CN108764197A - With vehicle identification method, device, terminal and computer readable storage medium - Google Patents
With vehicle identification method, device, terminal and computer readable storage medium Download PDFInfo
- Publication number
- CN108764197A CN108764197A CN201810571504.7A CN201810571504A CN108764197A CN 108764197 A CN108764197 A CN 108764197A CN 201810571504 A CN201810571504 A CN 201810571504A CN 108764197 A CN108764197 A CN 108764197A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- monitoring point
- monitored
- frequent
- support
- 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.)
- Pending
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
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
- G06V20/54—Surveillance or monitoring of activities, e.g. for recognising suspicious objects of traffic, e.g. cars on the road, trains or boats
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
- G06V30/14—Image acquisition
- G06V30/148—Segmentation of character regions
- G06V30/153—Segmentation of character regions using recognition of characters or words
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/08—Detecting or categorising vehicles
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Traffic Control Systems (AREA)
Abstract
Disclosing a kind of adjoint vehicle identification method, device, terminal and computer readable storage medium this method includes：Choose monitoring point；It is marked respectively in given monitoring time section and is monitored whether vehicle occurs in monitoring point；It according to monitored vehicle the case where monitoring point occurs, obtains and is monitored vehicle, in the probability that monitoring monitoring point occurs, and be denoted as support；Frequent 1 item collection of iterative extraction successively, frequent 2 item collection, frequent 3 item collection ..., frequent i item collections filter out the vehicle group of support >=given support；Under conditions of given frequent item set number, the vehicle group of confidence level >=given confidence threshold value is obtained, as waiting investigating with vehicle group.The device is implemented for this method.The step of method that the adjoint vehicle identification program stored in the terminal and computer readable storage medium realizes this with vehicle identification when being executed by processor.It can identify the vehicle often occurred together in the case where license plate number is unknown from the data of magnanimity.
Description
Technical field
The present invention relates to technical field of intelligent traffic, more particularly to a kind of adjoint vehicle identification method, device, terminal and
Computer readable storage medium.
Background technology
Refer to that with certain probability, there are the vehicles of accompanying relationship with tracking vehicle within a certain period of time with vehicle.This vehicle
The great suspicion with mutually shielding and clique's crime, monitors and identifies with vehicle, can effectively reduce road safety early
Risk factor in system, to preventing public security related with road is reduced and criminal case, it may have highly important meaning.
Invention content
In view of this, the present invention provides a kind of adjoint vehicle identification method, device, terminal and computer-readable storage mediums
Matter can identify the vehicle often occurred together, as the row of waiting in the case where license plate number is unknown from the data of magnanimity
Look into vehicle group.Thus more suitable for practicality.
In order to reach above-mentioned first purpose, the technical solution of adjoint vehicle identification method provided by the invention is as follows：
Adjoint vehicle identification method provided by the invention includes the following steps：
Choose monitoring point, respectively monitoring point 1, monitoring point 2 ..., monitoring point m；
It is marked respectively in given monitoring time section and is monitored vehicle, including vehicle 1, vehicle 2 ..., whether vehicle n is in the prison
Measuring point, including monitoring point 1, monitoring point 2 ..., monitoring point m occur；
According to the monitored vehicle, including vehicle 1, vehicle 2 ..., vehicle n is in the monitoring point, including monitoring point 1, monitoring point
2 ..., the case where monitoring point m occurs, obtains and is monitored vehicle, including vehicle 1, vehicle 2 ..., vehicle n in the monitoring monitoring point, including
Monitoring point 1, monitoring point 2 ..., the probability that monitoring point m occurs, and it is denoted as support；
Frequent 1 item collection of iterative extraction successively, frequent 2 item collection, frequent 3 item collection ..., frequent i item collections, filter out support >=
The vehicle group of given support；
Under conditions of given frequent item set number, the vehicle group of confidence level >=given confidence threshold value is obtained, as waiting for
Investigation is with vehicle group.
Adjoint vehicle identification method provided by the invention also can be used following technical measures and further realize.
Preferably, described according to the monitored vehicle, including vehicle 1, vehicle 2 ..., vehicle n is in the monitoring point, including prison
The case where measuring point 1, monitoring point 2 ..., monitoring point m occurs, obtains and is monitored vehicle, including vehicle 1, and vehicle 2 ..., vehicle n is in the prison
Monitoring point, including monitoring point 1, monitoring point 2 ..., the probability that monitoring point m occurs are surveyed, and is denoted as support and specifically includes following step
Suddenly：
The monitored vehicle, including vehicle 1, vehicle 2 ..., vehicle n are indicated with abscissa；Ordinate indicates the monitoring point, packet
Monitoring point 1, monitoring point 2 ..., monitoring point m are included, if the monitored vehicle appears in the monitoring point, corresponding coordinate mark
It is denoted as 1；If the monitored vehicle does not appear in the monitoring point, corresponding coordinate is labeled as 0, obtains the monitored vehicle
, including vehicle 1, vehicle 2 ..., vehicle n and the monitoring point, including monitoring point 1, monitoring point 2 ..., corresponding between the m of monitoring point close
System；
According to the monitored vehicle, including vehicle 1, vehicle 2 ..., vehicle n and the monitoring point, including monitoring point 1, monitoring point
Correspondence between 2 ..., monitoring point m obtains by calculating and is monitored vehicle, including vehicle 1, vehicle 2 ..., vehicle n is in the prison
Monitoring point, including monitoring point 1, monitoring point 2 ..., the probability that monitoring point m occurs are surveyed, and is denoted as support.
