A method, device and electronic device for obtaining a vehicle travel trajectory

Abstract

The present invention provides a method, apparatus and electronic device for obtaining a vehicle travel trajectory, which relates to the field of intelligent transportation technology. Among them, the method for obtaining a vehicle travel trajectory includes: verifying vehicle data of multiple traffic checkpoints based on satellite positioning data to obtain verified data, and obtaining a first vehicle trajectory between multiple traffic checkpoints by arranging the verified data in time sequence; calculating a second vehicle trajectory between a first positioning point in a first traffic area and the traffic checkpoint with the earliest time arrangement, and a third vehicle trajectory between a second positioning point in a second traffic area and the traffic checkpoint with the latest time arrangement based on traffic flow; adding the first vehicle trajectory, the second vehicle trajectory and the third vehicle trajectory to obtain the vehicle travel trajectory. By verifying the vehicle trajectory of traffic checkpoints and adding the trajectory from the positioning point in the traffic area to the traffic checkpoint, the vehicle travel trajectory is improved, and the accuracy of the vehicle travel trajectory is enhanced in the embodiments of the present invention.

Description

Technical Field

[0001] The embodiments of the present invention relate to the technical field of intelligent transportation, and in particular, to a method, an apparatus, and an electronic device for obtaining a vehicle travel trajectory. Background Art

[0002] With the continuous development of cities, traffic planning has become one of the main links in urban development. Vehicle travel trajectories are one of the important data bases for traffic planning. In the current related technologies, the vehicle travel trajectories are confirmed by using Global Positioning System (GPS) and traffic checkpoint data of traffic sections. However, in the prior art, there may be problems such as abnormal detection and missed detection in the traffic checkpoint data of traffic sections, resulting in the situation that the positions and clocks of the detected data are not synchronized, and causing abnormal problems in the final results in the subsequent calculation of obtaining the vehicle travel trajectories, thus reducing the accuracy of the vehicle travel trajectories.

[0003] It can be seen that there is a problem of low accuracy of vehicle travel trajectories in the prior art. Summary of the Invention

[0004] The embodiments of the present invention provide a method, an apparatus, and an electronic device for obtaining a vehicle travel trajectory to solve the problem of low accuracy of vehicle travel trajectories in the prior art.

[0005] To solve the above problems, the present invention is implemented as follows:

[0006] In a first aspect, the embodiments of the present invention provide a method for obtaining a vehicle travel trajectory, including:

[0007] Checking the vehicle data of multiple traffic checkpoints based on satellite positioning data to obtain checked data, and obtaining a first vehicle trajectory between the multiple traffic checkpoints by arranging the checked data in time;

[0008] Calculating a second vehicle trajectory between a first positioning point in a first traffic area and the traffic checkpoint with the earliest time arrangement, and a third vehicle trajectory between a second positioning point in a second traffic area and the traffic checkpoint with the latest time arrangement based on traffic flow, where the first traffic area and the second traffic area are the same traffic area or different traffic areas;

[0009] Adding the first vehicle trajectory, the second vehicle trajectory, and the third vehicle trajectory to obtain a vehicle travel trajectory.

[0010] In a second aspect, the embodiments of the present invention further provide a device for obtaining a vehicle travel trajectory, including:

[0011] The first processing module is configured to check the vehicle data of multiple traffic checkpoints based on satellite positioning data to obtain checked data, and obtain the first vehicle trajectories between multiple traffic checkpoints by arranging the checked data in time order;

[0012] The second processing module is configured to calculate, based on traffic flow, the second vehicle trajectory between the first positioning point in the first traffic area and the traffic checkpoint with the earliest time arrangement, and the third vehicle trajectory between the second positioning point in the second traffic area and the traffic checkpoint with the latest time arrangement, where the first traffic area and the second traffic area are the same traffic area or different traffic areas;

[0013] The third processing module is configured to add the first vehicle trajectory, the second vehicle trajectory, and the third vehicle trajectory to obtain the vehicle travel trajectory.

[0014] In a third aspect, an embodiment of the present invention further provides an electronic device, including a processor, a memory, and a computer program stored on the memory and executable on the processor. When the computer program is executed by the processor, the steps in the vehicle travel trajectory acquisition method described in the foregoing first aspect are implemented.

[0015] In a fourth aspect, an embodiment of the present invention further provides a readable storage medium for storing a program, which when executed by a processor implements the steps in the vehicle travel trajectory acquisition method described in the foregoing first aspect.

[0016] In the embodiments of the present invention, by checking the vehicle travel trajectories between traffic checkpoints through satellite positioning data, more accurate vehicle travel trajectories between traffic checkpoints are obtained; at the same time, the vehicle travel trajectories between positioning points in the traffic area and traffic checkpoints are increased, supplementing the vehicle travel trajectories, thereby improving the accuracy of the vehicle travel trajectories. Description of the Drawings

[0017] To more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments of the present invention. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0018] Figure 1 is a flowchart of a vehicle travel trajectory acquisition method provided by an embodiment of the present invention;

[0019] Figure 2 is a schematic diagram of multiple first prediction trajectories between adjacent traffic checkpoints provided by an embodiment of the present invention;

[0020] Figure 3It is the first vehicle trajectory map before and after satellite positioning data verification provided by an embodiment of the present invention;

[0021] Figure 4 It is a schematic diagram of the relationship between a traffic area and a traffic checkpoint provided by an embodiment of the present invention;

[0022] Figure 5 It is a schematic diagram before and after supplementing the vehicle travel trajectories between a traffic area and a traffic checkpoint provided by an embodiment of the present invention;

[0023] Figure 6 It is a schematic structural diagram of a vehicle travel trajectory acquisition device provided by an embodiment of the present invention;

[0024] Figure 7 It is a schematic structural diagram of an electronic device provided by an embodiment of the present invention. Detailed implementation manners

[0025] 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 some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0026] Please refer to Figure 1 , Figure 1 It is a flowchart of a vehicle travel trajectory acquisition method provided by an embodiment of the present invention. As Figure 1 shown, the vehicle travel trajectory acquisition method includes the following steps:

[0027] S101. Verify the vehicle data of multiple traffic checkpoints based on satellite positioning data to obtain verification data, and obtain the first vehicle trajectory between multiple traffic checkpoints by arranging the verification data in time sequence.

