A method, device, electronic device and storage medium for completing missing tracks
By screening and selecting vehicle trajectories, the problem of inefficient completion of vehicle trajectory missing completion in the prior art is solved, and a faster trajectory completion process is achieved.
Patent Information
- Application Number
- CN202210191819.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2022-02-28
- Publication Date
- 2024-12-03
- Estimated Expiration
- 2042-02-28
AI Technical Summary
In the complete completion of vehicle trajectory missing, the calculation of the shortest time path is complicated and time-consuming, resulting in inefficient efficiency, especially when the data volume is large.
By obtaining the monitoring point identification of the starting and ending positions of the missing track section, the candidate vehicle trajectory is selected, and the target vehicle trajectory is selected according to the vehicle's pass ratio to complete it, the process of calculating the shortest time path is avoided.
The efficiency of vehicle trajectory missing completion is improved, and the calculation time is reduced, especially when the data volume is large.
Smart Images

Figure CN114817660B_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of urban smart transportation, and in particular to a method, device, electronic device and storage medium for completing missing trajectories. Background Art
[0002] With the development of smart urban transportation, a large number of checkpoints have been deployed on urban roads. Checkpoints can record various vehicle information at different times and map these vehicle information to maps to record vehicle driving trajectories, providing real-time and complete vehicle information support for road traffic index calculations. Furthermore, the number of methods for completing missing vehicle trajectories based on checkpoint data is increasing.
[0003] For example, in daily life, in order to solve the problem of missing vehicle trajectories, it is necessary to predict the vehicle's driving trajectory based on a large amount of tollgate data obtained by the tollgate equipment, so as to complete the vehicle trajectory with missing trajectories.
[0004] Specifically, in actual scenarios, we first obtain vehicle information on the urban road network, and map the relevant information of the checkpoint equipment to the urban road network, establish a complete topological map of the checkpoint equipment and the urban road network, and then, based on the checkpoint equipment and the topological map of the urban road network, establish a static table of the relationship between the shortest time path between any two checkpoint devices on the urban road network, and finally, according to the preset cycle time and the static table of the relationship between the shortest time path, complete the checkpoint data in real time.
[0005] However, the vehicle trajectory missing completion using the above method will complete the checkpoint data in real time based on the static table of the shortest time path relationship. Since the process of calculating the shortest time path is relatively cumbersome and takes a lot of time when the amount of data is large, the above method will reduce the efficiency of vehicle trajectory missing completion. Summary of the invention
[0006] The present application provides a missing track detection method, system, electronic device and storage medium to improve the efficiency of vehicle missing track completion.
[0007] In a first aspect, an embodiment of the present application provides a method for completing missing trajectories, the method comprising:
[0008] Based on the track missing section of the target vehicle, the monitoring point identifiers corresponding to the starting position point and the ending position point of the track missing section are obtained.
[0009] Based on the obtained monitoring point identifier, at least one candidate vehicle trajectory is screened out from the vehicle trajectory database; wherein each candidate vehicle trajectory includes: complete road section information between a starting position point and an ending position point.
[0010] Based on the number of vehicle passes corresponding to each of the at least one candidate vehicle trajectories within a specified historical time range and the total number of vehicle passes corresponding to the at least one candidate vehicle trajectory, a target vehicle trajectory is selected from the at least one candidate vehicle trajectory.
[0011] Based on the complete road section information contained in the target vehicle trajectory, the missing sections of the trajectory are completed.
[0012] In a second aspect, an embodiment of the present application further provides a device for completing missing tracks, the device comprising:
[0013] The acquisition module is used to acquire the monitoring point identifiers corresponding to the starting position point and the ending position point of the track missing section based on the track missing section of the target vehicle.
[0014] The screening module is used to screen out at least one candidate vehicle track from the vehicle track database based on the obtained monitoring point identification; wherein each candidate vehicle track includes: complete road section information between a starting position point and an ending position point.
[0015] The processing module is used to select a target vehicle trajectory from at least one candidate vehicle trajectory based on the number of vehicle passes corresponding to each of the at least one candidate vehicle trajectory and the total number of vehicle passes corresponding to the at least one candidate vehicle trajectory within a specified historical time range; and complete the missing sections of the trajectory based on the complete section information contained in the target vehicle trajectory.
[0016] In an optional embodiment, before obtaining the monitoring point identifiers corresponding to the starting position point and the ending position point of the track missing section based on the track missing section of the target vehicle, the obtaining module is further used to:
[0017] Obtain location information corresponding to at least two monitoring points.
[0018] Based on the position information corresponding to the at least two monitoring points, monitoring point identifiers corresponding to the at least two monitoring points are generated respectively.
[0019] In an optional embodiment, when respectively generating monitoring point identifiers corresponding to at least two monitoring points based on the position information corresponding to at least two monitoring points, the processing module is specifically configured to:
[0020] Perform geo-hash coding on the location information corresponding to at least two monitoring points respectively to obtain corresponding coding results.
[0021] Based on the values of the obtained encoding results, the encoding results are sorted to obtain the serial numbers of the corresponding encoding results.
[0022] Based on the obtained serial numbers, monitoring point identifiers of corresponding monitoring points are generated respectively.
[0023] In an optional embodiment, before obtaining the monitoring point identifiers corresponding to the starting position point and the ending position point of the track missing section based on the track missing section of the target vehicle, the obtaining module is further used to:
[0024] For each historical vehicle, perform the following operations:
[0025] At least two pieces of historical monitoring information obtained by each monitoring point for a historical vehicle within a set historical monitoring range are obtained; wherein each piece of historical monitoring information includes: the time when the corresponding monitoring point monitored a historical vehicle within the historical monitoring range.
[0026] For each two adjacent historical monitoring information among at least two historical monitoring information, the following operations are performed respectively: a historical monitoring time interval between two adjacent historical monitoring information is determined; when it is determined that the historical monitoring time interval is not greater than a preset interval threshold, a road section between the monitoring points corresponding to the two historical monitoring information is used as a candidate vehicle trajectory.
[0027] In an optional embodiment, before obtaining the monitoring point identifiers corresponding to the starting position point and the ending position point of the track missing section based on the track missing section of the target vehicle, the obtaining module is further used to:
[0028] At least two target monitoring information of the target vehicle obtained by each monitoring point on the historical vehicle trajectory are obtained; wherein each target monitoring information includes: the time when the corresponding monitoring point monitors the target vehicle on the historical vehicle trajectory.
[0029] For each two adjacent target monitoring information obtained from at least two target monitoring information, the following operations are performed respectively:
[0030] Determine the target monitoring time interval between two adjacent target monitoring information.
[0031] When it is determined that the target monitoring time interval is greater than a preset interval threshold, the section between the monitoring points corresponding to the two target monitoring information is regarded as a track missing section.
[0032] In an optional embodiment, based on the number of vehicle passes corresponding to each of at least one candidate vehicle trajectory and the total number of vehicle passes corresponding to at least one candidate vehicle trajectory within a specified historical time range, when selecting a target vehicle trajectory from at least one candidate vehicle trajectory, the acquisition module is further used to:
[0033] Obtain the number of historical vehicle passes corresponding to at least one candidate vehicle trajectory within a specified historical time range, and the total number of historical vehicle passes corresponding to at least one candidate vehicle trajectory.
[0034] Based on the obtained number of historical vehicle passes and the total number of historical vehicle passes, the historical vehicle pass ratios of the corresponding candidate vehicle trajectories are determined respectively.
[0035] Based on the obtained historical vehicle traffic proportions and the preset historical vehicle traffic proportion threshold, the target vehicle trajectory is selected from the candidate vehicle trajectories.
[0036] In an optional embodiment, based on the number of vehicle passes corresponding to each of at least one candidate vehicle trajectory and the total number of vehicle passes corresponding to at least one candidate vehicle trajectory within a specified historical time range, when selecting a target vehicle trajectory from at least one candidate vehicle trajectory, the acquisition module is further used to:
[0037] Obtain the target vehicle passing times corresponding to at least one candidate vehicle trajectory and the total target vehicle passing times corresponding to at least one candidate vehicle trajectory within a specified historical time range.
[0038] Based on the obtained number of passes of each target vehicle and the total number of passes of the target vehicle, the target vehicle pass ratio of the corresponding candidate vehicle trajectory is determined respectively.
[0039] Based on the obtained traffic proportions of each target vehicle and the preset traffic proportion threshold of the target vehicle, the target vehicle trajectory is selected from each candidate vehicle trajectory.
