Vehicle travel road detection method and device

Abstract

The application provides a vehicle driving road detection method and device. The method comprises the following steps: firstly, obtaining a target electronic fence of a target road section, a trajectory point sequence when a vehicle is driving, and at least one fence staggered access point pair. Then, according to the trajectory point sequence, it is determined whether the vehicle is in the target electronic fence or outside the target electronic fence. If the last trajectory point of the vehicle is outside the target electronic fence and the next trajectory point is inside the target electronic fence, it is determined whether the vehicle enters the target road section according to the last trajectory point, the next trajectory point and the fence staggered access point pair. The application improves the accuracy of road vehicle statistics.

Description

Technical Field

[0001] This application relates to the field of vehicle networking technology, and in particular to a method and device for detecting vehicle driving roads. Background Technology

[0002] With the development of vehicle-to-everything (V2X) technology, road traffic flow statistics are of great significance for road management and maintenance. Accurate road traffic flow statistics can help alleviate traffic congestion, reduce traffic accident rates, and provide data support for the implementation of intelligent transportation systems.

[0003] In existing technologies, for road traffic flow statistics, electronic fences are generally set up for monitored roads to determine whether the latitude and longitude of vehicle locations are within the electronic fence in real time, so as to determine whether vehicles are traveling on monitored roads, and then to count the traffic flow on the monitored roads.

[0004] However, for roads with intersecting Z-axis spaces, such as overpasses, electronic fences may cause vehicles on different road levels to be counted on the same road level, resulting in low accuracy in road vehicle counting. Summary of the Invention

[0005] This application provides a method and apparatus for detecting vehicle driving roads, in order to improve the accuracy of road vehicle statistics.

[0006] In a first aspect, embodiments of this application provide a method for detecting a vehicle's driving road, including:

[0007] Acquire the target electronic fence of the target road segment, the trajectory point sequence of the vehicle when it is driving, and at least one fence intersecting entry and exit point pair. The fence intersecting entry and exit point pair is the intersecting entry point and intersecting exit point between the target electronic fence of the target road segment and other road segments.

[0008] Based on the trajectory point sequence, determine whether the vehicle is inside or outside the target electronic fence;

[0009] If the vehicle's previous trajectory point is outside the target electronic fence and the next trajectory point is inside the target electronic fence, then the vehicle's entry or exit point is determined based on the previous trajectory point, the next trajectory point, and the fence's staggered entry and exit points.

[0010] In one possible implementation, the sample trajectory of each sample vehicle in the sample fleet is obtained within a historical time period. The sample trajectory includes a first trajectory point when the sample vehicle enters the target electronic fence and a second trajectory point when the sample vehicle leaves the target electronic fence within a first preset time period. At least one real entry point is obtained, which is used to characterize the entry point of the sample vehicle entering the target road segment. Based on the sample trajectory and at least one real entry point, a fence staggered entry and exit point pair is determined.

[0011] In one possible implementation, at least one initial cutting point pair is determined based on the sample trajectory. The initial cutting point pair represents the cutting point pair between the sample trajectory and the target electronic fence. Based on at least one real entry point, at least one initial cutting point pair is eliminated to obtain at least one non-real cutting point pair. The non-real cutting point pair represents the cutting point pair between the target electronic fence and other road segments, which are located at different height planes from the target road segment. The at least one non-real cutting point pair is clustered to obtain a cluster center point pair, which serves as the fence staggered entry and exit point pair.

[0012] In one possible implementation, based on the sample trajectory, a first adjacent trajectory point adjacent to the first trajectory point and a second adjacent trajectory point adjacent to the second trajectory point are obtained, wherein the first adjacent trajectory point is outside the target electronic fence and the second adjacent trajectory point is inside the target electronic fence; the first center point of the first trajectory point and the first adjacent trajectory point and the second center point of the second trajectory point and the second adjacent trajectory point are obtained to form an initial cutting point pair.

[0013] In one possible implementation, if a sample vehicle enters the target electronic fence and does not leave the target electronic fence after traveling at a constant speed for a second preset time, the entry trajectory point of the sample vehicle entering the target electronic fence is determined as a candidate entry point, and the second preset time is longer than the first preset time; the candidate entry point of each sample vehicle is used as the actual entry point.

[0014] In one possible implementation, the latitude and longitude of each candidate entry point are converted into a string; based on the similarity of the strings, the candidate entry points are clustered into at least one cluster; and based on the latitude and longitude of each candidate entry point in the cluster, a center point is determined as the actual entry point.

[0015] In one possible implementation, a first distance between the initial entry point of the fence and the actual entry point in the initial cutting point pair is determined; a second distance between the initial exit point of the fence and the actual entry point in the initial cutting point pair is determined; if the first distance is less than a preset distance threshold and / or the second distance is less than a preset distance threshold, the initial cutting point pair is discarded.

[0016] In one possible implementation, a first non-real cut point pair is selected from at least one non-real cut point pair as an initial cluster center point pair; a third distance is determined between a first entry point in the first non-real cut point pair and a second entry point in the second non-real cut point pair; a fourth distance is determined between a first exit point in the first non-real cut point pair and a second exit point in the second non-real cut point pair; if both the third distance and the fourth distance are less than a preset distance threshold, the latitude and longitude of the cluster entry points in the initial cluster center pair are updated according to the latitude and longitude of the first entry point and the second entry point, and the latitude and longitude of the cluster exit points in the initial cluster center pair are updated according to the latitude and longitude of the first exit point and the second exit point.

[0017] In one possible implementation, the target distance between the next trajectory point and each fence staggered entry / exit point pair is obtained; the vector angle is obtained based on the first vector formed by the previous trajectory point and the next trajectory point, and the second vector formed by the staggered entry point and staggered exit point in the fence staggered entry / exit point pair; if the target distance is less than a preset distance threshold and the vector angle is less than a preset angle threshold, it is determined that the vehicle did not enter the target road segment from other road segments.

