Vehicle positioning method, device, electronic equipment and storage medium

Abstract

The present application provides a vehicle positioning method, device, electronic device and storage medium. The method includes: obtaining first track point information of a first track point of a vehicle at the current moment, and second track point information of a second track point of the vehicle at N moments before the current moment, where N is a positive integer, and the first track point and the second track point are continuous track points; obtaining a first candidate track point corresponding to the first track point, and a second candidate track point corresponding to the second track point; calculating the matching probability of the first candidate track point according to the first track point information, the second track point information, the track point information of the first candidate track point and the track point information of the second candidate track point; selecting a preset number of candidate track points from the first candidate track points according to the matching probability; determining a target candidate track point among the candidate track points according to the road network model corresponding to the first candidate track point, so as to locate the position of the vehicle at the current moment.

Description

Technical Field

[0001] The present application relates to the technical field of vehicle trajectory matching, and in particular to a vehicle positioning method, device, electronic device and storage medium. Background Art

[0002] In the travel industry, real-time positioning of the vehicle's road position can help the system accurately grasp the driver's position, so that it can efficiently dispatch orders, dynamically adjust routes during the trip, monitor the vehicle's position in real time, ensure that the driver drives according to the scheduled route, and improve safety.

[0003] At present, the commonly used vehicle positioning methods include the following:

[0004] 1. The nearest neighbor method matches the trajectory point to the nearest road node or road section. This method has a simple algorithm and is easy to implement, but it only considers the nearest road node of a single trajectory point, is easily affected by trajectory noise and drift, does not consider the previous trajectory point information, and has a low matching result accuracy.

[0005] 2. The hidden Markov model matching method combines the previous trajectory information and the current trajectory point information of the trajectory point to improve the matching accuracy. However, it only uses the distance between the trajectory point and the road network and the path length information of the matching point of the sequence trajectory. It does not fully utilize the relationship between the candidate road and the surrounding roads. It is easily affected by trajectory noise and trajectory deviation in scenes such as intersections and parallel main and auxiliary roads, resulting in problems such as matching errors in intersections and main and auxiliary roads.

[0006] 3. The Viterbi algorithm, based on the industry-wide method of hidden Markov model matching, finds the global optimal path to ensure the consistency and rationality of the overall trajectory. Like the hidden Markov model matching method, it does not fully utilize the relationship between the candidate road and the surrounding roads, nor can it solve the problems encountered by the hidden Markov model matching method.

[0007] The above methods have the problem that real-time matching in scenes such as intersections and parallel roads is prone to mismatching, resulting in a low accuracy rate in real-time matching of vehicle positions. Summary of the invention

[0008] The technical problem to be solved by the embodiments of the present application is to provide a vehicle positioning method, device, electronic device and storage medium to effectively improve the accuracy of vehicle position matching.

[0009] In a first aspect, an embodiment of the present application provides a vehicle positioning method, the method comprising:

[0010] Acquire first trajectory point information of a first trajectory point of a vehicle at a current moment, and second trajectory point information of a second trajectory point of the vehicle at N moments before the current moment, where N is a positive integer, and the first trajectory point and the second trajectory point are continuous trajectory points;

[0011] Acquire a first candidate trajectory point corresponding to the first trajectory point, and a second candidate trajectory point corresponding to the second trajectory point;

[0012] Calculating a matching probability of the first candidate trajectory point according to the first trajectory point information, the second trajectory point information, the trajectory point information of the first candidate trajectory point, and the trajectory point information of the second candidate trajectory point;

[0013] According to the matching probability, a preset number of candidate trajectory points are screened out from the first candidate trajectory points;

[0014] According to the road network model corresponding to the candidate trajectory points, a target candidate trajectory point among the candidate trajectory points is determined to locate the position of the vehicle at the current moment.

[0015] In a second aspect, an embodiment of the present application provides a vehicle positioning device, the device comprising:

[0016] a trajectory point information acquisition module, used to acquire first trajectory point information of a first trajectory point of the vehicle at a current moment, and second trajectory point information of a second trajectory point of the vehicle at N moments before the current moment, where N is a positive integer, and the first trajectory point and the second trajectory point are continuous trajectory points;

[0017] A candidate trajectory point acquisition module, used to acquire a first candidate trajectory point corresponding to the first trajectory point, and a second candidate trajectory point corresponding to the second trajectory point;

[0018] a matching probability calculation module, configured to calculate a matching probability of the first candidate trajectory point according to the first trajectory point information, the second trajectory point information, the trajectory point information of the first candidate trajectory point and the trajectory point information of the second candidate trajectory point;

[0019] A candidate trajectory point screening module, configured to screen a preset number of candidate trajectory points from the first candidate trajectory points according to the matching probability;

[0020] The vehicle position positioning module is used to determine the target candidate trajectory point among the candidate trajectory points according to the road network model corresponding to the candidate trajectory points, so as to locate the position of the vehicle at the current moment.

[0021] In a third aspect, an embodiment of the present application provides an electronic device, including:

[0022] A processor, a memory, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, any one of the above vehicle positioning methods is implemented.

[0023] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium. When instructions in the storage medium are executed by a processor of an electronic device, the electronic device is enabled to execute any of the vehicle positioning methods described above.

[0024] Compared with the prior art, the embodiments of the present application have the following advantages:

[0025] In the embodiment of the present application, by obtaining the first trajectory point information of the first trajectory point of the vehicle at the current moment, and the second trajectory point information of the second trajectory point of the vehicle at N moments before the current moment, N is a positive integer, and the first trajectory point and the second trajectory point are continuous trajectory points. A first candidate trajectory point corresponding to the first trajectory point and a second candidate trajectory point corresponding to the second trajectory point are obtained. According to the first trajectory point information, the second trajectory point information, the trajectory point information of the first candidate trajectory point and the trajectory point information of the second candidate trajectory point, the matching probability of the first candidate trajectory point is calculated. According to the matching probability, a preset number of candidate trajectory points are screened out from the first candidate trajectory point. According to the road network model corresponding to the first candidate trajectory point, the target candidate trajectory point among the candidate trajectory points is determined to locate the position of the vehicle at the current moment. In the embodiment of the present application, a road network model is introduced into the road network matching, and the trajectory points are cleaned by using the road network model. After the probability matching, the matching results are finely screened, so as to solve the problem that the real-time matching in scenes such as intersections and parallel roads is prone to matching errors, thereby improving the matching accuracy of the real-time road network matching.