[0040] In a third aspect, the present application provides an electronic device, the electronic device comprising:
[0041] Memory, used to store computer programs;
[0042] The processor is used to implement the above-mentioned method steps for completing missing tracks when executing the computer program stored in the memory.
[0043] In a fourth aspect, the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method steps for completing missing traces described above are implemented.
[0044] According to a fifth aspect, a computer program product is provided. When the computer program product is called by a computer, the computer executes the steps of the method for completing missing tracks according to the first aspect.
[0045] The missing track completion method provided in the embodiment of the present application obtains at least one candidate vehicle track based on the identifiers corresponding to the starting point position and the ending point position of the missing track section, and then selects the target vehicle track based on the vehicle traffic ratio corresponding to the at least one candidate track obtained, and finally completes the missing track section based on the complete road section information of the target vehicle track. In this way, the target vehicle track is determined by the vehicle traffic ratio of each candidate vehicle track, and then the missing track section is completed, which avoids the cumbersome process of calculating the shortest time path in the traditional method, and when the amount of data is large, it takes a lot of time, thereby improving the efficiency of vehicle track missing completion. BRIEF DESCRIPTION OF THE DRAWINGS
[0046] Figure 1 The following is a schematic diagram of a system architecture applicable to the embodiments of the present application;
[0047] Figure 2 A schematic diagram of a method flow of a process for generating a monitoring point identifier provided by an embodiment of the present application is exemplified;
[0048] Figure 3 An example of a logic diagram for obtaining location information provided by an embodiment of the present application is shown;
[0049] Figure 4 A schematic diagram of a vehicle trajectory provided by an embodiment of the present application is exemplified;
[0050] Figure 5 A schematic diagram of a method for generating a monitoring point identifier provided in an embodiment of the present application is exemplified;
[0051] Figure 6 A logic diagram of obtaining a sequence number of a coding result provided by an embodiment of the present application is exemplified;
[0052] Figure 7 A schematic flow chart of a method for obtaining candidate vehicle trajectories provided in an embodiment of the present application is exemplified;
[0053] Figure 8 Another method for obtaining candidate vehicle trajectories provided in an embodiment of the present application is exemplified as a flowchart;
[0054] Fig. 9 A schematic diagram of a method for completing missing trajectories provided in an embodiment of the present application is exemplified;
[0055] Fig.10 A schematic diagram of a candidate vehicle trajectory provided by an embodiment of the present application is exemplified;
[0056] Fig.11A schematic flow chart of a method for selecting a target vehicle trajectory provided by an embodiment of the present application is exemplified;
[0057] Fig.12 The following is a flow chart of another method for selecting a target vehicle trajectory provided by an embodiment of the present application;
[0058] Fig.13 The following is a schematic diagram of the structure of a missing track completion device provided by an embodiment of the present application;
[0059] Fig.14 The schematic diagram of the structure of an electronic device provided in an embodiment of the present application is exemplified. DETAILED DESCRIPTION
[0060] In order to improve the efficiency of completing missing vehicle trajectories, in an embodiment of the present application, at least one candidate vehicle trajectory is obtained based on the identifiers corresponding to the starting point position and the ending point position of the missing trajectory section, and then the target vehicle trajectory is screened out in combination with the vehicle traffic ratio corresponding to each of the at least one candidate vehicle obtained, and finally the missing trajectory section is completed based on the complete section information of the target vehicle trajectory.
[0061] In order to better understand the embodiments of the present application, the technical terms involved in the embodiments of the present application are first explained below.
[0062] (1) Missed shot: Monitoring points A, B, and C are three consecutive monitoring points on the same vehicle trajectory. When vehicle 1 appears after monitoring point A and at monitoring point C, it must pass through monitoring point B. If the vehicle trajectory record of vehicle 1 only contains snapshot records of monitoring point A and monitoring point C, the missing snapshot record of monitoring point B is considered a missed shot.
[0063] (2) Geohash coding: Geohash coding refers to converting a longitude and latitude coordinate into a string code that can be sorted and compared. The Geohash coding rule is: the longitude range is [-180, 180] and the latitude range is [-90, 90], and the equator and the prime meridian are used as boundaries. The latitude range [-90, 0) is represented by binary 0, (0, 90] is represented by binary 1, the longitude range [-180, 0) is represented by binary 0, (0, 180] is represented by binary 1; and the geohash code is recursively divided into two halves.
[0064] Furthermore, first convert the longitude and latitude into binary according to the rule, then merge the binary codes of longitude and latitude according to the rule that longitude is in even positions and latitude is in odd positions, and finally form a Geohash code according to the Base32 encoding table.
[0065] For example, taking the latitude and longitude coordinates of monitoring point 1 [116.390705, 39.923201] as an example, the latitude 39.923201 belongs to (0, 90], so it is coded as 1; then (0, 90] is divided into two intervals (0, 45) and (45, 90], and 39.923201 is located at (0, 45), so it is coded as 0; then (0, 45) is divided into two intervals (0, 22.5) and (22.5, 45), and 39 .923201 is located at (22.5, 45), so it is encoded as 1; and so on. Through the above encoding method, the binary encoding of the latitude of monitoring point 1 is: 101110001100011111. Similarly, the binary encoding of the longitude of monitoring point 1 is: 11010010110001000100. Further, the binary encoding of longitude and latitude is combined, longitude occupies even bits, and latitude occupies odd bits, and the mixed binary encoding is: 11100 11101 00100 01111 00000 01101 01011 00001. If the Base32 encoding table uses 0-9, bz (remove a, i, l, o) these 32 characters for encoding, then the Base32 encoding corresponding to the binary mixed encoding is: wx4g0ec1.
[0066] (3) Base32 encoding: refers to encoding binary data into visible strings. The encoding rule is: given any binary data, it is divided into groups of 5 bits, and each group is encoded to obtain a visible character. For ease of understanding, in this article, the Base32 encoding table uses 32 characters 0-9, bz (remove a, i, l, o) for encoding.
[0067] It should be noted that the above-mentioned naming method of technical terms is only an example, and the embodiments of the present application do not limit the naming method of the above-mentioned technical terms.
[0068] Figure 1 The system architecture diagram applicable to the embodiment of the present application is shown as an example. Figure 1 As shown, the system architecture includes: a server 101, terminal devices (102a, 102b, 102c) and image acquisition devices (103a, 103b, 103c). The terminal device 102a is connected to the image acquisition device 103a, the terminal device 102b is connected to the image acquisition device 103b, and the terminal device 102c is connected to the image acquisition device 103c. The server 101 and the terminal devices (102a, 102b, 102c) can exchange information through wireless communication or wired communication.
[0069] Exemplarily, the server 101 can access the network through cellular mobile communication technology to communicate with the terminal devices (102a, 102b, 102c). The cellular mobile communication technology, for example, includes the fifth generation mobile communication (5th Generation Mobile Networks, 5G) technology.
[0070] Optionally, the server 101 may access the network via short-range wireless communication to communicate with the terminal devices (102a, 102b, 102c), wherein the short-range wireless communication method includes, for example, Wireless Fidelity (Wi-Fi) technology.
[0071] It should be noted that each terminal device can be connected to one or more image acquisition devices, and the embodiment of the present application does not limit the number of servers and the above-mentioned other devices. Figure 1 Only one server is used as an example for description.
[0072] The server 101 is used to obtain monitoring point identifiers corresponding to the start point and the end point of the missing section of the target vehicle's trajectory based on the missing section of the target vehicle's trajectory; based on the obtained monitoring point identifiers, screen at least one candidate vehicle trajectory from a vehicle trajectory database; based on the number of vehicle passes corresponding to each of the at least one candidate vehicle trajectory within a specified historical time range, and the total number of vehicle passes corresponding to the at least one candidate vehicle trajectory, select the target vehicle trajectory from the at least one candidate vehicle trajectory; based on the complete section information contained in the target vehicle trajectory, complete the missing section of the trajectory.
[0073] The terminal device (102a, 102b, 103c) is a device that can provide voice and / or data connectivity to users, including handheld terminal devices with wireless connection functions, vehicle-mounted terminal devices, etc.
[0074] Exemplarily, the terminal device may be: a mobile phone, a tablet computer, a laptop computer, a PDA, a mobile internet device (MID), a wearable device, a virtual reality (VR) device, an augmented reality (AR) device, a wireless terminal device in industrial control, a wireless terminal device in unmanned driving, a wireless terminal device in a smart grid, a wireless terminal device in transportation safety, a wireless terminal device in a smart city, or a wireless terminal device in a smart home, etc.
