A vehicle speed compliance detection method, device and electronic equipment

Abstract

The application provides a vehicle speed compliance detection method and device and electronic equipment. The method comprises the following steps: generating a trajectory point sequence according to vehicle running trajectory information, and determining the nearest distance between each trajectory point in the trajectory point sequence and all target road segment endpoints; screening candidate trajectory points representing the entry and exit of a vehicle from a target road segment from all trajectory points according to the nearest distance and a plurality of preset constraint conditions; determining the entry and exit index of the target road segment according to the traffic type, and generating a trajectory point interval representing the passing of the target road segment; eliminating the front and rear transition sections in the trajectory point interval to obtain a core interval, and constructing an effective trajectory point set according to the trajectory points in the core interval; and judging the vehicle speed compliance of each effective trajectory point, and marking the effective trajectory points that do not meet the vehicle speed compliance as abnormal vehicle speed. Through the above vehicle speed compliance detection method, device and electronic equipment, the problems of unstable road section interval recognition, high dependence on high-precision maps and low processing efficiency are solved.

Description

Technical Field

[0001] This application relates to the field of vehicle engineering technology, and more specifically, to a method, apparatus, and electronic device for detecting vehicle speed compliance. Background Technology

[0002] With the development of vehicle operation monitoring, road testing and verification and intelligent management technologies, scenarios such as whole vehicle road testing, test track monitoring, closed park management and specific task road evaluation all require automated analysis of the vehicle's operating status on preset multi-target road sections. Among these, vehicle speed compliance is the core evaluation indicator. Existing methods for evaluating vehicle speed compliance mainly fall into three categories: First, manual or semi-automatic offline analysis, which relies on manual marking of road segment locations and combining video and mileage markers. This method suffers from low efficiency, strong subjectivity, and difficulty in adapting to long-term monitoring needs. Second, interval identification based on geofencing or single-point triggering, which determines road segment entry and exit solely through fixed coordinate ranges. In scenarios with multiple road segments continuously distributed, near start and end points, and repeated vehicle detours, this method is susceptible to location drift, changes in sampling frequency, and low-speed parking, leading to errors in road segment extraction and confusion with adjacent road segment data. Third, trajectory matching methods based on road maps or centerlines require projecting the trajectory onto the road network and then calculating vehicle speed segment by segment. This method heavily relies on high-precision map data, and its accuracy is insufficient in scenarios without high-precision maps, such as closed test roads, non-public roads, and temporary road segments. Furthermore, the computational complexity of large-scale trajectory data is high, which is not conducive to engineering deployment.

[0003] In summary, existing technologies generally suffer from problems such as unstable road segment identification, susceptibility to interference from boundary transition sections, high dependence on maps, and low batch processing efficiency. They are unable to achieve stable road segment positioning and accurate and repeatable automated assessment of vehicle speed compliance under conditions of no high-precision maps, dense distribution of multiple road segments, and the presence of trajectory noise. They are also unable to meet the needs of multi-scenario, long-term, and standardized vehicle speed quality monitoring. Summary of the Invention

[0004] In view of this, the purpose of this application is to provide a vehicle speed compliance detection method, device and electronic device to overcome at least one of the above-mentioned defects.

[0005] In a first aspect, embodiments of this application provide a method for detecting vehicle speed compliance, including: Collect vehicle trajectory information and generate a sequence of trajectory points based on the vehicle trajectory information; Determine the shortest distance between each trajectory point in the trajectory point sequence and all target road segment endpoints. Based on the shortest distance and multiple preset constraints, select candidate trajectory points that represent vehicle entry and exit from all trajectory points. The candidate trajectory points include different traffic types. The entry and exit indices of the target road segment are determined based on the traffic type of the candidate trajectory points, and the trajectory point intervals representing the vehicle passing through the target road segment are generated. The core interval is obtained by removing the transition segments between the beginning and end of the trajectory point interval, and a set of valid trajectory points is constructed based on the valid trajectory points within the core interval. Determine the speed compliance of each valid trajectory point, and mark the valid trajectory points that do not meet the speed compliance requirements as having abnormal speeds.

[0006] In an optional implementation, the step of selecting candidate trajectory points representing vehicle entry and exit from all trajectory points based on the nearest distance and multiple preset constraints includes: determining the trajectory points whose nearest distance meets the entry and exit range requirements as initial candidate trajectory points; and determining the initial candidate trajectory points that simultaneously meet multiple preset constraints as the final candidate trajectory points for the target road segment. The multiple preset constraints include the nearest distance constraint, auxiliary geometric constraints, and distance trend constraints.

