Nighttime on-street vehicle illegal parking identification method, device, equipment, medium and product

Abstract

The application discloses a kind of night road vehicle illegal parking identification method, device, equipment, medium and product.The method comprises: obtaining the vehicle driving track point of target vehicle under current monitoring time period, trajectory point screening is carried out to vehicle driving track point, and parking track point is obtained;According to the parking time stamp corresponding to each parking track point, at least one candidate parking segment of target vehicle is determined;According to the parking track point of each candidate parking segment, the target parking position and target parking time period corresponding to each candidate parking segment are determined;If at least one night parking segment is obtained according to the target parking time period corresponding to each candidate parking segment screening, then the night road illegal parking identification result of target vehicle is determined according to the target parking position corresponding to each night parking segment.The accuracy of the night road vehicle illegal parking identification of the embodiment technical scheme of the application is improved.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and in particular to a method, device, equipment, medium, and product for identifying illegally parked vehicles on the road at night. Background Technology

[0002] In the field of data processing technology, the accurate identification and information determination of illegal parking on roads at night is a core link in regulating road traffic order and improving traffic management efficiency. It is directly related to the smoothness of urban road traffic, the level of precision of traffic control, and the travel experience of citizens.

[0003] Current methods for identifying illegally parked vehicles at night largely rely on manual on-site enforcement or fixed camera captures. These methods lack comprehensive analysis of vehicle parking trajectories, leading to incomplete identification coverage and time-based judgment errors. This results in low efficiency and insufficient accuracy in identifying illegally parked vehicles at night, failing to provide efficient and reliable technical support for managing such violations. Therefore, there is an urgent need for a technical solution capable of accurately identifying illegally parked vehicles at night to address the low accuracy of traditional methods. Summary of the Invention

[0004] This invention provides a method, device, equipment, medium, and product for identifying illegally parked vehicles on the road at night, in order to improve the accuracy of identifying illegally parked vehicles on the road at night.

[0005] According to one aspect of the present invention, a method for identifying illegally parked vehicles on the road at night is provided, the method comprising:

[0006] Obtain the vehicle driving trajectory points of the target vehicle under the current monitoring time period, and filter the vehicle driving trajectory points to obtain parking trajectory points; wherein, the parking trajectory points include parking timestamp and parking location;

[0007] Based on the parking timestamps corresponding to each parking trajectory point, at least one candidate parking segment for the target vehicle is determined; the candidate parking segment contains at least two parking trajectory points.

[0008] Based on the parking trajectory points of each candidate parking segment, determine the target parking location and target parking time period corresponding to each candidate parking segment;

[0009] If at least one nighttime parking segment is obtained by filtering according to the target parking time period corresponding to each of the candidate parking segments, then the nighttime on-street illegal parking identification result of the target vehicle is determined according to the target parking location corresponding to each of the nighttime parking segments.

[0010] According to another aspect of the present invention, a nighttime on-street vehicle illegal parking detection device is provided, the device comprising:

[0011] The parking trajectory point acquisition module is used to acquire the vehicle driving trajectory points of the target vehicle under the current monitoring time period, and to filter the vehicle driving trajectory points to obtain parking trajectory points; wherein, the parking trajectory point includes a parking timestamp and a parking location;

[0012] The candidate parking segment determination module is used to determine at least one candidate parking segment of the target vehicle based on the parking timestamps corresponding to each of the parking trajectory points; the candidate parking segment contains at least two parking trajectory points;

[0013] The target parking information determination module is used to determine the target parking location and target parking time period corresponding to each candidate parking segment based on the parking trajectory points of each candidate parking segment.

[0014] The illegal parking identification result determination module is used to filter at least one nighttime parking segment based on the target parking time period corresponding to each of the candidate parking segments, and then determine the nighttime on-street illegal parking identification result of the target vehicle based on the target parking location corresponding to each of the nighttime parking segments.

[0015] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0016] At least one processor; and

[0017] A memory that is communicatively connected to at least one processor; wherein,

[0018] The memory stores a computer program that can be executed by at least one processor, such that the at least one processor is able to perform the nighttime on-street vehicle illegal parking identification method according to any embodiment of the present invention.

[0019] According to another aspect of the present invention, a computer-readable storage medium is provided, which stores computer instructions for causing a processor to execute and implement the nighttime on-street vehicle illegal parking identification method of any embodiment of the present invention.

[0020] According to another aspect of the present invention, a computer program product is provided, comprising a computer program that, when executed by a processor, implements the nighttime on-street vehicle illegal parking identification method of any embodiment of the present invention.

[0021] The technical solution of this invention obtains the vehicle trajectory points of the target vehicle during the current monitoring time period, filters these trajectory points to obtain parking trajectory points, and determines at least one candidate parking segment for the target vehicle based on the parking timestamps corresponding to each parking trajectory point. Based on the parking trajectory points of each candidate parking segment, the target parking location and target parking time period corresponding to each candidate parking segment are determined. If at least one nighttime parking segment is obtained by filtering the target parking time periods corresponding to each candidate parking segment, the nighttime on-street illegal parking identification result of the target vehicle is determined based on the target parking location corresponding to each nighttime parking segment. This method can sequentially complete the determination of candidate parking segments, target parking locations, and target parking time periods based on the parking timestamps of the parking trajectory points, achieving accurate identification of nighttime on-street illegal parking segments and information. It effectively solves the problems of incomplete coverage, judgment bias, and low efficiency in traditional nighttime on-street illegal parking identification methods, improving the accuracy and efficiency of nighttime on-street illegal parking identification in the field of intelligent transportation, and providing reliable technical support for the refined management of urban traffic illegal parking.