Preferably, the expression formula of the support is：
Wherein, support (A)-support, count (A)-are monitored vehicle and appear in monitoring point, including monitoring point 1,
Monitoring point 2 ..., the number of monitoring point m, the number of m-monitoring point.
Preferably,
The result of frequent 1 item collection is shaped like { vehicle 1 }, { vehicle 3 }, { vehicle 6 } ...；
The result of frequent 2 item collection is shaped like { vehicle 1, vehicle 2 }, { vehicle 1, vehicle 3 }, { vehicle 3, vehicle 5 } ...；
The result of frequent 3 item collection is shaped like { vehicle 1, vehicle 2, vehicle 3 }, { vehicle 3, vehicle 5, vehicle 6 }, { vehicle 8, vehicle 11, vehicle 18 } ...；
And so on, until obtaining the frequent i item collections.
Preferably, frequently i+1 item collections are obtained by each frequent i item collections.
Preferably, the expression formula of the confidence level is：
Wherein,
confidence(A->B there is the probability for causing monitored vehicle B to occur in)-monitored vehicle A, support (A,
B)-and it is monitored the probability that vehicle A and monitored vehicle B occurs simultaneously, support (A)-is monitored the probability that vehicle A occurs.
In order to reach above-mentioned second purpose, the technical solution of adjoint vehicle identifier provided by the invention is as follows：
Adjoint vehicle identification device provided by the invention includes：
Camera or video camera are laid in the monitoring point of selection, for from the monitoring point of the selection by vehicle
Taken pictures or imaged, with obtain from the monitoring point of the selection by vehicle car plate image；
Image identification unit, for from the monitoring point of the selection by vehicle car plate image be identified after
Obtain the license plate number in the license plate image；
Monitored marking of cars unit is monitored vehicle, including vehicle for being marked respectively in given monitoring time section
1, vehicle 2 ..., whether vehicle n is in the monitoring point, including monitoring point 1, monitoring point 2 ..., monitoring point m appearance；
Support acquiring unit, for according to the monitored vehicle, including vehicle 1, vehicle 2 ..., vehicle n in the monitoring point,
Including monitoring point 1, the case where monitoring point 2 ..., monitoring point m occurs, obtains and be monitored vehicle, including vehicle 1, vehicle 2 ..., vehicle n exist
The monitoring monitoring point, including monitoring point 1, monitoring point 2 ..., the probability that monitoring point m occurs, and it is denoted as support；
Support screening unit, for frequent 1 item collection of iterative extraction successively, frequent 2 item collection, frequent 3 item collection ..., frequent i
Item collection filters out the vehicle group of support >=given support；
It waits investigating with vehicle group acquiring unit, be used under conditions of given frequent item set number, acquisition confidence level >=
The vehicle group of given confidence threshold value, as waiting investigating with vehicle group.
Adjoint vehicle identifier provided by the invention also can be used following technical measures and further realize.
Preferably, the adjoint vehicle identification device further includes：
Table drawing unit, for indicating the monitored vehicle, including vehicle 1, vehicle 2 ..., vehicle n with abscissa；Ordinate
The monitoring point, including monitoring point 1, monitoring point 2 ..., monitoring point m are indicated, if the monitored vehicle appears in the monitoring
Point, then corresponding coordinate is labeled as 1；If the monitored vehicle does not appear in the monitoring point, corresponding coordinate is labeled as
0, draw the monitored vehicle, including vehicle 1, vehicle 2 ..., vehicle n and the monitoring point, including monitoring point 1, monitoring point 2 ..., prison
The table of correspondence between measuring point m.
In order to reach above-mentioned third purpose, the technical solution of adjoint vehicle identification terminal provided by the invention is as follows：
Adjoint vehicle identification terminal provided by the invention includes camera or video camera, processor, memory and storage
On the memory and the adjoint vehicle identification program that can run on the processor, wherein：
The camera either video camera for from the monitoring point of the selection by vehicle taken pictures or taken the photograph
Picture, with obtain from the monitoring point of the selection by vehicle car plate image；
The adjoint vehicle identification program realizes adjoint vehicle identification provided by the invention when being executed by the processor
The step of method；
Wherein,
The camera either video camera can by take pictures or image obtain from the point being monitored by vehicle
The image of car plate upload the processor, the adjoint vehicle identification program can be known by the image to the car plate
The license plate number in the license plate image is not obtained afterwards.
In order to reach above-mentioned 4th purpose, the technical solution of computer readable storage medium provided by the invention is as follows：
It is stored on computer readable storage medium provided by the invention with vehicle identification program, the adjoint vehicle is known
Other program realizes the step of method of adjoint vehicle identification provided by the invention when being executed by processor.
The m prison of adjoint vehicle recognition methods, device, terminal and computer readable storage medium provided by the invention in selection
Measuring point in monitoring in the given period from the m monitoring point by n monitored vehicle then carried by an iteration
The frequent i item collections for taking n monitored vehicle to occur m monitoring point, under conditions of given frequent item set number, with confidence level
It is used as more than or equal to the vehicle group of given confidence threshold value and waits investigating adjoint vehicle group.This method only needs to be selected
Camera or video camera for monitoring vehicle pass-through is arranged in m monitoring point, and by image identification unit to by camera
The picture for the monitored vehicle that either video camera obtains or the license plate number in video resource are identified, and then, pass through calculating
It can be obtained and wait investigating with vehicle group, operation equipment is simple, of low cost.Also, due to applying companion provided by the invention
During vehicle recognition methods, it is that camera by being set to m monitoring point or video camera are random that n amounts, which are monitored vehicle,
Shooting, it, can be in the case where license plate number be unknown, from the data of magnanimity without learning the license plate number of vehicle to be investigated in advance
In identify the vehicle group often occurred together.