[0007] In an optional implementation, the following methods are used to determine whether the initial candidate trajectory point simultaneously satisfies multiple preset constraints: the nearest distance constraint is determined based on the difference between the endpoint distance and the nearest distance between the initial candidate trajectory point and the endpoint of the target road segment; the auxiliary geometric constraint is determined based on the comparison result between the endpoint distance and the effective length of the target road segment; and the distance trend constraint is determined based on the comparison result between the endpoint distance and the endpoint distance between the next initial candidate trajectory point and the endpoint of the target road segment.

[0008] In an optional implementation, the trajectory point interval includes a first trajectory point representing the vehicle entering the target road segment and a second trajectory point representing the vehicle leaving the target road segment. The method further includes: determining the vehicle travel time based on the time of the first trajectory point and the time of the second trajectory point; and verifying the travel time to eliminate abnormal trajectory point intervals.

[0009] In an optional implementation, the step of removing the preceding and following transition segments in the trajectory point interval to obtain the core interval includes: determining the number of trajectory points between the first trajectory point and the second trajectory point, and based on the number of trajectory points and a preset ratio, determining the number of trajectory points in the first transition segment before the preceding transition segment and the number of trajectory points in the second transition segment before the following transition segment; determining the trajectory point located at the number of trajectory points in the first transition segment after the first trajectory point as the first core trajectory point of the core interval, and determining the trajectory point located at the number of trajectory points in the second transition segment after the first trajectory point as the second core trajectory point of the core interval.

[0010] In an optional implementation, the step of determining the speed compliance of each valid trajectory point and marking the speed of valid trajectory points that do not meet the speed compliance requirements as abnormal includes: verifying the speed compliance of each valid trajectory point using a two-sided tolerance criterion method based on a preset reference speed and a preset allowable deviation; and setting an abnormal speed mark for valid trajectory points that do not meet the speed compliance requirements.

[0011] In an optional implementation, the method further includes: counting the number of valid entries into the target road segment, the speed qualification rate, the average speed deviation, and the number of braking triggers. The speed qualification rate is determined based on the ratio of the number of abnormal trajectory points to the number of valid trajectory points. The average speed deviation is determined based on the difference between the speed of each valid trajectory point and the preset reference speed. The number of braking triggers is determined based on the number of rising edges of the stop marker.

[0012] In an optional implementation, the trajectory point sequence includes the latitude and longitude of the vehicle at each trajectory point. The step of determining the shortest distance between each trajectory point in the trajectory point sequence and all target road segment endpoints includes: for each trajectory point, converting the latitude and longitude of the trajectory point into radians, and using the spherical distance formula based on the radians to determine the ground distance between the trajectory point and each target road segment endpoint; and selecting the minimum value from all ground distances as the shortest distance of the trajectory point.

[0013] Secondly, embodiments of this application also provide a vehicle speed compliance detection device, the device comprising: The sequence generation module is used to collect vehicle trajectory information and generate a sequence of trajectory points based on the vehicle trajectory information. The trajectory point filtering module is used to determine the shortest distance between each trajectory point in the trajectory point sequence and all target road segment endpoints. Based on the shortest distance and multiple preset constraints, candidate trajectory points that represent vehicles entering and exiting the target road segments are filtered from all trajectory points. The candidate trajectory points include different traffic types. The interval generation module is used to determine the entry and exit index of the target road segment based on the traffic type of the candidate trajectory points, and generate the trajectory point interval representing the vehicle passing through the target road segment. The interval elimination module is used to eliminate the transition segments between the beginning and end of the trajectory point interval to obtain the core interval, and to construct a set of valid trajectory points based on the valid trajectory points within the core interval. The compliance determination module is used to determine the speed compliance of each valid trajectory point and mark the valid trajectory points that do not meet the speed compliance requirements as having abnormal speeds.

[0014] Thirdly, embodiments of this application also provide an electronic device, including: a processor, a memory, and a bus. The memory stores machine-readable instructions executable by the processor. When the electronic device is running, the processor communicates with the memory via the bus. When the machine-readable instructions are executed by the processor, the steps of the vehicle speed compliance detection method described above are performed.

[0015] The embodiments of this application bring the following beneficial effects: This application provides a vehicle speed compliance detection method, device, and electronic device. It can filter candidate trajectory points and generate trajectory point intervals by using the nearest distance between trajectory points and road segment endpoints, as well as multiple preset constraints. This accurately locates the effective interval for a vehicle to pass through a target road segment, reducing positioning drift and road segment misjudgment, and improving road segment recognition stability. Simultaneously, by eliminating transition sections before and after the target road segment, it significantly improves the accuracy and reliability of vehicle speed compliance detection results. The overall solution does not rely on high-precision maps, has high computational efficiency, and is suitable for automated and standardized vehicle speed detection needs in closed test tracks and multi-road-segment dense scenarios. Compared with existing vehicle speed compliance detection methods, it solves the problems of unstable road segment interval recognition, susceptibility to interference from boundary transition sections, high dependence on high-precision maps, and low batch processing efficiency.

