update module 605 includes:
a fourth determining sub-module 6051, configured to determine a plurality of correlation values between the reference attribute information and a plurality of candidate attribute information in an element library, where the element library includes: a plurality of candidate attribute information, and existing map elements corresponding to part of the candidate attribute information;
a fifth determining submodule 6052 configured to determine candidate attribute information corresponding to a largest correlation value among the plurality of correlation values;
a matching sub-module 6053, configured to match, according to the corresponding candidate attribute information and the target spatial position information, the map element with an existing map element in the element library to obtain a matching result;
and an update sub-module 6054 configured to update the map element according to the matching result.
In some embodiments of the present disclosure, the existing map element has corresponding reference spatial location information, where the update sub-module 6054 is specifically configured to:
if the existing map elements corresponding to the corresponding candidate attribute information do not exist in the element library, marking the map elements as newly added map elements;
if existing map elements corresponding to the corresponding candidate attribute information exist in the element library, and the Euclidean distance between the reference space position information of the corresponding existing map elements and the target space position information meets the set condition, the map elements are marked as the existing map elements;
and if the existing map elements corresponding to the corresponding candidate attribute information do not exist in the element library, and the Euclidean distance between any existing map element in the element library and the map element does not meet the set condition, marking the map element as a deleted map element.
In some embodiments of the present disclosure, among others, the update sub-module 6054 is specifically configured to:
and if the reference attribute information is determined not to have correlation with the candidate attribute information in the element library respectively, marking the map element as a deleted map element.
It is understood that the high-precision map element updating apparatus 60 in fig. 6 of the present embodiment and the high-precision map element updating apparatus 50 in the foregoing embodiment, the first determining module 601 and the first determining module 501 in the foregoing embodiment, the obtaining module 602 and the obtaining module 502 in the foregoing embodiment, the parsing module 603 and the parsing module 503 in the foregoing embodiment, the second determining module 604 and the second determining module 504 in the foregoing embodiment, and the updating module 605 and the updating module 505 in the foregoing embodiment may have the same functions and structures.
It should be noted that the above explanation of the high-precision map element updating method is also applicable to the high-precision map element updating apparatus of the present embodiment, and is not repeated herein.
In the embodiment, reference attribute information of a map element is determined, a scene image is acquired, the scene image is analyzed to obtain scene description information, element description information corresponding to the map element is analyzed from the scene description information according to the reference attribute information, target space position information of the map element mapped in a scene is determined according to the element description information, and the map element is updated according to the target space position information, so that the update cost of the high-precision map element can be effectively reduced, the update efficiency of the map element can be effectively improved, the map freshness can be effectively guaranteed, and the updated map element can effectively meet the requirement of a driving scene with higher real-time performance.
The present disclosure also provides an electronic device, a readable storage medium, and a computer program product according to embodiments of the present disclosure.
FIG. 7 shows a schematic block diagram of an example electronic device to implement the high precision map element update method of embodiments of the present disclosure. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be examples only, and are not meant to limit implementations of the disclosure described and/or claimed herein.
As shown in fig. 7, the device 700 comprises a computing unit 701, which may perform various suitable actions and processes according to a computer program stored in a Read Only Memory (ROM)702 or a computer program loaded from a storage unit 708 into a Random Access Memory (RAM) 703. In the RAM 703, various programs and data required for the operation of the device 700 can also be stored. The computing unit 701, the ROM 702, and the RAM 703 are connected to each other by a bus 704. An input/output (I/O) interface 705 is also connected to bus 704.
Various components in the device 700 are connected to the I/O interface 705, including: an input unit 706 such as a keyboard, a mouse, or the like; an output unit 707 such as various types of displays, speakers, and the like; a storage unit 708 such as a magnetic disk, optical disk, or the like; and a communication unit 709 such as a network card, modem, wireless communication transceiver, etc. The communication unit 709 allows the device 700 to exchange information/data with other devices via a computer network, such as the internet, and/or various telecommunication networks.
Computing unit 701 may be a variety of general purpose and/or special purpose processing components with processing and computing capabilities. Some examples of the computing unit 701 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various computing units running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, and so forth. The calculation unit 701 executes the respective methods and processes described above, such as the high-precision map element update method. For example, in some embodiments, the high precision map element update method may be implemented as a computer software program tangibly embodied in a machine-readable medium, such as storage unit 708. In some embodiments, part or all of a computer program may be loaded onto and/or installed onto device 700 via ROM 702 and/or communications unit 709. When the computer program is loaded into the RAM 703 and executed by the computing unit 701, one or more steps of the high-precision map element updating method described above may be performed. Alternatively, in other embodiments, the computing unit 701 may be configured to perform the high-precision map element update method by any other suitable means (e.g., by means of firmware).
Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuitry, Field Programmable Gate Arrays (FPGAs), Application Specific Integrated Circuits (ASICs), Application Specific Standard Products (ASSPs), system on a chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs that are executable and/or interpretable on a programmable system including at least one programmable processor, which may be special or general purpose, receiving data and instructions from, and transmitting data and instructions to, a storage system, at least one input device, and at least one output device.
Program code for implementing the methods of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the program codes, when executed by the processor or controller, cause the functions/operations specified in the flowchart and/or block diagram to be performed. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine or entirely on the remote machine or server.
In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which a user can provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic, speech, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a back-end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back-end, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), Wide Area Networks (WANs), the internet, and blockchain networks.
The computer system may include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The Server can be a cloud Server, also called a cloud computing Server or a cloud host, and is a host product in a cloud computing service system, so as to solve the defects of high management difficulty and weak service expansibility in the traditional physical host and VPS service ("Virtual Private Server", or simply "VPS"). The server may also be a server of a distributed system, or a server incorporating a blockchain.
It should be understood that various forms of the flows shown above may be used, with steps reordered, added, or deleted. For example, the steps described in the present disclosure may be executed in parallel, sequentially, or in different orders, as long as the desired results of the technical solutions disclosed in the present disclosure can be achieved, and the present disclosure is not limited herein.
The above detailed description should not be construed as limiting the scope of the disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may be made in accordance with design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present disclosure should be included in the scope of protection of the present disclosure.

