CN105139659A - Vehicle license plate recognition method and device - Google Patents
Vehicle license plate recognition method and device Download PDFInfo
- Publication number
- CN105139659A CN105139659A CN201510650632.7A CN201510650632A CN105139659A CN 105139659 A CN105139659 A CN 105139659A CN 201510650632 A CN201510650632 A CN 201510650632A CN 105139659 A CN105139659 A CN 105139659A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- target vehicle
- license plate
- characters
- image
- 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
Landscapes
- Traffic Control Systems (AREA)
- Image Analysis (AREA)
Abstract
The invention provides a vehicle license plate recognition method and device. The method comprises the following steps: determining a target vehicle in vehicle pictures captured by checkpoint cameras, and identifying a vehicle license plate of the target vehicle; when identifying the vehicle license plate of the target vehicle is unsuccessful, with the picture snapshot time and the picture snapshot place of the target vehicle as a base point, obtaining a snapshot vehicle picture set in a set time range and a set area coverage range; and carrying out statistical analysis on the vehicle pictures in the snapshot vehicle picture set according to feature information of the target vehicle, and determining license plate characters of the target vehicle according to the statistical analysis result, wherein the feature information comprises the license plate characters and one or more of the following features: vehicle model, color, brand and driving direction. The method and device can accurately recognize the license plate characters under the complex environment of light ray influence and target interference influence and the like, and relieve the problem of low recognition rate under the complex environment.
Description
Technical field
The present invention relates to vehicle identification field, particularly licence plate recognition method and device.
Background technology
In recent years, under the overall situation that economic transition and urbanization process are accelerated, road construction is fast-developing, vehicle guaranteeding organic quantity increases sharply, the thing followed, the illegal activities (as the traffic violation, hit-and-run, robber rob the behaviors such as vehicle) relevant to vehicle occur in a large number, and this not only causes great threat for people's lives and properties and social security, simultaneously also for society brings very big economic loss.For tackling above-mentioned situation, country improves day by day to the requirement of traffic safety management, because intelligent transportation system has science, accurately and efficiently advantage more compared with conventional traffic system, therefore intelligent transportation system has become the advanced subject of China and even TRANSPOWORLD area research.
The generally acknowledged definition of intelligent transportation system be by the infotech of advanced person and computer processing technology integrated application in whole traffic management system, people's bus or train route is combined regularly, sets up one multi-transportation management system accurately and efficiently.License plate recognition technology as the important component part of intelligent transportation system, driving against traffic regulations, hit-and-run, crime escape, the major event such as robbery of motor vehicle management in there is irreplaceable vital role.
Provide multiple licence plate recognition method in prior art, but when utilizing licence plate recognition method of the prior art to carry out Car license recognition under complex environment, Car license recognition rate is lower.Complex environment comprises following several: the complex environment that (1) illumination factor causes, wherein illumination factor comprises the outdoor natural light of round-the-clock acute variation, and, car bulb or sunshine generation direct projection or a large amount of strong jamming light sources reflected to form.(2) complex environment that causes of jamming target, wherein jamming target comprises hanging near car plate and causes to car plate the payment board, operation board etc. that block.
For above-mentioned under complex environment, carry out Car license recognition time, the problem that Car license recognition rate is lower, not yet has good solution at present.
Summary of the invention
The invention provides a kind of licence plate recognition method and device, can affect at light, accurately identify characters on license plate under the complex environment such as jamming target impact, alleviate the problem that in prior art, under complex environment, car plate discrimination is low.
First aspect, embodiments provides a kind of licence plate recognition method, and described method comprises:
In the vehicle image that bayonet camera is captured, determine target vehicle, identify the car plate of described target vehicle;
When identifying the car plate failure of described target vehicle, with the video capture time of described target vehicle and video capture place for basic point, obtain the set of the vehicle image captured in the time range of setting and the regional extent of setting;
Characteristic information according to described target vehicle carries out statistical study to the vehicle image in the set of the described vehicle image captured, and determines the characters on license plate of described target vehicle according to the result of described statistical study; Wherein, described characteristic information comprises one or more in characters on license plate and following characteristics: vehicle, color, brand and travel direction.
In conjunction with first aspect, embodiments provide the first possible embodiment of first aspect, wherein, the described characteristic information according to described target vehicle carries out statistical study to the vehicle image in the set of the described vehicle image captured, determine the characters on license plate of described target vehicle according to the result of described statistical study, comprising:
The characteristic information of the vehicle in the characteristic information of target vehicle described in comparison and the set of the described vehicle image captured, filters out the vehicle image with the characteristic information identical with described target vehicle according to described comparison result in the set of the described vehicle image captured;
In the described vehicle image filtered out, select to occur the characters on license plate of the characters on license plate of maximum probability as described target vehicle.
In conjunction with the first possible embodiment of first aspect, embodiments provide the embodiment that first aspect the second is possible, wherein, describedly in the set of the described vehicle image captured, filter out the vehicle image with the characteristic information identical with described target vehicle according to described comparison result, comprising:
When identifying the part characters on license plate of described target vehicle, in the set of the described vehicle image captured, screening the characters on license plate vehicle image identical with the described part characters on license plate of described target vehicle, forming the first image subset and closing;
In described first image subset is closed, filtering out characters on license plate by the vehicle image identified completely, can form the second image subset and closes;
In described second image subset is closed, filter out the vehicle image that the travel direction vehicle identical with described target vehicle is corresponding, the vehicle image set that composition finishing screen is selected.
In conjunction with the first possible embodiment of first aspect, embodiments provide the third possible embodiment of first aspect, wherein, describedly in the set of the described vehicle image captured, filter out the vehicle image with the characteristic information identical with described target vehicle according to described comparison result, comprising:
When the whole recognition failures of the characters on license plate of described target vehicle, in the set of the described vehicle image captured, filter out the vehicle image that vehicle, color, brand and the travel direction vehicle all identical with described target vehicle is corresponding, composition the 4th image subset is closed;
In described 4th image subset is closed, filtering out characters on license plate can by the vehicle image identified completely, the vehicle image set that composition finishing screen is selected.
In conjunction with first aspect, embodiments provide first aspect the 4th kind of possible embodiment, wherein, the described characteristic information according to described target vehicle carries out statistical study to the vehicle image in the set of the described vehicle image captured, determine the characters on license plate of described target vehicle according to the result of described statistical study, comprising:
According to the characteristic information of described target vehicle, in the set of the described vehicle image captured, determine the image collection of described target vehicle;
According to the Car license recognition degree of the vehicle image in the image collection of described target vehicle, determine the characters on license plate of described target vehicle.
In conjunction with first aspect, embodiments provide first aspect the 5th kind of possible embodiment, wherein, described with the video capture time of described target vehicle and video capture place for basic point, obtain the set of the vehicle image captured in the time range of setting and the regional extent of setting, comprising:
By the time range of time range [T0-T1, T0] as setting, wherein, T0 is the video capture time of described target vehicle, and T1 is prefixed time interval;
With the video capture place of described target vehicle for the center of circle, using the regional extent of the geographic range within the scope of predetermined radii as setting;
Obtain the set of the vehicle image captured in the time range of described setting and the regional extent of described setting.
Second aspect, embodiments provides a kind of license plate recognition device, and described device comprises:
Identification module, determines target vehicle in the vehicle image captured in bayonet camera, identifies the car plate of described target vehicle;
Acquisition module, for when identifying the car plate failure of described target vehicle, with the video capture time of described target vehicle and video capture place for basic point, obtains the set of the vehicle image captured in the time range of setting and the regional extent of setting;
Determination module, carries out statistical study for the characteristic information according to described target vehicle to the vehicle image in the set of the described vehicle image captured, determines the characters on license plate of described target vehicle according to the result of described statistical study; Wherein, described characteristic information comprises one or more in characters on license plate and following characteristics: vehicle, color, brand and travel direction.