[0018] Secondly, embodiments of this application provide a vehicle driving road detection device, including:

[0019] The acquisition module is used to acquire the target electronic fence of the target road segment, the trajectory point sequence of the vehicle when it is driving, and at least one fence staggered entry and exit point pair. The fence staggered entry and exit point pair is the staggered entry point and staggered exit point between the target electronic fence of the target road segment and other road segments.

[0020] The first determining module is used to determine whether the vehicle is inside or outside the target electronic fence based on the trajectory point sequence.

[0021] The second determining module is used to determine whether a vehicle has entered the target road segment if the vehicle's previous trajectory point is outside the target electronic fence and the next trajectory point is inside the target electronic fence, based on the previous trajectory point, the next trajectory point, and the fence's staggered entry and exit points.

[0022] Thirdly, embodiments of this application provide an electronic device, including: a memory and a processor;

[0023] The memory stores the instructions that the computer executes;

[0024] The processor executes computer execution instructions stored in memory, causing the processor to perform the first aspect and / or various possible implementations of the first aspect as described above.

[0025] Fourthly, embodiments of this application provide a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the first aspect and / or various possible implementations of the first aspect.

[0026] Fifthly, embodiments of this application provide a computer program product, including a computer program that, when executed by a processor, implements the first aspect and / or various possible implementations of the first aspect.

[0027] The vehicle driving road detection method and apparatus provided in this application delineate the target road segment by acquiring the target electronic fence. Simultaneously, it acquires the trajectory point sequence of the vehicle as a basis for determining the vehicle trajectory. Furthermore, it acquires fence intersection entry / exit point pairs to represent the intersection entry / exit points of other road segments and the target electronic fence. Then, based on the trajectory point sequence, it determines whether the vehicle is inside or outside the target electronic fence, thus determining whether the vehicle has entered the target electronic fence. If the vehicle's previous trajectory point is outside the target electronic fence and the next trajectory point is inside the target electronic fence, then based on the trajectory points before and after the vehicle enters the target electronic fence and the fence intersection entry / exit point pairs, it is determined whether the vehicle has entered the target road segment. This eliminates the possibility of vehicle trajectories from roads at different elevations interfering with the target electronic fence, thus improving the accuracy of road vehicle statistics. Attached Figure Description

[0028] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0029] Figure 1 A schematic diagram of a target electronic fence provided in an embodiment of this application;

[0030] Figure 2 A flowchart illustrating the vehicle driving road detection method provided in this application embodiment. Figure 1 ;

[0031] Figure 3 A flowchart illustrating the vehicle driving road detection method provided in this application embodiment. Figure 2 ;

[0032] Figure 4 A flowchart illustrating the vehicle driving road detection method provided in this application embodiment. Figure 3 ;

[0033] Figure 5 A flowchart illustrating the vehicle driving road detection method provided in this application embodiment. Figure 4 ;

[0034] Figure 6 This is a schematic diagram of the vehicle driving road detection device provided in the embodiments of this application;

[0035] Figure 7 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application.

[0036] The accompanying drawings illustrate specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concept of this application to those skilled in the art through reference to particular embodiments. Detailed Implementation

[0037] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0038] First, let me explain the terms used in this application:

[0039] The Haversine formula is used to calculate the great circle distance (the shortest distance along the Earth's surface) between two points on the Earth's surface.

[0040] Figure 1 This is a schematic diagram of a target electronic fence provided in an embodiment of this application, such as... Figure 1 As shown, the specific application scenario of this application is that when a vehicle is traveling above or below the target road electronic fence, when the vehicle enters the target road electronic fence, simply judging whether the vehicle's trajectory latitude and longitude points are within the range of the electronic fence cannot correctly determine whether the vehicle is traveling through the road where the target road electronic fence is located, or through the road above or below the electronic fence. This may lead to misjudgment and make the road traffic flow statistics inaccurate.

[0041] Based on the above scenarios, it is clear that existing technologies suffer from low accuracy in road vehicle statistics.

[0042] The vehicle driving road detection method provided in this application notes that regardless of whether the vehicle is traveling on the road where the target road electronic fence is located, or traveling above or below it, a cutting point will be generated with the target road electronic fence. A pair of cutting points will exist when entering and leaving the fence. If the cutting point can be determined with the target road segment (i.e.... Figure 1 (Target road) All fences on different planes that intersect with this fence at the entrance / exit points (i.e. Figure 1 By using the intersecting entry and exit points of the fence, it can determine whether a vehicle, after entering the fence, has entered the target road segment or is simply traveling on another road segment that intersects with the target road's electronic fence. This allows for accurate determination of whether a vehicle has entered the target road segment or entered another road segment that is at a different level from the target road segment, improving the accuracy of road vehicle statistics.

[0043] In the field of new energy vehicles, road vehicle statistics play a crucial role. By monitoring and analyzing the number of new energy vehicles on various road sections, we can accurately grasp vehicle travel characteristics and hotspot areas, providing data support for the scientific planning and layout of charging infrastructure and avoiding uneven distribution of charging stations. Simultaneously, by combining real-time traffic flow and traffic conditions, we can optimize battery range prediction models, improve the accuracy of range display, and alleviate users' range anxiety.

[0044] The technical solution of this application and how the technical solution of this application solves the above-mentioned technical problems are described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of this application will now be described with reference to the accompanying drawings.

[0045] Figure 2 A flowchart illustrating the vehicle driving road detection method provided in this application embodiment. Figure 1 ,like Figure 2 As shown, the method includes:

[0046] S201. Obtain the target electronic fence of the target road segment, the trajectory point sequence of the vehicle during travel, and at least one fence intersecting entry and exit point pair.

[0047] The target road segment refers to the road segment where vehicle entry and exit statistics need to be collected. For example, when it is necessary to collect statistics on vehicles traveling between City A and City B, the target road segment is the road segment between City A and City B.

[0048] A target electronic fence refers to an electronic fence set up for a target road segment, used to delineate the area of ​​the target road segment that needs to be monitored.