[0075] The image acquisition device (103a, 103b, 103c) is a device used to acquire images or record images, including a handheld image acquisition device with a wireless connection function, a head-mounted image acquisition device, and a fixed image acquisition device.
[0076] Exemplarily, the image acquisition device may be: a camera, a camcorder, a digital still camera (DSC), a single-lens reflex camera (SLRC), other image acquisition devices with a camera function (mobile phones, tablet computers, etc.), a video capture card, etc.
[0077] It should be noted that in the embodiment of the present application, the image acquisition device at the monitoring point is described by taking a bayonet device as an example. The bayonet device can acquire the image and vehicle trajectory information of the target vehicle, and store the acquired vehicle trajectory information in a database, and finally upload it to the terminal device.
[0078] Further, based on the above system architecture, the monitoring point identifiers corresponding to each monitoring point are obtained, see Figure 2 As shown, in the embodiment of the present application, the specific steps of generating the monitoring point identifier corresponding to each monitoring point are as follows:
[0079] S201: Obtain location information corresponding to at least two monitoring points.
[0080] Specifically, when executing step S201, the server can extract the location information of the corresponding monitoring point from the monitoring information uploaded by each monitoring point at any time according to a feature extraction algorithm based on location information; further, based on the location information corresponding to each monitoring point and combined with the data type of longitude and latitude, the server can determine the longitude and latitude coordinates corresponding to each monitoring point.
[0081] For example, see Figure 3 As shown, the server extracts features from the monitoring information corresponding to each monitoring point; then, it matches the features of the location information for all the extracted features; and finally, it selects the location information corresponding to each monitoring point. The monitoring information at least includes the vehicle information of the target vehicle and the location information of the monitoring point.
[0082] For example, see Figure 4As shown, for ease of understanding, take a certain area where 6 checkpoints are deployed as monitoring points as an example, where the road section between any two checkpoints can constitute a route, so a total of 15 routes can be constituted. The server receives the monitoring information obtained by each of the 6 checkpoints at any time, uses the feature extraction algorithm of the location information, detects the 6 monitoring information respectively, and obtains the location information corresponding to each checkpoint device. The monitoring information and location information corresponding to each checkpoint device are shown in Table 1:
[0083] Table 1
[0084]
[0085]
[0086] As can be seen from the above table, the server can extract features from each monitoring information according to the feature extraction algorithm of the location information to obtain the location information of the corresponding camera device. For example, taking camera device A as an example, the server uses the feature extraction algorithm of the location information to extract features from the monitoring information Message.JA obtained by camera device A at a certain moment, and can obtain the corresponding location information, that is, Message.LA, and so on.
[0087] Furthermore, after the server obtains the location information of the six checkpoint devices, it can obtain the longitude and latitude coordinates corresponding to the corresponding checkpoint devices from each location information according to the data type of longitude and latitude. The location information of each checkpoint device and its longitude and latitude coordinates are shown in Table 2:
[0088] Table 2
[0089] Location Information Message.LA Message.LB Message.LC Message.LD Message.LE Message.LF Longitude coordinates Lon.A Lon.B Lon.C Lon.D Lon.E Lon.F Latitude coordinates Lat.A Lat.B Lat.C Lat.D Lat.E Lat.F
[0090] As can be seen from the above table, the server can obtain the longitude and latitude coordinates corresponding to each camera device according to the data type in the location information of each camera device. Still taking camera device A as an example, the server extracts the corresponding longitude coordinate, i.e., Lon.A, from the Message.LA of camera device A according to the data type of the longitude coordinate; and extracts the corresponding latitude coordinate, i.e., Lat.A, from the Message.LA of camera device A according to the data type of the latitude coordinate. Further, the server can obtain the longitude and latitude coordinates of camera device A as (Lon.A, Lat.A) according to the longitude and latitude coordinates of camera device A.
[0091] S202: Based on the position information corresponding to the at least two monitoring points, respectively generate monitoring point identifiers corresponding to the at least two monitoring points.
[0092] In a possible implementation, when executing step S202, after obtaining the location information corresponding to at least two monitoring points, the server generates corresponding monitoring point identifiers for each monitoring point based on the latitude and longitude coordinates corresponding to each monitoring point and in combination with Geohash coding. Figure 5 As shown, the specific steps are as follows:
[0093] S2021: Perform geo-hash encoding on the location information corresponding to at least two monitoring points respectively to obtain corresponding encoding results.
[0094] Specifically, when executing step S2021, after obtaining the location information corresponding to each monitoring point, the server uses Geohash coding according to the longitude and latitude coordinates corresponding to each monitoring point to obtain corresponding coding results.
[0095] Exemplarily, still taking the longitude and latitude coordinates corresponding to each of the six card slot devices in Table 2 as an example, after obtaining the six longitude and latitude coordinates, the server uses Geohash encoding respectively, that is, encodes each longitude and latitude to obtain the corresponding binary encoding, and then merges the binary encoding of the longitude and latitude, with the longitude occupying the even number of bits and the latitude occupying the odd number of bits, to obtain the mixed binary encoding of the longitude and latitude of each card slot device, and finally obtains the corresponding Geohash encoding result according to the 32Base encoding. The Geohash encoding results corresponding to each card slot device are shown in Table 3:
[0096] Table 3
[0097]
[0098] As can be seen from the above table, the server can obtain the corresponding Geohash code according to the longitude and latitude coordinates of each card slot device. For example, taking card slot device A as an example, after obtaining the longitude and latitude coordinates (Lon.A, Lat.A) of card slot device A, the server first uses Geohash coding for the longitude Lon.A and latitude Lat.A of card slot device A to obtain the corresponding binary code, and then obtains the mixed binary code of the longitude and latitude of card slot device A according to the rule that longitude occupies even digits and latitude occupies odd digits, and finally obtains the Geohash coding result of card slot device A according to 32Base coding. Among them, the Base32 coding table uses 32 characters 0-9, bz (remove a, i, l, o) for coding.
[0099] S2022: Sort the encoding results based on the values of the encoding results obtained, and obtain serial numbers of the corresponding encoding results respectively.
[0100] Specifically, when executing step S2022, after obtaining the Geohash coding results of each card slot device, the server arranges the Geohash coding results of each monitoring point in descending order based on the values of each Geohash coding result, and then obtains the arrangement sequence number of the corresponding Geohash coding result.
[0101] For example, see Figure 6 As shown, still taking the 6 bayonet devices in Table 3, bayonet device A, bayonet device B, bayonet device C, bayonet device D, bayonet device E and bayonet device F as an example, the server arranges the Geohash encoding results corresponding to each bayonet device in descending order according to the order of the value of the Geohash encoding result. The arrangement order of the Geohash encoding results corresponding to the 6 bayonet devices is: bayonet device BG, bayonet device FG, bayonet device DG, bayonet device CG, bayonet device AG, bayonet device EG. Further, the server can know that the arrangement numbers of the Geohash codes of the 6 bayonet devices are: 5, 1, 4, 3, 6, 2.
[0102] S2023: Based on the obtained serial numbers, generate monitoring point identifiers of corresponding monitoring points respectively.
[0103] Specifically, when executing step S2023, after obtaining the arrangement sequence number of the Geohash code of each monitoring point, the server generates a unique monitoring point identifier for each monitoring point.
[0104] Exemplarily, the server selects a unique card slot device identifier for each card slot device from the card slot device identifier library according to the sequence number of the Geohash code corresponding to each card slot device, wherein the number of card slot device identifiers in the card slot device identifier library is much larger than the number of card slot devices. For example, according to the sequence number of the Geohash code of the card slot device, the server uses the corresponding sequence of lowercase English letters as the card slot device identifier of the card slot device. Figure 6 Taking the Geohash encoding result shown in the figure as an example, the arrangement sequence numbers of each card slot device and its card slot device identification are shown in Table 4:
[0105] Table 4
[0106]
[0107]
[0108] It can be seen from the above table that the server generates corresponding card slot device identifiers for the six card slot devices based on the arrangement sequence numbers of the Geohash corresponding to each of the six card slot devices. For example, taking card slot device A as an example, the server generates a unique card slot device identifier e for card slot device A based on the arrangement sequence number of the Geohash of card slot device A being 5; and taking card slot device B as an example, the server generates a unique card slot device identifier a for card slot device B based on the arrangement sequence number of the Geohash of card slot device B being 1.
[0109] Optionally, based on the above system architecture, obtain each candidate vehicle trajectory within the set historical monitoring range, see Figure 7 As shown, in the embodiment of the present application, the process of obtaining a candidate vehicle trajectory includes the following specific steps:
[0110] S701: Obtain at least two pieces of historical monitoring information of a historical vehicle obtained by each monitoring point within a set historical monitoring range.