[0016] To make the above-mentioned objectives, features and advantages of this application more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description

[0017] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 A flowchart of the vehicle speed compliance detection method provided in this application embodiment is shown; Figure 2 A flowchart of the candidate trajectory point filtering steps provided in the embodiments of this application is shown; Figure 3 A schematic diagram of the vehicle speed compliance detection device provided in an embodiment of this application is shown; Figure 4 A schematic diagram of the structure of the electronic device provided in the embodiments of this application is shown. Detailed Implementation

[0019] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. The components of the embodiments of this application described and shown in the accompanying drawings can generally be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of this application provided in the accompanying drawings is not intended to limit the scope of the claimed application, but merely represents selected embodiments of this application. Based on the embodiments of this application, every other embodiment obtained by those skilled in the art without inventive effort falls within the scope of protection of this application.

[0020] To facilitate understanding of this embodiment, the following description uses the vehicle speed compliance detection method provided in this application embodiment applied to a terminal device as an example to illustrate the above exemplary steps provided in this application embodiment.

[0021] Please see Figure 1 , Figure 1 This is a flowchart illustrating a vehicle speed compliance detection method provided in an embodiment of this application. Figure 1 As shown in the embodiments of this application, the vehicle speed compliance detection method includes: Step S101: Collect vehicle trajectory information and generate a trajectory point sequence based on the vehicle trajectory information.

[0022] The vehicle can refer to the vehicle to be inspected, which is equipped with data acquisition equipment. The data acquisition equipment includes at least a positioning acquisition module, a vehicle speed acquisition module, and a storage module.

[0023] The positioning acquisition module is used to output GPS (Global Positioning System) longitude and GPS latitude, the vehicle speed acquisition module is used to output vehicle speed signals, and the storage module is used to collect and store time-series data according to a fixed sampling period.

[0024] During the operation of the vehicle in the test track, closed park or road test section, the data acquisition equipment continuously collects the vehicle's running trajectory information at fixed intervals. The vehicle running trajectory information includes latitude and longitude and vehicle speed. Based on the vehicle running trajectory information, a trajectory point sequence is generated. The trajectory point sequence includes the timestamp, latitude, and vehicle speed information of each trajectory point.

[0025] In one embodiment, a parking marker can be set for each trajectory point based on the vehicle speed at that point. The parking marker uses a zero-speed criterion: if the vehicle speed is 0, the parking marker for that trajectory point is set to 1; if the vehicle speed is not 0, the parking marker for that trajectory point is set to 0.

[0026] At the same time, the road information of all target road segments is read from the preset test road segment parameter configuration file. The road information of each target road segment includes the starting latitude and longitude, ending latitude and longitude, effective length, preset reference speed, and allowable deviation. The allowable deviation includes allowable upper deviation and allowable lower deviation.

[0027] It should be noted that in the speed compliance test, the vehicle needs to pass through all target road segments in multiple cycles. Each time the vehicle passes through all target road segments, it completes one cycle. Subsequent steps can be performed after each cycle based on the trajectory point sequence of that cycle, or after the vehicle completes all cycles based on the trajectory point sequence of all cycles.

[0028] The following example illustrates how subsequent steps are executed based on the trajectory point sequence of the current cycle after each vehicle cycle.

[0029] Step S102: Determine the shortest distance between each trajectory point in the trajectory point sequence and all target road segment endpoints, and select candidate trajectory points representing vehicle entry and exit from all trajectory points based on the shortest distance and multiple preset constraints.

[0030] When determining the shortest distance, for each trajectory point, the latitude and longitude of the trajectory point are converted into radians, and the surface distance between the trajectory point and the endpoint of each target road segment is determined using the spherical distance formula based on the radians; the minimum value among all surface distances is selected as the shortest distance of the trajectory point.

[0031] For example, to convert the latitude and longitude of all trajectory points from angle values ​​to radian values, the conversion formula is: , ;in, In latitude radians, In longitude in radians, This is the latitude angle value. This is the longitude angle value.

[0032] At any trajectory point ( , ) and any target road segment endpoint ( , When calculating the surface distance d between two points, the Havelsing spherical distance formula can be used: , , , , , where R represents the Earth's radius.

[0033] There is at least one target road segment. When there are multiple target road segments, each trajectory point corresponds to multiple surface distances. The surface distance with the smallest value among all calculated surface distances is selected as the nearest distance for that trajectory point. The endpoints of a target road segment include a start point and an end point. The surface distance between each trajectory point and an endpoint of a target road segment includes the surface distance from the trajectory point to the start point of the target road segment and the surface distance from the trajectory point to the end point of the target road segment.

