Target vehicle determination method and device, equipment and medium

Abstract

The invention relates to the technical field of traffic, in particular to a target vehicle determination method and device, equipment and a medium, and the method comprises the steps: obtaining the number of road sections between two end points of a target road, the number of intersections in the target road, and the number of average branches corresponding to the intersections based on the given target road, and in combination with a preset weight corresponding to each piece of road condition data, performing weighted summation to obtain a target road complexity score, determining a target reporting time interval threshold value corresponding to the target road complexity score according to a preset relationship correspondence table, and reporting the target road complexity score according to the target reporting time interval threshold value. Screening z vehicles passing through the target checkpoint equipment to determine a plurality of target vehicles; according to the method and the device, the corresponding preset reporting time interval threshold value can be determined according to the complexity of the road, and the target vehicle is screened out through the preset reporting time interval threshold value, so that the accuracy of vehicle track completion and checkpoint correction is ensured.

Description

Technical Field

[0001] The present invention relates to the field of traffic technology, and in particular to a method, device, equipment and medium for determining a target vehicle. Background Art

[0002] In the traffic management of vehicles, in order to record the driving information of several vehicles passing through the checkpoint device, the approximate location information of the checkpoint device is usually collected in advance, but this location information is not accurate. There are even cases where the location information of some checkpoint devices is not collected in advance, which affects the accurate judgment of the vehicle's driving trajectory by the checkpoint device. At present, the position of the checkpoint device is generally corrected based on the location information of the vehicle passing through the checkpoint device. However, since the exact location of the vehicle passing through the checkpoint device cannot be determined, especially when the vehicle-mounted GPS reporting interval is sparse, it is even more impossible to obtain the real-time and accurate location of the vehicle passing through the checkpoint device, which in turn affects the accuracy of the checkpoint correction. Summary of the invention

[0003] The purpose of the present invention is to provide a target vehicle determination method, device, equipment and medium, which can screen out target vehicles that meet the requirements according to the complexity of the road, so as to improve the accuracy of the checkpoint correction based on the driving information of the target vehicle.

[0004] According to a first aspect of the present invention, a method for determining a target vehicle is provided, comprising the following steps: Based on a given target road, a traffic condition data set corresponding to the target road is obtained; the traffic condition data set includes the number of road sections between the two end points of the target road, the number of intersections in the target road, and the average number of forks corresponding to the intersections; the target road refers to a section of road where a given target checkpoint device is located.

[0005] The complexity score of the target road is obtained by weighted summing up the number of road sections between the two end points of the target road in the road condition data set, the number of intersections in the target road, the average number of forks corresponding to the intersections, and the preset weight corresponding to each road condition data in the road condition data set.

[0006] According to a preset relationship correspondence table, the target reporting time interval threshold corresponding to the target road complexity score is determined; the relationship correspondence table refers to a table that records a one-to-one correspondence between several preset reporting time interval thresholds and several preset road complexity score ranges, wherein the preset reporting time interval threshold is inversely proportional to the preset road complexity score range.

[0007] According to the target reporting time interval threshold, z vehicles passing through the target checkpoint device are screened and several target vehicles are determined for correcting the position of the target checkpoint device; the target vehicle refers to any vehicle whose corresponding GPS reporting time interval is less than the target reporting time interval threshold.

[0008] Furthermore, the preset weight corresponding to the number of intersections in the target road is greater than the preset weight corresponding to the number of sections between two end points of the target road; The preset weight corresponding to the number of road sections between the two end points of the target road is greater than the preset weight corresponding to the average number of forks at the intersection.

[0009] Further, the target reporting time interval threshold corresponding to the target road complexity score is determined by the following steps: According to the target road complexity score, a target road complexity score range corresponding to the target road complexity score is determined from a plurality of preset road complexity score ranges.

[0010] The target road complexity score range is mapped in the relationship correspondence table, a preset reporting time interval threshold corresponding to the target road complexity score range is obtained, and the target reporting time interval threshold corresponding to the target road complexity score is determined.

[0011] Furthermore, the method further comprises the following steps: According to the shooting time of each target vehicle by the target checkpoint device, a number of GPS reporting time points and a number of vehicle position information respectively corresponding to each target vehicle before and after the corresponding shooting time are obtained.

[0012] For any target vehicle, according to several GPS reporting time points and several vehicle position information corresponding to the target vehicle, the trajectory completion model is used to complete the vehicle trajectory between every two adjacent vehicle position information to obtain the completed vehicle trajectory corresponding to the target vehicle.

[0013] Furthermore, the method further comprises the following steps: According to the completed vehicle trajectory corresponding to each target vehicle, a number of key vehicles are screened out from a number of target vehicles; wherein the key vehicle refers to any target vehicle whose vehicle trajectory between a previous GPS reporting time point and a subsequent GPS reporting time point of the corresponding shooting time is a straight trajectory.

[0014] For any key vehicle, obtain the real-time correspondence between the driving time and the longitude and latitude position of the key vehicle in the target trajectory; the target trajectory refers to the vehicle trajectory between the previous GPS reporting time point and the next GPS reporting time point corresponding to the shooting time of the key vehicle itself.

[0015] According to the shooting time of any of the key vehicles by the target checkpoint device, the target position information of the key vehicle itself at the corresponding shooting time is determined, and the target position information is determined as the position information of the target checkpoint device.

[0016] According to a second aspect of the present invention, there is provided a target vehicle determination device, the device comprising: The first acquisition module is used to acquire a road condition data set corresponding to a given target road based on the target road; the road condition data set includes the number of road sections between the two end points of the target road, the number of intersections in the target road, and the average number of forks corresponding to the intersections; the target road refers to a section of road where a given target checkpoint device is located.