Description of the drawings
By reading the detailed description of hereafter preferred embodiment, various other advantages and benefit are common for this field
Technical staff will become clear.Attached drawing only for the purpose of illustrating preferred embodiments, and is not considered as to the present invention
Limitation.And throughout the drawings, the same reference numbers will be used to refer to the same parts.In the accompanying drawings：
Fig. 1 is the step flow chart for the adjoint vehicle identification method that the embodiment of the present invention one provides；
Fig. 2 is the specific steps flow chart for the adjoint vehicle identification method that the embodiment of the present invention one provides；
Fig. 3 is that the signal of adjoint vehicle identifier provided by Embodiment 2 of the present invention flows to relation schematic diagram；
Fig. 4 is that the concrete signal of adjoint vehicle identifier provided by Embodiment 2 of the present invention flows to relation schematic diagram.
Specific implementation mode
The present invention in order to solve the problems existing in the prior art, provides a kind of adjoint vehicle identification method, device, terminal and meter
Calculation machine readable storage medium storing program for executing can be identified often from the data of magnanimity and is occurred together in the case where license plate number is unknown
Vehicle, as vehicle group to be investigated.Thus more suitable for practicality.
It is of the invention to reach the technological means and effect that predetermined goal of the invention is taken further to illustrate, below in conjunction with
Attached drawing and preferred embodiment, adjoint vehicle identification method, device, terminal and computer-readable storage to proposing according to the present invention
Medium, specific implementation mode, structure, feature and its effect are described in detail as after.In the following description, a different " implementation
What example " or " embodiment " referred to is not necessarily the same embodiment.In addition, the feature, structure or feature in one or more embodiments can
It is combined by any suitable form.
The terms "and/or", only a kind of incidence relation of description affiliated partner, indicates that there may be three kinds of passes
System, for example, A and/or B, is specifically interpreted as：Can include A and B simultaneously, can be with individualism A, it can also individualism
B can have above-mentioned three kinds of any case.
Embodiment one
Referring to attached drawing 1 and attached drawing 2, the adjoint vehicle identification method that the embodiment of the present invention one provides includes the following steps：
Step S1：Choose monitoring point, respectively monitoring point 1, monitoring point 2 ..., monitoring point m；
Step S2：It is marked respectively in given monitoring time section and is monitored vehicle, including vehicle 1, vehicle 2 ..., whether vehicle n
In monitoring point, including monitoring point 1, monitoring point 2 ..., monitoring point m occurs；
Step S3：According to monitored vehicle, including vehicle 1, vehicle 2 ..., vehicle n is in monitoring point, including monitoring point 1, monitoring point
2 ..., the case where monitoring point m occurs, obtains and is monitored vehicle, including vehicle 1, and vehicle 2 ..., vehicle n is in monitoring monitoring point, including monitoring
Point 1, monitoring point 2 ..., the probability that monitoring point m occurs, and it is denoted as support；Specifically：
According to monitored vehicle, including vehicle 1, vehicle 2 ..., vehicle n is in monitoring point, including monitoring point 1, monitoring point 2 ..., monitoring
The case where point m occurs obtains and is monitored vehicle, including vehicle 1, and vehicle 2 ..., vehicle n is in monitoring monitoring point, including monitoring point 1, monitoring
Point 2 ..., the probability that monitoring point m occurs, and be denoted as support and specifically include following steps：
Monitored vehicle, including vehicle 1, vehicle 2 ..., vehicle n are indicated with abscissa；Ordinate indicates monitoring point, including monitoring point
1, monitoring point 2 ..., monitoring point m, if monitored vehicle appears in monitoring point, corresponding coordinate is labeled as 1；If monitored vehicle
Monitoring point is not appeared in, then corresponding coordinate is labeled as 0, obtains and is monitored vehicle, including vehicle 1, vehicle 2 ..., vehicle n and monitoring
Point, including monitoring point 1, monitoring point 2 ..., the correspondence between the m of monitoring point；
According to monitored vehicle, including vehicle 1, vehicle 2 ..., vehicle n and monitoring point, including monitoring point 1, monitoring point 2 ..., monitoring
Correspondence between point m obtains by calculating and is monitored vehicle, including vehicle 1, vehicle 2 ..., and vehicle n is monitoring monitoring point, including
Monitoring point 1, monitoring point 2 ..., the probability that monitoring point m occurs, and it is denoted as support, such as：
The data of acquisition are made following table by given monitoring time section, and abscissa indicates that vehicle, ordinate indicate monitoring
Point.Vehicle appears in some monitoring point and is denoted as 1, is otherwise 0, as shown in the table：
| Vehicle 1 | Vehicle 2 | … | Vehicle n | |
| Monitoring point 1 | 1 | 0 | … | 0 |
| Monitoring point 2 | 1 | 0 | … | 1 |
| … | … | … | … | … |
| Monitoring point m | 1 | 1 | … | 0 |
Step S4：Frequent 1 item collection of iterative extraction successively, frequent 2 item collection, frequent 3 item collection ..., frequent i item collections filter out
The vehicle group of support >=given support；Wherein, the expression formula of support is：
Wherein, support (A)-support, count (A)-are monitored vehicle and appear in monitoring point, including monitoring point 1,
Monitoring point 2 ..., the number of monitoring point m, the number of m-monitoring point.