[0026] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 A flowchart of a vehicle positioning method provided in an embodiment of the present application;

[0028] Figure 2 A flowchart of a method for obtaining candidate trajectory points provided in an embodiment of the present application;

[0029] Figure 3 A flowchart of a matching probability calculation method provided in an embodiment of the present application;

[0030] Figure 4 A schematic diagram of a road network model provided in an embodiment of the present application;

[0031] Figure 5 A schematic diagram of the difference in U-turn characteristics on different roads provided in an embodiment of the present application;

[0032] Figure 6 A schematic diagram of track noise on an upper and lower line separation road provided in an embodiment of the present application;

[0033] Figure 7 A schematic diagram of confusing road matching provided in an embodiment of the present application;

[0034] Figure 8 A schematic diagram of a T-junction trajectory turning provided in an embodiment of the present application;

[0035] Fig. 9 A schematic diagram of refined screening of intersection trajectory matching provided in an embodiment of the present application;

[0036] Fig.10 A schematic diagram of a road network model provided in an embodiment of the present application for application in matching;

[0037] Fig.11 A schematic diagram of a trajectory matching process provided in an embodiment of the present application;

[0038] Fig.12 A schematic diagram of the structure of a vehicle positioning device provided in an embodiment of the present application;

[0039] Fig.13 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0040] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0041] The terms used in the embodiments of the present application are only for the purpose of describing specific embodiments, and are not intended to limit the present application. The singular forms "a", "said" and "the" used in the embodiments of the present application and the appended claims are also intended to include plural forms, unless the context clearly indicates other meanings.

[0042] Reference Figure 1 , shows a flow chart of the steps of a vehicle positioning method provided by an embodiment of the present application, such as Figure 1 As shown, the vehicle positioning method may include: step 101, step 102, step 103, step 104 and step 105.

[0043] Step 101: Obtain first trajectory point information of a first trajectory point of a vehicle at a current moment, and second trajectory point information of a second trajectory point of the vehicle at N moments before the current moment, where N is a positive integer, and the first trajectory point and the second trajectory point are continuous trajectory points.

[0044] In the embodiment of the present application, the first track point refers to the track point of the vehicle at the current moment. The first track point information is the track point information of the first track point, which includes: the longitude of the track point of the vehicle at the current moment, the latitude of the track point, the timestamp of the track point, the driving direction of the track point, and the speed of the track point, which can be expressed as: (x, y, t, dir, v).

[0045] The second trajectory point refers to the second trajectory point information of the second trajectory point of the vehicle at N moments before the current moment, where N is a positive integer. The first trajectory point and the second trajectory point are continuous trajectory points, that is, the first trajectory point and the second trajectory point are continuous trajectory points at the same time. The second trajectory point information is the trajectory point information of the second trajectory point, which includes the longitude of the trajectory point at N moments before the current moment, the latitude of the trajectory point, the timestamp of the trajectory point, the driving direction of the trajectory point, and the speed of the trajectory point.

[0046] During the driving process of the vehicle, the first track point information of the first track point of the vehicle at the current moment can be obtained. At the same time, the second track point information of the second track point of the vehicle at N moments before the current moment can be obtained from the cached track points. Specifically, the track point information of the vehicle in the previous period stored in the platform can be obtained according to the virtual code of the driver of the vehicle.

[0047] After obtaining the first track point information of the first track point of the vehicle at the current moment and the second track point information of the second track point of the vehicle at N moments before the current moment, step 102 is performed.

[0048] Step 102: Obtain a first candidate trajectory point corresponding to the first trajectory point, and a second candidate trajectory point corresponding to the second trajectory point.

[0049] The first candidate trajectory point refers to a candidate trajectory point selected from roads within a preset range of the first trajectory point for trajectory point matching.

[0050] The second candidate trajectory point refers to a candidate trajectory point that is selected from roads within a preset range of the second trajectory point and matches the second trajectory point.

[0051] After obtaining the first track point information of the first track point of the vehicle at the current moment and the second track point information of the second track point of the vehicle at N moments before the current moment, the first candidate track point corresponding to the first track point and the second candidate track point corresponding to the second track point can be obtained. The method for obtaining the candidate track points can be combined with Figure 2 This is described in detail as follows.

[0052] Reference Figure 2 , shows a flowchart of the steps of a method for obtaining candidate trajectory points provided by an embodiment of the present application. Figure 2 As shown, the candidate trajectory point acquisition method may include: step 201, step 202 and step 203.

[0053] Step 201: Determine a first road network information range corresponding to the first trajectory point according to the trajectory point coordinates of the first trajectory point and a preset query range; and determine a second road network information range corresponding to the second trajectory point according to the trajectory point coordinates of the second trajectory point and the query range.

[0054] In this embodiment, after obtaining the first trajectory point and the second trajectory point, the first road network information range corresponding to the first trajectory point can be determined according to the trajectory point coordinates of the first trajectory point and the preset query range. And the second road network information range corresponding to the second trajectory point can be determined according to the trajectory point coordinates of the second trajectory point and the query range. Specifically, the first trajectory point and the second trajectory point can be used as the center of the circle and the query range can be used as the radius to limit the road network information area to determine the first road network information range and the second road network information range.

[0055] In the specific implementation, in order to efficiently query the road network information, it is necessary to establish a spatial index. The spatial index is a data structure that allows the road network information in a specific area to be quickly located. In practical applications, the spatial index method can be R-tree, quadtree, grid index, etc. For each trajectory point, its coordinates can be used as the center point of the query, and according to the preset query range (for example, a certain radius or a specific geographical area), the spatial index can be used to quickly locate the road network information within the range.

[0056] After determining a first road network information range corresponding to the first trajectory point according to the trajectory point coordinates of the first trajectory point and the preset query range, and determining a second road network information range corresponding to the second trajectory point according to the trajectory point coordinates of the second trajectory point and the query range, step 202 is performed.

[0057] Step 202: Acquire all first roads within the first road network information range and all second roads within the second road network information range.

[0058] After the first road network information range and the second road network information range are determined, all first roads within the first road network information range and all second roads within the second road network information range may be acquired.

[0059] After all first roads within the first road network information range and all second roads within the second road network information range are acquired, step 203 is executed.

[0060] Step 203: taking the point on all the first roads that is closest to the first trajectory point as a first candidate trajectory point, and taking the point on all the second roads that is closest to the second trajectory point as a second candidate trajectory point.

[0061] After obtaining all the first roads within the first road network information range and all the second roads within the second road network information range, the points on all the first roads that are closest to the first trajectory point can be used as first candidate trajectory points, and the points on all the second roads that are closest to the second trajectory point can be used as second candidate trajectory points. Specifically, the points on all the first roads that are closest to the first trajectory point can be obtained as first candidate trajectory points. At the same time, the points on all the second roads that are closest to the second trajectory point can be obtained as second candidate trajectory points.

[0062] The embodiment of the present application can narrow the search range and reduce the interference of irrelevant roads by determining the road network information range corresponding to the trajectory point. When determining the candidate trajectory point, the road point closest to the trajectory point is selected, which helps to more accurately reflect the vehicle position.

[0063] After obtaining the first candidate trajectory point corresponding to the first trajectory point and the second candidate trajectory point corresponding to the second trajectory point, step 103 is performed.

[0064] Step 103: Calculate the matching probability of the first candidate trajectory point according to the first trajectory point information, the second trajectory point information, the trajectory point information of the first candidate trajectory point and the trajectory point information of the second candidate trajectory point.

