CN105719489B - A kind of fake-licensed car detection method that probability is flowed to based on bayonet vehicle - Google Patents
A kind of fake-licensed car detection method that probability is flowed to based on bayonet vehicle Download PDFInfo
- Publication number
- CN105719489B CN105719489B CN201610172075.7A CN201610172075A CN105719489B CN 105719489 B CN105719489 B CN 105719489B CN 201610172075 A CN201610172075 A CN 201610172075A CN 105719489 B CN105719489 B CN 105719489B
- Authority
- CN
- China
- Prior art keywords
- bayonet socket
- probability
- bayonet
- 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.)
- Active
Links
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
Abstract
A kind of fake-licensed car detection method that probability is flowed to based on bayonet vehicle, is comprised the following steps：S1. the extraction of bayonet socket data；S2. the cleaning of bayonet socket data；S3. wheelpath is determined；S4. bayonet socket vector is extracted；S5. probability is flowed to according between bayonet socket vector calculating bayonet socket；S6. wheelpath probability is calculated：Wheelpath for including N number of point, 1 bayonet socket vector of N is obtained, probability is flowed to according to bayonet socket in S5, each vector corresponds to a probability, and 1 probable value of N is always obtained, is designated as Qm, m=1,2 ..., N 1, if QmLess than the bayonet socket K of settingiThreshold value Ti, then assert that an abnormal behavior occurs in the car, if abnormal behavior number is more, illustrate that deck probability is higher.Accurate bayonet socket coordinate and road network structure, simplified calculating, the fake-licensed car detection method that probability is flowed to based on vehicle of applicability well are avoided relying on the invention provides a kind of.
Description
Technical field
The present invention relates to intelligent transportation field, and in particular 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 the formalities such as other number plate of vehicles and driving license
The vehicle of road traveling.With expanding economy, vehicle population is more and more, and fake-licensed car is also continuously increased.Fake-licensed car can be upset
Management and control of the public security organ to public safety, because fake-licensed car does not have legal procedure and insurance, once traffic accident, driver occurs
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 taxes
Take, cause a large amount of losses of the national expenses of taxation, and upset the order of transport market.Fake-licensed car can damage the legitimate rights and interests of true car owner,
In vehicular traffic violation, accident treatment etc., true car owner will often serve as " person who spends money wastefully and foolishly ".
The identification investigation difficulty of this act of violating regulations of fake-licensed car is very big, and people's police are difficult the short time during on duty according to car
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 is referred to using advanced photoelectricity, computer, image procossing, pattern-recognition, remote data access etc.
Technology, to monitoring the car lane in section, bicycle lane carry out it is round-the-clock monitor in real time and record dependent image data, and from
The data such as the dynamic passage time for obtaining vehicle, place, travel direction, brand number, number plate color, body color.
In patent in published patent and examination, bayonet socket distribution and road network structure data, these sides are mainly based upon
Method includes：
(the patent No. of method one：CN201110280822.6)：Based on the time in bayonet socket database and geographical position come
Identify whether deck, if the difference for measuring the car time is less than 2 points of theoretical shortest route time, judge the car for deck
Car.
(the patent No. of method two：CN103914986A)：Based on bayonet socket communication information, letter is connected according to the bayonet socket pre-saved
Breath, judges to whether there is a paths in reachable path, and the bayonet socket quantity that the paths pass through is less than or equal to preset value N, if
It is no, then it is determined as fake-licensed car.
(the patent No. of method three：CN201310034242.8)：By the way that urban road is divided into grid, rail is travelled to vehicle
Mark is analyzed, if driving trace discontinuously if be determined as fake-licensed car.
Existing method general principle is the characteristic of utilization space, it is necessary to there is the accurate bayonet socket positional information (He of method one
Method three) or road grid data (method two and method three), and require that bayonet socket captures for vehicle 100%, it is actual to answer
In, these conditions are difficult to meet well.
