CN106022296A - Fake plate vehicle detection method based on vehicle hot spot area probability aggregation - Google Patents
Fake plate vehicle detection method based on vehicle hot spot area probability aggregation Download PDFInfo
- Publication number
- CN106022296A CN106022296A CN201610380318.6A CN201610380318A CN106022296A CN 106022296 A CN106022296 A CN 106022296A CN 201610380318 A CN201610380318 A CN 201610380318A CN 106022296 A CN106022296 A CN 106022296A
- Authority
- CN
- China
- Prior art keywords
- bayonet socket
- vehicle
- probability
- car
- fake
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
- G06V20/58—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads
- G06V20/584—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads of vehicle lights or traffic lights
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
-
- 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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/62—Text, e.g. of license plates, overlay texts or captions on TV images
- G06V20/625—License plates
Abstract
The invention discloses a fake plate vehicle detection method based on vehicle hot spot area probability aggregation. The fake plate vehicle detection method comprises the steps that S1, checkpoint data is extracted; S2, the checkpoint data is cleaned; S3, flow directions between the checkpoints are calculated; S4, a list of abnormally-acting vehicles are calculated: according to a checkpoint pair of every vehicle extracted by S2, checkpoint pair probabilities are calculated, and are arranged in a descending order according to times having probabilities lower than a threshold value, and then first N rows are selected to be used as the list of the abnormally-acting vehicles; S5, vehicle hot spot area checkpoint points are calculated; S6, the probabilities of the vehicles moving between two hot spot area checkpoint points are calculated; S7, the checkpoints are aggregated together according to the probabilities calculated by S6; S8, probabilities of fake plate vehicles Z are calculated according to a vehicle checkpoint aggregation condition. Random checkpoint license number identification errors are overcome, and by using a characteristic of relatively fixed vehicle moving areas, the vehicles having large suspicion of faking the license plates are selected, the suspicion range is greatly reduced, and the practicability is good.
Description
Technical field
The present invention relates to intelligent transportation field, be specifically related to a kind of fake-licensed car detection method.
Background technology
Fake-licensed car is commonly called as cloning car, refers to by forging or illegally extracting in other formality such as number plate of vehicle and driving license
The vehicle that road travels.Along with expanding economy, vehicle population gets more and more, and fake-licensed car is also continuously increased.Fake-licensed car can be upset
, owing to fake-licensed car does not has legal procedure and insurance, once there is vehicle accident, driver in Public Security Organs's management and control to public safety
Easily escape.Fake-licensed car also provides tool used in crime for criminal activity, considerably increases difficulty of solving a case.Fake-licensed car can escape various tax
Take, cause a large amount of losses of country's expenses of taxation, and upset the order of transport market.Fake-licensed car can damage the legitimate rights and interests of true car owner,
At the aspect such as vehicular traffic violation, accident treatment, true car owner often to serve as " person who spends money wastefully and foolishly ".
It is very big that difficulty is investigated and prosecuted in the identification of this act of violating regulations of fake-licensed car, and people's police are difficult to the short time according to car during on duty
Board and external appearance characteristic artificial judgment go out whether vehicle is fake-licensed car.There are some fake-licensed cars based on bayonet socket data automatic now
Change recognition methods.Bayonet socket refers to and uses the photoelectricity of advanced person, computer, image procossing, pattern recognition, remote data access etc.
Technology, carries out round-the-clock real-time monitoring to the monitoring car lane in section, bicycle lane and records dependent image data, and from
Dynamic obtain vehicle by data such as time, place, travel direction, brand number, number plate color, body colors.
In published patent and the patent in examining, it is largely divided into three major types, 1, based on image recognition, special by vehicle
Levy and judge.2, based on auxiliary device: such as install electronic license plate, reserved security password etc..3, based on bayonet socket data, right
Track of vehicle is analyzed.
Patent based on first kind method has:
One: application number [201510102368.3] proposes, based on the license plate number and the deck of brand message that identify vehicle
Car detection method.1, license plate number and the brand message of vehicle are identified, if license plate number and brand message are the most corresponding, then by this vehicle
Add fake-licensed car suspicion storehouse；2, the vehicle adding fake-licensed car suspicion storehouse is accurately differentiated, remove the vehicle of wrong report；3) statistics
The number of times that vehicle occurs in fake-licensed car suspicion storehouse, sends alarm when the occurrence number of certain vehicle exceedes setting value K.
Two: application number [201410333789.2] proposes, the side of a kind of fake-licensed car identification based on testing vehicle register identification
Method and device.1, from picture or video, extract vehicle, identify this vehicle characteristics.2, for compare with traffic administration institute data base
Right, when finding that some feature of vehicle is not mated with feature in data base, report to the police.2, carry out checking cloth in urban district inner bayonet
Control, when finding that the feature identical vehicle diverse location in the same time occurs, then carries out set and reports to the police.3, historical data is carried out
Comparison, when the vehicle finding that the number-plate number is identical, when other features of vehicle differ, reports to the police.
In above patented method, the identification of the factor such as weather, light meeting interferogram picture, partial domestic car and imported car profile
The most similar, also can cause difficulty to identification.There is former car and fake-licensed car brand, model identical, the defect such as cannot detect.
Patent based on Equations of The Second Kind method has:
One: application number [201320365827.3] proposes, a kind of vacation based on super high frequency radio frequency identification technology, fake-licensed car
Identify device.Vacation based on super high frequency radio frequency identification technology, fake license plate vehicle identification device, by radio frequency identification read-write equipment pair
Electronic tag on automobile detects, and judges the information in electronic tag, then with license plate image collecting device
The number-plate number drawn is compared, and carries out fake-licensed car differentiation.
Two: application number [200910107671.7] proposes, a kind of motor vehicles deck false-trademark based on security password is illegal
Behavioral value method.Traffic police's interior vehicle management system platform reserves vehicle safety detection password；The law enforcement hand-held long-range control of traffic police
The examined vehicle region code of terminal processed input and the number-plate number；Contrast with log-on message；It is close that vehicle safety detection is looked in input
Code；Input password contrasts automatically with reserving cipher, it may be judged whether deck false-trademark.
Above patent needs to relate to extra platform construction and vehicle remoulding.