[0022] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0023] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0024] Figure 1 This is a flowchart of a method for identifying illegally parked vehicles on the road at night, according to Embodiment 1 of the present invention;

[0025] Figure 2 This is a flowchart of a method for identifying illegally parked vehicles on the road at night, according to Embodiment 2 of the present invention;

[0026] Figure 3 This is a flowchart of a method for identifying illegally parked vehicles on the road at night, according to Embodiment 3 of the present invention;

[0027] Figure 4 This is a schematic diagram of the structure of a nighttime on-street vehicle illegal parking identification device according to Embodiment 4 of the present invention;

[0028] Figure 5 This is a schematic diagram of the structure of an electronic device that implements a nighttime roadside vehicle illegal parking identification method according to an embodiment of the present invention. Detailed Implementation

[0029] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0030] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0031] Example 1

[0032] Figure 1 This is a flowchart of a nighttime on-street vehicle illegal parking identification method provided in Embodiment 1 of the present invention. This embodiment is applicable to the field of intelligent transportation and can be implemented by an organization monitoring vehicle illegal parking. It acquires monitoring data on roads and vehicles in real time or offline through the organization's server, thereby accurately identifying on-street vehicle illegal parking at night. This method can be executed by a nighttime on-street vehicle illegal parking identification device, which can be implemented in hardware and / or software. This nighttime on-street vehicle illegal parking identification device can be configured in the server of the organization monitoring vehicle illegal parking information. Figure 1 As shown, the method includes:

[0033] S101. Obtain the vehicle driving trajectory points of the target vehicle under the current monitoring time period, and filter the vehicle driving trajectory points to obtain the parking trajectory points. Among them, the parking trajectory points include the parking timestamp and the parking location.

[0034] S102. Based on the parking timestamps corresponding to each parking trajectory point, determine at least one candidate parking segment for the target vehicle. Each candidate parking segment contains at least two parking trajectory points.

[0035] S103. Based on the parking trajectory points of each candidate parking segment, determine the target parking location and target parking time period corresponding to each candidate parking segment.

[0036] S104. If at least one nighttime parking segment is obtained by filtering according to the target parking time period corresponding to each candidate parking segment, the nighttime on-street illegal parking identification result of the target vehicle is determined according to the target parking location corresponding to each nighttime parking segment.

[0037] The current monitoring time period can be a pre-set time period for monitoring the target vehicle, such as one day or half a day, as defined by relevant technical personnel. The target vehicle can be any vehicle monitored on the pre-defined detection section within the current monitoring time period, and its license plate can be used as a unique identifier. The vehicle's travel trajectory point can be the Global Navigation Satellite System (GNSS) positioning trajectory point generated by the target vehicle within the monitoring period, representing the spatial and temporal record of the target vehicle's location. The parking trajectory point can be a trajectory point used to determine the current status of the vehicle's travel trajectory point, filtered from the vehicle's travel trajectory points. The parking timestamp can be the GNSS positioning time corresponding to the parking trajectory point. The parking location can be the longitude and latitude of the target vehicle corresponding to the parking trajectory point, representing the spatial coordinate information of the vehicle's location.

[0038] For example, GNSS positioning trajectory points of the target vehicle within the past 30 days can be obtained as parking trajectory points. These parking trajectory points include the specific time of each vehicle positioning, as well as the corresponding longitude and latitude coordinates. For instance, GNSS trajectory points of a vehicle with license plate number 53246 within the past 30 days can be obtained. One trajectory point has a parking timestamp of 2020-10-12 22:00:00, a parking longitude of 129.3456, a parking latitude of 30.2434, and a speed of 50 km / h.

[0039] Furthermore, in order to eliminate invalid trajectory data, reduce computational overhead, and improve the effectiveness of parking trajectory points, in an optional embodiment, trajectory point filtering is performed on vehicle driving trajectory points to obtain parking trajectory points, including:

[0040] Based on the instantaneous speed of the vehicle and the parking timestamp in the vehicle's driving trajectory points, the data of the vehicle's driving trajectory points is cleaned to obtain cleaned vehicle driving trajectory points. Based on the instantaneous speed of the vehicle in the cleaned vehicle driving trajectory points, the parking trajectory points are determined.

[0041] The instantaneous vehicle speed can be the speed of the target vehicle at the current parking trajectory point stored in the parking trajectory points. The cleaned vehicle driving trajectory points can be the vehicle driving trajectory points obtained after data cleaning.

[0042] For example, firstly, the positional changes of all target vehicle trajectory points are statistically analyzed. If the number of duplicate longitudes or latitudes is less than or equal to 1, and the vehicle speeds corresponding to all trajectory points are concentrated between 0-1 km / h, then these are considered invalid data and directly removed. Secondly, parking trajectory points with empty parking timestamps, parking latitude and longitude, and other key fields are removed. Finally, the filtered parking trajectory points are sorted in ascending order according to the parking timestamp to obtain the cleaned parking trajectory points. For example, if the target vehicle has 4 trajectory points: trajectory point a has a longitude of 154.1 and a speed of 0.2 km / h, trajectory point b has a longitude of 154.1 and a speed of 0.3 km / h, trajectory point c has a longitude of 154.1 and a speed of 0.1 km / h, and trajectory point d has a longitude of 154.1 and a speed of 0.2 km / h, after deduplication, all four have a longitude of 154.1, and the vehicle speeds are concentrated between 0-1 km / h. Therefore, these 4 trajectory points are considered invalid data and need to be cleaned to obtain the final parking trajectory points.

[0043] The above technical solution obtains parking trajectory points by filtering invalid data, validating key fields, and sorting them in time sequence from the original driving trajectory points, which can effectively improve the accuracy and computational efficiency of subsequent parking behavior recognition.

[0044] Among them, the candidate parking segment can be a set of trajectories consisting of multiple consecutive parking trajectory points, representing a vehicle's continuous parking behavior.