[0049] A trajectory point sequence refers to the set of trajectory points traversed by a vehicle.

[0050] For example, the trajectory point sequence of vehicle A is sequentially arranged in chronological order using... This means that connecting each point in sequence forms the trajectory of vehicle A.

[0051] The staggered entry and exit points of the fence refer to the staggered entry and exit points between the target electronic fence of the target road segment and other road segments.

[0052] Other road segments refer to road segments that intersect with the target electronic fence but are not on the same plane as the target road segment. For example, the target electronic fence may define road segment 1, road segment 2, and road segment 3. These three road segments are not at the same height, that is, these three road segments are not on the same plane. When the target road segment is road segment 1, the other road segments are road segments 2 and 3.

[0053] It should be understood that the target road segment and other road segments are intersected within the target electronic fence, but are not on the same plane.

[0054] An interleaved entry point refers to the entry point when a vehicle enters the target electronic fence area while traveling on other roads. An interleaved exit point refers to the exit point when a vehicle leaves the target electronic fence area while traveling on other roads.

[0055] S202. Based on the trajectory point sequence, determine whether the vehicle is inside or outside the target electronic fence.

[0056] In determining whether a vehicle is inside or outside a target electronic fence, the ray casting method can be used to determine whether each trajectory point in the vehicle's trajectory point sequence is inside or outside the target electronic fence, and then determine whether the vehicle is inside or outside the target electronic fence.

[0057] In one possible implementation, it can be based on a time-ordered sequence of trajectory points for each vehicle (using... (represented), for the point to be measured A ray is emitted in any direction, and the number of intersections with the target electronic fence boundary is counted. If the number of intersections is even, then the point is considered an even point. Outside the fence, if the number of intersections is odd, then the point... Inside the fence.

[0058] S203. If the vehicle's previous trajectory point is outside the target electronic fence and the next trajectory point is inside the target electronic fence, then determine whether the vehicle has entered the target road section based on the previous trajectory point, the next trajectory point, and the fence's staggered entry and exit points.

[0059] The previous and next trajectory points are defined in chronological order. For example, there is a trajectory point at 2:01. There is a trajectory point at 2:02. ,So For the previous trajectory point, This is the next trajectory point.

[0060] Whether a vehicle has entered the target road segment refers to whether the vehicle is driving on the road within the target road segment.

[0061] It should be understood that the fence staggered entry and exit point pairs are the exit and entry points calculated in this application embodiment that are at different heights from the target road segment and intersect with the target electronic fence. Therefore, it can be determined whether a vehicle has entered the target road segment based on the previous trajectory point, the next trajectory point, and the fence staggered entry and exit point pairs.

[0062] In one possible implementation, the target distance between the next trajectory point and each pair of fence entry / exit points is obtained. Then, based on the first vector formed by the previous trajectory point and the next trajectory point, and the second vector formed by the staggered entry and exit points in the fence entry / exit point pairs, the vector angle is obtained. If the target distance is less than a preset distance threshold and the vector angle is less than a preset angle threshold, it is determined that the vehicle did not enter the target road segment from other road segments.

[0063] The target distance refers to the distance between the next trajectory point and the staggered entrance point of the fence staggered entrance / exit point pair, and the distance between the next trajectory point and the staggered exit point of the fence staggered entrance / exit point pair.

[0064] It should be understood that when the distance between the next trajectory point of the vehicle and the intersection point of the fence is small, it means that the vehicle may be close to the target electronic fence at the time corresponding to the next trajectory point, and may enter the target road section.

[0065] The first vector refers to the vector formed by the previous trajectory point and the next trajectory point.

[0066] The second vector refers to the vector formed by the staggered entry points and staggered exit points.

[0067] An interlaced entrance point refers to the entrance point where the fence intersects with the entrance points, and an interlaced exit point refers to the exit point where the fence intersects with the entrance points.

[0068] The vector angle refers to the angle between the first vector and the second vector.

[0069] The preset angle threshold refers to the threshold used to measure the angle between the first vector and the second vector.

[0070] For example, there exists a vehicle's trajectory point. This monitors the vehicle's entry and exit status within the target electronic fence road (i.e., whether it enters the target road segment). For example, if the time... Time trajectory points The status is outside the fence, next trajectory point It has been moved to within the fence. (Date) At this point, the trajectory point is determined. staggered entry and exit points at distance from the fence ( The target distance and the angle between the vectors are ( ).

[0071] If the target distance <4m and the included angle of the vectors satisfies ,here , These are the staggered entrance and exit points of the fence. If this condition is met, it is determined that the vehicle has not entered the target road section, but has passed through the space above or below the road. If this condition is not met, it is determined that the vehicle has entered the target road section, so that corresponding monitoring and statistics or corresponding control measures can be implemented.

[0072] The vehicle driving road detection method provided in this application identifies the intersection points and exit points between the target electronic fence and other road segments by combining the target electronic fence with the vehicle's trajectory point sequence. These are used as fence intersection entry / exit point pairs, representing the entry and exit points where other road segments intersect with the target electronic fence. Thus, if the vehicle's trajectory points show that the previous trajectory point is outside the target electronic fence and the next trajectory point is inside the target electronic fence, the vehicle has entered the target electronic fence. By combining these two trajectory points and the fence intersection entry / exit point pairs, it can be determined whether the vehicle has entered the target road segment. This improves the accuracy of road vehicle statistics when calculating traffic flow on the target road segment.

[0073] In practical applications, the latitude and longitude trajectory data reported by vehicles undergoes coordinate transformation from the Earth coordinate system to the Mars coordinate system to obtain encrypted and offset latitude and longitude coordinates. Furthermore, based on the Mars coordinate system, a polygonal electronic fence is created around the target road segment on the front-end page, enclosing the target road segment, and the latitude and longitude coordinates of its fence vertices are collected. The vertex assignments are then set as follows: , ... The corresponding latitude and longitude are , Indicates longitude. Indicates latitude.

[0074] Figure 3 A flowchart illustrating the vehicle driving road detection method provided in this application embodiment. Figure 2 ,like Figure 3 As shown, in this embodiment... Figure 2 Based on the embodiments, the method for detecting vehicle driving roads is described in detail, and the method includes:

[0075] S301. Obtain the sample trajectory of each sample vehicle in the sample fleet within a historical time period.

[0076] The sample fleet refers to a pre-set fleet, and the trajectory of the sample fleet must include the trajectory of the target road segment as well as the trajectory of the fleet in other road segments.

[0077] For example, consider two teams, Team A and Team B. Team A has not traveled on the target road segment but has only traveled on other road segments, while Team B has traveled on both the target road segment and other road segments. In this case, Team B is selected as the sample team.

[0078] Sample vehicles refer to the vehicles in the sample fleet.

[0079] Historical time period refers to the time period selected for the trajectory of the target vehicle fleet. For example, selecting one year as the historical time period means selecting the trajectory of the sample vehicle fleet within one year.

[0080] A sample trajectory refers to the trajectory of a sample vehicle fleet. The sample trajectory is selected from the trajectories of sample vehicle fleets within a historical time period.

[0081] For example, for the historical trajectories of sample vehicles in the sample fleet over a year, the vehicles are grouped, and within each group, the historical trajectory points of individual sample vehicles are obtained in chronological order. The trajectory coordinates of each sample vehicle can be represented as follows: .

[0082] The sample trajectory includes the first trajectory point when the sample vehicle enters the target electronic fence, and the second trajectory point when the sample vehicle leaves the target electronic fence within a first preset time period.

[0083] The first trajectory point refers to the first trajectory point of the sample vehicle after entering the target electronic fence in the time sequence of trajectory points; the first trajectory point is inside the target electronic fence. The second trajectory point refers to the first trajectory point of the sample vehicle after leaving the target electronic fence in the time sequence of trajectory points; the second trajectory point is outside the target electronic fence.

[0084] The first preset duration refers to the threshold for measuring the time a sample vehicle stays within the target electronic fence.

[0085] S302. Obtain at least one real entry point.

[0086] The real entry point is used to characterize the entry point where the sample vehicle enters the target road segment, that is, the entry point where the sample vehicle enters the target electronic fence when driving on the target road segment.

[0087] In one possible implementation, if a sample vehicle enters the target electronic fence and does not leave the target electronic fence after traveling at a constant speed for a second preset time, the entry trajectory point of the sample vehicle entering the target electronic fence is determined as a candidate entry point, and the second preset time is longer than the first preset time; the candidate entry point of each sample vehicle is used as the actual entry point.

[0088] The second preset duration also refers to a threshold for measuring the time a sample vehicle stays within the target electronic fence, but the second preset duration is longer than the first preset duration. For example, the first preset duration is set to 10 seconds, and the second preset duration is set to 1 minute.

[0089] Candidate entry points refer to the entry points into the target electronic fence when the sample vehicle does not leave the target electronic fence within the preset time.

[0090] For example, a sample vehicle C from the target electronic fence Enter, with speed as If a vehicle has been traveling at a constant speed for time T without leaving the target electronic fence, it is considered to have entered the target road segment. This is the candidate entry point corresponding to sample vehicle C.

[0091] For example, for each candidate entry point generated by a sample vehicle, the set { can be used as the actual entry point}. , , ... } is used for representation.

[0092] In practical applications, a sample vehicle may enter the target road segment multiple times, thus generating multiple candidate entry points with the target electronic fence. In this case, the multiple candidate entry points of this sample vehicle can be clustered and used as the final candidate entry point representing the sample vehicle.

[0093] For each sample vehicle in the sample fleet, each trajectory will generate multiple entry points at the same geographical location's real road entrance. Therefore, it is necessary to integrate multiple points at the same entry point into a single point. Thus, one possible implementation involves converting the latitude and longitude of each candidate entry point into a string. Then, based on the similarity of the strings, the candidate entry points are clustered into at least one cluster. Finally, based on the latitude and longitude of each candidate entry point within a cluster, a center point is determined as the real entry point.

[0094] The string refers to the expression corresponding to the latitude and longitude of the candidate entry point, used to represent each candidate entry point.

[0095] A cluster is a set of similar candidate entry points.

[0096] The center point refers to the center point among multiple candidate entry points in a cluster.

[0097] In practical applications, the real entry point set is clustered, and a geospatial hashing algorithm (GeographicHash, GeoHash algorithm) is used to convert the latitude and longitude of these points into strings. Points with the same first 9 characters in the string are identified as belonging to the same 4-meter-wide geographic grid. Points in the same cluster are centered by taking the (mean of longitude, mean of latitude).

[0098] S303. Based on the sample trajectory and at least one real entry point, determine the fenced staggered entry and exit point pairs.

[0099] In one possible implementation, at least one initial cut point pair is first determined based on the sample trajectory. Then, based on at least one true entry point, the at least one initial cut point pair is eliminated, resulting in at least one non-true cut point pair. Next, the at least one non-true cut point pair is clustered to obtain cluster center point pairs, which serve as fence staggered entry / exit point pairs.

[0100] The initial cut point pair represents the cut point pair between the sample trajectory and the target electronic fence.

[0101] For example, the initial cut-off point pair includes the initial entry point and the initial exit point of the target electronic fence. The initial entry point is the cut-off point between the sample vehicle's trajectory and the target electronic fence when the sample vehicle enters the target electronic fence, and the initial exit point is the cut-off point between the sample vehicle's trajectory and the target electronic fence when the sample vehicle leaves the target electronic fence.

[0102] In one possible implementation, based on the sample trajectory, a first adjacent trajectory point adjacent to the first trajectory point and a second adjacent trajectory point adjacent to the second trajectory point are obtained. Then, the first center point of the first trajectory point and the first adjacent trajectory point, and the second center point of the second trajectory point and the second adjacent trajectory point are obtained to form an initial cutting point pair.

[0103] The first adjacent trajectory point refers to the trajectory point adjacent to the first trajectory point, which is located outside the target electronic fence.

[0104] The second adjacent trajectory point refers to the trajectory point adjacent to the second trajectory point, and the second adjacent trajectory point is located within the target electronic fence.

[0105] It should be understood that the first adjacent trajectory point and the first trajectory point are used to represent the trajectory point pair when entering the target electronic fence. The second adjacent trajectory point and the second trajectory point are used to represent the trajectory point pair when leaving the target electronic fence.

[0106] The first center point refers to the center point between the first trajectory point and the first adjacent trajectory point, used to represent the cutting point generated when the sample vehicle enters the target electronic fence. The second center point refers to the center point between the second trajectory point and the second adjacent trajectory point, used to represent the cutting point generated when the sample vehicle leaves the target electronic fence. Accordingly, the cutting points generated upon entry and those generated upon exit are combined to form an initial cutting point pair.

[0107] For example, there exists a first trajectory point as The first adjacent trajectory point is At this point, the first trajectory point Within the target electronic fence, the first adjacent trajectory point Outside the target electronic fence, , The line connecting the target electronic fence creates a cutting point, at which point... and The center point, as the first center point. .

[0108] There also exists a second trajectory point. The second adjacent trajectory point is At this time, the second trajectory point Outside the target electronic fence, the second adjacent trajectory point Within the target electronic fence, , The line connecting the target electronic fence creates a cutting point, at which point... and The center point, as the second center point .

[0109] It should be understood that the first center point Second center point This refers to the event generated when a sample vehicle enters the target electronic fence and then leaves the target electronic fence within a first preset time period, and consists of... This is used to indicate that the sample vehicle traveled along a road that intersected with the target electronic fence. That is, the initial cutting point pair. This is the initial entry point of the fence. This is the initial exit point of the fence.

[0110] For multiple sample vehicles in the sample convoy, the set of initial cut-off point pairs is { , ,... This set includes both cut-off point pairs that intersect with the target electronic fence on other road segments and cut-off point pairs that intersect with the target electronic fence on the target road segment.

[0111] In practical applications, sample vehicles may pass through the target road segment or other road segments multiple times, thus creating multiple cutting point pairs by intersecting with the target electronic fence.

[0112] Non-real cut point pairs represent the cut point pairs between the target electronic fence and other road segments, that is, the cut point pairs remaining after removing the initial cut point pairs.

[0113] For example, a non-real cut point pair includes a real fence entry point and a real fence exit point.

[0114] The actual entry point of the fence refers to the entry point where the sample vehicle enters the target electronic fence while driving on other road sections.

[0115] The actual exit point of the fence refers to the exit point where the sample vehicle leaves the target electronic fence on other road sections.

[0116] The method for removing initial cut point pairs can be combined with the semi-sine formula. In one possible implementation, a first distance between the initial fence entry point and the actual entry point in the initial cut point pair is determined. Then, a second distance between the initial fence exit point and the actual entry point in the initial cut point pair is determined. If the first distance is less than a preset distance threshold and / or the second distance is less than a preset distance threshold, the initial cut point pair is removed.

[0117] The first distance refers to the distance between the initial entrance point of the fence and the actual entrance point, and the second distance refers to the distance between the initial exit point of the fence and the actual entrance point.

[0118] The preset distance threshold refers to the threshold used to measure the distance between the initial cut point pair and the actual entry point.

[0119] It should be understood that if the first distance is less than a preset distance threshold and / or the second distance is less than a preset distance threshold, it means that the initial entry point of the fence in the initial cutting point pair is closer to the actual entry point, and / or the initial exit point of the fence is closer to the actual entry point. This means that the initial entry point of the fence may be on the same plane as the actual entry point, and / or the initial exit point of the fence may be on the same plane as the actual entry point. After removing this type of point pair, point pairs on the same plane as the actual entry point are eliminated. The remaining point pairs represent points at different heights from the actual entry point and different heights from the target road segment, i.e., the cutting point pairs between the vehicle and the target electronic fence after the vehicle enters other road segments.

[0120] For example, for a certain initial cutting point pair Calculate the initial entry point of the fence. With the real entry point First distance, initial exit point of the fence With the real entry point The second distance.

[0121] In practical applications, for the first distance, the formula for the semi-versus is used. , and c. Calculation.

[0122] in, , for and latitude, , for and longitude, for - , for - . The Earth's radius is 6,370,996.81 meters. This is the first distance.

[0123] for and The second distance between them is calculated in the same way as described above.

[0124] For the real entry point set { , , ... Each point in} is related to The first and second distances corresponding to each actual entry point are calculated. When the preset distance threshold is 4 meters, if there exists a first distance and / or a second distance that is less than 4 meters, it is assumed that... Indicates the first distance, Indicates the second distance, i.e. <4 meters and / or If it is less than 4 meters, then it is considered , Belonging to the same cutting point, and / or , Belonging to the same cutting point, Removed.

[0125] Thus, the final remaining initial cutting point pairs, that is, the cutting point pairs determined to be on a plane not at the same height as the target road segment fence, i.e., the cutting point pairs between the vehicle and the target electronic fence after entering other road segments, are represented by { , ,... } is used for representation.

[0126] Cluster center pairs refer to non-real cut point pairs after clustering.

[0127] It should be understood that when there are multiple sample vehicles in the sample vehicle fleet, the trajectories of multiple sample vehicles may have cutting points with the target electronic fence. There are multiple cutting points at the same location. Therefore, in order to facilitate subsequent calculations, it is necessary to cluster the non-real cutting point pairs.

[0128] Therefore, in one possible implementation, the first non-true cut point pair is selected from at least one non-true cut point pair as the initial cluster center point pair.

[0129] Next, determine the third distance between the first entry point in the first non-real cutting point pair and the second entry point in the second non-real cutting point pair; determine the fourth distance between the first exit point in the first non-real cutting point pair and the second exit point in the second non-real cutting point pair.

[0130] If both the third and fourth distances are less than the preset distance threshold, then the latitude and longitude of the initial cluster center-to-cluster entry point are updated according to the latitude and longitude of the first and second entry points, and the latitude and longitude of the initial cluster center-to-cluster exit point are updated according to the latitude and longitude of the first and second exit points.

[0131] The first non-true cut point pair refers to the pair selected from at least one determined non-true cut point pair. The selection method can be to arbitrarily select a non-true cut point pair as the initial cluster center pair. Then, from the remaining non-true cut point pairs excluding the initial cluster center pair, another non-true cut point pair is arbitrarily selected as the second non-true cut point pair.

[0132] The first and second entry points refer to the entry points when entering the target electronic fence, which are not actual cutting points.

[0133] The first and second exit points refer to the exit points when leaving the target electronic fence, which are not actual cutting points.

[0134] The first distance refers to the distance between the first entrance point and the second entrance point, and the second distance refers to the distance between the first exit point and the second exit point.

[0135] It should be understood that if both the first distance and the second distance are less than the preset distance threshold, it means that the distance between the first non-real cutting point pair and the second non-real cutting point pair is similar, and they can be regarded as the same non-real cutting point pair, that is, clustering.

[0136] For example, when the first non-real cutting point is used The second non-real cutting point is used When indicated, the first entry point is The second entrance point is The first exit point is The second exit point is When, can be used Indicates the first distance, This indicates the second distance. When the preset distance threshold is 4 meters, when... Miqie When the first non-real cut point pair and the second non-real cut point pair can be clustered.

[0137] In one possible implementation, through the formula , Calculate the latitude and longitude of the initial cluster center-to-internal cluster entry point and the initial cluster center-to-internal cluster exit point.

[0138] in, The latitude and longitude of the initial cluster center are the coordinates of the entry point of the central cluster. The latitude and longitude of the initial cluster center and the exit point of the central cluster; The latitude and longitude of the first entry point. The latitude and longitude of the second entry point; The latitude and longitude of the first exit point. The coordinates of the second exit point are latitude and longitude.

[0139] In practical applications, if rice or When this occurs, it means that the first and second non-real cut point pairs cannot be clustered. In this case, the first non-real cut point pair... As the initial pair of cluster centers, determine a new pair of non-true cut points. Based on this, a new judgment is made, and each non-true cut point pair is classified by performing the above calculation with the existing centroid pairs one by one until multiple cluster centroid pairs are finally obtained. To express.

[0140] The vehicle driving road detection method provided in this application collects the trajectories of sample vehicle convoys within historical time periods, extracts the first trajectory point of a vehicle entering a target electronic fence and the corresponding second trajectory point of a vehicle leaving within a first preset time period. Then, it determines at least one actual entry point for the sample vehicle entering the target road segment. Finally, based on the sample trajectories and actual entry points, it obtains a fence-interleaved entry and exit point pair.

[0141] Figure 4 A flowchart illustrating the vehicle driving road detection method provided in this application embodiment. Figure 3 ,like Figure 4 As shown, the method includes:

[0142] S401. Upload the trajectory point sequence of the target vehicle to the big data analysis platform.

[0143] Among them, the trajectory point sequence is the latitude and longitude data reported by the vehicle to the big data analysis platform in real time.

[0144] A vehicle driving road detection system has been deployed on the big data analysis platform, which is the main body for implementing the vehicle driving road detection method.

[0145] S402. Determine whether the target vehicle has entered the target electronic fence.

[0146] Specifically, if the previous trajectory point of the target vehicle is outside the target electronic fence and the next trajectory point is inside the target electronic fence, then the target vehicle enters the target electronic fence.

[0147] S403. Determine whether the target distance to the target vehicle is less than the preset distance threshold. If yes, execute S404; otherwise, execute S406.

[0148] Specifically, if the target distance between the next trajectory point of the target vehicle and each pair of fence entry and exit points is less than a preset distance threshold, then the target distance of the target vehicle is less than the preset distance threshold.

[0149] S404. Determine whether the vector angle of the target vehicle is less than the preset angle threshold. If yes, execute S405; otherwise, execute S406.

[0150] Specifically, the vector angle is obtained based on the first vector formed by the previous trajectory point and the next trajectory point, and the second vector formed by the staggered entrance and exit points in the fence staggered entrance and exit point pair. When the vector angle is less than a preset angle threshold, the vector angle of the target vehicle is less than the preset angle threshold.

[0151] S405, the target vehicle was traveling on other road sections and did not enter the target road section.

[0152] S406. If a target vehicle enters the target road segment from another road segment, it will be included in the traffic flow statistics of that target road segment.

[0153] Figure 5 A flowchart illustrating the vehicle driving road detection method provided in this application embodiment. Figure 4 ,like Figure 5 As shown, the method includes:

[0154] S501. Upload the sample trajectory to the big data analysis platform.

[0155] S502. Construct target electronic fences for target road sections.

[0156] S503. Based on the sample trajectory, determine the initial cutting point pair where the trajectory intersects with the target electronic fence.

[0157] S504. Obtain at least one real entry point.

[0158] S505. Based on at least one real entry point, at least one initial cutting point pair is discarded to obtain at least one non-real cutting point pair.

[0159] S506. Clustering at least one pair of non-real cutting points yields a pair of cluster center points, which serve as fence staggered entry and exit point pairs.

[0160] Figure 6 This is a schematic diagram of the vehicle driving road detection device provided in the embodiments of this application, as shown below. Figure 6 As shown, the vehicle driving road detection device 60 provided in this embodiment includes:

[0161] The acquisition module 601 is used to acquire the target electronic fence of the target road segment, the trajectory point sequence of the vehicle when it is driving, and at least one fence staggered entry and exit point pair, which is the staggered entry point and staggered exit point between the target electronic fence of the target road segment and other road segments.

[0162] The first determining module 602 is used to determine whether the vehicle is inside or outside the target electronic fence based on the trajectory point sequence.

