CN115601974A - Method and device for determining fake-licensed vehicles on expressway - Google Patents
Method and device for determining fake-licensed vehicles on expressway Download PDFInfo
- Publication number
- CN115601974A CN115601974A CN202211200281.6A CN202211200281A CN115601974A CN 115601974 A CN115601974 A CN 115601974A CN 202211200281 A CN202211200281 A CN 202211200281A CN 115601974 A CN115601974 A CN 115601974A
- Authority
- CN
- China
- Prior art keywords
- time
- target
- license plate
- portal
- identification
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 42
- 230000002159 abnormal effect Effects 0.000 claims abstract description 60
- 238000004364 calculation method Methods 0.000 claims abstract description 18
- 239000011159 matrix material Substances 0.000 claims description 11
- 230000002123 temporal effect Effects 0.000 claims description 8
- 230000014509 gene expression Effects 0.000 claims description 5
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 4
- 238000001514 detection method Methods 0.000 abstract description 4
- 230000008569 process Effects 0.000 description 12
- 238000004891 communication Methods 0.000 description 7
- 230000006870 function Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 238000013480 data collection Methods 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 230000008034 disappearance Effects 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 230000006855 networking Effects 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/017—Detecting movement of traffic to be counted or controlled identifying vehicles
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0125—Traffic data processing
- G08G1/0129—Traffic data processing for creating historical data or processing based on historical data
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Traffic Control Systems (AREA)
Abstract
The application discloses a method and a device for determining a fake-licensed vehicle on an expressway, wherein a first target vehicle is determined by acquiring an entrance data set and a portal flow set, a second target vehicle is determined through a time window, a portal identification license plate of the second target vehicle in a target time period is obtained, whether the portal identification license plate meets a preset rule is judged, if yes, the fake-licensed vehicle is determined, the first target vehicle is determined through the entrance data set and the portal flow set, the second target vehicle is determined from the first target vehicle through the time window, the portal flow set is divided through a passing mark of the second target vehicle, the portal identification license plate of the second target vehicle in the target time period is determined, the abnormal license plate is determined according to the preset rule, the fake-licensed vehicle is determined through calculation, and compared with the prior art, the fake-licensed vehicle is determined through the entrance data set and the portal flow set, the accuracy of detecting the fake-licensed vehicle is improved, and the detection efficiency is further improved.
Description
Technical Field
The application relates to the field of vehicle identification, in particular to a method and a device for determining a fake-licensed vehicle on a highway.
Background
With the development of economy, expressways in China are continuously built, and the provincial networking and trans-provincial networking charging of expressways is widely implemented. Meanwhile, with the continuous expansion of highway networks, some illegal vehicle owners can evade high-speed tolls by using a means of changing license plates under the driving of economic benefits.
The existing method for detecting the fake-licensed vehicles mainly extracts and compares the characteristics of the shot vehicle pictures to judge whether the fake-licensed vehicles exist or not, and because the conditions of different license plates of the same vehicle type and different license plates exist and the vehicles can be disguised, the accuracy rate of detecting the fake-licensed vehicles through the pictures is low, the detection efficiency is not high, and the problem that people pay attention to how to improve the efficiency of detecting the fake-licensed vehicles is solved.
Disclosure of Invention
In view of this, the present application provides a method and an apparatus for determining a fake-licensed vehicle on an expressway, which are used to improve the detection efficiency of the fake-licensed vehicle.
In order to achieve the above object, the proposed solution is as follows:
a method of highway fake-licensed vehicle determination, comprising:
the method comprises the steps that an entrance and exit data set D1 and a portal assembly set D2 are obtained, the entrance and exit data set D1 comprises a passing identification, an entrance license plate, an exit license plate, entrance time and exit time of each vehicle, and the portal assembly set D2 comprises the passing identification, a portal identification license plate and portal identification time of each vehicle;
determining first target vehicles according to the entrance license plate, the exit license plate and the portal identification license plate of the same pass identifier, and forming a first target set C1, wherein the first target set C1 comprises the pass identifier, the entrance time, the exit time and the portal identification time of the first target vehicles;
determining the passing identification of a second target vehicle by using the entry time, the exit time, the portal identification time and the time window of the first target set C1 and forming a second target set C2;
according to the passing identification in the second target set C2, the portal flow set D2 is divided to obtain portal recognition license plates of second target vehicles in a target time period and form a third target set C3;
judging whether the portal identification license plate in the third target set C3 meets a preset rule or not;
if yes, determining the second target vehicle as an abnormal license plate and forming a fourth target set C4 by each abnormal license plate;
and calculating and determining a fake-licensed vehicle by using the fourth target set C4.
Optionally, the determining a first target vehicle and forming a first target set C1 according to the entrance license plate, the exit license plate and the portal identification license plate of the same passage identifier includes:
extracting feature matrixes of the entrance and exit data set D1 and the portal flow set D2 according to the pass identification;
determining whether the number of the portals through which vehicles passing through the entrance license plate, the exit license plate and the portal identification license plate is consistent is smaller than a first threshold value within the entrance time and the exit time range;
if yes, determining the vehicle as a first target vehicle, and forming a first target set C1 by the passing identification, the entrance time, the exit time and the portal identification time of the first target vehicle.
Optionally, determining a first target vehicle and forming a first target set C1 according to the entrance license plate, the exit license plate and the portal identification license plate of the same pass identifier includes:
determining the first target set C1 using the following relation:
D1 vm =[D1 v1 D1 v2 … D1 vm ],D2 vn =[D2 v1 D2 v2 … D2 vn ]
where T1 represents an entrance time, T4 represents an exit time, D1vm represents a feature matrix of the entrance data set D1, D2vn represents a feature matrix of the portal flow set D2, T represents a time between T1 and T4, and X1 represents a first threshold.
