Road matching method, device, equipment and medium

Abstract

The invention discloses a road matching method and device, equipment and a medium, and relates to the technical field of intelligent traffic, and the method comprises the steps: executing an incremental updating mode if a vehicle driving state meets a preset track continuity judgment condition; the mode comprises the following steps: selecting first k cumulative state probabilities greater than a first probability threshold from cumulative state probabilities of a previous frame of vehicle in each candidate road, and updating transition probabilities related to the first k cumulative state probabilities in a state transition probability matrix; based on the first k cumulative state probabilities, the updated state transition probability matrix and the observation probabilities of the current frame vehicle positioning data obtained when the current frame vehicle is located on the candidate roads, determining the cumulative state probabilities of the current frame vehicle on the candidate roads; and selecting a final matched road according to the cumulative state probability of the continuous multi-frame vehicles in each candidate road. According to the method, unnecessary calculation is reduced, the real-time requirement is met, and the requirement for the performance of a memory and the performance of a processor is also reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent transportation, and particularly relates to a road matching method, device, equipment and medium. Background Technique

[0002] With the development of intelligent transportation systems, more and more vehicles are equipped with Beidou positioning devices, which can report the longitude and latitude information of vehicle driving trajectories in real time. By processing this longitude and latitude information, the vehicle driving trajectory can be accurately tracked, thus providing support for functions such as billing, dispatching, and path planning.

[0003] Current positioning technologies adopt a road matching algorithm based on the Hidden Markov Model (HMM). Although this algorithm performs well in matching accuracy, it has the problem of high computational complexity and is difficult to meet real-time requirements. Specifically, the existing HMM-based road matching algorithms mainly face the following challenges: First, the computational complexity is high, and this algorithm needs to perform complex probability calculations for all states; second, the real-time performance is insufficient and it cannot quickly process a large amount of real-time positioning data; third, the requirements for computing resources are high, and it has high requirements for memory and processor performance during operation. Summary of the Invention

[0004] In view of this, the purpose of the present invention is to provide a road matching method, device, equipment and medium, which reduces unnecessary calculations, meets real-time requirements, and also reduces the requirements for memory and processor performance. The specific solutions are as follows:

[0005] In a first aspect, the present application discloses a road matching method, including:

[0006] Determine a set of candidate roads corresponding to the current frame of vehicle positioning data, and determine whether the vehicle driving state meets a preset trajectory continuity judgment condition; the set of candidate roads includes multiple candidate roads;

[0007] If it is satisfied, an incremental update mode is executed; wherein, the incremental update mode includes: screening out the top k cumulative state probabilities greater than a first probability threshold from the cumulative state probabilities of the vehicle in each of the candidate roads in the previous frame, and updating the transition probabilities in the state transition probability matrix related to the top k cumulative state probabilities; where k is a positive integer, and the state transition probability matrix represents the probability of the vehicle transferring between different candidate roads in the front and rear frames;

[0008] Based on the top k cumulative state probabilities, the updated state transition probability matrix, and the observation probability of the current frame of vehicle positioning data obtained when the vehicle is in each of the candidate roads, determine the cumulative state probability of the vehicle in each of the candidate roads in the current frame;

[0009] Based on the cumulative state probabilities of the vehicle on each of the candidate roads in consecutive multiple frames, the final matching road is screened out from each of the candidate roads.

[0010] Optionally, the determining the set of candidate roads corresponding to the current frame vehicle positioning data includes:

[0011] Performing coordinate transformation on the current frame vehicle positioning data to obtain transformed data;

[0012] Determining a target search range according to the transformed data, and determining the roads within the target search range as the candidate roads in the set of candidate roads.

[0013] Optionally, the judging whether the vehicle driving state meets the preset trajectory continuity judgment condition includes:

[0014] If the difference between the vehicle speed vector of the current frame and the vehicle speed vector of the previous frame is less than a preset difference threshold, it is determined that the vehicle driving state meets the first trajectory continuity judgment condition;

[0015] By using a first sliding window to record the candidate road with the maximum cumulative state probability in each of the most recent M frames, if the number of times any candidate road is recorded is greater than a first number threshold, it is determined that the vehicle driving state meets the second trajectory continuity judgment condition; where M is a positive integer;

[0016] If the vehicle driving state meets the first trajectory continuity judgment condition and the second trajectory continuity judgment condition, it is determined that the vehicle driving state meets the preset trajectory continuity judgment condition.

[0017] Optionally, the screening out the final matching road from each of the candidate roads according to the cumulative state probabilities of the vehicle on each of the candidate roads in consecutive multiple frames includes:

[0018] By using a second sliding window to record the candidate road with the maximum cumulative state probability in each of the most recent N frames, if the number of times any candidate road is recorded is greater than a second number threshold, and the cumulative state probability of the any candidate road is greater than a second probability threshold, then the any candidate road is determined as the final matching road; where N is a positive integer.

[0019] Optionally, the road matching method further includes:

[0020] If it is detected that the cumulative state probability of the optimal candidate road in each of the most recent P frames shows a decreasing trend, or the projected distance between the current frame vehicle positioning data and the optimal candidate road is greater than a preset distance threshold, then switch to the global update mode; where the candidate road with the maximum cumulative state probability in each frame is the optimal candidate road for the corresponding frame; the global update mode includes:

[0021] Update all the transition probabilities in the state transition probability matrix, and based on the cumulative state probability of the vehicle being on each candidate road in the previous frame, the updated state transition probability matrix, and the observation probability of the current frame vehicle positioning data obtained when the vehicle is on each candidate road, determine the cumulative state probability of the vehicle being on each candidate road in the current frame.

[0022] Optionally, the road matching method further includes:

[0023] Calculate a target adjustment parameter according to the vehicle speed change amount, speed change sensitivity, positioning error compensation coefficient, and positioning accuracy standard deviation; where the speed change sensitivity is a first target value, the positioning error compensation coefficient is a second target value, and the positioning accuracy standard deviation is calculated based on the current frame vehicle positioning data;

[0024] Adjust the state transition parameter according to the target adjustment parameter; where the state transition parameter is used to calculate the state transition probability matrix.

[0025] Optionally, the calculating the target adjustment parameter according to the vehicle speed change amount, speed change sensitivity, positioning error compensation coefficient, and positioning accuracy standard deviation includes:

[0026] Use a target formula to calculate the target adjustment parameter according to the vehicle speed change amount, the speed change sensitivity, the positioning error compensation coefficient, and the positioning accuracy standard deviation;

[0027] Wherein, the target formula includes:

[0028] ;

[0029] Wherein, represents the calculated value of the target adjustment parameter, represents the initial value of the target adjustment parameter, represents the speed change sensitivity, represents the vehicle speed change amount, represents the maximum speed, represents the positioning error compensation coefficient, represents the positioning accuracy standard deviation, Represents the maximum standard deviation of positioning accuracy.

[0030] In a second aspect, the present application discloses a road matching device, including:

[0031] A candidate road determination module, configured to determine a set of candidate roads corresponding to the current frame of vehicle positioning data, and determine whether the vehicle driving state meets a preset trajectory continuity determination condition; the set of candidate roads includes multiple candidate roads;

[0032] An incremental update module, configured to perform an incremental update mode if the condition is met; wherein, the incremental update mode includes: screening out the top k cumulative state probabilities greater than a first probability threshold from the cumulative state probabilities of the vehicle in each of the candidate roads in the previous frame, and updating the transition probabilities in the state transition probability matrix related to the top k cumulative state probabilities; where k is a positive integer, and the state transition probability matrix represents the probability of the vehicle transferring between different candidate roads in the front and rear frames;

[0033] A probability calculation module, configured to determine the cumulative state probability of the current frame of vehicle in each of the candidate roads based on the top k cumulative state probabilities, the updated state transition probability matrix, and the observation probability of the current frame of vehicle positioning data obtained when the current frame of vehicle is in each of the candidate roads;

[0034] A road screening module, configured to screen out the final matching road from each of the candidate roads according to the cumulative state probabilities of the vehicle in each of the candidate roads in multiple consecutive frames.

[0035] In a third aspect, the present application discloses an electronic device, including:

[0036] A memory, configured to store a computer program;

[0037] A processor, configured to execute the computer program to implement the road matching method disclosed above.

[0038] In a fourth aspect, the present application discloses a computer-readable storage medium, configured to store a computer program; wherein, when the computer program is executed by a processor, the road matching method disclosed above is implemented.

[0039] It can be seen that the present application proposes a road matching method, including: determining a set of candidate roads corresponding to the current frame of vehicle positioning data, and determining whether the vehicle driving state meets a preset trajectory continuity determination condition; the set of candidate roads includes multiple candidate roads; if it is satisfied, an incremental update mode is executed; wherein, the incremental update mode includes: screening out the top k cumulative state probabilities greater than a first probability threshold from the cumulative state probabilities of the vehicle in each of the candidate roads in the previous frame, and updating the transition probabilities in the state transition probability matrix related to the top k cumulative state probabilities; where k is a positive integer, and the state transition probability matrix represents the probabilities of the vehicle transferring between different candidate roads in the previous and current frames; determining the cumulative state probabilities of the vehicle in each of the candidate roads in the current frame based on the top k cumulative state probabilities, the updated state transition probability matrix, and the observation probabilities of the current frame of vehicle positioning data obtained when the vehicle is in each of the candidate roads; screening out the final matching road from each of the candidate roads according to the cumulative state probabilities of the vehicle in each of the candidate roads in multiple consecutive frames. It can be seen that the present application first determines a set of candidate roads corresponding to the current frame of vehicle positioning data, thus narrowing the matching range and reducing unnecessary calculations. Further, after determining that the vehicle driving state meets the preset trajectory continuity determination condition, an incremental update mode is executed. In the incremental update mode, the top k cumulative state probabilities greater than the first probability threshold are screened out from the cumulative state probabilities of the vehicle in each candidate road in the previous frame, and only the transition probabilities in the state transition probability matrix related to these top k cumulative state probabilities are updated, avoiding complex probability calculations for all states, effectively reducing the computational complexity, improving the speed of processing vehicle positioning data, and meeting the real-time requirements. At the same time, since unnecessary calculations are reduced, the requirements of the present application for memory and processor performance are also reduced accordingly, thus effectively solving the problem of high requirements for computing resources. Description of the Drawings

[0040] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only the embodiments of the present invention, and those of ordinary skill in the art can also obtain other drawings according to the provided drawings without creative efforts.

[0041] Figure 1 Flowchart of a road matching method disclosed in the present application;

[0042] Figure 2 Flowchart of a specific road matching method disclosed in the present application;

[0043] Figure 3Schematic structural diagram of a road matching device disclosed in the present application;

[0044] Figure 4 Structural diagram of an electronic device disclosed in the present application. Detailed implementation manners

[0045] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0046] Current positioning technologies adopt a road matching algorithm based on the Hidden Markov Model (HMM). Although this algorithm performs well in terms of matching accuracy, it has the problem of high computational complexity and is difficult to meet the real-time requirements. Specifically, the existing HMM-based road matching algorithms mainly face the following challenges: First, the computational complexity is high, and this algorithm requires complex probability calculations for all states; second, the real-time performance is insufficient, and it cannot quickly process a large amount of real-time positioning data; third, the requirements for computing resources are high, and it has high requirements for memory and processor performance during operation.

[0047] Therefore, the embodiments of the present application propose a road matching solution, which reduces unnecessary calculations, meets the real-time requirements, and also reduces the requirements for memory and processor performance.

[0048] The embodiments of the present application disclose a road matching method. Refer to Figure 1 and Figure 2 as shown, the method includes:

[0049] Step S11: Determine a set of candidate roads corresponding to the current frame of vehicle positioning data, and determine whether the vehicle driving state meets a preset trajectory continuity judgment condition; the set of candidate roads includes multiple candidate roads.

[0050] Perform coordinate conversion on the current frame of vehicle positioning data to obtain the converted data, and determine the target search range according to the converted data, and determine the roads within the target search range as the candidate roads in the set of candidate roads. For example, convert the current frame of vehicle positioning data to the data in the WGS84 (World Geodetic System 1984) coordinate system to obtain the converted data, and based on the R-tree spatial technology, with the converted data as the origin, determine the roads within a radius of 100 meters as the candidate roads in the set of candidate roads.

[0051] In this embodiment, if the difference between the vehicle speed vector of the current frame and the vehicle speed vector of the previous frame is less than a preset difference threshold, it is determined that the vehicle driving state meets the first trajectory continuity judgment condition; the first sliding window is used to record the candidate road with the maximum cumulative state probability in each of the most recent M frames. If the number of times any candidate road is recorded is greater than the first number threshold, it is determined that the vehicle driving state meets the second trajectory continuity judgment condition; where M is a positive integer; if the vehicle driving state simultaneously meets the first trajectory continuity judgment condition and the second trajectory continuity judgment condition, it is determined that the vehicle driving state meets the preset trajectory continuity judgment condition. For example, if , it is determined that the vehicle driving state meets the first trajectory continuity judgment condition, is the difference between the vehicle speed vector of the previous frame and the vehicle speed vector of the previous previous frame, is the speed change sensitivity, which can take a value of 0.15, is the maximum speed, is the preset difference threshold. By verifying whether the vehicle driving state meets the first trajectory continuity judgment condition, it can be determined whether the vehicle driving state meets the speed vector consistency. For example, M can be 3, and the first number threshold can be 2. The first sliding window is used to record the candidate road with the maximum cumulative state probability in each of the most recent 3 frames. If the number of times any candidate road is recorded is greater than 2, it is determined that the vehicle driving state meets the second trajectory continuity judgment condition. By verifying whether the vehicle driving state meets the second trajectory continuity judgment condition, it can be determined whether the vehicle driving state meets the time continuity. If the vehicle driving state meets the first trajectory continuity judgment condition and the second trajectory continuity judgment condition, it is determined that the vehicle driving state meets the preset trajectory continuity judgment condition.

[0052] Step S12: If satisfied, execute the incremental update mode; where the incremental update mode includes: screening out the top k cumulative state probabilities greater than the first probability threshold from the cumulative state probabilities of the vehicle on each candidate road in the previous frame, and updating the transition probabilities in the state transition probability matrix related to the top k cumulative state probabilities; where k is a positive integer, and the state transition probability matrix represents the probability of the vehicle transferring between different candidate roads in the front and back frames.

[0053] In this embodiment, the calculation formula of the state transition probability is:

[0054] ;

[0055] represents the connected length from road i to j, represents the road steering angle difference, and the value range is [-π, π], represents the instantaneous speed of the vehicle, which is obtained through in-vehicle sensors. represents the positioning data time interval, and the typical value is 1 second. represents the continuity weight, which is determined by training with historical data and can take the value of 0.7. represents the steering angle penalty coefficient, which can take the value of 0.5. represents the exponential function with the natural constant e as the base.

[0056] In this embodiment, k can be 5, that is, from the cumulative state probabilities of the vehicle being in each of the candidate roads in the previous frame, the top 5 cumulative state probabilities greater than the first probability threshold are selected, and in the state transition probability matrix, the transition probabilities related to the top 5 cumulative state probabilities (about 30% of the transition probabilities are updated); it can be understood that the state transition probability matrix represents the probabilities of the vehicle transferring between different candidate roads in the front and rear frames.

[0057] Step S13: Based on the top k cumulative state probabilities, the updated state transition probability matrix, and the observation probabilities of the current frame vehicle positioning data obtained when the current frame vehicle is in each of the candidate roads, determine the cumulative state probabilities of the current frame vehicle being in each of the candidate roads.

[0058] In this embodiment, the calculation formula for the cumulative state probability is:

[0059] ;

[0060] where k = 5, ;

[0061] where, represents the cumulative state probabilities of the current frame vehicle being in each of the candidate roads, represents the cumulative state probabilities of the previous frame vehicle being in each of the candidate roads, represents the observation probabilities of the current frame vehicle positioning data obtained when the current frame vehicle is in each of the candidate roads.

[0062] where, the calculation formula for the observation probability is:

[0063] ;

[0064] represents the projected distance of the i-th candidate road, represents the standard deviation of the positioning error of this road.

[0065] Step S14: According to the cumulative state probabilities of the vehicle being in each of the candidate roads in multiple consecutive frames, screen out the final matching road from each of the candidate roads.

[0066] In this embodiment, the second sliding window is used to record the candidate road with the largest cumulative state probability in each of the most recent N frames. If the number of times any candidate road is recorded is greater than the second threshold number, and the cumulative state probability of any candidate road is greater than the second probability threshold, then any candidate road is determined as the final matching road; where N is a positive integer. For example, N is 3, the second threshold number is 2, and the second sliding window is used to record the candidate road with the largest cumulative state probability in each of the most recent 3 frames. If the number of times any candidate road is recorded is greater than 2 times, and the cumulative state probability of any candidate road is greater than the second probability threshold, then any candidate road is determined as the final matching road.

[0067] Furthermore, if it is detected that in the most recent P frames, the cumulative state probabilities of the optimal candidate roads in each frame show a decreasing trend, or the projected distance between the vehicle positioning data of the current frame and the optimal candidate road is greater than the preset distance threshold, then the global update mode is switched; where the candidate road with the largest cumulative state probability in each frame is the optimal candidate road for the corresponding frame; the global update mode includes: reselecting the candidate road set, updating all the transition probabilities in the state transition probability matrix, and determining the cumulative state probabilities of the vehicle in each candidate road in the current frame based on the cumulative state probabilities of the vehicle in each candidate road in the previous frame, the updated state transition probability matrix, and the observation probability of the vehicle positioning data of the current frame obtained when the vehicle is in each candidate road. For example, P is 3. If it is detected that in the most recent 3 frames, the cumulative state probabilities of the optimal candidate roads in each frame show a decreasing trend, or the road nodes or sections matched by the vehicle positioning data in consecutive time frames show an unreasonable long-distance jump in the road network topology, such as the topological distance jump > 500 meters, or the projected distance between the vehicle positioning data of the current frame and the optimal candidate road is greater than the preset distance threshold, or the speed vector difference > 45°, then the global update mode is switched.

[0068] Furthermore, if the vehicle driving state does not meet the preset trajectory continuity judgment condition, then the global update mode is directly executed. The proposed hybrid decision-making mechanism in this application significantly improves the calculation efficiency while ensuring the path matching accuracy by intelligently switching between the incremental update and global update modes.

[0069] Furthermore, using the target formula, the target adjustment parameter is calculated according to the vehicle speed change amount, speed change sensitivity, positioning error compensation coefficient, and positioning accuracy standard deviation; where the speed change sensitivity is the first target value, the positioning error compensation coefficient is the second target value, and the positioning accuracy standard deviation is calculated based on the vehicle positioning data of the current frame; the state transition parameter is adjusted according to the target adjustment parameter; where the state transition parameter is used to calculate the state transition probability matrix. Among them, the target formula includes:

[0070] ;

[0071] wherein, represents the calculated value of the target adjustment parameter, represents the initial value of the target adjustment parameter, represents the speed change sensitivity, represents the vehicle speed change amount, represents the maximum speed, represents the positioning error compensation coefficient, represents the standard deviation of the positioning accuracy, represents the maximum value of the standard deviation of the positioning accuracy. It should be noted that replaces in the state transition probability calculation formula, and indirectly controls the recursion depth by dynamically adjusting the parameters in the state transition formula. The recursion depth refers to the number of historical states that the algorithm backtracks when calculating the current state.

[0072] This application realizes road matching calculation through a three - level computing engine. Specifically, the three - level computing engine specifically includes a pre - processing layer, an HMM layer, and an incremental optimization layer. The pre - processing layer is used to implement coordinate conversion and preliminary road screening based on the R - tree space technology. The HMM core layer is used to calculate the state probability and observation probability in parallel. The incremental optimization layer is used to implement dynamic pruning and confidence verification. It should be noted that dynamic pruning means only retaining the top 5 high - probability road states per frame, that is, in the calculation process of the hidden Markov model (HMM), by dynamically eliminating low - probability candidate road states, thereby significantly reducing memory occupancy and reducing the optimization method of computational complexity. Confidence verification means adopting a sliding window mechanism, that is, by using the second sliding window to record the candidate road with the largest cumulative state probability in each of the last 3 frames. If the number of times any candidate road is recorded is greater than 2 times, and the cumulative state probability of any candidate road is greater than the second probability threshold, then any candidate road is determined as the final matching road.

[0073] Compared with the traditional technology, this application has the following advantages, as shown in Table 1:

[0074] Table 1

[0075]

[0076] By applying this application in different scenarios, the achievable accuracy rate is shown in Table 2,

[0077] Table 2

[0078]

[0079] It can be seen that the present application proposes a road matching method, including: determining a set of candidate roads corresponding to the current frame of vehicle positioning data, and determining whether the vehicle driving state meets a preset trajectory continuity judgment condition; the set of candidate roads includes multiple candidate roads; if it is satisfied, an incremental update mode is executed; wherein, the incremental update mode includes: screening out the top k cumulative state probabilities greater than a first probability threshold from the cumulative state probabilities of the vehicle in each of the candidate roads in the previous frame, and updating the transition probabilities in the state transition probability matrix that are related to the top k cumulative state probabilities; where k is a positive integer, and the state transition probability matrix represents the probabilities of the vehicle transferring between different candidate roads in the previous and current frames; determining the cumulative state probabilities of the vehicle in each of the candidate roads in the current frame based on the top k cumulative state probabilities, the updated state transition probability matrix, and the observation probabilities of the current frame of vehicle positioning data obtained when the vehicle is in each of the candidate roads; screening out the final matching road from each of the candidate roads according to the cumulative state probabilities of the vehicle in each of the candidate roads in multiple consecutive frames. It can be seen that the present application first determines a set of candidate roads corresponding to the current frame of vehicle positioning data, thus narrowing the matching range and reducing unnecessary calculations. Further, after determining that the vehicle driving state meets the preset trajectory continuity judgment condition, an incremental update mode is executed. In the incremental update mode, the top k cumulative state probabilities greater than the first probability threshold are screened out from the cumulative state probabilities of the vehicle in each candidate road in the previous frame, and only the transition probabilities in the state transition probability matrix that are related to these top k cumulative state probabilities are updated, avoiding complex probability calculations for all states, effectively reducing the computational complexity, improving the speed of processing vehicle positioning data, and meeting the real-time requirements. At the same time, since unnecessary calculations are reduced, the requirements of the present application for memory and processor performance are also reduced accordingly. In this way, the problem of high requirements for computing resources is effectively solved.

[0080] Correspondingly, an embodiment of the present application also discloses a road matching device, as shown in Figure 3 The device includes:

[0081] A candidate road determination module 11, configured to determine a set of candidate roads corresponding to the current frame of vehicle positioning data, and determine whether the vehicle driving state meets a preset trajectory continuity judgment condition; the set of candidate roads includes multiple candidate roads;

[0082] An incremental update module 12, configured to execute an incremental update mode if the condition is met; wherein, the incremental update mode includes: screening out the top k cumulative state probabilities greater than a first probability threshold from the cumulative state probabilities of the vehicle on each of the candidate roads in the previous frame, and updating the transition probabilities in the state transition probability matrix that are related to the top k cumulative state probabilities; wherein, k is a positive integer, and the state transition probability matrix represents the probabilities of the vehicle transferring between different candidate roads in consecutive frames.

[0083] A probability calculation module 13, configured to determine the cumulative state probabilities of the current frame vehicle on each of the candidate roads based on the top k cumulative state probabilities, the updated state transition probability matrix, and the observation probabilities of the current frame vehicle positioning data obtained when the current frame vehicle is on each of the candidate roads.

[0084] A road screening module 14, configured to screen out the final matching road from each of the candidate roads according to the cumulative state probabilities of the vehicle on each of the candidate roads in multiple consecutive frames. For the more specific working processes of the above respective modules, reference may be made to the corresponding content disclosed in the foregoing embodiments, and details thereof will not be elaborated herein.

[0085] It can be seen that the present application proposes a road matching method, including: determining a set of candidate roads corresponding to the current frame of vehicle positioning data, and determining whether the vehicle driving state meets a preset trajectory continuity judgment condition; the set of candidate roads includes multiple candidate roads; if it is satisfied, an incremental update mode is executed; wherein, the incremental update mode includes: screening out the top k cumulative state probabilities greater than a first probability threshold from the cumulative state probabilities of the vehicle in each of the candidate roads in the previous frame, and updating the transition probabilities in the state transition probability matrix related to the top k cumulative state probabilities; wherein, k is a positive integer, and the state transition probability matrix represents the probabilities of the vehicle transferring between different candidate roads in the front and rear frames; determining the cumulative state probabilities of the vehicle in each of the candidate roads in the current frame based on the top k cumulative state probabilities, the updated state transition probability matrix, and the observation probabilities of the current frame of vehicle positioning data obtained when the vehicle is in each of the candidate roads in the current frame; screening out the final matching road from each of the candidate roads according to the cumulative state probabilities of the vehicle in each of the candidate roads in multiple consecutive frames. It can be seen that the present application first determines a set of candidate roads corresponding to the current frame of vehicle positioning data, thus narrowing the matching range and reducing unnecessary calculations. Further, after determining that the vehicle driving state meets the preset trajectory continuity judgment condition, an incremental update mode is executed. In the incremental update mode, the top k cumulative state probabilities greater than the first probability threshold are screened out from the cumulative state probabilities of the vehicle in each candidate road in the previous frame, and only the transition probabilities related to these top k cumulative state probabilities in the state transition probability matrix are updated, avoiding complex probability calculations for all states, effectively reducing the computational complexity, improving the speed of processing vehicle positioning data, and meeting the real-time requirements. At the same time, since unnecessary calculations are reduced, the requirements of the present application for memory and processor performance are also reduced accordingly, thus effectively solving the problem of high requirements for computing resources.

[0086] Furthermore, an embodiment of the present application also provides an electronic device. Figure 4 It is a structural diagram of an electronic device 20 shown according to an exemplary embodiment, and the content in the figure should not be considered as any limitation to the scope of use of the present application.

[0087] Figure 4 It is a structural schematic diagram of an electronic device 20 provided by an embodiment of the present application. The electronic device 20 may specifically include: at least one processor 21, at least one memory 22, a display screen 23, an input / output interface 24, a communication interface 25, a power supply 26, and a communication bus 27. Among them, the memory 22 is used to store a computer program, and the computer program is loaded and executed by the processor 21 to implement the relevant steps in the road matching method disclosed in any of the foregoing embodiments. In addition, the electronic device 20 in this embodiment may specifically be an electronic computer.

[0088] In this embodiment, the power supply 26 is used to provide operating voltages for each hardware device on the electronic device 20; the communication interface 25 can create a data transmission channel between the electronic device 20 and external devices, and the communication protocol it follows can be any communication protocol applicable to the technical solution of this application, and specific limitations are not imposed here; the input / output interface 24 is used to obtain external input data or output data to the outside, and its specific interface type can be selected according to specific application requirements, and specific limitations are not imposed here.

[0089] In addition, the memory 22, as a carrier for resource storage, can be a read-only memory, a random access memory, a magnetic disk, an optical disk, etc., and the resources stored thereon can include a computer program 221, and the storage method can be transient storage or permanent storage. Among them, in addition to the computer program that can be used to complete the road matching method executed by the electronic device 20 disclosed in any of the foregoing embodiments, the computer program 221 can further include computer programs that can be used to complete other specific tasks.

[0090] Furthermore, an embodiment of this application also discloses a computer-readable storage medium for storing a computer program; wherein, when the computer program is executed by a processor, the road matching method disclosed above is implemented.

[0091] For the specific steps of this method, reference can be made to the corresponding content disclosed in the foregoing embodiments, and details will not be repeated here.

[0092] The various embodiments in this application book are described in a progressive manner. Each embodiment focuses on the differences from other embodiments. For the same or similar parts between the various embodiments, reference can be made to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and reference can be made to the description in the method part for the relevant parts.

[0093] Those skilled in the art can further realize that the units and algorithm steps of each example described in combination with the embodiments disclosed in this article can be implemented by electronic hardware, computer software, or a combination of the two. To clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described according to functions in the above description. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of this application.

[0094] The steps of the methods or algorithms described in combination with the embodiments disclosed in this article can be implemented directly by hardware, software modules executed by a processor, or a combination of both. The software modules can be placed in a random access memory (RAM), internal memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium well-known in the technical field.

[0095] Finally, it should also be noted that in this article, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements not only includes those elements, but also includes other elements not expressly listed, or also includes elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "comprising an..." does not exclude the existence of additional identical elements in the process, method, article or device comprising the element.

[0096] The above has introduced in detail a road matching method, device, equipment, and storage medium provided by this application. Specific examples are used in this article to elaborate on the principle and implementation manner of this application. The description of the above embodiments is only used to help understand the method and its core idea of this application; at the same time, for those of ordinary skill in the art, according to the idea of this application, there will be changes in the specific implementation manner and application scope. In summary, the content of this specification should not be construed as a limitation to this application.

Claims

1. A road matching method, characterized in that, Including: Determine a set of candidate roads corresponding to the vehicle positioning data of the current frame, and determine whether the vehicle driving state meets the preset trajectory continuity judgment condition; The set of candidate roads includes multiple candidate roads; If it is satisfied, an incremental update mode is executed; wherein, the incremental update mode includes: screening out the top k cumulative state probabilities greater than the first probability threshold from the cumulative state probabilities of the vehicle in each of the candidate roads in the previous frame, and in the state transition probability matrix, updating the transition probabilities related to the top k cumulative state probabilities; wherein, k is a positive integer, and the state transition probability matrix represents the probability of the vehicle transferring between different candidate roads in the front and rear frames; Based on the top k cumulative state probabilities, the updated state transition probability matrix, and the observation probability of the vehicle positioning data obtained when the vehicle is in each of the candidate roads in the current frame, determine the cumulative state probability of the vehicle in each of the candidate roads in the current frame; According to the cumulative state probabilities of the vehicle in each of the candidate roads in multiple consecutive frames, screen out the final matching road from each of the candidate roads.

2. The road matching method according to claim 1, wherein The determining the set of candidate roads corresponding to the vehicle positioning data of the current frame includes: Perform coordinate transformation on the vehicle positioning data of the current frame to obtain transformed data; Determine a target search range according to the transformed data, and determine the roads within the target search range as the candidate roads in the set of candidate roads.

3. The road matching method according to claim 1, wherein The determining whether the vehicle driving state meets the preset trajectory continuity judgment condition includes: If the difference between the vehicle speed vector of the current frame and the vehicle speed vector of the previous frame is less than the preset difference threshold, it is determined that the vehicle driving state meets the first trajectory continuity judgment condition; Record the candidate road with the largest cumulative state probability in each of the most recent M frames through a first sliding window. If the number of times any candidate road is recorded is greater than the first number threshold, it is determined that the vehicle driving state meets the second trajectory continuity judgment condition; wherein, M is a positive integer; If the vehicle driving state meets the first trajectory continuity judgment condition and the second trajectory continuity judgment condition, it is determined that the vehicle driving state meets the preset trajectory continuity judgment condition.

4. The road matching method according to claim 3, characterized in that The screening out the final matching road from each of the candidate roads according to the cumulative state probabilities of the vehicle in each of the candidate roads in multiple consecutive frames includes: Record the candidate road with the largest cumulative state probability in each of the most recent N frames through a second sliding window. If the number of times any candidate road is recorded is greater than the second number threshold, and the cumulative state probability of the any candidate road is greater than the second probability threshold, then determine the any candidate road as the final matching road; wherein, N is a positive integer.

5. The road matching method according to claim 4, wherein Also including: If it is detected that the cumulative state probability of the optimal candidate road in each of the most recent P frames shows a decreasing trend, or the projected distance between the current frame vehicle positioning data and the optimal candidate road is greater than a preset distance threshold, then switch to the global update mode; where, the candidate road with the largest cumulative state probability in each frame is the optimal candidate road for the corresponding frame; the global update mode includes: Update all the transition probabilities in the state transition probability matrix, and based on the cumulative state probability of the vehicle being in each candidate road in the previous frame, the updated state transition probability matrix, and the observation probability of the current frame vehicle positioning data obtained when the vehicle is in each candidate road, determine the cumulative state probability of the vehicle being in each candidate road in the current frame.

6. The road matching method according to any one of claims 1 to 5, characterized in that It also includes: Calculate a target adjustment parameter according to the vehicle speed change amount, speed change sensitivity, positioning error compensation coefficient, and positioning accuracy standard deviation; where, the speed change sensitivity is a first target value, the positioning error compensation coefficient is a second target value, and the positioning accuracy standard deviation is calculated based on the current frame vehicle positioning data; Adjust the state transition parameter according to the target adjustment parameter; where, the state transition parameter is used to calculate the state transition probability matrix.

7. The road matching method according to claim 6, wherein The calculating a target adjustment parameter according to the vehicle speed change amount, speed change sensitivity, positioning error compensation coefficient, and positioning accuracy standard deviation includes: Use a target formula to calculate the target adjustment parameter according to the vehicle speed change amount, the speed change sensitivity, the positioning error compensation coefficient, and the positioning accuracy standard deviation; Where, the target formula includes: ； Wherein, represents the calculated value of the target adjustment parameter, represents the initial value of the target adjustment parameter, represents the speed change sensitivity, represents the vehicle speed change amount, represents the maximum speed, represents the positioning error compensation coefficient, represents the standard deviation of the positioning accuracy, represents the maximum value of the standard deviation of the positioning accuracy.

8. A road matching device, characterized in that, It includes: A candidate road determination module, configured to determine a set of candidate roads corresponding to the current frame vehicle positioning data, and determine whether the vehicle driving state meets a preset trajectory continuity determination condition; the set of candidate roads includes multiple candidate roads; An incremental update module, configured to, if it is satisfied, execute an incremental update mode; where, the incremental update mode includes: screening out the top k cumulative state probabilities greater than a first probability threshold from the cumulative state probabilities of the vehicle being in each candidate road in the previous frame, and updating the transition probabilities in the state transition probability matrix related to the top k cumulative state probabilities; where, k is a positive integer, and the state transition probability matrix represents the probability of the vehicle transferring between different candidate roads in the front and rear frames; A probability calculation module, configured to determine the cumulative state probability of the vehicle being in each candidate road in the current frame based on the top k cumulative state probabilities, the updated state transition probability matrix, and the observation probability of the current frame vehicle positioning data obtained when the vehicle is in each candidate road in the current frame; A road screening module, configured to screen out the final matching road from each candidate road according to the cumulative state probabilities of the vehicle being in each candidate road in multiple consecutive frames.

9. An electronic device, characterized in that, It includes: A memory, configured to store a computer program; A processor, configured to execute the computer program to implement the road matching method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, For storing a computer program; wherein, when the computer program is executed by a processor, it implements the road matching method according to any one of claims 1 to 7.

Images