Patent based on the 3rd class method has:
One: application number [201210438702.9] proposes, a kind of fake-licensed car detection method occured simultaneously based on the time.Obtain
Pick up the car a moment entering and leaving this position and the time of staying section in this position, match two-by-two, if the stop of correspondence
There is common factor time period, then there is fake-licensed car, if without occuring simultaneously, then poor according to the theoretical shortest time between 2 o'clock and actual time
Judge whether fake-licensed car.In the program, the theoretical shortest time calculates complexity, relates to road network structure, road section length, hands over
All multiparameters such as logical congestion degree.
Two: application number [201310730531.1] proposes, the automatic catching method in region of a kind of fake-licensed car vehicle.In envelope
The zone boundary closed arranges control point, if vehicle rolls away from from this region, but does not sail information into, then judge that this vehicle is as set
Board vehicle.Closed area in the program is difficult in practice.
Three: application number [201310034242.8] proposes, the capture of a kind of fake-licensed car vehicle formatted based on road network
Method.Urban road area carried out gridding according to grid segmentation principle, checks same license plate number vehicle in temporal sequence
Grid track is the most continuous, if there is discontinuous grid track, then using license plate number corresponding for this grid track as doubtful set
The board car number-plate number.The program needs detailed road network structure.
Four: application number [201410094882.2] proposes, the side that a kind of deck connective based on bayonet socket is analyzed.1, root
The most consistent with the bayonet socket communication information pre-saved through the order of bayonet socket according to vehicle, if inconsistent, further according to protecting in advance
The bayonet socket communication information deposited determines arbitrary inconsistent bayonet socket all reachable paths to its adjacent bayonet socket, it is judged that described up to road
Whether there is a paths in footpath, the bayonet socket quantity of this paths process is less than or equal to preset value N, if it is, described car plate
Non-deck, otherwise, there is deck in described car plate.
Existing method is all based on single vehicle driving trace and judges.In practical situation, owing to bayonet socket number plate is known
The not existence of mistake, it is individual that the fake-licensed car suspicion inventory that algorithm above draws often reaches several ten thousand even hundreds of thousands.
The bayonet socket number plate identification mistake of randomness refers to due to the factor such as illumination, angle, car plate at part bayonet socket or
Time period can correctly identify, part bayonet socket or time period are identified as other car plates.This situation accounts for number plate identification mistake
The overwhelming majority.Nonrandomness number plate identification mistake is stained mainly due to number plate of vehicle and causes, and this car plate can be by all bayonet sockets
It is identified as the wrong number plate fixed.Example license plate number " Zhejiang A****R ", wherein the character R lower right corner is blocked, but remainder is equal
Being apparent from, this Car license recognition has all been become " Zhejiang A****P " by all bayonet sockets.
Summary of the invention
In order to overcome existing fake license plate vehicle detection method owing to there is the bayonet socket number plate identification mistake of randomness, suspicion model
Enclosing deficiency excessive, that practicality is poor, the present invention provides a kind of bayonet socket number plate identification mistake overcoming randomness, utilizes vehicle to live
The relatively-stationary characteristic in dynamic region, filters out the bigger vehicle of deck suspicion degree, to be substantially reduced suspicion scope, practicality good
The fake-licensed car detection method of probability polymerization based on movable vehicle hot spot region.
The technical solution adopted for the present invention to solve the technical problems is:
A kind of fake-licensed car detection method of probability polymerization based on vehicle hot spot region, described fake license plate vehicle detection method bag
Include following steps:
S1. the extraction of bayonet socket data: obtain card and make a slip of the tongue car record data, retain the dimension needed, including bayonet socket numbering, card
Mouth direction, brand number, number plate kind, spend the car time；
S2. the cleaning of bayonet socket data；
S3. calculating between bayonet socket and flow to probability, process is as follows:
3.1, according to wheelpath, extracting bayonet socket vector: by bayonet socket data according to brand number, card car time of making a slip of the tongue is carried out
Sequence, obtains the wheelpath of each car, with the bayonet socket sequence (K of processa,Kb,Kc·Ki·Kn) represent, extract each
Bayonet socket pair adjacent in wheelpath, forms bayonet socket sequence vector (Ka,Kb)·(Ki, Kj)·。K a, represent vehicle process
The a bayonet socket, vector (Ka,Kb) represent that sequence of cars is through two bayonet socket KaAnd Kb, and KaAnd KbIn wheelpath adjacent；
3.2, calculate between bayonet socket and flow to probability: to bayonet socket KiCounting, obtains KiBayonet socket flow out gross vehicle and, with count (Ki)
Represent.To vector (Ki,Kj) counting, obtain bayonet socket KiTo bayonet socket KjCurrent gross vehicle and, with count (Ki,Kj) represent.Bayonet socket Ki
To bayonet socket KjThe probability that flows to be Pij=count (Ki,Kj)/count(Ki)；
S4. calculate dystropy vehicle inventory: according to the bayonet socket pair of each the car extracted in S2, calculate bayonet socket pair
Probability, according to probability less than setting threshold value TiNumber of times, descending, choose front N row as required, as dystropy vehicle
Inventory, N chooses according to actual needs；
S5. vehicle hot spot region bayonet socket point is calculated: thermal point structure region bayonet socket point refers to the card that vehicle is often captured
Mouthful, the number of times that calculating vehicle occurs at each bayonet socket point, if greater than threshold value M setv, then it is assumed that this bayonet socket is the heat of vehicle
Point zone of action bayonet socket point；
S6. the probability that calculating vehicle is current between 2 hot spot region bayonet socket points: the heat that each car is calculated in S5
Point bayonet socket does cartesian product, and the probability calculated according to S2, carries out assignment to every a pair bayonet socket, and choose forward and reverse in relatively
Big probability；If the probability P (Ki, Kj) of bayonet socket Ki to the bayonet socket Kj < probability P (Kj, Ki) of bayonet socket Kj to bayonet socket Ki, then will
P (Kj, Ki) is assigned to bayonet socket to (Ki, Kj)；
S7. according to probability between S6 gained bayonet socket, all bayonet sockets are polymerized, it is ensured that each packets inner, for arbitrary
Bayonet socket is to (Ki, Kj), there is a paths from KiTo Kj, on path, the probability of all adjacent bayonet sockets pair is all not less than setting threshold value
Ti, between each packet, for arbitrary bayonet socket Ki, there is not bayonet socket K in other groupsj, meet P (Ki,Kj) more than the threshold value set
Ti；
S8. calculate the probability of vehicle fake-license, calculate vehicle fake-license probability Z, Z=N*i* according to vehicle bayonet socket polymerization situation
s4, N represents vehicle focus bayonet socket sum, and i depends on number of packet L, if L=2, i=1, if L=3, i=1/2, otherwise i
=0；S depends on the quantity ratio of bayonet socket in packet, and NAi represents the quantity of bayonet socket in each group；S=max (NAi, 2)/max
(Nai, 1), max (NAi, 1) represents that quantity is maximum, and max (NAi, 2) represents that quantity is second largest.