Optionally, determining a passing identifier of a second target vehicle by using the entry time, the exit time, the portal identification time, and the time window of the first target set C1, and forming a second target set C2, includes:
constructing time sequence historical characteristics of a time window by using the entry time, the exit time and the portal identification time of the first target set C1;
determining a second threshold value of the time window by using the time series historical characteristics;
calculating the difference value of the gantry identification time of the first target set C1;
selecting the first target vehicle with the difference value larger than the second threshold value as a second target vehicle;
and forming a second target set C2 by the pass identifications of the second target vehicles.
Optionally, determining time characteristic values by using the entry time, the exit time, the gantry recognition time, and the time window of the first target set C1, and forming a second target set C2 by using the time characteristic values, includes:
determining the second target set C2 using the following relationship:
wherein ,represents the time of recognition of the previous portal,representing the latter gantry identification time, t2 representing the first temporal signature sequence, t3 representing the second temporal signature sequence, and x2 representing the second threshold.
Optionally, judging whether the portal identification license plate in the third target set C3 meets a preset rule includes:
and judging whether the portal identification license plate in the third target set C3 is not in the time period from the entrance time to the first portal identification time and the time period from the second portal identification time to the next entrance time, and is not in the entrance and exit data set D1.
Optionally, determining the second target vehicle as an abnormal license plate and grouping each abnormal license plate into a fourth target set C4 includes:
determining each abnormal license plate and forming the fourth target set C4 by using the following relational expression:
wherein ,Fv Representing a license plate, C3 representing a third target set, C2 representing a second target set, D1 representing an entrance data set, T n Representing the nth temporal characteristic value.
Optionally, using the fourth target set C4, calculating and determining a fake-licensed vehicle includes:
calculating a result set of support degree, confidence degree and promotion degree of each abnormal license plate by using the fourth target set C4;
and determining the fake-licensed vehicles according to the result set of the support degree, the confidence degree and the promotion degree of each abnormal license plate.
Optionally, the calculating a result set of the support degree, the confidence degree, and the promotion degree of each abnormal license plate includes:
calculating the result set of support degree, confidence degree and promotion degree of each abnormal license plate according to the following relational expression
Wherein support represents support degree, conf represents confidence degree, and lift represents liftResult set in liter degree, L sample Indicates the number of items of the fourth target collection C4, count indicates the number, C1 Vm Indicating a normal license plate, C4 Vn Indicating an abnormal license plate.
An expressway fake-licensed vehicle determination apparatus comprising:
the system comprises a data acquisition unit, a portal data collection unit and a portal flow collection unit, wherein the data acquisition unit is used for acquiring a portal data collection D1 and a portal flow collection D2, the portal data collection D1 comprises a passing identifier, an entrance license plate, an exit license plate, entrance time and exit time of each vehicle, and the portal flow collection D2 comprises a passing identifier, a portal identification license plate and portal identification time of each vehicle;
a first target set determining unit, configured to determine first target vehicles according to the entry license plate, the exit license plate, and the portal identification license plate of the same pass identifier, and form a first target set C1, where the first target set C1 includes the pass identifier, the entry time, the exit time, and the portal identification time of the first target vehicle;
the second target set determining unit is used for determining the passing identification of a second target vehicle by using the entrance time, the exit time, the portal identification time and the time window of the first target set C1 and forming a second target set C2;
a third target set determining unit, configured to segment the portal running water set D2 according to the passage identifier in the second target set C2, obtain portal identification license plates of second target vehicles in a target time period, and form a third target set C3;
the rule judging unit is used for judging whether the portal identification license plate in the third target set C3 meets a preset rule or not;
a fourth target set determining unit, configured to determine, after the rule determining unit is executed, if yes, the second target vehicle as an abnormal license plate and form each abnormal license plate into a fourth target set C4;
and the calculation and determination unit is used for calculating and determining the fake-licensed vehicles by utilizing the fourth target set C4.
According to the technical scheme, the method and the device for determining the fake-licensed vehicles on the expressway are characterized in that a first target vehicle is determined through an entrance data set and a portal flow set, a second target vehicle is determined from the first target vehicle through a time window, the portal flow set is divided through a passing identifier of the second target vehicle, portal identification license plates of the second target vehicle in a target time period are determined, abnormal license plates are determined from the portal identification license plates in the target time periods according to preset rules, and the fake-licensed vehicles are determined by calculating related numerical values of the abnormal license plates.
Drawings
FIG. 1 is a flow chart of a method for determining a fake-licensed vehicle for a highway according to an embodiment of the present application;
fig. 2 is a schematic view of an application scenario of a method for determining a fake-licensed vehicle on an expressway according to an embodiment of the present application;
FIG. 3 is a schematic structural diagram of an expressway fake-licensed vehicle determination apparatus according to an embodiment of the present application;
fig. 4 is a block diagram of a hardware structure of an expressway fake-licensed vehicle determination apparatus disclosed in an embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
Fig. 1 is a method for determining a highway fake-licensed vehicle according to an embodiment of the present application, where the method may include the following steps:
and S100, acquiring an entrance data set D1 and a portal pipelining set D2.
Specifically, the entrance and exit data set D1 may include a passage identifier, an entrance license plate, an exit license plate, entrance time, and exit time of each vehicle, the portal flow set D2 may include a passage identifier, a portal recognition license plate, and portal recognition time of each vehicle, and the entrance and exit data set D1 and the portal flow set D2 may be acquired through a data interface or an electronic device having a data transmission function.
And S110, determining a first target vehicle according to the entrance license plate, the exit license plate and the portal identification license plate of the same pass identifier, and forming a first target set C1.
Specifically, the first target set C1 may include a passage identifier, entrance time, exit time, and portal identification time of the first target vehicle, and may be determined by locking the passage data information of the same vehicle from an entrance license plate, an exit license plate, and a portal identification license plate, such as the entrance data set D1 and the portal assembly data set D2, through the same passage identifier, and forming the first target set C1.