[0034] In one embodiment, when calculating the ground distance, a vectorized batch calculation method can be used for the entire trajectory point sequence, that is, the ground distance calculation from all trajectory points to the endpoint of the same target road segment can be completed at one time to reduce the overhead of repeated loops.

[0035] Multiple preset constraints include proximity constraints, auxiliary geometric constraints, and distance trend constraints.

[0036] The proximity constraint is used to ensure that trajectory points are matched with the nearest road segment endpoints, thereby suppressing mismatches and misjudgments caused by adjacent road segments, dense road segments, and intersections, and ensuring the uniqueness and accuracy of road segment attribution judgments.

[0037] Auxiliary geometric constraints are used to reliably trigger road segment entry or exit events even in abnormal scenarios such as GPS drift, sparse sampling points, lost trajectory points, and vehicles not passing through road segment endpoints, thus avoiding missed or incorrect judgments and improving the robustness of the entire interval recognition.

[0038] Distance trend constraints are used to accurately determine the direction (entry / exit) of vehicles passing through the endpoints of road segments, and to suppress repeated triggering caused by positioning jitter and repeated detours, so as to ensure the temporal correctness and uniqueness of interval identification.

[0039] The following reference Figure 2 This section will introduce the process of selecting candidate trajectory points.

[0040] Figure 2 A flowchart of the candidate trajectory point filtering steps provided in the embodiments of this application is shown, as follows: Figure 2 As shown, the candidate trajectory point filtering steps include: Step S1021: The trajectory point whose closest distance meets the entry / exit range requirements is determined as the initial candidate trajectory point.

[0041] Traverse each trajectory point in the sequence of trajectory points in chronological order, and perform preliminary screening by using a distance threshold to determine the initial candidate trajectory points.

[0042] For example, the nearest distance to the kth trajectory point is denoted as: The distance threshold is denoted as: ,like This indicates that the trajectory point is near the end of the road segment and can be used as a candidate trajectory point to represent entering or leaving the target road segment; therefore, this trajectory point is determined as the initial candidate trajectory point. If the trajectory point is not an initial candidate trajectory point, it will not proceed to the subsequent processing flow. For example, It can be 14 meters or 16 meters, which can be set according to the actual situation by those skilled in the art.

[0043] Step S1022: Initial candidate trajectory points that simultaneously satisfy multiple preset constraints are determined as the final candidate trajectory points for the target road segment.

[0044] For each initial candidate trajectory point, determine whether the initial candidate trajectory point simultaneously satisfies multiple preset constraints. If it simultaneously satisfies multiple preset constraints, then the initial candidate trajectory point is determined as a candidate trajectory point.

[0045] In one embodiment, when determining whether the nearest constraint condition is met, it can be based on the difference between the endpoint distance and the nearest distance between the initial candidate trajectory point and the endpoint of the target road segment.

[0046] For example, the endpoint distance between the initial candidate trajectory point and the endpoint of the target road segment is denoted as: The preset difference threshold is denoted as: ,like If, then the nearest-to-the-time constraint is satisfied; if If so, then the nearest-to-the-time constraint is not satisfied.

[0047] In one embodiment, the determination of whether the auxiliary geometric constraints are met can be based on a comparison between the endpoint distance and the effective length of the target road segment.

[0048] For example: the effective length of the target road segment is denoted as L, the scaling factor is denoted as α, and the distance from the initial candidate trajectory point to the end point of the target road segment is denoted as: The distance from the initial candidate trajectory point to the starting point of the target road segment is denoted as: .like or If the initial candidate trajectory point has entered or exceeded the geometric coverage of the target road segment, it can be used as an auxiliary criterion for entering or leaving the road segment. If so, the auxiliary geometric constraint condition is satisfied; otherwise, it is determined that the auxiliary geometric constraint condition is not satisfied. The auxiliary geometric constraint condition is used to compensate for anomalies such as GPS drift, sparse sampling points, and trajectory loss, and to avoid missed or incorrect judgments.

[0049] In one embodiment, when determining whether the distance trend constraint is satisfied, it can be based on the comparison result between the endpoint distance and the endpoint distance between the next initial candidate trajectory point and the endpoint of the target road segment.

[0050] For example, the monotonicity of distance can be used to determine the direction in which a vehicle passes through the endpoint of a road segment. The distance trend constraints include an entry trend criterion and a departure trend criterion. The entry trend criterion is as follows: The criterion for leaving the trend is: If an initial candidate trajectory point satisfies the trend entry criterion or the trend exit criterion, then the initial candidate trajectory point is determined to satisfy the trend constraint condition; otherwise, the initial candidate trajectory point is determined not to satisfy the trend constraint condition.