Further, individual in described step S7, polymerization process is as follows:
Step7.1. obtaining can be with number plate of vehicle inventory；
Step7.2. from number plate inventory, take out a number, according to number, obtain this number plate thermal point structure region bayonet socket
(K1, K2, K3 Kn), is designated as array A0, and occurs in the number of times flashback arrangement of this bayonet socket according to vehicle；
Step7.3. first bayonet socket K1 in A0 is added in array A1, and K1 is removed from A0；
Step7.4. judge in K1 and A0 the undirected probability Q (K1, Ki) between each bayonet socket whether more than threshold value Ti, as
Fruit is, Ki adds to A1 and empty array A_new, and is removed from array A0 by Ki；
Step7.5. from array A_new, a bayonet socket Kj is taken out, it is judged that undirected between each bayonet socket in Kj and A0
Whether probability Q (Kj, Ki) is more than threshold value Ti, if it is, Ki adds to A1 and empty array A_new, and by Ki from array A0
Middle removal, removes Kj from array A_new；
Step7.6. Step7.5 is repeated, until A_new is empty；
Step7.7. increase array Ai, repeat step Step7.3-7.6；
Step7.8. Step7.7 is repeated, until A0 is empty；
Step7.9. Step7.2-7.8 is repeated, until number plate inventory is empty.
Further, in described step S2, the cleaning process of bayonet socket data is as follows:
2.1, cleaning repeats record；
2.2, cleaning dirty data, described dirty data refers to that brand number does not meets the record of naming rule；
2.3, determining time interval, record the most complete bayonet socket data in cleaning this interval, these situations include that bayonet socket damages
Bad and power-off causes bayonet socket to work, or network interrupts and disk size deficiency causes data to fail to store, and cleans this card
The all data of mouth.
Further, in described step S4, threshold value TiIt is set, to bayonet socket K according to bayonet socket number plate recognition correct rate FiAnd
Speech, TiValue should meet F≤∑jPij<F-Ti, wherein j meets Pij>TI,, bayonet socket number plate recognition correct rate F=1-is (by card
The still number plate of the mouth not car record number excessively in number plate storehouse)/(all car record numbers excessively), TiRepresent bayonet socket KiThreshold value, Pij
Represent bayonet socket PiProbability to other bayonet sockets.
The technology of the present invention is contemplated that: based on based on current Probability Detection vehicle fake-license method, utilize vehicle focus
Active area characteristics, reduces investigation scope.
In actually used, due to factors such as light, angle, number plate are stained, bayonet socket is unable to reach for the discrimination of number plate
100% (typically at about 96%-98%).Car plate can correctly identify at major part bayonet socket or time period, fraction bayonet socket
Or the time period is identified as other car plates, it is random for identifying that the bayonet socket point of mistake is often distributed, and number of passing through is less.With
Time, normal home car substantially can travel on the most fixing route, identify that correct bayonet socket point is often distributed in these
In route, and number of times is more.Therefore number of pass times less bayonet socket point is removed, can be by the bayonet socket of major part identification mistake
Get rid of.
Vehicle frequently by bayonet socket the most spatially there is seriality.If these bayonet socket points are substantially distributed presents two
Individual community, and associate the most weak between community, illustrate to be likely to be two cars respectively at two regional activities, say, that this car bright
Deck probability higher.
Beneficial effects of the present invention is mainly manifested in: the number plate identification that can overcome bayonet socket randomness to a certain extent is wrong
By mistake, investigation scope, practicality are reduced greatly good；Without relying on road network structure, the suitability is stronger.
Accompanying drawing explanation
Fig. 1 is the flow chart of the fake-licensed car detection method of probability polymerization based on movable vehicle hot spot region.
Fig. 2 is the distribution of normal vehicle focus bayonet socket, is characterized between bayonet socket having stronger relatedness.
Fig. 3 is the distribution of doubtful fake license plate vehicle focus bayonet socket, is characterized in substantially being scattered in Liang Ge community.
Fig. 4 is the vehicle focus bayonet socket distribution of mistake more easy to identify, is characterized in being scattered in multiple community.
Detailed description of the invention
The invention will be further described below in conjunction with the accompanying drawings.
Reference Fig. 1～Fig. 4, the fake-licensed car detection method of a kind of probability polymerization based on movable vehicle hot spot region, including
Following steps:
S1. the extraction of data: obtain card and make a slip of the tongue car record data, retain the dimension needed, including bayonet socket numbering, bayonet socket side
To, brand number, number plate kind, cross the car time.(bayonet socket numbering uniquely determines position, bayonet socket crossing, and bayonet socket direction determines bayonet socket
Shooting direction, i.e. direction of traffic, number plate kind and brand number uniquely determine a motor vehicles)
The present embodiment has extracted the data of Hangzhou 489 bayonet socket records on the 27th on 1-January of January, and altogether 129534497
Bar, bayonet socket data form such as table 1 below:
| Field | Data type | Implication |
| KKID | VARchar(20) | Bayonet socket ID |
| FXBH | VARchar(2) | Bayonet socket direction |
| HPHM | VARchar(10) | Brand number |
| HPLX | VARchar(2) | Number plate kind |
| JGSJ | VARchar(20) | Spend the car time |
Table 1
Wherein KKID+FXBH uniquely determines a bayonet socket, and HPHM+HPZL uniquely determines an automobile.JGSJ is accurate to the second,
(in following steps, bayonet socket ID contains bayonet socket direction, and brand number contains number plate kind, repeats no more)
S2. the cleaning of data, process is as follows:
2.1, repetition data are cleaned: for bayonet socket, catch the vehicle of a process, many data may be produced, make
Become the repetition of data, as shown in table 2 below:
Table 2
Article 3, cross with the 4th article car record the bayonet socket ID of process consistent, and it is identical to spend the car time, and this belonging to repeats to remember
Record.
