Vehicle abnormal parking processing method, system and device and storage medium

Abstract

The invention discloses a vehicle abnormal parking processing method, system and device and a storage medium, and the method comprises the steps: carrying out the fitting of electronic police checkpoint data and radar data, and obtaining the time-space data of a vehicle track at a current moment; determining a plurality of target vehicle objects in a preset monitoring area range and driving states corresponding to the target vehicle objects according to the vehicle track spatio-temporal data at the previous moment and the vehicle track spatio-temporal data at the current moment; selecting a static vehicle object corresponding to a static driving state from the plurality of target vehicle objects, and determining the parking duration of the static vehicle object; and determining an abnormal parking event type corresponding to the static vehicle object according to the parking duration, and performing abnormal parking processing on the static vehicle object based on the abnormal parking event type. According to the invention, the electronic police checkpoint and the radar equipment at the intersection fit vehicle trajectory data, and analyze and extract abnormal parking events, so that the working efficiency of a management department is improved, and road traffic accidents are effectively prevented and reduced.

Description

Technical Field

[0001] The present invention relates to the field of information intelligent transportation technology, and in particular to a method, system, device and storage medium for handling abnormal parking of a vehicle. Background Art

[0002] As the urbanization process continues to accelerate, road traffic pressure continues to increase, and intersection traffic problems have become a difficult and painful point in urban traffic management. Among them, abnormal parking incidents at urban road intersections are frequent and easy to cause secondary accidents, becoming a prominent hidden danger in road traffic safety.

[0003] At present, the public security traffic police department still mostly uses manual video inspections to discover related events. The traditional manual inspection method has problems such as incomplete inspection coverage, waste of police resources, low efficiency, and failure to obtain accurate event-related information in a timely manner. In addition to traditional manual inspections, the driving changes of vehicles in actual traffic scenes are diverse, and it is difficult to determine the actual location of the vehicle through the detection area image, which makes the detection accuracy of traditional methods low, and it is also impossible to extract detailed information about the event. Therefore, how to accurately and efficiently analyze abnormal parking events at intersections and quickly warn and deal with emergencies has become an urgent problem to be solved.

[0004] The above contents are only used to assist in understanding the technical solution of the present invention and do not constitute an admission that the above contents are prior art. Summary of the invention

[0005] The main purpose of the present invention is to provide a method, system, device and storage medium for handling abnormal parking of vehicles, aiming to solve the technical problem of how to accurately and efficiently analyze abnormal parking events at intersections and quickly warn and deal with emergencies.

[0006] To achieve the above object, the present invention provides a method for handling abnormal parking of a vehicle, the method comprising:

[0007] Acquire the electric police checkpoint data and radar data within the preset monitoring area of ​​the current road in real time, and fit the electric police checkpoint data and the radar data to obtain the spatiotemporal data of the vehicle trajectory at the current moment;

[0008] Determine a plurality of target vehicle objects within the preset monitoring area and a driving state corresponding to each target vehicle object according to the spatiotemporal data of the vehicle trajectory at the previous moment and the spatiotemporal data of the vehicle trajectory at the current moment;

[0009] Selecting a stationary vehicle object corresponding to the stationary driving state from a plurality of target vehicle objects, and determining a parking duration of the stationary vehicle object;

[0010] The abnormal parking event type corresponding to the stationary vehicle object is determined according to the parking duration, and abnormal parking processing is performed on the stationary vehicle object based on the abnormal parking event type.

[0011] Optionally, before the step of acquiring the electric police checkpoint data and radar data in the preset area of ​​the current road in real time, the step includes:

[0012] Determine the electric police location information, checkpoint location information and radar location information of the current road respectively;

[0013] Determine the road shooting area range according to the electric police position information, the checkpoint position information and the radar position information;

[0014] The preset monitoring area range is determined according to the road shooting area range based on the vehicle lane information of the current road.

[0015] Optionally, the step of determining a plurality of target vehicle objects within the preset monitoring area and a driving state corresponding to each target vehicle object according to the spatiotemporal data of the vehicle trajectory at the previous moment and the spatiotemporal data of the vehicle trajectory at the current moment includes:

[0016] Determine the ID number of each vehicle object at the previous moment according to the spatiotemporal data of the vehicle trajectory at the previous moment, and determine the ID number of each vehicle object at the current moment according to the spatiotemporal data of the vehicle trajectory at the current moment;

[0017] Determine a plurality of target vehicle objects according to the ID number of each vehicle object at the previous moment and the ID number of each vehicle object at the current moment;

[0018] Determine the latitude and longitude information of each target vehicle object at a previous moment according to the spatiotemporal data of the vehicle trajectory at a previous moment, and determine the latitude and longitude information of each target vehicle object at a current moment according to the spatiotemporal data of the vehicle trajectory at a current moment;

[0019] Determine the current travel distance of each target vehicle object based on the previous longitude and latitude information of each target vehicle object and the current longitude and latitude information of each target vehicle object, and determine the current travel speed of each target vehicle object based on the current travel distance of each target vehicle object and the capture time interval;

[0020] The driving state corresponding to each target vehicle object is determined according to the current driving speed.