[0028] Among them, the satellite positioning data can be obtained through the GPS system, or through the BeiDou Navigation Satellite System (BDS) of China, or through the Galileo satellite navigation system (GALILEO) or other satellite positioning systems. The satellite positioning data includes various vehicle-related information data such as vehicle position information, vehicle speed information, and vehicle time information.

[0029] Traffic checkpoints are specific places on public roads, such as toll booths, traffic or public security checkpoints, etc. Traffic checkpoints can record vehicle license plate information, vehicle speed information, and vehicle time information by taking photos or videos and uploading them to designated devices or the cloud.

[0030] Among them, the verification of vehicle data at the traffic checkpoint based on satellite positioning data is to correct or supplement the abnormal or missing traffic checkpoint data detected by calculation based on the satellite positioning data.

[0031] Among them, it is necessary to connect the verified traffic checkpoint positions in chronological order in the road network map or the road network system to obtain a first vehicle trajectory schematic diagram of the vehicle in the road network map or the road network system.

[0032] S102. Calculate, based on traffic flow, a second vehicle trajectory between a first positioning point in a first traffic area and the traffic checkpoint with the earliest time arrangement, and a third vehicle trajectory between a second positioning point in a second traffic area and the traffic checkpoint with the latest time arrangement, wherein the first traffic area and the second traffic area are the same traffic area or different traffic areas.

[0033] The first positioning point is the starting point of the vehicle trajectory, and the second positioning point is the ending point of the vehicle trajectory. The traffic area includes at least one positioning point, which is both the starting point and the ending point. In the road network system, the first positioning point is connected to the traffic checkpoint to obtain a trajectory map of the vehicle starting from the traffic area and passing through the traffic checkpoint, that is, the second vehicle trajectory. Similarly, the second positioning point is connected to the traffic checkpoint to obtain a trajectory map of the vehicle that ends its journey from the traffic checkpoint to the traffic area, that is, the third vehicle trajectory.

[0034] The traffic area is pre-divided according to the distribution of the first positioning point or the second positioning point, or can be divided according to the distribution of the terminal signal. The divided traffic area can be used to obtain the traffic flow of people entering and leaving the traffic area through mobile phone signaling and other methods.

[0035] Among them, traffic flow is formed by the trajectories of multiple vehicles. By calculating the distribution of traffic flow in the road network system, the trajectory with the largest traffic flow is defaulted to be the vehicle's driving trajectory, thereby inferring the trajectory of the vehicle from the traffic area to the first traffic checkpoint.

[0036] S103: Add the first vehicle trajectory, the second vehicle trajectory and the third vehicle trajectory to obtain a vehicle travel trajectory.

[0037] In this implementation, the vehicle travel trajectory is split into a first vehicle trajectory, a second vehicle trajectory and a third vehicle trajectory, the first vehicle trajectory is corrected and supplemented through satellite positioning data verification, and the second vehicle trajectory and the third vehicle trajectory are extrapolated through traffic flow to supplement the entire vehicle travel trajectory, thereby improving the accuracy of the vehicle travel trajectory while supplementing the vehicle travel trajectory and improving the integrity of the vehicle travel trajectory.

[0038] As an optional implementation manner, the vehicle data includes checkpoint location data and checkpoint time data, the satellite positioning data includes satellite positioning location data and satellite positioning time data, and the verification data includes verification location data and verification time data;

[0039] The method of verifying the vehicle data of the plurality of traffic checkpoints based on the satellite positioning data to obtain verification data, and obtaining the first vehicle trajectory between the plurality of traffic checkpoints by arranging the verification data in time, comprises:

[0040] Extracting vehicle data and satellite positioning data of a plurality of said traffic checkpoints;

[0041] Verify the checkpoint position data based on the satellite positioning position data and the satellite positioning time data to obtain the verified position data;

[0042] Verify the checkpoint time data based on the satellite positioning time data to obtain the verified time data;

[0043] The verification time data are arranged in chronological order, and the corresponding verification position data are connected on a preset road network diagram to obtain the first vehicle trajectory.

[0044] In this embodiment, the position of the traffic checkpoint is verified by satellite positioning data so that the location information of the traffic checkpoint can be distributed at the correct position in the road network system, avoiding the position of a certain traffic checkpoint from being offset, resulting in abnormal deviation in the trajectory of vehicles passing through the traffic intersection, thereby improving the accuracy of the first vehicle trajectory.

[0045] In addition, the checkpoint time data of the traffic checkpoints is verified through satellite time data so that the time of all traffic checkpoints can be unified. The corresponding checkpoint time data can accurately indicate the order in which vehicles pass through different traffic checkpoints, thereby avoiding the error in the order in which vehicles pass through the traffic checkpoints due to time deviation, which causes the deviation of the first vehicle's trajectory.

[0046] Among them, the vehicle data of the traffic checkpoint is obtained through the checkpoint equipment, and the checkpoint equipment is set at the traffic checkpoint to collect the license plate information and time information of the vehicles passing through the traffic checkpoint.

[0047] As an alternative implementation, the verification of the checkpoint location data based on the satellite positioning location data and the satellite positioning time data to obtain the verified location data includes:

[0048] Count the number of the checkpoint location data within a preset time period to obtain a statistical quantity;

[0049] When the statistical quantity does not exceed the threshold, use the checkpoint location data as the verified location data;

[0050] When the statistical quantity exceeds the threshold, use the satellite positioning location data as the verified location data.

[0051] In this implementation, the checkpoint location data is verified through satellite positioning data, so that the checkpoint location data can accurately represent the driving conditions of vehicles. The abnormal data is replaced with the satellite positioning location data, expanding the sample of vehicle data and improving the accuracy of the finally obtained vehicle trajectory.

[0052] Among them, when an abnormal situation occurs in a certain checkpoint device and the checkpoint location data is misidentified as the location of other checkpoint devices, it will cause an incorrect deviation in the trajectory connected in the road network system. In this implementation, by presetting a time T, count the number of vehicles passing through the checkpoint location data L={link} within the time range of T±ΔT to obtain the number of vehicles passing through a single traffic checkpoint n link , when n link is significantly larger than the preset threshold, it is considered that the location information of this traffic checkpoint is incorrect, that is, the traffic checkpoint location corresponding to n link_max is abnormal.

[0053] After obtaining the information of the abnormal traffic checkpoint through statistics, the data information of this traffic checkpoint is verified, that is, for the vehicle data obtained by the checkpoint device corresponding to this traffic checkpoint, after analyzing the vehicle license plate, the satellite positioning location data corresponding to different vehicles is used to replace the checkpoint location data to obtain the verified location data. For example, after counting the checkpoint location data of traffic checkpoints A, B, and C, the location data of traffic checkpoint A exceeds the threshold. In this case, the data of traffic checkpoint A needs to be verified. The vehicles corresponding to traffic checkpoint A include the first vehicle, the second vehicle, and the third vehicle. Obtain the corresponding satellite positioning location data according to the license plate information of the first vehicle, the second vehicle, and the third vehicle, that is, the satellite positioning location data of the first vehicle, the satellite positioning location data of the second vehicle, and the satellite positioning location data of the third vehicle. At this time, the satellite positioning location data of the first vehicle, the satellite positioning location data of the second vehicle, and the satellite positioning location data of the third vehicle are used as the verified location data passing through traffic checkpoint A.

[0054] As an alternative implementation, the method of verifying the bayonet time data based on the satellite positioning time data to obtain the verified time data includes:

[0055] Select a set of the bayonet time data, and select the satellite positioning time data of the vehicle corresponding to the bayonet time data;

[0056] Subtract the bayonet time data from the satellite time positioning data to obtain the time deviation of the traffic bayonet;

[0057] Subtract the time deviation from the bayonet time data of the traffic bayonet to obtain the verified time data.

[0058] In this implementation, since there may be deviations in the set times between different bayonet devices, the deviations may cause changes in the order of vehicles passing through the traffic bayonet, affecting the final first vehicle trajectory. By verifying the vehicle trajectory using the satellite positioning time, the times of the bayonet devices can be unified, thereby achieving the effect of improving the accuracy of the first vehicle trajectory.

[0059] Among them, in the process of the bayonet device obtaining vehicle information, it is determined that the time when the bayonet device identifies a vehicle is a random variable T at a certain point d . This random variable T d is the sum of a certain fixed time deviation and a random variable with a normal distribution, that is:

[0060] T d = D + ε

[0061] Among them, D is the fixed time deviation, which is a definite value, and ε is a random variable with a normal distribution. There is

[0062] E(T d ) = E(D + ε) = E(D) + E(ε) = D + T

[0063] It is determined that the satellite positioning times in the travel trajectory of a single vehicle are evenly distributed. Let this time random variable be T GPS . If a symmetric area around the fixed point where the bayonet device identifies the vehicle is selected, then

[0064] E(T GPS ) = T = E(ε)

[0065] Since the time distribution of the travel trajectory and the time distribution of the bayonet device identification are independent of each other, therefore, there is

[0066] E(T d- T GPS ) = (D + T) - T = D

[0067] Thus, the time deviation can be obtained.

[0068] Specifically, obtain the location time of vehicle A passing through the first checkpoint, and the satellite positioning times of vehicle A passing through positions B and C. The midpoint position between positions B and C is the checkpoint position of the first checkpoint. Calculate the time average of vehicle A passing through positions B and C as the satellite positioning time of the first checkpoint, and then subtract the checkpoint location time to obtain the time deviation of the first checkpoint. Subtract the time deviation from the checkpoint time data obtained by the checkpoint device corresponding to the first checkpoint to obtain the verified checkpoint time data of the first checkpoint.

[0069] As an alternative implementation, when there is at least one of the traffic checkpoints between two consecutive traffic checkpoints passed by a certain vehicle, the first vehicle trajectory includes multiple first prediction trajectories;

[0070] After arranging the verified time data in chronological order and connecting the corresponding verified location data on the preset road network map to obtain the first vehicle trajectory, the method further includes:

[0071] Obtain the vehicle recognition rates of the traffic checkpoints on multiple first prediction trajectories;

[0072] Obtain the distribution probability corresponding to the first prediction trajectory by normalizing the vehicle recognition rate;

[0073] Take the first prediction trajectory with the maximum distribution probability as the first vehicle trajectory.