[0017] The calculation module is used to obtain a target road complexity score by weighted summation based on the number of road sections between the two end points of the target road in the road condition data set, the number of intersections in the target road, the average number of forks corresponding to the intersections, and the preset weight corresponding to each road condition data in the road condition data set.

[0018] The first determination module is used to determine the target reporting time interval threshold value corresponding to the target road complexity score according to a preset relationship correspondence table; the relationship correspondence table refers to a table that records a one-to-one correspondence between a plurality of preset reporting time interval threshold values ​​and a plurality of preset road complexity score ranges, wherein the preset reporting time interval threshold value is inversely proportional to the preset road complexity score range.

[0019] The second determination module is used to screen the z vehicles passing through the target checkpoint device according to the target reporting time interval threshold, and determine a number of target vehicles for correcting the position of the target checkpoint device; the target vehicle refers to any vehicle whose corresponding GPS reporting time interval is less than the target reporting time interval threshold.

[0020] Furthermore, the preset weight corresponding to the number of intersections in the target road is greater than the preset weight corresponding to the number of sections between two end points of the target road; The preset weight corresponding to the number of road sections between the two end points of the target road is greater than the preset weight corresponding to the average number of forks at the intersection.

[0021] Furthermore, the first determining module includes: The third determination module is used to determine, according to the target road complexity score, a target road complexity score range corresponding to the target road complexity score from a plurality of preset road complexity score ranges.

[0022] The fourth determination module is used to map the target road complexity score range in the relationship correspondence table, obtain the preset reporting time interval threshold corresponding to the target road complexity score range, and determine it as the target reporting time interval threshold corresponding to the target road complexity score.

[0023] Furthermore, the device further comprises a trajectory completion module, and the trajectory completion module comprises: The second acquisition module is used to acquire a number of GPS reporting time points and a number of vehicle position information corresponding to each target vehicle before and after the corresponding shooting time according to the shooting time of each target vehicle by the target checkpoint device.

[0024] The third acquisition module is used to, for any target vehicle, use a trajectory completion model to complete the vehicle trajectory between each two adjacent vehicle position information according to a number of GPS reporting time points corresponding to the target vehicle and a number of vehicle position information corresponding to the target vehicle, so as to obtain the completed vehicle trajectory corresponding to the target vehicle.

[0025] Furthermore, the device further includes a location determination module, and the location determination module includes: The screening module is used to screen out a number of key vehicles from a number of target vehicles according to the completed vehicle trajectory corresponding to each target vehicle; wherein the key vehicle refers to any target vehicle whose vehicle trajectory between a previous GPS reporting time point and a subsequent GPS reporting time point of the corresponding shooting time is a straight trajectory.

[0026] The fourth acquisition module is used to obtain the real-time correspondence between the driving time and the longitude and latitude position of any key vehicle in the target trajectory; the target trajectory refers to the vehicle trajectory between the previous GPS reporting time point and the next GPS reporting time point corresponding to the shooting time of the key vehicle itself.

[0027] The fifth determination module is used to determine the target position information of the key vehicle itself at the corresponding shooting time according to the shooting time of any of the key vehicles by the target checkpoint device, and determine the target position information as the position information of the target checkpoint device.

[0028] According to a third aspect of the present invention, an electronic device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned target vehicle determination method when executing the computer program.

[0029] According to a fourth aspect of the present invention, there is provided a computer-readable storage medium storing a computer program, wherein the computer program implements the above-mentioned target vehicle determination method when executed by a processor.

[0030] Compared with the prior art, the present invention has at least the following beneficial effects: The target vehicle determination method described in the present invention first obtains the number of sections between the two end points of the target road, the number of intersections in the target road, and the average number of forks corresponding to the intersections based on a given target road, and calculates a more reasonable target road complexity score in combination with the preset weights corresponding to the number of sections, the number of intersections, and the average number of forks. When the road is more complex, in order to ensure the accuracy of vehicle trajectory completion, the corresponding preset reporting time interval threshold should be smaller. Therefore, according to the preset relationship correspondence table, the target reporting time interval threshold corresponding to the target road complexity score is determined. Finally, according to the target reporting time interval threshold, z vehicles passing through the target checkpoint device are screened to determine a number of target vehicles. In the above manner, target vehicles that meet the requirements can be screened to ensure the accuracy of vehicle trajectory completion and the accuracy of checkpoint device position correction. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0032] Figure 1 A flow chart of a target vehicle determination method provided in Embodiment 1 of the present invention; Figure 2 A flowchart of step S300 provided in the first embodiment of the present invention; Figure 3 A flowchart of the steps of completing the vehicle trajectory provided in the first embodiment of the present invention; Figure 4 A flowchart of the steps of determining the bayonet position provided in the first embodiment of the present invention; Figure 5 A schematic diagram of the structure of a target vehicle determination device provided in Embodiment 2 of the present invention; Figure 6A schematic diagram of the structure of the first determination module 300 provided in the second embodiment of the present invention; Figure 7 A schematic diagram of the structure of a trajectory completion module provided in Embodiment 2 of the present invention; Figure 8 This is a schematic diagram of the structure of a location determination module provided in Embodiment 2 of the present invention. DETAILED DESCRIPTION

[0033] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0034] Embodiment 1 like Figure 1 As shown, this embodiment provides a method for determining a target vehicle, comprising the following steps: S100, based on a given target road, obtaining a traffic condition data set corresponding to the target road; the traffic condition data set includes the number of road sections between the two endpoints of the target road, the number of intersections in the target road, and the average number of forks corresponding to the intersections; the target road refers to a section of road where a given target checkpoint device is located; it can be understood that: the target road refers to a road including a target checkpoint device, and several road sections and several intersections, wherein the target checkpoint device is located at a random intersection between the two endpoints of the target road. In a specific implementation, the target checkpoint device is located in the middle of the target road or at an intersection close to the middle of the target road as much as possible.