[0065] After obtaining the first candidate trajectory point corresponding to the first trajectory point and the second candidate trajectory point corresponding to the second trajectory point, the matching probability of the first candidate trajectory point can be calculated based on the first trajectory point information, the second trajectory point information, the trajectory point information of the first candidate trajectory point, and the trajectory point information of the second candidate trajectory point. In this example, the basic matching probability and the cumulative matching probability of the first candidate trajectory point can be calculated first, and the matching probability of the first candidate trajectory point can be calculated by combining the basic matching probability and the cumulative matching probability. Figure 3 This is described in detail as follows.

[0066] Reference Figure 3 , shows a flowchart of a matching probability calculation method provided by an embodiment of the present application. Figure 3 As shown, the matching probability calculation method may include: step 301, step 302 and step 303.

[0067] Step 301: Calculate the straight-line distance between the first trajectory point and the first candidate trajectory point according to the first trajectory point information and the trajectory point information of the first candidate trajectory point, and determine the basic matching probability of the first candidate trajectory point according to the straight-line distance.

[0068] In this embodiment, the straight-line distance between the first trajectory point and the first candidate trajectory point can be calculated based on the first trajectory point information and the trajectory point information of the first candidate trajectory point, and the basic matching probability of the first candidate trajectory point can be determined based on the straight-line distance. In this example, the straight-line distance between the first trajectory point and the first candidate trajectory point can be calculated, and the basic matching probability of the first candidate trajectory point can be calculated using the following formula (1):

[0069]

[0070] In the above formula, p is the basic matching probability, σ can be trained through specific trajectory information and road network information, and different thresholds are used in different scenarios. Dis is the straight-line distance between the first trajectory point and the first candidate trajectory point.

[0071] In this example, the basic matching probability can adopt the normal distribution of the distance between the trajectory point and the candidate trajectory point. In order to prevent overflow and underflow problems in the calculation, log processing is performed on the basis of the normal distribution.

[0072] Step 302: Calculate the cumulative matching probability of the first candidate trajectory point according to the trajectory point information of the first candidate trajectory point and the trajectory point information of the second candidate trajectory point.

[0073] After obtaining the first candidate trajectory point and the second candidate trajectory point, the cumulative matching probability of the first candidate trajectory point can be calculated based on the trajectory point information of the first candidate trajectory point and the trajectory point information of the second candidate trajectory point. The implementation process can be described in detail in conjunction with the following specific implementation manner.

[0074] In a specific implementation of the present application, the above step 302 may include:

[0075] Sub-step A1: Calculate a first path length, a first path direction, and a first path speed between the first trajectory point and the second trajectory point according to the first trajectory point information and the second trajectory point information.

[0076] In this embodiment, the first path length, the first path direction and the first path speed between the first trajectory point and the second trajectory point can be calculated based on the first trajectory point information and the second trajectory point information. t and the previous trajectory point (i.e. the second trajectory point) p t-1 The straight-line distance dis pt-1pt 、Direction of line dir pt-1pt and speed v pt-1pt .

[0077] Sub-step A2: calculating a second path length, a second path direction and a second path speed between the first candidate trajectory point and the second candidate trajectory point according to the trajectory point information of the first candidate trajectory point and the trajectory point information of the second candidate trajectory point.

[0078] After obtaining the first candidate trajectory point and the second candidate trajectory point, the second path length, the second path direction and the second path speed between the first candidate trajectory point and the second candidate trajectory point can be calculated according to the trajectory point information of the first candidate trajectory point and the trajectory point information of the second candidate trajectory point. t The trajectory point (i.e. the first trajectory point) has n first candidate trajectory points, p t-1 The trajectory point (i.e., the second trajectory point) has m second candidate trajectory points, and calculates p t-1 Trajectory points and p t The path length dis between all candidate trajectory points of the trajectory point pt-1ciptcj and path direction dir pt-1ciptcj (where 0≤i≤m, 0≤j≤n). And calculate the path speed v between all candidate trajectory points pt-1ciptcj .

[0079] Sub-step A3: Calculate the path mileage difference between the first path length and the second path length, the path direction difference between the first path direction and the second path direction, and the path speed difference between the first path speed and the second path speed.

[0080] After obtaining the first path length, the first path direction, the first path speed, the second path length, the second path direction, and the second path speed, the path mileage difference between the first path length and the second path length, the path direction difference between the first path direction and the second path direction, and the path speed difference between the first path speed and the second path speed can be calculated.

[0081] Sub-step A4: Based on the path mileage difference, the path direction difference and the path speed difference, the cumulative matching probability of the first candidate trajectory point is calculated.

[0082] After obtaining the path mileage difference, path direction difference and path speed difference, the cumulative matching probability of the first candidate trajectory point can be calculated based on the path mileage difference, path direction difference and path speed difference. Taking the example in the above sub-step A2 as an example, the path mileage difference between the trajectory point and the candidate trajectory point can be calculated. It is used to reflect the rationality of the routes matched to different roads by trajectory points, d dis The smaller the value, the closer the candidate matching road point is to the trajectory point in terms of mileage. It is used to reflect the rationality of matching trajectory points to driving directions on different roads, d dir The smaller the candidate road matching point, the more reasonable it is. The speed difference between the trajectory point and the path speed between the candidate trajectory points Similar to the previous two features, it mainly reflects whether the speed is reasonable. The smaller the value, the higher the matching probability.

[0083] After calculating the features between trajectory points, the following formula (2) is used to calculate the cumulative matching probability (where a1, a2, a3, b1, b2, and b3 are trained according to trajectory information and road network models, and different thresholds are used in different scenarios). The three features currently use the same weight.

[0084]

[0085] When calculating the cumulative matching probability, the probability of all features uses the sigmoid function (a commonly used activation function that can map any value to the interval (0, 1) and express it as a probability). In order to prevent overflow and underflow problems in the calculation, log processing is performed, which can be adjusted well to ensure that when the features between trajectory points are good (when the differences between features are small), the cumulative matching probability is high and changes slowly. This is because the output value of the sigmoid function changes slowly when the input value is close to 0, and the log processing maintains this slow change. When the difference between the features of the trajectory points exceeds the threshold (the threshold is a pre-defined value), the cumulative matching probability changes rapidly. This is because the output value of the sigmoid function changes rapidly when the input value is far from 0, which can well distinguish good features between trajectory points from poor features between trajectory points. When the features between trajectory points are poor (that is, when the differences between the features between trajectory points are large), the cumulative matching probability is close to the minimum value. This is because the output value of the sigmoid function is close to 0 when the input value is negative, indicating that the matching probability is extremely low, so these poor features can be filtered out.

[0086] It can be understood that, taking the above example, there are n first candidate trajectory points for the first trajectory point and m second candidate trajectory points for the second trajectory point. For each first candidate trajectory point, the above formula (2) can be used to calculate the cumulative matching probability between each second candidate trajectory point and the first candidate trajectory point, that is, each first candidate trajectory point can calculate m cumulative matching probabilities, and then, the cumulative matching probability with the largest value can be screened out from the m cumulative matching probabilities to serve as the final cumulative matching probability of the first candidate trajectory point.