[0051] When an initial candidate trajectory point simultaneously satisfies the nearest constraint, the auxiliary geometric constraint, and the distance trend constraint, the initial candidate trajectory point is determined as the final candidate trajectory point.

[0052] In one embodiment, the candidate trajectory points include candidate trajectory points of different traffic types. The different traffic types include a first type representing a vehicle entering the target road segment and a second type representing a vehicle leaving the target road segment. The candidate trajectory points of the first type are called first trajectory points, and the candidate trajectory points of the second type are called second trajectory points. The first trajectory points are candidate trajectory points that satisfy the entry trend criterion, and the second trajectory points are candidate trajectory points that satisfy the departure trend criterion.

[0053] Step S103: Determine the entry and exit index of the target road segment based on the traffic type of the candidate trajectory points, and generate the trajectory point interval representing the vehicle passing through the target road segment.

[0054] For each target road segment, the sequence number of the first trajectory point corresponding to the target road segment is recorded as the entry index, and the sequence number of the second trajectory point corresponding to the target road segment is recorded as the exit index.

[0055] If the candidate trajectory point's sequence number is recorded as an entry index, it indicates that the vehicle begins entering the target road segment at that candidate trajectory point; if the candidate trajectory point's sequence number is recorded as a exit index, it indicates that the vehicle completely exits the target road segment at that candidate trajectory point. The entry index of target road segment j is denoted as: Leaving the index is denoted as: .

[0056] In one embodiment, a state latching mechanism can be used to prevent consecutive candidate trajectory points from being recorded repeatedly, so that the same passage behavior corresponds to a set of entry and exit indices.

[0057] For example, there are ten target road segments. A vehicle will cycle through these ten target road segments multiple times. In the current cycle, the vehicle passes through these ten target road segments in sequence, and in the next cycle, the vehicle will pass through these ten target road segments again in sequence. In this cycle, if it is determined that a vehicle has entered a target road segment, a state lock is set for that target road segment. The state lock is only released after it is detected that the vehicle has left the target road segment, thereby generating a set of entry and exit indices corresponding to that target road segment.

[0058] By using the entry and exit indices of the target road segment, a trajectory point range representing the complete passage of a vehicle through the target road segment is generated. , If the number of times the vehicle passes through the target road segment is 6, then each target road segment corresponds to 6 sets of trajectory point intervals.

[0059] In one embodiment, in order to exclude abnormal trajectory point intervals caused by vehicles staying for a long time, taking detours, or data anomalies, the vehicle travel time can be determined based on the time of the first trajectory point and the time of the second trajectory point, and the travel time can be verified to eliminate abnormal trajectory point intervals.

[0060] For example, the time of the first trajectory point is denoted as: The time of the second trajectory point is denoted as: The travel time is The passage duration will be [not specified]. If the travel time is greater than the preset time limit, the trajectory point interval is determined to be an abnormal trajectory point interval and removed; if the travel time is less than or equal to the preset time limit, the trajectory point interval is determined to be a normal trajectory point interval.

[0061] Step S104: Remove the transition segments between the beginning and end of the trajectory point interval to obtain the core interval, and construct a set of valid trajectory points based on the valid trajectory points within the core interval.

[0062] To reduce interference from acceleration / deceleration and positioning drift during the entry / exit phases, the transition segments before and after the trajectory point interval can be removed according to a preset ratio, retaining only the core interval.

[0063] In one embodiment, for a normal trajectory point interval j, the number of trajectory points between the first trajectory point and the second trajectory point in the interval is first determined. This involves determining the number of sampling points within the trajectory point interval. Then, based on the number of trajectory points and a preset ratio, the number of trajectory points in the first transition segment before the preceding transition segment and the number of trajectory points in the second transition segment before the following transition segment are determined. The trajectory point located at the number of trajectory points in the first transition segment after the first trajectory point is determined as the first core trajectory point of the core interval, and the trajectory point located at the number of trajectory points in the second transition segment after the first trajectory point is determined as the second core trajectory point of the core interval.

[0064] For example: if the preset ratio is denoted as β, then the number of trajectory points in the first transition segment is β × The number of trajectory points in the second transition segment is The first core trajectory point for Second core trajectory point for The core interval is [ ].

[0065] like Then [ The trajectory points within the range are taken as the valid trajectory points of the target road segment. The valid trajectory points under the current detection are used to update the existing set of valid trajectory points under the target road segment, thereby obtaining all the valid trajectory points corresponding to multiple trajectory point intervals under different cyclic detection to form the set of valid trajectory points. It should be noted that when there are multiple target road segments, steps S102 to S104 are executed for each target road segment to update the set of valid trajectory points for that target road segment in real time after each loop through the target road segment. For example, if the target road segment is detected nine times in total, the set of valid trajectory points includes the valid trajectory points corresponding to each of the nine trajectory point intervals.