In conjunction with second aspect, embodiments provide the first possible embodiment of second aspect, wherein, described determination module comprises:
Comparison screening unit, for the characteristic information of the vehicle in the characteristic information of target vehicle described in comparison and the set of the described vehicle image captured, in the set of the described vehicle image captured, filter out the vehicle image with the characteristic information identical with described target vehicle according to described comparison result;
Selection unit, in the described vehicle image filtered out, selects to occur the characters on license plate of the characters on license plate of maximum probability as described target vehicle.
In conjunction with the first possible embodiment of second aspect, embodiments provide the embodiment that second aspect the second is possible, wherein, described comparison screening unit comprises:
First screening subelement, for when identifying the part characters on license plate of described target vehicle, in the set of the described vehicle image captured, screen the characters on license plate vehicle image identical with the described part characters on license plate of described target vehicle, form the first image subset and close;
Second screening subelement, in closing in described first image subset, filtering out characters on license plate by the vehicle image identified completely, can form the second image subset and closes;
Three screening subelement, in closing in described second image subset, filters out the vehicle image that the travel direction vehicle identical with described target vehicle is corresponding, the vehicle image set that composition finishing screen is selected.
In conjunction with the first possible embodiment of second aspect, embodiments provide the third possible embodiment of second aspect, wherein, described comparison screening unit comprises:
4th screening subelement, for when the whole recognition failures of the characters on license plate of described target vehicle, in the set of the described vehicle image captured, filter out the vehicle image that vehicle, color, brand and the travel direction vehicle all identical with described target vehicle is corresponding, composition the 4th image subset is closed;
5th screening subelement, in closing in described 4th image subset, filtering out characters on license plate can by the vehicle image identified completely, the vehicle image set that composition finishing screen is selected.
In conjunction with second aspect, embodiments provide second aspect the 4th kind of possible embodiment, wherein, described determination module comprises:
Image collection determining unit, for the characteristic information according to described target vehicle, determines the image collection of described target vehicle in the set of the described vehicle image captured;
Characters on license plate determining unit, for the Car license recognition degree according to the vehicle image in the image collection of described target vehicle, determines the characters on license plate of described target vehicle.
In conjunction with second aspect, embodiments provide second aspect the 5th kind of possible embodiment, wherein, described acquisition module comprises:
Time range setting unit, for by time range [T0-T1, T0] as setting time range, wherein, T0 is the video capture time of described target vehicle, and T1 is prefixed time interval;
Regional extent setting unit, for the video capture place of described target vehicle for the center of circle, using the geographic range within the scope of predetermined radii as setting regional extent;
Image acquisition unit, for the set of vehicle image of having captured in the regional extent of the time range and described setting that obtain described setting.
The licence plate recognition method that the embodiment of the present invention provides and device, the characteristic information according to target vehicle carries out statistical study to the vehicle image in the set of the vehicle image captured, according to the characters on license plate of the result determination target vehicle of statistical study.Because the characteristic information of target vehicle can not affect at light, change under the complex environment such as jamming target impact, therefore the characters on license plate of target vehicle determined of the characteristic information of based target vehicle accurately and reliably.Therefore accurately identify characters on license plate under the complex environment such as licence plate recognition method and device can affect at light, jamming target impact provided by the embodiment of the present invention, alleviate the problem that in prior art, under complex environment, car plate discrimination is low.
Accompanying drawing explanation
In order to be illustrated more clearly in the technical scheme of the embodiment of the present invention, be briefly described to the accompanying drawing used required in embodiment below, be to be understood that, the following drawings illustrate only some embodiment of the present invention, therefore the restriction to scope should be counted as, for those of ordinary skill in the art, under the prerequisite not paying creative work, other relevant accompanying drawings can also be obtained according to these accompanying drawings.
Fig. 1 illustrates the first schematic flow sheet of the licence plate recognition method that the embodiment of the present invention provides;
Fig. 2 illustrates the second schematic flow sheet of the licence plate recognition method that the embodiment of the present invention provides;
Fig. 3 illustrates the third schematic flow sheet of the licence plate recognition method that the embodiment of the present invention provides;
Fig. 4 illustrates the 4th kind of schematic flow sheet of the licence plate recognition method that the embodiment of the present invention provides;
Fig. 5 illustrates the 5th kind of schematic flow sheet of the licence plate recognition method that the embodiment of the present invention provides;
Fig. 6 illustrates the structural representation of the license plate recognition device that the embodiment of the present invention provides;
Fig. 7 illustrates the first structural representation of the determination module that the embodiment of the present invention provides;
Fig. 8 illustrates the first structural representation of the comparison screening unit that the embodiment of the present invention provides;
Fig. 9 illustrates the second structural representation of the comparison screening unit that the embodiment of the present invention provides;
Figure 10 illustrates the second structural representation of the determination module that the embodiment of the present invention provides;
Figure 11 illustrates the structural representation of the acquisition module that the embodiment of the present invention provides.
Embodiment
For making the object of the embodiment of the present invention, technical scheme and advantage clearly, below in conjunction with accompanying drawing in the embodiment of the present invention, technical scheme in the embodiment of the present invention is clearly and completely described, obviously, described embodiment is only the present invention's part embodiment, instead of whole embodiments.The assembly of the embodiment of the present invention describing and illustrate in usual accompanying drawing herein can be arranged with various different configuration and design.Therefore, below to the detailed description of the embodiments of the invention provided in the accompanying drawings and the claimed scope of the present invention of not intended to be limiting, but selected embodiment of the present invention is only represented.Based on embodiments of the invention, the every other embodiment that those skilled in the art obtain under the prerequisite not making creative work, all belongs to the scope of protection of the invention.
For when carrying out Car license recognition in prior art under complex environment, the problem that Car license recognition rate is lower, the invention provides a kind of licence plate recognition method and device, characteristic information based on vehicle carries out Car license recognition, can affect at light, accurately identify characters on license plate under the complex environment such as jamming target impact, thus the problem that under alleviating complex environment, car plate discrimination is low.Be described below by embodiment.
With reference to the schematic flow sheet of licence plate recognition method as shown in Figure 1, the method comprises:
Step 102, determines target vehicle, identifies the car plate of target vehicle in the vehicle image that bayonet camera is captured;
Determination and the Car license recognition process of objectives vehicle can adopt following manner: (1) utilizes the existing multiple bayonet camera being arranged on the ground such as toll station, traffic checking place and public security inspection department to take pictures to the vehicle by bayonet socket, obtains a large amount of vehicle images; (2) be target vehicle getting in a large amount of vehicle images the vehicle determined in certain vehicle image; (3) identify according to the vehicle image of existing licence plate recognition method to target vehicle, to identify the car plate of target vehicle.This mode make use of existing bayonet camera and obtains a large amount of vehicle images, realize simple and convenient, and cost is lower.
Step 104, when identifying the car plate failure of target vehicle, with the video capture time of target vehicle and video capture place for basic point, obtains the set of the vehicle image captured in the time range of setting and the regional extent of setting;
Wherein, identify that the car plate of target vehicle unsuccessfully comprises the equal None-identified of alphabet on the car plate of target vehicle, and the situation such as the partial character on the car plate of target vehicle can identify, all the other character None-identifieds.
Step 106, the characteristic information according to target vehicle carries out statistical study to the vehicle image in the set of the above-mentioned vehicle image captured, according to the characters on license plate of the result determination target vehicle of this statistical study; Wherein, above-mentioned characteristic information comprises one or more in characters on license plate and following characteristics: vehicle, color, brand and travel direction etc.
The licence plate recognition method that the embodiment of the present invention provides, the characteristic information according to target vehicle carries out statistical study to the vehicle image in the set of the vehicle image captured, according to the characters on license plate of the result determination target vehicle of statistical study.Because the characteristic information of target vehicle can not affect at light, change under the complex environment such as jamming target impact, therefore the characters on license plate of target vehicle determined of the characteristic information of based target vehicle accurately and reliably.Accurately identify characters on license plate under the complex environments such as the licence plate recognition method therefore provided by the embodiment of the present invention can be affected at light, jamming target impact, alleviate the problem that car plate discrimination under complex environment is low.