Claims (21)

1. A high-precision map element updating method comprises the following steps:
determining reference attribute information of the map element;
acquiring a scene image, and analyzing the scene image to obtain scene description information;
analyzing the scene description information to obtain element description information corresponding to the map element according to the reference attribute information;
determining target space position information of the map elements mapped in the scene according to the element description information; and
and updating the map element according to the target space position information.
2. The method of claim 1, wherein the parsing element description information corresponding to the map element from the scene description information according to the reference attribute information comprises:
according to the reference attribute information, respectively identifying a plurality of corresponding element images from the plurality of scene images, wherein the element images are local images corresponding to the map elements in the corresponding scene images;
determining a plurality of element image information respectively corresponding to the plurality of element images;
and analyzing the corresponding element description information from the corresponding scene description information according to the element image information.
3. The method of claim 2, wherein the parsing the corresponding element description information from the corresponding scene description information according to the element image information comprises:
determining, from the element image information, that the respective map element corresponds to an element position in the scene image;
and analyzing the corresponding element description information from the corresponding scene description information according to the element position.
4. The method of claim 3, wherein the determining, from the element description information, spatial location information of objects mapped by the map element in a scene comprises:
generating external reference description information corresponding to the map elements according to the element description information;
determining initial spatial position information of the map element mapped in the scene according to the external reference description information; and
and determining target spatial position information from the plurality of initial spatial position information according to the external reference description information and the element position.
5. The method of claim 4, wherein determining target spatial location information from the plurality of initial spatial location information in accordance with the extrinsic description information in combination with the element location comprises:
determining a plurality of position loss values respectively corresponding to the plurality of initial spatial position information according to the external reference description information and the element position;
determining a target position loss value with the minimum value from the plurality of position loss values;
and taking the initial spatial position information corresponding to the target position loss value as the target spatial position information.
6. The method of claim 5, wherein said determining a plurality of position loss values corresponding to said plurality of said initial spatial position information, respectively, in accordance with said extrinsic description information in combination with said element position comprises:
inputting the external description information, the element positions and the initial spatial position information into a target adjustment model to obtain a position loss value which is output by the target adjustment model and corresponds to the initial spatial position information;
the initial adjustment model is trained in advance according to sample external reference description information, sample element positions and labeling space position information related to sample map elements until the adjustment model converges, and the adjustment model obtained through training is used as the target adjustment model.
7. The method of claim 1, wherein said updating the map element in accordance with the target spatial location information comprises:
determining a plurality of correlation values between the reference attribute information and a plurality of candidate attribute information in an element library respectively, wherein the element library comprises: a plurality of candidate attribute information, and existing map elements corresponding to a portion of the candidate attribute information;
determining candidate attribute information corresponding to the correlation value with the maximum value among the plurality of correlation values;
matching the map elements with the existing map elements in the element library according to the corresponding candidate attribute information and the target space position information to obtain a matching result;
and updating the map elements according to the matching result.
8. The method of claim 7, the existing map element having corresponding reference spatial location information, wherein the updating the map element according to the matching result comprises:
if the existing map elements corresponding to the corresponding candidate attribute information do not exist in the element library, marking the map elements as newly added map elements;
if existing map elements corresponding to the corresponding candidate attribute information exist in the element library, and the Euclidean distance between the reference space position information of the corresponding existing map elements and the target space position information meets a set condition, marking the map elements as the existing map elements;
and if the existing map elements corresponding to the corresponding candidate attribute information do not exist in the element library, and the Euclidean distance between any existing map element in the element library and the map element does not meet the set condition, marking the map element as a deleted map element.
9. The method of claim 7, further comprising:
and if the reference attribute information is determined not to have correlation with the candidate attribute information in the element library respectively, marking the map element as a deleted map element.
10. A high-precision map element updating apparatus comprising:
a first determination module for determining reference attribute information of a map element;
the system comprises an acquisition module, a processing module and a display module, wherein the acquisition module is used for acquiring a scene image and analyzing the scene image to obtain scene description information;
the analysis module is used for analyzing the scene description information to obtain element description information corresponding to the map elements according to the reference attribute information;