[0066] Step S105: Determine the speed compliance of each valid trajectory point, and mark the valid trajectory points that do not meet the speed compliance as having abnormal speeds.

[0067] For each valid trajectory point in the set of valid trajectory points corresponding to each target road segment, the vehicle speed of each valid trajectory point is checked for compliance based on the preset reference speed and the preset allowable deviation using a two-sided tolerance criterion method. For valid trajectory points that do not meet the speed compliance requirements, an abnormal speed mark is set.

[0068] For example, the vehicle speed at point k on the valid trajectory is denoted as: The preset reference speed is recorded as: The allowable upper deviation is denoted as: The allowable deviation is denoted as: ,like or If the speed does not meet the compliance requirement, the abnormal speed mark for that valid trajectory point is set to 1; otherwise, if the speed meets the compliance requirement, the abnormal speed mark for that valid trajectory point is set to 0. Simultaneously, a correlation is established between that valid trajectory point and the road segment name and speed limit rules of the target road segment to ensure the traceability of the trajectory data.

[0069] In one embodiment, to facilitate the analysis of vehicle speed, the effective number of entries into the target road segment, the speed qualification rate, the average speed deviation, and the number of braking triggers can also be statistically analyzed.

[0070] Among them, the speed qualification rate is determined based on the ratio of the number of abnormal trajectory points to the number of valid trajectory points; the average speed deviation is determined based on the difference between the speed of each valid trajectory point and the preset reference speed, which is used to reflect the overall trend of speeding or underspeeding; the number of braking triggers is determined based on the number of rising edges of the stop mark.

[0071] When determining the number of valid entries, the number of cycles of the vehicle speed compliance check can be used as the number of valid entries.

[0072] When determining the speed compliance rate, the number of abnormal trajectory points is the difference between the number of trajectory points in all trajectory point intervals corresponding to the target road segment and the number of valid trajectory points in the set of valid trajectory points. The number of valid trajectory points is denoted as: The number of abnormal trajectory points is denoted as: Then the speed pass rate Q is If the preset reference speed for the target road segment is zero or not set, then the target road segment will not be included in the speed compliance rate statistics.

[0073] Determining the average deviation of vehicle speed When the time is right, the calculation formula is: .

[0074] When determining the number of braking triggers, the rising edge of the parking marker is used for counting; that is, a trigger is recorded when the marker changes from 0 to 1. Let the parking marker sequence be... The number of triggers for: ; In the above formula, This is an indicator function; it takes the value 1 when the condition is true, and 0 otherwise.

[0075] In one embodiment, the road segment-level quota statistics results can be output as a structured table, which includes road segment name, number of cycles, speed compliance rate, average deviation, number of braking triggers, etc. Simultaneously, trajectory point-level result verification data is output, retaining the corresponding time, latitude and longitude, vehicle speed, road segment, speed limit rule, and abnormal speed marker for each valid trajectory point. Rows containing abnormal trajectory points are highlighted to facilitate manual spot checks.

[0076] In addition, it can further generate a visual curve of vehicle speed changing over time and display abnormal speed points in different colors, so that the road segment-level statistical results can be traced back to the corresponding original trajectory points, and the specific time and spatial location of the abnormal speed can be located and verified.

[0077] The vehicle speed compliance detection method provided in this application has the following beneficial effects: First, through the combined effect of multiple conditions such as multi-point distance matching, proximity constraint, auxiliary geometric constraint and distance trend constraint, the system can accurately identify the location of vehicles entering and leaving road segments in scenarios with dense distribution of multiple road segments, cyclical vehicle traffic and GPS positioning drift, avoiding interference from adjacent road segments, false triggering and missed judgment, and significantly improving the reliability of interval identification.

[0078] Secondly, by proportionally removing the transition sections before and after the trajectory point intervals and retaining only the core intervals for stable driving in the middle, the influence of boundary noise such as acceleration at the starting point, deceleration at the end point, and positioning fluctuations is effectively reduced, making the vehicle speed compliance statistics closer to the real driving state, and the evaluation results more stable and repeatable.

[0079] Third, the entire process is based solely on the spherical distance between the trajectory point and the endpoint of the road segment to achieve road segment positioning. It does not require high-precision maps, road networks, or road centerline data, and can be used normally in scenarios without map support, such as closed test sites, non-public roads, and temporary road segments, greatly improving its versatility and deployment flexibility.

[0080] Fourth, it adopts a vectorized batch distance calculation method, which can complete the matching of multiple road segments in a single traversal, avoiding repeated loop calculations for each road segment. It maintains high efficiency even under large-scale trajectory data and supports batch processing of multiple vehicles, multiple dates, and multiple tasks, as well as long-term stable operation.

