Method for portraying suspected fake-licensed vehicle based on ETC (Electronic Toll Collection) portal data

Abstract

The invention discloses a suspected fake-licensed vehicle portraying method based on ETC (Electronic Toll Collection) portal data, which belongs to the technical field of expressway traffic management and comprises the following steps of: S1, extracting a main data field from a database generated by an ETC portal; s2, according to the time sequence of the recorded data of the vehicles with the same license plate, a track recording sequence of the vehicles is formed, and then the track recording sequence is judged to be in an abnormal sequence condition or a normal sequence condition according to the upstream and downstream portal association relation; and S3, distinguishing three types of equipment failure, normal vehicles and suspected fake-licensed vehicles to form a suspected fake-licensed vehicle portrait. According to the method, highway traffic big data is fully mined, the method is applied to illegal fake-licensed vehicle identification and portrait, the effectiveness of mass data is realized, the initiative of traffic management and monitoring can be improved, and the limitation of traffic police routine inspection and the labor cost are reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of highway traffic management, and in particular to a method for profiling suspected fake-license plate vehicles based on ETC toll gantry data. Background Art

[0003] Therefore, it has become an important task for highway traffic management to identify vehicles suspected of having duplicate license plates or being cloned based on existing equipment, so as to proactively and early discover and characterize and label these special vehicles. The ETC toll gates set up by highways to collect vehicle fees include data collection points at toll gates and exits as well as mid-way sections. The collected data can serve as a high-precision data foundation covering time, space and vehicle information, providing effective support for the analysis and research of vehicle operation trajectories. By analyzing the abnormalities of vehicle trajectory record data, a vehicle profile of suspected cloned vehicles can be constructed.

[0004] At present, the monitoring of vehicles with fake license plates mainly relies on manual discovery of anomalies, while active and automatic data monitoring has not been fully studied. The problems faced are: First, the average daily amount of data generated by highway toll gantries is huge and complex, and the advantages of big data have not been effectively utilized and served in the work of profiling suspected fake license plate vehicles through data processing and analysis. Second, how to effectively identify the suspected fake license plate features in the ETC trajectory records under the same vehicle license plate requires a detailed establishment of an algorithm process. Therefore, in view of the limitations of current research, the present invention proposes a suspected fake license plate vehicle profiling method based on ETC toll gantry data, which uses the special ETC trajectory record features caused by fake license plate and cloned vehicles with a certain travel time intersection to automatically identify suspected fake license plate vehicles to the greatest extent. Summary of the invention

[0005] The purpose of the present invention is to provide a method for profiling suspected fake-license plate vehicles based on ETC toll gantry data, which can improve the initiative of traffic management and monitoring, provide traffic management departments with automated screening of illegal vehicles, provide strong support for the construction and optimization of intelligent transportation systems, and promote the development of intelligent transportation systems towards automatic monitoring and active control.

[0006] To achieve the above-mentioned purpose, the present invention provides a method for profiling suspected fake license plate vehicles based on ETC toll gantry data, which uses the ETC toll gantry deployed on the highway as a data collection device, including the ETC gantry records at the entrances and exits of the toll station and the license plate recognition data of the manual channel, as well as the ETC gantry passage record data of the segmented billing in the intermediate section. Then, based on the ETC record information of the vehicle in the time dimension, a vehicle trajectory record sequence is formed, and the trajectory record sequence is analyzed and divided into two situations: abnormal and normal upstream and downstream gantry sequences. Finally, the rationality of the trajectory order or the rationality of the spatiotemporal changes in these two situations is analyzed one by one, thereby profiling and labeling whether the vehicle is a suspected fake license plate vehicle.