And step S120, determining the passing identification of a second target vehicle by using the entrance time, the exit time, the portal identification time and the time window of the first target set C1, and forming a second target set C2.
Specifically, the second target vehicle may be determined from the first target set C1 as needed by using the entry time, the exit time, and the gantry recognition time of the first target set C1, and the passing identifier of the second target vehicle may be formed into the second target set C2.
Step S130, according to the passing identification in the second target set C2, the portal flow set D2 is divided, portal identification license plates of second target vehicles in a target time period are obtained, and a third target set C3 is formed.
Specifically, the portal flow set D2 includes a passage identifier, a portal identification license plate, and a portal identification time of each vehicle, so that the portal identification license plate and the portal identification time of the second target vehicle can be determined according to the passage identifier in the second target set C2, and the portal identification license plate of the second target vehicle in the target time period can be selected according to the portal identification time of the second target vehicle to form a third target set C3.
Step S140, judging whether the portal identification license plate in the third target set C3 accords with a preset rule or not.
Specifically, the preset rule can be set according to the requirement, and whether the license plate meets the preset rule or not can be identified by judging the portal frames in the third target set C3.
Step S150, the second target vehicle is determined to be an abnormal license plate, and each abnormal license plate is formed into a fourth target set C4.
Specifically, when a second target vehicle in the target time period meets a preset rule, the second target vehicle may be determined as an abnormal license plate, and the abnormal license plates are combined into a fourth target set C4.
And step S160, calculating and determining the fake-licensed vehicle by using the fourth target set C4.
In particular, the fake-licensed vehicle may be determined by calculating the correlation data for the second target vehicle in the fourth target set C4.
In the embodiment of the application, a first target vehicle is determined through an entrance data set and a portal flow set, a second target vehicle is determined from the first target vehicle through a time window, the portal flow set is divided through passing identification of the second target vehicle, a portal identification license plate of the second target vehicle in a target time period is determined, an abnormal license plate is determined from the portal identification license plates in the target time periods according to preset rules, a fake-licensed vehicle is determined through calculating related numerical values of the abnormal license plate, compared with the image feature extraction comparison in the prior art, the accuracy of detecting the fake-licensed vehicle can be improved through data analysis calculation of the entrance data set and the portal flow set, and the detection efficiency is further improved.
In some embodiments of the present application, the process of determining the first target vehicle and forming the first target set C1 according to the entrance license plate, the exit license plate and the portal identification license plate of the same passing identifier in step S110 is further described below, and the process may include the following steps:
and S111, extracting feature matrixes of the entrance and exit data set D1 and the portal flow set D2 according to the passage identification.
Specifically, license plate features in the entry data set D1 can be extracted through the pass identification to serve as a feature matrix, and license plate features in the portal flow set D2 can be extracted through the pass identification to serve as a feature matrix.
And step S112, determining whether the number of the door frames, through which the vehicles with the entrance license plate, the exit license plate and the door frame identification license plate consistent with each other pass, is smaller than a first threshold value within the entrance time and the exit time range.
Specifically, the route range of the vehicle can be determined through the time range of the entrance time and the exit time, the license plate is identified through the entrance license plate, the exit license plate and the door frames in the route, the running route of the vehicle is determined, whether the license plate is changed or not in the running process of the vehicle can be judged through the number of the door frames set in the running route, namely, whether the number of the door frames, through which the vehicle with the consistent entrance license plate, the exit license plate and the door frame identification license plate passes, is smaller than a first threshold value or not in the range of the entrance time and the exit time is determined, and the first threshold value can be the number of the door frames set in the running route.
Step S113, if yes, determining the vehicle as a first target vehicle, and forming a first target set C1 by the passing identification, the entrance time, the exit time and the portal identification time of the first target vehicle.
Specifically, if the number of the portals through which the vehicle passes is smaller than the first threshold, the vehicle may be determined as a first target vehicle, the first target vehicle may be a suspected vehicle with a fake-licensed vehicle problem, or may be a suspected vehicle whose number of portals through which the vehicle passes is smaller than the first threshold due to a failure of the portal identification device, so that the passing identifier, the entrance time, the exit time, and the portal identification time of the first target vehicle may be combined into a first target set C1, for example, a trip should have 15 records of the number of portals, and as a result, only 3, and then 3 are smaller than 15, and the vehicle is determined as the first target vehicle.
Further, in some embodiments of the present application, the first target set C1 may be determined using the following relationship:
D1 vm =[D1 v1 D1 v2 … D1 vm ],D2 vn =[D2 v1 D2 v2 … D2 vn ]
where T1 may represent an entry time, T4 may represent an exit time, D1vm may represent a feature matrix of the entrance and exit data set D1, D2vn may represent a feature matrix of the portal flow set D2, T may represent a time between T1 and T4, and X1 may represent a first threshold.
In some embodiments of the present application, the following describes the process of determining the passing identifier of the second target vehicle and forming the second target set C2 by using the entry time, the exit time, the portal identification time and the time window of the first target set C1 in step S120, and the process may include the following steps:
and step S121, constructing time sequence historical characteristics of a time window by using the entry time, the exit time and the portal identification time of the first target set C1.
Specifically, the time window may be a sliding time window, the offset of the time window may be 1, the time series historical feature may be obtained through known time training, and the time series historical feature of the time window may be constructed by using the entry time, the exit time, and the gantry recognition time of the first target set C1.
And step S122, determining a second threshold value of the time window by using the time series historical characteristics.
Specifically, it may be determined that the normal travel time through the road segment is within a certain time range through the time-series history feature, and a second threshold may be set through the time range, that is, the second threshold of the time window may be determined by using the time-series history feature.
Step S123, calculating a difference between the gantry identification times of the first target set C1.
