CN112884837B - Road positioning method, device, equipment and storage medium - Google Patents

Road positioning method, device, equipment and storage medium Download PDF

Info

Publication number
CN112884837B
CN112884837B CN202110282157.8A CN202110282157A CN112884837B CN 112884837 B CN112884837 B CN 112884837B CN 202110282157 A CN202110282157 A CN 202110282157A CN 112884837 B CN112884837 B CN 112884837B
Authority
CN
China
Prior art keywords
road
target vehicle
characteristic information
time
information
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.)
Active
Application number
CN202110282157.8A
Other languages
Chinese (zh)
Other versions
CN112884837A (en
Inventor
朱晓辉
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.)
Beijing Baidu Netcom Science and Technology Co Ltd
Original Assignee
Beijing Baidu Netcom Science and Technology 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 Beijing Baidu Netcom Science and Technology Co Ltd filed Critical Beijing Baidu Netcom Science and Technology Co Ltd
Priority to CN202110282157.8A priority Critical patent/CN112884837B/en
Publication of CN112884837A publication Critical patent/CN112884837A/en
Application granted granted Critical
Publication of CN112884837B publication Critical patent/CN112884837B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

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
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/70—Determining position or orientation of objects or cameras
    • G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/29—Geographical information databases
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30248—Vehicle exterior or interior
    • G06T2207/30252—Vehicle exterior; Vicinity of vehicle
    • G06T2207/30256—Lane; Road marking
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
    • Y02T10/00—Road transport of goods or passengers
    • Y02T10/10—Internal combustion engine [ICE] based vehicles
    • Y02T10/40—Engine management systems

Abstract

The disclosure provides a road positioning method, a device, equipment and a storage medium, and relates to the field of automatic driving. The specific implementation scheme is as follows: predicting to obtain position characteristic information of target vehicles at N adjacent moments, wherein the predicted position characteristic information characterizes a probability value of at least one candidate road associated with the target vehicle at the current moment; obtaining transfer characteristic information of the target vehicle from t time to t+1 time in the N time based on the position characteristic information of the target vehicle at the N time, wherein the transfer characteristic information at least represents a probability value of a transfer path corresponding to at least one candidate road associated with the t time for transferring the target vehicle from the at least one candidate road associated with the t time to the at least one candidate road associated with the t+1 time; and predicting an initial road where the target vehicle is located in a period corresponding to the N moments from all candidate roads based on the position characteristic information and the road transfer information. In this way, road-level positioning is achieved.

Description

Road positioning method, device, equipment and storage medium
Technical Field
The present disclosure relates to the field of data processing technology, and in particular, to the field of autopilot.
Background
Road level positioning technology refers to finding the road in which the current positioning is located in a map road network in the presence of global navigation satellite system (GNSS, global Navigation Satellite System) positioning. This is a basic function of applications such as map navigation technology. However, under the practical application condition, the positioning accuracy error of the mobile device or the vehicle-mounted GNSS can be as high as ten meters or even tens of meters, if a plurality of roads exist in the GNSS error range, the road is not directly determined by positioning, so that the user experience is reduced, and meanwhile, the use scene is limited.
Disclosure of Invention
The disclosure provides a road positioning method, a device, equipment and a storage medium.
According to an aspect of the present disclosure, there is provided a road positioning method including:
predicting and obtaining position characteristic information of target vehicles at N adjacent moments, wherein the predicted position characteristic information represents a probability value that the target vehicle is in at least one associated candidate road at the current moment; the N is an integer greater than or equal to 2;
obtaining transfer characteristic information of the target vehicle from t time to t+1 time in the N time based on the position characteristic information of the target vehicle at the N time, wherein the transfer characteristic information at least represents a probability value of a transfer path corresponding to the target vehicle from at least one candidate road associated with the t time to at least one candidate road associated with the t+1 time;
and predicting an initial road where the target vehicle is located in a period corresponding to the N moments from all the candidate roads based on the position characteristic information and the road transfer information.
According to another aspect of the present disclosure, there is provided a road positioning apparatus including:
the prediction unit is used for predicting and obtaining position characteristic information of target vehicles at N adjacent moments, wherein the predicted position characteristic information characterizes a probability value of the target vehicle at the current moment in an associated at least one candidate road; the N is an integer greater than or equal to 2;
a transfer characteristic determining unit, configured to obtain transfer characteristic information of the target vehicle from a time t to a time t+1 of the N times based on position characteristic information of the target vehicle at the N times, where the transfer characteristic information at least characterizes a probability value of a transfer path corresponding to the target vehicle transferring from at least one candidate road associated with the time t to at least one candidate road associated with the time t+1;
and the initial road determining unit is used for predicting the initial road where the target vehicle is located in the period corresponding to the N moments from all the candidate roads based on the position characteristic information and the road transfer information.
According to another aspect of the present disclosure, there is provided an electronic device including:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein, the liquid crystal display device comprises a liquid crystal display device,
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 the embodiments of the present disclosure.
According to another aspect of the present disclosure, there is provided a non-transitory computer-readable storage medium storing computer instructions for causing a computer to perform the method of any of the embodiments of the present disclosure.
According to another aspect of the present disclosure, there is provided a computer program product comprising a computer program which, when executed by a processor, implements the method in any of the embodiments of the present disclosure.
According to the technology disclosed by the invention, the initial positioning of the road level is realized, the user experience is improved, and meanwhile, the use scene is enriched.
It should be understood that the description in this section is not intended to identify key or critical features of the embodiments of the disclosure, nor is it intended to be used to limit the scope of the disclosure. Other features of the present disclosure will become apparent from the following specification.
Drawings
The drawings are for a better understanding of the present solution and are not to be construed as limiting the present disclosure. Wherein:
FIG. 1 is a schematic flow diagram of an implementation of a road positioning method according to an embodiment of the disclosure;
FIG. 2 is a schematic diagram of a process flow in a specific example of a road positioning method according to an embodiment of the disclosure;
FIG. 3 is a schematic diagram of a road location method in a specific example according to an embodiment of the disclosure;
FIG. 4 is a schematic structural view of a road positioning device according to an embodiment of the present disclosure;
fig. 5 is a block diagram of an electronic device for implementing a road positioning method of an embodiment of the present disclosure.
Detailed Description
Exemplary embodiments of the present disclosure are described below in conjunction with the accompanying drawings, which include various details of the embodiments of the present disclosure to facilitate understanding, and should be considered as merely exemplary. Accordingly, one 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.
In practical application, road level positioning can be simply divided into two stages of initialization and stable positioning. In the stable positioning phase, the road at the previous moment is already determined, and even when the vehicle is currently driving to the intersection, the selectable roads are limited, because the road which is not connected in the topology structure (such as the road network structure) at the previous moment is not considered. Thus, the method is equivalent to stable prior information, and reduces the selection range. But in the initialization phase there is no a priori information and it is necessary to select the correct road from the roads within a certain radius around the current position of the vehicle with a very high accuracy. Based on this, the present application provides a road positioning scheme.
Specifically, the present application provides a road positioning method, as shown in fig. 1, which includes:
step S101: predicting and obtaining position characteristic information of target vehicles at N adjacent moments, wherein the predicted position characteristic information represents a probability value that the target vehicle is in at least one associated candidate road at the current moment; and N is an integer greater than or equal to 2.
Step S102: and obtaining transfer characteristic information of the target vehicle from the t moment to the t+1 moment in the N moments based on the position characteristic information of the target vehicle at the N moments, wherein the transfer characteristic information at least represents a probability value of a transfer path corresponding to the target vehicle from at least one candidate road associated with the t moment to at least one candidate road associated with the t+1 moment. Here, t and t+1 are adjacent two times among N times.
Step S103: and predicting an initial road where the target vehicle is located in a period corresponding to the N moments from all the candidate roads based on the position characteristic information and the road transfer information.
In this way, the initial road of the target vehicle is estimated based on the probability value of the candidate road associated with the current moment of the target vehicle and the probability value of the transition path between two adjacent moments (namely, between the moment t and the moment t+1), so that each candidate road and the transition path are quantized from the aspect of probability, the initial road is selected, the problem of larger error is solved, the user experience is improved on the basis of realizing the road-level positioning, and the use scene is enriched.
In practical application, in the automatic driving scene, the positioning accuracy of decimeter or even centimeter level is required. Before high-precision positioning is achieved, road-level positioning with extremely high accuracy is achieved first. Obviously, the scheme can be applied to the automatic driving scene, and provides support for realizing accurate road level positioning of the automatic driving scene.
Here, the candidate road associated with the time t may be the same as or different from the candidate road associated with the time t+1, or may be only partially the same as or different from the candidate road associated with the time t+1; based on this, the transition path may be a transition from the candidate road a at the time t to the candidate road B at the time t+1, or a transition from the candidate road a at the time t to the candidate road a at the time t+1, that is, the traveling road is not changed, which is not limited by the scheme of the present application.
In a specific example of the present application, to further improve the accuracy of the located initial road, the present application may also be applied to a training scenario, where the actual initial road is known in advance, so that the accuracy of the locating result is further improved. Specifically, based on the difference characteristics between the predicted initial road and the actual initial road of the target vehicle in the period corresponding to the N moments, optimizing the predicted position characteristic information.
In a specific example of the solution of the present application, the location feature information may be obtained in the following manner, specifically, the road image information of the target vehicle at the time t and the geographic location information where the road image information is located are obtained; the road image information may be specifically a road on which the target vehicle is traveling at the current time, and the information may be acquired by an in-vehicle apparatus, for example, an in-vehicle camera, and uploaded to a server for positioning processing. Further, based on the road image information and the geographic position information, predicting at least one candidate road associated with the target vehicle at the time t and a probability value that the target vehicle is on the associated candidate road; and then, taking at least one candidate road associated with the target vehicle at the t moment and the probability value of the target vehicle on the associated candidate road as the position characteristic information of the target vehicle at the t moment, so that the position characteristic information of the target vehicle at each moment in N moments is predicted and obtained, and laying a foundation for realizing road level positioning subsequently.
In a specific example of the solution of the present application, the probability value of the candidate road associated with a certain moment may be obtained by determining, specifically, at least two preset features required for locating the road where the target vehicle is located, and initial weights of the preset features; here, the preset feature may be set arbitrarily based on the actual positioning requirement, and accordingly, the initial weight may also be set arbitrarily based on the actual requirement, which is not limited in the present application. Further, an initial feature value of the preset feature is determined, wherein the initial feature value is determined based on road image information of the target vehicle at a time t in the N times and geographic position information; and further, based on the initial weight and the initial characteristic value, obtaining a probability value that the target vehicle at the moment t is on an associated candidate road, so that the position characteristic information at the moment t is obtained through prediction, and further, the position characteristic information of the target vehicle at each moment in N adjacent moments is obtained through prediction, and a foundation is laid for realizing road-level positioning subsequently.
In a specific example of the present application, the optimizing processing on the predicted location feature information specifically includes: optimizing the initial weight of the preset feature to obtain a target weight aiming at the preset feature; and the initial road obtained based on target weight prediction is matched with the real initial road. Specifically, the probability value of the candidate road associated with the target vehicle at the time t can be obtained based on the target weight, the probability value of the candidate road associated with the target vehicle at the time t+1 can be obtained, and then the probability value of the transition path corresponding to the candidate road associated with the target vehicle at the time t is obtained, so that the initial road is obtained through prediction.
In a specific example of the present application, the obtaining, based on the location feature information of the target vehicle at the N times, transfer feature information of the target vehicle from the t time to the t+1 time in the N times may specifically include: acquiring the position characteristic information at the time t and the position characteristic information at the time t+1; multiplying the probability value of the candidate road associated with the position characteristic information at the time t with the probability value of the candidate road associated with the position characteristic information at the time t+1; and taking the product processing result as transfer characteristic information of the target vehicle from the t moment to the t+1 moment in the N moments. That is, the product processing result is taken as a probability value of a transition path corresponding to the candidate road associated with the t moment to the candidate road associated with the t+1 moment, for example, the probability value of the candidate road a associated with the t moment is A1, the probability value of the candidate road B associated with the t+1 moment is B1, and at this time, the probability value of the transition path is A1 multiplied by B1. Therefore, based on a simple quantification mode, transfer characteristic information from the time t to the time t+1 is obtained, and a foundation is laid for accurately determining an initial road.
In a specific example of the present application, the predicting, based on the location feature information and the road transfer information, the initial road where the target vehicle is located in the period corresponding to the N times from all the candidate roads may specifically include: and obtaining probability values of all transfer paths based on the position characteristic information and the road transfer information, for example, obtaining the probability values of all transfer paths based on a product relation, and further determining an initial road where the target vehicle is located based on a candidate road corresponding to the transfer path with the largest probability value. That is, the transfer path with the highest probability is selected as the driving path of the target vehicle, so that the initial road is predicted, the road-level positioning is realized, meanwhile, the user experience is improved, and the use scene is enriched.
Here, it should be noted that, in the above-mentioned scheme of the present application, the time t is any time of the adjacent N times, in other words, in practical application, the processing flow of the related information at any time of the adjacent N times may refer to the processing manner for the time t in the above-mentioned example, and here, details of each time are not repeated.
In this way, the initial road of the target vehicle is estimated based on the probability value of the candidate road associated with the current moment of the target vehicle and the probability value of the transition path between two adjacent moments (namely, between the moment t and the moment t+1), so that each candidate road and the transition path are quantized from the aspect of probability, the initial road is selected, the problem of larger error is solved, the user experience is improved on the basis of realizing the road-level positioning, and the use scene is enriched.
The following describes the present application in further detail with reference to specific examples, specifically, in terms of information, the road level positioning technology may use historical information and current information, and the hidden markov frame may well integrate the two angles of information, based on which, the present example adopts the hidden markov frame to implement positioning of the initial road, as shown in fig. 2, where a state may also be referred to as state information, and may be obtained by estimation based on observation (i.e., observation information), and therefore, the state may also be referred to as hidden state. And the probability value of the transition road corresponding to the two adjacent states can be obtained based on time sequence derivation. Specifically, the timing derivation and information matching are described in detail:
first, time sequence deducing, obtaining the transition probability of the state deduction of the current frame to the state of the next frame. Here, a frame may be understood as overall characteristic information including at least road image information and geographical position information for a target vehicle at the present time. In a real scene, a real road is divided into a plurality of segments, and each segment can be called a link and has a unique id, namely a link id. Based on this, the state of the frame can be understood as a set of candidate link ids where the target vehicle is presumed to be located based on the observation at the present time (i.e., the overall feature information). Further, the time sequence between adjacent states is deduced, and a probability, namely transition probability, is represented based on map topological connectivity and the similarity between the change amounts of the front state and the back state and the change amounts observed before and after. For example, in the state T-1 and the state T in fig. 2, assuming that there are m possible link ids of the state T-1 and n possible link ids of the state T, a transition matrix T is obtained based on time sequence derivation, and the transition matrix T is a matrix of m×n. Further, after the probability values of m link ids in the state t-1 and the probability values of n link ids in the state t are determined, the probability values of the transition paths involved in the transition matrix, namely the transition probability, can be obtained.
Secondly, the information matching can be understood as a matching process of the overall feature information of the current frame and the map information, and can be characterized by similarity probability, namely, the probability value of link id is characterized by the similarity probability. For example, the candidate road of the target vehicle at the current moment can be primarily screened out based on the related information of the GNSS, and then the attribute of the road where the positioning is located can be more accurately determined based on the acquired perception information and the like. For example, based on the road image information, it may be detected that there are three lanes on the road where the target vehicle is currently located, the lane line attributes are solid lines, broken lines, dashed lines, and solid lines, and the color is white, and after matching with the map information, a probability value may be given to the link id.
In practical applications, the similarity probability is not defined by a standard. Based on the above, preset characteristics, such as a GNSS heading and map heading difference, a GNSS position-to-map vertical distance, sensing information (such as information obtained by an on-vehicle sensor) and map matching degree, a vehicle speed and map road speed limit difference, a GNSS elevation and map elevation difference, and the like, can be predetermined to comprehensively calculate the similarity probability of link ids. Specifically, the above-described preset feature may be noted as:
X＝(x 1 ，x x ，...，x n )
each preset feature is assumed to have independent distribution, and then converted into a probability value for representation, so that the probability value is obtained:
P＝(p 1 ，p 2 ，...，p n )
and obtaining similar probabilities of a single link id by adopting a linear weighting form among the probabilities:
Figure BDA0002979000340000081
note that the weight ω, whose magnitude represents the importance of the corresponding preset feature, can be trained by data driven to obtain the optimal weight combination.
Specifically, the best weight combination is obtained through training in a sliding window mode, and here, assuming that the window size is N, that is, N times are included, N observations exist inside the window, and N states are corresponding to the N observations. Based on this, the optimal value of each state, i.e., the optimal link id of each state, can be determined by determining the state chain (i.e., transition path) of the maximum probability inside the window. Here, in the above-described process, training is performed using the real road information as the reference information, and thus, an optimal weight combination is obtained.
Specifically, the following formula is derived based on the similarity probability and the transition probability:
(probability of similarity at time t) x (probability of transition from time t to time t+1) × (probability of similarity at time t+1) × … × (probability of similarity at time t+n-1) × (probability of transition from time t+n-1 to time t+n) × (probability of similarity at time t+n).
For each transition path (i.e. chain), the probability is a function of ω, and after the probability normalization of all chains, the proportion of the chain to all options can be seen, for example, by means of the probability vector a.
Further, true value labeling of the real scene is performed, for example, in the real scene, the probability of the road on which the target vehicle is located is 1, the probability of the road on which the target vehicle is not traveling is 0, and the like, and thus the above formula is rewritten into the probability vector B. In this case, the loss function may be a square of a difference between the normalized probability (probability vector a) and the true value (probability vector B). Thus, by a simple gradient descent method, the optimal omega parameter can be trained, so that the road selected by the continuous multiplication of the probability of omega expression is the road with the highest accuracy.
For example, as shown in fig. 3, let N be equal to 3, i.e. 3 times are included in the sliding window, wherein the road associated with the time 1 includes a road a and a road D, and the probability value of the road a at the time 1 is ρ 1A The probability value of the road D at time 1 is ρ 1D The method comprises the steps of carrying out a first treatment on the surface of the Similarly, the roads associated with time 2 include road a, road B and road C, and accordingly the probability values are ρ 2A ，ρ 2B And ρ 2C The method comprises the steps of carrying out a first treatment on the surface of the The roads associated with time 3 include road B and road D, and accordingly, the probability values are ρ 3B And ρ 3D . At this time, based on the scheme of the present application, the probabilities of all chains in the sliding window, that is, ρ (AAB) (representing the probability value of the transition path corresponding to the road a from time 1, the road a to time 2, and the road C to time 3), ρ (AAD), ρ (ABB), and the like, need to be exhausted in practical applications. Further, the p (AAB) =ρ 1A ×T AA ×ρ 2A ×T AB ×ρ 2B Here, the T AA That is, the probability value of the transition path corresponding to the transition from the road a at the time 1 to the road a at the time 2 is, for example, equal ρ 1A ×ρ 2A . Thus, the chain with the highest probability is determined, and the initial road is obtained.
In summary, the problem of the initialization of the hidden Markov model based on the sliding window is emphasized, compared with the current situation that the initialization stage lacks discussion and implementation in the traditional technology, the method and the device of the application have the advantages that the initialization technology is completely abstracted, the related information of multiple sensors of the target vehicle is fully utilized, the initialization is simplified into the problem of the classification model, and then the initial road with higher accuracy is obtained. At present, the accuracy rate of more than 99.9% can be basically achieved on the test data of 1w kilometer in the scheme of the application.
The application scheme still provides a road positioner, as shown in fig. 4, and this device includes:
a prediction unit 401, configured to predict and obtain location feature information of target vehicles at N adjacent moments, where the predicted location feature information characterizes a probability value that the target vehicle is in an associated at least one candidate road at a current moment; the N is an integer greater than or equal to 2;
a transition feature determining unit 402, configured to obtain transition feature information of the target vehicle from a time t to a time t+1 of the N times based on position feature information of the target vehicle at the N times, where the transition feature information at least characterizes a probability value of a transition path corresponding to the target vehicle from at least one candidate road associated with the time t to at least one candidate road associated with the time t+1;
and an initial road determining unit 403, configured to predict, from all the candidate roads, an initial road where the target vehicle is located in a period corresponding to the N times, based on the location feature information and the road transition information.
In a specific example of the present application, further includes:
and the optimizing unit is used for optimizing the predicted position characteristic information based on the difference characteristics between the predicted initial road and the real initial road of the target vehicle in the period corresponding to the N moments.
In a specific example of the solution of the present application, the prediction unit is further configured to obtain road image information of the target vehicle at the time t and geographical location information of the target vehicle; predicting at least one candidate road associated with the target vehicle at the time t and a probability value of the target vehicle being on the associated candidate road based on the road image information and the geographic position information; and taking at least one candidate road associated with the target vehicle at the t moment and the probability value of the target vehicle on the associated candidate road as the position characteristic information of the target vehicle at the t moment so as to predict and obtain the position characteristic information of the target vehicle at N moments.
In a specific example of the solution of the present application, the prediction unit is further configured to determine at least two preset features required for locating a road on which the target vehicle is located, and initial weights of the preset features; determining an initial feature value of the preset feature, wherein the initial feature value is determined based on road image information of the target vehicle at a t moment in the N moments and geographic position information; and obtaining a probability value of the candidate road associated with the target vehicle at the moment t based on the initial weight and the initial characteristic value so as to predict and obtain the position characteristic information at the moment t.
In a specific example of the solution of the present application, the optimizing unit is further configured to optimize an initial weight of the preset feature to obtain a target weight for the preset feature; and the initial road obtained based on target weight prediction is matched with the real initial road.
In a specific example of the solution of the present application, the transfer feature determining unit is further configured to obtain location feature information at the time t and location feature information at the time t+1; multiplying the probability value of the candidate road associated with the position characteristic information at the time t with the probability value of the candidate road associated with the position characteristic information at the time t+1; and taking the product processing result as transfer characteristic information of the target vehicle from the t moment to the t+1 moment in the N moments.
In a specific example of the present application, the initial road determining unit is further configured to obtain probability values of all the transition paths based on the location feature information and the road transition information; and determining an initial road where the target vehicle is located based on the candidate road corresponding to the transfer path with the maximum probability value.
The functions of each unit in the road positioning device according to the embodiment of the present invention may be referred to the corresponding descriptions in the above method, and will not be described herein.
According to embodiments of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium and a computer program product.
Fig. 5 illustrates a schematic block diagram of an example electronic device 500 that may be used to implement 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 telephones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the disclosure described and/or claimed herein.
As shown in fig. 5, the electronic device 500 includes a computing unit 501 that can perform various suitable actions and processes according to a computer program stored in a Read Only Memory (ROM) 502 or a computer program loaded from a storage unit 508 into a Random Access Memory (RAM) 503. In the RAM 503, various programs and data required for the operation of the electronic device 500 may also be stored. The computing unit 501, ROM 502, and RAM 503 are connected to each other by a bus 504. An input output (I/O) interface 505 is also connected to bus 504.
A number of components in electronic device 500 are connected to I/O interface 505, including: an input unit 506 such as a keyboard, a mouse, etc.; an output unit 507 such as various types of displays, speakers, and the like; a storage unit 508 such as a magnetic disk, an optical disk, or the like; and a communication unit 509 such as a network card, modem, wireless communication transceiver, etc. The communication unit 509 allows the electronic device 500 to exchange information/data with other devices via a computer network such as the internet and/or various telecommunication networks.
The computing unit 501 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of computing unit 501 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, etc. The computing unit 501 performs the various methods and processes described above, such as the road location method. For example, in some embodiments, the road location method may be implemented as a computer software program tangibly embodied on a machine-readable medium, such as the storage unit 508. In some embodiments, part or all of the computer program may be loaded and/or installed onto the electronic device 500 via the ROM 502 and/or the communication unit 509. When the computer program is loaded into the RAM 503 and executed by the computing unit 501, one or more steps of the road positioning method described above may be performed. Alternatively, in other embodiments, the computing unit 501 may be configured to perform the road location 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 circuit systems, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), systems On 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, the one or more computer programs may be executed and/or interpreted on a programmable system including at least one programmable processor, which may be a special purpose or general-purpose programmable processor, that may receive data and instructions from, and transmit data and instructions to, a storage system, at least one input device, and at least one output device.
Program code for carrying out methods of the present disclosure may be written in any combination of one or more programming languages. These program code 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 code, when executed by the processor or controller, causes the functions/operations specified in the flowchart and/or block diagram to be implemented. 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. The 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 pointing device (e.g., a mouse or 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 may 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 input, speech input, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a background 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 background, 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), and the internet.
The computer system may include a client and a server. The client and server are typically 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.
It should be appreciated that various forms of the flows shown above may be used to reorder, add, or delete steps. For example, the steps recited in the present disclosure may be performed in parallel, sequentially, or in a different order, provided that the desired results of the disclosed aspects are achieved, and are not limited herein.
The above detailed description should not be taken as limiting the scope of the present disclosure. It will be apparent to those skilled in the art that various modifications, combinations, sub-combinations and alternatives are possible, depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present disclosure are intended to be included within the scope of the present disclosure.

Claims (14)

1. A road positioning method, comprising:
predicting and obtaining position characteristic information of target vehicles at N adjacent moments, wherein the position characteristic information represents probability values of at least one candidate road associated with the target vehicles at the current moment; the N is an integer greater than or equal to 2;
obtaining transfer characteristic information of the target vehicle from t time to t+1 time in the N time based on the position characteristic information of the target vehicle at the N time, wherein the transfer characteristic information at least represents a probability value of a transfer path corresponding to the target vehicle from at least one candidate road associated with the t time to at least one candidate road associated with the t+1 time;
based on the position characteristic information and the transfer characteristic information, predicting an initial road where the target vehicle is located in a period corresponding to the N moments from all the candidate roads;
the obtaining, based on the position feature information of the target vehicle at the N times, transfer feature information of the target vehicle from a time t to a time t+1 of the N times includes:
acquiring the position characteristic information at the time t and the position characteristic information at the time t+1;
multiplying the probability value of the candidate road associated with the position characteristic information at the time t with the probability value of the candidate road associated with the position characteristic information at the time t+1;
and taking the product processing result as transfer characteristic information of the target vehicle from the t moment to the t+1 moment in the N moments.
2. The method of claim 1, further comprising:
and optimizing the predicted position characteristic information based on the difference characteristics between the predicted initial road and the actual initial road of the target vehicle in the period corresponding to the N moments.
3. The method of claim 2, further comprising:
acquiring road image information of the target vehicle at the time t and geographical position information of the target vehicle;
predicting at least one candidate road associated with the target vehicle at the time t and a probability value of the target vehicle being on the associated candidate road based on the road image information and the geographic position information;
and taking at least one candidate road associated with the target vehicle at the t moment and the probability value of the target vehicle on the associated candidate road as the position characteristic information of the target vehicle at the t moment so as to predict and obtain the position characteristic information of the target vehicle at N moments.
4. A method according to claim 2 or 3, further comprising:
determining at least two preset features required for positioning a road where the target vehicle is located and initial weights of the preset features;
determining an initial feature value of the preset feature, wherein the initial feature value is determined based on road image information of the target vehicle at a t moment in the N moments and geographic position information;
and obtaining a probability value of the candidate road associated with the target vehicle at the moment t based on the initial weight and the initial characteristic value so as to predict and obtain the position characteristic information at the moment t.
5. The method according to claim 4, wherein the optimizing the predicted location feature information includes:
optimizing the initial weight of the preset feature to obtain a target weight aiming at the preset feature; and the initial road obtained based on target weight prediction is matched with the real initial road.
6. The method according to claim 3, wherein predicting, based on the location feature information and the transfer feature information, an initial road where the target vehicle is located in a period corresponding to the N times from all the candidate roads includes:
obtaining probability values of all transfer paths based on the position characteristic information and the transfer characteristic information;
and determining an initial road where the target vehicle is located based on the candidate road corresponding to the transfer path with the maximum probability value.
7. A roadway positioning apparatus comprising:
the prediction unit is used for predicting and obtaining position characteristic information of target vehicles at N adjacent moments, wherein the position characteristic information represents a probability value that the target vehicle is in at least one associated candidate road at the current moment; the N is an integer greater than or equal to 2;
a transfer characteristic determining unit, configured to obtain transfer characteristic information of the target vehicle from a time t to a time t+1 of the N times based on position characteristic information of the target vehicle at the N times, where the transfer characteristic information at least characterizes a probability value of a transfer path corresponding to the target vehicle transferring from at least one candidate road associated with the time t to at least one candidate road associated with the time t+1;
an initial road determining unit, configured to predict, from all the candidate roads, an initial road where the target vehicle is located in a period corresponding to the N moments, based on the location feature information and the transfer feature information;
the transfer characteristic determining unit is further configured to obtain location characteristic information at the time t and location characteristic information at the time t+1; multiplying the probability value of the candidate road associated with the position characteristic information at the time t with the probability value of the candidate road associated with the position characteristic information at the time t+1; and taking the product processing result as transfer characteristic information of the target vehicle from the t moment to the t+1 moment in the N moments.
8. The apparatus of claim 7, further comprising:
and the optimizing unit is used for optimizing the predicted position characteristic information based on the difference characteristics between the predicted initial road and the real initial road of the target vehicle in the period corresponding to the N moments.
9. The apparatus of claim 8, wherein the prediction unit is further configured to obtain road image information of the target vehicle at the time t and geographical location information; predicting at least one candidate road associated with the target vehicle at the time t and a probability value of the target vehicle being on the associated candidate road based on the road image information and the geographic position information; and taking at least one candidate road associated with the target vehicle at the t moment and the probability value of the target vehicle on the associated candidate road as the position characteristic information of the target vehicle at the t moment so as to predict and obtain the position characteristic information of the target vehicle at N moments.
10. The apparatus according to claim 8 or 9, wherein the prediction unit is further configured to determine at least two preset features required for locating the road on which the target vehicle is located, and initial weights of the preset features; determining an initial feature value of the preset feature, wherein the initial feature value is determined based on road image information of the target vehicle at a t moment in the N moments and geographic position information; and obtaining a probability value of the candidate road associated with the target vehicle at the moment t based on the initial weight and the initial characteristic value so as to predict and obtain the position characteristic information at the moment t.
11. The apparatus of claim 10, wherein the optimizing unit is further configured to optimize an initial weight of the preset feature to obtain a target weight for the preset feature; and the initial road obtained based on target weight prediction is matched with the real initial road.
12. The apparatus of claim 9, wherein the initial road determination unit is further configured to obtain probability values of all transition paths based on the location feature information and the transition feature information; and determining an initial road where the target vehicle is located based on the candidate road corresponding to the transfer path with the maximum probability value.
13. An electronic device, comprising:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein, the liquid crystal display device comprises a liquid crystal display device,
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 1-6.
14. A non-transitory computer readable storage medium storing computer instructions for causing a computer to perform the method of any one of claims 1-6.
CN202110282157.8A 2021-03-16 2021-03-16 Road positioning method, device, equipment and storage medium Active CN112884837B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110282157.8A CN112884837B (en) 2021-03-16 2021-03-16 Road positioning method, device, equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110282157.8A CN112884837B (en) 2021-03-16 2021-03-16 Road positioning method, device, equipment and storage medium

Publications (2)

Publication Number Publication Date
CN112884837A CN112884837A (en) 2021-06-01
CN112884837B true CN112884837B (en) 2023-06-20

Family

ID=76042672

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110282157.8A Active CN112884837B (en) 2021-03-16 2021-03-16 Road positioning method, device, equipment and storage medium

Country Status (1)

Country Link
CN (1) CN112884837B (en)

Families Citing this family (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114092911B (en) * 2021-11-23 2023-08-01 北京百度网讯科技有限公司 Road identification method, device, electronic equipment and storage medium
CN114216467A (en) * 2021-12-13 2022-03-22 禾多科技（北京）有限公司 Road positioning method, device, computer equipment and storage medium
CN116086469B (en) * 2023-01-16 2023-10-24 禾多科技（北京）有限公司 Lane positioning method and device
CN116007638B (en) * 2023-03-24 2023-05-30 北京集度科技有限公司 Vehicle track map matching method and device, electronic equipment and vehicle

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2019218861A1 (en) * 2018-05-14 2019-11-21 华为技术有限公司 Method for estimating driving road and driving road estimation system
CN110689719A (en) * 2019-05-31 2020-01-14 北京嘀嘀无限科技发展有限公司 System and method for identifying closed road sections
CN111177285A (en) * 2018-11-09 2020-05-19 厦门雅迅网络股份有限公司 Electronic map accurate positioning method, terminal equipment and storage medium
CN111340856A (en) * 2018-12-19 2020-06-26 杭州海康威视系统技术有限公司 Vehicle tracking method, device, equipment and storage medium
WO2020237710A1 (en) * 2019-05-31 2020-12-03 Beijing Didi Infinity Technology And Development Co., Ltd. Systems and methods for route planning

Family Cites Families (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP3046389B2 (en) * 1991-05-23 2000-05-29 アルパイン株式会社 Vehicle position detection device for in-vehicle navigator
CN104900059B (en) * 2015-05-26 2017-04-12 大连理工大学 Method for enhancing cell phone base station positioning precision
CN106205161B (en) * 2016-07-09 2018-09-18 腾讯科技（深圳）有限公司 traffic information transmission method and device
JP6758160B2 (en) * 2016-11-10 2020-09-23 株式会社デンソーアイティーラボラトリ Vehicle position detection device, vehicle position detection method and computer program for vehicle position detection
KR20200100810A (en) * 2018-02-01 2020-08-26 토르드라이브 아이엔씨 Own vehicle location prediction method and autonomous driving device for autonomous driving
US11531346B2 (en) * 2019-07-05 2022-12-20 Uatc, Llc Goal-directed occupancy prediction for autonomous driving
CN111737379B (en) * 2020-04-13 2023-07-18 腾讯科技（深圳）有限公司 Road collection task generation device, electronic equipment and readable storage medium
CN111651538B (en) * 2020-05-11 2022-11-01 腾讯科技（深圳）有限公司 Position mapping method, device and equipment and readable storage medium
CN111858817B (en) * 2020-07-23 2021-05-18 中国石油大学(华东) BilSTM-CRF path inference method for sparse track

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2019218861A1 (en) * 2018-05-14 2019-11-21 华为技术有限公司 Method for estimating driving road and driving road estimation system
CN111177285A (en) * 2018-11-09 2020-05-19 厦门雅迅网络股份有限公司 Electronic map accurate positioning method, terminal equipment and storage medium
CN111340856A (en) * 2018-12-19 2020-06-26 杭州海康威视系统技术有限公司 Vehicle tracking method, device, equipment and storage medium
CN110689719A (en) * 2019-05-31 2020-01-14 北京嘀嘀无限科技发展有限公司 System and method for identifying closed road sections
WO2020237710A1 (en) * 2019-05-31 2020-12-03 Beijing Didi Infinity Technology And Development Co., Ltd. Systems and methods for route planning

Also Published As

Publication number Publication date
CN112884837A (en) 2021-06-01

Similar Documents

Publication Publication Date Title
CN112884837B (en) Road positioning method, device, equipment and storage medium
CN112763995B (en) Radar calibration method and device, electronic equipment and road side equipment
CN112560680A (en) Lane line processing method and device, electronic device and storage medium
CN114036253B (en) High-precision map data processing method, device, electronic equipment and medium
CN114626169A (en) Traffic network optimization method, device, equipment, readable storage medium and product
CN114312843B (en) Method and device for determining information
CN114140759A (en) High-precision map lane line position determining method and device and automatic driving vehicle
CN115147680A (en) Pre-training method, device and equipment of target detection model
CN113219505B (en) Method, device and equipment for acquiring GPS coordinates for vehicle-road cooperative tunnel scene
CN112883236B (en) Map updating method and device, electronic equipment and storage medium
CN113029136A (en) Method, apparatus, storage medium, and program product for positioning information processing
CN116007638B (en) Vehicle track map matching method and device, electronic equipment and vehicle
CN114842305A (en) Depth prediction model training method, depth prediction method and related device
CN115792985A (en) Vehicle positioning method and device, electronic equipment, storage medium and vehicle
CN113139258B (en) Road data processing method, device, equipment and storage medium
CN113836661B (en) Time prediction method, model training method, related device and electronic equipment
CN115206102A (en) Method, apparatus, electronic device, and medium for determining traffic path
CN114170300A (en) High-precision map point cloud pose optimization method, device, equipment and medium
CN113970754A (en) Positioning method and device of autonomous travelable equipment
CN114158119B (en) Driving direction identification method and device, electronic equipment and medium
CN112507951B (en) Indicating lamp identification method, indicating lamp identification device, indicating lamp identification equipment, road side equipment and cloud control platform
CN113970773B (en) Positioning method and device and electronic equipment
CN116448105B (en) Pose updating method and device, electronic equipment and storage medium
CN115860077B (en) Method, device, equipment and storage medium for processing state data
CN114459494B (en) Method and device for acquiring reachable area, electronic equipment and storage 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
GR01 Patent grant
GR01 Patent grant