[0007] Specifically, the following steps are included: Step S1, based on the ETC toll gantry deployed on the highway as a data collection device, the data includes the vehicle traffic record data of the ETC gantry at the entrance and exit of the toll station and the ETC gantry at the intermediate section, and extracts the main data fields from the database generated by the ETC toll gantry, including the vehicle billing (through the ETC toll gantry) time, the Hex value of the ETC gantry at the intermediate section (non-toll station), the vehicle license plate, the passing medium, the toll model, the recording time and Hex number value of the ETC gantry at the entrance and exit of the toll station. Take the main data fields;

[0008] Step S2, forming a trajectory record sequence of the vehicle according to the time sequence of the recorded data of the vehicle with the same license plate, and then judging the trajectory record sequence as abnormal sequence or normal sequence according to the association relationship between the upstream and downstream gantries;

[0009] Step S3: For abnormal sequence, focus on judging the rationality of the gantry sequence in its trajectory sequence; for normal sequence, focus on judging the rationality of the spatiotemporal changes between the ETC gantry at the toll station exit of the expressway during the previous trip and the ETC gantry at the toll station entrance of the expressway during the next trip. Distinguish between three types of vehicles: equipment failure, normal vehicles, and suspected fake license plate vehicles, and form a portrait of suspected fake license plate vehicles. Preferably, step S2 is specifically as follows:

[0010] Step S201: randomly obtain data of a target vehicle according to the license plate, match and fuse the license plate recognition data of the high-speed camera under the same license plate with the pure ETC radio frequency recognition data according to the vehicle license plate field, the matching standard is the approximate recording time, and form a vehicle running trajectory sequence according to the vehicle billing time;

[0011] Step S202, based on the upstream and downstream association table of the ETC toll gantry, that is, the Hex value of the downstream ETC gantry corresponding to the Hex value of the upstream ETC gantry, identify whether the Hex value information of two adjacent ETC gantries in the target vehicle operation trajectory sequence conforms to the upstream and downstream association relationship, and thus divide it into two categories: abnormal trajectory data and normal trajectory data.

[0012] Preferably, in step S201, the license plate data is identified by a high-speed camera installed on the toll gantry, and the electronic tag information of the vehicle OBU card or CPC card is obtained by the ETC radio frequency identification device; but since the recording times of different instruments have small deviations, the license plate recognition data and the electronic tag data with extremely similar recording times can be matched, and the electronic tag data shall prevail; in addition, the camera license plate recognition data generated by a vehicle using another person's license plate will also be loaded into the vehicle operation trajectory sequence under the forged license plate number in order of the data recording time.

[0013] Preferably, step S3 comprises the following steps:

[0014] Step S301, analyzing the abnormal data of the vehicle trajectory, judging the rationality standard of the ETC toll gantry sequence in the trajectory, and determining whether it is a suspected fake license plate vehicle, or whether the ETC gantry equipment is faulty;

[0015] Step S302: Analyze the normal data of the vehicle trajectory, and judge the rationality of the spatiotemporal changes between the vehicle leaving the expressway and the next time it enters the expressway, to determine whether it is a suspected fake license plate vehicle or a normal vehicle;

[0016] Step S303: Through steps S301 and S302, three types of vehicles, namely, equipment failure, normal vehicles and suspected fake license plate vehicles, are distinguished, thereby forming a portrait of the suspected fake license plate vehicle.

[0017] Preferably, step S301 is specifically as follows: step S3011, determining whether the record of the Hex value of the ETC gantry at the entrance of a toll station is updated before the record of the Hex value of the ETC gantry at the exit of a toll station appears in the trajectory sequence, if so, the vehicle is portrayed as a suspected fake license plate vehicle; if not, proceeding to step S3012;

[0018] Step S3012, determine whether the next record of the toll station exit ETC gantry Hex value in the trajectory sequence is the mid-section ETC gantry Hex value rather than the toll station entrance ETC gantry Hex value, if so, then the vehicle image is a suspected fake license plate vehicle; if not, proceed to step S3013;

[0019] Step S3013: Determine the cumulative number of upstream and downstream association errors in the trajectory sequence N errorIs it greater than the specified threshold? If so, the vehicle is portrayed as a suspected fake license plate vehicle; if not, it indicates that the gantry equipment failure caused data collection omissions.