Specifically：
(i) the 1st iteration：Extract a frequent item collection
Given support extracts all vehicles met more than or equal to support.It is given as the support of vehicle 1 is more than or equal to
Fixed support then filters out vehicle 1, and so on.As a result shaped like { vehicle 1 }, { vehicle 3 }, { vehicle 6 } ...
(ii) the 2nd iteration：Extract frequent two item collection
Given support extracts all vehicle groups for meeting and being more than or equal to and occurring while support.Such as vehicle 1 and vehicle 2
The support occurred simultaneously is more than or equal to given support, then screens.As a result shaped like { vehicle 1, vehicle 2 }, { vehicle 1, vehicle 3 },
{ vehicle 3, vehicle 5 } ...
(iii) the 3rd iteration：Extract frequent three item collection
Given support extracts all vehicle groups for meeting and being more than or equal to and occurring while support.As vehicle 1, vehicle 2,
The support that vehicle 3 occurs simultaneously is more than or equal to given support, then screens.As a result shaped like { vehicle 1, vehicle 2, vehicle 3 }, { vehicle
3, vehicle 5, vehicle 6 } ...
(iv) and so on ..., until extracting all frequent item sets.
Explanation：All item collections that iteration i is obtained are combined in iteration i+1 times and are assessed.If in iteration 1
In { vehicle 1 }, { vehicle 3 } meet condition, and { vehicle 2 } is unsatisfactory for condition, then only needs to consider whether { vehicle 1, vehicle 3 } meets item in iteration 2
Part is not required to consider { vehicle 1, vehicle 2 }, { vehicle 3, vehicle 2 }, and which reduces assessment numbers, save the time.
Step S5：Under conditions of given frequent item set number, the vehicle group of confidence level >=given confidence threshold value is obtained,
As waiting investigating with vehicle group, wherein the expression formula of confidence level is：
Wherein,
confidence(A->B there is the probability for causing monitored vehicle B to occur in)-monitored vehicle A, support (A,
B)-and it is monitored the probability that vehicle A and monitored vehicle B occurs simultaneously, support (A)-is monitored the probability that vehicle A occurs；
Specifically：
(i) one group of frequent item set (the i.e. above-mentioned adjoint vehicle group for meeting condition) is given, is produced according to all possible subset
The raw rule rules that such as { vehicle 1, vehicle 2 } can generate have { vehicle 1 }->{ vehicle 2 }, { vehicle 2 }->{ vehicle 1 } this expression vehicle 1 is the adjoint of vehicle 2
Vehicle or vehicle 2 are the adjoint vehicles of vehicle 1.
(ii) minimum confidence threshold value is given, by all adjoint vehicle group extractions met more than or equal to min confidence
Out.Such as confidence ({ vehicle 1, vehicle 3, vehicle 4 }->{ vehicle 2 }) be more than or equal to given confidence level, then the Rule Extraction is gone out
Come.Think that vehicle 1, vehicle 3, vehicle 4, vehicle 2 are adjoint vehicle groups, and the appearance of rear car 2 first occur in vehicle 1, vehicle 3, vehicle 4.
Embodiment two
Referring to attached drawing 3 and attached drawing 4, adjoint vehicle identification device provided by Embodiment 2 of the present invention includes：
Camera or video camera are laid in the monitoring point of selection, for from the monitoring point of selection by vehicle into
Row take pictures or image, with obtain from the monitoring point of selection by vehicle car plate image；
Image identification unit, for from the monitoring point of selection by vehicle car plate image be identified after obtain
License plate number in license plate image；
Monitored marking of cars unit is monitored vehicle, including vehicle for being marked respectively in given monitoring time section
1, vehicle 2 ..., whether vehicle n is in monitoring point, including monitoring point 1, monitoring point 2 ..., monitoring point m appearance；
Support acquiring unit, for according to vehicle, including vehicle 1 is monitored, vehicle 2 ..., vehicle n to be in monitoring point, including monitoring
It the case where point 1, monitoring point 2 ..., monitoring point m occurs, obtains and is monitored vehicle, including vehicle 1, vehicle 2 ..., vehicle n is monitored in monitoring
Point, including monitoring point 1, monitoring point 2 ..., the probability that monitoring point m occurs, and it is denoted as support；Wherein, support acquiring unit
In be integrated with table drawing unit, be monitored vehicle, including vehicle 1, vehicle 2 ..., vehicle n for being indicated with abscissa；Ordinate indicates
Monitoring point, including monitoring point 1, monitoring point 2 ..., monitoring point m, if monitored vehicle appears in monitoring point, corresponding coordinate mark
It is denoted as 1；If monitored vehicle does not appear in monitoring point, corresponding coordinate is labeled as 0, draws and is monitored vehicle, including vehicle 1,
Vehicle 2 ..., vehicle n and monitoring point, including monitoring point 1, monitoring point 2 ..., the table of the correspondence between the m of monitoring point；It is specific and
Speech：
According to monitored vehicle, including vehicle 1, vehicle 2 ..., vehicle n is in monitoring point, including monitoring point 1, monitoring point 2 ..., monitoring
The case where point m occurs obtains and is monitored vehicle, including vehicle 1, and vehicle 2 ..., vehicle n is in monitoring monitoring point, including monitoring point 1, monitoring
Point 2 ..., the probability that monitoring point m occurs, and be denoted as support and specifically include following steps：
Table drawing unit indicates monitored vehicle, including vehicle 1, vehicle 2 ..., vehicle n with table abscissa；Table ordinate
Monitoring point, including monitoring point 1, monitoring point 2 ..., monitoring point m are indicated, if monitored vehicle appears in monitoring point, corresponding seat
Mark is labeled as 1；If monitored vehicle does not appear in monitoring point, corresponding coordinate is labeled as 0, obtains and is monitored vehicle, including
Vehicle 1, vehicle 2 ..., vehicle n and monitoring point, including monitoring point 1, monitoring point 2 ..., the correspondence between the m of monitoring point；
According to monitored vehicle, including vehicle 1, vehicle 2 ..., vehicle n and monitoring point, including monitoring point 1, monitoring point 2 ..., monitoring
Correspondence between point m obtains by calculating and is monitored vehicle, including vehicle 1, vehicle 2 ..., and vehicle n is monitoring monitoring point, including
Monitoring point 1, monitoring point 2 ..., the probability that monitoring point m occurs, and it is denoted as support, such as：
The data of acquisition are made following table by given monitoring time section, and abscissa indicates that vehicle, ordinate indicate monitoring
Point.Vehicle appears in some monitoring point and is denoted as 1, is otherwise 0, as shown in the table：
| Vehicle 1 | Vehicle 2 | … | Vehicle n | |
| Monitoring point 1 | 1 | 0 | … | 0 |
| Monitoring point 2 | 1 | 0 | … | 1 |
| … | … | … | … | … |
| Monitoring point m | 1 | 1 | … | 0 |
Support screening unit, for frequent 1 item collection of iterative extraction successively, frequent 2 item collection, frequent 3 item collection ..., frequent i
Item collection filters out the vehicle group of support >=given support；Wherein, the expression formula of support is：
Wherein, support (A)-support, count (A)-are monitored vehicle and appear in monitoring point, including monitoring point 1,
Monitoring point 2 ..., the number of monitoring point m, the number of m-monitoring point.
Specifically：
(i) the 1st iteration：Extract a frequent item collection
Given support extracts all vehicles met more than or equal to support.It is given as the support of vehicle 1 is more than or equal to
Fixed support then filters out vehicle 1, and so on.As a result shaped like { vehicle 1 }, { vehicle 3 }, { vehicle 6 } ...
(ii) the 2nd iteration：Extract frequent two item collection
Given support extracts all vehicle groups for meeting and being more than or equal to and occurring while support.Such as vehicle 1 and vehicle 2
The support occurred simultaneously is more than or equal to given support, then screens.As a result shaped like { vehicle 1, vehicle 2 }, { vehicle 1, vehicle 3 },
{ vehicle 3, vehicle 5 } ...
(iii) the 3rd iteration：Extract frequent three item collection
Given support extracts all vehicle groups for meeting and being more than or equal to and occurring while support.As vehicle 1, vehicle 2,
The support that vehicle 3 occurs simultaneously is more than or equal to given support, then screens.As a result shaped like { vehicle 1, vehicle 2, vehicle 3 }, { vehicle
3, vehicle 5, vehicle 6 } ...
(iv) and so on ..., until extracting all frequent item sets.
Explanation：All item collections that iteration i is obtained are combined in iteration i+1 times and are assessed.If in iteration 1
In { vehicle 1 }, { vehicle 3 } meet condition, and { vehicle 2 } is unsatisfactory for condition, then only needs to consider whether { vehicle 1, vehicle 3 } meets item in iteration 2
Part is not required to consider { vehicle 1, vehicle 2 }, { vehicle 3, vehicle 2 }, and which reduces assessment numbers, save the time.
It waits investigating with vehicle group acquiring unit, be used under conditions of given frequent item set number, acquisition confidence level >=
The vehicle group of given confidence threshold value, as waiting investigating with vehicle group, wherein the expression formula of confidence level is：
Wherein,
confidence(A->B there is the probability for causing monitored vehicle B to occur in)-monitored vehicle A, support (A,
B)-and it is monitored the probability that vehicle A and monitored vehicle B occurs simultaneously, support (A)-is monitored the probability that vehicle A occurs；
Specifically：
(i) one group of frequent item set (the i.e. above-mentioned adjoint vehicle group for meeting condition) is given, is produced according to all possible subset
The raw rule rules that such as { vehicle 1, vehicle 2 } can generate have { vehicle 1 }->{ vehicle 2 }, { vehicle 2 }->{ vehicle 1 } this expression vehicle 1 is the adjoint of vehicle 2
Vehicle or vehicle 2 are the adjoint vehicles of vehicle 1.
(ii) minimum confidence threshold value is given, by all adjoint vehicle group extractions met more than or equal to min confidence
Out.Such as confidence ({ vehicle 1, vehicle 3, vehicle 4 }->{ vehicle 2 }) be more than or equal to given confidence level, then the Rule Extraction is gone out
Come.Think that vehicle 1, vehicle 3, vehicle 4, vehicle 2 are adjoint vehicle groups, and the appearance of rear car 2 first occur in vehicle 1, vehicle 3, vehicle 4.
The embodiment of the present invention three provide adjoint vehicle identification terminal adjoint vehicle identification terminal provided by the invention include
Camera or video camera, processor, memory and storage are on a memory and the adjoint vehicle knowledge that can run on a processor
Other program, wherein：
Camera either video camera for from the monitoring point of selection by vehicle taken pictures or imaged, to obtain
Take from the monitoring point of selection by vehicle car plate image；
The step of the method for adjoint vehicle identification provided by the invention is realized when being executed by processor with vehicle identification program
Suddenly；
Wherein,
Camera either video camera can by take pictures or image obtain from point being monitored by vehicle car plate
Image upload process device obtains after capable of being identified by the image to car plate with vehicle identification program in license plate image
License plate number.Specifically,
The image that processor can also travel certificate with the vehicle that vehicle management center is put on record is compared, and is supervised with determination
Measuring car with its entrained by license plate number uniformity.In this case, replacing vehicle board can be avoided to travel, and caused to companion
It is interfered with accurately identifying for vehicle.
It is stored on the computer readable storage medium that the embodiment of the present invention four provides with vehicle identification program, with vehicle
The step of recognizer realizes the method for adjoint vehicle identification provided by the invention when being executed by processor.
The adjoint vehicle recognition methods of the offer of the embodiment of the present invention one, the device of the offer of embodiment two, embodiment three provide
Terminal and example IV computer readable storage medium are a from the m in monitoring in the given period in m monitoring point of selection
Monitoring point by n monitored vehicle then n monitored vehicle is extracted by an iteration and is occurred m monitoring point
Frequent i item collections are more than or equal to the vehicle of given confidence threshold value with confidence level under conditions of given frequent item set number
Group, which is used as, to be waited investigating with vehicle group.This method only needs to be arranged for monitoring vehicle pass-through in m monitoring point being selected
Camera either video camera and by image identification unit to by camera or video camera acquisition monitored vehicle picture
Or the license plate number in video resource is identified, and then, is waited investigating with vehicle group by calculating can be obtained, operation is set
It is standby simple, of low cost.Also, during due to application adjoint vehicle recognition methods provided by the invention, n amounts are monitored vehicle
It is the camera or video camera random shooting by being set to m monitoring point, without learning vehicle to be investigated in advance
License plate number can identify the vehicle group often occurred together in the case where license plate number is unknown from the data of magnanimity.
Although preferred embodiments of the present invention have been described, it is created once a person skilled in the art knows basic
Property concept, then additional changes and modifications may be made to these embodiments.So it includes excellent that the following claims are intended to be interpreted as
It selects embodiment and falls into all change and modification of the scope of the invention.
Obviously, various changes and modifications can be made to the invention without departing from essence of the invention by those skilled in the art
God and range.In this way, if these modifications and changes of the present invention belongs to the range of the claims in the present invention and its equivalent technologies
Within, then the present invention is also intended to include these modifications and variations.
Claims (10)
1. a kind of adjoint vehicle identification method, which is characterized in that include the following steps：
Choose monitoring point, respectively monitoring point 1, monitoring point 2 ..., monitoring point m；
It is marked respectively in given monitoring time section and is monitored vehicle, including vehicle 1, vehicle 2 ..., whether vehicle n is in the monitoring
Point, including monitoring point 1, monitoring point 2 ..., monitoring point m occur；
According to the monitored vehicle, including vehicle 1, vehicle 2 ..., vehicle n is in the monitoring point, including monitoring point 1, monitoring point 2 ...,
The case where monitoring point m occurs obtains and is monitored vehicle, including vehicle 1, and vehicle 2 ..., vehicle n is in the monitoring monitoring point, including monitoring
Point 1, monitoring point 2 ..., the probability that monitoring point m occurs, and it is denoted as support；
Frequent 1 item collection of iterative extraction successively, frequent 2 item collection, frequent 3 item collection ..., frequent i item collections filter out support >=given
The vehicle group of support；
Under conditions of given frequent item set number, the vehicle group of confidence level >=given confidence threshold value is obtained, as waiting investigating
With vehicle group.
2. adjoint vehicle recognition methods according to claim 1, which is characterized in that described according to the monitored vehicle, packet
Include vehicle 1, vehicle 2 ..., vehicle n obtains quilt the monitoring point, including monitoring point 1, monitoring point 2 ..., monitoring point m occurs the case where
Vehicle is monitored, including vehicle 1, vehicle 2 ..., vehicle n go out in the monitoring monitoring point, including monitoring point 1, monitoring point 2 ..., monitoring point m
Existing probability, and be denoted as support and specifically include following steps：
The monitored vehicle, including vehicle 1, vehicle 2 ..., vehicle n are indicated with abscissa；Ordinate indicates the monitoring point, including prison
Measuring point 1, monitoring point 2 ..., monitoring point m, if the monitored vehicle appears in the monitoring point, corresponding coordinate is labeled as
1；If the monitored vehicle does not appear in the monitoring point, corresponding coordinate is labeled as 0, obtains the monitored vehicle,
Including vehicle 1, vehicle 2 ..., vehicle n and the monitoring point, including monitoring point 1, monitoring point 2 ..., the correspondence between the m of monitoring point；
According to the monitored vehicle, including vehicle 1, vehicle 2 ..., vehicle n and the monitoring point, including monitoring point 1, monitoring point 2 ...,
Correspondence between the m of monitoring point obtains by calculating and is monitored vehicle, including vehicle 1, vehicle 2 ..., vehicle n are supervised in the monitoring
Measuring point, including monitoring point 1, monitoring point 2 ..., the probability that monitoring point m occurs, and it is denoted as support.
3. adjoint vehicle identification method according to claim 1, which is characterized in that institute
The expression formula for stating support is：
Wherein, support (A)-support, count (A)-are monitored vehicle and appear in monitoring point, including monitoring point 1, monitor
Point 2 ..., the number of monitoring point m, the number of m-monitoring point.