[0021] Optionally, the step of determining the parking duration of the stationary vehicle object comprises:

[0022] Determine the last moment's travel speed of the stationary vehicle object;

[0023] Determining whether the driving speed at the previous moment is a stationary state;

[0024] If not, determining the capture time at the previous moment according to the spatiotemporal data of the vehicle trajectory at the previous moment, and determining the capture time at the current moment according to the spatiotemporal data of the vehicle trajectory at the current moment;

[0025] The parking duration of the stationary vehicle object is determined according to the last snapshot time and the current snapshot time.

[0026] Optionally, after the step of determining whether the driving speed at the previous moment is in a stationary state, the following steps are included:

[0027] If yes, the cumulative static duration of the static vehicle object is determined through the data structure trajectory table, and the capture time at the previous moment is determined according to the spatiotemporal data of the vehicle trajectory at the previous moment, and the capture time at the current moment is determined according to the spatiotemporal data of the vehicle trajectory at the current moment;

[0028] The parking duration of the stationary vehicle object is determined according to the current snapshot time, the previous snapshot time and the accumulated static duration.

[0029] Optionally, the step of determining the abnormal parking event type corresponding to the stationary vehicle object according to the parking duration includes:

[0030] When the parking duration is longer than a preset time threshold, extracting relevant information of the stationary vehicle object from the spatiotemporal data of the vehicle trajectory at the current moment;

[0031] Generate an abnormal parking event according to the parking duration, the relevant information of the stationary vehicle object and the intersection number of the current road;

[0032] Analyzing the abnormal parking event to determine associated information of the stationary vehicle object;

[0033] The type of the abnormal parking event is determined according to the association information between the abnormal parking event and the stationary vehicle object.

[0034] Optionally, the step of performing abnormal parking processing on the stationary vehicle object based on the abnormal parking event type includes:

[0035] generating event data according to the abnormal parking event, the associated information of the stationary vehicle object, and the type of the abnormal parking event;

[0036] Determine historical trajectory data of the stationary vehicle object according to the event data, and fit an abnormal parking simulation video of the stationary vehicle object based on the historical trajectory data;

[0037] Determining an abnormal parking event level according to the abnormal parking event type, and determining a corresponding abnormal event processing rule according to the abnormal parking event level;

[0038] Based on the abnormal parking simulation video, abnormal parking processing is performed on the stationary vehicle object according to the abnormal event processing rule.

[0039] In addition, to achieve the above-mentioned purpose, the present invention also proposes a vehicle abnormal parking processing system, the vehicle abnormal parking processing system comprising:

[0040] A fitting module is used to obtain the electric police checkpoint data and radar data within the preset monitoring area of ​​the current road in real time, and fit the electric police checkpoint data and the radar data to obtain the spatiotemporal data of the vehicle trajectory at the current moment;

[0041] A determination module, used to determine a plurality of target vehicle objects within the preset monitoring area and a driving state corresponding to each target vehicle object according to the spatiotemporal data of the vehicle trajectory at the previous moment and the spatiotemporal data of the vehicle trajectory at the current moment;

[0042] A calculation module, configured to select a stationary vehicle object corresponding to the stationary driving state from a plurality of target vehicle objects, and determine a parking duration of the stationary vehicle object;

[0043] A processing module is used to determine the abnormal parking event type corresponding to the stationary vehicle object according to the parking duration, and perform abnormal parking processing on the stationary vehicle object based on the abnormal parking event type.

[0044] In addition, to achieve the above-mentioned purpose, the present invention also proposes a vehicle abnormal parking processing device, which includes: a memory, a processor, and a vehicle abnormal parking processing program stored in the memory and executable on the processor, wherein the vehicle abnormal parking processing program is configured to implement the steps of the vehicle abnormal parking processing method described above.

[0045] In addition, to achieve the above-mentioned purpose, the present invention also proposes a storage medium, on which a vehicle abnormal parking processing program is stored. When the vehicle abnormal parking processing program is executed by a processor, the steps of the vehicle abnormal parking processing method described above are implemented.

[0046] The present invention firstly acquires the electric police checkpoint data and radar data within the preset monitoring area of ​​the current road in real time, and fits the electric police checkpoint data and the radar data to obtain the spatiotemporal data of the vehicle trajectory at the current moment, and then determines multiple target vehicle objects within the preset monitoring area and the driving states corresponding to each target vehicle object according to the spatiotemporal data of the vehicle trajectory at the previous moment and the spatiotemporal data of the vehicle trajectory at the current moment, and selects a stationary vehicle object corresponding to a stationary driving state from the multiple target vehicle objects, determines the parking duration of the stationary vehicle object, and then determines the abnormal parking event type corresponding to the stationary vehicle object according to the parking duration, and performs abnormal parking processing on the stationary vehicle object based on the abnormal parking event type. Compared with the manual inspection method in the prior art, which has the problems of incomplete inspection coverage, waste of police resources, low efficiency and failure to obtain accurate event-related information in a timely manner, the present invention abandons the previous analysis method of using manual video inspection or camera calibration based on video stream, and fits vehicle trajectory data based on the electric police checkpoints and radar equipment at the intersection. By extracting and analyzing the vehicle trajectory data, it accurately and efficiently analyzes abnormal parking events at the intersection, classifies the events and pushes the corresponding detailed information to the early warning center or management department, so as to achieve the effect of rapid early warning and disposal of the emergency. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 It is a structural schematic diagram of a vehicle abnormal parking processing device in a hardware operating environment involved in an embodiment of the present invention;