[0035] Specifically, the average number of forks corresponding to the intersection refers to the average number of forks corresponding to all intersections in the target road; for example, the number of forks corresponding to a three-fork intersection is 3, and the number of forks corresponding to a four-fork intersection is 4.

[0036] S200, performing weighted summation according to the number of road sections between the two end points of the target road in the road condition data set, the number of intersections in the target road, the average number of forks corresponding to the intersections, and the preset weight corresponding to each road condition data in the road condition data set to obtain a complexity score of the target road.

[0037] Specifically, the preset weight corresponding to the number of intersections in the target road is greater than the preset weight corresponding to the number of sections between the two endpoints of the target road; the preset weight corresponding to the number of sections between the two endpoints of the target road is greater than the preset weight corresponding to the average number of forks corresponding to the intersections.

[0038] Specifically, the target road complexity score meets the following conditions: S=a×Q1+b×Q2+c×Q3, where S is the complexity score of the target road, Q1 is the number of sections between the two end points of the target road, a is the preset weight corresponding to Q1, Q2 is the number of intersections in the target road, b is the preset weight corresponding to Q2, Q3 is the average number of forks corresponding to the intersection, and c is the preset weight corresponding to Q3.

[0039] As mentioned above, since the road is composed of sections and intersections, the number of sections, intersections and forks are introduced when calculating the road complexity score, and corresponding weight values ​​are assigned according to their importance, thereby obtaining a more reasonable road complexity score. The higher the score, the higher the complexity of the road, which is conducive to subsequently determining the target reporting time interval threshold corresponding to the road according to different road complexities, and then screening out target vehicles that meet the requirements.

[0040] S300, determining the target reporting time interval threshold corresponding to the target road complexity score according to a preset relationship correspondence table; the relationship correspondence table refers to a table recording a one-to-one correspondence between a plurality of preset reporting time interval thresholds and a plurality of preset road complexity score ranges, wherein the preset reporting time interval threshold is inversely proportional to the preset road complexity score range.

[0041] In a specific implementation, since the reporting intervals of GPS are mostly inconsistent for vehicles of different industries or brands, but the reporting intervals of most vehicles are between 30-60 seconds, the preset reporting time interval thresholds in this embodiment are set to 30 seconds, 40 seconds, 50 seconds and 60 seconds. Technical personnel in this field set the road complexity score range according to actual needs.

[0042] Specifically, Figure 2 As shown, step S300 includes the following steps: S301, according to the target road complexity score, determining a target road complexity score range corresponding to the target road complexity score from a plurality of preset road complexity score ranges.

[0043] S302, mapping the target road complexity score range in the relationship correspondence table, obtaining a preset reporting time interval threshold corresponding to the target road complexity score range, and determining it as the target reporting time interval threshold corresponding to the target road complexity score.

[0044] As mentioned above, when the road complexity is high, there will be relatively more driving plans for the vehicle between two reporting time points, which will affect the accuracy of vehicle trajectory completion. Therefore, when the road is more complex, the corresponding preset reporting time interval threshold should be smaller, that is, according to the complexity of the road, the corresponding preset reporting time interval threshold is selected, and the corresponding vehicles are screened by the preset reporting time interval threshold, which can ensure the accuracy of vehicle trajectory completion.

[0045] S400, according to the target reporting time interval threshold, screen the z vehicles passing through the target checkpoint device, and determine a number of target vehicles for use in correcting the position of the target checkpoint device; the target vehicle refers to any vehicle whose corresponding GPS reporting time interval is less than the target reporting time interval threshold.

[0046] As mentioned above, when the GPS reporting time interval of the vehicle is not less than the target reporting time interval threshold, it will affect the accuracy of the completed vehicle trajectory. Therefore, the vehicle is screened out, and the vehicle whose corresponding GPS reporting time interval is less than the target reporting time interval threshold is used as the screened target vehicle. The position of the target checkpoint device is corrected through the completed vehicle trajectory, which is beneficial to improve the accuracy of the correction of the target checkpoint device position.

[0047] In a specific embodiment, Figure 3 As shown, the method further comprises the following steps: S10, according to the shooting time of each target vehicle by the target checkpoint device, obtain a number of GPS reporting time points and a number of vehicle position information corresponding to each target vehicle before and after the corresponding shooting time; it can be understood that: the vehicle position information refers to mapping the longitude and latitude information of the target vehicle reported at any GPS reporting time point to the longitude and latitude information on the center line of the road where it is located.

[0048] Preferably, the number of GPS reporting time points of the target vehicle obtained before and after the corresponding shooting time is the same, so as to observe whether the target vehicle has a normal driving track before and after the shooting time.

[0049] In a preferred embodiment, there are no less than 5 corresponding GPS reporting time points before and after the corresponding shooting time. Through a total of 10 GPS reporting time points before and after the shooting time, it can be ensured that the target vehicle is on a normal driving trajectory.