[0045] For example, a candidate parking segment may contain dozens to hundreds of consecutive parking trajectory points to represent a complete parking process of the target vehicle.

[0046] Furthermore, to eliminate false candidate parking segments caused by short-term stops such as waiting at red lights, temporary loading / unloading, and traffic congestion, and to ensure that the candidate parking segments represent actual long-term parking behavior, after the initial grouping of candidate parking segments, a time-constrained screening of parking duration can be performed. This method also includes:

[0047] The duration of each candidate parking segment after initial grouping is calculated. The duration is the difference between the parking timestamp of the first parking trajectory point and the parking timestamp of the last parking trajectory point in the candidate parking segment. The preset parking duration constraint threshold is a time threshold set by relevant technical personnel according to actual needs. If the duration of a candidate parking segment is less than the parking duration constraint threshold, it is determined to be an invalid pseudo parking segment and is removed. Only candidate parking segments with a duration greater than the threshold are retained.

[0048] For example, if the preset parking duration constraint threshold is set to 5 minutes, and the duration of a candidate parking segment is 3 minutes, which is less than the preset threshold, it is determined to be a false parking segment generated by waiting at a red light and is removed. If the duration of another candidate parking segment is 20 minutes, which is greater than the preset threshold, it is determined to be a valid candidate parking segment, and then subsequent spatial constraint screening can continue.

[0049] Furthermore, in order to eliminate parking trajectory segments caused by vehicle movement and improve the spatial accuracy of parking behavior determination, after determining candidate parking segments, in an optional embodiment, the method further includes:

[0050] Calculate the longitude range and latitude range of all parking trajectory points within each candidate parking segment. The longitude range is the difference between the maximum and minimum parking longitude within the segment, and the latitude range is the difference between the maximum and minimum parking latitude within the segment. If both the longitude and latitude ranges of a candidate parking segment are less than or equal to the parking space constraint thresholds preset by relevant technical personnel based on actual needs, the candidate parking segment is considered a valid parking segment and can be retained. If any range exceeds the threshold, it is determined to be an invalid candidate parking segment and is removed.

[0051] For example, if the preset parking space constraint threshold is 20 meters, and the longitude range of candidate parking segment A is 12 meters and the latitude range is 8 meters, both of which are less than the threshold, it is determined to be a valid candidate parking segment. If the longitude range of candidate parking segment B is 25 meters, which exceeds the threshold of 20 meters, the segment is directly eliminated.

[0052] Furthermore, to clarify the grouping criteria for parking trajectory points and achieve accurate segmentation of candidate parking segments, in one optional embodiment, at least one candidate parking segment of the target vehicle is determined based on the parking timestamp corresponding to each parking trajectory point, including:

[0053] Step a1: Based on the parking timestamps corresponding to each parking trajectory point, determine at least one adjacent trajectory point; an adjacent trajectory point is two parking trajectory points whose parking timestamps are adjacent.

[0054] Step a2: For any adjacent trajectory point, determine the difference in parking timestamps between the two parking trajectory points in that adjacent trajectory point.

[0055] Step a3: If the difference in parking timestamps is not greater than the preset parking timestamp threshold, and there is a candidate parking segment that includes any parking trajectory point among the adjacent trajectory points, then add the parking trajectory points among the adjacent trajectory points that are not included in the candidate parking segment to the candidate parking segment.

[0056] Step a4: If the difference in parking timestamps is greater than the preset parking timestamp threshold, and there is a candidate parking segment that includes any parking trajectory point among the adjacent trajectory points, then create a new candidate parking segment and add the parking trajectory points among the adjacent trajectory points that are not included in the candidate parking segment to the newly created candidate parking segment.

[0057] Among them, adjacent trajectory points can be obtained by sorting all parking trajectory points according to their timestamps.

[0058] For example, if the cleaned and sorted trajectory points are denoted as P1, P2, and P3 respectively, then (P1, P2) and (P2, P3) are adjacent trajectory points.

[0059] The parking timestamp difference can be the time difference between the parking timestamp of the second trajectory point and the parking timestamp of the first trajectory point in an adjacent trajectory point.

[0060] For example, if the parking timestamp of the first trajectory point is 22:46:00 and the parking timestamp of the second trajectory point is 22:46:30, the difference between the parking timestamps of the two trajectory points is 30 seconds. If the timestamp of the first trajectory point is 22:47:00 and the timestamp of the second trajectory point is 22:48:00, then the difference between the parking timestamps is 60 seconds.

[0061] Among them, the parking timestamp threshold can be the maximum time interval for determining whether a vehicle is continuously parked, which can be preset by relevant technical personnel according to actual needs.

[0062] For example, if the parking timestamp threshold is set to 60 seconds, and the difference between the parking timestamps of two adjacent parking trajectory points is less than or equal to 60 seconds, then they are considered as the same consecutive parking, that is, the same candidate parking segment. Parking trajectory points that are not included in the candidate parking segment are added to the candidate parking segment.

[0063] For example, if the parking timestamp threshold is set to 60 seconds and the time difference between two adjacent parking trajectory points exceeds 60 seconds, it is considered that the vehicle has left or the data is interrupted. In this case, the two adjacent parking trajectory points belong to different candidate parking segments. The latter point is then used as the starting point of the new candidate parking segment, that is, the parking trajectory points that are not included in the candidate parking segment are added to the newly created candidate parking segment.

[0064] The above technical solution achieves accurate grouping of continuous parking behavior by judging the adjacency of parking trajectory points and calculating the time difference based on the parking timestamp, combined with the preset parking timestamp threshold. It can effectively avoid the missplitting and merging of parking segments caused by abnormal data intervals, improve the rationality and stability of candidate parking segment division, and provide an accurate data foundation for subsequent nighttime parking judgment and on-street illegal parking identification.