[0048] Figure 2 This is an overall flow chart of abnormal parking event analysis of the first embodiment of the method for handling abnormal parking of a vehicle of the present invention;

[0049] Figure 3 A schematic diagram of a flow chart of a first embodiment of a method for handling abnormal parking of a vehicle according to the present invention;

[0050] Figure 4 The data structure trajectory table 1 of the first embodiment of the vehicle abnormal parking processing method of the present invention;

[0051] Figure 5 The data structure trajectory table 2 of the first embodiment of the vehicle abnormal parking processing method of the present invention;

[0052] Figure 6 Table 3 of the data structure trajectory of the first embodiment of the method for handling abnormal parking of a vehicle according to the present invention;

[0053] Figure 7 A detailed business flow chart of abnormal parking event analysis of the first embodiment of the method for handling abnormal parking of a vehicle according to the present invention;

[0054] Figure 8The event data table of the first embodiment of the method for handling abnormal parking of a vehicle according to the present invention;

[0055] Fig. 9 It is a Web display flow chart of abnormal parking events of the first embodiment of the method for handling abnormal parking of a vehicle of the present invention;

[0056] Fig.10 The abnormal parking event video rendering of the first embodiment of the abnormal parking processing method of the present invention Figure 1 ;

[0057] Fig.11 The abnormal parking event video rendering of the first embodiment of the abnormal parking processing method of the present invention Figure 2 ;

[0058] Fig.12 The abnormal parking event video rendering of the first embodiment of the abnormal parking processing method of the present invention Figure 3 ;

[0059] Fig.13 This is a diagram of an abnormal parking event push warning interface of the first embodiment of the vehicle abnormal parking processing method of the present invention;

[0060] Fig.14 It is a structural block diagram of the first embodiment of the vehicle abnormal parking processing system of the present invention.

[0061] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0062] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0063] Reference Figure 1 , Figure 1 The present invention is a schematic diagram of the structure of a vehicle abnormal parking processing device in the hardware operating environment involved in the embodiment of the present invention.

[0064] like Figure 1As shown, the vehicle abnormal parking processing device may include: a processor 1001, such as a central processing unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. Among them, the communication bus 1002 is used to realize the connection and communication between these components. The user interface 1003 may include a display screen (Display), an input unit such as a keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface and a wireless interface. The network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a wireless fidelity (Wireless-Fidelity, Wi-Fi) interface). The memory 1005 may be a high-speed random access memory (RandomAccess Memory, RAM), or a stable non-volatile memory (Non-Vo latile Memory, NVM), such as a disk storage. The memory 1005 may also be a storage system independent of the aforementioned processor 1001.

[0065] Those skilled in the art will understand that Figure 1 The structure shown in the figure does not constitute a limitation on the vehicle abnormal parking processing device, and may include more or less components than those shown in the figure, or combine certain components, or arrange the components differently.

[0066] like Figure 1 As shown, the memory 1005 as a storage medium may include an operating system, a network communication module, a user interface module, and a vehicle abnormal parking processing program.

[0067] exist Figure 1 In the vehicle abnormal parking processing device shown, the network interface 1004 is mainly used for data communication with the network server; the user interface 1003 is mainly used for data interaction with the user; the processor 1001 and the memory 1005 in the vehicle abnormal parking processing device of the present invention can be set in the vehicle abnormal parking processing device, and the vehicle abnormal parking processing device calls the vehicle abnormal parking processing program stored in the memory 1005 through the processor 1001, and executes the vehicle abnormal parking processing method provided by the embodiment of the present invention.

[0068] In this embodiment, reference Figure 2 , Figure 2This is the overall flow chart of abnormal parking event analysis of the first embodiment of the vehicle abnormal parking processing method of the present invention. Based on the fitting of vehicle trajectory data by the electric police checkpoint and radar equipment at the intersection, abnormal parking events are analyzed and extracted. Then, according to the parking duration of the main target object of the parking event, whether there are other related vehicles in time and space, etc., the specific type and information of the parking event are analyzed to be traffic conflict, abnormal parking, suspected vehicle accident, etc. The abnormal parking events analyzed are then pushed to the early warning center in real time, so that the management department can obtain the event and its related detailed information as soon as possible and respond to the event quickly.

[0069] The embodiment of the present invention provides a method for handling abnormal parking of a vehicle, referring to Figure 3 , Figure 3 It is a flowchart of the first embodiment of the method for handling abnormal parking of a vehicle according to the present invention.

[0070] In this embodiment, the method for handling abnormal parking of a vehicle includes the following steps:

[0071] Step S10: Acquire the electric police checkpoint data and radar data within the preset monitoring area of ​​the current road in real time, and fit the electric police checkpoint data and the radar data to obtain the spatiotemporal data of the vehicle trajectory at the current moment.

[0072] It is easy to understand that the execution subject of this embodiment can be a vehicle abnormal parking processing system with functions such as data processing, network communication and program running, or other computer equipment with similar functions, etc., and this embodiment is not limited.