[0050] S20, for any target vehicle, according to a number of GPS reporting time points corresponding to the target vehicle and a number of vehicle position information corresponding to the target vehicle, a trajectory completion model is used to complete the vehicle trajectory between each two adjacent vehicle position information, so as to obtain the completed vehicle trajectory corresponding to the target vehicle; wherein, the principle of the trajectory completion model is to infer the missing trajectory based on the time series data composed of an existing series of position points, so as to achieve the purpose of complete trajectory reconstruction and prediction. Those skilled in the art know the specific implementation of the trajectory completion model, which will not be repeated here.

[0051] As mentioned above, after obtaining several reporting time points corresponding to the target vehicle before and after the corresponding shooting time, it is considered that the target vehicle is on a normal driving trajectory before and after passing the target checkpoint device. Therefore, completing the vehicle driving trajectory of the target vehicle is conducive to the subsequent inference of the corresponding vehicle position information when passing the target checkpoint device, and then determining the position of the target checkpoint device.

[0052] Furthermore, if Figure 4 As shown, the method further comprises the following steps: S001, according to the completed vehicle trajectory corresponding to each target vehicle, select a number of key vehicles from a number of target vehicles; wherein the key vehicle refers to any target vehicle whose vehicle trajectory between the previous GPS reporting time point and the next GPS reporting time point of the corresponding shooting time is a straight trajectory.

[0053] S002, for any key vehicle, obtain the real-time correspondence between the driving time and the longitude and latitude position of the key vehicle in the target trajectory; the target trajectory refers to the vehicle trajectory between the previous GPS reporting time point and the next GPS reporting time point corresponding to the shooting time of the key vehicle itself.

[0054] Specifically, the real-time correspondence between the driving time and the longitude and latitude position of the key vehicle in the target trajectory refers to the real-time correspondence between the driving time and the longitude and latitude position fitted according to the uniform speed driving.

[0055] S003, according to the shooting time of any of the key vehicles by the target checkpoint device, determining the target position information of the key vehicle itself at the corresponding shooting time, and determining the target position information as the position information of the target checkpoint device.

[0056] As described above, based on the completed vehicle trajectory, the real-time correspondence between the driving time and the longitude and latitude position is obtained, and the vehicle position information corresponding to the key vehicle when it passes the target checkpoint device and is photographed can be known. Using this vehicle position information as a reference for the target checkpoint device position information can improve the accuracy of the target checkpoint device position prediction.

[0057] In a parallel implementation, the method further obtains the location information of the target bayonet device by the following steps: H100, according to the completed vehicle trajectory corresponding to each target vehicle, select the final vehicle set D = {D1, D2, ..., D i , ..., D m}, where D i is the i-th final vehicle screened out, i=1, 2, ..., m, m is the number of final vehicles screened out; the final vehicle is any target vehicle whose corresponding completed vehicle trajectory meets the preset normal trajectory rules.

[0058] Specifically, the compliance with the preset normal trajectory rule means that the completed vehicle trajectory is a trajectory that normally travels from one end point of the vehicle trajectory to another end point; for example, when the vehicle trajectory has a reverse trajectory, it does not comply with the preset normal trajectory rule.

[0059] H200, when T 0 With D i When the corresponding GPS reporting time points do not coincide, i In the corresponding completed vehicle trajectory, obtain D i The corresponding GPS reporting time points are 0 The adjacent previous GPS reporting time point and T 0 The intermediate trajectory between the adjacent next GPS reporting time points, and the fitting is D i The real-time correspondence between the driving time and the latitude and longitude position of the vehicle in the intermediate trajectory, where T 0 It is the time when the target camera equipment photographs any target vehicle.

[0060] Specifically, the H200 step also includes the following steps: H201, when D i The corresponding GPS reporting time points are 0 The adjacent previous GPS reporting time point and T 0 When several sections corresponding to the intermediate tracks between the adjacent next GPS reporting time points are of the same type, determine D i In the corresponding middle track, it is a uniform speed. According to the uniform speed, D i The real-time correspondence between the driving time in the intermediate trajectory and the latitude and longitude position of the vehicle is fitted; it can be understood that the same type of road section refers to urban roads of different levels divided according to the "Urban Road Engineering Design Code", for example, there are four levels: expressways, main roads, secondary roads, and branch roads.

[0061] H202, when Di The corresponding GPS reporting time points are 0 The adjacent previous GPS reporting time point and T 0 When the sections corresponding to the intermediate trajectory between the adjacent next GPS reporting time points include sections of different types, a speed ratio is allocated to each section in the intermediate trajectory according to the preset driving speeds corresponding to the sections of different types, and D is allocated according to the allocation result. i The real-time correspondence between the travel time of each road section in the intermediate trajectory and the latitude and longitude position of the vehicle is fitted.

[0062] As mentioned above, when the intermediate trajectory of the target vehicle is the same type of road section, it is considered that the driving speed is the same. Therefore, the real-time correspondence between the driving time and the longitude and latitude position of the vehicle in this intermediate trajectory is fitted based on the uniform speed driving. When any driving time is known, the real-time corresponding longitude and latitude position of the vehicle can be obtained according to the driving speed. When the intermediate trajectory includes different types of sections, the speed ratio of each type of section is divided, thereby obtaining the real-time correspondence between the driving time of each section and the longitude and latitude position of the vehicle, which provides a basis for determining the position of the target checkpoint equipment.

[0063] H300, according to D i The real-time correspondence between the driving time and the latitude and longitude position of the vehicle in the intermediate trajectory is calculated. i In T 0 The latitude and longitude position of the vehicle at the time; it can be understood as: D i In T 0 The vehicle latitude and longitude position corresponding to the time is D i The corresponding longitude and latitude positions of the vehicle when passing through the target checkpoint device and being photographed by the target checkpoint device reflect the preliminary position information of the target checkpoint device.