[0111] Specifically, when executing step S701, the server can filter out each historical monitoring information obtained by each monitoring point that meets the set historical monitoring range from the original monitoring database based on the set historical monitoring range. Each historical monitoring information includes: the time when the corresponding monitoring node monitored the historical vehicle within the historical monitoring range.
[0112] For example, each historical monitoring information in the original monitoring time database has a corresponding time tag. By setting the historical monitoring range, each historical monitoring information obtained by each monitoring point that meets the set historical monitoring time range is screened out.
[0113] For example, it is assumed that the original monitoring database contains 6 historical monitoring information with different time tags corresponding to 6 checkpoint devices, among which L.T1, L.T3 and L.T5 belong to the set historical monitoring time range, and L.T2, L.T4 and L.T6 do not belong to the set historical monitoring time range. The historical monitoring information and whether it belongs to the historical time monitoring range are shown in Table 5:
[0114] Table 5
[0115]
[0116] As can be seen from the above table, the server can determine whether the corresponding historical monitoring information belongs to the set historical monitoring range based on the time stamp of each historical monitoring information in the original monitoring database. For example, taking monitoring information .L.1 as an example, the server obtains the time stamp of monitoring information .L.1 as L.T1. After judgment, it can be known that L.T1 belongs to the set historical monitoring time range, so monitoring information .L.1 is extracted from the original monitoring database; taking monitoring information .L.2 as an example, the server obtains the time stamp of monitoring information .L.2 as L.T2. After judgment, it can be known that L.T2 does not belong to the set historical monitoring time range, so monitoring information .L.2 is not extracted from the original monitoring database, and so on.
[0117] Based on the above method, the server can obtain multiple historical monitoring information corresponding to each historical vehicle within the set historical monitoring range.
[0118] S702: Determine a historical monitoring time interval between two adjacent historical monitoring information. When it is determined that the historical monitoring time interval is not greater than a preset interval threshold, take a road section between monitoring points corresponding to the two historical monitoring information as a candidate vehicle trajectory.
[0119] Specifically, when executing step S702, after the server obtains various historical monitoring information of a historical vehicle within the set historical monitoring range, it determines whether to use the road section between the monitoring points corresponding to the two historical monitoring information as a candidate vehicle trajectory based on the historical monitoring time interval of the two adjacent historical monitoring information and the time interval interval to which they belong. If the historical monitoring time interval is not greater than the preset interval threshold, the road section between the monitoring points corresponding to the two historical monitoring information is used as a candidate vehicle trajectory; if the historical monitoring time interval is greater than the preset interval threshold, the road section between the monitoring points corresponding to the two historical monitoring information is not used as a candidate vehicle trajectory. Among them, the calculation formula of the historical monitoring time interval is as follows:
[0120] ΔT1=T 2 -T 1
[0121] Among them, the historical monitoring time T 1 Earlier than the historical monitoring time T 2
[0122] For example, Figure 4 As shown, the checkpoint device A and the checkpoint device C are used as monitoring points. Assume that the historical monitoring time of the historical vehicle detected in the historical monitoring information of the checkpoint device A is T A In the historical monitoring information of the checkpoint device C, the historical monitoring time of the historical vehicle is T C , then the historical monitoring time interval ΔTAC =T C -T A , where the historical monitoring time T A Earlier than the historical monitoring time T C .
[0123] Further, assume that the maximum time required for a vehicle to travel from checkpoint device A to checkpoint device C is 10 minutes. If the actual time taken by the historical vehicle to travel from checkpoint device A to checkpoint device C is 5 minutes, it can be seen by comparison that the actual time is less than the preset maximum time, and the section between checkpoint device A and checkpoint device C can be used as a candidate vehicle trajectory; if the actual time taken by the historical vehicle to travel from checkpoint device A to checkpoint device C is 12 minutes, it can be seen by comparison that the actual time is greater than the preset maximum time, and the section between checkpoint device A and checkpoint device C will not be used as a candidate vehicle trajectory.
[0124] Optionally, if the road sections between the checkpoint device A, the checkpoint device B and the checkpoint device C constitute a vehicle trajectory ABC. If the actual duration of the historical vehicle from the checkpoint device A to the checkpoint device B, and the actual duration from the checkpoint device B to the checkpoint device C, are not greater than the preset maximum duration, the vehicle trajectory ABC can be used as a candidate vehicle trajectory.
[0125] Optionally, based on the above system architecture, obtain the missing sections of the track on the historical vehicle track of the target vehicle, see Figure 8 As shown, in the embodiment of the present application, the method flow for obtaining the missing section of the track is as follows:
[0126] S801: Obtain at least two target monitoring information of the target vehicle obtained by each monitoring point on the historical vehicle trajectory.
[0127] Specifically, when executing step S801, the server can filter out each target monitoring information obtained by each monitoring point that meets the driving time range from the original monitoring database based on the driving time range of the target vehicle in the historical vehicle trajectory. Each target monitoring information includes: the time when the corresponding monitoring node monitors the target vehicle on the historical vehicle trajectory.
[0128] For example, each target monitoring information in the original monitoring time database has a corresponding time tag. Through the driving time range of the historical vehicle trajectory, each target monitoring information obtained by each monitoring point that meets the driving time range is screened out.
[0129] For example, it is assumed that the original monitoring database contains 6 target detection information with different time marks corresponding to 6 bayonet devices, among which M.T1, M.T2, and M.T5 belong to the driving time range, and M.T3, M.T4, and M.T6 do not belong to the driving time range. The monitoring information of each target and whether it belongs to the driving time range are shown in Table 6:
[0130] Table 6
[0131]
[0132] It can be seen from the above table that the server can determine whether the corresponding target monitoring information belongs to the set target monitoring range based on the time mark of each target monitoring information in the original monitoring database. For example, taking monitoring information .M.1 as an example, the server obtains the time mark of monitoring information .M.1 as M.T1. After judgment, it can be known that M.T1 belongs to the driving time range, so monitoring information .M.1 is extracted from the original monitoring database; taking monitoring information .M.3 as an example, the server obtains the time mark of monitoring information .M.3 as M.T3. After judgment, it can be known that M.T3 does not belong to the driving time range, so monitoring information .M.3 is not extracted from the original monitoring database, and so on.
[0133] S802: Determine the target monitoring time interval between two adjacent target monitoring information.
[0134] Specifically, when executing step S802, after the server obtains each target monitoring information of the target vehicle in the historical vehicle trajectory, it obtains the corresponding target monitoring time interval based on the target monitoring time of two adjacent target monitoring information obtained. The calculation formula of the target monitoring time interval is as follows:
[0135] ΔT2=T 4 -T 3
[0136] Among them, the target monitoring time T 3 Earlier than the target monitoring time T 4 .
[0137] For example, Figure 4 As shown in the figure, assuming that the historical vehicle trajectory is: A→B→E, where the target monitoring time of the checkpoint device A is T A , the target monitoring time of the bayonet device B is T B , the target monitoring time of the bayonet device E is T E , the target monitoring time is in the following order: T A 、T B 、T E; According to the target monitoring time interval calculation formula, we can know that the target monitoring time interval ΔT between the bayonet device A and the bayonet device B is: AB =T B -T A ; Target monitoring time interval ΔT between the bayonet device A and the bayonet device B BE =T E -T B .
[0138] S803: When it is determined that the target monitoring time interval is greater than a preset interval threshold, the section between the monitoring points corresponding to the two target monitoring information is regarded as a track missing section.
[0139] Specifically, when executing step S803, after the server obtains each target monitoring information of the target vehicle on the historical vehicle trajectory, based on the target monitoring time interval of two adjacent target monitoring information, and the time interval interval to which they belong, it is determined whether to use the section between the monitoring points corresponding to the two target monitoring information as the missing section of the trajectory. If the target monitoring time interval is not greater than the preset interval threshold, the section between the monitoring points corresponding to the two target monitoring information is not used as the missing section of the trajectory; if the target monitoring time interval is greater than the preset interval threshold, the section between the monitoring points corresponding to the two target monitoring information is used as the missing section of the trajectory.
[0140] For example, still taking the target trajectory: A→B→E as an example, assuming that the maximum time required for a vehicle to travel from checkpoint device A to checkpoint device B is 15 minutes, and the maximum time required for a vehicle to travel from checkpoint device B to checkpoint device E is 18 minutes. If the target monitoring time interval measured during the process of the target vehicle traveling from checkpoint device A to checkpoint device B is 12 minutes, and the target monitoring time interval measured during the process of the target vehicle traveling from checkpoint device B to checkpoint device E is 20 minutes, by comparison, it can be seen that the target monitoring time interval measured in the former is less than the maximum time required, and the target monitoring time interval measured in the latter is greater than the maximum time required, so it can be determined that in the historical vehicle trajectory A→B→E, B→E is a missing section of the trajectory.
[0141] Further, based on the above pre-operation processing, the server generates monitoring point identifiers corresponding to each monitoring point, and obtains the missing sections of the track of each candidate vehicle track and the historical vehicle track of the target vehicle, see Fig. 9 As shown, in the embodiment of the present application, the method flow for completing the missing track of the target vehicle on the missing track section is as follows:
[0142] S901: Based on the track missing section of the target vehicle, obtain the monitoring point identifiers corresponding to the starting position point and the ending position point of the track missing section.
[0143] Specifically, when executing step S901, the server obtains the monitoring point identifiers corresponding to the starting position point and the ending position point of the missing trajectory section based on the determined missing trajectory section of the target vehicle and the position information corresponding to the starting position point and the ending position point of the missing trajectory section.
[0144] For example, still taking the corresponding checkpoint device identifiers of each checkpoint device in Table 4 and the target vehicle's track missing section: B→E as an example, it is easy to know that checkpoint device B is the starting position point of the track missing section, and checkpoint device E is the ending position point of the track missing section. Based on the corresponding position information of checkpoint device B and checkpoint device E, the server can determine the monitoring point identifier of the starting point of the position as a, and the monitoring point identifier of the ending point of the position as f from the checkpoint device identifier library.
[0145] S902: Based on the obtained monitoring point identifier, at least one candidate vehicle trajectory is screened out from the vehicle trajectory database.
[0146] Specifically, when executing step S902, after obtaining the monitoring point identifiers corresponding to the starting position point and the ending position point of the missing track section, the server screens out all candidate vehicle trajectories between the monitoring points corresponding to the two monitoring point identifiers from the vehicle trajectory database based on the obtained monitoring point identifiers corresponding to the starting position point and the ending position point of the missing track section.
[0147] For example, see Fig.10 As shown, the server can obtain four monitoring point identification arrays: aef, adf, acf, abf from the vehicle trajectory database according to the monitoring point identification a of the starting point of the missing section of the trajectory and the monitoring point identification f of the ending point of the location. Further, according to the four monitoring point identification arrays, four candidate vehicle trajectories can be obtained in order: B→A→E, B→C→E, B→D→E, B→F→E.
[0148] It should be noted that the maximum duration required for the above four candidate vehicle trajectories is no greater than the maximum duration required for the missing section of the trajectory: B→E.
[0149] S903: After the candidate vehicle trajectories are screened, based on the number of vehicle passes corresponding to each of the at least one candidate vehicle trajectories and the total number of vehicle passes corresponding to the at least one candidate vehicle trajectory within a specified historical time range, a target vehicle trajectory is selected from the at least one candidate vehicle trajectory.
[0150] In a possible implementation, when executing step S903, the server obtains the number of historical vehicle passes corresponding to at least one candidate vehicle trajectory within a specified historical time range, and the total number of historical vehicle passes corresponding to at least one candidate vehicle trajectory, and then selects the target vehicle trajectory. Fig.11 As shown, the specific steps are as follows:
[0151] S9031a: Based on the obtained number of historical vehicle passes and the total number of historical vehicle passes, determine the historical vehicle pass ratios of the corresponding candidate vehicle trajectories.
[0152] Specifically, when executing step S9031a, the server performs quotient processing based on the obtained historical vehicle pass times and the total historical vehicle pass times to obtain the historical vehicle pass ratio of the corresponding candidate vehicle trajectory. The calculation formula for the historical vehicle pass ratio of the candidate vehicle trajectory is as follows:
[0153]
[0154] Among them, α i is the historical vehicle traffic ratio corresponding to candidate vehicle trajectory i; w i is the number of historical vehicle passes corresponding to candidate vehicle trajectory i; W is the total number of historical vehicle passes of all candidate vehicles.
[0155] For example, it is assumed that the total number of historical vehicle passes of the above four candidate vehicle trajectories in one day is 10,000 times, among which the number of historical vehicle passes of candidate vehicle trajectory B→A→E is 700 times, the number of historical vehicle passes of candidate vehicle trajectory B→C→E is 800 times, the number of historical vehicle passes of candidate vehicle trajectory B→D→E is 8,000 times, and the total number of historical vehicle passes of candidate vehicle trajectory B→F→E is 500 times. According to the calculation formula of the historical vehicle pass ratio of the candidate vehicle trajectories, the server can obtain that the historical vehicle pass ratio of B→A→E is 7%, the historical vehicle pass ratio of B→C→E is 8%, the historical vehicle pass ratio of B→D→E is 80%, and the historical vehicle pass ratio of B→F→E is 5%.
[0156] S9032a: Based on the obtained historical vehicle traffic proportions, determine the order of arrangement of the historical vehicle traffic proportions.
[0157] Specifically, when executing step S9032a, after determining the historical vehicle traffic proportions, the server determines the corresponding arrangement order of the historical vehicle traffic proportions based on the historical vehicle traffic proportions corresponding to each candidate vehicle trajectory and in order of proportions.
[0158] For example, the server knows that the historical vehicle traffic ratio of B→A→E is 7%, the historical vehicle traffic ratio of B→C→E is 8%, the historical vehicle traffic ratio of B→D→E is 80%, and the historical vehicle traffic ratio of B→F→E is 5%. The traffic ratios are arranged in descending order of the ratios. The historical vehicle traffic ratios and their arrangement order are shown in Table 7:
[0159] Table 7
[0160] Candidate vehicle trajectories B→A→E B→C→E B→D→E B→F→E Historical vehicle traffic ratio 7% 8% 80% 5% Sort by percentage 3 2 1 4
[0161] As can be seen from the above table, the server can sort the candidate vehicle trajectories by the historical vehicle trajectory traffic ratio according to the traffic ratio of each historical vehicle trajectory. For example, taking the candidate vehicle trajectory B→A→E as an example, the historical vehicle traffic ratio is 7%, which is only greater than the candidate vehicle trajectory B→F→E, so the historical vehicle trajectory traffic ratio of the candidate vehicle trajectory is 3, and so on.
[0162] S9033a: Based on the order of the historical vehicle traffic ratios and a preset historical vehicle traffic ratio threshold, a target vehicle trajectory is selected from each candidate vehicle trajectory.
[0163] Specifically, when executing step S9033a, after determining the order of arrangement of historical vehicle traffic proportions, the server selects the maximum historical vehicle traffic proportion based on the obtained order of arrangement of historical vehicle traffic proportions, and when it is determined that the maximum historical vehicle traffic proportion is greater than a preset historical vehicle traffic proportion threshold, the candidate vehicle trajectory corresponding to the maximum historical vehicle traffic proportion is used as the target vehicle trajectory.
[0164] Exemplarily, assuming that the preset historical vehicle traffic ratio threshold is 75%, still taking the 4 candidate vehicle trajectories in Table 7 as an example, among the historical vehicle traffic ratios of the 4 candidate vehicle trajectories, the server obtains that the historical vehicle traffic ratio of the candidate vehicle trajectory B→D→E is ranked highest, and the historical vehicle traffic ratio of the candidate vehicle trajectory B→D→E is 80%, which is greater than the preset historical vehicle traffic ratio threshold of 75%, then the candidate vehicle trajectory B→D→E is used as the target vehicle trajectory.
[0165] In a possible implementation, when executing step S903, the server obtains the number of target vehicle passes corresponding to at least one candidate vehicle trajectory within a specified historical time range, and the total number of target vehicle passes corresponding to at least one candidate vehicle trajectory, and then selects the target vehicle trajectory. Fig.12 As shown, the specific steps are as follows:
[0166] S9031b: Based on the obtained number of passes of each target vehicle and the total number of passes of the target vehicle, the target vehicle pass ratios of the corresponding candidate vehicle trajectories are determined respectively.
[0167] Specifically, when executing step S9031b, the server performs quotient processing based on the obtained number of passes of each target vehicle and the total number of passes of the target vehicle to obtain the target vehicle pass ratio of the corresponding candidate vehicle trajectory. The calculation formula for the target vehicle pass ratio of the candidate vehicle trajectory is as follows:
[0168]
[0169] Among them, β i is the target vehicle traffic ratio corresponding to candidate vehicle trajectory i; m i is the number of target vehicle passes corresponding to candidate vehicle trajectory i; M is the total number of target vehicle passes for all candidate vehicles.
[0170] For example, it is assumed that the total number of target vehicle passes of the above four candidate vehicle trajectories within one year is 5000 times, among which the target vehicle pass number of candidate vehicle trajectory B→A→E is 200 times, the target vehicle pass number of candidate vehicle trajectory B→C→E is 4400 times, the target vehicle pass number of candidate vehicle trajectory B→D→E is 100 times, and the total number of target vehicle passes of candidate vehicle trajectory B→F→E is 300 times. The server calculates the target vehicle pass ratio of the candidate vehicle trajectories according to the target vehicle pass ratio calculation formula, and obtains that the target vehicle pass ratio of B→A→E is 4%, the target vehicle pass ratio of B→C→E is 88%, the target vehicle pass ratio of B→D→E is 2%, and the target vehicle pass ratio of B→F→E is 6%.
[0171] S9032b: Based on the obtained traffic proportions of each target vehicle, determine the order of the traffic proportions of the target vehicles.
[0172] Specifically, when executing step S9032b, after determining the traffic proportion of each target vehicle, the server determines the corresponding target vehicle traffic proportion arrangement order based on the traffic proportion of the target vehicles corresponding to each candidate vehicle trajectory and in order of the proportion.
[0173] For example, the server knows that the target vehicle traffic ratio of B→A→E is 4%, the target vehicle traffic ratio of B→C→E is 88%, the target vehicle traffic ratio of B→D→E is 2%, and the target vehicle traffic ratio of B→F→E is 6%. The traffic ratios of the target vehicles are arranged in descending order of the ratios. The traffic ratios of the target vehicles and their arrangement order are shown in Table 8:
[0174] Table 8
[0175] Candidate vehicle trajectories B→A→E B→C→E B→D→E B→F→E Target vehicle traffic ratio 4% 88% 2% 6% Sort by percentage 3 1 4 2
[0176] As can be seen from the above table, the server can sort the target vehicle trajectory traffic ratios of each candidate vehicle trajectory according to the traffic ratios of each target vehicle trajectory. For example, taking the candidate vehicle trajectory B→A→E as an example, the target vehicle traffic ratio is 4%, which is only less than the target vehicle traffic ratio of the candidate vehicle trajectory B→D→E. Therefore, the target vehicle trajectory traffic ratio of this candidate vehicle trajectory is 3, and so on.
[0177] S9033b: Based on the order of the target vehicle traffic ratios and a preset target vehicle traffic ratio threshold, a target vehicle trajectory is selected from each candidate vehicle trajectory.
[0178] Specifically, when executing step S9033b, after determining the order of arrangement of the target vehicle traffic proportions, the server selects the maximum target vehicle traffic proportion based on the obtained order of arrangement of the target vehicle traffic proportions. When it is determined that the maximum target vehicle traffic proportion is greater than a preset target traffic proportion threshold, the candidate vehicle trajectory corresponding to the maximum target vehicle traffic proportion is used as the target vehicle trajectory.
[0179] Exemplarily, assuming that the preset target vehicle traffic ratio threshold is 85%, still taking the 4 candidate vehicle trajectories in Table 8 as an example, among the target vehicle traffic ratios of the 4 candidate vehicle trajectories, the server obtains that the target vehicle traffic ratio of the candidate vehicle trajectory B→C→E is ranked highest, and the target vehicle traffic ratio of the candidate vehicle trajectory B→C→E is 88%, which is greater than the preset target vehicle traffic ratio threshold of 85%, then the candidate vehicle trajectory B→C→E is used as the target vehicle trajectory.
[0180] S904: Based on the complete road section information contained in the target vehicle trajectory, the missing road sections of the trajectory are completed.
[0181] Exemplarily, taking Table 7 as an example, when executing step S904, after selecting the target vehicle trajectory, the server can complete the missing sections of the original trajectory, namely, B→D and D→E in B→E, based on the selected candidate vehicle trajectory, i.e., B→D→E, to obtain the complete target vehicle trajectory.
[0182] Optionally, taking Table 8 as an example, when executing step S904, the server can complete the missing sections of the original trajectory, namely, B→C→E, based on the selected target vehicle trajectory, i.e., B→C→E, to obtain the complete target vehicle trajectory.
[0183] The missing track completion method provided in the embodiment of the present application obtains at least one candidate vehicle track based on the identifiers corresponding to the starting point position and the ending point position of the missing track section, and then selects the target vehicle track based on the vehicle traffic ratio corresponding to the at least one candidate track obtained, and finally completes the missing track section based on the complete road section information of the target vehicle track. In this way, the target vehicle track is determined by the vehicle traffic ratio of each candidate vehicle track, and then the missing track section is completed, which avoids the cumbersome process of calculating the shortest time path in the traditional method, and when the amount of data is large, it takes a lot of time, thereby improving the efficiency of vehicle track missing completion.
[0184] Based on the same technical concept, the embodiment of the present application further provides a missing track completion device, which can implement the above method flow of the embodiment of the present application.
[0185] Fig.13 The following is a schematic diagram showing the structure of a track missing completion device provided by an embodiment of the present application. Fig.13 As shown, the missing track completion includes: an acquisition module 1301, a screening module 1302 and a processing module 1303, wherein:
[0186] The acquisition module 1301 is used to acquire the monitoring point identifiers corresponding to the start position point and the end position point of the track missing section based on the track missing section of the target vehicle.
[0187] The screening module 1302 is used to screen out at least one candidate vehicle trajectory from the vehicle trajectory database based on the obtained monitoring point identifier; wherein each candidate vehicle trajectory includes: complete road section information between a starting position point and an ending position point.
[0188] The processing module 1303 is used to select a target vehicle trajectory from at least one candidate vehicle trajectory based on the number of vehicle passes corresponding to each of the at least one candidate vehicle trajectory and the total number of vehicle passes corresponding to the at least one candidate vehicle trajectory within a specified historical time range; and complete the missing sections of the trajectory based on the complete section information contained in the target vehicle trajectory.
[0189] In a second aspect, an embodiment of the present application further provides a device for completing missing tracks, the device comprising:
[0190] The acquisition module 1301 is used to acquire the monitoring point identifiers corresponding to the start position point and the end position point of the track missing section based on the track missing section of the target vehicle.
[0191] The screening module 1302 is used to screen out at least one candidate vehicle trajectory from the vehicle trajectory database based on the obtained monitoring point identifier; wherein each candidate vehicle trajectory includes: complete road section information between a starting position point and an ending position point.
[0192] The processing module 1303 is used to select a target vehicle trajectory from at least one candidate vehicle trajectory based on the number of vehicle passes corresponding to each of the at least one candidate vehicle trajectory and the total number of vehicle passes corresponding to the at least one candidate vehicle trajectory within a specified historical time range; and complete the missing sections of the trajectory based on the complete section information contained in the target vehicle trajectory.
[0193] In an optional embodiment, before obtaining the monitoring point identifiers corresponding to the starting position point and the ending position point of the track missing section based on the track missing section of the target vehicle, the obtaining module 1301 is further used to:
[0194] Obtain location information corresponding to at least two monitoring points.
[0195] Based on the position information corresponding to the at least two monitoring points, monitoring point identifiers corresponding to the at least two monitoring points are generated respectively.
[0196] In an optional embodiment, when respectively generating monitoring point identifiers corresponding to at least two monitoring points based on the position information corresponding to at least two monitoring points, the processing module 1303 is specifically used to:
[0197] Perform geo-hash coding on the location information corresponding to at least two monitoring points respectively to obtain corresponding coding results.
[0198] Based on the values of the obtained encoding results, the encoding results are sorted to obtain the serial numbers of the corresponding encoding results.
[0199] Based on the obtained serial numbers, monitoring point identifiers of corresponding monitoring points are generated respectively.
[0200] In an optional embodiment, before obtaining the monitoring point identifiers corresponding to the starting position point and the ending position point of the track missing section based on the track missing section of the target vehicle, the obtaining module 1301 is further used to:
[0201] For each historical vehicle, perform the following operations:
[0202] At least two pieces of historical monitoring information obtained by each monitoring point for a historical vehicle within a set historical monitoring range are obtained; wherein each piece of historical monitoring information includes: the time when the corresponding monitoring point monitored a historical vehicle within the historical monitoring range.