[0074] In this embodiment, when there is at least one traffic checkpoint between two consecutive traffic checkpoints passed by a certain vehicle, it can be determined that there is a missed detection situation at the existing traffic checkpoint, and the vehicle passing through cannot be accurately identified, which makes it possible for the first vehicle trajectory to deviate. Therefore, it is necessary to supplement the first vehicle trajectory.

[0075] Specifically, let the set of traffic checkpoints passed by the vehicle be {r i}, i ∈ [1, n r , where n r is the total number of sections passed by the vehicle, that is, the dimension of the set {r i}. For adjacent traffic checkpoints r i , r i+1 for which the unique path cannot be determined, let O be the location of r i and D be the location of r i+1 . Find all paths starting from O and ending at D in the road network system, that is, the first prediction trajectories, to form the set {P j}, j ∈ [1, n p , where n p is the total number of all paths starting from O and ending at D, that is, the dimension of the set {P jThe dimension of}, such as Figure 2 shown.

[0076] For any path P in the set {P j}, the traffic checkpoint set is j , where where is the number of traffic checkpoints on path P j . Let be the recognition rate of the traffic checkpoint:

[0077]

[0078] If there is no checkpoint device at this traffic checkpoint, then is 0. For any path P in the set {P j}, its comprehensive recognition rate is: j

[0079]

[0080] Let α j be the normalized allocation probability of path P j , then the traffic flow allocation on path P considering the comprehensive recognition rate j is:

[0081]

[0082] where α j is the normalized prior traffic flow ratio of path P j , that is:

[0083]

[0084] where, max(P j ) is the maximum allocation probability among the allocation probabilities for all paths starting from O and ending at D, and min(P j ) is the minimum allocation probability among the allocation probabilities for all paths starting from O and ending at D.

[0085] Obtain the allocation probability of the first predicted trajectory through calculation, and use the first predicted trajectory with the largest allocation probability as the first vehicle trajectory to supplement the undetected part of the traffic checkpoint.

[0086] As an optional implementation manner, after obtaining the allocation probability corresponding to the first predicted trajectory by normalizing the vehicle recognition rate, the method further includes:

[0087] Extract the distance data, road grade data, and traffic light data of the first predicted trajectory;

[0088] Normalize the distance data, the road grade data, and the traffic light data to obtain a comprehensive influence matrix;

[0089] Multiply the allocation probability by the comprehensive influence matrix to obtain an optimized allocation probability;

[0090] Take the first predicted trajectory with the maximum optimized allocation probability as the first vehicle trajectory.

[0091] In this embodiment, since there are multiple possibilities for the first predicted trajectory, and the distances, traffic lights, road grades, etc. of the sections passed by different trajectories are inconsistent, it is necessary to consider all influencing factors to improve the accuracy of the first predicted trajectory.

[0092] Specifically, obtain the distance data, road grade data, and traffic light data sets of different first predicted trajectories:

[0093]

[0094] Among them, is the path P j The utility function considering distance, road grade, and the number of intersections, where are respectively the calibration parameters of distance, road grade, and the number of intersections under the path P j and can be calibrated according to the selection probability of the path P j in the historical data and the comprehensive recognition rate of the traffic checkpoints.

[0095] Among them, are respectively the influencing factors of distance, road grade, and traffic lights under the path P j , where i.e., the reciprocal of the actual geographical distance of the path P j , which is obtained by calculating the actual length of the road and can be obtained by summing all sections {link} in the system; i.e., the reciprocal of the road grade weight, which can be obtained in actual application cases, such as expressways, arterial roads, sub-arterial roads, branch roads, or highways, first-class highways, second-class highways, etc., and then the corresponding weights are subjectively assigned according to the road grades in the actual road network; is the reciprocal of the number of intersections with traffic lights in the path, and its value can be calculated according to the actual road network and the corresponding path.

[0096] In addition, obtained from the road network data, and normalize the influencing factors respectively, that is:

[0097]

[0098] Among them,

[0099] Calculate the comprehensive influence matrix β through a probability selection model considering comprehensive factors j :

[0100]

[0101] Finally, calculate the optimized allocation probability:

[0102]

[0103] Take the first predicted trajectory with the maximum optimized allocation probability as the first vehicle trajectory, which improves the accuracy of the first vehicle trajectory

[0104] As Figure 3 shown Figure 3 is the first vehicle trajectory diagram before and after satellite positioning data verification provided by an embodiment of the present invention. After verification, supplementation and optimization, the accuracy of the first vehicle trajectory can be effectively optimized, and abnormal data is reduced

[0105] As an optional implementation manner, after obtaining verification data by verifying vehicle data of multiple traffic checkpoints based on satellite positioning data, and obtaining the first vehicle trajectory between multiple traffic checkpoints by arranging the verification data in time sequence, the method further includes:

[0106] Calculate and process the first vehicle trajectory according to a preset speed to obtain the vehicle travel time

[0107] When the travel time is greater than the preset threshold time, obtain the vehicle stop point based on the satellite positioning data and the road network data

[0108] Based on the vehicle stop point, divide the first vehicle trajectory into a first trajectory and a second trajectory, where the end point of the first trajectory is the stop point, and the starting point of the second trajectory is the stop point

[0109] In this embodiment, when the vehicle stays at a certain point in the first vehicle trajectory for too long, exceeding the threshold time, it can be considered that the vehicle has ended all its trips at this point. The first vehicle trajectory is the calculation result of splicing two trips, and this result needs to be optimized

[0110] Among them, the position point where the vehicle stays for too long can be confirmed through satellite positioning data, and this position point is set as the stop point; alternatively, according to the road network data, the predicted stop points along the first vehicle trajectory can be obtained, and the nearest stop point to the point with the longest stay time is selected as the final stop point