Specifically, the time difference between the gantries may be calculated by the gantry identification time of the first target set C1, that is, the difference between the gantry identification times of the first target set C1 may be calculated, which is shown in the following table:
Id | VehclePlate | TransTime | TransTime_new | |
1 | yue | T1 | T2 | |
2 | Yue | T2 | T3 | |
3 | Yue | T3 | T4 | |
4 | Yue C | T4 | null |
Wherein, id represents the code number of each road section, vehclePlate represents the license plate, transTime represents the previous portal identification time, and TransTime _ new represents the next portal identification time.
And step S124, selecting the first target vehicle with the difference value larger than the second threshold value as a second target vehicle.
Specifically, after the difference is obtained through calculation, the suspected vehicle, that is, the first target vehicle, may be further determined, and the first target vehicle whose difference is greater than the second threshold may be selected as the second target vehicle.
And step S125, forming a second target set C2 by the passing identifications of the second target vehicles.
Specifically, after the second target vehicle is determined, a set of pass identifiers corresponding to the second target vehicle may be made, that is, the pass identifiers of the second target vehicle form a second target set C2.
Further, in some embodiments of the present application, the second target set C2 may be determined using the following relation:
wherein ,the previous gantry recognition time can be represented,may represent a subsequent gantry identification time, t2 may represent a first time characteristic sequence, t3 may represent a second time characteristic sequence, X2 may represent a second threshold value, the first time characteristic sequence may represent that a time period between a previous gantry and a subsequent gantry, through which the vehicle is detected to pass during the abnormal time period, i.e., the driving of the vehicle during a certain road section, exceeds a previous gantry identification time during a normal driving time period, and similarly, the second time characteristic sequence may represent that a time period between a previous gantry and a subsequent gantry, through which the vehicle is detected to pass during the abnormal time period, i.e., the driving of the vehicle during a certain road section, exceeds a normal driving time periodThe latter portal identifies time.
In some embodiments of the present application, a process of determining whether the portal identification license plate in the third target set C3 meets a preset rule in step S140 is described below, where the process may include:
and judging whether the portal identification license plate in the third target set C3 is not in the time period from the entrance time to the first portal identification time and the time period from the second portal identification time to the next entrance time, and is not in the entrance and exit data set D1.
Specifically, whether the portal identification license plate in the third target set C3 is in the portal identification license plate and whether the portal identification license plate in the third target set C3 is in the gateway data set D1 at the same time may be determined by retrieving the license plates from the time period from the entry time to the first portal identification time and from the second portal identification time to the next entry time, and when the portal identification license plate in the third target set C3 is not in the time period from the entry time to the first portal identification time and is not in the gateway data set D1, it may be determined as yes, and otherwise, it may be determined as no. For example, as shown in the following table, passId is a pass identifier, vehicle is a license plate, entime is entry time t1, losttime is last door frame identification disappearance time t2, apeartime is appearance time t3, exitime is current exit time t4, and Nexttime is next trip entry time t5 of the Vehicle.
Finding the portal identification license plate appears in the time from losttime (t 2) to Apeartime (t 3), namely 2030-07-01.
Further, in some embodiments of the present application, in the step S150, the process of determining the second target vehicle as an abnormal license plate and forming each abnormal license plate into the fourth target set C4 may determine each abnormal license plate and form the fourth target set C4 by using the following relation:
wherein ,Fv Can represent a license plate, C3 can represent a third target set, C2 can represent a second target set, D1 can represent an entrance data set, T n The nth temporal characteristic value may be represented.
In some embodiments of the present application, the following describes the process of calculating and determining a fake-licensed vehicle using the fourth target set C4 in step S160, which may include the following steps:
step S161, calculating a result set of support degree, confidence degree and promotion degree of each abnormal license plate by using the fourth target set C4.
Specifically, the support degree may represent the frequency of occurrence of a certain item set, the confidence degree may represent the frequency of occurrence of an item B when an item a occurs, the enhancement degree may represent the frequency of occurrence of an item a and an item B together, but the respective frequencies of occurrence of the two items are considered at the same time, and the support degree, the confidence degree, and the enhancement degree of each abnormal license plate may be calculated by using the fourth target set C4 to form a result set.
And S162, determining the fake-licensed vehicles according to the result set of the support degree, the confidence degree and the promotion degree of each abnormal license plate.
Specifically, after the result set of the support degree, the confidence degree, and the promotion degree of the abnormal license plate is obtained, the fake-licensed vehicle may be determined according to each support degree, confidence degree, and promotion degree in the result set, for example, the fake-licensed vehicle may be determined according to a preset weight multiplied by the support degree, the confidence degree, and the promotion degree, and finally summed, ranked according to the sum, and a vehicle within a preset ranking range is selected as the fake-licensed vehicle. Examples are shown in the following table:
PassId | normal license plate | Abnormal license plate |
01 | Guangdong A1 | Guangdong A2, guangdong A3, guangdong B2, guangdong C3 |
02 | Guangdong A1 | Yue A3, yue C4 |
03 | Guangdong A1 | Yue A3, yue C5 |
04 | Guangdong A1 | Yue B3, yue A5 |
05 | Guangdong B1 | Yue B2, yue A4 |
License plate association | Degree of support | Confidence level | Degree of lifting |
Guangdong A1 |
3/5 | 3/4 | 5/4 |
And carrying out normalization processing on the abnormal license plate, and carrying out association rule algorithm calculation on the data item set so as to obtain a support degree, a confidence degree and a promotion degree result set of the vehicle and the abnormal license plate, wherein the correlation can be determined according to the promotion degree, the promotion degree is greater than 1, which indicates that the positive correlation is stronger, the promotion degree is less than 1, which indicates that the negative correlation is higher, and the promotion degree =1, which indicates that no correlation exists, namely, the correlation is mutually independent.