[0087] The embodiment of the present application calculates the actual path parameters (such as length, direction, speed, etc.) between the first trajectory point and the second trajectory point, and compares them with the path parameters between the candidate trajectory points, so as to quantify the similarities and differences between the trajectory points. The calculation of the path mileage difference, path direction difference and path speed difference provides a specific quantitative indicator for evaluating the accuracy of the candidate trajectory points.

[0088] After the basic matching probability and the cumulative matching probability are calculated, step 303 is executed.

[0089] Step 303: Calculate the matching probability of the first candidate trajectory point according to the basic matching probability and the cumulative matching probability.

[0090] After the basic matching probability and the cumulative matching probability are obtained, the matching probability of the first candidate trajectory point can be calculated based on the basic matching probability and the cumulative matching probability, that is, the matching probability of the candidate trajectory point = basic matching probability + cumulative matching probability.

[0091] The embodiment of the present application calculates the straight-line distance between the first trajectory point and the first candidate trajectory point to preliminarily evaluate the proximity between the two and provide a basis for determining the basic matching probability. The introduction of the cumulative matching probability further considers the correlation and consistency between the first candidate trajectory point and other second candidate trajectory points, thereby improving the accuracy and reliability of trajectory point matching.

[0092] After the matching probability of the first candidate trajectory point is calculated according to the first trajectory point information, the second trajectory point information, the trajectory point information of the first candidate trajectory point and the trajectory point information of the second candidate trajectory point, step 104 is performed.

[0093] Step 104: Filtering a preset number of candidate trajectory points from the first candidate trajectory points according to the matching probability.

[0094] The preset number refers to the number of track points that are preset for screening candidate track points. In this example, the preset number may be 3, 5, etc. Specifically, the specific value of the preset number may be determined according to business requirements, and this embodiment does not limit this.

[0095] After obtaining the matching probability of the first candidate trajectory point, a preset number of candidate trajectory points can be screened out from the first candidate trajectory points according to the matching probability. Specifically, a preset number of candidate trajectory points with the largest matching probability can be screened out from the first candidate trajectory points. For example, the first candidate trajectory points include: trajectory point 1, trajectory point 2, ..., trajectory point 10, the preset number is 3, and the matching probabilities of trajectory point 1, trajectory point 2, ..., trajectory point 10 are: 0.3, 0.6, 0.8, 0.5, 0.4, 0.7, 0.6, 0.9, 0.2, 0.3, respectively. At this time, trajectory point 3 (matching probability 0.8), trajectory point 6 (matching probability 0.7) and trajectory point 8 (matching probability 0.9) can be screened out from trajectory point 1, trajectory point 2, ..., trajectory point 10 as candidate trajectory points, etc.

[0096] It can be understood that the above examples are merely examples listed for a better understanding of the technical solutions of the embodiments of the present application, and are not intended to be the sole limitation to the embodiments.

[0097] After a preset number of candidate trajectory points are screened out from the first candidate trajectory points according to the assigned probabilities, step 105 is executed.

[0098] Step 105: Determine a target candidate trajectory point among the candidate trajectory points according to the road network model corresponding to the candidate trajectory points, so as to locate the position of the vehicle at the current moment.

[0099] After a preset number of candidate trajectory points are screened out from the first candidate trajectory points according to the assigned probabilities, target candidate trajectory points among the candidate trajectory points may be determined according to the road network model corresponding to the candidate trajectory points to locate the position of the vehicle at the current moment.

[0100] The embodiment of the present application introduces a road network model into the road network matching, uses the road network model to clean the trajectory points, and after the probability matching, finely screens the matching results, thereby solving the problem of easy matching errors in real-time matching in scenes such as intersections and parallel roads, and thus improving the matching accuracy of real-time road network matching.

[0101] In this embodiment, 8 road network models are introduced, such as Figure 4As shown in the figure, the road network is divided into 8 basic types: two-way roads, separated up-and-down roads, confused parallel roads, ordinary parallel roads, T-junctions, crossroads, grid intersections, and spatially intersecting roads. The basic types can be combined with each other to generate more complex road network types. The matching is adjusted according to different road network types, and the matching probability and the road network model are combined to make a refined selection of the matching results. Among them, a two-way road refers to a road that can be traveled in two directions. A separated up-and-down road refers to two parallel one-way roads. A confused parallel road refers to a road where the road width changes and is divided into two roads. An ordinary parallel road refers to two or more roads that are visually parallel, have no intersection points, and generally have a constant distance. A T-junction refers to an intersection where two roads intersect and form a shape similar to the letter "T". A crossroad refers to a place where two roads cross and form a four-way road intersection. A grid intersection refers to an intersection formed by the intersection of four roads, and the shape is similar to the Chinese character "井". A spatially intersecting road refers to a road where there are intersection points in space for traffic facilities such as roads, bridges, and tunnels.

[0102] Next, the matching process of target candidate trajectory points for 8 types of road models will be described in detail in combination with specific embodiments.

[0103] In a specific implementation of the present application, when the road network model of the candidate trajectory point is a two-way road model, the distance between the first trajectory point and the target straight line is obtained, and the target straight line is the connection line between the first point and the last point of the second trajectory points. When the distance is less than a pre-set distance threshold, the candidate trajectory point on the two-way road is determined as the target candidate trajectory point. When the distance is greater than or equal to the distance threshold, the candidate trajectory point on the connecting road of the U-turn is determined as the target candidate trajectory point.

[0104] As Figure 5 shown, the two-way road model is mainly used in the matching and screening to solve the problem that it is difficult to distinguish the matching results when there are both in-line U-turns and U-turns at the U-turn. As Figure 5 shown, the black solid line is the road, the arrows on the road are the directions in which the road can be traveled, the gray points are the trajectory points, and the arrows between the gray points are the trajectory driving directions. Figure 5 The left figure is a U-turn in place, and the right figure is a U-turn through the U-turn. When the trajectory makes a U-turn on different roads, there are differences in the offset of the U-turn distance of the trajectory. However, in the matching probability, due to the similar characteristics between the trajectory points, it is impossible to distinguish. By introducing the road network model and adding the distance characteristics between the current trajectory point and the trajectory point before the U-turn, when the distance characteristic of the trajectory point is less than the threshold (the distance threshold is determined by analyzing the U-turn distance characteristics of the U-turn in place and the separated up-and-down road), the two-way road is preferentially selected, otherwise the connecting road of the U-turn is selected.

[0105] In another specific implementation of the present application, when the road network model of the candidate trajectory point is a road model with separated upper and lower lines, it is determined whether the first trajectory point and the second trajectory point are on the same road. When the first trajectory point and the second trajectory point are not on the same road, the candidate trajectory point is cleared, and the first trajectory point is corrected, and the corrected trajectory point is used as the target candidate trajectory point.