[0073] It should be noted that the edge computing box installed at the road intersection can obtain real-time spatiotemporal data of vehicle trajectories by fitting the data of the electric police checkpoint and the radar data. Each batch of accessed data will contain the real-time trajectory information of all vehicle objects within the monitoring range of the intersection. This system collects and records the trajectory data. The collected and recorded spatiotemporal data of vehicle trajectories are written in batches into the original vehicle trajectory library.

[0074] It should be understood that it is also necessary to separately determine the electric police position information, checkpoint location information and radar position information on the current road, determine the road shooting area range based on the electric police position information, checkpoint location information and radar position information, and determine the preset monitoring area range based on the road shooting area range based on the vehicle lane information of the current road.

[0075] In a specific implementation, technicians can manually set the preset monitoring area range according to the road shooting area range, and can also determine the preset monitoring area range according to the road shooting area range based on the vehicle lane information of the current road (i.e., the boundary line of the outer vehicle lane).

[0076] Relevant information of multiple vehicle objects can be clearly collected within the preset monitoring area, such as target latitude and longitude, license plate number, vehicle color, etc.

[0077] In this embodiment, the edge computing box installed on the road intersection side fits the electric police checkpoint data and radar data to obtain the spatiotemporal data of the vehicle trajectory at the current intersection at the current moment. The spatiotemporal data of the vehicle trajectory includes the vehicle ID number within the preset monitoring area, the intersection number and the capture time of the electric police checkpoint and radar equipment, the target longitude and latitude of the vehicle, the license plate number, the license plate color, the vehicle type, etc. Then, the data structure trajectory table 1 is generated based on the spatiotemporal data of the vehicle trajectory, and the reference Figure 4 , Figure 4 This is a data structure trajectory table 1 of the first embodiment of the vehicle abnormal parking processing method of the present invention.

[0078] The vehicle ID number (i.e., object movement ID), intersection number, license plate color, and vehicle type can all be replaced by pre-set codes based on demand, or can be recorded based on real information.

[0079] It should also be noted that the capture time is the capture time pre-set by the electric police checkpoint and radar equipment.

[0080] Step S20: determining a plurality of target vehicle objects within the preset monitoring area and a driving state corresponding to each target vehicle object according to the spatiotemporal data of the vehicle trajectory at the previous moment and the spatiotemporal data of the vehicle trajectory at the current moment.

[0081] It should be understood that the ID number of each vehicle object at the previous moment is determined based on the spatiotemporal data of the vehicle trajectory at the previous moment, and the ID number of each vehicle object at the current moment is determined based on the spatiotemporal data of the vehicle trajectory at the current moment; multiple target vehicle objects are determined based on the ID number of each vehicle object at the previous moment and the ID number of each vehicle object at the current moment; the longitude and latitude information of each target vehicle object at the previous moment is determined respectively based on the spatiotemporal data of the vehicle trajectory at the previous moment, and the longitude and latitude information of each target vehicle object at the current moment is determined respectively based on the spatiotemporal data of the vehicle trajectory at the current moment; the current trajectory travel distance of each target vehicle object is determined based on the longitude and latitude information of each target vehicle object at the previous moment and the longitude and latitude information of each target vehicle object at the current moment, and the current moment driving speed of each target vehicle object is determined based on the current trajectory travel distance of each target vehicle object and the capture time interval; the driving state corresponding to each target vehicle object is determined based on the current moment driving speed.

[0082] Since the vehicle is always in driving state, each vehicle object at each intersection has a unique and unchanged movement ID (TrackID) from the beginning of monitoring to leaving the monitoring area. The information of the vehicle's current action can be continuously tracked based on the ID. In practice, the vehicle objects contained in the vehicle trajectory spatiotemporal data at the previous moment may have a small change from the vehicle objects contained in the vehicle trajectory spatiotemporal data at the current moment. Therefore, it is necessary to determine the ID numbers of all vehicle objects at the previous moment and the ID numbers of all vehicle objects at the current moment, and compare them, and select the vehicle object with the same ID number at the previous moment and the current moment as the target vehicle object.

[0083] In this embodiment, it is also necessary to calculate the real-time driving speed of each target vehicle object. The vehicle speed calculation processing logic is as follows:

[0084] Definition 1: The current track travel distance D1 can be calculated by using the longitude and latitude information in the currently accessed track data and the longitude and latitude information in the previous track (i.e., the previous moment) of the movement ID;

[0085] Definition 2: The current trajectory travel time T1 can be calculated by using the capture time in the currently accessed trajectory data and the capture time in the previous trajectory of the movement ID;

[0086] Definition 3: Based on the distance D1 and time T1 obtained from Definition 1 and Definition 2, the average speed of the vehicle passing this time can be obtained as S1 = D1 / T1;

[0087] The target driving speed obtained in Definition 3 is added to the vehicle trajectory spatiotemporal data and data structure trajectory table 1 to obtain data structure trajectory table 2. The speed field is added to obtain Figure 5 , Figure 5 This is the data structure trajectory table 2 of the first embodiment of the vehicle abnormal parking processing method of the present invention.

[0088] It should also be noted that the driving state includes a stationary state and a running state. The stationary state is a state where the speed is 0, and the running state is a state where the speed is greater than 0.