[0020] Preferably, in step S3013, the cumulative number of upstream and downstream association errors N error The calculation method of is as follows:

[0021]

[0022] In the formula, Indicates a function that returns 1 if the condition in the brackets is true and 0 if it is false; T i Indicates the Hex value of the ETC gantry that the vehicle passes through in the trajectory sequence; U j Indicates the Hex value of the upstream ETC gantry in row j of the ETC gantry upstream and downstream association table; D j It represents the Hex value of the downstream ETC gantry in the jth row in the upstream and downstream association table of the ETC gantry; I represents the length of the vehicle trajectory sequence, that is, the total number of gantries passed; J represents the total number of rows in the upstream and downstream association table of the ETC gantry.

[0023] Preferably, step S302 is specifically as follows:

[0024] Step S3021, obtaining the shortest path distance between the position recorded by the ETC gantry at the toll station exit of the previous trip and the position recorded by the ETC gantry at the toll station entrance of the next trip on the non-highway section, and the time interval between the passing time recorded by the ETC gantry at the toll station exit of the previous trip and the passing time recorded by the ETC gantry at the toll station entrance of the next trip in the trajectory record sequence;

[0025] Step S3022: determine whether the time interval is greater than a time threshold, where the time threshold is the minimum travel time required to travel the spatial distance on the non-highway section, that is, assuming that all non-highway sections are unobstructed; if it is less than the threshold, the vehicle is portrayed as a suspected fake-license vehicle.

[0026] Preferably, in step S3022, when the vehicle is traveling on a non-highway section, the travel time interval t from the toll station exit of the previous travel trajectory to the toll station entrance of the next travel trajectory is o,e and time threshold t' o,e The calculation formula is as follows:

[0027]

[0028] Where, t o,eIndicates the time interval between the passing time recorded by the ETC gantry at the toll station exit of the previous trip and the passing time recorded by the ETC gantry at the toll station entrance of the next trip in the vehicle's historical trajectory record; represents the ETC gantry passing time of the toll station entrance e for the next trip; t 0 i Indicates the time it took to pass the ETC gantry at the toll station exit o during the previous trip; t' o,e It indicates the minimum travel time from the toll station exit o to the toll station entrance e on the non-highway section; d o,e represents the minimum path distance of the non-highway section from the toll station exit o to the toll station entrance e; v o,e represents the free-flow speed of the non-highway section from the toll station exit o to the toll station entrance e; σ is the adjustable margin of the time threshold.

[0029] Therefore, the present invention adopts the above-mentioned method for profiling suspected duplicate license plate vehicles based on ETC toll gantry data, first extracts the historical driving trajectory data of vehicles with the same license plate recorded by the ETC toll gantry, and then identifies whether the driving trajectory data has the abnormality of "upstream and downstream gantry continuity relationship", further analyzes both abnormal and normal situations, and finally generates a portrait label of the suspected duplicate license plate vehicle. This method realizes the locking of duplicate or cloned license plate vehicles with high suspicion, can improve the initiative of traffic management and monitoring, provide traffic management departments with automated screening of suspected illegal duplicate license plate vehicles, and provide strong support for the construction and optimization of intelligent transportation systems. It can reduce the limitations and labor costs of routine inspections by traffic police, and promote the development of intelligent transportation systems towards automatic monitoring and active control.

[0030] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] Figure 1 It is a flow chart of an embodiment of a method for profiling suspected fake license plate vehicles based on ETC toll gate data of the present invention;

[0032] Figure 2 It is a schematic representation of the upstream and downstream association of an ETC toll gate according to an embodiment of a method for profiling a suspected fake license plate vehicle based on ETC toll gate data of the present invention;

[0033] Figure 3 It is a schematic diagram of an example of vehicle operation trajectory recording with potential problems in an embodiment of a method for profiling suspected fake-license-plate vehicles based on ETC toll gantry data of the present invention. DETAILED DESCRIPTION

[0034] The technical solution of the present invention is further described below through the accompanying drawings and embodiments.