The content of the invention
In order to overcome the accurate bayonet socket coordinate of the dependence of existing fake-licensed car detection method and road network structure, amount of calculation larger, suitable
With the deficiency that property is poor, avoid relying on accurate bayonet socket coordinate and road network structure the invention provides one kind, simplify calculating, applicability
The good fake-licensed car detection method that probability is flowed to based on vehicle.
The technical solution adopted for the present invention to solve the technical problems is：
A kind of fake-licensed car detection method that probability is flowed to based on bayonet vehicle, the detection method are comprised the following steps：
S1. the extraction of bayonet socket data：Obtain bayonet socket and cross car record data, retain the dimension of needs, including bayonet socket numbering, card
Mouth direction, brand number, number plate species, spend the car time；
S2. the cleaning of bayonet socket data；
S3. wheelpath is determined：According to brand number, number plate species, spending the car time is ranked up, and obtains each car
Wheelpath, i.e. bayonet socket sequence, the bayonet socket sequence include bayonet socket numbering and bayonet socket direction；
S4. bayonet socket vector is extracted：Bayonet socket pair adjacent in each garage's wheel paths is extracted, forms bayonet socket sequence vector,
Vector (Ki,Kj) represent that car is passing through bayonet socket KiAfter can be by bayonet socket KjCapture；
S5. probability is flowed between calculating bayonet socket：To KiCount, bayonet socket outflow vehicle summation is obtained, to vector (Ki,Kj) meter
Number, obtains bayonet socket KiTo bayonet socket KjCurrent record sum, bayonet socket KiTo bayonet socket KjThe probability that flows to be Pij=count (Ki,Kj)/
count(Ki)；
The probability that the bayonet socket flows to all bayonet sockets is calculated to each bayonet socket, if the current record between two bayonet sockets
Number is zero, then current probability is designated as 0%；
S6. wheelpath probability is calculated：Wheelpath for including N number of point, N-1 bayonet socket vector is obtained, according to S5
Middle bayonet socket flows to probability, and each vector corresponds to a probability, and N-1 probable value is always obtained, is designated as Qm, m=1,2 ..., N-
1, if QmLess than the bayonet socket K of settingiThreshold value Ti, then assert that an abnormal behavior (deck suspicion) occurs in the car.
Further, the fake-licensed car detection method also comprises the following steps：
S7. according to QmLess than threshold value TiNumber sequence, number is more, it is meant that suspicion degree is larger, preferential investigation time
The most suspicion car of number.
Further, in the step S6, threshold value TiSet according to bayonet socket number plate recognition correct rate F, to bayonet socket Ki
For, TiValue should meet F<=∑jPij<F+Ti, wherein j meets Pij>Ti, bayonet socket number plate recognition correct rate F=1- (passes through
The still number plate of bayonet socket crosses car record number not in number plate storehouse)/(all to cross cars record number), TiRepresent bayonet socket KiThreshold value,
PijRepresent bayonet socket KiTo bayonet socket KjFlow to probability.
Further, in the step S2, the cleaning process of bayonet socket data is as follows：
2.1st, cleaning repeats to record；
2.2nd, dirty data is cleaned, that is, deletes the record that brand number does not meet naming rule；
2.3rd, time interval is determined, cleans the bayonet socket data that record is not complete in the section.
The present invention general principle be：The certain event of probability, frequency is more, and the probability not occurred once is got over
It is low.Under normal circumstances, vehicle passes through a bayonet socket KiAfterwards, can be preferentially by neighbouring bayonet socket Kj(Direct Acquisition refers to Direct Acquisition
It is by bayonet socket KiAfterwards, by bayonet socket KjBefore capture, do not captured by other bayonet sockets), distant bayonet socket is reached, it is middle
Need by other more bayonet sockets, only in the case of not by any one bayonet socket capture on road, being possible to can quilt
Bayonet socket Direct Acquisition farther out, distance is more remote, lower by the probability of Direct Acquisition.By counting all tracks of vehicle, can obtain
Take from a bayonet socket, by the probability of other bayonet socket Direct Acquisitions.If vehicle is often captured by the relatively low bayonet socket of probability, say
Bright vehicle often jumps directly to bayonet socket farther out, that is to say, that the track of vehicle spatially is discontinuous, such car
The possibility of deck is larger.