[0106] like Figure 6 As shown in , the driving direction of the road with separated upper and lower lines is fixed and cannot be turned. Therefore, if the previous matching point is on the road with separated upper and lower lines and the current track point has a turning behavior, it can be considered that the current track point has noise, and noise cleaning is performed before matching. Figure 6 As shown in the figure, the previous track points 1, 2, and 3 travel on the road with separated upper and lower lines, and the gray-filled track point 4 has track drift, so noise cleaning is performed to obtain the white-filled track point 4 (i.e., the corrected track point), while the gray track point 5 not only has longitudinal offset, but also horizontal noise, which is directly cleaned in the track cleaning without matching. If the upper and lower line separation road model is not introduced, it will be easy to directly think that the track has turned around by using probability matching.

[0107] In another specific implementation of the present application, when the road network model of the candidate trajectory point is a confused parallel road model, two roads closest to the first trajectory point are obtained. The path planning road of the two roads can be determined according to the path planning result of the vehicle, and the candidate trajectory point on the path planning road is used as the target candidate trajectory point.

[0108] like Figure 7 As shown in the figure, there are two parallel divergent roads (dashed roads) in the direction of travel on a road. Because the road is confused and the manual work cannot determine the road where the track point is located, the track point will be matched to both roads at the same time during matching, and then the business side will select the track point on the consistent road based on the path planning result. If there is no path planning, the subsequent business needs to consider the situation of vehicles on different roads at the same time.

[0109] In another specific implementation of the present application, when the road network model of the candidate trajectory points is a parallel road model, the candidate trajectory points with the highest matching probability can be screened out from the candidate trajectory points as the target candidate trajectory points. That is, for ordinary parallel roads, two roads with parallel travel directions have differences in the preceding entry roads. For ordinary parallel roads, the preceding trajectory points that need to be cached are matched to determine the entry roads of the parallel roads, and then the specific driving roads of the vehicles are distinguished according to the matching probability matching, so as to prevent matching errors caused by similar parallel matching features of the roads, thereby improving the matching accuracy.

[0110] In another specific implementation of the present application, when the road network model of the candidate trajectory point is a T-junction model, the third trajectory point and the fourth trajectory point in the second trajectory point can be obtained, the first trajectory point, the third trajectory point and the fourth trajectory point are continuous trajectory points, and the time of the third trajectory point is later than the time of the fourth trajectory point. And the angle between the line connecting the first trajectory point and the third trajectory point and the line connecting the third trajectory point and the fourth trajectory point is obtained. Finally, the target candidate trajectory point in the candidate trajectory points can be determined according to the angle and the pre-set angle threshold.

[0111] like Figure 8 As shown in the figure, the turning road for vehicles at T-junctions is fixed, so when the trajectory changes in driving direction, the turning road is preferred to avoid matching errors caused by trajectory drift or insufficient road network accuracy. Figure 8 As shown in the figure, the direction of travel of trajectory point 4 changes at the intersection. If the matching point a has better features based on the features between trajectory points, the matching probability is higher. However, the road network is a digital expression of the real world. In reality, the intersection is a surface, and the road network has only one point. When the trajectory changes direction, the vehicle has actually passed the intersection and entered the road, and then exited the road after entering the intersection. Therefore, it is more reasonable to match point b. The T-junction model is introduced to make a refined selection of matching points a and b by judging the change in the direction of travel of trajectory point 4 (i.e., the relationship between the angle of the line connecting the continuous trajectory points and the angle threshold).

[0112] In another specific implementation of the present application, when the road network model of the candidate trajectory points is an intersection model, the candidate trajectory points located at the intersection among the candidate trajectory points can be obtained, and the candidate trajectory points located at the intersection are used as target candidate trajectory points. Fig. 9 As shown in the figure, the intersection is where two roads meet. Since the road network data is a digital representation of the real road, the intersection location road network data has only one point, while the real world is a surface. When a vehicle is driving at an intersection, there will be multiple track points. Therefore, when the track point is near the intersection point, the intersection point is matched first. On the one hand, it is more in line with the real scene; on the other hand, it can also avoid the matching error problem caused by track drift or insufficient road network accuracy. Fig. 9 As shown in the figure, based on probability matching, there are three candidate points with similar matching probabilities for trajectory point 4, in the order of a>c>b. If matching is based on probability, matching point a will be selected, but if the subsequent trajectory point is 5_1, matching point a is found to be wrong. Similarly, if matching point b is selected, if the subsequent trajectory point is 5_2, matching point b is found to be wrong. By introducing the intersection model, point c is matched first, and the matching result is normal regardless of whether the subsequent trajectory point is 5_1 or 5_2.

[0113] When the road network model of the candidate trajectory point is a tic-tac-toe intersection model, the candidate trajectory point located at the tic-tac-toe intersection among the candidate trajectory points can be obtained, and the candidate trajectory point located at the tic-tac-toe intersection can be used as the target candidate trajectory point. Similar to a crossroad, a tic-tac-toe intersection is the result of a road intersection with physical isolation in reality. Unlike a crossroad, a tic-tac-toe intersection is composed of four roads within the intersection. Therefore, for the vehicle turning trajectory point, the four roads within the intersection should be preferably selected for matching.

[0114] When the road network model of the candidate trajectory points is a spatial intersection road network model, the candidate trajectory points located on the spatial intersection road can be removed from the candidate trajectory points to obtain the target candidate trajectory points. Spatial intersection is the intersection of the overpass road and the road surface in space. Normally, it is impossible to connect them. Therefore, they can be removed in advance during matching to prevent the overall drift of the trajectory from causing matching judgment errors.

[0115] The vehicle trajectory point matching process can be combined Fig.11 The following is a detailed description. Fig.11 As shown, the process may include:

[0116] 1. Get the vehicle's track point data, including the vehicle's current track point and previous track point.

[0117] 2. Obtain the vehicle cached trajectory point data (i.e., the trajectory point data of the previous trajectory point) and the road network data within a certain range of the trajectory point data. Specifically, the platform can be used to obtain the vehicle's trajectory point information for a period of time stored in the platform based on the driver's virtual code, and the road network information within a certain range of the trajectory point coordinates can be obtained through spatial indexing.

[0118] 3. Calculate the distance between the denoised GPS trajectory point and the candidate road neighboring point in the road network, and calculate the basic matching probability between the denoised GPS trajectory point and the road section neighboring point. The basic matching probability can be calculated by referring to the above formula (1).

[0119] 4. Based on the GPS cache data, calculate the driving distance, driving direction and driving speed characteristics of the denoised GPS trajectory points. Based on the cached road network matching data, calculate the road mileage, driving direction, road speed limit and road type characteristics of the road section neighboring points and the cached road network matching points. And calculate the cumulative matching probability of the denoised GPS trajectory points and the road section neighboring points. The calculation method can refer to the above formula (2).

[0120] 5. Based on the basic matching probability and the cumulative matching probability, the final matching probability of the neighboring points of the denoised GPS trajectory points in different road sections is calculated, that is, the sum of the basic matching probability and the cumulative matching probability is taken as the final matching probability.

[0121] 6. Calculate the road network model of all candidate road sections: two-way roads, roads with upper and lower lanes separated, ordinary parallel roads, confused parallel roads, etc. Finally, combine the road network model and matching probability to determine the road network matching result of the vehicle. That is, introduce the road network model, use the road network model to clean the trajectory points, and after the probability matching, finely screen the matching results, thereby improving the matching accuracy of real-time road network matching.