[0065] The target parking location can be the core latitude and longitude coordinates of the target vehicle that actually stays the longest within the candidate parking segment. The target parking time period can be the complete time interval from the start to the end of parking for the target vehicle in a candidate parking segment.

[0066] For example, the target parking location is obtained through a clustering anti-drift algorithm, and the target parking time period is determined by the timestamps of the beginning and end of the segment.

[0067] Furthermore, to accurately identify high-risk illegal parking behavior at night and improve the rationality of nighttime parking determination, in an optional embodiment, before determining the nighttime on-street illegal parking identification result of the target vehicle based on the target parking location corresponding to each nighttime parking segment, if at least one nighttime parking segment is obtained by filtering according to the target parking time period corresponding to each candidate parking segment, the method further includes:

[0068] Step b1: For any candidate parking segment, if it is determined that the candidate parking segment has a corresponding nighttime parking period based on the target parking time period and the preset nighttime parking time period, then determine the nighttime parking percentage based on the nighttime parking time period and the target parking time period.

[0069] Step b2: If the proportion of nighttime parking is greater than the preset nighttime parking proportion threshold, then the candidate parking segment is determined to be a nighttime parking segment.

[0070] The preset nighttime parking period can be a high-risk period for nighttime illegal parking control pre-set by relevant technical personnel according to actual needs, such as the period from night to early morning of the next day. The nighttime parking period can be the overlapping time interval between the parking period of the candidate parking segment and the preset nighttime parking period. The nighttime parking percentage can be the ratio of the length of the nighttime parking period of the candidate parking segment to the length of the parking period of the candidate parking segment.

[0071] For example, when calculating the proportion of nighttime parking, it is necessary to accurately calculate the actual duration of the nighttime parking period and the parking period of the candidate parking segment separately. For parking behaviors that span multiple calendar days, the time intervals need to be broken down by day before the total duration is calculated to ensure that the duration calculation is accurate. For instance, if the nighttime parking period of the candidate parking segment corresponds to 22:00:00 on October 12, 2025 to 08:00:00 on October 13, 2025, with a nighttime parking duration of 10 hours; and if the target parking period of the candidate parking segment is 22:00:00 on October 12, 2025 to 10:00:00 on October 13, 2025, with a duration of 11 hours, then the nighttime parking proportion of this candidate parking segment is 10 / 11 = 83.3%.

[0072] The nighttime parking percentage threshold can be a pre-set critical value for the nighttime parking percentage by relevant technical personnel based on actual needs. A nighttime parking segment can be a parking segment where the nighttime parking percentage exceeds the threshold.

[0073] For example, if the relevant technical personnel set the preset nighttime parking determination threshold to 80%, and the parking time period of a certain candidate parking segment is from 21:00:00 on October 12, 2023 to 07:00:00 on October 13, 2023, with a total duration of 10 hours, and this overlaps with the preset nighttime parking time period from 19:00 on the same day to 08:00 on the next day, the nighttime parking time period obtained is from 21:00:00 on October 12, 2023 to 07:00:00 on October 13, 2023, with a duration of 9 hours, the calculated nighttime parking ratio is 90%, which is greater than the preset nighttime parking determination threshold of 80%. Therefore, the candidate parking segment is determined to be a nighttime parking segment.

[0074] The above technical solution obtains the overlapping nighttime parking time periods by comparing the target parking time period with the preset nighttime parking time period, and then calculates the nighttime parking proportion by the ratio of the duration of the two time intervals. Combined with the preset nighttime parking judgment threshold, the nighttime parking segment is judged. This avoids the one-sidedness of simply judging based on a single time range, effectively excludes non-illegal parking behaviors that stop briefly at night, and improves the scientificity and accuracy of nighttime parking segment judgment.

[0075] Among them, the nighttime on-street illegal parking identification results can be the final result including the target vehicle's license plate number, illegal parking time, illegal parking location, and illegal parking section.

[0076] For example, if the target parking location falls within a no-parking zone, it is determined to be illegal parking on the road at night, and complete illegal parking information is output.

[0077] The technical solution of this invention obtains the vehicle trajectory points of the target vehicle during the current monitoring time period, filters these trajectory points to obtain parking trajectory points, and determines at least one candidate parking segment for the target vehicle based on the parking timestamps corresponding to each parking trajectory point. Based on the parking trajectory points of each candidate parking segment, the target parking location and target parking time period corresponding to each candidate parking segment are determined. If at least one nighttime parking segment is obtained by filtering the target parking time periods corresponding to each candidate parking segment, the nighttime on-street illegal parking identification result of the target vehicle is determined based on the target parking location corresponding to each nighttime parking segment. This method can sequentially complete the determination of candidate parking segments, target parking locations, and target parking time periods based on the parking timestamps of the parking trajectory points, achieving accurate identification of nighttime on-street illegal parking segments and information. It effectively solves the problems of incomplete coverage, judgment bias, and low efficiency in traditional nighttime on-street illegal parking identification methods, improving the accuracy and efficiency of nighttime on-street illegal parking identification in the field of intelligent transportation, and providing reliable technical support for the refined management of urban traffic illegal parking.

[0078] Example 2

[0079] Figure 2 This is a flowchart of a nighttime on-street vehicle illegal parking identification method provided in Embodiment 2 of the present invention. This embodiment optimizes and improves upon the above-mentioned technical solutions. The step "determine the target parking location and target parking time period corresponding to each candidate parking segment based on the parking trajectory points of each candidate parking segment" is refined to "for any candidate parking segment, cluster the parking trajectory points contained in the candidate parking segment to obtain at least one parking trajectory point category; determine the target parking location based on the parking location and parking duration of each parking trajectory point in each category; determine the target parking time period corresponding to the candidate parking segment based on the parking timestamps corresponding to each parking trajectory point contained in the candidate parking segment." This improves the accuracy of determining the target parking location and target parking time period.