[0203] For each two adjacent historical monitoring information among at least two historical monitoring information, the following operations are performed respectively: a historical monitoring time interval between two adjacent historical monitoring information is determined; when it is determined that the historical monitoring time interval is not greater than a preset interval threshold, a road section between the monitoring points corresponding to the two historical monitoring information is used as a candidate vehicle trajectory.
[0204] In an optional embodiment, before obtaining the monitoring point identifiers corresponding to the starting position point and the ending position point of the track missing section based on the track missing section of the target vehicle, the obtaining module 1301 is further used to:
[0205] At least two target monitoring information of the target vehicle obtained by each monitoring point on the historical vehicle trajectory are obtained; wherein each target monitoring information includes: the time when the corresponding monitoring point monitors the target vehicle on the historical vehicle trajectory.
[0206] For each two adjacent target monitoring information obtained from at least two target monitoring information, the following operations are performed respectively:
[0207] Determine the target monitoring time interval between two adjacent target monitoring information.
[0208] When it is determined that the target monitoring time interval is greater than a preset interval threshold, the section between the monitoring points corresponding to the two target monitoring information is regarded as a track missing section.
[0209] In an optional embodiment, based on the number of vehicle passes corresponding to each of at least one candidate vehicle trajectory and the total number of vehicle passes corresponding to at least one candidate vehicle trajectory within a specified historical time range, when selecting a target vehicle trajectory from at least one candidate vehicle trajectory, the acquisition module 1301 is further used to:
[0210] Obtain the number of historical vehicle passes corresponding to at least one candidate vehicle trajectory within a specified historical time range, and the total number of historical vehicle passes corresponding to at least one candidate vehicle trajectory.
[0211] Based on the obtained number of historical vehicle passes and the total number of historical vehicle passes, the historical vehicle pass ratios of the corresponding candidate vehicle trajectories are determined respectively.
[0212] Based on the obtained historical vehicle traffic proportions and the preset historical vehicle traffic proportion threshold, the target vehicle trajectory is selected from the candidate vehicle trajectories.
[0213] In an optional embodiment, based on the number of vehicle passes corresponding to each of at least one candidate vehicle trajectory and the total number of vehicle passes corresponding to at least one candidate vehicle trajectory within a specified historical time range, when selecting a target vehicle trajectory from at least one candidate vehicle trajectory, the acquisition module 1301 is further used to:
[0214] Obtain the target vehicle passing times corresponding to at least one candidate vehicle trajectory and the total target vehicle passing times corresponding to at least one candidate vehicle trajectory within a specified historical time range.
[0215] Based on the obtained number of passes of each target vehicle and the total number of passes of the target vehicle, the target vehicle pass ratio of the corresponding candidate vehicle trajectory is determined respectively.
[0216] Based on the obtained traffic proportions of each target vehicle and the preset traffic proportion threshold of the target vehicle, the target vehicle trajectory is selected from each candidate vehicle trajectory.
[0217] Based on the same technical concept, the embodiment of the present application also provides an electronic device, which can implement the method flow provided in the above embodiment of the present application. In one embodiment, the electronic device can be a server, or a terminal device or other electronic device.
[0218] Fig.14 The following is a schematic diagram showing the structure of an electronic device provided by an embodiment of the present application. Fig.14 As shown, the electronic device may include:
[0219] At least one processor 1401, and a memory 1402 connected to the at least one processor 1401. The specific connection medium between the processor 1401 and the memory 1402 is not limited in the embodiment of the present application. Fig.14 In the example, the processor 1401 and the memory 1402 are connected via the bus 1400. Fig.14 The connections between other components are shown in bold lines, and are not intended to be limiting. The bus 1400 can be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, Fig.14 Only one thick line is used in the figure, but it does not mean that there is only one bus or one type of bus. Alternatively, the processor 1401 can also be called a controller, and there is no limitation on the name.
[0220] In the embodiment of the present application, the memory 1402 stores instructions that can be executed by at least one processor 1401. The at least one processor 1401 can execute a missing track completion method discussed above by executing the instructions stored in the memory 1402. The processor 1401 can implement Fig.13The functions of each module in the device shown.
[0221] Among them, processor 1401 is the control center of the device, which can use various interfaces and lines to connect various parts of the entire control device, and monitor the device as a whole by running or executing instructions stored in memory 1402 and calling data stored in memory 1402, various functions of the device and processing data.
[0222] In one possible design, the processor 1401 may include one or more processing units, and the processor 1401 may integrate an application processor and a modem processor, wherein the application processor mainly processes an operating system, a user interface, and application programs, and the modem processor mainly processes wireless communications. It is understandable that the modem processor may not be integrated into the processor 1401. In some embodiments, the processor 1401 and the memory 1402 may be implemented on the same chip, and in some embodiments, they may also be implemented separately on separate chips.
[0223] Processor 1401 can be a general-purpose processor, such as a CPU (CPU), a digital signal processor, an application-specific integrated circuit, a field programmable gate array or other programmable logic device, a discrete gate or transistor logic device, a discrete hardware component, and can implement or execute the methods, steps and logic block diagrams disclosed in the embodiments of the present application. A general-purpose processor can be a microprocessor or any conventional processor, etc. The steps of a missing track completion method disclosed in the embodiments of the present application can be directly embodied as a hardware processor execution, or a combination of hardware and software modules in the processor.
[0224] Memory 1402, as a non-volatile computer-readable storage medium, can be used to store non-volatile software programs, non-volatile computer executable programs and modules. Memory 1402 may include at least one type of storage medium, such as flash memory, hard disk, multimedia card, card-type memory, random access memory (Random Access Memory, RAM), static random access memory (Static Random Access Memory, SRAM), programmable read-only memory (Programmable Read Only Memory, PROM), read-only memory (Read Only Memory, ROM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, EEPROM), magnetic memory, disk, optical disk, etc. Memory 1402 is any other medium that can be used to carry or store a desired program code in the form of an instruction or data structure and can be accessed by a computer, but is not limited thereto. The memory 1402 in the embodiment of the present application can also be a circuit or any other device that can realize a storage function, for storing program instructions and / or data.
[0225] By programming the processor 1401, the code corresponding to the missing track completion method described in the above embodiment can be fixed into the chip, so that the chip can execute the code when running. Fig. 9 The steps of a missing trace completion method of the embodiment shown are as follows: How to design and program the processor 1401 is a technique known to those skilled in the art and will not be described in detail here.
[0226] Based on the same inventive concept, an embodiment of the present application further provides a storage medium, which stores computer instructions. When the computer instructions are executed on a computer, the computer executes a missing track completion method discussed above.
[0227] In some possible implementations, various aspects of a missing trace completion method provided by the present application may also be implemented in the form of a program product, which includes a program code. When the program product is run on an apparatus, the program code is used to enable the control device to execute the steps of a missing trace completion method according to various exemplary implementations of the present application described above in this specification.
[0228] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may 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 may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.
[0229] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (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 device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device 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.
[0230] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.
[0231] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.
[0232] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.
Claims
1. A method for completing missing trajectories, It is characterized in that include: Based on the historical monitoring time interval of two adjacent historical monitoring information, when it is determined that the historical monitoring time interval is not greater than a preset interval threshold, the road section between the monitoring points corresponding to the two historical monitoring information is used as a candidate vehicle trajectory, wherein each candidate vehicle trajectory includes: complete road section information between a starting position point and an ending position point; Based on the track missing section of the target vehicle, obtaining the monitoring point identifiers corresponding to the starting position point and the ending position point of the track missing section respectively; Based on the obtained monitoring point identifier, at least one candidate vehicle trajectory is screened out from the vehicle trajectory database; wherein each candidate vehicle trajectory includes: complete road section information between the starting position point and the ending position point; Based on the number of vehicle passes corresponding to each of the at least one candidate vehicle trajectories within a specified historical time range and the total number of vehicle passes corresponding to the at least one candidate vehicle trajectory, a target vehicle trajectory is selected from the at least one candidate vehicle trajectory; Based on the complete road section information contained in the target vehicle trajectory, the missing road sections of the trajectory are completed.
2. The method according to claim 1, It is characterized in that Before obtaining the monitoring point identifiers corresponding to the starting position point and the ending position point of the track missing section based on the target vehicle, the method further includes: Obtaining location information corresponding to at least two monitoring points; Based on the position information corresponding to the at least two monitoring points, monitoring point identifiers corresponding to the at least two monitoring points are generated respectively.
3. The method according to claim 2, It is characterized in that The generating, based on the location information corresponding to the at least two monitoring points, the monitoring point identifiers corresponding to the at least two monitoring points respectively, comprises: Performing geo-hash coding on the location information corresponding to the at least two monitoring points respectively to obtain corresponding coding results; Based on the values of each obtained encoding result, the encoding results are sorted to obtain the sequence numbers of the corresponding encoding results respectively; Based on each obtained serial number, a monitoring point identifier of the corresponding monitoring point is generated respectively.
4. The method according to claim 1, It is characterized in that Before obtaining the monitoring point identifiers corresponding to the starting position point and the ending position point of the track missing section based on the target vehicle, the method further includes: For each historical vehicle, perform the following operations: At least two pieces of historical monitoring information of a historical vehicle obtained by each monitoring point within a set historical monitoring range are obtained; wherein each piece of historical monitoring information includes: the time when the corresponding monitoring point monitored the historical vehicle within the historical monitoring range.
5. The method according to claim 1, It is characterized in that Before obtaining the monitoring point identifiers corresponding to the starting position point and the ending position point of the track missing section based on the target vehicle, the method further includes: Acquire at least two target monitoring information of the target vehicle obtained by each monitoring point on the historical vehicle trajectory; wherein each target monitoring information includes: the time when the corresponding monitoring point monitored the target vehicle on the historical vehicle trajectory; For each two pieces of target monitoring information obtained adjacently in the at least two pieces of target monitoring information, the following operations are performed respectively: Determine the target monitoring time interval between two adjacent target monitoring information; When it is determined that the target monitoring time interval is greater than a preset interval threshold, the section between the monitoring points corresponding to the two target monitoring information is regarded as a track missing section.
6. The method according to claim 1, It is characterized in that The selecting a target vehicle trajectory from the at least one candidate vehicle trajectory based on the number of vehicle passes corresponding to each of the at least one candidate vehicle trajectory and the total number of vehicle passes corresponding to the at least one candidate vehicle trajectory within the specified historical time range includes: Obtaining the number of historical vehicle passes corresponding to each of the at least one candidate vehicle trajectory within a specified historical time range, and the total number of historical vehicle passes corresponding to the at least one candidate vehicle trajectory; Based on the obtained number of historical vehicle passes and the total number of historical vehicle passes, respectively determine the historical vehicle pass ratio of the corresponding candidate vehicle trajectory; Based on the obtained historical vehicle traffic proportions and in combination with a preset historical vehicle traffic proportion threshold, a target vehicle trajectory is selected from the candidate vehicle trajectories.
7. The method according to claim 1, It is characterized in that The selecting a target vehicle trajectory from the at least one candidate vehicle trajectory based on the number of vehicle passes corresponding to each of the at least one candidate vehicle trajectory and the total number of vehicle passes corresponding to the at least one candidate vehicle trajectory within the specified historical time range includes: Obtaining the number of target vehicle passes corresponding to each of the at least one candidate vehicle trajectory within a specified historical time range, and the total number of target vehicle passes corresponding to the at least one candidate vehicle trajectory; Based on the obtained number of passes of each target vehicle and the total number of passes of the target vehicle, respectively determine the target vehicle pass ratio of the corresponding candidate vehicle trajectory; Based on the obtained traffic proportions of each target vehicle and in combination with a preset traffic proportion threshold of the target vehicle, a target vehicle trajectory is selected from the candidate vehicle trajectories.
8. A device for completing missing tracks, It is characterized in that include: An acquisition module, used for acquiring monitoring point identifiers corresponding to the starting position point and the ending position point of the track missing section based on the track missing section of the target vehicle; A screening module is used to screen out at least one candidate vehicle track from the vehicle track database based on the obtained monitoring point identification; wherein each candidate vehicle track includes: complete road section information between a starting position point and an ending position point; The processing module is used to select a target vehicle trajectory from the at least one candidate vehicle trajectory based on the number of vehicle passes corresponding to each of the at least one candidate vehicle trajectory and the total number of vehicle passes corresponding to the at least one candidate vehicle trajectory within a specified historical time range; and complete the missing sections of the trajectory based on the complete section information contained in the target vehicle trajectory.
9. The device as claimed in claim 8, It is characterized in that Before obtaining the monitoring point identifiers corresponding to the starting position point and the ending position point of the track missing section based on the target vehicle, the obtaining module is further used to: Obtaining location information corresponding to at least two monitoring points; Based on the position information corresponding to the at least two monitoring points, monitoring point identifiers corresponding to the at least two monitoring points are generated respectively.
10. The device according to claim 8, It is characterized in that When respectively generating the monitoring point identifiers corresponding to the at least two monitoring points based on the position information corresponding to the at least two monitoring points, the processing module is specifically used to: Performing geo-hash coding on the location information corresponding to the at least two monitoring points respectively to obtain corresponding coding results; Based on the values of each obtained encoding result, the encoding results are sorted to obtain the sequence numbers of the corresponding encoding results respectively; Based on each obtained serial number, a monitoring point identifier of the corresponding monitoring point is generated respectively.
11. The device according to claim 8, It is characterized in that Before obtaining the monitoring point identifiers corresponding to the starting position point and the ending position point of the track missing section based on the target vehicle, the obtaining module is further used to: For each historical vehicle, perform the following operations: Obtain at least two pieces of historical monitoring information of a historical vehicle obtained by each monitoring point within a set historical monitoring range; wherein each piece of historical monitoring information includes: the time when the corresponding monitoring point monitored the historical vehicle within the historical monitoring range; For each two adjacent historical monitoring information among the at least two historical monitoring information, the following operations are performed respectively: a historical monitoring time interval between two adjacent historical monitoring information is determined; when it is determined that the historical monitoring time interval is not greater than a preset interval threshold, a road section between the monitoring points corresponding to each of the two historical monitoring information is used as a candidate vehicle trajectory.
12. The device according to claim 8, It is characterized in that Before obtaining the monitoring point identifiers corresponding to the starting position point and the ending position point of the track missing section based on the target vehicle, the obtaining module is further used to: Acquire at least two target monitoring information of the target vehicle obtained by each monitoring point on the historical vehicle trajectory; wherein each target monitoring information includes: the time when the corresponding monitoring point monitored the target vehicle on the historical vehicle trajectory; For each two pieces of target monitoring information obtained adjacently in the at least two pieces of target monitoring information, the following operations are performed respectively: Determine the target monitoring time interval between two adjacent target monitoring information; When it is determined that the target monitoring time interval is greater than a preset interval threshold, the section between the monitoring points corresponding to the two target monitoring information is regarded as a track missing section.
13. The device according to claim 8, It is characterized in that The number of vehicle passes corresponding to each of the at least one candidate vehicle trajectory and the total number of vehicle passes corresponding to the at least one candidate vehicle trajectory within the specified historical time range, when selecting a target vehicle trajectory from the at least one candidate vehicle trajectory, the acquisition module is further used to: Obtaining the number of historical vehicle passes corresponding to each of the at least one candidate vehicle trajectory within a specified historical time range, and the total number of historical vehicle passes corresponding to the at least one candidate vehicle trajectory; Based on the obtained number of historical vehicle passes and the total number of historical vehicle passes, respectively determine the historical vehicle pass ratio of the corresponding candidate vehicle trajectory; Based on the obtained historical vehicle traffic proportions and in combination with a preset historical vehicle traffic proportion threshold, a target vehicle trajectory is selected from the candidate vehicle trajectories.
14. The device according to claim 8, It is characterized in that The number of vehicle passes corresponding to each of the at least one candidate vehicle trajectory and the total number of vehicle passes corresponding to the at least one candidate vehicle trajectory within the specified historical time range, when selecting a target vehicle trajectory from the at least one candidate vehicle trajectory, the acquisition module is further used to: Obtaining the number of target vehicle passes corresponding to each of the at least one candidate vehicle trajectory within a specified historical time range, and the total number of target vehicle passes corresponding to the at least one candidate vehicle trajectory; Based on the obtained number of passes of each target vehicle and the total number of passes of the target vehicle, respectively determine the target vehicle pass ratio of the corresponding candidate vehicle trajectory; Based on the obtained traffic proportions of each target vehicle and in combination with a preset traffic proportion threshold of the target vehicle, a target vehicle trajectory is selected from the candidate vehicle trajectories.
15. An electronic device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, It is characterized in that When the processor executes the computer program, the method according to any one of claims 1 to 7 is implemented.
16. A computer-readable storage medium having a computer program stored thereon, It is characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.
17. A computer program product, It is characterized in that When the computer program product is called by a computer, the computer executes the method according to any one of claims 1 to 7.