[0111] As an alternative implementation, calculating the second vehicle trajectory between the first positioning point in the traffic area and the traffic checkpoint with the earliest time arrangement, and the third vehicle trajectory between the second positioning point in the traffic area and the traffic checkpoint with the latest time arrangement includes:

[0112] Obtain the total generated traffic volume of the first traffic area, multiple second predicted trajectories between the first positioning point and the traffic checkpoint with the earliest time arrangement, and the distances of the second predicted trajectories, and obtain the total attracted traffic volume of the second traffic area, multiple third predicted trajectories between the second positioning point and the traffic checkpoint with the latest time arrangement, and the distances of the third predicted trajectories;

[0113] Fitting and calculating the distance of the second predicted trajectory according to the gravity model to obtain the first intermediate probability of the second predicted trajectory, and fitting and calculating the distance of the third predicted trajectory according to the gravity model to obtain the second intermediate probability of the third predicted trajectory;

[0114] Calculating the first probability according to the preset first reduction formula for the first intermediate probability, and calculating the second probability according to the first reduction formula for the second intermediate probability;

[0115] Multiplying the first probability by the total generated traffic volume to obtain the intermediate generated traffic volume of the second predicted trajectory, and multiplying the second probability by the total attracted traffic volume to obtain the intermediate attracted traffic volume of the third predicted trajectory;

[0116] Calculating the generated traffic volume of the second predicted trajectory according to the preset second reduction formula for the intermediate generated traffic volume of the second predicted trajectory, and calculating the attracted traffic volume of the third predicted trajectory according to the preset second reduction formula for the intermediate attracted traffic volume of the third predicted trajectory;

[0117] Taking the second predicted trajectory with the largest generated traffic volume of the second predicted trajectories as the second vehicle trajectory;

[0118] Taking the third predicted trajectory with the largest attracted traffic volume of the third predicted trajectories as the third vehicle trajectory.

[0119] In this implementation, by adding the second vehicle trajectory and the third vehicle trajectory from the traffic area to the traffic checkpoint, the integrity of the vehicle travel trajectory can be increased, and the accuracy of the vehicle travel trajectory can be improved.

[0120] Specifically, the traffic area can be a community, a residential area, or other possible starting or ending positions of vehicles. This position is a positioning point, and the positioning point cannot be obtained by the checkpoint device. Let N O be the total number of the first traffic areas, and i (i = 1..NO );Let N D be the total number of the second traffic areas, and j (j = 1..2N D ).

[0121] Statistically calculate the total generated traffic volume O i of the first traffic area and the total attracted traffic volume D j of the second traffic area, as well as the total traffic volume X n (n = 1…N) of each cross-section after sample expansion, where N is the total number of bayonet devices.

[0122] Among them, the statistical basic processes of the total generated traffic volume O i and the total attracted traffic volume D j are as follows:

[0123] (1) According to the longitude and latitude information of the base stations, cluster and merge the base stations within a certain distance (according to the average service radius of the base stations);

[0124] (2) Determine the stay trajectory of the terminal according to the aggregated base stations;

[0125] (3) Select the effective stay points with a stay time not less than the set stay threshold in each effective stay trajectory of each terminal;

[0126] For example, set the stay time of 1 hour as the time threshold for one purposeful trip.

[0127] (4) If the distance between two adjacent effective stay points of the terminal is not less than 0.5 km (signaling drift or short trip elimination), then the interval between the two stay points is regarded as one trip of the terminal;

[0128] (5) Traverse all the effective stay tables of the terminals and judge the traffic areas where the start and end points of their travel chains are located;

[0129] (6) Statistically calculate the total generated traffic volume O i of the first traffic area and the total attracted traffic volume D j .

[0130] Among them, the total traffic volume X n (n = 1…N) after sample expansion is modified to statistically calculate the traffic volume X n (n = 1…N) detected by the bayonet devices connecting each traffic area, and this value is obtained from the bayonet devices, where N is the total number of bayonet devices connecting the traffic areas.

[0131] Fit and calculate the first intermediate probability P n i and the second intermediate probability P n j :

[0132]

[0133]

[0134] where d i n is the distance of the second predicted trajectory, d j n is the distance of the third predicted trajectory. α, β, and K are calibration parameters of the probability model, which are calibrated by obtaining vehicle trajectory data and survey data.

[0135] Since the first traffic area includes multiple first positioning points and the second traffic area includes multiple second positioning points, the first intermediate probability and the second intermediate probability need to be reduced as follows:

[0136]

[0137]

[0138] where P n i ’ is the first probability, P n j ’ is the second probability.

[0139] Obtain the intermediate production volume O i n ’ of the second predicted trajectory and the intermediate attraction volume D j n ’ of the third predicted trajectory:

[0140]

[0141]

[0142] Then, based on the intermediate production volume O i n ’ of the second predicted trajectory and the intermediate production volume D j n ’ of the third predicted trajectory, obtain the production traffic volume O i n of the second predicted trajectory and the attraction traffic volume D j n of the third predicted trajectory:

[0143]

[0144]

[0145] where γ i and γ j are the second reduction formulas, and their formulas are:

[0146]

[0147]

[0148] The generated traffic volume O of the second predicted trajectory obtained by calculation i n The largest of the second predicted trajectories is used as the second vehicle trajectory, and the attracted traffic volume D of the third predicted trajectory j n The largest of the third predicted trajectories is used as the third vehicle trajectory, thereby supplementing the vehicle travel trajectory and improving the integrity.