[0080] It should be noted that for parts not described in detail in the embodiments of the present invention, please refer to the descriptions in other embodiments. For example... Figure 2 As shown, the method includes the following specific steps:

[0081] S201. Obtain the vehicle driving trajectory points of the target vehicle under the current monitoring time period, filter the vehicle driving trajectory points to obtain the parking trajectory points; wherein, the parking trajectory points include the parking timestamp and the parking location.

[0082] S202. Based on the parking timestamps corresponding to each parking trajectory point, determine at least one candidate parking segment for the target vehicle; wherein, the candidate parking segment contains at least two parking trajectory points.

[0083] S203. For any candidate parking segment, cluster each parking trajectory point contained in the candidate parking segment to obtain at least one parking trajectory point category.

[0084] S204. Determine the target parking location based on the parking location and parking duration of each parking trajectory point in each parking trajectory point category.

[0085] S205. Determine the target parking time period corresponding to the candidate parking segment based on the parking timestamps corresponding to each parking trajectory point contained in the candidate parking segment.

[0086] S206. If at least one nighttime parking segment is obtained by filtering according to the target parking time period corresponding to each candidate parking segment, the nighttime on-street illegal parking identification result of the target vehicle is determined according to the target parking location corresponding to each nighttime parking segment.

[0087] The parking location of a parking trajectory point can be its latitude and longitude coordinates. The parking trajectory point category can be a set of trajectory points belonging to the same actual parking location, obtained by sliding clustering of parking trajectory points within a candidate parking segment according to a preset position drift tolerance. The position drift tolerance is a pre-set spatial distance threshold to resist random coordinate fluctuations of the GNSS positioning device when the vehicle is stationary. It is used to determine whether multiple trajectory points belong to the same actual parking location of the vehicle. Position changes within this spatial distance threshold range can be considered as device drift rather than actual vehicle movement.

[0088] For example, if the position drift tolerance is set to 10 meters, the starting parking trajectory point of the candidate parking segment is first selected as the clustering reference point. All subsequent parking trajectory points within the segment are traversed, and the straight-line distance between each trajectory point and the clustering reference point is calculated in turn. If the distance between a trajectory point and the clustering reference point is less than or equal to 10 meters, it is determined that the point belongs to the same parking trajectory point category as the reference point. If the distance is greater than 10 meters, it is determined that the vehicle has deviated from its actual position. The point with a distance greater than 10 meters is used as the new clustering reference point, a new parking trajectory point category is created, and the clustering of all trajectory points is completed. Finally, one or more parking trajectory point categories are obtained.

[0089] For example, the target parking location is determined based on the parking trajectory point categories. For each parking trajectory point category obtained from clustering, the timestamp difference between the earliest and latest parking trajectory points within that category is calculated as the dwell time corresponding to that category. All parking trajectory point categories are traversed, and the category with the longest dwell time is selected as the actual parking category for the vehicle. The arithmetic mean of the longitude and latitude of all parking trajectory points within that category is calculated to obtain the centroid latitude and longitude of that category, and this centroid latitude and longitude is determined as the target parking location for that candidate parking segment. For example, the dwell time corresponding to each category is calculated, and the category with the longest dwell time is selected, with the centroid latitude and longitude of all trajectory points within that category used as the target parking location. For example, if a segment is clustered into 3 categories with dwell times of 60 minutes, 240 minutes, and 30 minutes, the centroid latitude and longitude of the 240-minute category is selected as the target parking location.

[0090] For example, the target parking time period can be determined based on parking trajectory points. For instance, the trajectory point with the earliest timestamp among the candidate parking segments can be taken as the parking start time, and the trajectory point with the latest timestamp as the parking end time, forming a complete target parking time period. If the earliest time is 2025-10-12 22:00:00 and the latest time is 2025-10-13 06:00:00, then the target parking time period is from 2025-10-12 22:00:00 to 2025-10-13 06:00:00.

[0091] Furthermore, in order to accurately determine whether a nighttime parking segment constitutes illegal parking on the road and improve the accuracy of nighttime illegal parking identification, in an optional embodiment, the nighttime illegal parking identification result of the target vehicle is determined based on the target parking location corresponding to each nighttime parking segment, including:

[0092] Step c1: Obtain the road space information of the target vehicle's current environment.

[0093] Step c2: For any nighttime parking segment, generate a road space information matching result based on the target parking location and road space information corresponding to the nighttime parking segment.

[0094] Step c3: Based on the road space information matching results, determine the nighttime illegal parking identification results of the target vehicle.

[0095] Among them, the environmental road surface spatial information can be the spatial location information of various road sections and intersections in the city that relevant technical personnel have obtained in advance. The environmental road surface spatial information can accurately describe the spatial boundary between roads and non-road areas, and provide a spatial benchmark for judging illegal parking.

[0096] For example, when determining illegal parking, the target parking location corresponding to the nighttime parking segment is spatially superimposed and matched with the preset road space information, and the location attribution is determined by spatial calculation. The geographical area type in which the parking coordinate point falls is determined, clarifying whether the vehicle is parked within the road area, in a legal parking lot, or in other non-road areas, thereby distinguishing between legal parking and illegal parking on the road.

[0097] The road surface spatial information matching result can be determined by whether the final parking location's latitude and longitude for a nighttime parking segment falls within the preset road surface spatial information coordinate range. Specifically, this can include results such as the parking location being located in a no-parking zone, a legal parking zone, or a non-road area.