[0081] Fifth, based on the two-sided tolerance criterion, the vehicle speed compliance is determined point by point, and each valid trajectory point is associated with the road segment name, speed limit rule and abnormal speed mark, forming a traceable structure of trajectory points, road segments and evaluation rules, which facilitates anomaly location, manual review and quality audit.

[0082] Sixth, it can automatically output multi-dimensional road segment-level statistical indicators such as cycle count, vehicle speed pass rate, average vehicle speed deviation, and number of parking / braking triggers, comprehensively reflecting the vehicle's driving compliance and stability, and meeting the needs of test monitoring, management evaluation, and data accumulation.

[0083] Based on the same inventive concept, this application also provides a vehicle speed compliance detection device corresponding to the vehicle speed compliance detection method. Since the principle of the device in this application is similar to the vehicle speed compliance detection method described above in this application, the implementation of the device can refer to the implementation of the method, and the repeated parts will not be described again.

[0084] Please see Figure 3 , Figure 3 This is a schematic diagram of the structure of a vehicle speed compliance detection device provided in an embodiment of this application. Figure 3 As shown, the vehicle speed compliance detection device 200 includes: The sequence generation module 201 is used to collect vehicle trajectory information and generate a sequence of trajectory points based on the vehicle trajectory information. The trajectory point filtering module 202 is used to determine the shortest distance between each trajectory point in the trajectory point sequence and all target road segment endpoints, and to filter candidate trajectory points representing vehicle entry and exit from all trajectory points based on the shortest distance and multiple preset constraints. The candidate trajectory points include different traffic types. The interval generation module 203 is used to determine the entry and exit index of the target road segment based on the traffic type of the candidate trajectory points, and generate the trajectory point interval representing the vehicle passing through the target road segment. The interval elimination module 204 is used to eliminate the transition segments between the beginning and end of the trajectory point interval to obtain the core interval, and to construct a set of valid trajectory points based on the valid trajectory points within the core interval. The compliance determination module 205 is used to determine the speed compliance of each valid trajectory point and mark the valid trajectory points that do not meet the speed compliance requirements as having abnormal speeds.

[0085] Please see Figure 4 , Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Figure 4 As shown, the electronic device 300 includes a processor 310, a memory 320, and a bus 330.

[0086] The memory 320 stores machine-readable instructions executable by the processor 310. When the electronic device 300 is running, the processor 310 and the memory 320 communicate via the bus 330. When the machine-readable instructions are executed by the processor 310, they can perform the operations described above. Figure 1 The steps of the vehicle speed compliance detection method in the illustrated method embodiment can be found in the method embodiment for specific implementation methods, which will not be repeated here.

[0087] This application also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, can perform the above-described actions. Figure 1 The steps of the vehicle speed compliance detection method in the illustrated method embodiment can be found in the method embodiment for specific implementation methods, which will not be repeated here.

[0088] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0089] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. The apparatus embodiments described above are merely illustrative. For example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. Furthermore, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Additionally, the shown or discussed mutual couplings, direct couplings, or communication connections may be through some communication interfaces; indirect couplings or communication connections between devices or units may be electrical, mechanical, or other forms.

[0090] 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.

[0091] In addition, the functional units in the various embodiments of this application 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.

[0092] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a processor-executable, non-volatile, computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion 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 described in the various embodiments of this application. 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.

[0093] Finally, it should be noted that the above-described embodiments are merely specific implementations of this application, used to illustrate the technical solutions of this application, and not to limit them. The scope of protection of this application is not limited thereto. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that any person skilled in the art can still modify or easily conceive of changes to the technical solutions described in the foregoing embodiments, or make equivalent substitutions for some of the technical features, within the scope of the technology disclosed in this application. Such modifications, changes, or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be covered within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A method for detecting vehicle speed compliance, characterized in that, include: Collect vehicle trajectory information and generate a trajectory point sequence based on the vehicle trajectory information; Determine the shortest distance between each trajectory point in the trajectory point sequence and all target road segment endpoints. Based on the shortest distance and multiple preset constraints, filter out candidate trajectory points that represent the vehicle's entry and exit from all trajectory points. The candidate trajectory points include different traffic types. Based on the traffic type of the candidate trajectory points, the entry and exit index of the target road segment is determined, and a trajectory point interval representing the vehicle passing through the target road segment is generated; The core interval is obtained by removing the transition segments between the beginning and end of the trajectory point interval, and a set of valid trajectory points is constructed based on the valid trajectory points within the core interval. Determine the speed compliance of each valid trajectory point, and mark the valid trajectory points that do not meet the speed compliance requirements as having abnormal speeds.

2. The method according to claim 1, characterized in that, The step of selecting candidate trajectory points representing the vehicle's entry and exit from the target road segment from all trajectory points based on the nearest distance and multiple preset constraints includes: The trajectory point whose closest distance meets the entry / exit range requirements is determined as the initial candidate trajectory point; Initial candidate trajectory points that simultaneously satisfy multiple preset constraints are determined as the final candidate trajectory points of the target road segment. The multiple preset constraints include proximity constraints, auxiliary geometric constraints, and distance trend constraints.

3. The method according to claim 2, characterized in that, Whether the initial candidate trajectory points simultaneously satisfy multiple preset constraints is determined by the following method: Based on the difference between the endpoint distance between the initial candidate trajectory point and the endpoint of the target road segment and the nearest distance, it is determined whether the nearest constraint condition is satisfied. Based on the comparison between the endpoint distance and the effective length of the target road segment, it is determined whether the auxiliary geometric constraint conditions are met. Based on the comparison between the endpoint distance and the endpoint distance between the next initial candidate trajectory point and the endpoint of the target road segment, it is determined whether the distance trend constraint condition is met.

4. The method according to claim 1, characterized in that, The trajectory point interval includes a first trajectory point representing the vehicle entering the target road segment and a second trajectory point representing the vehicle leaving the target road segment. The method further includes: The vehicle travel time is determined based on the time of the first trajectory point and the time of the second trajectory point; The passage time is verified to eliminate abnormal trajectory point intervals.

5. The method according to claim 4, characterized in that, The step of removing the transition segments before and after the trajectory point interval to obtain the core interval includes: Determine the number of trajectory points between the first trajectory point and the second trajectory point, and based on the number of trajectory points and a preset ratio, determine the number of trajectory points in the first transition segment before the previous transition segment and the number of trajectory points in the second transition segment before the subsequent transition segment. The trajectory point located at the number of trajectory points in the first transition segment after the first trajectory point is determined as the first core trajectory point of the core interval, and the trajectory point located at the number of trajectory points in the second transition segment after the first trajectory point is determined as the second core trajectory point of the core interval.

6. The method according to claim 1, characterized in that, The step of determining the speed compliance of each valid trajectory point and marking valid trajectory points that do not meet the speed compliance requirements as having abnormal speeds includes: Based on the preset reference speed and the preset allowable deviation, the speed of each valid trajectory point is verified for compliance using a two-sided tolerance criterion method. For valid trajectory points that do not meet the speed compliance requirements, an abnormal speed marker is set.

7. The method according to claim 1, characterized in that, The method further includes: The system counts the number of valid entries into the target road segment, as well as the speed qualification rate, average speed deviation, and number of braking triggers. The speed qualification rate is determined based on the ratio of the number of abnormal trajectory points to the number of valid trajectory points. The average speed deviation is determined based on the difference between the speed of each valid trajectory point and the preset reference speed. The number of braking triggers is determined based on the number of rising edges of the stop marker.

8. The method according to claim 1, characterized in that, The trajectory point sequence includes the latitude and longitude of the vehicle at each trajectory point. The step of determining the shortest distance between each trajectory point in the trajectory point sequence and all target road segment endpoints includes: For each trajectory point, the latitude and longitude of the trajectory point are converted into radians, and the surface distance between the trajectory point and the endpoint of each target road segment is determined using the spherical distance formula based on the radians. Select the minimum value from all surface distances as the nearest distance to the trajectory point.

9. A vehicle speed compliance detection device, characterized in that, include: The sequence generation module is used to collect vehicle trajectory information and generate a sequence of trajectory points based on the vehicle trajectory information. The trajectory point filtering module is used to determine the shortest distance between each trajectory point in the trajectory point sequence and all target road segment endpoints, and to filter candidate trajectory points representing the vehicle's entry and exit from all trajectory points based on the shortest distance and multiple preset constraints. The candidate trajectory points include different traffic types. The interval generation module is used to determine the entry and exit index of the target road segment based on the traffic type of the candidate trajectory points, and generate a trajectory point interval representing the vehicle passing through the target road segment; The interval elimination module is used to eliminate the transition segments between the beginning and end of the trajectory point interval to obtain the core interval, and to construct a set of valid trajectory points based on the valid trajectory points within the core interval. The compliance determination module is used to determine the speed compliance of each valid trajectory point and mark the valid trajectory points that do not meet the speed compliance requirements as having abnormal speeds.

10. An electronic device, characterized in that, include: The device includes a processor, a memory, and a bus. The memory stores machine-readable instructions executable by the processor. When the electronic device is running, the processor communicates with the memory via the bus, and the processor executes the machine-readable instructions to perform the steps of the vehicle speed compliance detection method as described in any one of claims 1 to 8.

Images