Mention in above-mentioned steps 104 with the video capture time of target vehicle and video capture place for basic point, obtain the set of the vehicle image captured in the time range of setting and the regional extent of setting, following implementation procedure can be adopted: (1) is by time range [T0-T1, T0] as the time range set, wherein, T0 is the video capture time of target vehicle, and T1 is prefixed time interval; (2) with the video capture place of target vehicle for the center of circle, using the geographic range within the scope of predetermined radii as setting regional extent; (3) set of the vehicle image captured in the time range of setting and the regional extent of setting is obtained.
In the process (1) of step 104, T1 is preferably 1 hour.One preferred embodiment in, can also by time range [T2, T3] as the time range set, wherein T2 is a time point before the video capture time T0 of target vehicle, T3 is a time point after the video capture time T0 of target vehicle, and the time interval between T2 and T0 and the time interval between T3 and T0 can set as required.In the process (2) of step 104, the coordinate in the video capture place of hypothetical target vehicle is x
0, y
0, predetermined radii scope is R, by coincidence formula
geographic range as the regional extent of setting, wherein (x, y) coordinate that is certain place, radius R can set as required.
One preferred embodiment in, a large amount of vehicle image of multiple bayonet camera shooting can be obtained by step 102, these a large amount of vehicle images composition vehicle image database.When performing step 104, after determining the regional extent of time range and the setting set, in vehicle image database, obtain the set of the vehicle image captured in the time range of setting and the regional extent of setting.This embodiment based on database can either comprehensive a large amount of vehicle image data, for traffic analysis provides data supporting, can be convenient to again the execution of step 102 and step 104, especially be convenient to the set being obtained the vehicle image captured by step 104.
By step 104, with the video capture time of target vehicle and video capture place for basic point, obtain the set of the vehicle image captured in the time range of setting and the regional extent of setting, can reduce the Car license recognition scope of target vehicle, the characters on license plate of target vehicle is determined in the set of the vehicle image captured to make follow-up basis.
That mentions in above-mentioned steps 106 carries out statistical study according to the characteristic information of target vehicle to the vehicle image in the set of the above-mentioned vehicle image captured, according to the characters on license plate of the result determination target vehicle of this statistical study, specifically in the following ways: the characteristic information of (1) comparison target vehicle and the characteristic information of the vehicle in the set of the vehicle image captured, filter out the vehicle image with the characteristic information identical with target vehicle in the set of the vehicle image captured according to comparison result; (2) in the vehicle image filtered out, select to occur the characters on license plate of the characters on license plate of maximum probability as target vehicle.In which, can by the vehicle image in the set of the vehicle image of existing image recognition technology identification target vehicle and the vehicle image captured, thus the characteristic information of vehicle in the characteristic information obtaining target vehicle and the set of vehicle image of having captured, this characteristic information comprise in characters on license plate and following characteristics one or more: vehicle, color, brand and travel direction.The vehicle image with the characteristic information identical with target vehicle screened in the set of the vehicle image captured, it can be the vehicle image with the vehicle identical with target vehicle, can also be the vehicle image with the color identical with target vehicle, can also be the vehicle image with the characters on license plate identical with target vehicle.In brief, the vehicle-to-target vehicle of the vehicle image screened has certain matching degree.The vehicle maximum due to probability of occurrence in the vehicle image that screens is most possibly target vehicle, therefore the process (2) of step 106, in the vehicle image screened, probability of occurrence is maximum, the characters on license plate that namely occurrence number is maximum is as the characters on license plate of target vehicle.
Step 106 filters out the vehicle image with the characteristic information identical with target vehicle by the method for comparison in the set of the vehicle image captured, and can reduce the Car license recognition scope of target vehicle further.Can ensure that using characteristic information as comparison standard the vehicle-to-target vehicle of the vehicle image screened has certain matching degree, thus give security for the accuracy of the characters on license plate of target vehicle finally determined.The vehicle maximum due to probability of occurrence in the vehicle image that screens is most possibly target vehicle, therefore adopts the characters on license plate of the method determination target vehicle of maximum probability, can ensure the characters on license plate determining target vehicle exactly.
Consider at step 104, identify that the car plate of target vehicle unsuccessfully can be divided into and identify part characters on license plate and characters on license plate does not identify two kinds of situations completely, and the diversity of the characteristic information of vehicle, in the present embodiment, in the process (1) of step 106, in the set of the vehicle image captured, the vehicle image with the characteristic information identical with target vehicle is filtered out according to comparison result, comprise following process: (a) is when identifying the part characters on license plate of target vehicle, the vehicle image that characters on license plate is identical with the part characters on license plate of target vehicle is screened in the set of the vehicle image captured, form the first image subset to close, b (), in the first image subset is closed, filtering out characters on license plate by the vehicle image identified completely, can form the second image subset and closes, c (), in the second image subset is closed, filters out the vehicle image that the travel direction vehicle identical with target vehicle is corresponding, the vehicle image set that composition finishing screen is selected.
Particularly, suppose that the set of the vehicle image captured is for set D.In process (a), suppose that the part characters on license plate identifying target vehicle by existing licence plate recognition method is latter three 123 of car plate, then identify the vehicle image in set D, set D in screen car plate rear three be similarly 123 vehicle image, form first image subset close.So far known, the vehicle image in the first image subset conjunction has the part characters on license plate identical with target vehicle.In process (b), in the first image subset is closed, filter out and by the vehicle image identified completely, the second image subset can be formed and close by prior art characters on license plate.So far known, the characters on license plate of the vehicle image in the second image subset conjunction can be identified completely, and the vehicle image in the second image subset conjunction has the part characters on license plate identical with target vehicle.In process (c), in the second image subset is closed, filter out the vehicle image that the travel direction vehicle identical with target vehicle is corresponding, the vehicle image set that composition finishing screen is selected.So far known, vehicle image in the set of the vehicle image that finishing screen is elected, there is the travel direction identical with target vehicle, identical part characters on license plate, and the characters on license plate of vehicle image in the set of vehicle image elected of finishing screen can be identified completely.
And then, by the process (2) of step 106, in the vehicle image screened, probability of occurrence is maximum, the characters on license plate that namely occurrence number is maximum is as the characters on license plate of target vehicle.
By process (a) as implied above, (b), (c), can when identifying the part characters on license plate of target vehicle, according to the comparison result of the characteristic information of the vehicle in the characteristic information of target vehicle and the set of vehicle image of having captured, progressively reduce the identification range of the car plate of target vehicle, until determine the final vehicle image screened, so that determined the characters on license plate of target vehicle by the process (2) of step 106.
In the present embodiment, in the process (1) of step 106, in the set of the vehicle image captured, the vehicle image with the characteristic information identical with target vehicle is filtered out according to comparison result, following process implementation can also be passed through: (d) is when the whole recognition failures of the characters on license plate of target vehicle, in the set of the vehicle image captured, filter out the vehicle image that vehicle, color, brand and the travel direction vehicle all identical with target vehicle is corresponding, composition the 4th image subset is closed; E (), in the 4th image subset is closed, filtering out characters on license plate can by the vehicle image identified completely, the vehicle image set that composition finishing screen is selected.
Particularly, suppose that the set of the vehicle image captured is for set D.In process (d), when any one characters on license plate by existing licence plate recognition method None-identified out target vehicle, then by the vehicle image of image-recognizing method identification target vehicle, determine the vehicle of target vehicle, color, brand and travel direction, and by the vehicle image in image-recognizing method identification set D, determine the vehicle of the vehicle gathered in D, color, brand and travel direction.In set D, select vehicle image corresponding to vehicle, color, brand and the travel direction vehicle all identical with target vehicle, composition the 4th image subset is closed.So far known, the vehicle image in the 4th image subset conjunction has the more characteristic information identical with target vehicle, larger with target vehicle matching degree.In process (e), identify the vehicle image in the 4th image subset conjunction, obtaining characters on license plate by the vehicle image identified completely, can be formed the vehicle image that finishing screen be elected by the vehicle image identified completely by characters on license plate.