the second determining module is used for determining the target space position information of the map element mapped in the scene according to the element description information; and
and the updating module is used for updating the map element according to the target space position information.
11. The apparatus of claim 10, wherein the parsing module comprises:
the identification submodule is used for respectively identifying a plurality of corresponding element images from the plurality of scene images according to the reference attribute information, wherein the element images are local images corresponding to the map elements in the corresponding scene images;
a first determination sub-module configured to determine a plurality of elemental image information respectively corresponding to the plurality of elemental images;
and the analysis submodule is used for analyzing the corresponding element description information from the corresponding scene description information according to the element image information.
12. The apparatus according to claim 11, wherein the parsing submodule is specifically configured to:
determining, from the element image information, that the respective map element corresponds to an element position in the scene image;
and analyzing the corresponding element description information from the corresponding scene description information according to the element position.
13. The apparatus of claim 12, wherein the second determining means comprises:
the generation submodule is used for generating external reference description information corresponding to the map elements according to the element description information;
the second determining submodule is used for determining initial spatial position information of the map elements mapped in the scene according to the external reference description information; and
and the third determining submodule is used for determining target spatial position information from the plurality of initial spatial position information according to the external reference description information and the element position.
14. The apparatus of claim 13, wherein the third determination submodule comprises:
a first determining unit, configured to determine, according to the external reference description information and in combination with the element position, a plurality of position loss values respectively corresponding to the plurality of pieces of initial spatial position information;
a second determination unit configured to determine a target position loss value having a minimum value from the plurality of position loss values;
and the processing unit is used for taking the initial spatial position information corresponding to the target position loss value as the target spatial position information.
15. The apparatus according to claim 14, wherein the first determining unit is specifically configured to:
inputting the external description information, the element positions and the initial spatial position information into a target adjustment model to obtain a position loss value which is output by the target adjustment model and corresponds to the initial spatial position information;
the initial adjustment model is trained in advance according to sample external reference description information, sample element positions and labeling space position information related to sample map elements until the adjustment model converges, and the adjustment model obtained through training is used as the target adjustment model.
16. The apparatus of claim 10, wherein the update module comprises:
a fourth determining sub-module, configured to determine a plurality of correlation values between the reference attribute information and a plurality of candidate attribute information in an element library, where the element library includes: a plurality of candidate attribute information, and existing map elements corresponding to a portion of the candidate attribute information;
a fifth determining submodule, configured to determine candidate attribute information corresponding to a maximum correlation value among the plurality of correlation values;
a matching sub-module, configured to match the map element with the existing map elements in the element library according to the corresponding candidate attribute information and the target spatial location information, so as to obtain a matching result;
and the updating submodule is used for updating the map elements according to the matching result.
17. The apparatus of claim 16, wherein the existing map element has corresponding reference spatial location information, and wherein the update sub-module is specifically configured to:
if the existing map elements corresponding to the corresponding candidate attribute information do not exist in the element library, marking the map elements as newly added map elements;
if existing map elements corresponding to the corresponding candidate attribute information exist in the element library, and the Euclidean distance between the reference space position information of the corresponding existing map elements and the target space position information meets a set condition, marking the map elements as the existing map elements;
and if the existing map elements corresponding to the corresponding candidate attribute information do not exist in the element library, and the Euclidean distance between any existing map element in the element library and the map element does not meet the set condition, marking the map element as a deleted map element.
18. The apparatus according to claim 16, wherein the update submodule is specifically configured to:
and if the reference attribute information is determined not to have correlation with the candidate attribute information in the element library respectively, marking the map element as a deleted map element.
19. An electronic device, comprising:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-9.
20. A non-transitory computer readable storage medium having stored thereon computer instructions for causing the computer to perform the method of any one of claims 1-9.
21. A computer program product comprising a computer program which, when being executed by a processor, carries out the steps of the method according to any one of claims 1-9.
CN202111210659.6A 2021-10-18 2021-10-18 High-precision map element updating method and device, electronic equipment and storage medium Pending CN114111813A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202111210659.6A CN114111813A (en) 2021-10-18 2021-10-18 High-precision map element updating method and device, electronic equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202111210659.6A CN114111813A (en) 2021-10-18 2021-10-18 High-precision map element updating method and device, electronic equipment and storage medium

Publications (1)

Publication Number Publication Date
CN114111813A true CN114111813A (en) 2022-03-01

Family

ID=80376256

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202111210659.6A Pending CN114111813A (en) 2021-10-18 2021-10-18 High-precision map element updating method and device, electronic equipment and storage medium

Country Status (1)

Country Link
CN (1) CN114111813A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114581667A (en) * 2022-03-04 2022-06-03 北京百度网讯科技有限公司 Map data processing method and device, electronic equipment and storage medium

Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108318043A (en) * 2017-12-29 2018-07-24 百度在线网络技术（北京）有限公司 Method, apparatus for updating electronic map and computer readable storage medium
EP3594902A1 (en) * 2018-07-09 2020-01-15 Autonomous Intelligent Driving GmbH Method for estimating a relative position of an object in the surroundings of a vehicle and electronic control unit for a vehicle and vehicle
CN111256687A (en) * 2018-11-30 2020-06-09 广东星舆科技有限公司 Map data processing method and device, acquisition equipment and storage medium
CN111784798A (en) * 2020-06-30 2020-10-16 滴图(北京)科技有限公司 Map generation method and device, electronic equipment and storage medium
WO2020224305A1 (en) * 2019-05-07 2020-11-12 北京市商汤科技开发有限公司 Method and apparatus for device positioning, and device
CN111982133A (en) * 2019-05-23 2020-11-24 北京地平线机器人技术研发有限公司 Method and device for positioning vehicle based on high-precision map and electronic equipment
CN112050806A (en) * 2019-06-06 2020-12-08 北京初速度科技有限公司 Positioning method and device for moving vehicle
CN112069856A (en) * 2019-06-10 2020-12-11 商汤集团有限公司 Map generation method, driving control method, device, electronic equipment and system
CN112785655A (en) * 2021-01-28 2021-05-11 中汽创智科技有限公司 Method, device and equipment for automatically calibrating external parameters of all-round camera based on lane line detection and computer storage medium
WO2021149254A1 (en) * 2020-01-24 2021-07-29 株式会社ソニー・インタラクティブエンタテインメント Environment map management device, environment map management method, and program