4. adjoint vehicle identification method according to claim 1, which is characterized in that
The result of frequent 1 item collection is shaped like { vehicle 1 }, { vehicle 3 }, { vehicle 6 } ...；
The result of frequent 2 item collection is shaped like { vehicle 1, vehicle 2 }, { vehicle 1, vehicle 3 }, { vehicle 3, vehicle 5 } ...；
The result of frequent 3 item collection is shaped like { vehicle 1, vehicle 2, vehicle 3 }, { vehicle 3, vehicle 5, vehicle 6 }, { vehicle 8, vehicle 11, vehicle 18 } ...；
And so on, until obtaining the frequent i item collections.
5. adjoint vehicle identification method according to claim 4, which is characterized in that frequent i+1 item collections are by each described
Frequent i item collections obtain.
6. adjoint vehicle identification method according to claim 1, which is characterized in that institute
The expression formula for stating confidence level is：
Wherein,
confidence(A->B there is the probability for causing monitored vehicle B to occur, support (A, B)-in)-monitored vehicle A
The probability that monitored vehicle A and monitored vehicle B occurs simultaneously, support (A)-are monitored the probability that vehicle A occurs.
7. a kind of adjoint vehicle identification device, which is characterized in that including：
Camera or video camera are laid in the monitoring point of selection, for from the monitoring point of the selection by vehicle into
Row take pictures or image, with obtain from the monitoring point of the selection by vehicle car plate image；
Image identification unit, for from the monitoring point of the selection by vehicle car plate image be identified after obtain
License plate number in the license plate image；
Monitored marking of cars unit is monitored vehicle, including vehicle 1, vehicle for being marked respectively in given monitoring time section
Whether 2 ..., vehicle n are in the monitoring point, including monitoring point 1, monitoring point 2 ..., monitoring point m appearance；
Support acquiring unit, for according to the monitored vehicle, including vehicle 1, vehicle 2 ..., vehicle n in the monitoring point, including
The case where monitoring point 1, monitoring point 2 ..., monitoring point m occurs, obtains and is monitored vehicle, including vehicle 1, and vehicle 2 ..., vehicle n is described
Monitoring point, including monitoring point 1, monitoring point 2 ..., the probability that monitoring point m occurs are monitored, and is denoted as support；
Support screening unit, for frequent 1 item collection of iterative extraction, frequent 2 item collection, frequent 3 item collection ... to be i frequent successively
Collection filters out the vehicle group of support >=given support；
It waits investigating with vehicle group acquiring unit, be used under conditions of given frequent item set number, acquisition confidence level >=given
The vehicle group of confidence threshold value, as waiting investigating with vehicle group.
8. adjoint vehicle identification device according to claim 7, which is characterized in that further include：
Table drawing unit, for indicating the monitored vehicle, including vehicle 1, vehicle 2 ..., vehicle n with abscissa；Ordinate indicates
The monitoring point, including monitoring point 1, monitoring point 2 ..., monitoring point m, if the monitored vehicle appears in the monitoring point,
Corresponding coordinate is labeled as 1；If the monitored vehicle does not appear in the monitoring point, corresponding coordinate is labeled as 0, draws
The monitored vehicle, including vehicle 1, vehicle 2 ..., vehicle n and the monitoring point, including monitoring point 1, monitoring point 2 ..., monitoring point m
Between correspondence table.
9. a kind of adjoint vehicle identification terminal, which is characterized in that including camera or video camera, processor, memory and deposit
The adjoint vehicle identification program that can be run on the memory and on the processor is stored up, wherein：
The camera either video camera for from the monitoring point of the selection by vehicle taken pictures or imaged,
With obtain from the monitoring point of the selection by vehicle car plate image；
Any adjoint vehicle in claim 1~6 is realized when the adjoint vehicle identification program is executed by the processor
Know method for distinguishing the step of；
Wherein,
The camera either video camera can by take pictures or image obtain from the point being monitored by vehicle vehicle
The image of board uploads the processor, after the adjoint vehicle identification program can be identified by the image to the car plate
Obtain the license plate number in the license plate image.
10. a kind of computer readable storage medium, which is characterized in that be stored on the computer readable storage medium with vehicle
Recognizer is realized any described adjoint in claim 1~6 when the adjoint vehicle identification program is executed by processor
The step of method of vehicle identification.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810571504.7A CN108764197A (en) | 2018-06-06 | 2018-06-06 | With vehicle identification method, device, terminal and computer readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810571504.7A CN108764197A (en) | 2018-06-06 | 2018-06-06 | With vehicle identification method, device, terminal and computer readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108764197A true CN108764197A (en) | 2018-11-06 |
Family
ID=64000071
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810571504.7A Pending CN108764197A (en) | 2018-06-06 | 2018-06-06 | With vehicle identification method, device, terminal and computer readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108764197A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110718070A (en) * | 2019-10-14 | 2020-01-21 | 深圳前海中电慧安科技有限公司 | Accompanying vehicle identification method, device, equipment and storage medium |
| CN110909263A (en) * | 2019-11-29 | 2020-03-24 | 北京明略软件系统有限公司 | Method and device for determining companion relationship of identity characteristics |
| CN112115305A (en) * | 2019-06-21 | 2020-12-22 | 杭州海康威视数字技术股份有限公司 | Group identification method and device and computer readable storage medium |
| CN112182121A (en) * | 2020-10-27 | 2021-01-05 | 南威软件股份有限公司 | Vehicle-related relationship discovery method, device, equipment and medium |
| CN112200472A (en) * | 2020-10-15 | 2021-01-08 | 平安国际智慧城市科技股份有限公司 | Accompanying vehicle detection method, device, electronic equipment and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104778245A (en) * | 2015-04-09 | 2015-07-15 | 北方工业大学 | Similar trajectory mining method and device on basis of massive license plate identification data |
| CN106021412A (en) * | 2016-05-13 | 2016-10-12 | 上海市计算技术研究所 | Large-scale vehicle-passing data oriented accompanying vehicle identification method |
| CN106781581A (en) * | 2016-11-29 | 2017-05-31 | 深圳职业技术学院 | Safe driving behavior monitoring early warning system and method based on the coupling of people's car |
| CN106846801A (en) * | 2017-02-06 | 2017-06-13 | 安徽新华博信息技术股份有限公司 | A kind of region based on track of vehicle is hovered anomaly detection method |
| US20170312614A1 (en) * | 2016-05-02 | 2017-11-02 | Bao Tran | Smart device |
-
2018
- 2018-06-06 CN CN201810571504.7A patent/CN108764197A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104778245A (en) * | 2015-04-09 | 2015-07-15 | 北方工业大学 | Similar trajectory mining method and device on basis of massive license plate identification data |
| US20170312614A1 (en) * | 2016-05-02 | 2017-11-02 | Bao Tran | Smart device |
| CN106021412A (en) * | 2016-05-13 | 2016-10-12 | 上海市计算技术研究所 | Large-scale vehicle-passing data oriented accompanying vehicle identification method |
| CN106781581A (en) * | 2016-11-29 | 2017-05-31 | 深圳职业技术学院 | Safe driving behavior monitoring early warning system and method based on the coupling of people's car |
| CN106846801A (en) * | 2017-02-06 | 2017-06-13 | 安徽新华博信息技术股份有限公司 | A kind of region based on track of vehicle is hovered anomaly detection method |
Non-Patent Citations (3)
| Title |
|---|
| 刘惠惠等: "基于Spark的FP-Growth伴随车辆发现与应用", 《计算机工程与应用》 * |
| 王路辉: "基于车牌流数据的伴随车发现方法研究", 《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》 * |
| 赵秋实等: "基于频繁集的伴随车辆检测算法研究", 《软件》 * |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112115305A (en) * | 2019-06-21 | 2020-12-22 | 杭州海康威视数字技术股份有限公司 | Group identification method and device and computer readable storage medium |
| CN112115305B (en) * | 2019-06-21 | 2024-04-09 | 杭州海康威视数字技术股份有限公司 | Group identification method apparatus and computer-readable storage medium |
| CN110718070A (en) * | 2019-10-14 | 2020-01-21 | 深圳前海中电慧安科技有限公司 | Accompanying vehicle identification method, device, equipment and storage medium |
| CN110909263A (en) * | 2019-11-29 | 2020-03-24 | 北京明略软件系统有限公司 | Method and device for determining companion relationship of identity characteristics |
| CN110909263B (en) * | 2019-11-29 | 2022-10-25 | 北京明略软件系统有限公司 | Method and device for determining companion relationship of identity characteristics |
| CN112200472A (en) * | 2020-10-15 | 2021-01-08 | 平安国际智慧城市科技股份有限公司 | Accompanying vehicle detection method, device, electronic equipment and storage medium |
| CN112200472B (en) * | 2020-10-15 | 2023-12-29 | 平安国际智慧城市科技股份有限公司 | Method and device for detecting accompanying vehicle, electronic equipment and storage medium |
| CN112182121A (en) * | 2020-10-27 | 2021-01-05 | 南威软件股份有限公司 | Vehicle-related relationship discovery method, device, equipment and medium |
| CN112182121B (en) * | 2020-10-27 | 2022-07-12 | 南威软件股份有限公司 | Vehicle-related relationship discovery method, device, equipment and medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108764197A (en) | With vehicle identification method, device, terminal and computer readable storage medium | |
| CN105702048B (en) | Highway front truck illegal road occupation identifying system based on automobile data recorder and method | |
| CN105321350B (en) | Fake-licensed car detection method and device | |
| US9208172B2 (en) | Method and system for vehicle identification | |
| JP2013196682A (en) | Group-of-people detection method and group-of-people detector | |
| CN110414459B (en) | Method and device for establishing man-vehicle association | |
| CN108492580B (en) | Method and system for judging suspected vehicle | |
| CN106326835A (en) | Human face data collection statistical system and method for gas station convenience store | |
| CN108921083A (en) | Illegal flowing street pedlar recognition methods based on deep learning target detection | |
| CN108694399A (en) | Licence plate recognition method, apparatus and system | |
| CN109547748B (en) | Object foot point determining method and device and storage medium | |
| DE112009005002T5 (en) | Techniques for recognizing video copies | |
| CN111753642B (en) | Method and device for determining key frame | |
| CN111444840A (en) | Automatic detection method and system for fake-licensed vehicle | |
| CN108052931A (en) | A kind of license plate recognition result fusion method and device | |
| CN111625687A (en) | Method and system for quickly searching people in media asset video library through human faces | |
| CN111639689A (en) | Face data processing method and device and computer readable storage medium | |
| CN109359689B (en) | Data identification method and device | |
| CN114049658A (en) | Floating population management method and device based on face recognition, computer equipment and storage medium | |
| CN106778765B (en) | License plate recognition method and device | |
| CN112580531A (en) | Method and system for identifying and detecting true and false license plates | |
| CN107944352A (en) | A kind of Vehicle License Plate Recognition System and method based on picture retrieval method | |
| CN112489436A (en) | Vehicle identity recognition method, device and system and electronic device | |
| CN107025435A (en) | A kind of face recognition processing method and system | |
| CN115083004B (en) | Identity recognition method and device and computer readable storage medium |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20181106 |
|
| RJ01 | Rejection of invention patent application after publication |