And then, by the process (2) of step 106, in the vehicle image screened, probability of occurrence is maximum, the characters on license plate that namely occurrence number is maximum is as the characters on license plate of target vehicle.
By as above process (d) and process (e), when the whole recognition failures of the characters on license plate of target vehicle, and vehicle image that characters on license plate completely identified the highest with target vehicle matching degree can be filtered out, so that finally determine the characters on license plate of target vehicle by the process (2) of step 106 in the set of the vehicle image captured.
Under considering a kind of situation, due to the impact of light or around shelter, for first vehicle image of target vehicle, the Part I characters on license plate of target vehicle can be identified, for second vehicle image of target vehicle, the Part II characters on license plate of target vehicle can be identified, Part I characters on license plate and Part II characters on license plate are combined, whole characters on license plate of target vehicle can be obtained.In the embodiment of the present invention, in step 106, characteristic information according to target vehicle carries out statistical study to the vehicle image in the set of the above-mentioned vehicle image captured, according to the characters on license plate of the result determination target vehicle of this statistical study, following process implementation can also be passed through: (m), according to the characteristic information of target vehicle, determines the image collection of target vehicle in the set of the vehicle image captured; N (), according to the Car license recognition degree of the vehicle image in the image collection of target vehicle, determines the characters on license plate of target vehicle.
Particularly, suppose that the set of the vehicle image captured is for set D.In a kind of situation, in process (m), identify the characters on license plate of target vehicle, if according to the vehicle image of target vehicle, the part characters on license plate of target vehicle can be identified, if last three characters on license plate identifying target vehicle are 456, then according to the vehicle of the part characters on license plate of target vehicle, target vehicle, color, brand and travel direction, the vehicle image all identical with the vehicle of the part characters on license plate of target vehicle, target vehicle, color, brand and travel direction is selected, composition set E in set D.Due to the vehicle image matched of vehicle image and the target vehicle in set E, therefore determine that gathering E is the image collection of target vehicle.So far known, the vehicle image in set E all has identical part characters on license plate, as last three characters on license plate 456, and may there is completely identified characters on license plate in set E.In another kind of situation, in process (m), if according to the vehicle image of target vehicle, any characters on license plate of None-identified target vehicle, then according to the vehicle of target vehicle, color, brand and travel direction, in set D, select the vehicle image all identical with the vehicle of target vehicle, color, brand and travel direction, composition set F, determine that set F is the image collection of target vehicle.So far known, completely identified characters on license plate may be there is in set F.
The specific implementation of process (n) can be: (n1), according to the Car license recognition degree of the vehicle image in the image collection of target vehicle, is combined into the alternative characters on license plate of target vehicle; (n2) alternative characters on license plate maximum for probability of occurrence is defined as the characters on license plate of target vehicle.
In process (n1), for completely identified characters on license plate, using the alternative characters on license plate of these completely identified characters on license plate as target vehicle.Completely identified vehicle image is not had for characters on license plate, the license plate recognition result of these vehicle images comprehensive, according to the mode of existing image combining, draw the array configuration of the characters on license plate of multiple possible target vehicle, thus obtain multiple alternative characters on license plate.Be 456 as some vehicle image can identify last three characters on license plate, it is capital A that some vehicle image can identify beginning two characters on license plate, it is H5 that some vehicle image can identify middle two characters on license plate, it is 6N that some vehicle image can identify middle two characters on license plate, then the alternative characters on license plate being combined into target vehicle is capital AH5456 and A6N456.
In process (n2), in the image collection of target vehicle, for the characters on license plate identified, comprise the characters on license plate of complete characters on license plate and part, the occurrence number in all vehicle images all can be appeared at according to it, calculate the probability that it occurs, and then calculate the probability of appearance of each alternative characters on license plate, and using the characters on license plate of characters on license plate the highest for probability of occurrence as target vehicle.As, in the image collection of target vehicle, comprise 6 vehicle images altogether, the result of identification is respectively: capital A10001, capital A10002, capital A10001, capital A, XX22XXX, XXXX333, and wherein X represents and do not identify.Can be combined into 3 alternative characters on license plate according to above-mentioned 6 vehicle images, be respectively capital A10001, capital A10002, capital A22333, its probability occurred separately is respectively 2/6,1/6,1/6*1/6*1/6, therefore determines that capital A10001 is the characters on license plate of target vehicle.
By as above process (m) and (n), can according to the characteristic information of target vehicle, the image collection of target vehicle is determined in the set of the vehicle image captured, according to the Car license recognition degree of the vehicle image in the image collection of target vehicle, determine the characters on license plate of target vehicle.Characteristic information due to target vehicle is objective constant factor, and the characters on license plate that probability of occurrence is larger is more likely the characters on license plate of target vehicle, therefore by as above process (m) and (n) accurately can determine the characters on license plate of target vehicle.
In summary, when light impact or jamming target impact cause the complete None-identified of car plate maybe can only identify part, by the licence plate recognition method in the present embodiment, can in a large amount of vehicle images, the identification range of target vehicle is successively reduced, according to the characters on license plate of the probability determination target vehicle that characters on license plate occurs according to the characteristic information of vehicle.Characteristic information due to vehicle is objective constant factor, and the vehicle character that probability of occurrence is larger is more likely the characters on license plate of target vehicle, accurately identify characters on license plate under the complex environments such as the method therefore in the embodiment of the present invention can affect at light, jamming target impact, thus alleviate the problem that in prior art, under complex environment, car plate discrimination is low.
By above description, the embodiment of the present invention additionally provides a kind of licence plate recognition method as shown in Figure 2, and the method comprises:
Step 202, determines target vehicle, identifies the car plate of target vehicle in the vehicle image that bayonet camera is captured;
Step 204, when identifying the part characters on license plate of target vehicle, with the video capture time of target vehicle and video capture place for basic point, obtains the set of the vehicle image captured in the time range of setting and the regional extent of setting;
Step 206, the characteristic information of the characteristic information of comparison target vehicle and the vehicle in the set of the vehicle image captured, in the set of the vehicle image captured, screen the vehicle image that characters on license plate is identical with the part characters on license plate of target vehicle, form the first image subset and close;
Step 208, in the first image subset is closed, filtering out characters on license plate by the vehicle image identified completely, can form the second image subset and closes;
Step 210, in the second image subset is closed, filters out the vehicle image that the travel direction vehicle identical with target vehicle is corresponding, the vehicle image set that composition finishing screen is selected;
Step 212, in the vehicle image filtered out, selects to occur the characters on license plate of the characters on license plate of maximum probability as target vehicle.
By method as shown in Figure 2, can work as due to light impact or jamming target impact, when can only identify the part characters on license plate of target vehicle, the part characters on license plate identified according to target vehicle, the travel direction of target vehicle, and the probability that characters on license plate occurs, in the set of the vehicle image captured, determine the characters on license plate of target vehicle, thus improve Car license recognition rate, alleviate the problem that in prior art, under complex environment, car plate discrimination is low.
As shown in Figure 3, the embodiment of the present invention additionally provides a kind of licence plate recognition method, comprising:
Step 302, determines target vehicle, identifies the car plate of target vehicle in the vehicle image that bayonet camera is captured;
Step 304, when the whole recognition failures of the characters on license plate of target vehicle, with the video capture time of target vehicle and video capture place for basic point, obtains the set of the vehicle image captured in the time range of setting and the regional extent of setting;
Step 306, the characteristic information of the characteristic information of comparison target vehicle and the vehicle in the set of the vehicle image captured, in the set of the vehicle image captured, filter out the vehicle image that vehicle, color, brand and the travel direction vehicle all identical with target vehicle is corresponding, composition the 4th image subset is closed;
Step 308, in the 4th image subset is closed, filtering out characters on license plate can by the vehicle image identified completely, the vehicle image set that composition finishing screen is selected;
Step 310, in the vehicle image filtered out, selects to occur the characters on license plate of the characters on license plate of maximum probability as target vehicle.
By method as shown in Figure 3, can work as due to light impact or jamming target impact, when None-identified goes out any characters on license plate of target vehicle, according to travel direction vehicle, color, brand, the travel direction of target vehicle, and the probability that characters on license plate occurs, in the set of the vehicle image captured, determine the characters on license plate of target vehicle, thus improve Car license recognition rate, alleviate the problem that in prior art, under complex environment, car plate discrimination is low.
As shown in Figure 4, the embodiment of the present invention additionally provides a kind of licence plate recognition method, comprising:
Step 402, determines target vehicle, identifies the car plate of target vehicle in the vehicle image that bayonet camera is captured;
Step 404, when identifying the car plate failure of target vehicle, with the video capture time of target vehicle and video capture place for basic point, obtains the set of the vehicle image captured in the time range of setting and the regional extent of setting;
Step 406, according to the characteristic information of target vehicle, determines the image collection of target vehicle in the set of the vehicle image captured;
Step 408, according to the Car license recognition degree of the vehicle image in the image collection of target vehicle, determines the characters on license plate of target vehicle.
By method as shown in Figure 4, can according to the characteristic information of target vehicle, in the set of the vehicle image captured, determine the image collection of target vehicle, and according to the Car license recognition degree of the vehicle image in the image collection of target vehicle, determine the characters on license plate of target vehicle.Because the characteristic information of target vehicle can not affect at light, change under the complex environment such as jamming target impact, therefore the characters on license plate of target vehicle determined of the characteristic information of based target vehicle accurately and reliably.Therefore can be affected at light by licence plate recognition method as shown in Figure 4, accurately identify characters on license plate under the complex environment such as jamming target impact, improve Car license recognition rate, alleviate the problem that in prior art, under complex environment, car plate discrimination is low.
As shown in Figure 5, the embodiment of the present invention additionally provides a kind of licence plate recognition method, comprising:
Step 502, determines target vehicle, identifies the car plate of target vehicle in the vehicle image that bayonet camera is captured;
Step 504, when identifying the car plate failure of target vehicle, with the video capture time of target vehicle and video capture place for basic point, obtains the set of the vehicle image captured in the time range of setting and the regional extent of setting;
Step 506, according to the characteristic information of target vehicle, determines the image collection of target vehicle in the set of the vehicle image captured;
Step 508, according to the Car license recognition degree of the vehicle image in the image collection of target vehicle, is combined into the alternative characters on license plate of target vehicle;
Step 510, is defined as the characters on license plate of target vehicle by alternative characters on license plate maximum for probability of occurrence.
By method as shown in Figure 5, according to the Car license recognition degree of the vehicle image in the image collection of target vehicle, the alternative characters on license plate of target vehicle can be combined into, and alternative characters on license plate maximum for probability of occurrence is defined as the characters on license plate of target vehicle.Characteristic information due to target vehicle is objective constant factor, and the characters on license plate that probability of occurrence is larger is more likely the characters on license plate of target vehicle, therefore the characters on license plate of target vehicle accurately can be determined by method as shown in Figure 5, improve Car license recognition rate, alleviate the problem that in prior art, under complex environment, car plate discrimination is low.
The embodiment of the present invention additionally provides a kind of license plate recognition device, and for performing above-mentioned licence plate recognition method, as shown in Figure 6, license plate recognition device comprises:
Identification module 61, determines target vehicle in the vehicle image captured in bayonet camera, identifies the car plate of target vehicle;
Acquisition module 62, for when identifying the car plate failure of target vehicle, with the video capture time of target vehicle and video capture place for basic point, obtains the set of the vehicle image captured in the time range of setting and the regional extent of setting;
Determination module 63, carries out statistical study for the characteristic information according to target vehicle to the vehicle image in the set of the vehicle image captured, according to the characters on license plate of the result determination target vehicle of statistical study; Wherein, characteristic information comprises one or more in characters on license plate and following characteristics: vehicle, color, brand and travel direction.
The license plate recognition device that the embodiment of the present invention provides, the characteristic information according to target vehicle carries out statistical study to the vehicle image in the set of the vehicle image captured, according to the characters on license plate of the result determination target vehicle of statistical study.Because the characteristic information of target vehicle can not affect at light, change under the complex environment such as jamming target impact, therefore the characters on license plate of target vehicle determined of the characteristic information of based target vehicle accurately and reliably.Accurately identify characters on license plate under the complex environments such as the license plate recognition device therefore provided by the embodiment of the present invention can be affected at light, jamming target impact, alleviate the problem that in prior art, under complex environment, car plate discrimination is low.
As shown in Figure 7, determination module 63 in the present embodiment can comprise: comparison screening unit 71, for the characteristic information of the vehicle in the characteristic information of comparison target vehicle and the set of the vehicle image captured, in the set of the vehicle image captured, filter out the vehicle image with the characteristic information identical with target vehicle according to comparison result; Selection unit 72, in the vehicle image filtered out, selects to occur the characters on license plate of the characters on license plate of maximum probability as target vehicle.
By comparison screening unit 71 and selection unit 72, in the set of the vehicle image captured, filter out the vehicle image with the characteristic information identical with target vehicle by the method for comparison, the Car license recognition scope of target vehicle can be reduced further.Can ensure that using characteristic information as comparison standard the vehicle-to-target vehicle of the vehicle image screened has certain matching degree, thus give security for the accuracy of the characters on license plate of target vehicle finally determined.The vehicle maximum due to probability of occurrence in the vehicle image that screens is most possibly target vehicle, therefore adopts the characters on license plate of the method determination target vehicle of maximum probability, can ensure the characters on license plate determining target vehicle exactly.
As shown in Figure 8, comparison screening unit 71 in the present embodiment comprises: the first screening subelement 81, for when identifying the part characters on license plate of target vehicle, in the set of the vehicle image captured, screen the vehicle image that characters on license plate is identical with the part characters on license plate of target vehicle, form the first image subset and close; Second screening subelement 82, in closing in the first image subset, filtering out characters on license plate by the vehicle image identified completely, can form the second image subset and closes; Three screening subelement 83, in closing in the second image subset, filters out the vehicle image that the travel direction vehicle identical with target vehicle is corresponding, the vehicle image set that composition finishing screen is selected.
Subelement 82 and three screening subelement 83 is screened by the as implied above first screening subelement 81, second, can when identifying the part characters on license plate of target vehicle, according to the comparison result of the characteristic information of the vehicle in the characteristic information of target vehicle and the set of vehicle image of having captured, progressively reduce the identification range of the car plate of target vehicle, until determine the final vehicle image screened, determine the characters on license plate of target vehicle so that follow-up.
As shown in Figure 9, comparison screening unit 71 in the present embodiment can also comprise: the 4th screening subelement 91, for when the whole recognition failures of the characters on license plate of target vehicle, in the set of the vehicle image captured, filter out the vehicle image that vehicle, color, brand and the travel direction vehicle all identical with target vehicle is corresponding, composition the 4th image subset is closed; 5th screening subelement 92, in closing in the 4th image subset, filtering out characters on license plate can by the vehicle image identified completely, the vehicle image set that composition finishing screen is selected.
By the as implied above the 4th screening subelement 91 and the 5th screening subelement 92, can when the whole recognition failures of the characters on license plate of target vehicle, and vehicle image that characters on license plate completely identified the highest with target vehicle matching degree is filtered out, so that the follow-up characters on license plate finally determining target vehicle in the set of the vehicle image captured.
As shown in Figure 10, the determination module 63 in the present embodiment can comprise: image collection determining unit 111, for the characteristic information according to target vehicle, determines the image collection of target vehicle in the set of the vehicle image captured; Characters on license plate determining unit 112, for the Car license recognition degree according to the vehicle image in the image collection of target vehicle, determines the characters on license plate of target vehicle.
Wherein, characters on license plate determining unit 112 can also comprise: combination subelement, for the Car license recognition degree according to the vehicle image in the image collection of target vehicle, is combined into the alternative characters on license plate of target vehicle; Probability determination subelement, for being defined as the characters on license plate of target vehicle by alternative characters on license plate maximum for probability of occurrence.
By image collection determining unit 111 as implied above and characters on license plate determining unit 112, can according to the characteristic information of target vehicle, the image collection of target vehicle is determined in the set of the vehicle image captured, according to the Car license recognition degree of the vehicle image in the image collection of target vehicle, determine the characters on license plate of target vehicle.Characteristic information due to target vehicle is objective constant factor, and the characters on license plate that probability of occurrence is larger is more likely the characters on license plate of target vehicle, the characters on license plate of target vehicle therefore accurately can be determined by image collection determining unit 111 as implied above and characters on license plate determining unit 112.
As shown in figure 11, the acquisition module 62 in the present embodiment can comprise: time range setting unit 121, for by time range [T0-T1, T0] as the time range set, wherein, T0 is the video capture time of target vehicle, and T1 is prefixed time interval; Regional extent setting unit 122, for the video capture place of target vehicle for the center of circle, using the geographic range within the scope of predetermined radii as setting regional extent; Image acquisition unit 123, for the set of vehicle image of having captured in the regional extent of the time range and setting that obtain setting.
By time range setting unit 121, regional extent setting unit 122 and image acquisition unit 123, with the video capture time of target vehicle and video capture place for basic point, obtain the set of the vehicle image captured in the time range of setting and the regional extent of setting, can reduce the Car license recognition scope of target vehicle, the characters on license plate of target vehicle is determined in the set of the vehicle image captured to make follow-up basis.
Based on the licence plate recognition method that Fig. 2 to Fig. 5 provides, those skilled in the art can know, each module shown in Fig. 6 to Figure 11, unit, subelement also can combine accordingly, to perform the licence plate recognition method that Fig. 2 to Fig. 5 provides, repeat no more here.
In summary, the licence plate recognition method that the embodiment of the present invention provides and device, the characteristic information according to target vehicle carries out statistical study to the vehicle image in the set of the vehicle image captured, according to the characters on license plate of the result determination target vehicle of statistical study.Because the characteristic information of target vehicle can not affect at light, change under the complex environment such as jamming target impact, therefore the characters on license plate of target vehicle determined of the characteristic information of based target vehicle accurately and reliably.Therefore accurately identify characters on license plate under the complex environment such as licence plate recognition method and device can affect at light, jamming target impact provided by the embodiment of the present invention, alleviate the problem that in prior art, under complex environment, car plate discrimination is low.
The license plate recognition device that the embodiment of the present invention provides can be the specific hardware on equipment or the software be installed on equipment or firmware etc.The device that the embodiment of the present invention provides, its technique effect realizing principle and generation is identical with preceding method embodiment, is concise and to the point description, and the not mentioned part of device embodiment part can with reference to corresponding contents in preceding method embodiment.Those skilled in the art can be well understood to, and for convenience and simplicity of description, the specific works process of the system of aforementioned description, device and unit, all with reference to the corresponding process in said method embodiment, can not repeat them here.
In embodiment provided by the present invention, should be understood that disclosed apparatus and method can realize by another way.Device embodiment described above is only schematic, such as, the division of described unit, be only a kind of logic function to divide, actual can have other dividing mode when realizing, again such as, multiple unit or assembly can in conjunction with or another system can be integrated into, or some features can be ignored, or do not perform.Another point, shown or discussed coupling each other or direct-coupling or communication connection can be by some communication interfaces, and the indirect coupling of device or unit or communication connection can be electrical, machinery or other form.
The described unit illustrated as separating component or can may not be and physically separates, and the parts as unit display can be or may not be physical location, namely can be positioned at a place, or also can be distributed in multiple network element.Some or all of unit wherein can be selected according to the actual needs to realize the object of the present embodiment scheme.
In addition, each functional unit in embodiment provided by the invention can be integrated in a processing unit, also can be that the independent physics of unit exists, also can two or more unit in a unit integrated.
If described function using the form of SFU software functional unit realize and as independently production marketing or use time, can be stored in a computer read/write memory medium.Based on such understanding, the part of the part that technical scheme of the present invention contributes to prior art in essence in other words or this technical scheme can embody with the form of software product, this computer software product is stored in a storage medium, comprising some instructions in order to make a computer equipment (can be personal computer, server, or the network equipment etc.) perform all or part of step of method described in each embodiment of the present invention.And aforesaid storage medium comprises: USB flash disk, portable hard drive, ROM (read-only memory) (ROM, Read-OnlyMemory), random access memory (RAM, RandomAccessMemory), magnetic disc or CD etc. various can be program code stored medium.
It should be noted that: in similar label and letter accompanying drawing below, represent similar terms, therefore, once be defined in an a certain Xiang Yi accompanying drawing, then do not need to define further it and explain in accompanying drawing subsequently, in addition, term " first ", " second ", " the 3rd " etc. only for distinguishing description, and can not be interpreted as instruction or hint relative importance.
Last it is noted that the above embodiment, be only the specific embodiment of the present invention, in order to technical scheme of the present invention to be described, be not intended to limit, protection scope of the present invention is not limited thereto, although with reference to previous embodiment to invention has been detailed description, those of ordinary skill in the art is to be understood that: be anyly familiar with those skilled in the art in the technical scope that the present invention discloses, it still can be modified to the technical scheme described in previous embodiment or can expect change easily, or equivalent replacement is carried out to wherein portion of techniques feature, and these amendments, change or replacement, do not make the essence of appropriate technical solution depart from the spirit and scope of embodiment of the present invention technical scheme.All should be encompassed within protection scope of the present invention.Therefore, protection scope of the present invention should described be as the criterion with the protection domain of claim.
Claims (12)
1. licence plate recognition method, is characterized in that, described method comprises:
In the vehicle image that bayonet camera is captured, determine target vehicle, identify the car plate of described target vehicle;
When identifying the car plate failure of described target vehicle, with the video capture time of described target vehicle and video capture place for basic point, obtain the set of the vehicle image captured in the time range of setting and the regional extent of setting;
Characteristic information according to described target vehicle carries out statistical study to the vehicle image in the set of the described vehicle image captured, and determines the characters on license plate of described target vehicle according to the result of described statistical study; Wherein, described characteristic information comprises one or more in characters on license plate and following characteristics: vehicle, color, brand and travel direction.
2. method according to claim 1, it is characterized in that, the described characteristic information according to described target vehicle carries out statistical study to the vehicle image in the set of the described vehicle image captured, and determines the characters on license plate of described target vehicle, comprising according to the result of described statistical study:
The characteristic information of the vehicle in the characteristic information of target vehicle described in comparison and the set of the described vehicle image captured, filters out the vehicle image with the characteristic information identical with described target vehicle according to described comparison result in the set of the described vehicle image captured;
In the described vehicle image filtered out, select to occur the characters on license plate of the characters on license plate of maximum probability as described target vehicle.
3. method according to claim 2, is characterized in that, describedly in the set of the described vehicle image captured, filters out the vehicle image with the characteristic information identical with described target vehicle according to described comparison result, and comprising:
When identifying the part characters on license plate of described target vehicle, in the set of the described vehicle image captured, screening the characters on license plate vehicle image identical with the described part characters on license plate of described target vehicle, forming the first image subset and closing;
In described first image subset is closed, filtering out characters on license plate by the vehicle image identified completely, can form the second image subset and closes;
In described second image subset is closed, filter out the vehicle image that the travel direction vehicle identical with described target vehicle is corresponding, the vehicle image set that composition finishing screen is selected.
4. method according to claim 2, is characterized in that, describedly in the set of the described vehicle image captured, filters out the vehicle image with the characteristic information identical with described target vehicle according to described comparison result, and comprising:
When the whole recognition failures of the characters on license plate of described target vehicle, in the set of the described vehicle image captured, filter out the vehicle image that vehicle, color, brand and the travel direction vehicle all identical with described target vehicle is corresponding, composition the 4th image subset is closed;
In described 4th image subset is closed, filtering out characters on license plate can by the vehicle image identified completely, the vehicle image set that composition finishing screen is selected.
5. method according to claim 1, it is characterized in that, the described characteristic information according to described target vehicle carries out statistical study to the vehicle image in the set of the described vehicle image captured, and determines the characters on license plate of described target vehicle, comprising according to the result of described statistical study:
According to the characteristic information of described target vehicle, in the set of the described vehicle image captured, determine the image collection of described target vehicle;
According to the Car license recognition degree of the vehicle image in the image collection of described target vehicle, determine the characters on license plate of described target vehicle.
6. method according to claim 1, is characterized in that, described with the video capture time of described target vehicle and video capture place for basic point, obtain the set of the vehicle image captured in the time range of setting and the regional extent of setting, comprising:
By the time range of time range [T0-T1, T0] as setting, wherein, T0 is the video capture time of described target vehicle, and T1 is prefixed time interval;
With the video capture place of described target vehicle for the center of circle, using the regional extent of the geographic range within the scope of predetermined radii as setting;
Obtain the set of the vehicle image captured in the time range of described setting and the regional extent of described setting.
7. license plate recognition device, is characterized in that, described device comprises:
Identification module, determines target vehicle in the vehicle image captured in bayonet camera, identifies the car plate of described target vehicle;
Acquisition module, for when identifying the car plate failure of described target vehicle, with the video capture time of described target vehicle and video capture place for basic point, obtains the set of the vehicle image captured in the time range of setting and the regional extent of setting;
Determination module, carries out statistical study for the characteristic information according to described target vehicle to the vehicle image in the set of the described vehicle image captured, determines the characters on license plate of described target vehicle according to the result of described statistical study; Wherein, described characteristic information comprises one or more in characters on license plate and following characteristics: vehicle, color, brand and travel direction.
8. device according to claim 7, is characterized in that, described determination module comprises:
Comparison screening unit, for the characteristic information of the vehicle in the characteristic information of target vehicle described in comparison and the set of the described vehicle image captured, in the set of the described vehicle image captured, filter out the vehicle image with the characteristic information identical with described target vehicle according to described comparison result;
Selection unit, in the described vehicle image filtered out, selects to occur the characters on license plate of the characters on license plate of maximum probability as described target vehicle.
9. device according to claim 8, is characterized in that, described comparison screening unit comprises:
First screening subelement, for when identifying the part characters on license plate of described target vehicle, in the set of the described vehicle image captured, screen the characters on license plate vehicle image identical with the described part characters on license plate of described target vehicle, form the first image subset and close;
Second screening subelement, in closing in described first image subset, filtering out characters on license plate by the vehicle image identified completely, can form the second image subset and closes;
Three screening subelement, in closing in described second image subset, filters out the vehicle image that the travel direction vehicle identical with described target vehicle is corresponding, the vehicle image set that composition finishing screen is selected.
10. device according to claim 8, is characterized in that, described comparison screening unit comprises:
4th screening subelement, for when the whole recognition failures of the characters on license plate of described target vehicle, in the set of the described vehicle image captured, filter out the vehicle image that vehicle, color, brand and the travel direction vehicle all identical with described target vehicle is corresponding, composition the 4th image subset is closed;
5th screening subelement, in closing in described 4th image subset, filtering out characters on license plate can by the vehicle image identified completely, the vehicle image set that composition finishing screen is selected.
11. devices according to claim 7, is characterized in that, described determination module comprises:
Image collection determining unit, for the characteristic information according to described target vehicle, determines the image collection of described target vehicle in the set of the described vehicle image captured;
Characters on license plate determining unit, for the Car license recognition degree according to the vehicle image in the image collection of described target vehicle, determines the characters on license plate of described target vehicle.
12. devices according to claim 7, is characterized in that, described acquisition module comprises:
Time range setting unit, for by time range [T0-T1, T0] as setting time range, wherein, T0 is the video capture time of described target vehicle, and T1 is prefixed time interval;
Regional extent setting unit, for the video capture place of described target vehicle for the center of circle, using the geographic range within the scope of predetermined radii as setting regional extent;
Image acquisition unit, for the set of vehicle image of having captured in the regional extent of the time range and described setting that obtain described setting.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510650632.7A CN105139659A (en) | 2015-10-09 | 2015-10-09 | Vehicle license plate recognition method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510650632.7A CN105139659A (en) | 2015-10-09 | 2015-10-09 | Vehicle license plate recognition method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105139659A true CN105139659A (en) | 2015-12-09 |
Family
ID=54724986
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510650632.7A Pending CN105139659A (en) | 2015-10-09 | 2015-10-09 | Vehicle license plate recognition method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105139659A (en) |
Cited By (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105551261A (en) * | 2016-03-04 | 2016-05-04 | 博康智能网络科技股份有限公司 | False-license-plate vehicle detection method and system |
| CN106530739A (en) * | 2016-12-30 | 2017-03-22 | 伟龙金溢科技（深圳）有限公司 | License plate recognition method, device and system thereof based on multiple camera device |
| CN107256397A (en) * | 2017-06-13 | 2017-10-17 | 成都尽知致远科技有限公司 | License plate number recognition methods in traffic video image |
| CN107273848A (en) * | 2017-06-13 | 2017-10-20 | 成都尽知致远科技有限公司 | Video analysis method based on Number Reorganization |
| CN108389396A (en) * | 2018-02-28 | 2018-08-10 | 北京精英智通科技股份有限公司 | A kind of vehicle matching process, device and charge system based on video |
| CN109272034A (en) * | 2018-09-07 | 2019-01-25 | 佳都新太科技股份有限公司 | A kind of missing inspection license plate prediction technique and processing terminal |
| CN109389622A (en) * | 2018-09-30 | 2019-02-26 | 佳都新太科技股份有限公司 | Car tracing method, apparatus, identification equipment and storage medium |
| CN110647884A (en) * | 2019-08-22 | 2020-01-03 | 讯飞智元信息科技有限公司 | Whistling snapshot method and related device |
| CN110826415A (en) * | 2019-10-11 | 2020-02-21 | 上海眼控科技股份有限公司 | Method and device for re-identifying vehicles in scene image |
| CN110874931A (en) * | 2018-08-29 | 2020-03-10 | 北京万集科技股份有限公司 | Method, system and device for recognizing license plate of vehicle |
| CN110874934A (en) * | 2018-08-29 | 2020-03-10 | 北京万集科技股份有限公司 | License plate recognition method, system and device |
| CN110874935A (en) * | 2018-08-29 | 2020-03-10 | 北京万集科技股份有限公司 | Method, system and device for recognizing license plate of vehicle |
| CN111192461A (en) * | 2020-01-21 | 2020-05-22 | 北京筑梦园科技有限公司 | License plate recognition method, server, parking charging method and system |
| CN111292530A (en) * | 2020-02-04 | 2020-06-16 | 浙江大华技术股份有限公司 | Method, device, server and storage medium for processing violation pictures |
| CN112071083A (en) * | 2020-09-15 | 2020-12-11 | 台州市远行客网络技术有限公司 | Motor vehicle license plate relay identification system and license plate relay identification method |
| CN112528056A (en) * | 2020-11-29 | 2021-03-19 | 泰州芯源半导体科技有限公司 | Double-index field data retrieval system and method |
| CN114005186A (en) * | 2021-10-25 | 2022-02-01 | 北京筑梦园科技有限公司 | License plate recognition method and device and parking management system |
| CN114463988A (en) * | 2020-11-09 | 2022-05-10 | 浙江宇视科技有限公司 | Image acquisition method and device, electronic equipment and storage medium |
| CN114495031A (en) * | 2022-03-31 | 2022-05-13 | 青岛海信网络科技股份有限公司 | License plate information correction method, equipment and device |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1825381A (en) * | 2005-02-24 | 2006-08-30 | 株式会社日立制作所 | Number plate recognition device, adjusting method of electric lens of number plate recognition device |
| CN103065138A (en) * | 2012-12-06 | 2013-04-24 | 新疆公众信息产业股份有限公司 | Recognition method of license plate number of motor vehicle |
| DE102012113009A1 (en) * | 2012-12-21 | 2014-06-26 | Jenoptik Robot Gmbh | Method for automatically classifying moving vehicles |
| CN103927880A (en) * | 2014-04-28 | 2014-07-16 | 浙江宇视科技有限公司 | Vehicle license plate recognizing and matching method and device |
| CN104915644A (en) * | 2015-05-29 | 2015-09-16 | 安徽四创电子股份有限公司 | License plate intelligent discrimination method based on difference data reconstruction |
-
2015
- 2015-10-09 CN CN201510650632.7A patent/CN105139659A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1825381A (en) * | 2005-02-24 | 2006-08-30 | 株式会社日立制作所 | Number plate recognition device, adjusting method of electric lens of number plate recognition device |
| CN103065138A (en) * | 2012-12-06 | 2013-04-24 | 新疆公众信息产业股份有限公司 | Recognition method of license plate number of motor vehicle |
| DE102012113009A1 (en) * | 2012-12-21 | 2014-06-26 | Jenoptik Robot Gmbh | Method for automatically classifying moving vehicles |
| CN103927880A (en) * | 2014-04-28 | 2014-07-16 | 浙江宇视科技有限公司 | Vehicle license plate recognizing and matching method and device |
| CN104915644A (en) * | 2015-05-29 | 2015-09-16 | 安徽四创电子股份有限公司 | License plate intelligent discrimination method based on difference data reconstruction |
Cited By (25)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105551261A (en) * | 2016-03-04 | 2016-05-04 | 博康智能网络科技股份有限公司 | False-license-plate vehicle detection method and system |
| CN106530739A (en) * | 2016-12-30 | 2017-03-22 | 伟龙金溢科技（深圳）有限公司 | License plate recognition method, device and system thereof based on multiple camera device |
| CN107273848A (en) * | 2017-06-13 | 2017-10-20 | 成都尽知致远科技有限公司 | Video analysis method based on Number Reorganization |
| CN107256397A (en) * | 2017-06-13 | 2017-10-17 | 成都尽知致远科技有限公司 | License plate number recognition methods in traffic video image |
| CN108389396A (en) * | 2018-02-28 | 2018-08-10 | 北京精英智通科技股份有限公司 | A kind of vehicle matching process, device and charge system based on video |
| CN108389396B (en) * | 2018-02-28 | 2021-05-28 | 北京精英路通科技有限公司 | Vehicle type matching method and device based on video and charging system |
| CN110874934B (en) * | 2018-08-29 | 2021-03-19 | 北京万集科技股份有限公司 | License plate recognition method, system and device |
| CN110874935B (en) * | 2018-08-29 | 2021-09-17 | 北京万集科技股份有限公司 | Method, system and device for recognizing license plate of vehicle |
| CN110874931B (en) * | 2018-08-29 | 2021-06-15 | 北京万集科技股份有限公司 | Method, system and device for recognizing license plate of vehicle |
| CN110874931A (en) * | 2018-08-29 | 2020-03-10 | 北京万集科技股份有限公司 | Method, system and device for recognizing license plate of vehicle |
| CN110874934A (en) * | 2018-08-29 | 2020-03-10 | 北京万集科技股份有限公司 | License plate recognition method, system and device |
| CN110874935A (en) * | 2018-08-29 | 2020-03-10 | 北京万集科技股份有限公司 | Method, system and device for recognizing license plate of vehicle |
| CN109272034A (en) * | 2018-09-07 | 2019-01-25 | 佳都新太科技股份有限公司 | A kind of missing inspection license plate prediction technique and processing terminal |
| CN109389622A (en) * | 2018-09-30 | 2019-02-26 | 佳都新太科技股份有限公司 | Car tracing method, apparatus, identification equipment and storage medium |
| CN110647884A (en) * | 2019-08-22 | 2020-01-03 | 讯飞智元信息科技有限公司 | Whistling snapshot method and related device |
| CN110826415A (en) * | 2019-10-11 | 2020-02-21 | 上海眼控科技股份有限公司 | Method and device for re-identifying vehicles in scene image |
| CN111192461A (en) * | 2020-01-21 | 2020-05-22 | 北京筑梦园科技有限公司 | License plate recognition method, server, parking charging method and system |
| CN111192461B (en) * | 2020-01-21 | 2022-06-28 | 北京筑梦园科技有限公司 | License plate recognition method, server, parking charging method and system |
| CN111292530A (en) * | 2020-02-04 | 2020-06-16 | 浙江大华技术股份有限公司 | Method, device, server and storage medium for processing violation pictures |
| CN112071083A (en) * | 2020-09-15 | 2020-12-11 | 台州市远行客网络技术有限公司 | Motor vehicle license plate relay identification system and license plate relay identification method |
| CN114463988A (en) * | 2020-11-09 | 2022-05-10 | 浙江宇视科技有限公司 | Image acquisition method and device, electronic equipment and storage medium |
| CN114463988B (en) * | 2020-11-09 | 2023-10-03 | 浙江宇视科技有限公司 | Image acquisition method, device, electronic equipment and storage medium |
| CN112528056A (en) * | 2020-11-29 | 2021-03-19 | 泰州芯源半导体科技有限公司 | Double-index field data retrieval system and method |
| CN114005186A (en) * | 2021-10-25 | 2022-02-01 | 北京筑梦园科技有限公司 | License plate recognition method and device and parking management system |
| CN114495031A (en) * | 2022-03-31 | 2022-05-13 | 青岛海信网络科技股份有限公司 | License plate information correction method, equipment and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105139659A (en) | Vehicle license plate recognition method and device | |
| US10706330B2 (en) | Methods and systems for accurately recognizing vehicle license plates | |
| US11113582B2 (en) | Method and system for facilitating detection and identification of vehicle parts | |
| CN103400500B (en) | Vehicle information data acquisition device and method | |
| US11587327B2 (en) | Methods and systems for accurately recognizing vehicle license plates | |
| CN105513368B (en) | A kind of false-trademark car screening technique based on uncertain information | |
| CN106169244A (en) | The guidance information utilizing crossing recognition result provides device and method | |
| CN106384532A (en) | Video data analysis method and apparatus thereof, and parking space monitoring system | |
| CN110222596B (en) | Driver behavior analysis anti-cheating method based on vision | |
| CN111063196B (en) | Comprehensive management system for inspection station | |
| CN105448105A (en) | Patrol police vehicle-based monitoring system | |
| CN111382735A (en) | Night vehicle detection method, device, equipment and storage medium | |
| CN111814751A (en) | Vehicle attribute analysis method and system based on deep learning target detection and image recognition | |
| CN114495011A (en) | Non-motor vehicle and pedestrian illegal intrusion identification method based on target detection, storage medium and computer equipment | |
| Sikirić et al. | Image representations on a budget: Traffic scene classification in a restricted bandwidth scenario | |
| CN113688709A (en) | Intelligent detection method, system, terminal and medium for wearing safety helmet | |
| CN113901946A (en) | Abnormal behavior detection method and device, electronic equipment and storage medium | |
| CN103794051A (en) | Cloned vehicle detecting system and corresponding detecting method based on parking information | |
| CN103761345A (en) | Video retrieval method based on OCR character recognition technology | |
| CN111241918A (en) | Vehicle anti-tracking method and system based on face recognition | |
| CN111753587A (en) | Method and device for detecting falling to ground | |
| CN115272924A (en) | Treatment system based on modularized video intelligent analysis engine | |
| KR102435435B1 (en) | System for searching numbers of vehicle and pedestrian based on artificial intelligence | |
| KR101071715B1 (en) | System and method for vehicle number ignition based on ip | |
| CN111639640B (en) | License plate recognition method, device and equipment based on artificial intelligence |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20151209 |