[0122] The embodiment of the present application introduces a road network model into the road network matching, uses the road network model to clean the trajectory points, and after the probability matching, finely screens the matching results, thereby improving the matching accuracy of the real-time road network matching, so as to solve the matching error problem of the existing matching method. Fig.10 As shown in the figure, when the trajectory passes through the intersection, when the trajectory point 4 is matched in real time, due to the drift of the trajectory point, the probability model such as the hidden Markov model will match if Fig.10 The black point position in the black vertical axis direction in A, but from track points 5 and 6, it can be found that the matching result of track point 4 is wrong. After the introduction of the road network model, for the track points near the intersection, the intersection point will be matched first, such as Fig.10 The black dot position on the horizontal axis in B shows that the matching result after introducing the road network model is more reasonable. When the trajectory passes through a confusing parallel road, a probability model such as the hidden Markov model is used. Since the trajectory characteristics are more inclined to go straight, if only the result corresponding to the maximum matching probability is selected, it will match if Fig.10 The black dot position of the lower road in C, but from track points 5 and 6, it can be found that the matching results are wrong. After introducing the road network model, it can be determined that the current scene is a confused parallel road. Due to the confused parallel roads, it is impossible for humans to determine the correct matching road without subsequent trajectory information. Therefore, track points 2, 3 and 4 are all matched to 2 confused parallel roads, as shown in 10D. After track point 5 appears, it is determined that the upper road of the parallel road should be the correct road, and then it is changed to a matching result. This can avoid the problem of incorrect matching results during driving on confused parallel roads.

[0123] The embodiment of the present application introduces a road network model to refine the probability matching results; the road network model is not limited to the above-mentioned eight types of two-way roads, upper and lower line separation roads, confused parallel roads, ordinary parallel roads, T-junctions, crossroads, tic-tac-toe intersections and spatial intersections, and also includes the combination of these eight types. At the same time, it proposes refined processing of the matching results of different models, including intersection point priority matching, confused parallel road simultaneous matching, etc.

[0124] The vehicle positioning method provided in the embodiment of the present application obtains the first trajectory point information of the first trajectory point of the vehicle at the current moment, and the second trajectory point information of the second trajectory point of the vehicle at N moments before the current moment, N is a positive integer, and the first trajectory point and the second trajectory point are continuous trajectory points. A first candidate trajectory point corresponding to the first trajectory point and a second candidate trajectory point corresponding to the second trajectory point are obtained. The matching probability of the first candidate trajectory point is calculated according to the first trajectory point information, the second trajectory point information, the trajectory point information of the first candidate trajectory point and the trajectory point information of the second candidate trajectory point. According to the matching probability, a preset number of candidate trajectory points are screened out from the first candidate trajectory point. According to the road network model corresponding to the first candidate trajectory point, the target candidate trajectory point among the candidate trajectory points is determined to locate the position of the vehicle at the current moment. The embodiment of the present application introduces a road network model into the road network matching, uses the road network model to clean the trajectory points, and after the probability matching, the matching results are finely screened, so as to solve the problem that the real-time matching in scenes such as intersections and parallel roads is prone to matching errors, thereby improving the matching accuracy of the real-time road network matching.

[0125] Reference Fig.12 , shows a schematic diagram of the structure of a vehicle positioning device provided by an embodiment of the present application, such as Fig.12 As shown, the vehicle positioning device 1200 may include the following modules:

[0126] A trajectory point information acquisition module 1210 is used to acquire first trajectory point information of a first trajectory point of a vehicle at a current moment, and second trajectory point information of a second trajectory point of the vehicle at N moments before the current moment, where N is a positive integer, and the first trajectory point and the second trajectory point are continuous trajectory points;

[0127] A candidate trajectory point acquisition module 1220, configured to acquire a first candidate trajectory point corresponding to the first trajectory point, and a second candidate trajectory point corresponding to the second trajectory point;

[0128] A matching probability calculation module 1230, configured to calculate a matching probability of the first candidate trajectory point according to the first trajectory point information, the second trajectory point information, the trajectory point information of the first candidate trajectory point, and the trajectory point information of the second candidate trajectory point;

[0129] A candidate trajectory point screening module 1240, configured to screen a preset number of candidate trajectory points from the first candidate trajectory points according to the matching probability;

[0130] The vehicle position positioning module 1250 is used to determine the target candidate trajectory point among the candidate trajectory points according to the road network model corresponding to the candidate trajectory points, so as to locate the position of the vehicle at the current moment.

[0131] Optionally, the candidate trajectory point acquisition module includes:

[0132] a road network information range determining unit, configured to determine a first road network information range corresponding to the first track point according to the track point coordinates of the first track point and a preset query range; and to determine a second road network information range corresponding to the second track point according to the track point coordinates of the second track point and the query range;

[0133] A road acquisition unit, used to acquire all first roads within the first road network information range and all second roads within the second road network information range;

[0134] The candidate trajectory point acquisition unit is used to take the point on all the first roads that is closest to the first trajectory point as the first candidate trajectory point, and take the point on all the second roads that is closest to the second trajectory point as the second candidate trajectory point.

[0135] Optionally, the matching probability calculation module includes:

[0136] a basic matching probability determining unit, configured to calculate a straight-line distance between the first trajectory point and the first candidate trajectory point according to the first trajectory point information and the trajectory point information of the first candidate trajectory point, and determine a basic matching probability of the first candidate trajectory point according to the straight-line distance;

[0137] a cumulative matching probability calculation unit, configured to calculate a cumulative matching probability of the first candidate trajectory point according to the trajectory point information of the first candidate trajectory point and the trajectory point information of the second candidate trajectory point;

[0138] A matching probability calculation unit is used to calculate the matching probability of the first candidate trajectory point according to the basic matching probability and the cumulative matching probability.

[0139] Optionally, the cumulative matching probability calculation unit includes:

[0140] A first path information calculation subunit, configured to calculate a first path length, a first path direction, and a first path speed between the first trajectory point and the second trajectory point according to the first trajectory point information and the second trajectory point information;

[0141] a second path information calculation subunit, configured to calculate a second path length, a second path direction, and a second path speed between the first candidate trajectory point and the second candidate trajectory point according to the trajectory point information of the first candidate trajectory point and the trajectory point information of the second candidate trajectory point;

[0142] a path difference calculation subunit, configured to calculate a path mileage difference between the first path length and the second path length, a path direction difference between the first path direction and the second path direction, and a path speed difference between the first path speed and the second path speed;

[0143] The cumulative matching probability calculation subunit is used to calculate the cumulative matching probability of the first candidate trajectory point based on the path mileage difference, the path direction difference and the path speed difference.

[0144] Optionally, the vehicle location positioning module includes:

[0145] a distance acquisition unit, configured to acquire the distance between the first trajectory point and a target straight line when the road network model is a bidirectional road model; the target straight line is a line connecting the first point and the last point in the second trajectory point;

[0146] A first target point determination unit, configured to determine, when the distance is less than a preset distance threshold, a candidate trajectory point on the two-way road as the target candidate trajectory point;

[0147] The second target point determination unit is used to determine a candidate trajectory point on the U-turn connection road as the target candidate trajectory point when the distance is greater than or equal to the distance threshold.