[0064] In another embodiment, when there is T 0 With D i When any corresponding GPS reporting time point coincides with T 0 D reported at the same GPS reporting time point i The vehicle position information is determined as D i In T 0 The latitude and longitude of the vehicle corresponding to the time; it can be understood as: when there is T 0 With D i When any corresponding GPS reporting time point coincides, it is considered that D i If the vehicle just passes the target checkpoint device at the overlapping GPS reporting time point, there is no need to calculate the position information of the vehicle passing the target checkpoint device again. The vehicle position information reported by the GPS at this time can be directly used as the preliminary position information of the target checkpoint device.

[0065] H400, based on m final vehicles in T 0 The longitude and latitude positions of the vehicles corresponding to the respective times are used to obtain the position information corresponding to the target checkpoint device, so as to realize the position correction of the target checkpoint device.

[0066] In a specific embodiment, in step H400, the position information corresponding to the target camera device is obtained through the following steps: H401, according to m final vehicles in T 0 The target position point is determined by the latitude and longitude positions of the vehicles corresponding to the respective moments; the target position point is any one of the latitude and longitude positions of the vehicles located at the edge position among the m latitude and longitude positions of the vehicles; it can be understood that: any one of the latitude and longitude positions of the vehicles located at the edge position refers to the latitude and longitude position of the vehicle corresponding to any one of the two endpoints when the m longitude and longitude positions of the vehicles are mapped to the center line of the road.

[0067] H402, based on the target location and the remaining m-1 vehicle longitude and latitude locations, obtain the distance difference list △L={△L1, △L2, ..., △L e , ..., △L m-1}, where △L e It is the distance difference between the e-th vehicle longitude and latitude position among the remaining m-1 vehicle longitude and latitude positions and the target position point, e=1, 2, ..., m-1.

[0068] H403, based on △L, calculate the target difference λ.

[0069] Among them, the target difference λ meets the following conditions: λ = (∑ m-1 e=1 △L e ) / m.

[0070] H404, obtain the position information corresponding to the target camera device according to the target position point and the target difference λ; it can be understood that: the position information corresponding to the target camera device refers to the position information obtained by adding the target difference λ to the target position point.

[0071] As mentioned above, through m final vehicles in T 0 The latitude and longitude positions of the vehicles corresponding to each moment are calculated to obtain the average position point, and this average position point is used as the final position corresponding to the target checkpoint device. By using the position information of multiple target vehicles passing through the target checkpoint device for calculation, the number of samples can be increased, thereby improving the accuracy of the target checkpoint device position.

[0072] In another specific embodiment, in step H400, the location information corresponding to the target bayonet device is obtained by further performing the following steps: H410, according to m final vehicles in T 0 The longitude and latitude of the vehicle corresponding to each time are obtained to obtain the longitude value X and latitude value Y corresponding to the target checkpoint device.

[0073] Among them, the longitude value X corresponding to the target camera device meets the following conditions: X=∑ m i=1 (1 / △T i ×P i ) / ∑ m i=1 (1 / △T i ), where △T i D i The corresponding n GPS reporting time points are 0 The next GPS reporting time point and T 0 The time difference between the adjacent previous GPS reporting time points, P i D i In T 0 The vehicle longitude value corresponding to the time.

[0074] The latitude value Y corresponding to the target bayonet device meets the following conditions: Y=∑ m i=1 (1 / △T i ×F i ) / ∑ m i=1 (1 / △T i ), where F i D i In T 0 The vehicle latitude value corresponding to the time.

[0075] H420, determine the location information corresponding to the target camera device according to the longitude and latitude values ​​corresponding to the target camera device.

[0076] As mentioned above, since the smaller the interval between GPS reporting time points, the more reliable the vehicle location information obtained when the target vehicle is photographed by the target checkpoint device, when calculating the longitude and latitude values, the inverse of the interval between GPS reporting time points is used as the weight of the vehicle longitude / longitude values ​​corresponding to the target vehicle at the time of shooting. The smaller the interval between GPS reporting time points, the greater the weight of the corresponding vehicle longitude / longitude values, and the location information of the target checkpoint device obtained in this way is more accurate.

[0077] Embodiment 2 like Figure 5 As shown, this embodiment 2 provides a target vehicle determination device, including: The first acquisition module 100 is used to acquire a traffic condition data set corresponding to a given target road based on the target road; the traffic condition data set includes the number of road sections between the two endpoints of the target road, the number of intersections in the target road, and the average number of forks corresponding to the intersections; the target road refers to a section of road where a given target checkpoint device is located; it can be understood that: the target road refers to a road including a target checkpoint device, and several road sections and several intersections, wherein the target checkpoint device is located at a random intersection between the two endpoints of the target road. In a specific implementation, the target checkpoint device is located in the middle of the target road or at an intersection close to the middle of the target road as much as possible.

[0078] Specifically, the average number of forks corresponding to the intersection refers to the average number of forks corresponding to all intersections in the target road; for example, the number of forks corresponding to a three-fork intersection is 3, and the number of forks corresponding to a four-fork intersection is 4.

[0079] The calculation module 200 is used to obtain a complexity score of the target road by performing weighted summation based on the number of road sections between the two end points of the target road in the road condition data set, the number of intersections in the target road, the average number of forks corresponding to the intersections, and the preset weight corresponding to each road condition data in the road condition data set.