Beneficial effects of the present invention are mainly manifested in：1st, the present invention need not rely on bayonet socket geographical coordinate and road network structure, individual
Other shortage of data does not interfere with this algorithm, strong applicability.2nd, the present invention has the small feature of amount of calculation.It is steady that bayonet socket, which flows to probability,
Fixed parameter, one month or only need multiple moons calculate once.After determining wheelpath, by once matching i.e. detectable set
Board car.3rd, the present invention can effectively be sorted to fake-licensed car probability, determine emphasis suspected vehicles.
Brief description of the drawings
Fig. 1 is a kind of flow chart for the fake-licensed car detection method that probability is flowed to based on bayonet vehicle.
Fig. 2 is the schematic diagram that track of vehicle is shown to map.
Embodiment
The invention will be further described below.
Referring to Figures 1 and 2, a kind of fake-licensed car detection method that probability is flowed to based on bayonet vehicle, is comprised the following steps：
S1. the extraction of data：Obtain bayonet socket and cross car record data, retain the dimension of needs, including bayonet socket numbering, bayonet socket side
To, brand number, number plate species, cross the car time.(bayonet socket numbering uniquely determines bayonet socket crossing position, and bayonet socket direction determines bayonet socket
Shooting direction, i.e. direction of traffic, number plate species and brand number uniquely determine a motor vehicle)
The present embodiment has extracted the data of 489 bayonet sockets records on Hangzhou 1-January of January 27, and altogether 129534497
Bar, bayonet socket data format 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 species |
| JGSJ | VARchar(20) | Spend the car time |
Table 1
Wherein KKID+FXBH uniquely determines a bayonet socket, and HPHM+HPZL uniquely determines an automobile, and JGSJ is accurate to the second.
(in following steps, bayonet socket ID contains bayonet socket direction, and brand number contains number plate species, repeated no more)
S2. the cleaning of data
2.1st, duplicate data is cleaned：For bayonet socket, when catching a vehicle passed through, more datas may be produced, are made
It is as shown in table 2 below into the repetition of data：
Table 2
3rd article consistent with the 4th article of the passed through bayonet socket ID of car record excessively, and the car time excessively is identical, this to belong to repetition note
Record.
When reason is due to bayonet socket capture vehicle, a plurality of record may be produced.Define same vehicle, same card
Mouthful, and be recorded as repetition of the time error no more than threshold value Δ T (the present embodiment is set to 4 seconds) records, and removes and repeats to record.
2.2nd, dirty data is cleaned：Due to brand number be bayonet system according to picture recognition, a number of car plate be present
Character, bayonet socket None- identified, the brand number in record do not meet naming rule, specifically included：" None- identified ", " NULL ",
Brand number contain symbol "”.The partial data is cleaned, 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 B711T | 2016-01-25 11:31:34 |
| 4 | Zhejiang A00NT | 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
2.3rd, cleaning records incomplete bayonet socket data：Under practical situation, due to power-off, suspension, bayonet socket damage etc. factor,
Missing be present in the data of part bayonet socket.For recording incomplete bayonet socket data, the bayonet socket data are cleaned.
In present case, the time interval of selection is January 1 to January 27, adds up in 489 bayonet sockets have 169 bayonet sockets extremely
There is shortage of data within few 1 day, clean all data of these bayonet sockets.
Bayonet socket shortage of data is defined as follows：If the bayonet socket car record of crossing of one day crosses the 1/20 of car record less than average daily, should
Bayonet socket this day data missing.