[0149] As Figure 5 shown Figure 5 is a schematic diagram of the front and back of a vehicle travel trajectory between a supplementary traffic area and a traffic checkpoint provided by an embodiment of the present invention. It can be seen from the figure that the vehicle trajectory can be effectively extended after supplementation and can be accurately reflected on the road network system.

[0150] Please refer to Figure 6 , Figure 6 is a schematic structural diagram of a vehicle travel trajectory acquisition device provided by an embodiment of the present invention. As Figure 6 shown, the vehicle travel trajectory acquisition device includes:

[0151] A first processing module 201, configured to check the vehicle data of multiple traffic checkpoints based on satellite positioning data to obtain check data, and obtain a first vehicle trajectory between the multiple traffic checkpoints through arranging the check data in time sequence;

[0152] A second processing module 202, configured to calculate a second vehicle trajectory between a first positioning point in a first traffic area and the traffic checkpoint with the earliest time arrangement, and a third vehicle trajectory between a second positioning point in a second traffic area and the traffic checkpoint with the latest time arrangement based on traffic flow, where the first traffic area and the second traffic area are the same traffic area or different traffic areas;

[0153] A third processing module 203, configured to add the first vehicle trajectory, the second vehicle trajectory, and the third vehicle trajectory to obtain a vehicle travel trajectory.

[0154] As an optional implementation manner, the vehicle data includes checkpoint position data and checkpoint time data, the satellite positioning data includes satellite positioning position data and satellite positioning time data, and the check data includes check position data and check time data;

[0155] The first processing module includes:

[0156] A first acquisition unit, configured to extract vehicle data and satellite positioning data of a plurality of the traffic checkpoints;

[0157] A first verification unit, configured to verify the checkpoint location data based on the satellite positioning location data and the satellite positioning time data to obtain the verified location data;

[0158] A second verification unit, configured to verify the checkpoint time data based on the satellite positioning time data to obtain the verified time data;

[0159] A first calculation unit, configured to arrange the verified time data in chronological order and connect the corresponding verified location data on a preset road network map to obtain the first vehicle trajectory.

[0160] As an optional implementation manner, the first verification unit includes:

[0161] A first statistics unit, configured to count the number of the checkpoint location data within a preset time period to obtain a statistical quantity;

[0162] A first setting unit, configured to use the checkpoint location data as the verified location data when the statistical quantity does not exceed a threshold;

[0163] A second setting unit, configured to use the satellite positioning location data as the verified location data when the statistical quantity exceeds the threshold.

[0164] As an optional implementation manner, the second verification unit includes:

[0165] A second statistics unit, configured to select a group of the checkpoint time data and select the satellite positioning time data of the vehicle corresponding to the checkpoint time data;

[0166] A second calculation unit, configured to subtract the checkpoint time data from the satellite time positioning data to obtain a time deviation of the traffic checkpoint;

[0167] A third setting unit, configured to subtract the time deviation from the checkpoint time data of the traffic checkpoint to obtain the verified time data.

[0168] As an optional implementation manner, when there is at least one traffic checkpoint between two traffic checkpoints continuously passed by a vehicle, the first vehicle trajectory includes a plurality of first prediction trajectories;

[0169] After the first processing module, the device further includes:

[0170] A first acquisition module, configured to acquire vehicle recognition rates of the traffic checkpoints on a plurality of the first prediction trajectories;

[0171] A fourth processing module, configured to obtain an allocation probability corresponding to the first predicted trajectory through normalizing the vehicle recognition rate.

[0172] A first setting module, configured to use the first predicted trajectory with the maximum allocation probability as the first vehicle trajectory.

[0173] As an optional implementation manner, after the fourth module, the apparatus further includes:

[0174] A second obtaining module, configured to extract distance data, road grade data, and traffic light data of the first predicted trajectory.

[0175] A fifth processing module, configured to perform normalization processing on the distance data, the road grade data, and the traffic light data to obtain a comprehensive influence matrix.

[0176] A sixth processing module, configured to multiply the allocation probability by the comprehensive influence matrix to obtain an optimized allocation probability.

[0177] A second setting module, configured to use the first predicted trajectory with the maximum optimized allocation probability as the first vehicle trajectory.

[0178] As an optional implementation manner, after the first processing module, the apparatus further includes:

[0179] A calculation module, configured to perform calculation processing on the first vehicle trajectory according to a preset speed to obtain a vehicle travel time.

[0180] A seventh processing module, configured to, when the travel time is greater than a preset threshold time, obtain a vehicle stop point based on the satellite positioning data and the road network data.

[0181] An eighth processing module, configured to divide the first vehicle trajectory into a first trajectory and a second trajectory based on the vehicle stop point, where the end point of the first trajectory is the stop point, and the start point of the second trajectory is the stop point.

[0182] As an optional implementation manner, the second processing module includes:

[0183] A second obtaining unit, configured to obtain the total generated traffic volume of the first traffic area, multiple second predicted trajectories between the first positioning point and the traffic checkpoint with the earliest time arrangement, and the distances of the second predicted trajectories, and obtain the total attracted traffic volume of the second traffic area, multiple third predicted trajectories between the second positioning point and the traffic checkpoint with the latest time arrangement, and the distances of the third predicted trajectories.

