CN109872541A - A kind of information of vehicles analysis method and device - Google Patents
A kind of information of vehicles analysis method and device Download PDFInfo
- Publication number
- CN109872541A CN109872541A CN201910171036.9A CN201910171036A CN109872541A CN 109872541 A CN109872541 A CN 109872541A CN 201910171036 A CN201910171036 A CN 201910171036A CN 109872541 A CN109872541 A CN 109872541A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- information
- vehicles
- parameter
- same
- 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
Abstract
The invention discloses a kind of information of vehicles analysis method and devices, it is single to solve acquisition information of vehicles mode in the prior art, the problem of cannot efficiently using to information of vehicles, extracts the first information of vehicles that the bayonet is crossed in vehicle picture this method comprises: obtaining bayonet crosses vehicle picture；The Target Photo comprising vehicle is extracted from video flowing, extracts the second information of vehicles in the Target Photo；From the first information of vehicles and the second information of vehicles of the extraction, the information of vehicles for belonging to same vehicle is obtained, and determine the vehicle with the presence or absence of deck suspicion according to the information of vehicles of same vehicle.The present invention crosses the information of vehicle by make a slip of the tongue vehicle, video monitoring of fusion card, carries out analytical calculation to information of vehicles, convenient when carrying out case for vehicle and studying and judging, and quickly finds the related thread of case-involving vehicle.
Description
Technical field
The present invention relates to algorithmic technique field more particularly to a kind of information of vehicles analysis method and devices.
Background technique
Current criminal offense is in high-incidence situation, and crime is related to multi-space, multizone.Suspect usually utilizes vehicle
It quickly flees from, therefore investigation organ needs to chase suspect by tracking vehicle.However, traditional investigation cannot
Adapt to current high efficiency, the requirement that high quality is combatted crime.In recent years, investigation organ is detectd using modern information technologies change
Mode, expansion investigation thinking are looked into, transformation investigation idea innovates methods of investigation, builds and largely relate to vehicle video, including public security bayonet,
Security monitoring, electronic police, traffic monitoring etc. have played important function hitting all kinds of relate in vehicle illegal activity.For
Vehicle crime case is related to, can recognize that feature is tracked and assert to vehicle by vehicle, carrying out vehicle investigation on this basis has
Its real necessity.
In addition, the various vehicle big data systems based on big data technology are also answered with the continuous popularization of big data technology
It transports and gives birth to, vehicle big data system is to be with vehicle data for support with technologies such as cloud computing, big data analysis, deep learnings
Core realizes the functions such as the networking access, analysis processing, cloud of multi-source magnanimity vehicle resources information store, intelligence is studied and judged.Effectively
The access for solving magnanimity vehicle data is difficult, the problems such as attribute is few, query and search is difficult and application depth is not high, be investigation organ
Strong technical support is provided.
Traditional vehicle big data system, is the analysis that vehicle picture is crossed based on bayonet, and data/address bus carries out front end data
Convergence, passback, system collected vehicle point, cross the data such as vehicle time, lane, direction, and vehicle pictures are carried out structuring processing,
Identify vehicle, headstock (tail), color, the vehicle body feature etc. of vehicle.But video monitoring is compared, the density of bayonet point is little,
In many close quarters, track of vehicle cannot be effectively only embodied by bayonet data.It crosses car data and contains abundant information, but often
The retrieval, comparison, inquiry of structuring can only be used to do, potential relationship also needs veteran user, by many and diverse
Operation is completed.
Summary of the invention
The present invention provides a kind of information of vehicles analysis method and device, solves acquisition information of vehicles mode in the prior art
It is single, the problem of cannot being efficiently used to information of vehicles.
In order to solve the above technical problems, the present invention provides a kind of information of vehicles analysis method and devices, specific to wrap
It includes:
According to first aspect present invention, the embodiment of the present invention provides a kind of information of vehicles analysis method, this method comprises:
It obtains bayonet and crosses vehicle picture, extract the first information of vehicles that the bayonet is crossed in vehicle picture；
The Target Photo comprising vehicle is extracted from video flowing, extracts the second information of vehicles in the Target Photo；
From the first information of vehicles and the second information of vehicles of the extraction, the information of vehicles for belonging to same vehicle is obtained,
And determine the vehicle with the presence or absence of deck suspicion according to the information of vehicles of same vehicle.
The above method crosses the information of vehicle by make a slip of the tongue vehicle, video monitoring of fusion card, carries out analytical calculation to information of vehicles,
Conveniently when studying and judging for vehicle progress case, the related thread of case-involving vehicle is quickly found.
In an optional implementation manner, it from the first information of vehicles and the second information of vehicles of the extraction, obtains
Belong to the information of vehicles of same vehicle, comprising: it is crossed in vehicle picture from a bayonet and obtains one group of vehicle parameter, and/or, from one
One group of vehicle parameter is obtained in Target Photo；By all groups of vehicle parameters comprising same vehicle identity, it is determined to belong to
The information of vehicles of same vehicle, the vehicle identification mark are used for the identity of unique identification vehicle.
In an optional implementation manner, by all groups of vehicle parameters comprising same vehicle identity, it is determined as
Belong to after the information of vehicles of same vehicle, further includes: for not including any group of vehicle parameter of vehicle identification mark, determine
The first specified parameter is identical as the first specified parameter in other any group of vehicle parameters in this group of vehicle parameter, and described other
When one group of vehicle parameter includes that vehicle identification identifies, this group of vehicle parameter and other any group of vehicle parameter categories are determined
In the information of vehicles of same vehicle.