Further, the support degree, the confidence degree and the promotion degree result set of each abnormal license plate can be calculated by using the following relational expression:
wherein support can represent support degree, conf can represent confidence degree, lift can represent result set of lifting degree, L sample May represent the number of items of the fourth target collection C4, and the Count may represent the number, C1 Vm Can indicate a normal license plate, c4 Vn An abnormal license plate may be indicated.
An application scenario of an alternative method for determining a fake-licensed vehicle on a highway is described below, and as shown in fig. 2, the flow steps may be as follows:
obtaining entrance and exit data D1, portal identification data D2 and portal transaction data D3;
acquiring a portal identification missing data set C1;
based on a time series sliding window algorithm and autocorrelation characteristic calculation, acquiring vehicle entrance and exit time, card identification disappearance/appearance time and next entrance time as a set C2;
a card identification data set C3 in the missing time;
the external association set D1 acquires abnormal license plate data C4;
obtaining the support degree, confidence degree and promotion degree of the vehicle and an abnormal license plate through license plate normalization processing calculation and association rule algorithm calculation;
and analyzing the correlation degree of the license plate to obtain a result.
The following describes the device for determining a vehicle for highway fake-licensed according to the embodiment of the present application, and the device for determining a vehicle for highway fake-licensed described below and the method for determining a vehicle for highway fake-licensed described above may be referred to correspondingly.
As shown in fig. 3, it discloses a schematic structural diagram of an expressway fake-licensed vehicle determination device, which may include:
the system comprises a data acquisition unit 11, a gateway data set D1 and a portal assembly line set D2, wherein the gateway data set D1 comprises a passage identifier, an entrance license plate, an exit license plate, entrance time and exit time of each vehicle, and the portal assembly line set D2 comprises a passage identifier, a portal identification license plate and portal identification time of each vehicle;
a first target set determining unit 12, configured to determine a first target vehicle and form a first target set C1 according to the entrance license plate, the exit license plate, and the portal identification license plate of the same passage identifier, where the first target set C1 includes the passage identifier, the entrance time, the exit time, and the portal identification time of the first target vehicle;
a second target set determining unit 13, configured to determine a passing identifier of a second target vehicle by using the entry time, the exit time, the portal identification time, and the time window of the first target set C1, and form a second target set C2;
a third target set determining unit 14, configured to segment the portal running water set D2 according to the passage identifier in the second target set C2, obtain portal identification license plates of second target vehicles in a target time period, and form a third target set C3;
a rule judging unit 15, configured to judge whether the portal identification license plate in the third target set C3 meets a preset rule;
a fourth target set determining unit 16, configured to determine, after executing the rule determining unit, if yes, the second target vehicle as an abnormal license plate, and form each abnormal license plate into a fourth target set C4;
and a calculation and determination unit 17, configured to calculate and determine a fake-licensed vehicle by using the fourth target set C4.
Optionally, the first target set determining unit 12 may include:
the matrix extraction unit is used for extracting the characteristic matrixes of the entrance and exit data set D1 and the portal flow set D2 according to the passing identification;
the portal number determining unit is used for determining whether the number of portals through which vehicles passing through the entrance license plate, the exit license plate and the portal identification license plate is consistent is smaller than a first threshold value in the entrance time and the exit time range;
and the first target set forming unit is used for determining the vehicle as a first target vehicle and forming the passing identifier, the entrance time, the exit time and the portal identification time of the first target vehicle into a first target set C1 if the number of the portals is determined by the first target set forming unit.
Optionally, the first target set determining unit 12 may include:
a first target set calculation unit, configured to determine the first target set C1 by using the following relation:
D1 vm =[D1 v1 D1 v2 … D1 vm ],D2 vn =[D2 v1 D2 v2 … D2 vn ]
where T1 represents an entrance time, T4 represents an exit time, D1vm represents a feature matrix of the entrance data set D1, D2vn represents a feature matrix of the portal flow set D2, T represents a time between T1 and T4, and X1 represents a first threshold.
Optionally, the second target set determining unit 13 may include:
the characteristic establishing unit is used for establishing time sequence historical characteristics of a time window by utilizing the entry time, the exit time and the portal identification time of the first target set C1;
a second threshold determination unit, configured to determine a second threshold of the time window by using the time-series historical feature;
a difference calculation unit, configured to calculate a difference between gantry identification times of the first target set C1;
the second target vehicle selecting unit is used for selecting the first target vehicle with the difference value larger than the second threshold value as a second target vehicle;
and a second target set forming unit, configured to form the passage identifier of the second target vehicle into a second target set C2.
Optionally, the second target set determining unit 13 may include:
a second target set calculation unit, configured to determine the second target set C2 by using the following relation:
wherein ,represents the time of recognition of the previous portal,the subsequent gantry recognition time is represented, t2 represents a first time signature sequence, t3 represents a second time signature sequence, and X2 represents a second threshold.
Optionally, the rule determining unit 15 may include:
and the first rule judging subunit is configured to judge whether the portal identification license plate in the third target set C3 is not in the time period from the entrance time to the first portal identification time and the time period from the second portal identification time to the next entrance time, and is not in the entrance and exit data set D1.
Optionally, the fourth target set determining unit 16 may include:
a fourth target set selecting unit, configured to determine each abnormal license plate and form the fourth target set C4 by using the following relation:
wherein ,Fv Representing a license plate, C3 representing a third target set, C2 representing a second target set, D1 representing an entrance data set, T n Representing the nth temporal characteristic value.
Optionally, the calculation and determination unit 17 may include:
the first calculation determining subunit is configured to calculate, by using the fourth target set C4, a result set of a support degree, a confidence degree, and a promotion degree of each abnormal license plate;
and the second calculation and determination subunit is used for determining the fake-licensed vehicles according to the result set of the support degree, the confidence degree and the promotion degree of each abnormal license plate.