[0089] Step S30: selecting a stationary vehicle object corresponding to the stationary driving state from a plurality of target vehicle objects, and determining a parking duration of the stationary vehicle object.

[0090] Further, determine the driving speed of the stationary vehicle object at the previous moment; determine whether the driving speed at the previous moment is a stationary state; if not, determine the capture time at the previous moment according to the spatiotemporal data of the vehicle trajectory at the previous moment, and determine the capture time at the current moment according to the spatiotemporal data of the vehicle trajectory at the current moment; determine the parking duration of the stationary vehicle object according to the capture time at the previous moment and the capture time at the current moment; if so, determine the cumulative stationary duration of the stationary vehicle object through the data structure trajectory table, and determine the capture time at the previous moment according to the spatiotemporal data of the vehicle trajectory at the previous moment, and determine the capture time at the current moment according to the spatiotemporal data of the vehicle trajectory at the current moment; determine the parking duration of the stationary vehicle object according to the capture time at the current moment, the capture time at the previous moment and the cumulative stationary duration.

[0091] In the specific implementation, the logic for calculating the duration when the vehicle's real-time speed is 0 is as follows:

[0092] 1. When the real-time speed of a vehicle track calculated in step 4 is 0,

[0093] a. When the speed of the previous track of the vehicle (same movement ID) is not 0, the duration of the vehicle speed being 0 = the current recording capture time - the capture time of the previous track;

[0094] b. When the speed of the previous track of the vehicle (same movement ID) is 0, the duration of the vehicle's speed being 0 = the current recorded capture time - the capture time of the previous track + the duration of the original cumulative speed being 0;

[0095] 2. For a vehicle trajectory that is connected in real time, if the calculated real-time speed of the vehicle is not 0, the duration value when the speed of the vehicle is 0 is set to 0.

[0096] 3. After analyzing the speed of each record, analyze the duration of the speed being 0 at the same time. Add the duration field value obtained by the analysis to the data structure trajectory table 2 and the vehicle trajectory spatiotemporal data to obtain Figure 6 , Figure 6 This is the data structure trajectory table 3 of the first embodiment of the vehicle abnormal parking processing method of the present invention.

[0097] It should also be noted that the trajectories are all within the monitoring area.

[0098] Step S40: determining the abnormal parking event type corresponding to the stationary vehicle object according to the parking duration, and performing abnormal parking processing on the stationary vehicle object based on the abnormal parking event type.

[0099] Furthermore, when the parking duration is greater than a preset time threshold, relevant information of the stationary vehicle object is extracted from the spatiotemporal data of the vehicle trajectory at the current moment; an abnormal parking event is generated according to the parking duration, relevant information of the stationary vehicle object and the intersection number of the current road; the abnormal parking event is analyzed to determine the associated information of the stationary vehicle object; and the type of the abnormal parking event is determined according to the associated information of the abnormal parking event and the stationary vehicle object.

[0100] The relevant information of the stationary vehicle object includes ID, event occurrence time, intersection number, target latitude and longitude of the vehicle, license plate number, license plate color, event duration, etc. The preset time threshold can be set by the user and can be 5s or 6s, etc.

[0101] Furthermore, a processing method for determining the type of abnormal parking event corresponding to a stationary vehicle object according to the parking duration is as follows: when the parking duration is greater than a preset time threshold, extracting relevant information of the stationary vehicle object from the spatiotemporal data of the vehicle trajectory at the current moment; generating an abnormal parking event according to the parking duration, the relevant information of the stationary vehicle object and the intersection number of the current road; analyzing the abnormal parking event to determine the associated information of the stationary vehicle object; determining the type of abnormal parking event according to the associated information of the abnormal parking event and the stationary vehicle object, wherein the abnormal parking event categories include traffic conflict event types, abnormal parking event types, vehicle-to-vehicle accident event types, etc.

[0102] In the specific implementation, the duration of the time when the speed of the vehicle at the intersection is 0 can be used to determine whether it is an abnormal parking event and the specific type of abnormal parking event based on this accumulated time. The specific determination definition is as follows:

[0103] Definition 1:

[0104] Valid events: Draw the area range for each intersection in the high-precision map to pre-analyze abnormal parking events. Only parking events that occur within this area can be correctly determined as valid events.

[0105] Definition 2:

[0106] Traffic conflict stop event: In the intersection monitoring area, a conflict occurs between a vehicle going straight and turning left, turning around, turning right, etc., or a vehicle stops immediately after crossing the stop line because the traffic light turns red, resulting in a short stop event. Definition: If it meets definition 1, and the speed is 0 and the duration is greater than or equal to 5s and less than 90s, it is a traffic conflict event type.

[0107] Definition 3:

[0108] Abnormal parking event: When it meets definition 1 and the speed is 0 and the duration is greater than or equal to 90s, it is this abnormal parking event type.

[0109] Definition 4:

[0110] Suspected vehicle - vehicle accident parking event: At the same intersection, the trajectories of two vehicles conform to Definition 1, the speed is 0 and the duration is >= 300s, and when the two vehicles are continuously parked, the straight - line distance calculated according to the longitude and latitude is <= 6m, and the time coincidence degree during continuous parking is >= 70%. When the above conditions are met, this event is determined to be a suspected vehicle - vehicle accident event. The determination priority of this event is higher than that of the abnormal parking event in Definition 3. If the speed is 0 and the duration is >= 300s, but other conditions are not met, it is determined to be an abnormal parking event.