[0080] Specifically, the preset weight corresponding to the number of intersections in the target road is greater than the preset weight corresponding to the number of sections between the two endpoints of the target road; the preset weight corresponding to the number of sections between the two endpoints of the target road is greater than the preset weight corresponding to the average number of forks corresponding to the intersections.

[0081] Specifically, the target road complexity score meets the following conditions: S=a×Q1+b×Q2+c×Q3, where S is the complexity score of the target road, Q1 is the number of sections between the two end points of the target road, a is the preset weight corresponding to Q1, Q2 is the number of intersections in the target road, b is the preset weight corresponding to Q2, Q3 is the average number of forks corresponding to the intersection, and c is the preset weight corresponding to Q3.

[0082] As mentioned above, since the road is composed of sections and intersections, the number of sections, intersections and forks are introduced when calculating the road complexity score, and corresponding weight values ​​are assigned according to their importance, thereby obtaining a more reasonable road complexity score. The higher the score, the higher the complexity of the road, which is conducive to subsequently determining the target reporting time interval threshold corresponding to the road according to different road complexities, and then screening out target vehicles that meet the requirements.

[0083] The first determination module 300 is used to determine the target reporting time interval threshold value corresponding to the target road complexity score according to a preset relationship correspondence table; the relationship correspondence table refers to a table that records a one-to-one correspondence between a plurality of preset reporting time interval threshold values ​​and a plurality of preset road complexity score ranges, wherein the preset reporting time interval threshold value is inversely proportional to the preset road complexity score range.

[0084] In a specific implementation, since the reporting intervals of GPS are mostly inconsistent for vehicles of different industries or brands, but the reporting intervals of most vehicles are between 30-60 seconds, the preset reporting time interval thresholds in this embodiment are set to 30 seconds, 40 seconds, 50 seconds and 60 seconds. Technical personnel in this field set the road complexity score range according to actual needs.

[0085] Specifically, Figure 6 As shown, the first determination module 300 includes: The third determining module 301 is used to determine, according to the target road complexity score, a target road complexity score range corresponding to the target road complexity score from a plurality of preset road complexity score ranges.

[0086] The fourth determination module 302 is used to map the target road complexity score range in the relationship correspondence table, obtain the preset reporting time interval threshold corresponding to the target road complexity score range, and determine it as the target reporting time interval threshold corresponding to the target road complexity score.

[0087] As mentioned above, when the road complexity is high, there will be relatively more driving plans for the vehicle between two reporting time points, which will affect the accuracy of vehicle trajectory completion. Therefore, when the road is more complex, the corresponding preset reporting time interval threshold should be smaller, that is, according to the complexity of the road, the corresponding preset reporting time interval threshold is selected, and the corresponding vehicles are screened by the preset reporting time interval threshold, which can ensure the accuracy of vehicle trajectory completion.

[0088] The second determination module 400 is used to screen the z vehicles passing through the target checkpoint device according to the target reporting time interval threshold, and determine a number of target vehicles for correcting the position of the target checkpoint device; the target vehicle refers to any vehicle whose corresponding GPS reporting time interval is less than the target reporting time interval threshold.

[0089] As mentioned above, when the GPS reporting time interval of the vehicle is not less than the target reporting time interval threshold, it will affect the accuracy of the completed vehicle trajectory. Therefore, the vehicle is screened out, and the vehicle whose corresponding GPS reporting time interval is less than the target reporting time interval threshold is used as the screened target vehicle. The position of the target checkpoint device is corrected through the completed vehicle trajectory, which is beneficial to improve the accuracy of the correction of the target checkpoint device position.

[0090] In a specific embodiment, Figure 7 As shown, the device further includes a trajectory completion module, and the trajectory completion module includes: The second acquisition module 10 is used to obtain a number of GPS reporting time points and a number of vehicle position information corresponding to each target vehicle before and after the corresponding shooting time according to the shooting time of each target vehicle by the target checkpoint device; it can be understood that: the vehicle position information refers to the longitude and latitude information of the target vehicle reported at any GPS reporting time point mapped to the longitude and latitude information on the center line of the road.

[0091] Preferably, the number of GPS reporting time points of the target vehicle obtained before and after the corresponding shooting time is the same, so as to observe whether the target vehicle has a normal driving track before and after the shooting time.

[0092] In a preferred embodiment, there are no less than 5 corresponding GPS reporting time points before and after the corresponding shooting time. Through a total of 10 GPS reporting time points before and after the shooting time, it can be ensured that the target vehicle is on a normal driving trajectory.

[0093] The third acquisition module 20 is used to, for any target vehicle, use a trajectory completion model to complete the vehicle trajectory between each two adjacent vehicle position information according to a number of GPS reporting time points corresponding to the target vehicle and a number of vehicle position information corresponding to the target vehicle, so as to obtain the completed vehicle trajectory corresponding to the target vehicle; wherein, the principle of the trajectory completion model is to infer the missing trajectory based on the time series data composed of an existing series of position points, so as to achieve the purpose of complete trajectory reconstruction and prediction. Those skilled in the art know the specific implementation method of the trajectory completion model, which will not be repeated here.

[0094] As mentioned above, after obtaining several reporting time points corresponding to the target vehicle before and after the corresponding shooting time, it is considered that the target vehicle is on a normal driving trajectory before and after passing the target checkpoint device. Therefore, completing the vehicle driving trajectory of the target vehicle is conducive to the subsequent inference of the corresponding vehicle position information when passing the target checkpoint device, and then determining the position of the target checkpoint device.

[0095] Furthermore, if Figure 8 As shown, the device also includes a position determination module, and the position determination module includes: The screening module 001 is used to screen out a number of key vehicles from a number of target vehicles according to the completed vehicle trajectory corresponding to each target vehicle; wherein the key vehicle refers to any target vehicle whose vehicle trajectory between the previous GPS reporting time point and the next GPS reporting time point of the corresponding shooting time is a straight trajectory.

[0096] The fourth acquisition module 002 is used to obtain the real-time correspondence between the driving time and the longitude and latitude position of any key vehicle in the target trajectory; the target trajectory refers to the vehicle trajectory between the previous GPS reporting time point and the next GPS reporting time point corresponding to the shooting time of the key vehicle itself.

[0097] Specifically, the real-time correspondence between the driving time and the longitude and latitude position refers to the real-time correspondence between the driving time and the longitude and latitude position fitted according to the uniform speed driving.

[0098] The fifth determination module 003 is used to determine the target position information of the key vehicle itself at the corresponding shooting time according to the shooting time of any of the key vehicles by the target checkpoint device, and determine the target position information as the position information of the target checkpoint device.

[0099] As described above, based on the completed vehicle trajectory, the real-time correspondence between the driving time and the longitude and latitude position is obtained, and the vehicle position information corresponding to the key vehicle when it passes the target checkpoint device and is photographed can be known. Using this vehicle position information as a reference for the target checkpoint device position information can improve the accuracy of the target checkpoint device position prediction.

[0100] Embodiment 3 This embodiment provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the following steps are implemented: Based on a given target road, a traffic condition data set corresponding to the target road is obtained; the traffic condition data set includes the number of road sections between the two end points of the target road, the number of intersections in the target road, and the average number of forks corresponding to the intersections; the target road refers to a section of road where a given target checkpoint device is located.

[0101] The complexity score of the target road is obtained by weighted summing up the number of road sections between the two end points of the target road in the road condition data set, the number of intersections in the target road, the average number of forks corresponding to the intersections, and the preset weight corresponding to each road condition data in the road condition data set.

[0102] According to a preset relationship correspondence table, the target reporting time interval threshold corresponding to the target road complexity score is determined; the relationship correspondence table refers to a table that records a one-to-one correspondence between several preset reporting time interval thresholds and several preset road complexity score ranges, wherein the preset reporting time interval threshold is inversely proportional to the preset road complexity score range.

[0103] According to the target reporting time interval threshold, z vehicles passing through the target checkpoint device are screened and several target vehicles are determined for correcting the position of the target checkpoint device; the target vehicle refers to any vehicle whose corresponding GPS reporting time interval is less than the target reporting time interval threshold.

[0104] Embodiment 4 This embodiment provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the following steps are implemented: Based on a given target road, a traffic condition data set corresponding to the target road is obtained; the traffic condition data set includes the number of road sections between the two end points of the target road, the number of intersections in the target road, and the average number of forks corresponding to the intersections; the target road refers to a section of road where a given target checkpoint device is located.

[0105] The complexity score of the target road is obtained by weighted summing up the number of road sections between the two end points of the target road in the road condition data set, the number of intersections in the target road, the average number of forks corresponding to the intersections, and the preset weight corresponding to each road condition data in the road condition data set.

[0106] According to a preset relationship correspondence table, the target reporting time interval threshold corresponding to the target road complexity score is determined; the relationship correspondence table refers to a table that records a one-to-one correspondence between several preset reporting time interval thresholds and several preset road complexity score ranges, wherein the preset reporting time interval threshold is inversely proportional to the preset road complexity score range.

[0107] According to the target reporting time interval threshold, z vehicles passing through the target checkpoint device are screened and several target vehicles are determined for correcting the position of the target checkpoint device; the target vehicle refers to any vehicle whose corresponding GPS reporting time interval is less than the target reporting time interval threshold.

[0108] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0109] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0110] Although some specific embodiments of the present invention have been described in detail by way of example, it will be appreciated by those skilled in the art that the above examples are for illustration only and are not intended to limit the scope of the present invention. It will also be appreciated by those skilled in the art that various modifications may be made to the embodiments without departing from the scope and spirit of the present invention. The scope of the present invention is defined by the appended claims.

Claims

1. A method for determining a target vehicle, characterized in that: The following steps are involved: Based on a given target road, a traffic condition data set corresponding to the target road is obtained; the traffic condition data set includes the number of road sections between two end points of the target road, the number of intersections in the target road, and the average number of forks corresponding to the intersections; the target road refers to a section of road where a given target checkpoint device is located; A target road complexity score is obtained by performing a weighted summation based on the number of road sections between the two end points of the target road in the road condition data set, the number of intersections in the target road, the average number of forks corresponding to the intersections, and the preset weight corresponding to each road condition data in the road condition data set; According to a preset relationship correspondence table, a target reporting time interval threshold corresponding to the target road complexity score is determined; the relationship correspondence table refers to a table recording a one-to-one correspondence between a plurality of preset reporting time interval thresholds and a plurality of preset road complexity score ranges, wherein the preset reporting time interval threshold is inversely proportional to the preset road complexity score range; According to the target reporting time interval threshold, z vehicles passing through the target checkpoint device are screened and several target vehicles are determined for correcting the position of the target checkpoint device; the target vehicle refers to any vehicle whose corresponding GPS reporting time interval is less than the target reporting time interval threshold.

2. The target vehicle determination method according to claim 1, characterized in that: The preset weight corresponding to the number of intersections in the target road is greater than the preset weight corresponding to the number of sections between the two end points of the target road; The preset weight corresponding to the number of road sections between the two end points of the target road is greater than the preset weight corresponding to the average number of forks at the intersection.

3. The target vehicle determination method according to claim 1, characterized in that: The target reporting time interval threshold corresponding to the target road complexity score is determined by the following steps: According to the target road complexity score, determining a target road complexity score range corresponding to the target road complexity score from a plurality of preset road complexity score ranges; The target road complexity score range is mapped in the relationship correspondence table, a preset reporting time interval threshold corresponding to the target road complexity score range is obtained, and the target reporting time interval threshold corresponding to the target road complexity score is determined.

4. The target vehicle determination method according to claim 1, characterized in that: The method further comprises the following steps: According to the shooting time of each target vehicle by the target checkpoint device, a number of GPS reporting time points and a number of vehicle position information corresponding to each target vehicle before and after the corresponding shooting time are obtained; For any target vehicle, according to several GPS reporting time points and several vehicle position information corresponding to the target vehicle, the trajectory completion model is used to complete the vehicle trajectory between every two adjacent vehicle position information to obtain the completed vehicle trajectory corresponding to the target vehicle.

5. The target vehicle determination method according to claim 4, characterized in that: The method further comprises the following steps: According to the completed vehicle trajectory corresponding to each target vehicle, a number of key vehicles are selected from a number of target vehicles; wherein the key vehicle refers to any target vehicle whose vehicle trajectory between the previous GPS reporting time point and the next GPS reporting time point of the corresponding shooting time is a straight trajectory; For any key vehicle, obtain the real-time correspondence between the driving time and the latitude and longitude position of the key vehicle in the target trajectory; the target trajectory refers to the vehicle trajectory between the previous GPS reporting time point and the next GPS reporting time point corresponding to the shooting time of the key vehicle itself; According to the shooting time of any of the key vehicles by the target checkpoint device, the target position information of the key vehicle itself at the corresponding shooting time is determined, and the target position information is determined as the position information of the target checkpoint device.

6. A target vehicle determination device, characterized in that: The device comprises: A first acquisition module is used to acquire a road condition data set corresponding to a given target road based on the target road; the road condition data set includes the number of road sections between two end points of the target road, the number of intersections in the target road, and the average number of forks corresponding to the intersections; the target road refers to a section of road where a given target checkpoint device is located; A calculation module, for obtaining a target road complexity score by weighted summation based on the number of road sections between the two end points of the target road in the road condition data set, the number of intersections in the target road, the average number of forks corresponding to the intersections, and the preset weight corresponding to each road condition data in the road condition data set; A first determination module is used to determine the target reporting time interval threshold value corresponding to the target road complexity score according to a preset relationship correspondence table; the relationship correspondence table refers to a table recording a one-to-one correspondence between a plurality of preset reporting time interval threshold values ​​and a plurality of preset road complexity score ranges, wherein the preset reporting time interval threshold value and the preset road complexity score range are inversely proportional; The second determination module is used to screen the z vehicles passing through the target checkpoint device according to the target reporting time interval threshold, and determine a number of target vehicles for correcting the position of the target checkpoint device; the target vehicle refers to any vehicle whose corresponding GPS reporting time interval is less than the target reporting time interval threshold.

7. The target vehicle determination device according to claim 6, characterized in that: The preset weight corresponding to the number of intersections in the target road is greater than the preset weight corresponding to the number of sections between the two end points of the target road; The preset weight corresponding to the number of road sections between the two end points of the target road is greater than the preset weight corresponding to the average number of forks at the intersection.

8. The target vehicle determination device according to claim 6, characterized in that: The first determining module comprises: A third determination module is used to determine, according to the target road complexity score, a target road complexity score range corresponding to the target road complexity score from a plurality of preset road complexity score ranges; The fourth determination module is used to map the target road complexity score range in the relationship correspondence table, obtain the preset reporting time interval threshold corresponding to the target road complexity score range, and determine it as the target reporting time interval threshold corresponding to the target road complexity score.

9. The target vehicle determination device according to claim 6, characterized in that: The device further includes a trajectory completion module, and the trajectory completion module includes: The second acquisition module is used to obtain a number of GPS reporting time points and a number of vehicle position information corresponding to each target vehicle before and after the corresponding shooting time according to the shooting time of each target vehicle by the target checkpoint device; The third acquisition module is used to, for any target vehicle, use a trajectory completion model to complete the vehicle trajectory between each two adjacent vehicle position information according to a number of GPS reporting time points corresponding to the target vehicle and a number of vehicle position information corresponding to the target vehicle, so as to obtain the completed vehicle trajectory corresponding to the target vehicle.

10. The target vehicle determination device according to claim 9, characterized in that: The device also includes a location determination module, and the location determination module includes: A screening module is used to screen out a number of key vehicles from a number of target vehicles according to the completed vehicle trajectory corresponding to each target vehicle; wherein the key vehicle refers to any target vehicle whose vehicle trajectory between a previous GPS reporting time point and a subsequent GPS reporting time point of the corresponding shooting time is a straight trajectory; The fourth acquisition module is used to obtain the real-time correspondence between the driving time and the longitude and latitude position of any key vehicle in the target trajectory; the target trajectory refers to the vehicle trajectory between the previous GPS reporting time point and the next GPS reporting time point of the shooting time corresponding to the key vehicle itself; The fifth determination module is used to determine the target position information of the key vehicle itself at the corresponding shooting time according to the shooting time of any of the key vehicles by the target checkpoint device, and determine the target position information as the position information of the target checkpoint device.

11. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the target vehicle determination method according to any one of claims 1 to 5 is implemented.

12. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the target vehicle determination method according to any one of claims 1 to 5 is implemented.

Images