In an optional implementation manner, determine that the vehicle is disliked with the presence or absence of deck according to the information of vehicles of same vehicle
It doubts, comprising: use clustering algorithm, the multiple groups vehicle parameter combination map for belonging to same vehicle is clustered, the vehicle is obtained
Space-time trajectory；It is and adjacent if judging the distance between the corresponding tracing point of adjacent time point in same vehicle space-time trajectory
When the ratio of time difference at time point is more than given threshold, determining the vehicle, there are deck suspicion.
In an optional implementation manner, determine that the vehicle is disliked with the presence or absence of deck according to the information of vehicles of same vehicle
It doubts, comprising: if the second specified parameter in the multiple groups vehicle parameter for the information of vehicles that judgement belongs to same vehicle is not identical, sentence
Breaking, there are deck suspicion for the vehicle.
In an optional implementation manner, the information of vehicles includes group that is following any or appointing multiple vehicle parameters
It closes: license plate number, vehicle model, vehicle color, car test mark number, Chinese herbaceous peony portion goods of furniture for display rather than for use, vehicle rear portion goods of furniture for display rather than for use, vehicle location, vehicle
Reach the time of position in picture.
According to second aspect of the present invention, the embodiment of the present invention also provides a kind of information of vehicles analytical equipment, described device packet
It includes:
First information of vehicles acquiring unit crosses vehicle picture for obtaining bayonet, extracts the bayonet is crossed in vehicle picture
One information of vehicles；
Second information of vehicles acquiring unit extracts the mesh for extracting the Target Photo comprising vehicle from video flowing
The second information of vehicles marked on a map in piece；
Information of vehicles analytical unit, for obtaining and belonging to from the first information of vehicles and the second information of vehicles of the extraction
Determine the vehicle with the presence or absence of deck suspicion in the information of vehicles of same vehicle, and according to the information of vehicles of same vehicle.
Above-mentioned apparatus crosses the information of vehicle by make a slip of the tongue vehicle, video monitoring of fusion card, carries out analytical calculation to information of vehicles,
Conveniently when studying and judging for vehicle progress case, the related thread of case-involving vehicle is quickly found.
In an optional implementation manner, the information of vehicles analytical unit, for the first vehicle from the extraction
In information and the second information of vehicles, the information of vehicles for belonging to same vehicle is obtained, is specifically used for: being crossed in vehicle picture from a bayonet
One group of vehicle parameter is obtained, and/or, one group of vehicle parameter is obtained from a Target Photo；It will include same vehicle identity mark
All groups of vehicle parameters known, are determined to belong to the information of vehicles of same vehicle, and the vehicle identification mark is used for unique identification
The identity of vehicle.
In an optional implementation manner, the information of vehicles analytical unit is specifically used for including same vehicle body
All groups of vehicle parameters of part mark, are determined to belong to after the information of vehicles of same vehicle, are also used to: for not including vehicle
Any group of vehicle parameter of identity determines in this group of vehicle parameter in the first specified parameter and other any group of vehicle parameters
First specified parameter is identical, and when other any group of vehicle parameter includes that vehicle identification identifies, determines this group of vehicle
Parameter and other any group of vehicle parameters belong to the information of vehicles of same vehicle.
In an optional implementation manner, the information of vehicles analytical unit, for being believed according to the vehicle of same vehicle
It ceases and determines that the vehicle whether there is deck suspicion, be specifically used for: using clustering algorithm, the multiple groups vehicle for belonging to same vehicle being joined
Number combines map to be clustered, and obtains the space-time trajectory of the vehicle；
If the distance between the corresponding tracing point of adjacent time point in same vehicle space-time trajectory is judged, with adjacent time point
When the ratio of time difference is more than given threshold, determining the vehicle, there are deck suspicion.
In an optional implementation manner, the information of vehicles analytical unit, for being believed according to the vehicle of same vehicle
It ceases and determines that the vehicle whether there is deck suspicion, be specifically used for: if judgement belongs to the multiple groups vehicle of the information of vehicles of same vehicle
When the second specified parameter in parameter is not identical, judging the vehicle, there are deck suspicion.
In an optional implementation manner, the information of vehicles includes group that is following any or appointing multiple vehicle parameters
It closes: license plate number, vehicle model, vehicle color, car test mark number, Chinese herbaceous peony portion goods of furniture for display rather than for use, vehicle rear portion goods of furniture for display rather than for use, vehicle location, vehicle
Reach the time of position in picture.
According to third aspect present invention, the embodiment of the present invention also provides a kind of information of vehicles analytical equipment, described device packet
Memory and processor are included, the processor is used for:
It obtains bayonet and crosses vehicle picture, extract the first information of vehicles that the bayonet is crossed in vehicle picture；
The Target Photo comprising vehicle is extracted from video flowing, extracts the second information of vehicles in the Target Photo；
From the first information of vehicles and the second information of vehicles of extraction, the information of vehicles for belonging to same vehicle, and root are obtained
Determine the vehicle with the presence or absence of deck suspicion according to the information of vehicles of same vehicle.
Above-mentioned apparatus crosses the information of vehicle by make a slip of the tongue vehicle, video monitoring of fusion card, carries out analytical calculation to information of vehicles,
Conveniently when studying and judging for vehicle progress case, the related thread of case-involving vehicle is quickly found.
In an optional implementation manner, the processor is specifically used for: crossing in vehicle picture from a bayonet and obtains one
Group vehicle parameter, and/or, one group of vehicle parameter is obtained from a Target Photo；By the institute comprising same vehicle identity
There is a group vehicle parameter, is determined to belong to the information of vehicles of same vehicle, the vehicle identification mark is for unique identification vehicle
Identity.