Optionally, the calculation determining unit 17 may include:
a third calculation determination subunit, configured to calculate a result set of support degree, confidence degree, and promotion degree of each abnormal license plate by using the following relations:
wherein support represents support degree, conf represents confidence degree, lift represents result set of lifting degree, and L sample Indicates the number of items of the fourth target collection C4, count indicates the number, C1 Vm Indicating a normal license plate, C4 Vn Indicating an abnormal license plate.
The device for determining the vehicle with the fake-licensed expressway provided by the embodiment of the application can be applied to equipment for determining the fake-licensed expressway vehicle. The highway fake-licensed vehicle determination device may be a terminal. Fig. 4 is a block diagram showing a hardware configuration of an expressway fake-licensed vehicle determination apparatus, and referring to fig. 4, the hardware configuration of the expressway fake-licensed vehicle determination apparatus may include: at least one processor 1, at least one communication interface 2, at least one memory 3 and at least one communication bus 4;
in the embodiment of the application, the number of the processor 1, the communication interface 2, the memory 3 and the communication bus 4 is at least one, and the processor 1, the communication interface 2 and the memory 3 complete mutual communication through the communication bus 4;
the processor 1 may be a central processing unit CPU, or an Application Specific Integrated Circuit ASIC (Application Specific Integrated Circuit), or one or more Integrated circuits configured to implement embodiments of the present invention, etc.;
the memory 3 may include a high-speed RAM memory, and may further include a non-volatile memory (non-volatile memory) or the like, such as at least one disk memory;
wherein the memory stores a program and the processor can call the program stored in the memory, the program for:
the method comprises the steps that an entrance and exit data set D1 and a portal assembly set D2 are obtained, the entrance and exit data set D1 comprises a passing identification, an entrance license plate, an exit license plate, entrance time and exit time of each vehicle, and the portal assembly set D2 comprises the passing identification, a portal identification license plate and portal identification time of each vehicle;
determining first target vehicles according to the entrance license plate, the exit license plate and the portal identification license plate of the same pass identification, and forming a first target set C1, wherein the first target set C1 comprises the pass identification, the entrance time, the exit time and the portal identification time of the first target vehicles;
determining a passing identifier of a second target vehicle by using the entrance time, the exit time, the portal identification time and the time window of the first target set C1 and forming a second target set C2;
according to the passing identification in the second target set C2, the portal flow set D2 is divided to obtain portal recognition license plates of second target vehicles in a target time period and form a third target set C3;
judging whether the portal identification license plate in the third target set C3 meets a preset rule or not;
if yes, determining the second target vehicle as an abnormal license plate and forming a fourth target set C4 by each abnormal license plate;
and calculating and determining a fake-licensed vehicle by using the fourth target set C4.
Alternatively, the detailed function and the extended function of the program may be as described above.
Embodiments of the present application further provide a storage medium, where a program suitable for execution by a processor may be stored, where the program is configured to:
the method comprises the steps that an entrance and exit data set D1 and a portal assembly set D2 are obtained, the entrance and exit data set D1 comprises a passing identification, an entrance license plate, an exit license plate, entrance time and exit time of each vehicle, and the portal assembly set D2 comprises the passing identification, a portal identification license plate and portal identification time of each vehicle;
determining first target vehicles according to the entrance license plate, the exit license plate and the portal identification license plate of the same pass identification, and forming a first target set C1, wherein the first target set C1 comprises the pass identification, the entrance time, the exit time and the portal identification time of the first target vehicles;
determining a passing identifier of a second target vehicle by using the entrance time, the exit time, the portal identification time and the time window of the first target set C1 and forming a second target set C2;
according to the passing identification in the second target set C2, the portal flow set D2 is divided to obtain portal recognition license plates of second target vehicles in a target time period and form a third target set C3;
judging whether the portal identification license plate in the third target set C3 meets a preset rule or not;
if yes, determining the second target vehicle as an abnormal license plate and forming a fourth target set C4 by each abnormal license plate;
and calculating and determining a fake-licensed vehicle by using the fourth target set C4.
Alternatively, the detailed function and the extended function of the program may be as described above.
Finally, it should also be noted that, in this document, relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrases "comprising one of 8230; \8230;" 8230; "does not exclude the presence of additional like elements in a process, method, article, or apparatus that comprises the element.
The embodiments in the present description are described in a progressive manner, each embodiment focuses on differences from other embodiments, the embodiments can be combined with each other, and the same and similar parts can be referred to each other.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (10)
1. A method for determining a highway fake-licensed vehicle, comprising:
the method comprises the steps that an entrance and exit data set D1 and a portal assembly set D2 are obtained, the entrance and exit data set D1 comprises a passing identification, an entrance license plate, an exit license plate, entrance time and exit time of each vehicle, and the portal assembly set D2 comprises the passing identification, a portal identification license plate and portal identification time of each vehicle;
determining first target vehicles according to the entrance license plate, the exit license plate and the portal identification license plate of the same pass identification, and forming a first target set C1, wherein the first target set C1 comprises the pass identification, the entrance time, the exit time and the portal identification time of the first target vehicles;
determining the passing identification of a second target vehicle by using the entry time, the exit time, the portal identification time and the time window of the first target set C1 and forming a second target set C2;
according to the passing identification in the second target set C2, the portal running water set D2 is segmented to obtain portal recognition license plates of second target vehicles in a target time period and form a third target set C3;
judging whether the portal identification license plate in the third target set C3 meets a preset rule or not;
if yes, determining the second target vehicle as an abnormal license plate and forming a fourth target set C4 by each abnormal license plate;
and calculating and determining a fake-licensed vehicle by using the fourth target set C4.