[0035] Unless otherwise defined, technical or scientific terms used in the present invention shall have the common meanings understood by one having ordinary skills in the field to which the present invention belongs.

[0036] Embodiment 1

[0037] like Figure 1 As shown, the present invention provides a method for profiling suspected fake license plate vehicles based on ETC toll gantry data, comprising the following steps:

[0038] Step S1, basic data extraction, based on the ETC toll gates deployed on the highway as data collection devices, the data includes the vehicle traffic record data of the ETC gates at the entrances and exits of the toll station and the ETC gates in the middle section, and extracts the following main data fields, vehicle billing (through the ETC toll gate) time, the Hex value of the ETC gate in the middle section (non-toll station), vehicle license plate, traffic medium, toll vehicle model, and the recording time and Hex number value of the ETC gates at the entrances and exits of the toll station. As shown in Table 1:

[0039] Table 1 Main fields of ETC toll gate data

[0040] Field Name Field meaning trans_time Vehicle charging (through ETC toll gate) time gantry_hex Hex value of ETC gantry in the middle section vehicle_plate vehicle license media_type Passing medium (OBU, CPC) en_time ETC gantry recording time at toll station entrance en_toll_station_hex Hex value of ETC gantry at toll station entrance ex_time ETC gantry recording time at toll station exit ex_toll_station_hex Hex value of ETC gantry at toll station exit vehicle_type Toll vehicle type identification

[0041] Step S2: According to the time sequence of the recorded data of the vehicle with the same license plate, a trajectory record sequence of the vehicle is formed, and then the trajectory record sequence is judged as abnormal sequence or normal sequence according to the correlation relationship between the upstream and downstream gantries.

[0042] Step S2 is specifically as follows:

[0043] Step S201, randomly obtain data of a target vehicle according to the license plate, match and fuse the license plate recognition data of the high-speed camera under the same license plate with the pure ETC radio frequency identification data according to the vehicle license plate field, the matching standard is the approximate recording time, and form a vehicle operation trajectory sequence according to the vehicle billing time; some toll gantries are equipped with high-speed cameras and ETC radio frequency identification devices at the same time, the high-speed cameras are used for license plate recognition data, and the ETC radio frequency identification device is used to obtain the electronic tag information of the vehicle OBU card or CPC card.

[0044] However, since the recording times of different instruments have small deviations, the license plate recognition data and electronic tag data with extremely similar recording times can be matched, and the electronic tag data shall prevail. In addition, the camera license plate recognition data generated by vehicles with other people's license plates will also be loaded into the vehicle running track sequence under the forged license plate number in the order of data recording time.

[0045] Step S202: According to the upstream and downstream association table of ETC toll gantries, such as Figure 2 shown, identify whether the running track sequence of the target vehicle conforms to the upstream and downstream association relationship recorded by the Hex values of two adjacent ETC toll gantries, and thus divide it into two cases: vehicle track abnormal data and vehicle track normal data.

[0046] Step S3: For the case of abnormal sequence, focus on judging the rationality standard of the gantry order in its track sequence; for the case of normal sequence, focus on judging the rationality standard of the spatio-temporal change between the ETC gantry at the toll station exit where the vehicle left the highway during the previous trip and the ETC gantry at the toll station entrance where the vehicle entered the highway during the next trip; distinguish among three types: equipment failure, normal vehicle, and suspected license plate cloning vehicle, and form a portrait of the suspected license plate cloning vehicle.