S3. wheelpath is determined
According to brand number, cross car time-sequencing and can obtain wheelpath.Wheelpath includes three part (bayonet sockets
ID, brand number, spend the car time), the bayonet socket and spend the car time that expression vehicle passes through successively.Form is as follows：The present embodiment shares
2123568 wheelpaths, (ellipsis part is non-display portion) as shown in table 4 below.
| Sequence number | Brand number | Bayonet socket ID | Spend the car time |
| 1 | Zhejiang A2M1** | 31000300007402 | 2016-01-04 07:51:09 |
| 2 | Zhejiang A2M1** | 31000300010702 | 2016-01-04 08:48:26 |
| 3 | Zhejiang A2M1** | 31000300010904 | 2016-01-04 08:50:13 |
| 4 | Zhejiang A2M1** | 31000300004504 | 2016-01-04 08:50:38 |
| 5 | Zhejiang A2M1** | 31000300004502 | 2016-01-04 08:50:58 |
| 6 | Zhejiang A2M1** | 31000300019902 | 2016-01-04 08:53:36 |
| 7 | Zhejiang A2M1** | 31000300005402 | 2016-01-04 08:59:18 |
| ··· | ······ | ······ | ······ |
Table 4
S4. bayonet socket vector is extracted:For two bayonet sockets adjacent in same garage's wheel paths, take out successively, as
Bayonet socket vector.For S3 cases, can be taken off six vectors (31,000,300 007402,31000300010702),
(31000300010702,31000300010904)、(31 000300010904,31000300004504)、
(31000300004504,3100030000450 2)、(31000300004502,31000300019902)、
(31000300019902,3100030 0005402)。
To 2123568 wheelpaths in the present embodiment, extracted vector is distinguished, what all wheelpaths can be taken out
Vector is 85259515.
S5. probability is flowed between calculating bayonet socket
Count all vector (Ki,Kj), it can obtain from bayonet socket KiOutflow, flows to bayonet socket KjVehicle number.Count Ki, I
Can obtain from KiThe vehicle fleet of outflow, obtain (ellipsis part is non-display portion) as shown in table 5 below.
Table 5
Bayonet socket flows to probability and bayonet socket distribution and road network structure is embodied in another dimension.If bayonet socket is distributed or road
Significant changes occur for web frame, and the probability needs to recalculate (morning and evening track, restricted driving etc. need not recalculate).
S6. wheelpath probability is calculated
We are extracted the wheelpath of each car in S3.One wheelpath for having N number of point corresponds to N-1
Bayonet socket vector, each bayonet socket vector, a corresponding bayonet socket flow to probability, that is to say, that one by N number of driving rail put and formed
Mark corresponds to N-1 probable value, is designated as Qm, m=1,2 ..., N-1, and with bayonet socket KiThreshold value TiIt is compared, such as table 6 below：
Table 6
In the present embodiment, bayonet socket threshold value T is calculatediCalculating process it is as follows：
6.1st, all bayonet sockets are counted first crosses car sum and number plate error number (vehicle of the brand number not in number plate storehouse).
Total car quantity of crossing is：87383083, number plate error number is：25244 76；Bayonet socket number plate recognition correct rate F, which can be calculated, is
97.1%.
6.2nd, threshold value T is calculated to each bayonet socketi：Such as bayonet socket 31000300015401, with other each bayonet sockets
Between probability according to descending arrange (ellipsis part is non-display portion) as shown in table 7 below：
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 T corresponding to each bayonet socketi, obtain that (ellipsis part is does not show such as table 8 below
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, reference picture 2, it has been found that this section is included in the wheelpath of 14 points, has 5 probability to be less than
Threshold value Ti。
If this 14 bayonet socket points are shown on map, it can be found that this 14 bayonet socket points occur 5 times discontinuously, it is bright
Aobvious to be scattered in two tracks, wherein this 8 points of k1, k2, k4, k5, k10, k11, k12, k13 are rendered obvious by a track, k3,
K6, k7, k8, k9, k14 are in substantially a track.
S7. suspicion degree sorts：QiLess than threshold value TiOnce, we are designated as once abnormal behavior, if abnormal behavior number
It is more, illustrate that discontinuity of the wheel paths in space is very high, that is to say, that the possibility of deck is very high, according to QiLess than threshold
Value TiNumber sequence, can obtain deck suspicion degree sequence.Present case partial results (ellipsis part as shown in table 9 below
For non-display portion)：
| Sequence number | Brand number | Total occurrence number | Abnormal behaviour number |
| 1 | Zhejiang AA59** | 892 | 28 |
| 2 | Zhejiang A925** | 475 | 22 |
| 3 | Zhejiang A2EM** | 453 | 21 |
| 4 | Zhejiang A2KA** | 608 | 21 |
| 5 | Zhejiang A255** | 251 | 19 |
| 6 | Zhejiang AK5X** | 500 | 18 |
| 7 | Zhejiang AC29** | 160 | 17 |
| 8 | Zhejiang A9EN** | 361 | 17 |
| 9 | Zhejiang A295** | 556 | 17 |
| 10 | Zhejiang AH52** | 75 | 16 |
| ······ | ······ | ······ | ······ |
| ······ | ······ | ······ | ······ |
Table 9
Abnormal behaviour number is higher, that is, the vehicle that deck suspicion degree is higher, can preferentially investigate.
Claims (4)
- A kind of 1. fake-licensed car detection method that probability is flowed to based on bayonet vehicle, it is characterised in that：The detection method include with Lower step：S1. the extraction of bayonet socket data：Obtain bayonet socket and cross car record data, retain the dimension of needs, including bayonet socket numbering, bayonet socket side To, brand number, number plate species and cross the car time；S2. the cleaning of bayonet socket data；S3. wheelpath is determined：It is ranked up according to brand number, number plate species, car time excessively, obtains the driving of each car Track, i.e. bayonet socket sequence, the bayonet socket sequence include bayonet socket numbering and bayonet socket direction；S4. bayonet socket vector is extracted：Bayonet socket pair adjacent in each garage's wheel paths is extracted, forms bayonet socket sequence vector, vector (Ki,Kj) represent that car is passing through bayonet socket KiAfter can be by bayonet socket KjCapture；S5. probability is flowed between calculating bayonet socket：To KiCount, bayonet socket outflow vehicle summation is obtained, to vector (Ki,Kj) count, obtain To bayonet socket KiTo bayonet socket KjCurrent record sum, bayonet socket KiTo bayonet socket KjThe probability that flows to be Pij=cout (Ki,Kj)/count (Ki)；The probability that the bayonet socket flows to all bayonet sockets is calculated to each bayonet socket, if the current record number between two bayonet sockets is Zero, then current probability is designated as 0%, flows to probability PijVehicle is expressed by bayonet socket KiBy bayonet socket K after capturejThe probability of capture；S6. wheelpath probability is calculated：Wheelpath for including N number of point, N-1 bayonet socket vector is obtained, is blocked according in S5 Mouth flows to probability, and each vector corresponds to a probability, and N-1 probable value is always obtained, is designated as Qm, m=1,2 ..., N-1, such as Fruit QmLess than the bayonet socket K of settingiThreshold value Ti, then assert that an abnormal behavior, i.e. deck suspicion occurs in the car.
- A kind of 2. fake-licensed car detection method that probability is flowed to based on bayonet vehicle as claimed in claim 1, it is characterised in that：Institute Fake-licensed car detection method is stated also to comprise the following steps：S7. according to QmLess than threshold value TiNumber sequence, number is more, it is meant that suspicion degree is larger, preferential to investigate number most More suspicion cars.
- 3. a kind of fake-licensed car detection method that probability is flowed to based on bayonet vehicle as claimed in claim 1 or 2, its feature are existed In：In the step S6, threshold value TiSet according to bayonet socket number plate recognition correct rate F, to bayonet socket KiFor, TiValue should Meet F<=∑jPij<F+Ti, wherein j meets Pij>Ti, bayonet socket number plate recognition correct rate F=1- (pass through bayonet socket but number plate Car record number is crossed not in number plate storehouse)/(all to cross car record number), TiRepresent bayonet socket KiThreshold value, PijRepresent bayonet socket KiTo card Mouth KjFlow to probability.
- 4. a kind of fake-licensed car detection method that probability is flowed to based on bayonet vehicle as claimed in claim 1 or 2, its feature are existed In：In the step S2, the cleaning process of bayonet socket data is as follows：2.1st, cleaning repeats to record；2.2nd, dirty data is cleaned, that is, deletes the record that brand number does not meet naming rule；2.3rd, time interval is determined, cleans the bayonet socket data that record is not complete in the section.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610172075.7A CN105719489B (en) | 2016-03-24 | 2016-03-24 | A kind of fake-licensed car detection method that probability is flowed to based on bayonet vehicle |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610172075.7A CN105719489B (en) | 2016-03-24 | 2016-03-24 | A kind of fake-licensed car detection method that probability is flowed to based on bayonet vehicle |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105719489A CN105719489A (en) | 2016-06-29 |
| CN105719489B true CN105719489B (en) | 2018-01-30 |
Family
ID=56159221
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610172075.7A Active CN105719489B (en) | 2016-03-24 | 2016-03-24 | A kind of fake-licensed car detection method that probability is flowed to based on bayonet vehicle |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105719489B (en) |
Families Citing this family (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106448178B (en) * | 2016-09-05 | 2019-12-20 | 青岛海信网络科技股份有限公司 | Fake-licensed vehicle analysis method and device |
| CN106297304A (en) * | 2016-09-08 | 2017-01-04 | 同济大学 | A kind of based on MapReduce towards the fake-licensed car recognition methods of extensive bayonet socket data |
| WO2018176191A1 (en) * | 2017-03-27 | 2018-10-04 | 深圳中兴力维技术有限公司 | Method and apparatus for identifying vehicle with fake registration plate |
| 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 |
| 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 |
| CN109272034B (en) * | 2018-09-07 | 2021-04-30 | 佳都新太科技股份有限公司 | Missing vehicle license plate prediction method and processing terminal |
| CN111179603B (en) * | 2018-11-09 | 2021-03-02 | 杭州海康威视数字技术股份有限公司 | Vehicle identification method and device, electronic equipment and storage medium |
| CN109493608B (en) * | 2018-12-06 | 2020-10-16 | 湖南科创信息技术股份有限公司 | Method and system for recognizing illegal operating vehicle and computer readable storage medium |
| CN110164138B (en) * | 2019-05-17 | 2021-02-09 | 湖南科创信息技术股份有限公司 | Identification method and system of fake-licensed vehicle based on bayonet convection direction probability and medium |
| CN110310478B (en) * | 2019-05-17 | 2020-12-18 | 湖南科创信息技术股份有限公司 | Method and system for identifying fake-licensed vehicle based on big data analysis and storage medium |
| CN111223305B (en) * | 2019-12-25 | 2022-05-17 | 华为技术有限公司 | Method and device for detecting illegal card involvement |
| CN111767776B (en) * | 2019-12-28 | 2024-03-29 | 西安宇视信息科技有限公司 | Abnormal license plate selecting method and device |
| CN112885101B (en) * | 2021-03-30 | 2022-06-14 | 浙江大华技术股份有限公司 | Method and device for determining abnormal equipment, storage medium and electronic device |
Family Cites Families (11)
| 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 |
| JP5085148B2 (en) * | 2007-02-08 | 2012-11-28 | 株式会社東芝 | Toll collection system, toll collection method |
| EP2009610B1 (en) * | 2007-06-26 | 2010-07-28 | Siemens Aktiengesellschaft | Method and device for determining a traffic quantity relating to a section of a street network |
| CN101587643B (en) * | 2009-06-08 | 2010-11-03 | 宁波大学 | Identification method of fake-licensed cars |
| CN102436746B (en) * | 2011-09-29 | 2014-10-22 | 杭州海康威视系统技术有限公司 | High efficient and real-time analytical method of vehicle fake license suspicion and apparatus thereof |
| CN102426786B (en) * | 2011-11-15 | 2014-02-12 | 无锡港湾网络科技有限公司 | Intelligent video analyzing system and method for automatically identifying fake plate vehicle |
| CN103377556B (en) * | 2012-04-26 | 2017-04-05 | 上海竞天科技股份有限公司 | The detection means of fake license plate vehicle, detecting system and its detection method |
| CN103116989B (en) * | 2013-01-29 | 2015-10-21 | 江苏省邮电规划设计院有限责任公司 | Based on the catching method of the fake-licensed car vehicle of smart city |
| CN103914986B (en) * | 2014-03-14 | 2016-07-13 | 浙江宇视科技有限公司 | The method and apparatus that a kind of deck is analyzed |
| CN104517445A (en) * | 2014-12-09 | 2015-04-15 | 浪潮电子信息产业股份有限公司 | Fake plate vehicle recognition method based on big data |
| CN104933870B (en) * | 2015-05-21 | 2017-04-12 | 中兴软创科技股份有限公司 | Vehicle fake plate identification method and device based on vehicle behavior analysis |
-
2016
- 2016-03-24 CN CN201610172075.7A patent/CN105719489B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN105719489A (en) | 2016-06-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105719489B (en) | A kind of fake-licensed car detection method that probability is flowed to based on bayonet vehicle | |
| CN106022296B (en) | A kind of fake-licensed car detection method of the probability polymerization based on vehicle hot spot region | |
| CN104200669B (en) | Fake-licensed car recognition method and system based on Hadoop | |
| CN108961747B (en) | A kind of urban road traffic state information extracting method under incomplete bayonet data qualification | |
| CN105225476B (en) | A kind of generation of track of vehicle, polymerization and device | |
| Bordagaray et al. | Capturing the conditions that introduce systematic variation in bike-sharing travel behavior using data mining techniques | |
| CN106971534A (en) | Commuter characteristic analysis method based on number plate data | |
| CN107329977B (en) | A kind of false-trademark vehicle postsearch screening method based on probability distribution | |
| CN112447041B (en) | Method and device for identifying operation behavior of vehicle and computing equipment | |
| CN107610471A (en) | Vehicle fake-license detection method and system | |
| CN106297304A (en) | A kind of based on MapReduce towards the fake-licensed car recognition methods of extensive bayonet socket data | |
| CN103700262B (en) | Automatic area acquisition method for fake-licensed vehicles | |
| CN105913668B (en) | Method is surveyed in a kind of orientation deck car test based on huge traffic data statistics | |
| CN103413440A (en) | Fake-licensed vehicle identification method based on smart city data base and identification rule base | |
| CN105260832A (en) | Performance evaluation method for taxi drivers based on order data | |
| CN109615853A (en) | Identify the method and apparatus of the doubtful illegal operation vehicle of highway | |
| CN106651732A (en) | Highway different-vehicle card-change toll-dodging vehicle screening method and system | |
| CN104318113A (en) | Passenger transfer spatial-temporal characteristics based method and system for calculating passengers' boarding stations | |
| CN110164136B (en) | Fake-licensed vehicle identification method | |
| CN111078973A (en) | Fake-licensed vehicle identification method and equipment based on big data and storage medium | |
| CN113470369A (en) | Method and system for judging true number plate of fake-licensed vehicle based on multi-dimensional information | |
| CN108681741A (en) | Based on the subway of IC card and resident's survey data commuting crowd's information fusion method | |
| CN110491157A (en) | A kind of vehicle correlating method based on parking data and bayonet data | |
| CN106781467A (en) | A kind of bus passenger based on collaborative filtering is swiped the card site information extracting method | |
| CN107730717B (en) | A kind of suspicious card identification method of public transport based on feature extraction |
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 | ||
| 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. |