[0111] In this implementation method, for the trajectory of a certain vehicle accessed in real - time, when the speed of this trajectory is calculated to be 0, the duration is marked as Ta, and the duration when the speed of the previous trajectory of this vehicle is 0 is marked as Tb: If Ta == 0 and Tb == 0, only record the operation of this trajectory data; if Ta == 0 and Tb!= 0, further determine whether the previous trajectory of this vehicle conforms to the above - mentioned Definition 2. If the event determination conditions of Definition 2 are met and there is no data of the same type of event associated with the ID of this trajectory movement direction in the database, then save this event into the database. Otherwise, no event is generated, and only record the operation of this trajectory data; if 0 < Ta < 300, only record the operation of this trajectory data and accumulate the duration when the speed is 0; if Ta >= 300, further determine whether Ta conforms to the above - mentioned Definitions 3 and 4. First, determine whether it meets Definition 4. If it does not meet, then determine whether it conforms to Definition 3. If one of them is met and there is no data of the same type of event associated with the ID of this trajectory movement direction in the database, then save this event into the database. Otherwise, no event is generated, and only record the operation of this trajectory data.

[0112] In this embodiment, the associated information of the stationary vehicle object includes the non - associated information of the stationary vehicle object, and the non - associated information is left blank without filling in data. It also includes the relevant information of the associated vehicle in the traffic accident of the stationary vehicle object. The relevant information of the associated vehicle includes the target movement direction ID of the associated vehicle, the license plate number of the associated vehicle, the license plate color of the associated vehicle, the target longitude and latitude of the associated vehicle, etc. Determine the event data according to the data corresponding to the abnormal parking event, the associated information of the stationary vehicle object, and the type of the abnormal parking event, generate an event data table according to the event data, and perform the operation of entering the event data into the abnormal parking database. Refer to Figure 7 and Figure 8 , Figure 7 is the detailed business flow chart of the abnormal parking event analysis in the first embodiment of the vehicle abnormal parking processing method of the present invention, Figure 8 is the event data table in the first embodiment of the vehicle abnormal parking processing method of the present invention.

[0113] Further, event data is generated according to the abnormal parking event, the associated information of the stationary vehicle object and the type of the abnormal parking event; historical trajectory data of the stationary vehicle object is determined according to the event data, and reference is made to Fig. 9 , Fig. 9 The abnormal parking event Web display flow chart of the first embodiment of the vehicle abnormal parking processing method of the present invention is based on the historical trajectory data to fit the abnormal parking simulation video (i.e., abnormal parking event video) of the stationary vehicle object, refer to 10-12, Fig.10 The abnormal parking event video rendering of the first embodiment of the abnormal parking processing method of the present invention Figure 1 (The vehicle passed the stop line but stopped in the center of the intersection because the traffic light turned red. The stop time was less than 90 seconds and was detected as a traffic conflict by the system); Fig.11 The abnormal parking event video rendering of the first embodiment of the abnormal parking processing method of the present invention Figure 2 (The vehicle stopped in the intersection monitoring area for more than 90 seconds, and there were no vehicles in the same state in the vicinity, which was detected by the system as abnormal parking); Fig.12 The abnormal parking event video rendering of the first embodiment of the abnormal parking processing method of the present invention Figure 3 (The two vehicles stopped at the same time in the intersection monitoring area for more than 300 seconds in a certain period of time and the distance between the vehicles was less than 6 meters, which was detected by the system as a suspected vehicle-to-vehicle accident); the abnormal parking event level was determined according to the abnormal parking event type, and the corresponding abnormal event processing rules were determined according to the abnormal parking event level; abnormal parking processing was performed on the stationary vehicle object according to the abnormal event processing rules based on the abnormal parking simulation video.

[0114] It should also be noted that users can customize the level corresponding to the abnormal parking event type, including level one, level two and level three. The abnormal event handling rules corresponding to level one can be no processing. For level two and above, the system can connect the analyzed event information to the early warning center or command and dispatch platform to send alarm messages to the inspection personnel in time. The early warning center or command and dispatch platform can view the abnormal parking event video, reference Fig.13 , Fig.13 This is a diagram of an abnormal parking event push warning interface of the first embodiment of the vehicle abnormal parking processing method of the present invention.

[0115] In the specific implementation, the event table data can be returned to the front end for display through the interface. When checking a certain event, the historical intersection vehicle trajectory data collected and recorded in step S10 and the GIS high-precision map can be associated. The event and the associated vehicles can be reproduced on the high-precision GIS map through the model, and the corresponding abnormal parking event video can be generated to accurately restore the situation at the time of the event. This provides an accurate basis for the management department to deal with the event and subsequently adjust the intersection organization.