In an optional implementation manner, the processor is also used to: any for not including vehicle identification mark
Group vehicle parameter, determines the first specified parameter and the first specified parameter phase in other any group of vehicle parameters in this group of vehicle parameter
Together, when and other any group of vehicle parameter includes that vehicle identification identifies, determine this group of vehicle parameter with it is described other
Any group of vehicle parameter belongs to the information of vehicles of same vehicle.
In an optional implementation manner, the processor is specifically used for: using clustering algorithm, will belong to same vehicle
Multiple groups vehicle parameter combination map clustered, obtain the space-time trajectory of the vehicle；
If the distance between the corresponding tracing point of adjacent time point in same vehicle space-time trajectory is judged, with adjacent time point
When the ratio of time difference is more than given threshold, determining the vehicle, there are deck suspicion.
In an optional implementation manner, the processor is specifically used for: if judgement belongs to the vehicle letter of same vehicle
When the second specified parameter in the multiple groups vehicle parameter of breath is not identical, judging the vehicle, there are deck suspicion.
In an optional implementation manner, the information of vehicles includes group that is following any or appointing multiple vehicle parameters
It closes: license plate number, vehicle model, vehicle color, car test mark number, Chinese herbaceous peony portion goods of furniture for display rather than for use, vehicle rear portion goods of furniture for display rather than for use, vehicle location, vehicle
Reach the time of position in picture.
According to fourth aspect present invention, a kind of computer storage medium is provided, the computer storage medium is stored with meter
Calculation machine program, which, which is performed, realizes above-mentioned method.
A kind of information of vehicles analysis method provided by the invention and device compared with prior art, have the following advantages that and have
Beneficial effect:
Bayonet is crossed car data to the present invention and video monitoring vehicle data carries out information of vehicles extraction and information merges, to knot
Information of vehicles after conjunction carries out Information Statistics analysis, and convenient when studying and judging for vehicle or region progress case, quickly discovery relates to
The related thread of case vehicle.
Detailed description of the invention
Fig. 1 is a kind of flow diagram for information of vehicles analysis method that embodiment provides；
Fig. 2 is a kind of information of vehicles analytical equipment schematic diagram that embodiment provides；
Fig. 3 is a kind of information of vehicles analytical equipment schematic diagram that embodiment provides.
Specific embodiment
To make the objectives, technical solutions, and advantages of the present invention clearer, below in conjunction with attached drawing to the present invention make into
It is described in detail to one step, it is clear that the described embodiment is only a part of the embodiment of the present invention, instead of all the embodiments.
Based on the embodiments of the present invention, obtained by those of ordinary skill in the art without making creative efforts all
Other embodiments shall fall within the protection scope of the present invention.
The application scenarios of description of the embodiment of the present invention are the technical solutions in order to more clearly illustrate the embodiment of the present invention,
The restriction for technical solution provided in an embodiment of the present invention is not constituted, those of ordinary skill in the art are it is found that with newly answering
With the appearance of scene, technical solution provided in an embodiment of the present invention is equally applicable for similar technical problem.Wherein, at this
In the description of invention, unless otherwise indicated, the meaning of " plurality " is two or more.
To make the objectives, technical solutions, and advantages of the present invention clearer, below in conjunction with attached drawing to the present invention make into
It is described in detail to one step, it is clear that described embodiments are only a part of the embodiments of the present invention, rather than whole implementation
Example.Based on the embodiments of the present invention, obtained by those of ordinary skill in the art without making creative efforts
All other embodiment, shall fall within the protection scope of the present invention.
The embodiment of the present invention provides a kind of information of vehicles analysis method, as shown in Figure 1, comprising:
Step 101, it obtains bayonet and crosses vehicle picture, extract the first information of vehicles that the bayonet is crossed in vehicle picture；
The bayonet is the entrance for having defence and checking facility, such as charge station, traffic or public security inspection station.To all logical
The vehicle for crossing bayonet is shot, recorded and is handled.
The bayonet cross vehicle picture be vehicle by bayonet when, the picture arrived which is shot.
First information of vehicles includes combination that is following any or appointing multiple vehicle parameters: license plate number, vehicle model,
Vehicle color, car test mark number, Chinese herbaceous peony portion goods of furniture for display rather than for use, vehicle rear portion goods of furniture for display rather than for use, vehicle location, vehicle reach the time of position in picture.
In an implementation, it must be arrived comprising vehicle model, vehicle color, vehicle location and vehicle in the first information of vehicles of extraction
Up to the temporal information of position in picture, remaining information is not necessarily and must extract if there is then extracting.
Step 102, the Target Photo comprising vehicle is extracted from video flowing, extracts the second vehicle in the Target Photo
Information；
The video flowing is the monitor video data shot in the monitoring device that the public domains such as road cell are installed.
The Target Photo comprising vehicle be video flowing in need to extract information of vehicles vehicle it is clearest in picture,
The maximum frame image of pixel.
Second information of vehicles includes combination that is following any or appointing multiple vehicle parameters: license plate number, vehicle model,
Vehicle color, car test mark number, Chinese herbaceous peony portion goods of furniture for display rather than for use, vehicle rear portion goods of furniture for display rather than for use, vehicle location, vehicle reach the time of position in picture.
In an implementation, it must be arrived comprising vehicle model, vehicle color, vehicle location and vehicle in the second information of vehicles of extraction
Up to the temporal information of position in picture, remaining information is not necessarily and must extract if there is then extracting.
In an implementation, the execution sequence of above-mentioned steps 101 and above-mentioned steps 102 also may be performed simultaneously without successively limitation.