[0163] The second determining module 603 is used to determine whether a vehicle has entered the target road segment if the vehicle's previous trajectory point is outside the target electronic fence and the next trajectory point is inside the target electronic fence, based on the previous trajectory point, the next trajectory point, and the fence's staggered entry and exit points.

[0164] In one possible implementation, the acquisition module 601 is further configured to acquire the sample trajectory of each sample vehicle in the sample fleet within a historical time period, the sample trajectory including a first trajectory point when the sample vehicle enters the target electronic fence, and a second trajectory point when the sample vehicle leaves the target electronic fence within a first preset time period; acquire at least one real entry point, the real entry point being used to characterize the entry point of the sample vehicle entering the target road segment; and determine the fence staggered entry and exit point pair based on the sample trajectory and at least one real entry point.

[0165] In one possible implementation, the acquisition module 601 is further configured to: determine at least one initial cutting point pair based on the sample trajectory, wherein the initial cutting point pair represents the cutting point pair between the sample trajectory and the target electronic fence; eliminate at least one initial cutting point pair based on at least one real entry point to obtain at least one non-real cutting point pair, wherein the non-real cutting point pair represents the cutting point pair between the target electronic fence and other road segments, wherein the other road segments and the target road segment are at different height planes; and cluster the at least one non-real cutting point pair to obtain a cluster center point pair as the fence staggered entry and exit point pair.

[0166] In one possible implementation, the acquisition module 601 is further configured to acquire, based on the sample trajectory, a first adjacent trajectory point adjacent to the first trajectory point and a second adjacent trajectory point adjacent to the second trajectory point, wherein the first adjacent trajectory point is outside the target electronic fence and the second adjacent trajectory point is inside the target electronic fence; and acquire the first center point of the first trajectory point and the first adjacent trajectory point, and the second center point of the second trajectory point and the second adjacent trajectory point, to form an initial cutting point pair.

[0167] In one possible implementation, the acquisition module 601 is further configured to determine the entry trajectory point of the sample vehicle entering the target electronic fence as a candidate entry point if the sample vehicle enters the target electronic fence and does not leave the target electronic fence after driving at a constant speed for a second preset time, wherein the second preset time is longer than the first preset time; and to use the candidate entry point of each sample vehicle as the actual entry point.

[0168] In one possible implementation, the acquisition module 601 is further configured to convert the latitude and longitude of each candidate entry point into a string; cluster each candidate entry point into at least one cluster based on the similarity of each string; and determine the center point as the real entry point based on the latitude and longitude of each candidate entry point in the cluster.

[0169] In one possible implementation, the acquisition module 601 is further configured to determine a first distance between the initial entry point of the fence and the actual entry point in the initial cutting point pair; determine a second distance between the initial exit point of the fence and the actual entry point in the initial cutting point pair; and if the first distance is less than a preset distance threshold and / or the second distance is less than a preset distance threshold, then the initial cutting point pair is discarded.

[0170] In one possible implementation, the acquisition module 601 is further configured to select a first non-real cutting point pair from at least one non-real cutting point pair as an initial cluster center point pair; determine a third distance between a first entry point in the first non-real cutting point pair and a second entry point in the second non-real cutting point pair; determine a fourth distance between a first exit point in the first non-real cutting point pair and a second exit point in the second non-real cutting point pair; if both the third distance and the fourth distance are less than a preset distance threshold, then update the latitude and longitude of the cluster entry points in the initial cluster center pair according to the latitude and longitude of the first entry point and the second entry point, and update the latitude and longitude of the cluster exit points in the initial cluster center pair according to the latitude and longitude of the first exit point and the second exit point.

[0171] In one possible implementation, the second determining module 603 is further configured to obtain the target distance between the next trajectory point and each fence staggered entry / exit point pair; obtain the vector angle based on the first vector formed by the previous trajectory point and the next trajectory point, and the second vector formed by the staggered entry point and staggered exit point in the fence staggered entry / exit point pair; if the target distance is less than a preset distance threshold and the vector angle is less than a preset angle threshold, then it is determined that the vehicle did not enter the target road segment from other road segments.

[0172] The vehicle driving road detection device provided in this embodiment can execute the method provided in the above method embodiment. Its implementation principle and technical effect are similar, and will not be described in detail here.

[0173] Figure 7 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Figure 7 As shown, the electronic device 70 provided in this embodiment includes at least one processor 701 and a memory 702. Optionally, the electronic device 70 further includes a communication component 703. The processor 701, memory 702, and communication component 703 are connected via a bus 704.

[0174] In a specific implementation, at least one processor 701 executes computer execution instructions stored in memory 702, causing at least one processor 701 to perform the above-described method.

[0175] The specific implementation process of processor 701 can be found in the above method embodiments, and its implementation principle and technical effect are similar. It will not be repeated here.

[0176] In the above embodiments, it should be understood that the processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in this invention can be directly implemented by a hardware processor, or implemented by a combination of hardware and software modules within the processor.

[0177] The memory may include random access memory (RAM) and may also include non-volatile memory (NVM), such as at least one disk storage device.

[0178] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of illustration, the buses shown in the accompanying drawings are not limited to a single bus or a single type of bus.

[0179] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the above-described method.

[0180] This application also provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the above-described method.

[0181] The aforementioned readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The readable storage medium can be any available medium accessible to a general-purpose or special-purpose computer.

[0182] An exemplary readable storage medium is coupled to a processor, enabling the processor to read information from and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can reside in an Application Specific Integrated Circuit (ASIC). Alternatively, the processor and the readable storage medium can exist as discrete components in the device.

[0183] The division of units is merely a logical functional division; in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces, devices, or units, and may be electrical, mechanical, or other forms.

[0184] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0185] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0186] If a function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0187] Those skilled in the art will understand that all or part of the steps of the above-described method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When executed, the program performs the steps of the above-described method embodiments; and the aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.