[0148] Optionally, the vehicle location positioning module includes:

[0149] a trajectory point determination unit, configured to determine whether the first trajectory point and the second trajectory point are on the same road when the road network model is a road model with separated upper and lower lines;

[0150] The first target point acquisition unit is used to clear the candidate track point when the first track point and the second track point are not on the same road, and to correct the first track point and use the corrected track point as the target candidate track point.

[0151] Optionally, the vehicle location positioning module includes:

[0152] A road acquisition unit, configured to acquire two roads closest to the first trajectory point when the road network model is a confused parallel road model;

[0153] The second target point acquisition unit is used to determine a path planning road among the two roads according to the path planning result of the vehicle, and use the candidate trajectory points on the path planning road as the target candidate trajectory points.

[0154] Optionally, the vehicle location positioning module includes:

[0155] The third target point acquisition unit is used to select a candidate trajectory point with the highest matching probability from the candidate trajectory points as the target candidate trajectory point when the road network model is a parallel road model.

[0156] Optionally, the vehicle location positioning module includes:

[0157] a trajectory point acquisition unit, configured to acquire, when the road network model is a T-junction model, a third trajectory point and a fourth trajectory point in the second trajectory point, wherein the first trajectory point, the third trajectory point and the fourth trajectory point are continuous trajectory points, and a time of the third trajectory point is later than a time of the fourth trajectory point;

[0158] an angle acquisition unit, configured to acquire an angle between a line connecting the first trajectory point and the third trajectory point, and a line connecting the third trajectory point and the fourth trajectory point;

[0159] The third target point determination unit is used to determine a target candidate trajectory point among the candidate trajectory points according to the angle and a preset angle threshold.

[0160] Optionally, the vehicle location positioning module includes:

[0161] a fourth target point acquisition unit, configured to acquire, when the road network model is an intersection model, candidate trajectory points located at intersections among the candidate trajectory points, and use the candidate trajectory points located at intersections as the target candidate trajectory points;

[0162] a fifth target point acquisition unit, configured to acquire, when the road network model is a tic-tac-toe intersection model, a candidate trajectory point located at a tic-tac-toe intersection among the candidate trajectory points, and use the candidate trajectory point located at the tic-tac-toe intersection as the target candidate trajectory point;

[0163] The sixth target point acquisition unit is used to remove the candidate trajectory points located on the spatial intersection road from the candidate trajectory points when the road network model is a spatial intersection road network model, so as to obtain the target candidate trajectory point.

[0164] The vehicle positioning device provided in the embodiment of the present application obtains the first trajectory point information of the first trajectory point of the vehicle at the current moment, and the second trajectory point information of the second trajectory point of the vehicle at N moments before the current moment, where N is a positive integer, and the first trajectory point and the second trajectory point are continuous trajectory points. A first candidate trajectory point corresponding to the first trajectory point and a second candidate trajectory point corresponding to the second trajectory point are obtained. The matching probability of the first candidate trajectory point is calculated based on the first trajectory point information, the second trajectory point information, the trajectory point information of the first candidate trajectory point and the trajectory point information of the second candidate trajectory point. According to the matching probability, a preset number of candidate trajectory points are screened out from the first candidate trajectory points. According to the road network model corresponding to the first candidate trajectory point, the target candidate trajectory point among the candidate trajectory points is determined to locate the position of the vehicle at the current moment. The embodiment of the present application introduces a road network model into the road network matching, uses the road network model to clean the trajectory points, and after the probability matching, the matching results are finely screened, so as to solve the problem that the real-time matching in scenes such as intersections and parallel roads is prone to matching errors, thereby improving the matching accuracy of the real-time road network matching.

[0165] An embodiment of the present application further provides an electronic device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program implements the above-mentioned vehicle positioning method when executed by the processor.

[0166] Fig.13 FIG. 1 is a schematic diagram showing the structure of an electronic device 1300 according to an embodiment of the present invention. Fig.13 As shown, the electronic device 1300 includes a central processing unit (CPU) 1301, which can perform various appropriate actions and processes according to computer program instructions stored in a read-only memory (ROM) 1302 or computer program instructions loaded from a storage unit 1308 to a random access memory (RAM) 1303. In the RAM 1303, various programs and data required for the operation of the electronic device 1300 can also be stored. The CPU 1301, the ROM 1302, and the RAM 1303 are connected to each other via a bus 1304. An input / output (I / O) interface 1305 is also connected to the bus 1304.

[0167] Multiple components in the electronic device 1300 are connected to the I / O interface 1305, including: an input unit 1306, such as a keyboard, a mouse, a microphone, etc.; an output unit 1307, such as various types of displays, speakers, etc.; a storage unit 1308, such as a disk, an optical disk, etc.; and a communication unit 1309, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 1309 allows the electronic device 1300 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0168] The various processes and processing described above may be performed by the processing unit 1301. For example, the method of any of the above embodiments may be implemented as a computer software program, which is tangibly contained in a computer-readable medium, such as the storage unit 1308. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 1300 via the ROM 1302 and / or the communication unit 1309. When the computer program is loaded into the RAM 1303 and executed by the CPU 1301, one or more actions in the method described above may be performed.

[0169] In addition, an embodiment of the present application further provides a computer-readable storage medium on which a computer program is stored, and when the program is executed by a processor, the above-mentioned vehicle positioning method is implemented.

[0170] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0171] Those skilled in the art will appreciate that the embodiments of the present application can be provided as methods, devices, or computer program products. Therefore, the present application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0172] The embodiments of the present application are described with reference to the flowcharts and / or block diagrams of the methods, terminals (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing terminal to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing terminal generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0173] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing terminal to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0174] These computer program instructions can also be loaded onto a computer or other programmable data processing terminal so that a series of operating steps are executed on the computer or other programmable terminal to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable terminal. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0175] Although the preferred embodiments of the present application have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the embodiments of the present application.

[0176] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or terminal including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or terminal. In the absence of further restrictions, the elements defined by the statement "comprise a ..." do not exclude the presence of other identical elements in the process, method, article or terminal including the elements.

[0177] The above is a detailed introduction to a vehicle positioning method, a vehicle positioning device, an electronic device and a computer-readable storage medium provided by the present application. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea. At the same time, for a person skilled in the art, according to the idea of ​​the present application, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A vehicle positioning method, characterized in that: The method comprises: Acquire first trajectory point information of a first trajectory point of a vehicle at a current moment, and second trajectory point information of a second trajectory point of the vehicle at N moments before the current moment, where N is a positive integer, and the first trajectory point and the second trajectory point are continuous trajectory points; Acquire a first candidate trajectory point corresponding to the first trajectory point, and a second candidate trajectory point corresponding to the second trajectory point; Calculating a matching probability of the first candidate trajectory point according to the first trajectory point information, the second trajectory point information, the trajectory point information of the first candidate trajectory point, and the trajectory point information of the second candidate trajectory point; According to the matching probability, a preset number of candidate trajectory points are screened out from the first candidate trajectory points; According to the road network model corresponding to the candidate trajectory points, a target candidate trajectory point among the candidate trajectory points is determined to locate the position of the vehicle at the current moment.