[0098] For example, the latitude and longitude of the target parking location corresponding to the nighttime parking segment (30.2434, 129.3456) are spatially matched with the preset road surface spatial information. After calculation, it is found that the coordinate point falls within the road segment coordinate range of Kaifa North Road in the road surface spatial information. Moreover, this road segment has been marked as a no-parking management section that prohibits temporary parking and long-term parking at night. It does not belong to a legal parking lot, service area, or area where parking is permitted. Therefore, it can be clearly determined that the target parking location is located in the no-parking zone on the road. That is, the road surface spatial information matching result is that the parking location is located in the no-parking zone on the road.

[0099] For example, if the final parking location of a nighttime parking segment is determined to be within an on-street area, the segment is identified as a nighttime on-street illegal parking segment. The following information is extracted: license plate number 53246, parking start time 2020-10-12 23:40:20, parking end time 2020-10-13 04:00:20, nighttime parking duration 260 minutes, parking latitude and longitude 30.2434, 129.3456, illegal parking road segment number 5479374, and illegal parking road segment name "Kaifa North Road." This information can be used together as the final identification result for this nighttime on-street illegal parking and can be used in subsequent statistical management of nighttime on-street illegal parking.

[0100] The above technical solution matches the final parking location of nighttime parking segments with road space information to obtain the road space information matching result, thus clarifying the judgment criteria and basis for illegal parking on the road. It can accurately distinguish parking behavior in no-parking areas and other compliant areas, effectively improving the accuracy of nighttime illegal parking identification and providing accurate data support for traffic control and illegal parking processing.

[0101] This embodiment's technical solution clusters parking trajectory points from candidate parking segments to obtain parking trajectory point categories, then determines the target parking location based on the dwell time of each parking trajectory point category. Simultaneously, it accurately defines the parking time period based on the parking trajectory points, abandoning the traditional, coarse method of determining location and time. This effectively resists positioning errors caused by GNSS static drift, avoids interference from single-point location deviations on the determination results, and accurately locks the vehicle's actual core parking location. This significantly improves the accuracy of determining the vehicle's parking location and time period, ensuring the accuracy and effectiveness of the entire process for determining vehicle illegal parking information on the road at night.

[0102] Example 3

[0103] Figure 3 This is a flowchart of a method for identifying illegally parked vehicles on the road at night, provided in Embodiment 3 of the present invention. Based on the above embodiments, this embodiment provides a preferred example. The method includes:

[0104] S301. Obtain the original GNSS positioning data of the target vehicle, and perform data cleaning and time-series sorting on the original GNSS positioning data to obtain the cleaned vehicle driving trajectory points.

[0105] S302. Based on the instantaneous speed of the vehicle's trajectory points after cleaning, select trajectory points whose instantaneous speed is less than or equal to the static state threshold and use them as parking trajectory points.

[0106] S303. Based on the positioning timestamps of each parking trajectory point, calculate the timestamp difference between two adjacent parking trajectory points to determine the adjacent trajectory points.

[0107] S304. Determine whether the timestamp difference between adjacent trajectory points is not greater than the preset parking timestamp threshold. If yes, execute S305; otherwise, execute S306.

[0108] S305. Group adjacent parking trajectory points into the same candidate parking segment.

[0109] S306. Create a new candidate parking segment, and add parking trajectory points that are not included in the candidate parking segment to the newly created candidate parking segment to obtain different candidate parking segments.

[0110] S307. For each candidate parking segment, calculate the parking duration and the latitude and longitude range of the location, and perform sliding clustering on the parking trajectory points according to the preset location drift tolerance to obtain at least one parking trajectory point category.

[0111] S308. Calculate the dwell time for each parking trajectory point category, and take the position with the longest dwell time as the target parking position for the candidate parking segment.

[0112] S309. Determine the target parking time period corresponding to the candidate parking segment based on the parking start and end times of the candidate parking segment.

[0113] S310. Calculate the total nighttime parking duration and the percentage of nighttime parking based on the target parking time period and the preset nighttime window.

[0114] S311. If the proportion of nighttime parking is greater than the preset nighttime parking determination threshold, then the candidate parking segment is determined as a nighttime parking segment.

[0115] S312. Obtain road surface vector data, and perform spatial matching between the target parking location of the nighttime parking segment and the road surface vector data to obtain the road surface spatial information matching result.

[0116] S313. Based on the matching results of road space information, determine whether the target parking location is located in the on-street parking area, generate the nighttime on-street illegal parking identification result and output it.

[0117] The information collected in the above embodiments of the present invention is all information and data authorized by the user or fully authorized by all parties. The collection, storage, use, processing, transmission, provision, disclosure and application of the relevant data all comply with the relevant laws, regulations and standards of the relevant countries and regions, necessary confidentiality measures have been taken, and they do not violate public order and good morals. Corresponding operation entry points are provided for users to choose to authorize or refuse.

[0118] Example 4

[0119] Figure 4 This is a schematic diagram of a nighttime on-street vehicle illegal parking identification device provided in Embodiment 4 of the present invention. The nighttime on-street vehicle illegal parking identification device provided in this embodiment of the present invention is applicable to scenarios involving the determination of vehicle illegal parking information at night in the field of intelligent transportation. This nighttime on-street vehicle illegal parking identification device can be implemented in hardware and / or software, and can be applied to a nighttime on-street vehicle illegal parking identification method. Specifically, it can be configured in the server of a vehicle illegal parking information monitoring agency. Figure 4 As shown, the device includes: a parking trajectory point acquisition module 401, a candidate parking segment determination module 402, a target parking information determination module 403, and an illegal parking identification result determination module 404. Wherein:

[0120] The parking trajectory point acquisition module 401 is used to acquire the vehicle driving trajectory points of the target vehicle under the current monitoring time period, and to filter the vehicle driving trajectory points to obtain parking trajectory points; wherein, the parking trajectory point includes a parking timestamp and a parking location;

[0121] The candidate parking segment determination module 402 is used to determine at least one candidate parking segment of the target vehicle based on the parking timestamps corresponding to each of the parking trajectory points; the candidate parking segment contains at least two parking trajectory points;

[0122] The target parking information determination module 403 is used to determine the target parking location and target parking time period corresponding to each candidate parking segment based on the parking trajectory points of each candidate parking segment.