[0047] It includes the following steps:

[0048] 1) Analyze the vehicle track abnormal data, judge the rationality standard of the ETC toll gantry order in its track, and obtain whether it is a suspected license plate cloning vehicle or an ETC gantry equipment failure; specifically:

[0049] First, identify the vehicle that directly uses a license plate to enter the highway at the toll station entrance, and judge whether the record of the Hex value of the ETC gantry at a certain toll station exit has been updated before the record of the Hex value of the ETC gantry at a certain toll station entrance appears in the track sequence, so as to identify the vehicle that enters the highway using a license plate. If so, portrait the vehicle as a suspected license plate cloning vehicle. For example Figure 3 as shown in Example (1) in, assume that the in-transit running track record of the vehicle with license plate "Yue A1XXXX" does not leave the highway after entering from the ETC gantry 4A0001 (entrance) at the toll station entrance, but a new record of the ETC gantry at the toll station entrance 4A0023 (entrance) appears. If not, continue to identify the situation of the vehicle that uses a license plate after entering the toll station entrance, and judge whether the next record of the Hex value of the ETC gantry at the toll station exit in the track sequence is the Hex value of the ETC gantry in the middle section, rather than the Hex value of the ETC gantry at the toll station entrance. If so, it means that there is a situation where the vehicle uses someone else's license plate to drive after entering the highway, and portrait the vehicle as a suspected license plate cloning vehicle. For example Figure 3 as shown in Example (2) in, assume that after the in-transit running track record of the vehicle with license plate "Yue A1XXXX" leaves the highway from the ETC gantry 4A0011 (exit) at the toll station exit, the next record that appears belongs to the ETC gantry 4A0026 in the middle section that is not the toll station entrance.

[0050] If not, continue to identify the situation where the license plate is applied after entering the toll station entrance and the vehicle is on the road at the same time as the vehicle with the forged license plate, and determine whether the cumulative number of upstream and downstream association errors in the trajectory sequence is greater than the specified threshold. If so, portrait the vehicle as a suspected vehicle with a forged license plate. For example Figure 3 As shown in Example (3), "Yue A2XXXX" travels with the forged license plate of "Yue A1XXXX" on the road sections with a gray background. At this time, the running trajectory data of the license plate "Yue A1XXXX" will merge the gantry information marked with a gray background in chronological order, and it is identified because the cumulative number of times that does not conform to the upstream and downstream association relationship is large; if not, it indicates that the data collection is missing due to the failure of the gantry equipment.

[0051] 2) Analyze the normal data of the vehicle trajectory, and judge according to the rationality standard of the spatio-temporal change when the vehicle leaves the expressway and enters the expressway next time, and find out whether it is a suspected vehicle with a forged license plate or a normal vehicle. Specifically:

[0052] For the situation where there is a vehicle with a forged license plate and the vehicle with the original license plate leaving and entering the expressway one after another, first obtain the shortest path distance on the non-expressway section between the position of the ETC gantry record at the exit of the toll station in the previous trip and the position of the ETC gantry record at the entrance of the toll station in the next trip in the trajectory record, and the time interval between the passing time of the ETC gantry record at the exit of the toll station in the previous trip and the passing time of the ETC gantry record at the entrance of the toll station in the next trip. Then judge whether the time interval is greater than the time threshold, and the time threshold is the minimum passing time required for the spatial distance traveled on the non-expressway section, that is, assuming that each non-expressway section is unobstructed. If the time interval is less than the threshold, portrait the vehicle as a suspected vehicle with a forged license plate. For example Figure 3 As shown in Example (4), the non-expressway section distance between the exit 4A0011 (exit) of the toll station in the previous trip and the entrance 4A0040 (entrance) of the toll station in the next trip requires at least 30 minutes to travel under completely unobstructed conditions, that is, the time threshold is 30 minutes. However, the time interval of the trajectory sequence is only 10 minutes, and it is identified as a suspected vehicle with a forged license plate because it significantly violates the convention.

[0053] Step S303: Distinguish three types of equipment failures, normal vehicles, and suspected vehicles with forged license plates through Step S301 and Step S302, and thus form a portrait of suspected vehicles with forged license plates.

[0054] It should be noted that the content not elaborated in detail in the present invention is all prior art and is well known to those skilled in the art.

[0055] Therefore, the present invention adopts the above-mentioned method of profiling suspected fake-license plate vehicles based on ETC toll gantry data. This method can improve the initiative of traffic management and monitoring, provide traffic management departments with automated screening of illegal vehicles, provide strong support for the construction and optimization of intelligent transportation systems, and promote the development of intelligent transportation systems towards automatic monitoring and active control.

[0056] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that they can still modify or replace the technical solution of the present invention with equivalents, and these modifications or equivalent replacements cannot cause the modified technical solution to deviate from the spirit and scope of the technical solution of the present invention.

Claims

1. A method for profiling suspected fake license plate vehicles based on ETC toll gate data, characterized in that: The following steps are involved: Step S1, based on the ETC toll gantry deployed on the highway as a data collection device, extract the main data fields from the database generated by the ETC toll gantry, including vehicle billing time, Hex value of the ETC gantry of the intermediate section, vehicle license plate, passing medium, toll vehicle type, recording time and Hex number value of the ETC gantry at the entrance and exit of the toll station; Step S2, forming a trajectory record sequence of the vehicle according to the time sequence of the recorded data of the vehicle with the same license plate, and then judging the trajectory record sequence as abnormal sequence or normal sequence according to the association relationship between the upstream and downstream gantries; Step S3, for abnormal sequence, focus on judging the rationality standard of the gantry order in its trajectory sequence; for normal sequence, focus on judging the rationality standard of the spatiotemporal changes between the ETC gantry at the toll station exit leaving the expressway during the previous trip and the ETC gantry at the toll station entrance entering the expressway during the next trip; distinguish between three types of vehicles: equipment failure, normal vehicles and suspected fake license plate vehicles, and form a portrait of the suspected fake license plate vehicles.

2. According to claim 1, a method for profiling suspected fake license plate vehicles based on ETC toll gate data is characterized in that: Step S2 is specifically as follows: Step S201: randomly obtain data of a target vehicle according to the license plate, match and fuse the license plate recognition data of the high-speed camera under the same license plate with the pure ETC radio frequency recognition data according to the vehicle license plate field, the matching standard is the approximate recording time, and form a vehicle running trajectory sequence according to the vehicle billing time; Step S202, based on the upstream and downstream association table of the ETC toll gantry, that is, the Hex value of the downstream ETC gantry corresponding to the Hex value of the upstream ETC gantry, identify whether the Hex value information of two adjacent ETC gantries in the target vehicle operation trajectory sequence conforms to the upstream and downstream association relationship, and thus divide it into two categories: abnormal trajectory data and normal trajectory data.

3. According to claim 2, a method for profiling suspected fake license plate vehicles based on ETC toll gate data is characterized in that: In step S201, the license plate data is recognized by the high-speed camera installed on the toll gantry, and the electronic tag information of the vehicle OBU card or CPC card is obtained through the ETC radio frequency identification device; the camera license plate recognition data generated by the vehicle using another person's license plate will also be loaded into the vehicle operation trajectory sequence under the forged license plate number in the order of data recording time.

4. According to claim 3, a method for profiling suspected fake license plate vehicles based on ETC toll gate data is characterized in that: Step S3 includes the following steps: Step S301, analyzing the abnormal data of the vehicle trajectory, judging the rationality standard of the ETC toll gantry sequence in the trajectory, and determining whether it is a suspected fake license plate vehicle, or whether the ETC gantry equipment is faulty; Step S302: Analyze the normal data of the vehicle trajectory, and judge the rationality of the spatiotemporal changes between the vehicle leaving the expressway and the next time it enters the expressway, to determine whether it is a suspected fake license plate vehicle or a normal vehicle; Step S303: Through steps S301 and S302, three types of vehicles, namely, ETC gantry equipment failure, normal vehicles and suspected fake-license vehicles, are distinguished, thereby forming a portrait of the suspected fake-license vehicle.