Step 103, from the first information of vehicles and the second information of vehicles of the extraction, the vehicle for belonging to same vehicle is obtained
Information, and determine the vehicle with the presence or absence of deck suspicion according to the information of vehicles of same vehicle.
In an implementation, the information of vehicles for belonging to same vehicle of acquisition is to belong in the first information of vehicles and the second information of vehicles
In the set of the information of vehicles of same vehicle.
The information of vehicles includes combination that is following any or appointing multiple vehicle parameters: license plate number, vehicle model, vehicle
Color, car test mark number, Chinese herbaceous peony portion goods of furniture for display rather than for use, vehicle rear portion goods of furniture for display rather than for use, vehicle location, vehicle reach the time of position in picture.
In an implementation, figure must be reached comprising vehicle model, vehicle color, vehicle location and vehicle in the information of vehicles of acquisition
The temporal information of position in piece, remaining information are not necessarily and must extract if there is then extracting.
As an alternative embodiment, crossed in vehicle picture from a bayonet obtain one group of vehicle parameter and/or, from one
One group of vehicle parameter is obtained in a Target Photo；
In an implementation, acquisition multiple groups vehicle parameter in vehicle picture is crossed from multiple bayonets of acquisition respectively, from the multiple of acquisition
Multiple groups vehicle parameter is obtained in Target Photo.
Optionally, it can identify that vehicle crosses the position in vehicle picture in bayonet by image recognition, in conjunction in vehicle information excessively
Vehicle location and license plate number information determine the target vehicle for needing to extract information of vehicles, by vehicle feature recognition to target
Vehicle carries out including license plate number, vehicle model, vehicle color, car test mark number, Chinese herbaceous peony portion goods of furniture for display rather than for use, vehicle rear portion goods of furniture for display rather than for use, vehicle
Position and vehicle reach the identification and extraction of the vehicle parameter of the time of position in picture.Herein not to the knowledge of vehicle parameter information
Not and extracting method limits.
Optionally, can include to from the vehicle in the Target Photo obtained in video flowing by vehicle feature recognition
License plate number, vehicle model, vehicle color, car test mark number, Chinese herbaceous peony portion goods of furniture for display rather than for use, vehicle rear portion goods of furniture for display rather than for use, vehicle location and vehicle reach
The identification and extraction of the vehicle parameter of the time of position into picture.Herein not to the identification of vehicle parameter information and extracting method
It limits.
Optionally, more then vehicle parameters of extraction can be stored in database according to certain format, herein not to storage lattice
Formula limits.
It in an implementation, can be according to any one or one group of vehicle parameter to the corresponding vehicle of the vehicle parameter in database
Information of vehicles retrieved.
Optionally, by all groups of vehicle parameters comprising same vehicle identity, it is determined to belong to the vehicle of same vehicle
Information, the vehicle identification mark are used for the identity of unique identification vehicle.
The same vehicle identity is vehicle license plate, from crossing all groups extracted in vehicle pictures video flowing in bayonet
In vehicle parameter, the identical several groups vehicle parameter of vehicle license plate is selected, is judged as the information of vehicles for belonging to same vehicle.
It in an implementation, can be to belong to the information of vehicles of same vehicle to establish formal vehicle archives, the formal vehicle archives
In be stored with all information of vehicles of the vehicle.
Optionally, by all groups of vehicle parameters comprising same vehicle identity, it is determined to belong to the vehicle of same vehicle
After information, further includes:
For not including any group of vehicle parameter of vehicle identification mark, the first specified parameter in this group of vehicle parameter is determined
It is identical as the first specified parameter in other any group of vehicle parameters, and other any group of vehicle parameter includes vehicle identification mark
When knowledge, determine that this group of vehicle parameter and other any group of vehicle parameters belong to the information of vehicles of same vehicle.
The first specified parameter is that can identify one or more vehicle parameters of vehicle identification in addition to vehicle license plate parameter
Combination, such as can be vehicle model and vehicle color combination, a combination thereof mode can for many kinds, herein not to first
Specified parameter limits.
In an implementation, if judgement does not include certain several vehicle parameter in any group of vehicle parameter of vehicle license plate, with it
When correspondence parameter in its one group of vehicle parameter comprising vehicle license plate is identical, judge that this does not include one group of vehicle of vehicle license plate
The corresponding vehicle of parameter, vehicle corresponding with other one comprising the vehicle license plate group vehicle parameters is same vehicle, by institute
The vehicle parameter information not comprising vehicle license plate is stated to be written in the vehicle archives of the vehicle.
It in an implementation, will be in specified parameter therein and each vehicle archives if any the one group of vehicle parameter newly obtained
Any group of vehicle parameter carries out the comparison of specified parameter, if be judged as the information of vehicles of same vehicle, by the new acquisition
One group of vehicle parameter is written in the vehicle archives of the vehicle, if judging the specified parameter of one group of vehicle parameter of the new acquisition
It is one group of the new acquisition when being all different with the specified parameter of any group of vehicle parameter in all existing vehicle archives
The corresponding vehicle of vehicle parameter establishes vehicle archives.Specified parameter is not defined herein.
In a kind of optional embodiment, if first in one not comprising the vehicle license plate group vehicle parameter obtained refers to
When determining the first specified parameter in parameter and remaining any group of vehicle parameter and being different from, to be described not comprising vehicle license plate
The corresponding vehicle of one group of vehicle parameter establishes scratch file, if the first specified parameter in the subsequent judgement vehicle parameter is with after
When identical comprising the first specified parameter in one group of vehicle parameter of vehicle license plate come certain group for obtaining, it is judged as same vehicle,
The scratch file is written into one comprising the vehicle license plate group vehicle parameter obtained later, the scratch file is converted to
Formal archives.
As an alternative embodiment, the multiple groups vehicle parameter for belonging to same vehicle is combined using clustering algorithm
Map is clustered, and the space-time trajectory of the vehicle is obtained.
In an implementation, it is clustered for the information of vehicles in each vehicle archives using clustering algorithm combination map,
The space-time trajectory map of each corresponding vehicle of vehicle archives, including vehicle are obtained in the sometime corresponding position in map
It sets.
The space-time trajectory map of the vehicle includes operation of the vehicle in all areas for having monitoring capture apparatus and bayonet
Track.
As an alternative embodiment, can be carried out to vehicle with the presence or absence of deck suspicion according to the space-time trajectory of vehicle
It studies and judges.
If judging the distance between the corresponding tracing point of adjacent time point in the space-time trajectory of same vehicle in an implementation, with
When the ratio of adjacent time point time difference is more than given threshold, determining the vehicle, there are deck suspicion.
In an implementation, the information of vehicles of the same vehicle is associated, be not it is isolated, vehicle in region will not be with
Vacate it is existing, will not the unordered appearance of great-jump-forward, if judging the corresponding tracing point of adjacent time point in same vehicle space-time trajectory
Between distance judge that vehicle mode occurs and do not meet reality when being more than given threshold with the ratio of adjacent time point time difference
Situation, it is thus determined that there are deck suspicion for the vehicle.Given threshold is not limited herein, threshold value should meet vehicle in setting
The possible rate request of real motion.
In a kind of optional embodiment, vehicle can be studied and judged with the presence or absence of deck suspicion memory according to vehicle archives.
If judgement belongs to a certain group in same vehicle archives in an implementation or second in a few groups of vehicle parameters is specified
When parameter is not identical, judging the vehicle, there are deck suspicion.
The second specified parameter can be the combination of vehicle model or vehicle color or vehicle model and vehicle color, this
Place does not limit the second specified parameter.
In a kind of optional embodiment, according to the information of vehicles in the vehicle archives of vehicle, by information of vehicles
Analysis, judge whether vehicle belongs to the vehicle in the area Xin Ru, if for often vehicle active in area.
In a kind of optional embodiment, in combination with the space-time trajectory map and vehicle archives and case information pair of vehicle
Vehicle is studied and judged.
It can determine that the crime period passes through the vehicle in crime region according to the space-time trajectory map of vehicle in an implementation, further
, the archives of these vehicles are analyzed, judge whether the vehicle is local resident vehicle, if the crime period it
It is preceding whether to stop near crime, if to set foot-point.
The present embodiment is a kind of equipment, and the principle which solves the problems, such as is similar to this method, therefore the reality of the equipment
The implementation for the method for may refer to is applied, overlaps will not be repeated.
The present embodiment provides a kind of information of vehicles analytical equipments, and schematic device is as shown in Fig. 2, described device includes:
First information of vehicles acquiring unit 201 crosses vehicle picture for obtaining bayonet, extracts the bayonet and cross in vehicle picture
First information of vehicles；
Second information of vehicles acquiring unit 202, for extracted from video flowing include vehicle Target Photo, described in extraction
The second information of vehicles in Target Photo；
Information of vehicles analytical unit 203, for obtaining from the first information of vehicles and the second information of vehicles of the extraction
Belong to the information of vehicles of same vehicle, and determines the vehicle with the presence or absence of deck suspicion according to the information of vehicles of same vehicle.
Optionally, the information of vehicles analytical unit 203, for the first information of vehicles and the second vehicle from the extraction
In information, the information of vehicles for belonging to same vehicle is obtained, is specifically used for: crossed in vehicle picture from a bayonet and obtain one group of vehicle ginseng
Number, and/or, one group of vehicle parameter is obtained from a Target Photo；By all groups of vehicles comprising same vehicle identity
Parameter, is determined to belong to the information of vehicles of same vehicle, and the vehicle identification mark is used for the identity of unique identification vehicle.
Optionally, the information of vehicles analytical unit 203, specifically for that will include all groups of same vehicle identity
Vehicle parameter is determined to belong to after the information of vehicles of same vehicle, is also used to: any for not including vehicle identification mark
Group vehicle parameter, determines the first specified parameter and the first specified parameter phase in other any group of vehicle parameters in this group of vehicle parameter
Together, when and other any group of vehicle parameter includes that vehicle identification identifies, determine this group of vehicle parameter with it is described other
Any group of vehicle parameter belongs to the information of vehicles of same vehicle.
Optionally, the information of vehicles analytical unit 203, for determining that the vehicle is according to the information of vehicles of same vehicle
No to be specifically used for there are deck suspicion: using clustering algorithm, the multiple groups vehicle parameter combination map that will belong to same vehicle carries out
Cluster, obtains the space-time trajectory of the vehicle；If judging the corresponding tracing point of adjacent time point in same vehicle space-time trajectory
Between distance, when being more than given threshold with the ratio of adjacent time point time difference, determining the vehicle, there are deck suspicion.
Optionally, the information of vehicles analytical unit 203, for determining that the vehicle is according to the information of vehicles of same vehicle
It is no there are deck suspicion, be specifically used for: if judgement belong to same vehicle information of vehicles multiple groups vehicle parameter in second refer to
Determine parameter it is not identical when, judging the vehicle, there are deck suspicion.
Optionally, the information of vehicles includes combination that is following any or appointing multiple vehicle parameters: license plate number, vehicle type
Number, vehicle color, car test mark number, Chinese herbaceous peony portion goods of furniture for display rather than for use, vehicle rear portion goods of furniture for display rather than for use, vehicle location, vehicle reach position in picture when
Between.
The present embodiment also provides a kind of information of vehicles analytical equipment, as shown in figure 3, described device includes 301 He of memory
Processor 302, the processor 302 are used for:
It obtains bayonet and crosses vehicle picture, extract the first information of vehicles that the bayonet is crossed in vehicle picture；
The Target Photo comprising vehicle is extracted from video flowing, extracts the second information of vehicles in the Target Photo；
From the first information of vehicles and the second information of vehicles of the extraction, the information of vehicles for belonging to same vehicle is obtained,
And determine the vehicle with the presence or absence of deck suspicion according to the information of vehicles of same vehicle.
Optionally, the processor 302 is specifically used for: it is crossed in vehicle picture from a bayonet and obtains one group of vehicle parameter, and/
Or, obtaining one group of vehicle parameter from a Target Photo；By all groups of vehicle parameters comprising same vehicle identity, really
It is set to the information of vehicles for belonging to same vehicle, the vehicle identification mark is used for the identity of unique identification vehicle.
Optionally, the processor 302 is also used to: any group of vehicle parameter for not including vehicle identification mark, really
The first specified parameter and the first specified parameter in other any group of vehicle parameters are identical and described other in fixed this group of vehicle parameter
When any group of vehicle parameter includes that vehicle identification identifies, this group of vehicle parameter and other any group of vehicle parameters are determined
Belong to the information of vehicles of same vehicle.
Optionally, the processor 302 is specifically used for: using clustering algorithm, the multiple groups vehicle for belonging to same vehicle is joined
Number combines map to be clustered, and obtains the space-time trajectory of the vehicle；
If the distance between the corresponding tracing point of adjacent time point in same vehicle space-time trajectory is judged, with adjacent time point
When the ratio of time difference is more than given threshold, determining the vehicle, there are deck suspicion.
Optionally, the processor 302 is specifically used for: if judgement belongs to the multiple groups vehicle ginseng of the information of vehicles of same vehicle
When the second specified parameter in number is not identical, judging the vehicle, there are deck suspicion.
Optionally, the information of vehicles includes combination that is following any or appointing multiple vehicle parameters: license plate number, vehicle type
Number, vehicle color, car test mark number, Chinese herbaceous peony portion goods of furniture for display rather than for use, vehicle rear portion goods of furniture for display rather than for use, vehicle location, vehicle reach position in picture when
Between.
The present embodiment is a kind of computer storage medium, and above-mentioned computer storage medium is stored with computer program, the meter
Calculation machine program is performed the content for realizing above-described embodiment.
It should be understood by those skilled in the art that, the embodiment of the present invention can provide as method, system or computer program
Product.Therefore, complete hardware embodiment, complete software embodiment or reality combining software and hardware aspects can be used in the present invention
Apply the form of example.Moreover, it wherein includes the computer of computer usable program code that the present invention, which can be used in one or more,
The shape for the computer program product implemented in usable storage medium (including but not limited to magnetic disk storage and optical memory etc.)
Formula.
The present invention be referring to according to the method for the embodiment of the present invention, the process of equipment (system) and computer program product
Figure and/or block diagram describe.It should be understood that every one stream in flowchart and/or the block diagram can be realized by computer program instructions
The combination of process and/or box in journey and/or box and flowchart and/or the block diagram.It can provide these computer programs
Instruct the processor of general purpose computer, special purpose computer, Embedded Processor or other programmable data processing devices to produce
A raw machine, so that being generated by the instruction that computer or the processor of other programmable data processing devices execute for real
The device for the function of being specified in present one or more flows of the flowchart and/or one or more blocks of the block diagram.
These computer program instructions, which may also be stored in, is able to guide computer or other programmable data processing devices with spy
Determine in the computer-readable memory that mode works, so that it includes referring to that instruction stored in the computer readable memory, which generates,
Enable the manufacture of device, the command device realize in one box of one or more flows of the flowchart and/or block diagram or
The function of being specified in multiple boxes.
These computer program instructions can also be loaded into computer or other programmable data processing devices, so that counting
Series of operation steps are executed on calculation machine or other programmable devices to generate computer implemented processing, thus in computer or
The instruction executed on other programmable devices is provided for realizing in one or more flows of the flowchart and/or block diagram one
The step of function of being specified in a box or multiple boxes.
Obviously, various changes and modifications can be made to the invention without departing from essence of the invention by those skilled in the art
Mind 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 information of vehicles analysis method characterized by comprising
It obtains bayonet and crosses vehicle picture, extract the first information of vehicles that the bayonet is crossed in vehicle picture；
The Target Photo comprising vehicle is extracted from video flowing, extracts the second information of vehicles in the Target Photo；
From the first information of vehicles and the second information of vehicles of extraction, the information of vehicles for belonging to same vehicle is obtained, and according to same
The information of vehicles of one vehicle determines the vehicle with the presence or absence of deck suspicion.
2. the method according to claim 1, wherein from the first information of vehicles and the second information of vehicles of extraction
In, obtain the information of vehicles for belonging to same vehicle, comprising:
It is crossed in vehicle picture from a bayonet and obtains one group of vehicle parameter, and/or, one group of vehicle ginseng is obtained from a Target Photo
Number；
By all groups of vehicle parameters comprising same vehicle identity, it is determined to belong to the information of vehicles of same vehicle, it is described
Vehicle identification mark is used for the identity of unique identification vehicle.
3. according to the method described in claim 2, it is characterized in that, all groups of vehicles comprising same vehicle identity are joined
Number, is determined to belong to after the information of vehicles of same vehicle, further includes:
For not including any group of vehicle parameter of vehicle identification mark, the first specified parameter and its are determined in this group of vehicle parameter
The first specified parameter is identical in its any group of vehicle parameter, and other any group of vehicle parameter is identified comprising vehicle identification
When, determine that this group of vehicle parameter and other any group of vehicle parameters belong to the information of vehicles of same vehicle.
4. according to any method of claim 2~3, which is characterized in that being determined according to the information of vehicles of same vehicle should
Vehicle whether there is deck suspicion, comprising:
Using clustering algorithm, the multiple groups vehicle parameter combination map for belonging to same vehicle is clustered, the vehicle is obtained
Space-time trajectory；
If the distance between the corresponding tracing point of adjacent time point in same vehicle space-time trajectory is judged, with the adjacent time point time
When the ratio of difference is more than given threshold, determining the vehicle, there are deck suspicion.
5. according to any method of claim 2~3, which is characterized in that being determined according to the information of vehicles of same vehicle should
Vehicle whether there is deck suspicion, comprising:
If judge that the second specified parameter in the multiple groups vehicle parameter for the information of vehicles for belonging to same vehicle is not identical, judgement should
There are deck suspicion for vehicle.
6. the method according to claim 1, wherein the information of vehicles includes following any or multiple vehicles
The combination of parameter:
License plate number, vehicle model, vehicle color, car test mark number, Chinese herbaceous peony portion goods of furniture for display rather than for use, vehicle rear portion goods of furniture for display rather than for use, vehicle location, vehicle
Reach the time of position in picture.
7. a kind of information of vehicles analytical equipment, which is characterized in that the device includes:
First information of vehicles acquiring unit crosses vehicle picture for obtaining bayonet, extracts the first vehicle that the bayonet is crossed in vehicle picture
Information；
Second information of vehicles acquiring unit extracts the target figure for extracting the Target Photo comprising vehicle from video flowing
The second information of vehicles in piece；
Information of vehicles analytical unit, for from the first information of vehicles and the second information of vehicles of the extraction, acquisition to belong to same
The information of vehicles of one vehicle, and determine the vehicle with the presence or absence of deck suspicion according to the information of vehicles of same vehicle.
8. device according to claim 7, which is characterized in that the information of vehicles analytical unit is used for from the extraction
In first information of vehicles and the second information of vehicles, the information of vehicles for belonging to same vehicle is obtained, comprising:
It is crossed in vehicle picture from a bayonet and obtains one group of vehicle parameter, and/or, one group of vehicle ginseng is obtained from a Target Photo
Number；
By all groups of vehicle parameters comprising same vehicle identity, it is determined to belong to the information of vehicles of same vehicle, it is described
Vehicle identification mark is used for the identity of unique identification vehicle.
9. device according to claim 8, which is characterized in that the information of vehicles analytical unit is used for according to same vehicle
Information of vehicles determine the vehicle with the presence or absence of deck suspicion, comprising:
Using clustering algorithm, the multiple groups vehicle parameter combination map for belonging to same vehicle is clustered, the vehicle is obtained
Space-time trajectory；
If the distance between the corresponding tracing point of adjacent time point in same vehicle space-time trajectory is judged, with the adjacent time point time
When the ratio of difference is more than given threshold, determining the vehicle, there are deck suspicion.
10. a kind of computer storage medium, which is characterized in that the computer storage medium is stored with computer program, the meter
Calculation machine program, which is performed, realizes method as claimed in any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910171036.9A CN109872541A (en) | 2019-03-07 | 2019-03-07 | A kind of information of vehicles analysis method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910171036.9A CN109872541A (en) | 2019-03-07 | 2019-03-07 | A kind of information of vehicles analysis method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109872541A true CN109872541A (en) | 2019-06-11 |
Family
ID=66919900
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910171036.9A Pending CN109872541A (en) | 2019-03-07 | 2019-03-07 | A kind of information of vehicles analysis method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109872541A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110517502A (en) * | 2019-07-12 | 2019-11-29 | 云宝宝大数据产业发展有限责任公司 | A kind of separated stop board recognition methods of single camera |
| CN110570652A (en) * | 2019-07-30 | 2019-12-13 | 深圳市天彦通信股份有限公司 | vehicle fake plate detection reminding method and related product |
| CN110598550A (en) * | 2019-08-08 | 2019-12-20 | 横琴善泊投资管理有限公司 | Vehicle networking identification system based on multilayer information intelligent analysis |
| CN112309126A (en) * | 2020-10-30 | 2021-02-02 | 杭州海康威视数字技术股份有限公司 | License plate detection method and device, electronic equipment and computer readable storage medium |
| CN114495545A (en) * | 2022-01-28 | 2022-05-13 | 常州海蓝利科物联网技术有限公司 | Vehicle control system and method |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TW424727U (en) * | 1999-12-06 | 2001-03-01 | Asia Sun Taiwan Inc | License plate add-on structure for true and fake recognition |
| CN103810859A (en) * | 2013-07-08 | 2014-05-21 | 陈昊 | Technology for completely eradicating fake and imitated license plates in current toll-gate and electronic police systems |
| CN104933870A (en) * | 2015-05-21 | 2015-09-23 | 中兴软创科技股份有限公司 | Vehicle fake plate identification method and device based on vehicle behavior analysis |
| CN105448099A (en) * | 2015-12-14 | 2016-03-30 | 南威软件股份有限公司 | Motor vehicle fake license identification method based on big data |
| CN106971552A (en) * | 2017-04-06 | 2017-07-21 | 北京悦畅科技有限公司 | Deck phenomenon detection method and system |
| 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 |
-
2019
- 2019-03-07 CN CN201910171036.9A patent/CN109872541A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TW424727U (en) * | 1999-12-06 | 2001-03-01 | Asia Sun Taiwan Inc | License plate add-on structure for true and fake recognition |
| CN103810859A (en) * | 2013-07-08 | 2014-05-21 | 陈昊 | Technology for completely eradicating fake and imitated license plates in current toll-gate and electronic police systems |
| CN104933870A (en) * | 2015-05-21 | 2015-09-23 | 中兴软创科技股份有限公司 | Vehicle fake plate identification method and device based on vehicle behavior analysis |
| CN105448099A (en) * | 2015-12-14 | 2016-03-30 | 南威软件股份有限公司 | Motor vehicle fake license identification method based on big 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 |
| CN106971552A (en) * | 2017-04-06 | 2017-07-21 | 北京悦畅科技有限公司 | Deck phenomenon detection method and system |
Non-Patent Citations (1)
| Title |
|---|
| 陈昱嘉: "大数据在智能交通领域的应用", 《中国安防》 * |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110517502A (en) * | 2019-07-12 | 2019-11-29 | 云宝宝大数据产业发展有限责任公司 | A kind of separated stop board recognition methods of single camera |
| CN110570652A (en) * | 2019-07-30 | 2019-12-13 | 深圳市天彦通信股份有限公司 | vehicle fake plate detection reminding method and related product |
| CN110570652B (en) * | 2019-07-30 | 2021-01-05 | 深圳市天彦通信股份有限公司 | Vehicle fake plate detection reminding method and related product |
| CN110598550A (en) * | 2019-08-08 | 2019-12-20 | 横琴善泊投资管理有限公司 | Vehicle networking identification system based on multilayer information intelligent analysis |
| CN110598550B (en) * | 2019-08-08 | 2021-02-26 | 善泊科技(珠海)有限公司 | Vehicle networking identification system based on multilayer information intelligent analysis |
| CN112309126A (en) * | 2020-10-30 | 2021-02-02 | 杭州海康威视数字技术股份有限公司 | License plate detection method and device, electronic equipment and computer readable storage medium |
| CN114495545A (en) * | 2022-01-28 | 2022-05-13 | 常州海蓝利科物联网技术有限公司 | Vehicle control system and method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109872541A (en) | A kind of information of vehicles analysis method and device | |
| CN108388888B (en) | Vehicle identification method and device and storage medium | |
| Fernandez-Sanjurjo et al. | Real-time visual detection and tracking system for traffic monitoring | |
| CN104244113B (en) | A kind of video abstraction generating method based on depth learning technology | |
| CN105405154B (en) | Target object tracking based on color-structure feature | |
| CN104303193B (en) | Target classification based on cluster | |
| CN105574543B (en) | A kind of vehicle brand type identifier method and system based on deep learning | |
| CN110852269B (en) | Cross-lens portrait correlation analysis method and device based on feature clustering | |
| CN105185121B (en) | A kind of method of virtual bayonet socket parallelism recognition car plate | |
| CN103413330A (en) | Method for reliably generating video abstraction in complex scene | |
| CN103177436B (en) | Method and system for tracking object | |
| US20230396738A1 (en) | Duration and potential region of interest for suspicious activities | |
| CN106412508A (en) | Intelligent monitoring method and system of illegal line press of vehicles | |
| CN103593679A (en) | Visual human-hand tracking method based on online machine learning | |
| CN103092930A (en) | Method of generation of video abstract and device of generation of video abstract | |
| CN105528626A (en) | RFID (Radio Frequency Identification) reader and camera integrated machine and application thereof | |
| CN112434566A (en) | Passenger flow statistical method and device, electronic equipment and storage medium | |
| CN114627526A (en) | Fusion duplicate removal method and device based on multi-camera snapshot image and readable medium | |
| CN103605956A (en) | Emergency intelligence identification system based on video abstraction | |
| Kejriwal et al. | Vehicle detection and counting using deep learning basedYOLO and deep SORT algorithm for urban traffic management system | |
| CN109727268A (en) | Method for tracking target, device, computer equipment and storage medium | |
| CN113705417A (en) | Image processing method and device, electronic equipment and computer readable storage medium | |
| CN112365520B (en) | Pedestrian target real-time tracking system and method based on video big data resource efficiency evaluation | |
| CN109271859A (en) | It combines related cases method and apparatus, electronic equipment, computer storage medium | |
| CN112738725A (en) | Real-time identification method, device, equipment and medium for target crowd in semi-closed area |
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 | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20200811 Address after: 266555 Qingdao economic and Technological Development Zone, Shandong, Hong Kong Road, No. 218 Applicant after: QINGDAO HISENSE ELECTRONIC INDUSTRY HOLDING Co.,Ltd. Address before: 266071 No. 151, Zhuzhou Road, Laoshan District, Shandong, Qingdao Applicant before: Hisense TransTech Co.,Ltd. |
|
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20201127 Address after: Donghai West Road 266071 Shandong city of Qingdao province No. 17 Applicant after: HISENSE Co.,Ltd. Address before: 266555 Qingdao economic and Technological Development Zone, Shandong, Hong Kong Road, No. 218 Applicant before: QINGDAO HISENSE ELECTRONIC INDUSTRY HOLDING Co.,Ltd. |
|
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190611 |