Patent Citations (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108318043A (en) * 2017-12-29 2018-07-24 百度在线网络技术（北京）有限公司 Method, apparatus for updating electronic map and computer readable storage medium
US20190204094A1 (en) * 2017-12-29 2019-07-04 Baidu Online Network Technology (Beijing) Co., Ltd. Method, apparatus, and computer readable storage medium for updating electronic map
EP3594902A1 (en) * 2018-07-09 2020-01-15 Autonomous Intelligent Driving GmbH Method for estimating a relative position of an object in the surroundings of a vehicle and electronic control unit for a vehicle and vehicle
CN111256687A (en) * 2018-11-30 2020-06-09 广东星舆科技有限公司 Map data processing method and device, acquisition equipment and storage medium
WO2020224305A1 (en) * 2019-05-07 2020-11-12 北京市商汤科技开发有限公司 Method and apparatus for device positioning, and device
CN111982133A (en) * 2019-05-23 2020-11-24 北京地平线机器人技术研发有限公司 Method and device for positioning vehicle based on high-precision map and electronic equipment
CN112050806A (en) * 2019-06-06 2020-12-08 北京初速度科技有限公司 Positioning method and device for moving vehicle
CN112069856A (en) * 2019-06-10 2020-12-11 商汤集团有限公司 Map generation method, driving control method, device, electronic equipment and system
WO2021149254A1 (en) * 2020-01-24 2021-07-29 株式会社ソニー・インタラクティブエンタテインメント Environment map management device, environment map management method, and program
CN111784798A (en) * 2020-06-30 2020-10-16 滴图(北京)科技有限公司 Map generation method and device, electronic equipment and storage medium
CN112785655A (en) * 2021-01-28 2021-05-11 中汽创智科技有限公司 Method, device and equipment for automatically calibrating external parameters of all-round camera based on lane line detection and computer storage medium

Non-Patent Citations (5)

* Cited by examiner, † Cited by third party
Title
J. S. BERRIO, J. WARD, S. WORRALL AND E. NEBOT: "Updating the visibility of a feature-based map for long-term maintenance", 2019 IEEE INTELLIGENT VEHICLES SYMPOSIUM (IV) *
夏辉;王喜春;: "低空管廊线状要素增量更新制图研究", 电子测量技术, no. 09 *
夏辉;王喜春;: "低空管廊线状要素增量更新制图研究", 电子测量技术, no. 09, 27 April 2018 (2018-04-27) *
曾利萍: "利用RGB-D传感器数据的室内导航数据模型构建", 《中国优秀硕士学位论文全文数据库·信息科技辑》, no. 8 *
王冕;: "面向自动驾驶的高精度地图及其应用方法", 地理信息世界, no. 04 *

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114581667A (en) * 2022-03-04 2022-06-03 北京百度网讯科技有限公司 Map data processing method and device, electronic equipment and storage medium

Similar Documents

Publication Publication Date Title
CN113361578B (en) Training method and device for image processing model, electronic equipment and storage medium
CN113920307A (en) Model training method, device, equipment, storage medium and image detection method
CN113191256A (en) Method and device for training lane line detection model, electronic device and storage medium
CN113947147B (en) Training method, positioning method and related device of target map model
CN113859264B (en) Vehicle control method, device, electronic equipment and storage medium
CN113177968A (en) Target tracking method and device, electronic equipment and storage medium
CN114648676A (en) Point cloud processing model training and point cloud instance segmentation method and device
EP4194807A1 (en) High-precision map construction method and apparatus, electronic device, and storage medium
CN114003613A (en) High-precision map lane line updating method and device, electronic equipment and storage medium
CN113361710A (en) Student model training method, picture processing device and electronic equipment
CN113361572A (en) Training method and device of image processing model, electronic equipment and storage medium
CN114443794A (en) Data processing and map updating method, device, equipment and storage medium
CN114140759A (en) High-precision map lane line position determining method and device and automatic driving vehicle
CN113298910A (en) Method, apparatus and storage medium for generating traffic sign line map
CN113724388B (en) High-precision map generation method, device, equipment and storage medium
JP2023531759A (en) Lane boundary detection model training method, lane boundary detection model training device, electronic device, storage medium and computer program
CN114186007A (en) High-precision map generation method and device, electronic equipment and storage medium
CN113932796A (en) High-precision map lane line generation method and device and electronic equipment
CN114111813A (en) High-precision map element updating method and device, electronic equipment and storage medium
CN114972910B (en) Training method and device for image-text recognition model, electronic equipment and storage medium
CN114743178B (en) Road edge line generation method, device, equipment and storage medium
CN113344121B (en) Method for training a sign classification model and sign classification
CN115357500A (en) Test method, device, equipment and medium for automatic driving system
CN114445668A (en) Image recognition method and device, electronic equipment and storage medium
CN111968030B (en) Information generation method, apparatus, electronic device and computer readable medium

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination