CN117475639B

CN117475639B - Bridge vehicle space-time distribution identification method integrating vehicle positioning data of different frequencies

Info

Publication number: CN117475639B
Application number: CN202311799613.1A
Authority: CN
Inventors: 孙超; 覃金庆; 杨宇星; 安茹; 陈振武
Original assignee: Shenzhen Urban Transport Planning Center Co Ltd
Current assignee: Shenzhen Urban Transport Planning Center Co Ltd
Priority date: 2023-12-26
Filing date: 2023-12-26
Publication date: 2024-04-30
Anticipated expiration: 2043-12-26
Also published as: CN117475639A

Abstract

The invention discloses a bridge vehicle space-time distribution identification method integrating vehicle positioning data with different frequencies, and belongs to the technical field of bridge vehicle space-time distribution identification. The method solves the problem that the traditional bridge vehicle space-time distribution identification method in the prior art is difficult to accurately identify the vehicle track under the condition that the vehicle positioning data track is sparse; according to the method, firstly, road section level positioning and bridge road section matching are carried out, and then, the positioning of a lane level in a single row of direction of a bridge is matched with a bridge lane, so that the vehicle space-time distribution of each bridge of a bridge group is obtained; the multi-mode vehicle lane change probability calculation model is constructed to match the road section lanes, so that whether the vehicle changes lanes or not and the possibility of changing lanes to other lanes can be effectively evaluated, and the optimal matching result of the vehicle positioning points and the road section lanes can be obtained according to the vehicle lane change constraint and the vehicle position constraint. The invention can realize high-precision recognition of the space-time distribution of vehicles of the urban large-scale bridge group and can be applied to recognition of the vehicle distribution of the bridge.

Description

Bridge vehicle space-time distribution identification method integrating vehicle positioning data of different frequencies

Technical Field

The invention relates to a method for identifying space-time distribution of bridge vehicles, in particular to a method for identifying space-time distribution of bridge vehicles by fusing vehicle positioning data with different frequencies, and belongs to the technical field of space-time distribution identification of bridge vehicles.

Background

The purpose of the space-time distribution of the bridge is to acquire the positions of all vehicles on the bridge at different moments, the space-time distribution of the bridge is influenced by travel demands, environments, traffic control and the boundaries of the bridge, the vehicles passing on the bridge have large uncertainty, and the space-time distribution of the bridge has important significance in the aspects of performance evaluation, residual service life prediction, durability analysis, maintenance and the like of the in-service bridge.

At present, the space-time distribution recognition technology of bridge vehicles mainly comprises the following two types: the method comprises the steps of obtaining information such as speed and locomotive spacing when a vehicle gets on a bridge through a charging system or a dynamic weighing system, obtaining a bridge deck vehicle probability distribution model through a statistical analysis method, and further obtaining space-time distribution of the bridge, wherein the statistical analysis is only performed for bridge deck distribution of a single bridge, and meanwhile, the obtained space-time distribution and actual distribution of the vehicle have large errors, high cost, time consumption and complex operation; the other is to identify the vehicle distribution at different positions by installing a plurality of cameras, radars and other devices on the bridge, and combine the same vehicle feature identification to obtain the space-time distribution of each vehicle on the bridge deck, but the cost is high, the time consumption is high, the operation is complex, and the vehicles are difficult to identify at night.

In the prior art, a patent document with the publication (bulletin) number of CN111709332B discloses a vehicle load space-time distribution method based on space-time distribution recognition of vehicles with multiple cameras, the method comprises the steps of installing multiple cameras at different positions on a bridge, acquiring images on the bridge from multiple directions, outputting video images with time labels, obtaining multi-channel characteristics of the vehicles on the bridge by using a dense neural network, analyzing all data and characteristics of the vehicles under the different cameras at the same moment to obtain the vehicle distribution situation on the bridge at any time, wherein the method is required to install multiple cameras on the bridge, needs a video recognition algorithm for recognition, has high operation difficulty, high cost and high calculation power requirement, and meanwhile does not consider the situations of vehicle lane changing, vehicle following and the like, and has errors with the actual vehicle distribution; the patent document with the publication number of CN105261212B discloses a travel time-space analysis method based on taxi positioning data map matching, a taxi positioning error accumulation distribution form is established, a secondary buffer area searching method is established, taxi travel data is extracted, taxi positioning data direction elements and distance elements are fused, a map matching method is established, positioning points are matched on a road section, travel time-space distribution characteristics are analyzed by using the matched taxi positioning data, the travel time-space distribution characteristics are identified by adopting the positioning data, equipment is not required to be installed, the operation is simple and convenient, the cost is low, all-weather uninterrupted identification can be realized, the matching results of the positioning data are not ordered according to priority, and the obtained information such as speed, time, vehicle type and position of a vehicle can be different from the actual information.

In view of the above, there is a need for a vehicle space-time distribution recognition method for bridge vehicle positioning data that is more accurate in recognition and does not require additional equipment.

Disclosure of Invention

The following presents a simplified summary of the invention in order to provide a basic understanding of some aspects of the invention. It should be understood that this summary is not an exhaustive overview of the invention. It is not intended to identify key or critical elements of the invention or to delineate the scope of the invention. Its purpose is to present some concepts in a simplified form as a prelude to the more detailed description that is discussed later.

In view of the above, the invention provides a method for identifying the space-time distribution of the bridge vehicles, which is used for fusing the vehicle positioning data with different frequencies, in order to solve the problem that the traditional method for identifying the space-time distribution of the bridge vehicles in the prior art is difficult to accurately identify the vehicle track under the condition that the vehicle positioning data track is sparse.

The technical proposal is as follows: the bridge vehicle space-time distribution identification method integrating the vehicle positioning data with different frequencies comprises the following steps:

S1, performing GIS topological network matching on a vehicle based on vehicle positioning data to obtain vehicle track data;

s11, selecting a monitoring area, and extracting and collecting vehicle positioning data;

Specific: the vehicle positioning data comprise vehicle length, vehicle type, license plate number, time, running speed and longitude and latitude coordinates;

s12, preprocessing vehicle positioning data, and collecting GIS topological network section information of a road network;

S13, acquiring bridge group information, and matching vehicle positioning data with GIS topological network section information;

s14, acquiring vehicle positioning data matched with each bridge road section in the bridge group according to the GIS topological network road section information to form vehicle track data;

S2, constructing a vehicle multi-mode lane change probability model according to the vehicle positioning data, constructing an optimized matching model according to the matching priority, and acquiring a matching result of the vehicle positioning data of the road section where each bridge line is located;

s21, selecting road section vehicle positioning data in the bridge traveling direction, and constructing a GIS topological network of the road section lane level in the bridge traveling direction;

s22, determining matching priorities according to sampling frequencies, constructing vehicle positioning sequence sets with different matching priorities for road section vehicle positioning data where bridge lines are located, and calculating the probability scores of the vehicle positioning data points matching each lane;

S23, fitting by adopting a Gaussian distribution model, identifying the possibility of lane change of the vehicle, calculating the probability of lane change of the vehicle, and constructing a multi-mode lane change probability model of the vehicle;

S24, constructing an optimized matching model based on the vehicle positioning data of the matching priority and the road section lane where the bridge is located according to the constraint condition 1 and the constraint condition 2;

s25, carrying out lane matching on each vehicle positioning according to different priorities, solving vehicle positioning point matching results with different sampling frequencies by adopting an optimized matching model, and integrating to obtain a point set for vehicle track correction;

S26, carrying out lane matching on the vehicle positioning data of the road section where each bridge row of each bridge in the bridge group is located, and obtaining a matching result of the vehicle positioning data of the road section where each bridge row is located;

s3, acquiring space-time distribution of bridge deck vehicles based on a bridge group lane-level road network simulation model;

S31, constructing a bridge group lane-level road network simulation model based on bridge design parameters and a microscopic traffic simulation model;

S32, acquiring a matching result of each vehicle positioning data and each lane of the GIS road network topology on a road section where a bridge group is located by adopting a positioning point optimal matching model based on a matching priority, calculating the time and speed of a single vehicle entering the bridge, and correcting the position conflict of the vehicle;

S33, extracting a bridge deck vehicle driving path according to a matching result, and setting simulation model parameters in a bridge lane level road network simulation model;

S34, running a lane-level road network simulation model to obtain vehicle space-time distribution, respectively simulating each bridge of the bridge group, and integrating the vehicle space-time distribution of all bridges of the bridge group to obtain bridge deck vehicle space-time distribution.

Further, in the step S12, the preprocessing of the vehicle positioning data includes missing value processing, error data processing and time sequencing processing, and the GIS topology network road section information includes a road section name, a road section id, a road section road class, a road section lane number and a road section lane direction;

in S13, selecting a bridge group according to the selected area, wherein the bridge group is expressed as ，/>Wherein/>For bridge line,/>For the number of bridges, matching the bridge group with GIS topological network road section information to obtain road sections matched with the bridge group, wherein the road section set matched with the GIS topological network by the bridge group is expressed as/>，/>Matching the vehicle positioning data with the information of each road section in the GIS topological network by adopting a hidden Markov model to obtain the road section matched with the vehicle positioning data, and obtaining the vehicle/>Road segment set of vehicle positioning data matched with road network GIS topology, namely vehicle/>Is expressed as/>，/>Wherein/>For the number of road segments traversed by the vehicle, the road segment set with the vehicle positioning data matched with the GIS topological network, namely the complete vehicle track is expressed as/>，Wherein/>Is the number of vehicles;

in S14, the bridge group is matched with the GIS topological network according to the road segment id Road segment set/>, matched with vehicle positioning data and GIS topological networkAnd matching to obtain the vehicle track of the road section where each bridge row of the bridge in the bridge group is located.

Further, in S21, vehicle positioning data of the road section where each bridge line of the bridge group is located is obtained, and a GIS road network topology is constructed according to the number of lanes, the length of lanes and GIS data of the road section where each bridge line is located, where the entrance of the road section where the bridge line is located is a starting point and the exit of the road section where the bridge line is located is an ending point;

in S22, for the vehicle positioning data of the road section where the single bridge line in the bridge group is located, the vehicle positioning data are ordered from high to low according to the sampling frequency, and a vehicle positioning sequence set with different matching priorities is constructed ，，/>The number of vehicles passing through the bridge in the single bridge traveling direction is the number of vehicles passing through the bridge in the single bridge traveling direction;

Using Gaussian distribution function to evaluate possibility of vehicle positioning points in each lane, wherein the lane set of the road section where the bridge is positioned is ，/>Wherein/>Calculating the shortest distance from a vehicle positioning point to a GIS road network topology of each lane and the probability score of the vehicle positioning point in each lane in the same lane driving process for the number of lanes of the road section where the bridge is positioned;

positioning point for vehicle In lane/>Probability score/>Expressed as:

；

Wherein, Is Gaussian model parameter, which is obtained by adopting a moment estimation parameter estimation method based on historical data,；

Positioning point for vehicleWith lane/>Shortest distance/>, of corresponding GIS road network topologyExpressed as:

；

Wherein, For lane/>Corresponding GIS road network topologically and vehicle locating point/>Projection coordinates of points forming the shortest distance,/>For the locating point/>, of the vehicleIs defined by the projection coordinates of (a);

In the step S23, according to the characteristic that the larger the angle difference between the vehicle track formed by the vehicle positioning points and the lane line shape is, the smaller the possibility of vehicle lane change is, fitting is performed by adopting a gaussian distribution model, and the possibility of vehicle lane change is identified;

positioning point for vehicle In lane/>Possibility of not changing lanes at the time of up/>Expressed as:

；

Current vehicle positioning point Vector and lane/>, formed with last vehicle anchor pointAngle of line/>Expressed as:

；

Wherein, For the locating point/>, of the vehicleProjection coordinates of the last point of (3)/>Locating point for vehicleProjection coordinates/>On the current lane GIS road network topology and vehicle locating point/>The point at which the shortest distance is made,For the locating point/>, of the vehicleProjection coordinates/>, of the last point of (c)On the current lane GIS road network topology and vehicle locating point/>Point forming shortest distance,/>As model parameters, performing parameter estimation and acquisition by adopting a moment estimation method according to historical data;

calculating the lane change probability of the vehicle according to the fact that the larger the distance between different lanes is, the smaller the possibility of lane change of the vehicle is;

Vehicle secondary lane Change to lane/>Probability/>Expressed as:

；

Wherein, For lane/>With lane/>Is a distance of (2);

integration is carried out to obtain a multi-mode lane change probability model of each vehicle positioning point in the vehicle positioning data ；

；

Wherein,When the vehicle is not changing lanes,/>When the vehicle changes lanes;

In the step S24, each vehicle positioning data point is matched with a lane, and a global optimal matching model of the vehicle positioning data and the lane of the road section where the bridge is located is established by taking the maximum sum of the probability score of each lane positioning point in the lane and the product of the vehicle lane change probability in the vehicle driving process as a target;

optimal matching model of vehicle positioning data and road section lane where bridge is located Expressed as:

；

Wherein, For vehicles in lanes/>Possibility of/(v)For vehicles from lanes/>Change to lane/>Probability of/>For the number of locating points of the vehicle on the road section of the bridge,/>The vehicle positioning point is the vehicle positioning point;

Constraint condition 1 is lane change constraint, the lane change of the vehicle is constrained in the matching process, and whether the number of lanes of the bridge is met or not is judged according to each lane change direction of each lane of the bridge, so that lanes are obtained By changing the direction of the channel/>Lane/>, where vehicle is located after lane changeIf lane change direction/>, is adoptedAfter lane change, the bridge does not have a corresponding lane, and the lane is expressed as 0;

Lane change constraints can be expressed as:

；

Constraint condition 2 is vehicle position constraint, constraint is carried out on vehicle position conflict at the same moment, each vehicle positioning data of a road section where a bridge is located is matched according to sampling frequency of each vehicle positioning data as priority, at the same moment, the matching position of a vehicle positioning point which is not matched with the matching position of a vehicle which is matched with the vehicle before is matched with the matching position of the vehicle positioning point, namely the error of the matching position of the vehicle positioning point, which occupies a lane length in combination with the length of the vehicle, and the error of the matching position of the vehicle which is matched with the matching position of the vehicle before at the same moment, which occupies a lane length in combination with the length of the vehicle before is matched with the matching position of the vehicle before is less than a set error value, and the vehicle positioning point to be matched is to be matched Is/>Vehicle anchor point/>Corresponding to the lane/>The shortest distance point of the GIS road network topology isVehicle anchor point/>Corresponding vehicle length is/>With the vehicle locating point/>Matched vehicle setpoint/>, at the same timeIs/>Vehicle anchor point/>Corresponding to the lane/>The shortest distance point of the GIS road network topology is/>Vehicle length is/>Position conflict tolerance is/>；

The vehicle position constraints are expressed as:

；

In S25, vehicle positioning sequence sets with different constructed matching priorities are adopted Solving the optimized matching model according to the sequence order to obtain the matching results of the vehicle positioning points with different sampling frequencies, wherein the matching results comprise the matched lane numbers and coordinate points closest to the vehicle positioning points on the matched lane GIS road network topology, and the coordinate points closest to the vehicle positioning points on the matched lane GIS road network topology are integrated into a point set/>, which is corrected by the vehicle track，/>。

Further, in the step S31, for the bridge group, each bridge row establishes a lane-level traffic simulation road network, and for a single bridge, according to bridge design parameters, the bridge length, the entrance, the exit, each lane width and each lane length are obtained, and the bridge entrance is used as a starting point, and the bridge exit is used as an ending point to establish a lane-level traffic simulation road network model of the bridge deck;

In S32, the matching results of the positioning data of the adjacent vehicles before and after each vehicle enters the bridge are intercepted, the adjacent vehicles are sequenced according to the sampling frequency, the priority is determined, the data of the two positioning points of each vehicle before and after entering the bridge and the positions of the matching results on the lanes are obtained from the matching results of each positioning point and each lane according to the position of each lane of the bridge entrance, the sequencing is carried out according to the sampling frequency, and the matching result set of the positioning points of the adjacent vehicles before and after each vehicle enters the bridge is obtained ，/>，/>Number of vehicles for a selected time;

acquiring matching results of each vehicle positioning data and each lane of the GIS road network topology on a road section where a bridge group is located by adopting a positioning point optimization matching model based on matching priority, respectively processing adjacent vehicle positioning point matching result sets before and after each vehicle enters the bridge according to sequence, and acquiring corresponding vehicle types and vehicle lengths according to the vehicle positioning data;

For the bridge line shape, dividing the line-shaped GIS road network topology data of each lane of the road section where the bridge is located into a plurality of discrete points according to the set space-time sampling frequency, and constructing a line-shaped GIS road network topology data point set of each lane of the road section where the bridge line direction is located ，/>，/>For lane/>The number of GIS road network topology data points;

matching result set according to adjacent vehicle positioning points before and after each vehicle enters bridge Calculating bridge entrance vehicle generation information, namely the time, speed and lane of the single vehicle entering the bridge according to the sampling frequency sequence from high to low, wherein the coordinates of adjacent vehicle locating points of the single vehicle in front of the bridge entrance are/>Adjacent vehicle locating point coordinates of single vehicle behind bridge entrance are/>The point coordinates of adjacent vehicle positioning points of a single vehicle in front of a bridge entrance on the corresponding matched lane GIS road network topology are/>The point coordinates of adjacent vehicle positioning points of a single vehicle behind a bridge entrance on the corresponding matched lane GIS road network topology are/>Adjacent vehicle locating point detection time of single vehicle before bridge entrance is/>The detection time of adjacent vehicle locating points of a single vehicle after a bridge entrance is，/>Adjacent vehicle positioning point of single vehicle before bridge entrance vehicle speed is/>Adjacent vehicle positioning point of single vehicle behind bridge entrance vehicle speed is/>The matching result point on the road network topology of the lane GIS at the entrance of the bridge is/>Or/>，/>；

When the vehicle positioning points match the resultAnd/>In the same lane, i.e. >When the vehicle enters the bridge, calculating the time of the vehicle entering the bridge;

Time of vehicle entering bridge Expressed as:

；

When the vehicle positioning points match the result And/>At different lanes, i.e./>When the vehicle enters the bridge, the lane matched with the vehicle locating point with the shortest distance at the entrance of the bridge is taken as the lane for the vehicle to enter the bridge, and the vehicle locating point with the shortest distance at the entrance of the bridge is taken as/>When the vehicle enters the bridge, the time for the vehicle to enter the bridge is/>；

The vehicle locating point with the shortest distance to the entrance of the bridge isWhen the vehicle enters the bridge, the time for the vehicle to enter the bridge is/>；

Time of vehicle entering bridgeExpressed as:

；

according to the positioning point of the vehicle Vehicle speed at time/>And the positioning point of the vehicle isVehicle speed at time/>Obtaining the average value/>, of the speed of the vehicle entering the bridge；

Average speed of vehicle entering bridgeExpressed as:

；

correcting the time and lane of the bridge where the vehicle enters, i.e. the vehicle locating point, when the time and lane of two vehicles enter the bridge collide And vehicle anchor point/>In the same lane,/>By modifying the parameter/>Correcting the speed of the vehicle and further correcting the time of the vehicle entering the bridge until the lanes do not conflict, and obtaining the corrected speed and the corrected time of the vehicle entering the bridge;

Correction speed Expressed as:

；

the time for the correction vehicle to enter the bridge is expressed as:

；

positioning point for vehicle And vehicle anchor point/>In different lanes, i.e. >When the vehicle position conflict is solved by modifying the lane where the current vehicle is located, when the time after the lane is modified or the conflict on the lane exists, the vehicle position conflict is solved by modifying the time of entering the bridge;

In the step S33, based on an optimized matching model of the vehicle positioning data of the matching priority and the road section lanes where the bridge is located, obtaining a matching result of the vehicle positioning data of the road section where the bridge is located in a single line direction and each lane, and according to the position of the bridge on the road section, obtaining the driving track of the vehicle on each lane on the bridge deck, as the driving path input of the vehicle in the lane-level road network simulation model, wherein the model parameters comprise a simulation step length, a vehicle following model and a vehicle lane changing model;

in S34, the bridge entrance vehicle generation information and the vehicle track of the vehicle in each lane are input into a bridge lane-level road network simulation model, simulation is run and the lane and the longitudinal position of each vehicle on the bridge at different moments are output, that is, the space-time distribution of each vehicle on the bridge deck is integrated, and the space-time distribution of the bridge deck vehicles is obtained.

Further, the simulation step length is obtained according to time intervals of space-time distribution of bridge deck vehicles, the vehicle following model is a Wiedemann following model, and the lane changing model is a rule-based model.

Further, the vehicle positioning data are obtained by collecting positioning data of a truck vehicle, a bus and a two-passenger one-risk vehicle and vehicle navigation data.

The beneficial effects of the invention are as follows: according to the invention, the bridge group facing the vehicle positioning data with different sampling frequencies considers different running directions of the bridge and the lane changing condition of the vehicle, the positioning data is matched with the bridge lanes by a multi-level positioning bridge lane matching method, the road section level positioning and the bridge road section matching are firstly carried out, and then the lane level positioning and the bridge lane matching are carried out in a single row direction of the bridge, so that the vehicle space-time distribution of each bridge of the bridge group is obtained; according to the invention, a multi-mode vehicle lane change probability calculation model is constructed to match road section lanes of vehicle positioning data with different sampling frequencies, so that whether a vehicle changes lanes or not and the possibility of changing lanes to other lanes can be effectively evaluated, the model is used as a target evaluation index of a vehicle positioning data and road section lane matching method based on matching priority, the characteristics of more accurate characteristics are extracted according to higher sampling frequencies, the sampling frequency is used as the matching priority of different vehicle positioning data, for single vehicle positioning data, the product of the probability of the lane where a vehicle positioning point is located in the process of a road section inlet to a road section outlet is used as a target, an optimal matching model based on the matching priority of the vehicle positioning data and the road section lane where a bridge is located is obtained, and the optimal matching result of the vehicle positioning point and the road section lane is obtained according to the vehicle lane change constraint and the vehicle position constraint, so that accurate vehicle track and the lane where the bridge inlet is located are provided; based on the advantages of all weather of vehicle positioning data and continuous vehicle track, the invention acquires the space-time distribution of bridge vehicles through matching the bridge surface lanes by the vehicle positioning data, does not need to be additionally provided with video equipment and a structural health monitoring system, greatly reduces the monitoring time and economic cost, can realize the space-time distribution identification of vehicles of urban large-scale bridge groups, can monitor all the day without manual operation, solves the problems of high cost, difficult installation and difficult identification of the space-time distribution of bridge vehicles at night in the video monitoring vehicle technology, and solves the problem of bridge vehicle distribution identification of non-installed cameras in urban large-scale bridges; the method provided by the invention can fully integrate the positioning data of trucks, taxis, network bus, buses, two-passenger one-danger, and vehicles navigation, so as to realize space-time distribution of bridge deck vehicles with different sampling frequency positioning data, improve data diversity and improve calculation accuracy; the method solves the problems that the positioning time of the vehicle positioning data is not uniform and the number of the vehicle positioning points is different in different sampling frequencies, builds a lane-level road network simulation model based on a microscopic traffic simulation model, considers the reality of the time and the lane when the vehicle enters the bridge, meets the principle that the vehicle position and the time at the entrance of the bridge are not in conflict, enables the recognized time and the lane when the vehicle enters the bridge to be closer to the reality value, improves the recognition precision, solves the problem that the vehicle positioning data track is sparse and the vehicle track is difficult to precisely recognize, and obtains the vehicle space-time distribution close to the real running condition through the microscopic simulation of the vehicle.

Drawings

The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the invention and do not constitute a limitation on the invention. In the drawings:

Fig. 1 is a flow chart of a method for identifying space-time distribution of bridge vehicles by fusing vehicle positioning data with different frequencies.

Detailed Description

In order to make the technical solutions and advantages of the embodiments of the present invention more apparent, the following detailed description of exemplary embodiments of the present invention is provided in conjunction with the accompanying drawings, and it is apparent that the described embodiments are only some embodiments of the present invention and not exhaustive of all embodiments. It should be noted that, without conflict, the embodiments of the present invention and features of the embodiments may be combined with each other.

Referring to fig. 1, the method for identifying the space-time distribution of the bridge vehicles by fusing the vehicle positioning data with different frequencies specifically includes the following steps:

in S13, selecting a bridge group according to the selected area, wherein the bridge group is expressed as ，/>Wherein/>For bridge line,/>For the number of bridges, matching the bridge group with GIS topological network road section information to obtain road sections matched with the bridge group, wherein the road section set matched with the GIS topological network by the bridge group is expressed as/>，/>Matching the vehicle positioning data with the information of each road section in the GIS topological network by adopting a hidden Markov model to obtain the road section matched with the vehicle positioning data, and obtaining the vehicle/>Road segment set of vehicle positioning data matched with road network GIS topology, namely vehicle/>Is expressed as/>，/>Wherein/>For the number of road segments traversed by the vehicle, the road segment set with the vehicle positioning data matched with the GIS topological network, namely the complete vehicle track is expressed as/>，/>Wherein/>Is the number of vehicles;

in S14, the bridge group is matched with the GIS topological network according to the road segment id Road segment set/>, matched with vehicle positioning data and GIS topological networkMatching to obtain vehicle tracks of road sections where bridge rows of the bridges in the bridge group are located;

In particular, when the bridge has one row, 1, When there are two rows of bridges,/>1 Or 2.

positioning point for vehicle In lane/>Probability score/>Expressed as:

；

Vehicle secondary lane Change to lane/>Probability/>Expressed as:

；

Wherein, For lane/>With lane/>Is a distance of (2);

；

Wherein, For vehicles in lanes/>Possibility of/(v)For vehicles from lanes/>Change to lane/>Is a function of the probability of (2),For the number of locating points of the vehicle on the road section of the bridge,/>The vehicle positioning point is the vehicle positioning point;

Lane change constraints can be expressed as:

；

The vehicle position constraints are expressed as:

；

matching result set according to adjacent vehicle positioning points before and after each vehicle enters bridge Calculating bridge entrance vehicle generation information, namely the time, speed and lane of the single vehicle entering the bridge according to the sampling frequency sequence from high to low, wherein the coordinates of adjacent vehicle locating points of the single vehicle in front of the bridge entrance are/>Adjacent vehicle locating point coordinates of single vehicle behind bridge entrance are/>The point coordinates of adjacent vehicle positioning points of a single vehicle in front of a bridge entrance on the corresponding matched lane GIS road network topology are/>The point coordinates of adjacent vehicle positioning points of a single vehicle behind a bridge entrance on the corresponding matched lane GIS road network topology are/>Adjacent vehicle locating point detection time of single vehicle before bridge entrance is/>Adjacent vehicle locating point detection time of single vehicle after bridge entrance is/>，Adjacent vehicle positioning point of single vehicle before bridge entrance vehicle speed is/>Adjacent vehicle positioning point of single vehicle behind bridge entrance vehicle speed is/>The matching result point on the road network topology of the lane GIS at the entrance of the bridge isOr/>，/>；

Time of vehicle entering bridge Expressed as:

；

Time of vehicle entering bridgeExpressed as:

；

according to the positioning point of the vehicle Vehicle speed at time/>And the vehicle positioning point is/>Vehicle speed at time/>Obtaining the average value/>, of the speed of the vehicle entering the bridge；

Average speed of vehicle entering bridgeExpressed as: /(I)

；

Correcting the time and lane of the bridge where the vehicle enters, i.e. the vehicle locating point, when the time and lane of two vehicles enter the bridge collideAnd vehicle anchor point/>In the same lane,/>By modifying the parameter/>Correcting the speed of the vehicle and further correcting the time of the vehicle entering the bridge until the lanes do not conflict, and obtaining the corrected speed and the corrected time of the vehicle entering the bridge;

Correction speed Expressed as:

；

the time for the correction vehicle to enter the bridge is expressed as:

；

In the step S34, the bridge entrance vehicle generation information and the vehicle track of the vehicle in each lane are input into a bridge lane-level road network simulation model, simulation is run and the lane and the longitudinal position of each vehicle on the bridge at different moments are output, namely the space-time distribution of each vehicle on the bridge deck is integrated, and the space-time distribution of the bridge deck vehicles is obtained;

Specifically, due to the fact that the sampling frequency of different positioning data is different, partial errors exist in calculation results, the time of entering the bridge by different vehicles is the same, the lanes are the same, and the time and the lanes are different from the actual situation, so that the time and the lanes of entering the bridge by each vehicle are not in conflict, the real accuracy of the space-time distribution simulation of bridge vehicles is improved, and when the time of the vehicle reaching the bridge is the same as the time and the lanes of the vehicle which are already calculated before, the position of the current vehicle, namely the time and the lanes of the bridge into which the vehicle enters, is corrected; the vehicle generation information in the current traffic simulation mainly adopts a vehicle head time interval distribution model constructed by poisson distribution, weber distribution and other distribution functions in a fitting way or is used as a vehicle generation information model, so that the positions of vehicles at different moments are generated, but the generated vehicle characteristics have randomness, are different from the actual vehicle spacing, speed, vehicle length and entrance, have certain errors, and are required to be input in a real enough traffic flow in order to ensure the accuracy of the vehicle time-space distribution in the bridge traffic microscopic simulation model, and the bridge vehicle generation information is obtained based on the vehicle positioning data of different sampling frequencies, so that the length, the vehicle type, the lane, the time and the speed of the vehicles entering the bridge are accurately acquired.

Specifically, according to the invention, different time intervals of space-time distribution of bridge deck vehicles can be selected according to actual requirements, in the embodiment, the time interval of space-time distribution of the bridge deck vehicles is set to be 0.2, the unit is s, the set space-time sampling frequency is that one point is acquired every 0.25 meter, a bridge line is divided into a plurality of points, and the bridge GIS position matched with a vehicle locating point and the time for entering a bridge are found.

While the invention has been described with respect to a limited number of embodiments, those skilled in the art, having benefit of the above description, will appreciate that other embodiments are contemplated within the scope of the invention as described herein. Furthermore, it should be noted that the language used in the specification has been principally selected for readability and instructional purposes, and may not have been selected to delineate or circumscribe the inventive subject matter. Accordingly, many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the appended claims. The disclosure of the present invention is intended to be illustrative, but not limiting, of the scope of the invention, which is defined by the appended claims.

Claims

1. The bridge vehicle space-time distribution identification method integrating the vehicle positioning data with different frequencies is characterized by comprising the following steps:

S34, running a lane-level road network simulation model to obtain vehicle space-time distribution, respectively simulating each bridge of the bridge group, and integrating the vehicle space-time distribution of all bridges of the bridge group to obtain bridge deck vehicle space-time distribution;

in the step S12, the preprocessing of the vehicle positioning data includes processing of missing values, processing of error data and processing of time sequencing, and the GIS topology network road section information includes road section names, road section ids, road section road grades, road section lane numbers and road section lane directions;

In S13, a bridge group is selected according to the selected area, the bridge group being denoted b, Wherein e is bridge row, k is bridge number, the bridge group is matched with GIS topological network road section information to obtain road sections matched with the bridge group, and the road section set matched with the GIS topological network is expressed as r,/>Matching the vehicle positioning data with the information of each road section in the GIS topological network by adopting a hidden Markov model to obtain a road section matched with the vehicle positioning data, wherein the road section set matched with the road network GIS topological network by the vehicle positioning data of the vehicle j, namely the vehicle track of the vehicle j is represented as re ^j,re^j＝{r₁,r₂,…,r_m, m is the number of road sections passed by the vehicle, and the road section set matched with the GIS topological network by the vehicle positioning data, namely the complete vehicle track is represented as re, re= { re ¹,re^j,…,re^p }, wherein p is the number of vehicles;

in S14, a road segment set r matching the bridge group with the GIS topology network is matched with a road segment set re matching the vehicle positioning data with the GIS topology network according to the road segment id, so as to obtain the vehicle track of the road segment where each bridge line of the bridge in the bridge group is located.

2. The method for identifying the space-time distribution of the bridge vehicles by fusing the vehicle positioning data with different frequencies according to claim 1, wherein in the step S21, the vehicle positioning data of the road sections where the bridge rows of the bridge group are located are obtained, and a GIS road network topology is constructed by taking the entrance of the road section where the bridge rows are located as a starting point and the exit of the road section where the bridge rows are located as an ending point according to the number of lanes, the length of lanes and GIS data of the road sections where the bridge rows are located in the directions of the bridge rows;

In the step S22, for the vehicle positioning data of the road section where the single bridge row in the bridge group is located, the vehicle positioning data are ordered from high to low according to the sampling frequency, and a vehicle positioning sequence set S with different matching priorities is constructed, s= { S ₁,S₂,…,S_r' }, and r' is the number of vehicles passing through the single bridge row direction of the bridge;

the probability of the vehicle positioning points in each lane is estimated by adopting a Gaussian distribution function, the road section lane set where the bridge is located is bl, bl= { bl ₁,bl₂,…,bl_s' }, wherein s' is the road section lane number where the bridge is located, and the shortest distance from the vehicle positioning points to the GIS road network topology of each lane and the probability score of the vehicle positioning points in each lane in the same lane driving process are respectively calculated;

Likelihood scoring of a vehicle setpoint k' in lane i Expressed as:

Wherein δ ² is a gaussian model parameter, which is obtained by using a moment estimation parameter estimation method based on historical data, i=1, 2, …, s';

Shortest distance of GIS road network topology corresponding to vehicle positioning point k' and lane i Expressed as:

Wherein, The projection coordinates of points forming the shortest distance with the vehicle positioning point k 'on the GIS road network topology corresponding to the lane i are the projection coordinates of the vehicle positioning point k';

possibility of vehicle setpoint k' not changing lanes when on lane i Expressed as:

angle between vector formed by current vehicle locating point k' and last vehicle locating point and line shape of lane i Expressed as:

Wherein, (x _k'-1,y_k'-1) is the projection coordinate of the last point of the vehicle positioning point k ', (x _k',y_k') is the projection coordinate of the vehicle positioning point k', (x _k' ^*,y_k' ^*) is the point of the projection coordinate (x _k',y_k') of the vehicle positioning point k 'which forms the shortest distance with the vehicle positioning point k' on the current lane GIS road network topology, (x _k'-1 ^*,y_k'-1 ^*) is the point of the projection coordinate (x _k'-1,y_k'-1) of the last point of the vehicle positioning point k 'which forms the shortest distance with the vehicle positioning point k' on the current lane GIS road network topology, lambda ² is a model parameter, and parameter estimation is carried out by adopting a moment estimation method according to historical data;

probability of a vehicle changing from lane i to lane v Expressed as:

Wherein d ^i,v is the distance between lane i and lane v;

integration is carried out to obtain a multi-mode lane change probability model of each vehicle positioning point in the vehicle positioning data

When v=i, the vehicle does not change lanes, and when v is not equal to i, the vehicle changes lanes;

the optimal matching model f of the vehicle positioning data and the road section lane where the bridge is located is expressed as:

Wherein, For the possibility of the vehicle being in lane i,/>The probability of changing the vehicle from the lane i to the lane v is given, N is the number of positioning points of the vehicle on the road section where the bridge is located, and q is the positioning point of the vehicle;

Constraint condition 1 is lane change constraint, wherein lane change constraint is carried out on vehicles in the matching process, whether the number of the lanes of the bridge is met or not is judged according to each lane change direction of each lane of the bridge, a lane h (bl _i, a ') where the vehicle is located after lane change is carried out by using a lane change direction a ' is obtained by using a lane bl _i, and if the corresponding lane does not exist in the bridge after the lane change is carried out by using the lane change direction a ', the lane h is expressed as 0;

Lane change constraints can be expressed as:

h(bl_i,a')≠0；

Constraint condition 2 is vehicle position constraint, constraint is carried out on vehicle position conflict at the same moment, the matching of all vehicle positioning data of the road section where the bridge is positioned is carried out according to the sampling frequency of all vehicle positioning data as priority, at the same moment, the matching position of the vehicle positioning point which is not matched is not in conflict with the position conflict of the point of the vehicle which is matched in the front, that is, the error between the matching position of the vehicle locating point and the lane length occupied by the length of the vehicle and the lane length occupied by the position of the matched vehicle and the length of the lane occupied by the length of the vehicle, which are matched before the same moment, should be smaller than the set error value, the coordinate of the vehicle locating point k 'to be matched is (bx _k',by_k'), and the point of the GIS road network topology shortest distance of the vehicle locating point k' corresponding to the matched lane i is The length of the vehicle locating point k 'corresponding to the vehicle is vl _k', the coordinate of the matched vehicle locating point q at the same time as the vehicle locating point k' is (hx _q,hy_q), and the point of the GIS road network topology shortest distance of the vehicle locating point q corresponding to the matched lane i is/>The length of the vehicle is vl _q, and the position conflict allowable error is χ;

The vehicle position constraints are expressed as:

In S25, according to the constructed vehicle positioning sequence set S with different matching priorities, the optimized matching model is solved according to the sequence order, and the vehicle positioning point matching results with different sampling frequencies are obtained, including the matched lane numbers and coordinate points closest to the vehicle positioning points on the matched lane GIS road network topology, and the coordinate points closest to the vehicle positioning points on the matched lane GIS road network topology are integrated into a point set S "= { S ₁",S₂",…,S_r'" } for vehicle track correction.

3. The method for recognizing the space-time distribution of the bridge vehicles by fusing the vehicle positioning data with different frequencies according to claim 2, wherein in the step S31, for the bridge group, each bridge row establishes a lane-level traffic simulation road network, for a single bridge, according to bridge design parameters, the bridge length, the entrance, the exit, each lane width and each lane length are obtained, and the bridge entrance is taken as a starting point, and the bridge exit is taken as an end point to establish a lane-level traffic simulation road network model of the bridge deck;

In S32, intercepting matching results of positioning data of adjacent vehicles before and after each vehicle enters the bridge, sorting according to sampling frequency, determining priority, acquiring two positioning point data of each vehicle before and after entering the bridge and the position of the matching result on the lane from the matching result of each positioning point and each lane according to the position of each lane of the bridge entrance, sorting according to sampling frequency, and obtaining a set si, si= { sv ₁,sv₂,…,sv_q' }, q 'of the matching result sets si, si= ₁,sv₂,…,sv_q' }, q' of the adjacent positioning points of each vehicle before and after entering the bridge;

For the bridge line shape, dividing the line-shaped GIS road network topology data of each lane of the road section where the bridge is positioned into a plurality of discrete points according to the set space-time sampling frequency, constructing a line-shaped GIS road network topology data point set Gbx ⁱ of each lane of the road section where the bridge line direction is positioned, L is the number of GIS road network topology data points of the lane i;

According to the adjacent vehicle locating point matching result set si before and after each vehicle enters the bridge, calculating bridge entrance vehicle generation information, namely the time, speed and lane of the single vehicle entering the bridge according to the sequence from high to low sampling frequency, wherein the coordinates of the adjacent vehicle locating point before the bridge entrance of the single vehicle are (bx _k′′,by_k′ '), the coordinates of the adjacent vehicle locating point after the bridge entrance of the single vehicle are (bx _k'+1',by_k'+1'), and the coordinates of the point on the GIS road network topology of the lane corresponding to the matching of the adjacent vehicle locating point before the bridge entrance of the single vehicle are The point coordinates of adjacent vehicle positioning points of a single vehicle behind a bridge entrance on the corresponding matched lane GIS road network topology are/>The detection time of adjacent vehicle locating points of a single vehicle before a bridge entrance is t _u', the detection time of adjacent vehicle locating points of the single vehicle after the bridge entrance is t _u'+c, c=1, 2,..n, and the vehicle speed of adjacent vehicle locating points of the single vehicle before the bridge entrance is/>Adjacent vehicle positioning point of single vehicle behind bridge entrance vehicle speed is/>The matching result point on the road network topology of the lane GIS at the bridge entrance is thatOr/>

When the vehicle positioning points match the resultAnd/>When the vehicle enters the bridge in the same lane, namely i=v, calculating the time when the vehicle enters the bridge;

The time t _u'+b for the vehicle to enter the bridge is expressed as:

When the vehicle positioning points match the result And/>When different lanes, namely i is not equal to v, the lane matched with the vehicle locating point with the shortest distance at the entrance of the bridge is taken as the lane for the vehicle to enter the bridge, and the vehicle locating point with the shortest distance at the entrance of the bridge is/>When the vehicle enters the bridge, the time for the vehicle to enter the bridge is t _u'+b;

The vehicle locating point with the shortest distance to the entrance of the bridge is When the vehicle enters the bridge, the time for entering the bridge is t _u'+b';

the time t _u'+b' for the vehicle to enter the bridge is expressed as:

according to the positioning point of the vehicle Vehicle speed at time/>And the positioning point of the vehicle isVehicle speed at time/>Obtaining a speed average value V' when the vehicle enters the bridge;

The average V' of the speed of the vehicle as it enters the bridge is expressed as:

correcting the time and lane of the bridge where the vehicle enters, i.e. the vehicle locating point, when the time and lane of two vehicles enter the bridge collide And vehicle anchor point/>When i=v in the same lane, correcting the speed of the vehicle through the correction parameter d so as to correct the time of the vehicle entering the bridge until the lanes do not conflict, and obtaining the corrected speed and the corrected time of the vehicle entering the bridge;

The correction speed V "is expressed as:

the time for the correction vehicle to enter the bridge is expressed as:

positioning point for vehicle And vehicle anchor point/>When the vehicle is in different lanes, namely i is not equal to v, the vehicle position conflict is solved by modifying the lane where the current vehicle is located, and when the time after the lane is modified or the conflict on the lane exists, the vehicle position conflict is solved by modifying the time of entering the bridge;

4. The method for recognizing the space-time distribution of the bridge vehicles by fusing the vehicle positioning data with different frequencies according to claim 3, wherein the simulation step length is obtained according to the time interval of the space-time distribution of the bridge vehicles, the vehicle following model is a Wiedemann following model, and the lane changing model is a rule-based model.

5. The method for recognizing the space-time distribution of the bridge vehicles fused with the vehicle positioning data with different frequencies according to claim 4, wherein the vehicle positioning data is obtained by collecting the positioning data of truck vehicles, buses and two-passenger one-risk vehicles and the vehicle navigation data.