[0116] In this embodiment, the electric police checkpoint data and radar data within the preset monitoring area of ​​the current road are first acquired in real time, and the electric police checkpoint data and radar data are fitted to obtain the spatiotemporal data of the vehicle trajectory at the current moment. Then, multiple target vehicle objects within the preset monitoring area and the driving status corresponding to each target vehicle object are determined according to the spatiotemporal data of the vehicle trajectory at the previous moment and the spatiotemporal data of the vehicle trajectory at the current moment. A stationary vehicle object corresponding to a stationary driving state is selected from the multiple target vehicle objects, and the parking duration of the stationary vehicle object is determined. Then, the type of abnormal parking event corresponding to the stationary vehicle object is determined according to the parking duration, and abnormal parking processing is performed on the stationary vehicle object based on the abnormal parking event type. Compared with the manual inspection method in the prior art, which has problems such as incomplete inspection coverage, waste of police resources, low efficiency, and inability to obtain accurate event-related information in a timely manner, this embodiment abandons the previous analysis method of using manual video inspection or camera calibration based on video streams, and fits vehicle trajectory data based on the electric police checkpoints and radar equipment at the intersection. By extracting and analyzing the vehicle trajectory data, it accurately and efficiently analyzes abnormal parking events at the intersection, classifies the events, and pushes the corresponding detailed information to the early warning center or management department, so as to achieve the effect of rapid early warning and disposal of the emergency.

[0117] Reference Fig.14 , Fig.14 It is a structural block diagram of the first embodiment of the vehicle abnormal parking processing system of the present invention.

[0118] like Fig.14 As shown, the vehicle abnormal parking processing system proposed in the embodiment of the present invention includes:

[0119] The fitting module 1401 is used to obtain the electric police checkpoint data and radar data within the preset monitoring area of ​​the current road in real time, and fit the electric police checkpoint data and the radar data to obtain the spatiotemporal data of the vehicle trajectory at the current moment;

[0120] A determination module 1402 is used to determine a plurality of target vehicle objects within the preset monitoring area and a driving state corresponding to each target vehicle object according to the spatiotemporal data of the vehicle trajectory at the previous moment and the spatiotemporal data of the vehicle trajectory at the current moment;

[0121] The calculation module 1403 is used to select a stationary vehicle object corresponding to the stationary driving state from a plurality of target vehicle objects, and determine the parking duration of the stationary vehicle object;

[0122] The processing module 1404 is used to determine the abnormal parking event type corresponding to the stationary vehicle object according to the parking duration, and perform abnormal parking processing on the stationary vehicle object based on the abnormal parking event type.

[0123] In this embodiment, the electric police checkpoint data and radar data within the preset monitoring area of ​​the current road are first acquired in real time, and the electric police checkpoint data and radar data are fitted to obtain the spatiotemporal data of the vehicle trajectory at the current moment. Then, multiple target vehicle objects within the preset monitoring area and the driving status corresponding to each target vehicle object are determined according to the spatiotemporal data of the vehicle trajectory at the previous moment and the spatiotemporal data of the vehicle trajectory at the current moment. A stationary vehicle object corresponding to a stationary driving state is selected from the multiple target vehicle objects, and the parking duration of the stationary vehicle object is determined. Then, the type of abnormal parking event corresponding to the stationary vehicle object is determined according to the parking duration, and abnormal parking processing is performed on the stationary vehicle object based on the abnormal parking event type. Compared with the manual inspection method in the prior art, which has problems such as incomplete inspection coverage, waste of police resources, low efficiency, and inability to obtain accurate event-related information in a timely manner, this embodiment abandons the previous analysis method of using manual video inspection or camera calibration based on video streams, and fits vehicle trajectory data based on the electric police checkpoints and radar equipment at the intersection. By extracting and analyzing the vehicle trajectory data, it accurately and efficiently analyzes abnormal parking events at the intersection, classifies the events, and pushes the corresponding detailed information to the early warning center or management department, so as to achieve the effect of rapid early warning and disposal of the emergency.

[0124] Other embodiments or specific implementations of the vehicle abnormal parking processing system of the present invention can refer to the above-mentioned method embodiments, which will not be repeated here.

[0125] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or system. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or system including the element.

[0126] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0127] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as a read-only memory / random access memory, a magnetic disk, or an optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present invention.

[0128] The above are only preferred embodiments of the present invention, and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A method for handling abnormal parking of a vehicle, characterized in that: The method for handling abnormal parking of a vehicle comprises the following steps: Acquire the electric police checkpoint data and radar data within the preset monitoring area of ​​the current road in real time, and fit the electric police checkpoint data and the radar data to obtain the spatiotemporal data of the vehicle trajectory at the current moment; Determine a plurality of target vehicle objects within the preset monitoring area and a driving state corresponding to each target vehicle object according to the spatiotemporal data of the vehicle trajectory at the previous moment and the spatiotemporal data of the vehicle trajectory at the current moment; Selecting a stationary vehicle object corresponding to the stationary driving state from a plurality of target vehicle objects, and determining a parking duration of the stationary vehicle object; The abnormal parking event type corresponding to the stationary vehicle object is determined according to the parking duration, and abnormal parking processing is performed on the stationary vehicle object based on the abnormal parking event type.

2. The method according to claim 1, characterized in that Before the step of obtaining the electric police checkpoint data and radar data in the preset area of ​​the current road in real time, the method includes: Determine the electric police location information, checkpoint location information and radar location information of the current road respectively; Determine the road shooting area range according to the electric police position information, the checkpoint position information and the radar position information; The preset monitoring area range is determined according to the road shooting area range based on the vehicle lane information of the current road.