[0123] The illegal parking identification result determination module 404 is used to filter at least one nighttime parking segment based on the target parking time period corresponding to each of the candidate parking segments, and then determine the nighttime on-street illegal parking identification result of the target vehicle based on the target parking location corresponding to each of the nighttime parking segments.

[0124] The technical solution of this invention obtains the vehicle trajectory points of the target vehicle during the current monitoring time period, filters these trajectory points to obtain parking trajectory points, and determines at least one candidate parking segment for the target vehicle based on the parking timestamps corresponding to each parking trajectory point. Based on the parking trajectory points of each candidate parking segment, the target parking location and target parking time period corresponding to each candidate parking segment are determined. If at least one nighttime parking segment is obtained by filtering the target parking time periods corresponding to each candidate parking segment, the nighttime on-street illegal parking identification result of the target vehicle is determined based on the target parking location corresponding to each nighttime parking segment. This method can sequentially complete the determination of candidate parking segments, target parking locations, and target parking time periods based on the parking timestamps of the parking trajectory points, achieving accurate identification of nighttime on-street illegal parking segments and information. It effectively solves the problems of incomplete coverage, judgment bias, and low efficiency in traditional nighttime on-street illegal parking identification methods, improving the accuracy and efficiency of nighttime on-street illegal parking identification in the field of intelligent transportation, and providing reliable technical support for the refined management of urban traffic illegal parking.

[0125] Optionally, the target parking information determination module 403 is specifically used for:

[0126] For any candidate parking segment, cluster each parking trajectory point contained in the candidate parking segment at its parking location to obtain at least one parking trajectory point category;

[0127] The target parking location is determined based on the parking location and parking duration of each parking trajectory point in each of the aforementioned parking trajectory point categories;

[0128] Based on the parking timestamps corresponding to each parking trajectory point contained in the candidate parking segment, the target parking time period corresponding to the candidate parking segment is determined.

[0129] Optionally, the device further includes:

[0130] The nighttime parking percentage determination module is used to determine the nighttime parking percentage for any candidate parking segment if it is determined that the candidate parking segment has a corresponding nighttime parking period based on the target parking period and the preset nighttime parking period.

[0131] The nighttime parking segment determination module is used to determine whether a candidate parking segment is a nighttime parking segment if the nighttime parking percentage is greater than a preset nighttime parking percentage threshold.

[0132] Optionally, the illegal parking identification result determination module 404 is specifically used for:

[0133] Obtain the road surface spatial information of the current environment of the target vehicle;

[0134] For any nighttime parking segment, a road space information matching result is generated based on the target parking location corresponding to the nighttime parking segment and the road space information.

[0135] Based on the road surface spatial information matching results, the nighttime roadside illegal parking identification result of the target vehicle is determined.

[0136] Optionally, the candidate parking segment determination module 402 is specifically used for:

[0137] Based on the parking timestamps corresponding to each parking trajectory point, at least one adjacent trajectory point is determined; the adjacent trajectory point is two parking trajectory points whose parking timestamps are adjacent.

[0138] For any two adjacent trajectory points, determine the difference in parking timestamps between the two parking trajectory points in that adjacent trajectory point;

[0139] If the difference in parking timestamps is not greater than the preset parking timestamp threshold, and there is a candidate parking segment that includes any parking trajectory point among the adjacent trajectory points, then the parking trajectory points among the adjacent trajectory points that are not included in the candidate parking segment will be added to the candidate parking segment.

[0140] If the difference in parking timestamps is greater than a preset parking timestamp threshold, and there is a candidate parking segment that includes any parking trajectory point among the adjacent trajectory points, then a new candidate parking segment is created, and parking trajectory points among the adjacent trajectory points that are not included in the candidate parking segment are added to the newly created candidate parking segment.

[0141] Optionally, the parking trajectory point acquisition module 401 is specifically used for:

[0142] Based on the instantaneous speed of the vehicle and the parking timestamp in the vehicle's driving trajectory points, the data of the vehicle's driving trajectory points is cleaned to obtain cleaned vehicle driving trajectory points. Based on the instantaneous speed of the vehicle in the cleaned vehicle driving trajectory points, the parking trajectory points are determined.

[0143] The nighttime on-street vehicle illegal parking identification device provided in this embodiment of the invention can execute a nighttime on-street vehicle illegal parking identification method provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the method.

[0144] Example 5

[0145] Figure 5 A schematic diagram of an electronic device 50 that can be used to implement embodiments of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0146] like Figure 5 As shown, the electronic device 50 includes at least one processor 51 and a memory, such as a read-only memory (ROM) 52 and a random access memory (RAM) 53, communicatively connected to the at least one processor 51. The memory stores computer programs executable by the at least one processor. The processor 51 can perform various appropriate actions and processes based on the computer program stored in the ROM 52 or loaded from storage unit 58 into the RAM 53. The RAM 53 can also store various programs and data required for the operation of the electronic device 50. The processor 51, ROM 52, and RAM 53 are interconnected via a bus 54. An input / output (I / O) interface 55 is also connected to the bus 54.

[0147] Multiple components in electronic device 50 are connected to I / O interface 55, including: input unit 56, such as keyboard, mouse, etc.; output unit 57, such as various types of monitors, speakers, etc.; storage unit 58, such as disk, optical disk, etc.; and communication unit 59, such as network card, modem, wireless transceiver, etc. Communication unit 59 allows electronic device 50 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0148] Processor 51 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 51 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 51 performs the various methods and processes described above, such as a method for identifying illegally parked vehicles on the road at night.