[0188] Finally, it should be noted that other embodiments of the invention will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This invention is intended to cover any variations, uses, or adaptations of the invention that follow the general principles of the invention and include common knowledge or customary techniques in the art not disclosed herein, and is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of the invention is limited only by the appended claims.

Claims

1. A method for detecting vehicle driving routes, characterized in that, include: Obtain the target electronic fence for the target road segment and the sequence of trajectory points of vehicles during their travel; Obtain at least one real entry point, which is used to characterize the entry point for each sample vehicle in the sample convoy to enter the target road segment; Based on the sample trajectory of each sample vehicle in the sample fleet within a historical time period and the at least one real entry point, at least one fence staggered entry / exit point pair is determined. The fence staggered entry / exit point pair is the staggered entry point and staggered exit point between the target electronic fence of the target road segment and other road segments. The sample trajectory includes the first trajectory point when the sample vehicle enters the target electronic fence, and the second trajectory point when the sample vehicle leaves the target electronic fence within a first preset time period. Based on the trajectory point sequence, it is determined whether the vehicle is inside or outside the target electronic fence; If the vehicle's previous trajectory point is outside the target electronic fence and the next trajectory point is inside the target electronic fence, then based on the previous trajectory point, the next trajectory point, and the fence's staggered entry and exit points, it is determined whether the vehicle has entered the target road segment; The step of obtaining at least one real entry point includes: if the sample vehicle enters the target electronic fence and does not leave the target electronic fence after driving at a constant speed for a second preset time, then the entry trajectory point of the sample vehicle entering the target electronic fence is determined as a candidate entry point, and the second preset time is longer than the first preset time. The candidate entry point for each sample vehicle is used as the actual entry point.

2. The method according to claim 1, characterized in that, Also includes: Obtain the sample trajectory of each sample vehicle in the sample fleet within a historical time period.

3. The method according to claim 2, characterized in that, Determining the fenced staggered entry / exit point pair based on the sample trajectory and the at least one real entry point includes: Based on the sample trajectory, at least one initial cutting point pair is determined, the initial cutting point pair representing the cutting point pair between the sample trajectory and the target electronic fence; Based on the at least one real entry point, the at least one initial cutting point pair is eliminated to obtain at least one non-real cutting point pair. The non-real cutting point pair represents the cutting point pair between the target electronic fence and other road segments, and the other road segments are at different height planes from the target road segment. Cluster the at least one non-real cutting point pair to obtain the cluster center point pair, which serves as the fence staggered entry and exit point pair.

4. The method according to claim 3, characterized in that, The step of determining at least one initial cutting point pair based on the sample trajectory includes: Based on the sample trajectory, a first adjacent trajectory point adjacent to the first trajectory point and a second adjacent trajectory point adjacent to the second trajectory point are obtained. The first adjacent trajectory point is outside the target electronic fence, and the second adjacent trajectory point is inside the target electronic fence. The first center point of the first trajectory point and the first adjacent trajectory point, and the second center point of the second trajectory point and the second adjacent trajectory point are obtained to form the initial cutting point pair.

5. The method according to claim 1, characterized in that, The candidate entry points based on each sample vehicle, used as the actual entry points, include: Convert the latitude and longitude of each candidate entry point into a string; Based on the similarity of each string, the candidate entry points are clustered into at least one class. Based on the latitude and longitude of each candidate entry point in the cluster, a center point is determined as the actual entry point.

6. The method according to claim 3, characterized in that, The step of eliminating at least one initial cutting point pair based on the at least one real entry point to obtain at least one non-real cutting point pair includes: Determine the first distance between the initial entry point of the fence and the actual entry point in the initial cutting point pair; Determine the second distance between the initial exit point of the fence and the actual entry point in the initial cutting point pair; If the first distance is less than a preset distance threshold and / or the second distance is less than a preset distance threshold, then the initial cutting point pair will be discarded.

7. The method according to claim 3, characterized in that, The step of clustering the at least one pair of non-real cut points to obtain a pair of cluster center points includes: Select the first non-real cut point pair from the at least one non-real cut point pair as the initial cluster center point pair; Determine the third distance between the first entry point in the first non-real cutting point pair and the second entry point in the second non-real cutting point pair; Determine the fourth distance between the first exit point in the first non-real cutting point pair and the second exit point in the second non-real cutting point pair; If both the third distance and the fourth distance are less than a preset distance threshold, then the latitude and longitude of the initial cluster center-to-cluster entry point are updated according to the latitude and longitude of the first entry point and the second entry point, and the latitude and longitude of the initial cluster center-to-cluster exit point are updated according to the latitude and longitude of the first exit point and the second exit point.

8. The method according to claim 1, characterized in that, The step of determining whether the vehicle has entered the target road segment based on the previous trajectory point, the next trajectory point, and the fence intersection entry / exit point pair includes: Obtain the target distance between the next trajectory point and each pair of fence entry / exit points; The included angle is obtained based on the first vector formed by the previous trajectory point and the next trajectory point, and the second vector formed by the staggered entrance point and staggered exit point in the fence staggered entrance and exit point pair. If the target distance is less than a preset distance threshold and the vector angle is less than a preset angle threshold, then it is determined that the vehicle did not enter the target road segment from the other road segments.

9. A vehicle driving road detection device, characterized in that, The vehicle driving road detection device is used to implement the vehicle driving road detection method according to any one of claims 1-8, and the device includes: The acquisition module is used to acquire the target electronic fence of the target road segment, the trajectory point sequence of the vehicle when it is driving, and at least one fence staggered entry and exit point pair, wherein the fence staggered entry and exit point pair is the staggered entry point and staggered exit point between the target electronic fence of the target road segment and other road segments. The first determining module is used to determine whether the vehicle is inside or outside the target electronic fence based on the trajectory point sequence. The second determining module is used to determine whether the vehicle has entered the target road segment if the vehicle's previous trajectory point is outside the target electronic fence and the next trajectory point is inside the target electronic fence, based on the previous trajectory point, the next trajectory point, and the fence's staggered entry and exit point pair.

Images