3. The method according to claim 1, characterized in that The step of determining a plurality of target vehicle objects within the preset monitoring area and the driving state corresponding to each target vehicle object according to the spatiotemporal data of the vehicle trajectory at the previous moment and the spatiotemporal data of the vehicle trajectory at the current moment comprises: Determine the ID number of each vehicle object at the previous moment according to the spatiotemporal data of the vehicle trajectory at the previous moment, and determine the ID number of each vehicle object at the current moment according to the spatiotemporal data of the vehicle trajectory at the current moment; Determine a plurality of target vehicle objects according to the ID number of each vehicle object at the previous moment and the ID number of each vehicle object at the current moment; Determine the latitude and longitude information of each target vehicle object at a previous moment according to the spatiotemporal data of the vehicle trajectory at a previous moment, and determine the latitude and longitude information of each target vehicle object at a current moment according to the spatiotemporal data of the vehicle trajectory at a current moment; Determine the current travel distance of each target vehicle object based on the previous longitude and latitude information of each target vehicle object and the current longitude and latitude information of each target vehicle object, and determine the current travel speed of each target vehicle object based on the current travel distance of each target vehicle object and the capture time interval; The driving state corresponding to each target vehicle object is determined according to the current driving speed.

4. The method according to any one of claims 1 to 3, characterized in that: The step of determining the parking duration of the stationary vehicle object comprises: Determine the last moment's travel speed of the stationary vehicle object; Determining whether the driving speed at the previous moment is a stationary state; If not, determining the capture time at the previous moment according to the spatiotemporal data of the vehicle trajectory at the previous moment, and determining the capture time at the current moment according to the spatiotemporal data of the vehicle trajectory at the current moment; The parking duration of the stationary vehicle object is determined according to the last snapshot time and the current snapshot time.

5. The method according to claim 4, characterized in that After the step of determining whether the driving speed at the previous moment is in a stationary state, the method further comprises: If yes, the cumulative static duration of the static vehicle object is determined through the data structure trajectory table, and the capture time at the previous moment is determined according to the spatiotemporal data of the vehicle trajectory at the previous moment, and the capture time at the current moment is determined according to the spatiotemporal data of the vehicle trajectory at the current moment; The parking duration of the stationary vehicle object is determined according to the current snapshot time, the previous snapshot time and the accumulated static duration.

6. The method according to claim 5, characterized in that The step of determining the abnormal parking event type corresponding to the stationary vehicle object according to the parking duration includes: When the parking duration is longer than a preset time threshold, extracting relevant information of the stationary vehicle object from the spatiotemporal data of the vehicle trajectory at the current moment; Generate an abnormal parking event according to the parking duration, the relevant information of the stationary vehicle object and the intersection number of the current road; Analyzing the abnormal parking event to determine associated information of the stationary vehicle object; The type of the abnormal parking event is determined according to the association information between the abnormal parking event and the stationary vehicle object.

7. The method according to claim 6, characterized in that The step of performing abnormal parking processing on the stationary vehicle object based on the abnormal parking event type comprises: generating event data according to the abnormal parking event, the associated information of the stationary vehicle object, and the type of the abnormal parking event; Determine historical trajectory data of the stationary vehicle object according to the event data, and fit an abnormal parking simulation video of the stationary vehicle object based on the historical trajectory data; Determining an abnormal parking event level according to the abnormal parking event type, and determining a corresponding abnormal event processing rule according to the abnormal parking event level; Based on the abnormal parking simulation video, abnormal parking processing is performed on the stationary vehicle object according to the abnormal event processing rule.

8. A vehicle abnormal parking processing system, characterized in that: The vehicle abnormal parking processing system comprises: A fitting module is used to obtain the electric police checkpoint data and radar data within the preset monitoring area of ​​the current road in real time, and fit the electric police checkpoint data and the radar data to obtain the spatiotemporal data of the vehicle trajectory at the current moment; A determination module, used to determine a plurality of target vehicle objects within the preset monitoring area and a driving state corresponding to each target vehicle object according to the spatiotemporal data of the vehicle trajectory at the previous moment and the spatiotemporal data of the vehicle trajectory at the current moment; A calculation module, configured to select a stationary vehicle object corresponding to the stationary driving state from a plurality of target vehicle objects, and determine a parking duration of the stationary vehicle object; A processing module is used to determine the abnormal parking event type corresponding to the stationary vehicle object according to the parking duration, and perform abnormal parking processing on the stationary vehicle object based on the abnormal parking event type.

9. A vehicle abnormal parking processing device, characterized in that: The device comprises: a memory, a processor, and a vehicle abnormal parking processing program stored in the memory and executable on the processor, wherein the vehicle abnormal parking processing program is configured to implement the steps of the vehicle abnormal parking processing method according to any one of claims 1 to 7.

10. A storage medium, characterized in that: The storage medium stores a vehicle abnormal parking processing program, and when the vehicle abnormal parking processing program is executed by the processor, the steps of the vehicle abnormal parking processing method according to any one of claims 1 to 7 are implemented.

Images