[0149] In some embodiments, the nighttime on-street vehicle illegal parking identification method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 58. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 50 via ROM 52 and / or communication unit 59. When the computer program is loaded into RAM 53 and executed by processor 51, one or more steps of the nighttime on-street vehicle illegal parking identification method described above may be performed. Alternatively, in other embodiments, processor 51 may be configured as a nighttime on-street vehicle illegal parking identification method by any other suitable means (e.g., by means of firmware).

[0150] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0151] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0152] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0153] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0154] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0155] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0156] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0157] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for identifying illegally parked vehicles on the road at night, characterized in that, include: Obtain the vehicle driving trajectory points of the target vehicle under the current monitoring time period, and filter the vehicle driving trajectory points to obtain parking trajectory points; wherein, the parking trajectory points include parking timestamp and parking location; Based on the parking timestamps corresponding to each parking trajectory point, at least one candidate parking segment for the target vehicle is determined; the candidate parking segment contains at least two parking trajectory points. Based on the parking trajectory points of each candidate parking segment, determine the target parking location and target parking time period corresponding to each candidate parking segment; If at least one nighttime parking segment is obtained by filtering according to the target parking time period corresponding to each of the candidate parking segments, then the nighttime on-street illegal parking identification result of the target vehicle is determined according to the target parking location corresponding to each of the nighttime parking segments.

2. The method according to claim 1, characterized in that, The step of determining the target parking location and target parking time period corresponding to each candidate parking segment based on the parking trajectory points of each candidate parking segment includes: For any candidate parking segment, cluster each parking trajectory point contained in the candidate parking segment at its parking location to obtain at least one parking trajectory point category; Based on the parking location and parking duration of each parking trajectory point in each of the aforementioned parking trajectory point categories, the target parking location is determined; and, Based on the parking timestamps corresponding to each parking trajectory point contained in the candidate parking segment, the target parking time period corresponding to the candidate parking segment is determined.

3. The method according to claim 1, characterized in that, Before determining the nighttime on-street illegal parking identification result of the target vehicle based on the target parking location corresponding to each of the candidate parking segments, if at least one nighttime parking segment is obtained by filtering according to the target parking time period corresponding to each of the candidate parking segments, the method further includes: For any candidate parking segment, if it is determined that the candidate parking segment has a corresponding nighttime parking period based on the target parking time period and the preset nighttime parking time period, then the nighttime parking percentage is determined based on the nighttime parking time period and the target parking time period. If the proportion of nighttime parking is greater than a preset threshold for the proportion of nighttime parking, then the candidate parking segment is determined to be a nighttime parking segment.

4. The method according to claim 1, characterized in that, The step of determining the nighttime on-street illegal parking identification result of the target vehicle based on the target parking location corresponding to each of the nighttime parking segments includes: Obtain the road surface spatial information of the current environment of the target vehicle; For any nighttime parking segment, a road space information matching result is generated based on the target parking location corresponding to the nighttime parking segment and the road space information. Based on the road surface spatial information matching results, the nighttime roadside illegal parking identification result of the target vehicle is determined.

5. The method according to claim 1, characterized in that, The step of determining at least one candidate parking segment for the target vehicle based on the parking timestamps corresponding to each of the parking trajectory points includes: Based on the parking timestamps corresponding to each parking trajectory point, at least one adjacent trajectory point is determined; the adjacent trajectory point is two parking trajectory points whose parking timestamps are adjacent. For any two adjacent trajectory points, determine the difference in parking timestamps between the two parking trajectory points in that adjacent trajectory point; If the difference in parking timestamps is not greater than the preset parking timestamp threshold, and there is a candidate parking segment that includes any parking trajectory point among the adjacent trajectory points, then the parking trajectory points among the adjacent trajectory points that are not included in the candidate parking segment will be added to the candidate parking segment. If the difference in parking timestamps is greater than a preset parking timestamp threshold, and there is a candidate parking segment that includes any parking trajectory point among the adjacent trajectory points, then a new candidate parking segment is created, and parking trajectory points among the adjacent trajectory points that are not included in the candidate parking segment are added to the newly created candidate parking segment.

6. The method according to claim 1, characterized in that, The step of filtering the vehicle's driving trajectory points to obtain parking trajectory points includes: Based on the instantaneous speed of the vehicle and the parking timestamp in the vehicle's driving trajectory points, the data of the vehicle's driving trajectory points is cleaned to obtain cleaned vehicle driving trajectory points. Based on the instantaneous speed of the vehicle in the cleaned vehicle driving trajectory points, the parking trajectory points are determined.

7. A nighttime on-street vehicle illegal parking identification device, characterized in that, include: The parking trajectory point acquisition module is used to acquire the vehicle driving trajectory points of the target vehicle under the current monitoring time period, and to filter the vehicle driving trajectory points to obtain parking trajectory points; wherein, the parking trajectory point includes a parking timestamp and a parking location; The candidate parking segment determination module is used to determine at least one candidate parking segment of the target vehicle based on the parking timestamps corresponding to each of the parking trajectory points; the candidate parking segment contains at least two parking trajectory points; The target parking information determination module is used to determine the target parking location and target parking time period corresponding to each candidate parking segment based on the parking trajectory points of each candidate parking segment. The illegal parking identification result determination module is used to filter at least one nighttime parking segment based on the target parking time period corresponding to each of the candidate parking segments, and then determine the nighttime on-street illegal parking identification result of the target vehicle based on the target parking location corresponding to each of the nighttime parking segments.

8. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the nighttime on-street vehicle illegal parking identification method according to any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that, when executed by a processor, implement the nighttime roadside vehicle illegal parking identification method according to any one of claims 1-6.

10. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the nighttime on-street vehicle illegal parking identification method according to any one of claims 1-6.

Images