5. According to claim 4, a method for profiling suspected fake license plate vehicles based on ETC toll gate data is characterized in that: Step S301 is specifically as follows: Step S3011, determining whether the record of the Hex value of the ETC gantry at a toll station entrance is updated before the record of the Hex value of the ETC gantry at a toll station exit is not updated in the trajectory sequence, if so, the vehicle image is regarded as a suspected fake license plate vehicle; if not, proceeding to step S3012; Step S3012, determine whether the next record of the toll station exit ETC gantry Hex value in the trajectory sequence is the mid-section ETC gantry Hex value rather than the toll station entrance ETC gantry Hex value, if so, then the vehicle image is a suspected fake license plate vehicle; if not, proceed to step S3013; Step S3013: Determine the cumulative number of upstream and downstream association errors in the trajectory sequence N error Is it greater than the specified threshold? If so, the vehicle is portrayed as a suspected fake license plate vehicle; if not, it indicates that the ETC gantry equipment failure caused data collection omissions.

6. According to claim 5, a method for profiling suspected fake license plate vehicles based on ETC toll gate data is characterized in that: In step S3013, the cumulative number of upstream and downstream association errors M error The calculation method of is as follows: In the formula, Indicates a function that returns 1 if the condition in the brackets is true and 0 if it is false; T i Indicates the Hex value of the ETC gantry that the vehicle passes through in the trajectory sequence; U j Indicates the Hex value of the upstream ETC gantry in row j of the ETC gantry upstream and downstream association table; D j It represents the Hex value of the downstream ETC gantry in the jth row in the upstream and downstream association table of the ETC gantry; I represents the length of the vehicle trajectory sequence, that is, the total number of gantries passed; J represents the total number of rows in the upstream and downstream association table of the ETC gantry.

7. According to claim 6, a method for profiling suspected fake license plate vehicles based on ETC toll gate data is characterized in that: Step S302 is specifically as follows: Step S3021, obtaining the shortest path distance between the position recorded by the ETC gantry at the toll station exit of the previous trip and the position recorded by the ETC gantry at the toll station entrance of the next trip on the non-highway section, and the time interval between the passing time recorded by the ETC gantry at the toll station exit of the previous trip and the passing time recorded by the ETC gantry at the toll station entrance of the next trip in the trajectory record sequence; Step S3022: determine whether the time interval is greater than a time threshold, where the time threshold is the minimum travel time required to travel the spatial distance on the non-highway section, that is, assuming that all non-highway sections are unobstructed; if it is less than the threshold, the vehicle is portrayed as a suspected fake-license vehicle.

8. The method for profiling suspected fake license plate vehicles based on ETC toll gate data according to claim 7 is characterized in that: In step S3022, the vehicle travels on a non-highway section, and the travel time interval t from the toll station exit of the previous travel trajectory to the toll station entrance of the next travel trajectory o,e and time threshold t' o,e The calculation formula is as follows: t o,e =t e i+1 -t o i ; t' o,e =d o,e / v o,e +σ; Where, t o,e It indicates the time interval between the passing time recorded by the ETC gantry at the toll station exit of the previous trip and the passing time recorded by the ETC gantry at the toll station entrance of the next trip in the history track record of the vehicle; t e i+1 Indicates the time of passing the ETC gantry at the toll station entrance e of the next trip; t0 i Indicates the ETC gantry passing time of the toll station exit o during the previous trip; t' o,e It indicates the minimum travel time from the toll station exit o to the toll station entrance e on the non-highway section; d o,e represents the minimum path distance of the non-highway section from the toll station exit o to the toll station entrance e; v o,e represents the free-flow speed of the non-highway section from the toll station exit o to the toll station entrance e; σ is the adjustable margin of the time threshold.

Images