[0184] A third calculation unit, configured to perform fitting calculation on the distance of the second predicted trajectory according to a gravity model to obtain a first intermediate probability of the second predicted trajectory, and perform fitting calculation on the distance of the third predicted trajectory according to the gravity model to obtain a second intermediate probability of the third predicted trajectory;

[0185] A fourth calculation unit, configured to calculate a first probability according to a preset first reduction formula for the first intermediate probability, and calculate a second probability according to the first reduction formula for the second intermediate probability;

[0186] A fifth calculation unit, configured to multiply the first probability by the total generated traffic volume to obtain an intermediate generated traffic volume of the second predicted trajectory, and multiply the second probability by the total attracted traffic volume to obtain an intermediate attracted traffic volume of the third predicted trajectory;

[0187] A sixth calculation unit, configured to calculate the generated traffic volume of the second predicted trajectory according to a preset second reduction formula for the intermediate generated traffic volume of the second predicted trajectory, and calculate the attracted traffic volume of the third predicted trajectory according to the preset second reduction formula for the intermediate attracted traffic volume of the third predicted trajectory;

[0188] A fourth setting unit, configured to use the second predicted trajectory with the largest generated traffic volume among the second predicted trajectories as the second vehicle trajectory;

[0189] A fifth setting unit, configured to use the third predicted trajectory with the largest attracted traffic volume among the third predicted trajectories as the third vehicle trajectory.

[0190] An embodiment of the present invention further provides an electronic device. Refer to Figure 7 , Figure 7 is a schematic structural diagram of an electronic device provided by an embodiment of the present invention. The electronic device includes a memory 301, a processor 302, and a program or instruction running on the memory 301. When the program or instruction is executed by the processor 302, it can implement Figure 1 any step in the corresponding method embodiment and achieve the same beneficial effects, which will not be elaborated here.

[0191] Among them, the processor 302 may be a CPU, an ASIC, an FPGA, or a CPLD.

[0192] Those of ordinary skill in the art can understand that all or part of the steps of implementing the method in the above embodiment can be completed by hardware related to program instructions, and the program can be stored in a readable medium. An embodiment of the present invention further provides a readable storage medium. The readable storage medium stores a computer program, and when the computer program is executed by a processor, it can implement the above Figure 1Any step in the corresponding method embodiment and can achieve the same technical effect. To avoid repetition, it will not be elaborated here.

[0193] The storage medium described above, such as a Read-Only Memory (ROM), Random Access Memory (RAM), magnetic disk, or optical disc, etc.

[0194] The terms "first", "second", etc. in the embodiments of the present invention are used to distinguish similar objects and do not necessarily need to describe a specific order or sequence. In addition, the terms "include" and "have" and any of their variants are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device including a series of steps or units does not necessarily have to be limited to those clearly listed steps or units, but may include other steps or units not clearly listed or inherent to these processes, methods, products, or devices. In addition, the use of "and / or" in this application represents at least one of the connected objects. For example, A and / or B and / or C represents 7 cases including A alone, B alone, C alone, A and B existing together, B and C existing together, A and C existing together, and A, B, and C existing together.

[0195] It should be noted that in this article, the term "include", "comprise" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article, or device including a series of elements not only includes those elements, but also includes other elements not clearly listed, or also includes elements inherent to such a process, method, article, or device. Without more limitations, the element defined by the statement "including one..." does not exclude the existence of other identical elements in the process, method, article, or device including the element.

[0196] Through the description of the above embodiments, those skilled in the art can clearly understand that the above embodiment methods can be implemented by means of software plus a necessary general hardware platform. Of course, it can also be implemented by hardware, but in many cases, the former is a better implementation method. Based on such an understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disc) and includes several instructions to enable a terminal (which can be a mobile phone, computer, server, air conditioner, or a second terminal device, etc.) to execute the methods described in various embodiments of this application.

[0197] The embodiments of the present application are described above in conjunction with the accompanying drawings. However, the present application is not limited to the specific implementation manners described above. The above specific implementation manners are merely illustrative rather than restrictive. Under the inspiration of the present application, those of ordinary skill in the art can also make many forms without departing from the purpose of the present application and the scope protected by the claims, and all of them fall within the protection scope of the present application.

Claims

1. A method for obtaining a vehicle travel trajectory, characterized in that, Including: Checking the vehicle data of multiple traffic checkpoints based on satellite positioning data to obtain checked data, and obtaining a first vehicle trajectory between multiple traffic checkpoints by arranging the checked data in time sequence; Calculating a second vehicle trajectory between a first positioning point in a first traffic area and the traffic checkpoint with the earliest time arrangement, and a third vehicle trajectory between a second positioning point in a second traffic area and the traffic checkpoint with the latest time arrangement based on traffic flow, where the first traffic area and the second traffic area are the same traffic area or different traffic areas, the first positioning point is the starting point of the vehicle trajectory, and the second positioning point is the ending point of the vehicle trajectory; Adding the first vehicle trajectory, the second vehicle trajectory, and the third vehicle trajectory to obtain a vehicle travel trajectory.

2. The method according to claim 1, characterized in that, The vehicle data includes checkpoint location data and checkpoint time data, the satellite positioning data includes satellite positioning location data and satellite positioning time data, and the checked data includes checked location data and checked time data; The step of checking the vehicle data of multiple traffic checkpoints based on satellite positioning data to obtain checked data, and obtaining a first vehicle trajectory between multiple traffic checkpoints by arranging the checked data in time sequence includes: Extracting the vehicle data and satellite positioning data of multiple traffic checkpoints; Checking the checkpoint location data based on the satellite positioning location data and the satellite positioning time data to obtain the checked location data; Checking the checkpoint time data based on the satellite positioning time data to obtain the checked time data; Arranging the checked time data in chronological order, and connecting the corresponding checked location data on a preset road network map to obtain the first vehicle trajectory.

3. The method according to claim 2, wherein The step of checking the checkpoint location data based on the satellite positioning location data and the satellite positioning time data to obtain the checked location data includes: Counting the number of the checkpoint location data within a preset time period to obtain a statistical quantity; When the statistical quantity does not exceed a set threshold, taking the checkpoint location data as the checked location data; When the statistical quantity exceeds the set threshold, taking the satellite positioning location data as the checked location data.

4. The method according to claim 2, wherein The step of checking the checkpoint time data based on the satellite positioning time data to obtain the checked time data includes: Selecting a set of the checkpoint time data, and selecting the satellite positioning time data of the vehicle corresponding to the checkpoint time data; Subtracting the checkpoint time data from the satellite positioning time data to obtain the time deviation of the traffic checkpoint; Subtracting the time deviation from the checkpoint time data of the traffic checkpoint to obtain the checked time data.

5. The method according to claim 2, characterized in that When there is at least one traffic checkpoint between two traffic checkpoints continuously passed by a vehicle, the first vehicle trajectory includes multiple first predicted trajectories; After arranging the checked time data in chronological order and connecting the corresponding checked location data on a preset road network map to obtain the first vehicle trajectory, the method further includes: Obtaining the vehicle recognition rates of the traffic checkpoints on multiple first predicted trajectories. Obtain the allocation probability corresponding to the first predicted trajectory through normalizing the vehicle recognition rate; Take the first predicted trajectory with the maximum allocation probability as the first vehicle trajectory.

6. The method according to claim 5, characterized in that, After obtaining the allocation probability corresponding to the first predicted trajectory through normalizing the vehicle recognition rate, the method further includes: Extract the distance data, road grade data, and traffic light data of the first predicted trajectory; Perform normalization processing on the distance data, road grade data, and traffic light data to obtain a comprehensive influence matrix; Multiply the allocation probability by the comprehensive influence matrix to obtain an optimized allocation probability; Take the first predicted trajectory with the maximum optimized allocation probability as the first vehicle trajectory.

7. The method according to claim 1, wherein After obtaining the verification data by verifying the vehicle data of multiple traffic checkpoints based on satellite positioning data, and obtaining the first vehicle trajectory between multiple traffic checkpoints by arranging the verification data in time sequence, the method further includes: Perform calculation processing on the first vehicle trajectory according to a preset speed to obtain the vehicle travel time; In the case where the travel time is greater than the preset threshold time, obtain the vehicle stop point based on the satellite positioning data and road network data; Based on the vehicle stop point, divide the first vehicle trajectory into a first trajectory and a second trajectory, where the end point of the first trajectory is the stop point, and the starting point of the second trajectory is the stop point.

8. The method according to claim 1, wherein The calculating the second vehicle trajectory between the first positioning point in the first traffic area and the traffic checkpoint with the earliest time arrangement, and the third vehicle trajectory between the second positioning point in the second traffic area and the traffic checkpoint with the latest time arrangement based on traffic flow includes: Obtain the total generated traffic volume in the first traffic area, multiple second predicted trajectories between the first positioning point and the traffic checkpoint with the earliest time arrangement, and the distances of the second predicted trajectories, and obtain the total attracted traffic volume in the second traffic area, multiple third predicted trajectories between the second positioning point and the traffic checkpoint with the latest time arrangement, and the distances of the third predicted trajectories; Perform fitting calculation on the distances of the second predicted trajectories according to the gravity model to obtain the first intermediate probability of the second predicted trajectories, and perform fitting calculation on the distances of the third predicted trajectories according to the gravity model to obtain the second intermediate probability of the third predicted trajectories; Calculate the first probability according to a preset first reduction formula for the first intermediate probability, and calculate the second probability according to the first reduction formula for the second intermediate probability; Multiply the first probability by the total generated traffic volume to obtain the intermediate generated traffic volume of the second predicted trajectories, and multiply the second probability by the total attracted traffic volume to obtain the intermediate attracted traffic volume of the third predicted trajectories; Calculate the generated traffic volume of the second predicted trajectories according to a preset second reduction formula for the intermediate generated traffic volume of the second predicted trajectories, and calculate the attracted traffic volume of the third predicted trajectories according to the preset second reduction formula for the intermediate attracted traffic volume of the third predicted trajectories; Take the second predicted trajectory with the largest generated traffic volume among the second predicted trajectories as the second vehicle trajectory; Take the third predicted trajectory with the largest attracted traffic volume among the third predicted trajectories as the third vehicle trajectory.

9. A vehicle travel trajectory acquisition device, characterized in that, Comprising: A first processing module, configured to verify vehicle data of multiple traffic checkpoints based on satellite positioning data to obtain verification data, and obtain a first vehicle trajectory between the multiple traffic checkpoints by arranging the verification data in time sequence; A second processing module, configured to calculate a second vehicle trajectory between a first positioning point in a first traffic area and the traffic checkpoint with the earliest time arrangement, and a third vehicle trajectory between a second positioning point in a second traffic area and the traffic checkpoint with the latest time arrangement based on traffic flow, where the first traffic area and the second traffic area are the same traffic area or different traffic areas; A third processing module, configured to add the first vehicle trajectory, the second vehicle trajectory, and the third vehicle trajectory to obtain a vehicle travel trajectory, where the first positioning point is the starting point of the vehicle trajectory, and the second positioning point is the ending point of the vehicle trajectory.

10. An electronic device, characterized in that, Comprising a processor, a memory, and a computer program stored on the memory and executable on the processor, where when the computer program is executed by the processor, the steps in the vehicle travel trajectory acquisition method according to any one of claims 1 to 8 are implemented.

11. A readable storage medium for storing a program, characterized in that, When the program is executed by the processor, the steps in the vehicle travel trajectory acquisition method according to any one of claims 1 to 8 are implemented.

Images