2. The method of claim 1, wherein the determining a first target vehicle and forming a first target set C1 according to the entrance license plate, the exit license plate and the portal identification license plate of the same pass identifier comprises:
extracting feature matrixes of the entrance and exit data set D1 and the portal flow set D2 according to the pass identification;
determining whether the number of the portals through which vehicles passing through the entrance license plate, the exit license plate and the portal identification license plate is consistent is smaller than a first threshold value within the entrance time and the exit time range;
if yes, determining the vehicle as a first target vehicle, and forming a first target set C1 by using the passing identification, the entrance time, the exit time and the portal identification time of the first target vehicle.
3. The method of claim 1, wherein determining a first target vehicle and forming a first target set C1 according to the entrance license plate, the exit license plate and the portal identification license plate of the same pass identification comprises:
determining the first target set C1 using the following relation:
D1 vm =[D1 v1 D1 v2 … D1 vm ],D2 vn =[D2 v1 D2 v2 … D2 vn ]
where T1 represents an entrance time, T4 represents an exit time, D1vm represents a feature matrix of the entrance data set D1, D2vn represents a feature matrix of the portal flow set D2, T represents a time between T1 and T4, and X1 represents a first threshold.
4. The method of claim 1, wherein determining the transit identity of a second target vehicle and composing a second target set C2 using the entry time, exit time, portal identification time, and time window of the first target set C1 comprises:
constructing time sequence historical characteristics of a time window by using the entry time, the exit time and the portal identification time of the first target set C1;
determining a second threshold value of the time window by using the time series historical characteristics;
calculating the difference value of the gantry identification time of the first target set C1;
selecting a first target vehicle with the difference value larger than the second threshold value as a second target vehicle;
and forming a second target set C2 by the pass identifications of the second target vehicles.
5. The method according to claim 1, wherein determining temporal characteristic values using the entry time, the exit time, the gantry identification time and the time window of the first target set C1 and composing the temporal characteristic values into a second target set C2 comprises:
determining the second target set C2 using the following relationship:
6. The method of claim 1, wherein the determining whether the portal identification license plate in the third target set C3 meets a preset rule comprises:
and judging whether the portal identification license plate in the third target set C3 is not in the time period from the entrance time to the first portal identification time and the time period from the second portal identification time to the next entrance time, and is not in the entrance and exit data set D1.
7. The method of claim 1, wherein determining the second target vehicle as an abnormal license plate and grouping each of the abnormal license plates into a fourth target set C4 comprises:
determining each abnormal license plate and forming the fourth target set C4 by using the following relational expression:
wherein ,Fv Representing a license plate, C3 representing a third target set, C2 representing a second target set, D1 representing an entrance data set, T n Representing the nth temporal characteristic value.
8. The method of claim 1, wherein computationally determining a fake-licensed vehicle using the fourth set of targets C4, comprises:
calculating a result set of support degree, confidence degree and promotion degree of each abnormal license plate by using the fourth target set C4;
and determining the fake-licensed vehicles according to the result set of the support degree, the confidence degree and the promotion degree of each abnormal license plate.
9. The method of claim 8, wherein the calculating a result set of support, confidence and promotion for each abnormal license plate comprises:
calculating a result set of support degree, confidence degree and promotion degree of each abnormal license plate by using the following relational expressions:
wherein support represents support degree, conf represents confidence degree, lift represents result set of lifting degree, and L sample Indicates the number of items of the fourth target collection C4, count indicates the number, C1 Vm Indicating a normal license plate, C4 Vn Indicating an abnormal license plate.
10. An expressway fake-licensed vehicle determining device, comprising:
the system comprises a data acquisition unit and a portal assembly unit, wherein the data acquisition unit is used for acquiring a portal data set D1 and a portal assembly set D2, the portal data set D1 comprises a passing identifier, a portal license plate, entrance time and exit time of each vehicle, and the portal assembly set D2 comprises a passing identifier, a portal identification license plate and portal identification time of each vehicle;
a first target set determining unit, configured to determine first target vehicles according to the entry license plate, the exit license plate, and the portal identification license plate of the same pass identifier, and form a first target set C1, where the first target set C1 includes the pass identifier, the entry time, the exit time, and the portal identification time of the first target vehicle;
the second target set determining unit is used for determining the passing identification of a second target vehicle by using the entrance time, the exit time, the portal identification time and the time window of the first target set C1 and forming a second target set C2;
a third target set determining unit, configured to segment the portal running water set D2 according to the passage identifier in the second target set C2, obtain portal identification license plates of second target vehicles in a target time period, and form a third target set C3;
a rule judging unit, configured to judge whether the portal identification license plate in the third target set C3 meets a preset rule;
a fourth target set determining unit, configured to determine, after the rule determining unit is executed, if yes, the second target vehicle as an abnormal license plate and form each abnormal license plate into a fourth target set C4;