The when that reason being due to bayonet socket capture vehicle, a plurality of record may be produced.Define same vehicle, same card
Mouthful, and time error is recorded as repeating record less than threshold value Δ T (the present embodiment is set to 4 seconds), removes and repeats record.
2.2, clean dirty data: due to brand number be bayonet system according to picture recognition, there is a number of car plate
Character, bayonet socket None-identified, the brand number in record does not meets naming rule, specifically includes: " None-identified ", " NULL ",
Brand number contain symbol "？”.Cleaning this part data, part case is as shown in table 3 below:
| Sequence number | Brand number | Spend the car time |
| 1 | ？？？？？？？ | 2016-01-15 14:52:51 |
| 2 | NULL | 2016-01-20 19:32:30 |
| 3 | Peaceful B？711T | 2016-01-25 11:31:34 |
| 4 | Zhejiang A00？NT | 2016-01-25 20:54:04 |
| 5 | Zhejiang A025X？ | 2016-01-21 14:18:13 |
| 6 | None-identified | 2016-01-10 22:49:28 |
Table 3
3.3, the bayonet socket data that record is the most complete are cleaned: under practical situation, due to factors such as power-off, suspension, bayonet socket damages,
There is disappearance in the data of part bayonet socket.For recording the most complete bayonet socket data, these bayonet socket data are all cleaned.
In present case, the time interval chosen be January 1 to January 27, accumulative 489 bayonet sockets have 169 bayonet sockets extremely
Few have shortage of data in 1 day, cleans all of data of these bayonet sockets.
Bayonet socket shortage of data is defined as follows: if the bayonet socket car record of crossing of a day crosses the 1/20 of car record less than average daily, should
This day data of bayonet socket lacks.
S3. calculate between bayonet socket and flow to probability
First 3.1 determine wheelpath, and extracts bayonet socket vector
Wheelpath determines process: according to brand number, crosses car time-sequencing and i.e. can get wheelpath.Wheelpath bag
Containing three parts (bayonet socket ID, brand number, excessively car time), the bayonet socket that expression vehicle sequentially passes through and car time excessively.Form is such as
Under: the present embodiment has 2123568 wheelpaths, (ellipsis part is not for showing part) as shown in table 4 below.
Table 4
Extraction bayonet socket vector: for two bayonet sockets adjacent in same garage's wheel paths, take out successively, as bayonet socket
Vector.For S3 case, can be taken off six vectors (31000300007402,31000300010702),
(31000300010702,31000300010904)、(31000300010904,31000300004504)、
(31000300004504,31000300004502)、(31000300004502,31000300019902)、
(31000300019902,31000300005402)。
To 2123568 wheelpaths in the present embodiment, extracted vector respectively, all of wheelpath can be taken out
Vector is 85259515.
3.2. calculate between bayonet socket and flow to probability
Add up all of vector (Ki,Kj), can obtain from bayonet socket KiFlow out, flow to bayonet socket KjVehicle number.Statistics Ki, I
Can obtain from KiThe vehicle fleet flowed out, obtains (ellipsis part is not for showing part) as shown in table 5 below.
Table 5
Bayonet socket flows to probability and embodies bayonet socket distribution and road network structure in another kind of dimension.If bayonet socket distribution or road
There is notable change in web frame, this probability needs to recalculate (morning and evening track, restricted driving etc. need not recalculate).
S4. dystropy vehicle inventory is calculated
We have been extracted the wheelpath of each car in S3.One wheelpath correspondence N-1 having N number of point
Bayonet socket vector, each bayonet socket vector, a corresponding bayonet socket flows to probability, say, that a driving rail being made up of N number of point
Mark correspondence N-1 probit, such as table 6 below:
| Sequence number | Brand number | Bayonet socket ID | Spend the car time | Occur in this probability |
| k1 | Zhejiang AF1*** | 31000300011101 | 2016-01-14 07:55:58 | |
| k2 | Zhejiang AF1*** | 31000300005401 | 2016-01-14 08:06:34 | 25.47% |
| k3 | Zhejiang AF1*** | 31000300004703 | 2016-01-14 08:53:38 | 0.00% |
| k4 | Zhejiang AF1*** | 31000300010502 | 2016-01-14 12:12:01 | 0.01% |
| k5 | Zhejiang AF1*** | 31000300010504 | 2016-01-14 12:12:34 | 13.07% |
| k6 | Zhejiang AF1*** | 31000300007301 | 2016-01-14 13:59:31 | 0.04% |
| k7 | Zhejiang AF1*** | 31000300004304 | 2016-01-14 16:34:15 | 0.28% |
| k8 | Zhejiang AF1*** | 31000300004302 | 2016-01-14 16:34:15 | 53.37% |
| k9 | Zhejiang AF1*** | 31000300005001 | 2016-01-14 16:49:02 | 1.71% |
| k10 | Zhejiang AF1*** | 31000300014819 | 2016-01-14 16:57:21 | 0.02% |
| k11 | Zhejiang AF1*** | 31000300010020 | 2016-01-14 17:08:16 | 10.55% |
| k12 | Zhejiang AF1*** | 31000300028603 | 2016-01-14 17:17:45 | 16.61% |
| k13 | Zhejiang AF1*** | 31000300025302 | 2016-01-14 17:39:38 | 2.19% |
| k14 | Zhejiang AF1*** | 31000300004702 | 2016-01-14 17:45:08 | 0.02% |
Table 6
In table 6, k3, k4, k6, k10 and k14 probability is below Ti.
In the present embodiment, calculate bayonet socket threshold value TiCalculating process as follows:
4.1, first add up all cards make a slip of the tongue car sum and number plate error number (the brand number not vehicle in number plate storehouse).
Total car quantity of crossing is: 87383083, and number plate error number is: 2524476；Can calculate bayonet socket number plate recognition correct rate F is
97.1%.
4.2, each bayonet socket is calculated threshold value Ti: such as bayonet socket 31000300015401, with other each bayonet sockets
Between probability according to descending (ellipsis part for do not show part) as shown in table 7 below:
| Sequence number | Ki | Kj | Probability |
| 1 | 31000300015401 | 31000300006701 | 49.594% |
| 2 | 31000300015401 | 31000300015501 | 13.035% |
| 3 | 31000300015401 | 31000300006504 | 11.874% |
| 4 | 31000300015401 | 31000300006001 | 8.771% |
| 5 | 31000300015401 | 31000300015601 | 3.733% |
| 6 | 31000300015401 | 31000300011501 | 2.199% |
| 7 | 31000300015401 | 31000300015701 | 1.821% |
| 8 | 31000300015401 | 31000300006502 | 1.490% |
| 9 | 31000300015401 | 31000300011601 | 0.957% |
| 10 | 31000300015401 | 31000300011504 | 0.854% |
| 11 | 31000300015401 | 31000300011701 | 0.832% |
| 12 | 31000300015401 | 31000300011704 | 0.730% |
| 13 | 31000300015401 | 31000300006904 | 0.728% |
| 14 | 31000300015401 | 31000300011503 | 0.309% |
| 15 | 31000300015401 | 31000300015801 | 0.268% |
| 16 | 31000300015401 | 31000300006901 | 0.256% |
| 17 | 31000300015401 | 31000300011703 | 0.255% |
| 18 | 31000300015401 | 31000300006902 | 0.135% |
| 19 | 31000300015401 | 31000300010404 | 0.133% |
| 20 | 31000300015401 | 31000300011604 | 0.128% |
| 21 | 31000300015401 | 31000300007003 | 0.096% |
| 22 | 31000300015401 | 31000300007602 | 0.087% |
| 23 | 31000300015401 | 31000300022904 | 0.082% |
| 24 | 31000300015401 | 31000300010801 | 0.073% |
| ··· | ··· | ··· | ··· |
Table 7
To bayonet socket KiFor, TiValue should meet F≤∑jPij<F+Ti, wherein j meets Pij>Ti, in present case, if
TiValue is 0.268%, ∑jPij=96.930% < F, if TiValue is 0.255%, F < ∑jPij=97.198% < F+Ti,
If TiValue is 0.135%, ∑jPij=97.333% > F+Ti, so for bayonet socket 31000300015401, threshold value Ti=
0.255%.
According to as above method, we calculate the T that each bayonet socket is correspondingi, obtain such as table 8 below that (ellipsis part is not for show
Show part):
| Sequence number | Bayonet socket ID | Ti |
| 1 | 31000300000704 | 0.262% |
| 2 | 31000300000801 | 0.222% |
| 3 | 31000300000803 | 0.283% |
| 4 | 31000300011804 | 0.273% |
| 5 | 31000300011919 | 0.236% |
| 6 | 31000300011920 | 0.191% |
| 7 | 31000300012119 | 0.147% |
| 8 | 31000300012120 | 0.249% |
| 9 | 31000300025301 | 0.146% |
| 10 | 31000300020004 | 0.255% |
| ··· | ··· | ··· |
Table 8
In the present embodiment, it has been found that this section comprises in the wheelpath of 14 points, there are 5 probability less than threshold value Ti.
These 14 bayonet socket points are shown on map, find that these 14 bayonet socket points are substantially scattered in two tracks, wherein k1,
These 8 points of k2, k4, k5, k10, k11, k12, k13 are rendered obvious by a track, and k3, k6, k7, k8, k9, k14 are substantially in one
Track.
Suspicion degree sorts: less than threshold value Ti once, we are designated as once dystropy to Qi, if dystropy number of times is relatively
Many, illustrate that this wheel paths discontinuity in space is the highest, say, that the probability of deck is the highest.Repeat step S6, I
Can obtain each the dystropic number of times of car, according to dystropic number of times descending, dystropy vehicle can be obtained
Inventory, partial results such as table 9 below:
Table 9
S5. vehicle hot spot region bayonet socket is calculated.
5.1, statistics is grouped according to number plate, the number of times that vehicle occurs at each bayonet socket, and according to occurrence number descending,
Can obtain such as table 10 below for vehicle " Zhejiang AN0M**** ":
Table 10
5.2, threshold value M that vehicle is corresponding is calculatedv.For vehicle " Zhejiang AN0M**** ", putting down of each bayonet socket point occurrence number
Average is 11.3, therefore, and its threshold value MvIt is set to 11.3*80%=9.1.
5.3, vehicle thermal point structure region bayonet socket is obtained.According to occurrence number more than this constraint of average 80%, sequence in table
Number it is vehicle vehicle " Zhejiang AN0M**** " movable hot spot region bayonet socket for the bayonet socket of 1-15.
S6. current between calculating two hot spot region bayonet socket points of vehicle probability:
The bayonet socket point in vehicle thermal point structure region is done cartesian product, obtains bayonet socket pair, and according to the probability in S5, give
Every a pair bayonet socket to carrying out assignment, and choose forward and reverse in bigger probability.
As a example by vehicle " Zhejiang AN0M**** ", accumulative 15 thermal point structure region bayonet socket points, permissible after doing cartesian product
Obtain 225 bayonet sockets pair, then give each bayonet socket to assignment, such as in S5 P (31000300020402,
31000300023902)=51.4%, P (31000300023902,31000300020402)=1.4%, then Q
(31000300020402,31000300023902)=Q (31000300023902,31000300020402)=51.4%, Q
(Ki,Kj) represent bayonet socket KiAnd KjBetween undirected current probability.
S7. according to probability between S6 gained bayonet socket, all bayonet sockets are polymerized.
In the present embodiment, bayonet socket is polymerized by the way of probability connects.
Step7.1. obtaining can be with number plate of vehicle inventory.
Step7.2. from number plate inventory, take out a number, according to number, obtain this number plate thermal point structure region bayonet socket
(K1, K2, K3 Kn), is designated as array A0, and occurs in the number of times flashback arrangement of this bayonet socket according to vehicle.
Step7.3. first bayonet socket K1 in A0 is added in array A1, and K1 is removed from A0.
Step7.4. judge in K1 and A0 the undirected probability Q (K1, Ki) between each bayonet socket whether more than threshold value Ti, as
Fruit is, Ki adds to A1 and empty array A_new, and is removed from array A0 by Ki.
Step7.5. from array A_new, a bayonet socket Kj is taken out, it is judged that undirected between each bayonet socket in Kj and A0
Whether probability Q (Kj, Ki) is more than threshold value Ti, if it is, Ki adds to A1 and empty array A_new, and by Ki from array A0
Middle removal, removes Kj from array A_new.
Step7.6. Step7.5 is repeated, until A_new is empty.
Step7.7. increase array Ai, repeat step Step7.3-7.6.
Step7.8. Step7.7 is repeated, until A0 is empty.
Step7.9. Step7.2-7.8 is repeated, until number plate inventory is empty.
By above computing, the polymerization situation of all vehicle thermal point structure regions bayonet socket point can be obtained.
S8. according to the polymerization situation of bayonet socket point, vehicle fake-license probability Z is calculated.
If all bayonet sockets all assign to A1 group, say, that vehicle all thermal point structure region bayonet socket can connect
Come, as shown in Figure 3, then vehicle is described, and often movable region is at a contiguity place, this car relatively closely
Deck probability is less.
If bayonet socket is assigned in A1 combination A2 group than more uniform, illustrate that vehicle thermal point structure region can significantly be divided into
Liang Ge community, as shown in Figure 4, then illustrate that movable vehicle, in the relatively low region of two contiguities, simultaneously takes account of this vehicle
Have and the most abnormal redirect behavior, illustrate that this vehicle fake-license probability is higher.
If bayonet socket is distributed in multiple groups, explanation may have multiple car plate to misidentify into this car, is grouped the most, explanation
The deck probability of this vehicle is the least.
In the present embodiment, some numerical results such as table 11 below (sorting according to dystropy number of times):
Table 11
In this enforcement, when suspicion degree Z is more than or equal to 1 when, it is believed that this car has higher deck probability, we
It is found that in the middle of front 100 cars that behavior frequency of abnormity is most, only 6 car suspicion degree Z are more than 1, namely 100
Investigation range shorter to 6 car of car.
Claims (4)
1. the fake-licensed car detection method of a probability polymerization based on vehicle hot spot region, it is characterised in that: described fake license plate vehicle
Detection method comprises the following steps:
S1. the extraction of bayonet socket data: obtain card and make a slip of the tongue car record data, retain the dimension needed, including bayonet socket numbering, bayonet socket side
To, brand number, number plate kind, cross the car time；
S2. the cleaning of bayonet socket data；
S3. calculating between bayonet socket and flow to probability, process is as follows:
3.1, according to wheelpath, extract bayonet socket vector: by bayonet socket data according to brand number, block the car time of making a slip of the tongue and arrange
Sequence, obtains the wheelpath of each car, with the bayonet socket sequence (K of processa,Kb,Kc·Ki·Kn) represent, extract each
Bayonet socket pair adjacent in wheelpath, forms bayonet socket sequence vector (Ka,Kb)·(Ki, Kj)·。K a, represent a of vehicle process
Individual bayonet socket, vector (Ka,Kb) represent that sequence of cars is through two bayonet socket KaAnd Kb, and KaAnd KbIn wheelpath adjacent；
3.2, calculate between bayonet socket and flow to probability: to bayonet socket KiCounting, obtains KiBayonet socket flow out gross vehicle and, with count (Ki) table
Show.To vector (Ki,Kj) counting, obtain bayonet socket KiTo bayonet socket KjCurrent gross vehicle and, with cou nt (Ki,Kj) represent.Bayonet socket Ki
To bayonet socket KjThe probability that flows to be Pij=count (Ki,Kj)/count(Ki)；
S4. calculate dystropy vehicle inventory: according to the bayonet socket pair of each the car extracted in S2, calculate bayonet socket to generally
Rate, according to probability less than setting threshold value TiNumber of times, descending, choose front N row as required, as dystropy cleaning vehicle
Single, N chooses according to actual needs；
S5. vehicle hot spot region bayonet socket point is calculated: thermal point structure region bayonet socket point refers to the bayonet socket that vehicle is often captured, system
The number of times that meter vehicle occurs at each bayonet socket point, if greater than threshold value M setv, then it is assumed that this bayonet socket is that the focus of vehicle is lived
Dynamic region bayonet socket point；
S6. the probability that calculating vehicle is current between 2 hot spot region bayonet socket points: the focus card that each car is calculated in S5
Mouth does cartesian product, and the probability calculated according to S2, carries out assignment to every a pair bayonet socket, and choose forward and reverse in bigger
Probability；If the probability P (Ki, Kj) of bayonet socket Ki to the bayonet socket Kj < probability P (Kj, Ki) of bayonet socket Kj to bayonet socket Ki, then by P
(Kj, Ki) is assigned to bayonet socket to (Ki, Kj)；
S7. according to probability between S6 gained bayonet socket, all bayonet sockets are polymerized, it is ensured that each packets inner, for arbitrary bayonet socket
To (Ki, Kj), there is a paths from KiTo Kj, on path, the probability of all adjacent bayonet sockets pair is all not less than setting threshold value Ti, respectively
Between individual packet, for arbitrary bayonet socket Ki, there is not bayonet socket K in other groupsj, meet P (Ki,Kj) more than threshold value T seti；
S8. calculate the probability of vehicle fake-license, calculate vehicle fake-license probability Z, Z=N*i*s according to vehicle bayonet socket polymerization situation4, N table
Showing vehicle focus bayonet socket sum, i depends on number of packet L, if L=2, i=1, if L=3, i=1/2, otherwise i=0；s
Depending on the quantity ratio of bayonet socket in packet, NAi represents the quantity of bayonet socket in each group；S=max (NAi, 2)/max (Nai, 1),
Max (NAi, 1) represents that quantity is maximum, and max (NAi, 2) represents that quantity is second largest.
A kind of fake-licensed car detection method of probability polymerization based on vehicle hot spot region, its feature
It is: individual in described step S7, polymerization process is as follows:
Step7.1. obtaining can be with number plate of vehicle inventory；
Step7.2. from number plate inventory take out a number, according to number, obtain this number plate thermal point structure region bayonet socket (K1,
K2, K3 Kn), it is designated as array A0, and occurs in the number of times flashback arrangement of this bayonet socket according to vehicle；
Step7.3. first bayonet socket K1 in A0 is added in array A1, and K1 is removed from A0；
Step7.4. judge in K1 and A0 the undirected probability Q (K1, Ki) between each bayonet socket whether more than threshold value Ti, if
It is Ki to be added to A1 and empty array A_new, and Ki is removed from array A0；
Step7.5. from array A_new, a bayonet socket Kj is taken out, it is judged that undirected probability Q between each bayonet socket in Kj and A0
Whether (Kj, Ki) is more than threshold value Ti, if it is, Ki adds to A1 and empty array A_n ew, and by Ki from array A0
Remove, Kj is removed from array A_new；
Step7.6. Step7.5 is repeated, until A_new is empty；
Step7.7. increase array Ai, repeat step Step7.3-7.6；
Step7.8. Step7.7 is repeated, until A0 is empty；
Step7.9. Step7.2-7.8 is repeated, until number plate inventory is empty.
The fake-licensed car detection method of a kind of probability polymerization based on vehicle hot spot region, it is special
Levying and be: in described step S2, the cleaning process of bayonet socket data is as follows:
2.1, cleaning repeats record；
2.2, clean dirty data, described dirty data refers to that brand number does not meets the record of naming rule；
2.3, determine time interval, clean and record the most complete bayonet socket data in this interval, these situations include bayonet socket damage and
Power-off causes bayonet socket to work, or network interrupts and disk size deficiency causes data to fail to store, and cleans this bayonet socket institute
There are data.
The fake-licensed car detection method of a kind of probability polymerization based on vehicle hot spot region, it is special
Levy and be: in described step S4, threshold value TiIt is set, to bayonet socket K according to bayonet socket number plate recognition correct rate FiFor, TiTake
Value should meet F≤∑jPij<F-Ti, wherein j meets Pij>Ti, bayonet socket number plate recognition correct rate F=1-is (by bayonet socket still
The number plate not car record number excessively in number plate storehouse)/(all car record numbers excessively), TiRepresent bayonet socket KiThreshold value, PijRepresent bayonet socket Pi
Probability to other bayonet sockets.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610380318.6A CN106022296B (en) | 2016-06-01 | 2016-06-01 | A kind of fake-licensed car detection method of the probability polymerization based on vehicle hot spot region |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610380318.6A CN106022296B (en) | 2016-06-01 | 2016-06-01 | A kind of fake-licensed car detection method of the probability polymerization based on vehicle hot spot region |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106022296A true CN106022296A (en) | 2016-10-12 |
| CN106022296B CN106022296B (en) | 2019-05-28 |
Family
ID=57092885
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610380318.6A Active CN106022296B (en) | 2016-06-01 | 2016-06-01 | A kind of fake-licensed car detection method of the probability polymerization based on vehicle hot spot region |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106022296B (en) |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107329977A (en) * | 2017-05-27 | 2017-11-07 | 银江股份有限公司 | A kind of false-trademark car postsearch screening method based on probability distribution |
| CN107563288A (en) * | 2017-07-31 | 2018-01-09 | 东软集团股份有限公司 | A kind of recognition methods of fake-licensed car vehicle and device |
| CN107832475A (en) * | 2017-12-01 | 2018-03-23 | 浪潮软件集团有限公司 | Deployment control method, deployment control engine and deployment control system |
| CN108022427A (en) * | 2017-10-30 | 2018-05-11 | 深圳市赛亿科技开发有限公司 | A kind of recognition methods of fake license plate vehicle and system |
| CN108242153A (en) * | 2018-03-12 | 2018-07-03 | 小草数语（北京）科技有限公司 | Abnormal bayonet recognition methods and device |
| CN108665699A (en) * | 2017-03-30 | 2018-10-16 | 杭州海康威视数字技术股份有限公司 | There is the method and device in place in a kind of prediction vehicle |
| CN109741227A (en) * | 2019-01-07 | 2019-05-10 | 巩志远 | One kind is based on nearest neighbor algorithm prediction people room consistency processing method and system |
| CN110164138A (en) * | 2019-05-17 | 2019-08-23 | 湖南科创信息技术股份有限公司 | Based on bayonet to the recognition methods for the fake license plate vehicle for flowing to probability and system, medium |
| CN110164140A (en) * | 2019-06-05 | 2019-08-23 | 上海易点时空网络有限公司 | Deck detection system and device |
| CN110310478A (en) * | 2019-05-17 | 2019-10-08 | 湖南科创信息技术股份有限公司 | The recognition methods of fake license plate vehicle based on big data analysis and system, storage medium |
| CN111369804A (en) * | 2019-07-05 | 2020-07-03 | 杭州海康威视系统技术有限公司 | Vehicle data processing method and device, electronic equipment and storage medium |
| CN112150795A (en) * | 2019-06-26 | 2020-12-29 | 杭州海康威视数字技术股份有限公司 | Method and device for detecting vehicle track abnormity |
| CN112733047A (en) * | 2020-11-05 | 2021-04-30 | 浙江大华技术股份有限公司 | Vehicle foothold generation method, device, equipment and computer storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2001034799A (en) * | 1999-07-21 | 2001-02-09 | Mitsubishi Electric Corp | Automatic toll collection system for traveling vehicle and its method |
| CN101587643A (en) * | 2009-06-08 | 2009-11-25 | 宁波大学 | Identification method of fake-licensed cars |
| CN103914986A (en) * | 2014-03-14 | 2014-07-09 | 浙江宇视科技有限公司 | Method and device for fake-license-plate analysis |
| CN104732765A (en) * | 2015-03-30 | 2015-06-24 | 杭州电子科技大学 | Real-time urban road saturability monitoring method based on checkpoint data |
-
2016
- 2016-06-01 CN CN201610380318.6A patent/CN106022296B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2001034799A (en) * | 1999-07-21 | 2001-02-09 | Mitsubishi Electric Corp | Automatic toll collection system for traveling vehicle and its method |
| CN101587643A (en) * | 2009-06-08 | 2009-11-25 | 宁波大学 | Identification method of fake-licensed cars |
| CN103914986A (en) * | 2014-03-14 | 2014-07-09 | 浙江宇视科技有限公司 | Method and device for fake-license-plate analysis |
| CN104732765A (en) * | 2015-03-30 | 2015-06-24 | 杭州电子科技大学 | Real-time urban road saturability monitoring method based on checkpoint data |
Cited By (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108665699B (en) * | 2017-03-30 | 2020-04-03 | 杭州海康威视数字技术股份有限公司 | Method and device for predicting vehicle appearance place |
| CN108665699A (en) * | 2017-03-30 | 2018-10-16 | 杭州海康威视数字技术股份有限公司 | There is the method and device in place in a kind of prediction vehicle |
| CN107329977B (en) * | 2017-05-27 | 2019-08-16 | 银江股份有限公司 | A kind of false-trademark vehicle postsearch screening method based on probability distribution |
| CN107329977A (en) * | 2017-05-27 | 2017-11-07 | 银江股份有限公司 | A kind of false-trademark car postsearch screening method based on probability distribution |
| CN107563288A (en) * | 2017-07-31 | 2018-01-09 | 东软集团股份有限公司 | A kind of recognition methods of fake-licensed car vehicle and device |
| CN108022427A (en) * | 2017-10-30 | 2018-05-11 | 深圳市赛亿科技开发有限公司 | A kind of recognition methods of fake license plate vehicle and system |
| CN107832475A (en) * | 2017-12-01 | 2018-03-23 | 浪潮软件集团有限公司 | Deployment control method, deployment control engine and deployment control system |
| CN108242153A (en) * | 2018-03-12 | 2018-07-03 | 小草数语（北京）科技有限公司 | Abnormal bayonet recognition methods and device |
| CN109741227A (en) * | 2019-01-07 | 2019-05-10 | 巩志远 | One kind is based on nearest neighbor algorithm prediction people room consistency processing method and system |
| CN109741227B (en) * | 2019-01-07 | 2020-12-08 | 巩志远 | Processing method and system for predicting human-room consistency based on nearest neighbor algorithm |
| CN110164138A (en) * | 2019-05-17 | 2019-08-23 | 湖南科创信息技术股份有限公司 | Based on bayonet to the recognition methods for the fake license plate vehicle for flowing to probability and system, medium |
| CN110310478A (en) * | 2019-05-17 | 2019-10-08 | 湖南科创信息技术股份有限公司 | The recognition methods of fake license plate vehicle based on big data analysis and system, storage medium |
| CN110164140A (en) * | 2019-06-05 | 2019-08-23 | 上海易点时空网络有限公司 | Deck detection system and device |
| CN112150795A (en) * | 2019-06-26 | 2020-12-29 | 杭州海康威视数字技术股份有限公司 | Method and device for detecting vehicle track abnormity |
| CN112150795B (en) * | 2019-06-26 | 2022-05-06 | 杭州海康威视数字技术股份有限公司 | Method and device for detecting vehicle track abnormity |
| CN111369804A (en) * | 2019-07-05 | 2020-07-03 | 杭州海康威视系统技术有限公司 | Vehicle data processing method and device, electronic equipment and storage medium |
| CN111369804B (en) * | 2019-07-05 | 2022-04-05 | 杭州海康威视系统技术有限公司 | Vehicle data processing method and device, electronic equipment and storage medium |
| CN112733047A (en) * | 2020-11-05 | 2021-04-30 | 浙江大华技术股份有限公司 | Vehicle foothold generation method, device, equipment and computer storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106022296B (en) | 2019-05-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106022296A (en) | Fake plate vehicle detection method based on vehicle hot spot area probability aggregation | |
| CN105719489B (en) | A kind of fake-licensed car detection method that probability is flowed to based on bayonet vehicle | |
| CN104200669B (en) | Fake-licensed car recognition method and system based on Hadoop | |
| CN105225476B (en) | A kind of generation of track of vehicle, polymerization and device | |
| CN101587643B (en) | Identification method of fake-licensed cars | |
| WO2017157119A1 (en) | Method and device for identifying abnormal behavior of vehicle | |
| CN107329977B (en) | A kind of false-trademark vehicle postsearch screening method based on probability distribution | |
| CN107256394A (en) | Driver information and information of vehicles checking method, device and system | |
| CN106971552B (en) | Fake plate phenomenon detection method and system | |
| CN105488479B (en) | A kind of counterfeit vehicle registration plate identification method and device based on weighting local feature comparison | |
| CN108961747A (en) | A kind of urban road traffic state information extracting method under incomplete bayonet data qualification | |
| CN105448092B (en) | The analysis method and device of a kind of associated vehicle | |
| CN103246876A (en) | Image feature comparison based counterfeit vehicle registration plate identification method | |
| CN110111581A (en) | Target identification method, device, computer equipment and storage medium | |
| CN107346435A (en) | A kind of suspicion fake-licensed car catching method based on vehicle characteristics storehouse | |
| CN105513368A (en) | Uncertain information-based method for screening vehicles with false license plates | |
| CN108230724A (en) | A kind of urban mass-transit system Vehicle station name announcing missing data method for repairing and mending based on maximum probability estimation | |
| CN107993444B (en) | Suspected vehicle identification method based on bayonet vehicle-passing big data analysis | |
| CN103514745A (en) | Fake license plate vehicle recognition method based on intelligent transportation | |
| CN107610471A (en) | Vehicle fake-license detection method and system | |
| CN103700262B (en) | Automatic area acquisition method for fake-licensed vehicles | |
| CN106297304A (en) | A kind of based on MapReduce towards the fake-licensed car recognition methods of extensive bayonet socket data | |
| CN106651732A (en) | Highway different-vehicle card-change toll-dodging vehicle screening method and system | |
| CN107563288A (en) | A kind of recognition methods of fake-licensed car vehicle and device | |
| CN112734219B (en) | Vehicle transportation running behavior analysis method and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CP01 | Change in the name or title of a patent holder |
Address after: 310012 1st floor, building 1, 223 Yile Road, Hangzhou City, Zhejiang Province Patentee after: Yinjiang Technology Co.,Ltd. Address before: 310012 1st floor, building 1, 223 Yile Road, Hangzhou City, Zhejiang Province Patentee before: ENJOYOR Co.,Ltd. |
|
| CP01 | Change in the name or title of a patent holder |