2. The method according to claim 1, characterized in that The obtaining of a first candidate trajectory point corresponding to the first trajectory point and a second candidate trajectory point corresponding to the second trajectory point includes: Determine a first road network information range corresponding to the first track point according to the track point coordinates of the first track point and a preset query range; and determine a second road network information range corresponding to the second track point according to the track point coordinates of the second track point and the query range; Acquire all first roads within the first road network information range, and all second roads within the second road network information range; The point on all the first roads that is closest to the first trajectory point is taken as a first candidate trajectory point, and the point on all the second roads that is closest to the second trajectory point is taken as a second candidate trajectory point.

3. The method according to claim 1, characterized in that: The calculating the matching probability of the first candidate trajectory point according to the first trajectory point information, the second trajectory point information, the trajectory point information of the first candidate trajectory point and the trajectory point information of the second candidate trajectory point includes: Calculate the straight-line distance between the first trajectory point and the first candidate trajectory point according to the first trajectory point information and the trajectory point information of the first candidate trajectory point, and determine the basic matching probability of the first candidate trajectory point according to the straight-line distance; Calculating a cumulative matching probability of the first candidate trajectory point according to the trajectory point information of the first candidate trajectory point and the trajectory point information of the second candidate trajectory point; The matching probability of the first candidate trajectory point is calculated according to the basic matching probability and the cumulative matching probability.

4. The method according to claim 3, characterized in that The calculating, according to the trajectory point information of the first candidate trajectory point and the trajectory point information of the second candidate trajectory point, a cumulative matching probability of the first candidate trajectory point includes: Calculate a first path length, a first path direction, and a first path speed between the first trajectory point and the second trajectory point according to the first trajectory point information and the second trajectory point information; Calculating a second path length, a second path direction, and a second path speed between the first candidate trajectory point and the second candidate trajectory point according to the trajectory point information of the first candidate trajectory point and the trajectory point information of the second candidate trajectory point; Calculating a path mileage difference between the first path length and the second path length, a path direction difference between the first path direction and the second path direction, and a path speed difference between the first path speed and the second path speed; Based on the path mileage difference, the path direction difference and the path speed difference, a cumulative matching probability of the first candidate trajectory point is calculated.

5. The method according to claim 1, characterized in that: The step of determining a target candidate trajectory point among the candidate trajectory points according to the road network model corresponding to the candidate trajectory points comprises: When the road network model is a bidirectional road model, obtaining the distance between the first trajectory point and a target straight line; the target straight line is a line between the first point and the last point in the second trajectory point; When the distance is less than a preset distance threshold, determining the candidate trajectory point on the two-way road as the target candidate trajectory point; When the distance is greater than or equal to the distance threshold, the candidate trajectory point on the U-turn connection road is determined as the target candidate trajectory point.

6. The method according to claim 1, characterized in that The step of determining a target candidate trajectory point among the candidate trajectory points according to the road network model corresponding to the candidate trajectory points comprises: In the case where the road network model is a road model with separated upper and lower lines, determining whether the first track point and the second track point are on the same road; In the case that the first trajectory point and the second trajectory point are not located on the same road, the candidate trajectory point is cleared, and the first trajectory point is corrected, and the corrected trajectory point is used as the target candidate trajectory point.

7. The method according to claim 1, characterized in that The step of determining a target candidate trajectory point among the candidate trajectory points according to the road network model corresponding to the candidate trajectory points comprises: When the road network model is a confused parallel road model, obtaining two roads closest to the first trajectory point; A path planning road among the two roads is determined according to the path planning result of the vehicle, and candidate trajectory points on the path planning road are used as the target candidate trajectory points.

8. The method according to claim 1, characterized in that The step of determining a target candidate trajectory point among the candidate trajectory points according to the road network model corresponding to the candidate trajectory points comprises: In the case where the road network model is a parallel road model, a candidate trajectory point with the highest matching probability is selected from the candidate trajectory points as the target candidate trajectory point.

9. The method according to claim 1, characterized in that: The determining, according to the road network model corresponding to the candidate trajectory points, a target candidate trajectory point among the candidate trajectory points comprises: When the road network model is a T-junction model, obtaining a third trajectory point and a fourth trajectory point in the second trajectory point, wherein the first trajectory point, the third trajectory point and the fourth trajectory point are continuous trajectory points, and a time of the third trajectory point is later than a time of the fourth trajectory point; Acquire an angle between a line connecting the first trajectory point and the third trajectory point and a line connecting the third trajectory point and the fourth trajectory point; According to the angle and a preset angle threshold, a target candidate trajectory point among the candidate trajectory points is determined.

10. The method according to claim 1, characterized in that The determining, according to the road network model corresponding to the candidate trajectory points, a target candidate trajectory point among the candidate trajectory points comprises: In the case where the road network model is an intersection model, obtaining candidate trajectory points located at the intersection among the candidate trajectory points, and using the candidate trajectory points located at the intersection as the target candidate trajectory points; In the case where the road network model is a tic-tac-toe intersection model, obtaining candidate trajectory points located at tic-tac-toe intersections among the candidate trajectory points, and using the candidate trajectory points located at tic-tac-toe intersections as the target candidate trajectory points; In the case where the road network model is a spatial intersection road network model, candidate trajectory points located on spatial intersection roads are removed from the candidate trajectory points to obtain the target candidate trajectory points.

11. A vehicle positioning device, characterized in that: The device comprises: a trajectory point information acquisition module, used to acquire first trajectory point information of a first trajectory point of the vehicle at a current moment, and second trajectory point information of a second trajectory point of the vehicle at N moments before the current moment, where N is a positive integer, and the first trajectory point and the second trajectory point are continuous trajectory points; A candidate trajectory point acquisition module, used to acquire a first candidate trajectory point corresponding to the first trajectory point, and a second candidate trajectory point corresponding to the second trajectory point; a matching probability calculation module, configured to calculate a matching probability of the first candidate trajectory point according to the first trajectory point information, the second trajectory point information, the trajectory point information of the first candidate trajectory point and the trajectory point information of the second candidate trajectory point; A candidate trajectory point screening module, configured to screen a preset number of candidate trajectory points from the first candidate trajectory points according to the matching probability; The vehicle position positioning module is used to determine the target candidate trajectory point among the candidate trajectory points according to the road network model corresponding to the candidate trajectory points, so as to locate the position of the vehicle at the current moment.

12. An electronic device, characterized in that: include: A processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the processor implements the vehicle positioning method according to any one of claims 1 to 10 when executing the program.

13. A computer-readable storage medium, characterized in that: When the instructions in the storage medium are executed by a processor of an electronic device, the electronic device is enabled to execute the vehicle positioning method according to any one of claims 1 to 10.

Images