and the calculation and determination unit is used for calculating and determining the fake-licensed vehicles by utilizing the fourth target set C4.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211200281.6A CN115601974B (en) | 2022-09-29 | 2022-09-29 | Method and device for determining highway fake-licensed vehicle |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211200281.6A CN115601974B (en) | 2022-09-29 | 2022-09-29 | Method and device for determining highway fake-licensed vehicle |
Publications (2)
Publication Number | Publication Date |
---|---|
CN115601974A true CN115601974A (en) | 2023-01-13 |
CN115601974B CN115601974B (en) | 2023-06-16 |
Family
ID=84845552
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202211200281.6A Active CN115601974B (en) | 2022-09-29 | 2022-09-29 | Method and device for determining highway fake-licensed vehicle |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115601974B (en) |
Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2004359208A (en) * | 2003-05-12 | 2004-12-24 | Denso Corp | Electronic license plate system and electronic license plate |
CN106128113A (en) * | 2016-08-01 | 2016-11-16 | 深圳市永兴元科技有限公司 | The recognition methods of fake license plate vehicle and device |
WO2017124302A1 (en) * | 2016-01-19 | 2017-07-27 | 冯旋宇 | Violation recognition method and system for intelligent transportation |
WO2017169012A1 (en) * | 2016-03-30 | 2017-10-05 | 住友電気工業株式会社 | Identification information determination device, identification information determination system, computer program, and identification information determination method |
CN108510747A (en) * | 2018-04-14 | 2018-09-07 | 苏州远征魂车船技术有限公司 | The recognition methods of fake license plate vehicle |
CN111369805A (en) * | 2020-01-09 | 2020-07-03 | 杭州海康威视系统技术有限公司 | Fake plate detection method and device, electronic equipment and computer readable storage medium |
WO2021217921A1 (en) * | 2020-04-27 | 2021-11-04 | 平安国际智慧城市科技股份有限公司 | Online payment method, apparatus and device for highway toll, and storage medium |
CN114140780A (en) * | 2021-11-19 | 2022-03-04 | 杭州海康威视数字技术股份有限公司 | Abnormal vehicle detection method, device and equipment |
CN114495028A (en) * | 2022-01-21 | 2022-05-13 | 北京华录高诚科技有限公司 | Vehicle fake plate identification method and device, electronic equipment and storage medium |
CN114743038A (en) * | 2022-04-12 | 2022-07-12 | 浙江大华技术股份有限公司 | Data clustering method and device, computer equipment and storage medium |
-
2022
- 2022-09-29 CN CN202211200281.6A patent/CN115601974B/en active Active
Patent Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2004359208A (en) * | 2003-05-12 | 2004-12-24 | Denso Corp | Electronic license plate system and electronic license plate |
WO2017124302A1 (en) * | 2016-01-19 | 2017-07-27 | 冯旋宇 | Violation recognition method and system for intelligent transportation |
WO2017169012A1 (en) * | 2016-03-30 | 2017-10-05 | 住友電気工業株式会社 | Identification information determination device, identification information determination system, computer program, and identification information determination method |
CN106128113A (en) * | 2016-08-01 | 2016-11-16 | 深圳市永兴元科技有限公司 | The recognition methods of fake license plate vehicle and device |
CN108510747A (en) * | 2018-04-14 | 2018-09-07 | 苏州远征魂车船技术有限公司 | The recognition methods of fake license plate vehicle |
CN111369805A (en) * | 2020-01-09 | 2020-07-03 | 杭州海康威视系统技术有限公司 | Fake plate detection method and device, electronic equipment and computer readable storage medium |
WO2021217921A1 (en) * | 2020-04-27 | 2021-11-04 | 平安国际智慧城市科技股份有限公司 | Online payment method, apparatus and device for highway toll, and storage medium |
CN114140780A (en) * | 2021-11-19 | 2022-03-04 | 杭州海康威视数字技术股份有限公司 | Abnormal vehicle detection method, device and equipment |
CN114495028A (en) * | 2022-01-21 | 2022-05-13 | 北京华录高诚科技有限公司 | Vehicle fake plate identification method and device, electronic equipment and storage medium |
CN114743038A (en) * | 2022-04-12 | 2022-07-12 | 浙江大华技术股份有限公司 | Data clustering method and device, computer equipment and storage medium |
Non-Patent Citations (2)
Title |
---|
XING-WANG ZHANG ET AL.: "A Vehicle License Plate Recognition Method Based on Neural Network", 2010 IEEE INTERNATIONAL CONFERENCE ON GRANULAR COMPUTING * |
李敏茜;毛嘉莉;袁培森;金澈清;: "基于卡口监测数据流的套牌车检测", 华东师范大学学报(自然科学版), no. 02 * |
Also Published As
Publication number | Publication date |
---|---|
CN115601974B (en) | 2023-06-16 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108009690B (en) | Ground bus stealing group automatic detection method based on modularity optimization | |
CN110751828B (en) | Road congestion measuring method and device, computer equipment and storage medium | |
CN102521534B (en) | Intrusion detection method based on crude entropy property reduction | |
Yang et al. | How to determine an optimal threshold to classify real-time crash-prone traffic conditions? | |
CN110444011B (en) | Traffic flow peak identification method and device, electronic equipment and storage medium | |
CN109446881B (en) | Heterogeneous data-based highway section traffic state detection method | |
CN113255430A (en) | Method for detecting and counting crowd distribution in video based on deep learning | |
CN112309126B (en) | License plate detection method and device, electronic equipment and computer readable storage medium | |
CN111950498A (en) | Lane line detection method and device based on end-to-end instance segmentation | |
CN111209317A (en) | Knowledge graph abnormal community detection method and device | |
CN112732748A (en) | Non-invasive household appliance load identification method based on adaptive feature selection | |
CN115565373B (en) | Expressway tunnel accident real-time risk prediction method, device, equipment and medium | |
CN113255580A (en) | Method and device for identifying sprinkled objects and vehicle sprinkling and leaking | |
Zhang et al. | Vehicle classification based on feature selection with anisotropic magnetoresistive sensor | |
CN113076922A (en) | Object detection method and device | |
CN109697851B (en) | Urban road traffic state discrimination method and system based on AFCM-L2 | |
CN115601974B (en) | Method and device for determining highway fake-licensed vehicle | |
CN111598158B (en) | Warehouse inventory state sensing method based on AI analysis technology | |
CN109543610B (en) | Vehicle detection tracking method, device, equipment and storage medium | |
CN107730717A (en) | A kind of suspicious card identification method of public transport of feature based extraction | |
CN112966728A (en) | Transaction monitoring method and device | |
CN117054998A (en) | Cluster target detection method and system based on information entropy background stability | |
CN107886524B (en) | Method for identifying motion track of elevator door | |
CN115588124A (en) | Fine-grained classification denoising training method based on soft label cross entropy tracking | |
CN108241837B (en) | Method and device for detecting remnants |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |