CN103617735B - A kind of vehicle identification method and system - Google Patents
A kind of vehicle identification method and system Download PDFInfo
- Publication number
- CN103617735B CN103617735B CN201310718188.9A CN201310718188A CN103617735B CN 103617735 B CN103617735 B CN 103617735B CN 201310718188 A CN201310718188 A CN 201310718188A CN 103617735 B CN103617735 B CN 103617735B
- Authority
- CN
- China
- Prior art keywords
- vehicle
- back side
- characteristic information
- information
- car
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Abstract
This application discloses a kind of vehicle identification method, the method includes: obtain the positive feature information that vehicle frontal is corresponding；Obtain the back side characteristic information that the described vehicle back side is corresponding；When the characteristic information in described positive feature information and/or back side characteristic information meets pre-conditioned, extract and described meet the pre-conditioned characteristic information recognition result as described vehicle.Back side characteristic information supplementing as positive feature information can be passed through, obtain the recognition result of vehicle more accurately, more more accurate as final recognition result merely with the recognition result of vehicle one side than in prior art.
Description
Technical field
The application relates to vehicle identification field, particularly relates to a kind of vehicle identification method and system.
Background technology
Along with social progress, automobile use scope in life is more and more extensive, the management work of automobile is also day by day heavy with quickly increasing of automobile quantity, needing to carry out the place of vehicle identification, such as crossroad, gateway, parking lot, important highway location etc., need to carry out the identification of vehicle specifying information, such as identify mark and the licence plate of vehicle, typically via video camera, the vehicle of process is taken pictures, information by photographic intelligence identification vehicle, but the installation site owing to identifying device has certain distance with vehicle, simultaneously because the impact of external environment, as sunlight reflection light on vehicle can disturb the shooting effect of camera head, or the too short information of vehicles making camera head can not photograph a wherein car of the distance of front and back two cars, so that to the identification of information of vehicles can not be correct identified.
The recognition method of such single camera can only be identified according to the image of the one side of vehicle, and if there is above-mentioned situation, such one side knows the needs that obviously can not meet vehicle identification otherwise.
Summary of the invention
In view of this, the embodiment of the present application provides a kind of vehicle identification method, it is possible to by back side characteristic information supplementing as positive feature information, obtain the recognition result of vehicle more accurately.
To achieve these goals, the technical scheme that the application provides is as follows:
A kind of vehicle identification method, the method includes:
Obtain the positive feature information that vehicle frontal is corresponding；
Obtain the back side characteristic information that the described vehicle back side is corresponding；
When the characteristic information in described positive feature information and/or back side characteristic information meets pre-conditioned, extract and described meet the pre-conditioned characteristic information recognition result as described vehicle.
Preferably, described characteristic information includes car mark information, the number-plate number, car plate type and car plate color, when the characteristic information in described positive feature information and back side characteristic information meets pre-conditioned, including:
When the confidence level of described car mark information, the number-plate number, car plate type or car plate color exceedes predetermined threshold value, meet pre-conditioned.
Preferably, described acquisition vehicle frontal characteristic of correspondence information particularly as follows:
Obtain the direct picture of the described vehicle shot；
According to direct picture described in vehicle feature recognition algorithm identification, to obtain described positive feature information.
Preferably, described acquisition vehicle back side characteristic of correspondence information particularly as follows:
Obtain the back side image of the described vehicle shot；
According to back side image described in described positive feature information identification, to obtain described back side characteristic information.
Preferably, extract described meet the pre-conditioned characteristic information recognition result as described vehicle before also include:
Determine that described vehicle is not with car phenomenon, particularly as follows: determine that described vehicle frontal or back side car plate be not by other occlusions.
Present invention also provides a kind of vehicle identification system, including:
First identification module, for identifying the positive feature information of vehicle；
Second identification module, for identifying the back side characteristic information of vehicle；
Processing module, the positive feature information corresponding for obtaining described vehicle frontal, and obtain the back side characteristic information that the described vehicle back side is corresponding, when the characteristic information in described positive feature information and/or back side characteristic information meets pre-conditioned, extract and described meet the pre-conditioned characteristic information recognition result as described vehicle.
Preferably, described first identification module includes:
First shooting unit, for shooting the direct picture of vehicle；
First recognition unit, for according to direct picture described in vehicle feature recognition algorithm identification, to obtain described positive feature information.
Preferably, described second identification module includes:
Second shooting unit, for shooting the direct picture of vehicle；
Second recognition unit, for according to back side image described in described positive feature information identification, to obtain described back side characteristic information.
Preferably, described system also includes:
First trigger module, is used for generating the first triggering signal, triggers described first identification module and starts working.
Second trigger module, is used for generating the second triggering signal, triggers described second identification module and starts working.
Preferably, described processing module also includes:
Determine unit with car, be used for determining that described vehicle is not with car situation, be specially the described vehicle frontal car plate of identification or back side car plate not by other occlusions.
The vehicle identification method that the embodiment of the present application provides, the positive feature information corresponding by obtaining described vehicle frontal；Obtain the back side characteristic information that the described vehicle back side is corresponding；When the characteristic information in described positive feature information and/or back side characteristic information meets pre-conditioned, extract and described meet the pre-conditioned characteristic information recognition result as described vehicle.Not only obtain the characteristic information of vehicle frontal, also obtain the characteristic information at the vehicle back side, achieve the identification of the multi-angle to vehicle characteristic information, if the characteristic information in front can not complete and accurate reflection vehicle real information, back side characteristic information supplementing as positive feature information can also be passed through, obtain the recognition result of vehicle more accurately, more more accurate as final recognition result merely with the recognition result of vehicle one side than in prior art.
Accompanying drawing explanation
In order to be illustrated more clearly that the embodiment of the present application or technical scheme of the prior art, the accompanying drawing used required in embodiment or description of the prior art will be briefly described below, apparently, the accompanying drawing that the following describes is only some embodiments recorded in the application, for those of ordinary skill in the art, under the premise not paying creative work, it is also possible to obtain other accompanying drawing according to these accompanying drawings.
The schematic flow sheet of a kind of vehicle identification method that Fig. 1 provides for the embodiment of the present application；
The schematic diagram of a kind of vehicle identification system that Fig. 2 provides for the embodiment of the present application.
Detailed description of the invention
In order to make those skilled in the art be more fully understood that the technical scheme in the application, below in conjunction with the accompanying drawing in the embodiment of the present application, technical scheme in the embodiment of the present application is clearly and completely described, obviously, described embodiment is only some embodiments of the present application, rather than whole embodiments.Based on the embodiment in the application, the every other embodiment that those of ordinary skill in the art obtain under not making creative work premise, all should belong to the scope of the application protection.
The embodiment of the present application provides a kind of vehicle identification method, as it is shown in figure 1, include:
Step 101, obtains the positive feature information that described vehicle frontal is corresponding；
In the embodiment of the present application, the acquisition process of the positive feature information of vehicle is particularly as follows: obtain the direct picture of the described vehicle shot；
According to direct picture described in vehicle identification algorithm identification, to obtain described positive feature information.
nullOwing to vehicle is through needing the place identified，Such as crossing、Gateway, parking lot etc.，It it is all forward travel，The camera head of shooting vehicle is typically all the direct picture first photographing vehicle，The one side of front car plate installed by the front of vehicle and vehicle，The direct picture of the vehicle by having been taken by，According to the direct picture that vehicle identification algorithm identification has been taken by，Positive feature information is obtained from direct picture，Positive feature information can include the car mark information in the front of vehicle、The number-plate number、Car plate type and car plate color，The concrete car mark obtaining vehicle can be identified from direct picture，From license plate image，Identify the concrete number obtaining car plate，Difference due to type of vehicle，Generally can be characterized by car plate，Normal domestic car plate such as China，Car plate is single blue end wrongly written or mispronounced character，First is the abbreviation in province, place from left to right，Second is the English alphabet in concrete city, place，Several is the concrete number being made up of letter and number afterwards，And goods stock，Car plate is yellow end surplus，And military license plate is single white gravoply, with black engraved characters etc.，And the car plate of country variant difference to some extent，Concrete identification process the application repeats no more.
Step 102, obtains the back side characteristic information that the described vehicle back side is corresponding；
Impact due to actual environment, make the positive feature information recognized from direct picture not accurate enough, or positive feature information can not be recognized, such as due to bonnet reflective before vehicle, make camera head can not photograph suitable direct picture, to make direct picture be a piece of white light due to reflective, and positive feature information can not be recognized from such image, or owing to the vehicle needing shooting is excessively near with car with previous car, previous car bumper is between filming apparatus and a rear car, make filming apparatus can not photograph the direct picture of a rear car, thus also None-identified gets positive feature information.
The embodiment of the present application is by after obtaining the positive feature information of vehicle, it is likely not to have and gets complete positive feature information, even if or got complete positive feature information, it is likely to be due to the image quality issues of shooting, recognition result is made to would be likely to occur deviation, so the embodiment of the present application is after getting positive feature information, obtain the back side characteristic information of vehicle again, the one side of back side car plate is installed in the back side of vehicle namely, back side characteristic information can include the car mark information at the vehicle back side, the number-plate number, the information such as car plate type and car plate color, by the back side image having been taken by, identify back side characteristic information.
When identifying back side characteristic information, can according to the positive feature information identification back side image got, it is the single car plate of blue end wrongly written or mispronounced character as recognized the car plate of vehicle already by direct picture, so when identifying back side image, the Recognition Algorithm of License Plate that just can directly use blue end wrongly written or mispronounced character single further identifies, without the colour recognition carrying out car plate again, owing to the topmost recognition result of Car license recognition is exactly the identification of the number-plate number, if so having had identified that the car plate color of front car plate, so the identification of back side image can according to the car plate color having identified that, it is made directly the identification of the number-plate number, without the identification carrying out car plate color again, reduce the calculating intensity identified.
The acquisition of direct picture and back side image can be triggered by other equipment, generates and triggers signal, after getting triggering signal, it is possible to front or the back side to vehicle shoot, and after shooting obtains image, carry out the identification of characteristic information.Triggering signal is exactly trigger to proceed by positive feature information and the acquisition of back side characteristic information.
Certainly, the identification of back side characteristic information can also be made directly identification, and not based on the positive feature information obtained, namely the identification of positive feature information and the identification of back side characteristic information are completely self-contained two identification processes, the concrete identification process of characteristic information is not limited by the application.
Step 103, when the characteristic information in described positive feature information and/or back side characteristic information meets pre-conditioned, extracts and described meets the pre-conditioned characteristic information recognition result as described vehicle.
Extract described meet pre-conditioned characteristic information as the recognition result of described vehicle before can also comprise determining that described vehicle is not with car phenomenon, particularly as follows: determine that described vehicle frontal or back side car plate be not by other occlusions.Can pass through to identify above-mentioned direct picture and back side image, it is judged that whether car plate therein is by other occlusions, when judging that obtaining car plate is not blocked, it is determined that described vehicle is not with car phenomenon, then carries out the extraction of characteristic information.
nullNow，If the recognition result difference of the front and back number-plate number is very big，And the confidence level of twice identification all meets pre-conditioned，It can be identified that occur with car phenomenon，In actual environment-identification，Following this situation can occur，After the identification of positive feature information having carried out a car，Vehicle forward，But owing to vehicle following distance is close below，Filming apparatus had both been not picked up by the back side car plate of previous car，Also without the front car plate of a vehicle after photographing，But after a rear car moves to precalculated position，Photograph the back side car plate of a rear vehicle，And then recognized the back side number-plate number of a rear vehicle，Now the positive feature information of previous vehicle can be meet to exceed confidence level condition，Then the confidence level of the back side characteristic information of a car also meets pre-conditioned，But there is very big difference in both number-plate number recognition results，So，Even if the confidence level of positive feature information and back side characteristic information all meets pre-conditioned，But there is very big difference in the number-plate number，Now it is assured that and learns that existence is with car phenomenon.
In the embodiment of the present application when described car mark information, the number-plate number, when the confidence level of car plate type or car plate color exceedes predetermined threshold value, meet pre-conditioned, owing to positive feature information and back side characteristic information can include multiple characteristic information, need to exceed confidence level therein the characteristic information final recognition result as vehicle of predetermined threshold value, positive feature information and back side characteristic information such as, all comprise same characteristic information, as positive feature information includes the recognition result of the number-plate number, back side characteristic information also includes the recognition result of the number-plate number, so by the recognition result of two number-plate numbers, the highest characteristic information of confidence level is as the recognition result of vehicle, so final recognition result will farthest reflect the truth of vehicle.
The vehicle identification method that the embodiment of the present application provides, the positive feature information corresponding by obtaining described vehicle frontal；Obtain the back side characteristic information that the described vehicle back side is corresponding；When the characteristic information in described positive feature information and/or back side characteristic information meets pre-conditioned, extract and described meet the pre-conditioned characteristic information recognition result as described vehicle.Not only obtain the characteristic information of vehicle frontal, also obtain the characteristic information at the vehicle back side, achieve the identification of the multi-angle to vehicle characteristic information, if the characteristic information in front can not complete and accurate reflection vehicle real information, back side characteristic information supplementing as positive feature information can also be passed through, obtain the recognition result of vehicle more accurately, more more accurate as final recognition result merely with the recognition result of vehicle one side than in prior art.
Present invention also provides a kind of vehicle identification system, as in figure 2 it is shown, include:
First identification module 100, for identifying the positive feature information of vehicle；
Second identification module 200, for identifying the back side characteristic information of vehicle；
Processing module 300, the positive feature information corresponding for obtaining described vehicle frontal, and obtain the back side characteristic information that the described vehicle back side is corresponding, when the characteristic information in described positive feature information and/or back side characteristic information meets pre-conditioned, extract and described meet the pre-conditioned characteristic information recognition result as described vehicle.
Described characteristic information includes car mark information, the number-plate number, car plate type and car plate color, when the characteristic information in described positive feature information and back side characteristic information meets pre-conditioned, including:
When the confidence level of described car mark information, the number-plate number, car plate type or car plate color exceedes predetermined threshold value, meet pre-conditioned.
Described first identification module, including:
First shooting unit, for shooting the direct picture of vehicle；
First recognition unit, for according to direct picture described in vehicle feature recognition algorithm identification, to obtain described positive feature information.
Described second identification module, including:
Second shooting unit, for shooting the direct picture of vehicle；
Second recognition unit, for according to back side image described in described positive feature information identification, to obtain described back side characteristic information.
Described system also includes:
First trigger module, is used for generating the first triggering signal, triggers described first identification module and starts working.
Second trigger module, is used for generating the second triggering signal, triggers described second identification module and starts working.
Described first trigger module, the second trigger module can be ground induction coils, or other sensors, at vehicle through out-of-date, generate and trigger signal, trigger identification module and start working.
Described processing module also includes:
Determine unit with car, be used for determining that described vehicle is not with car situation, be specially the described vehicle frontal car plate of identification or back side car plate not by other occlusions.
The vehicle identification system that the embodiment of the present application provides, it is possible to get the characteristic information on the front and back two sides of a car, it is possible to obtain the recognition result of vehicle more accurately is more more accurate than the feature only identifying vehicle one side in prior art.
It should be noted that, in this article, term " includes ", " comprising " or its any other variant are intended to comprising of nonexcludability, so that include the process of a series of key element, method, article or equipment not only include those key elements, but also include other key elements being not expressly set out, or also include the key element intrinsic for this process, method, article or equipment.When there is no more restriction, statement " including ... " key element limited, it is not excluded that there is also other identical element in including the process of described key element, method, article or equipment.
It should be noted that, the above is only a part of preferred embodiment of technical scheme, enable those skilled in the art to fully understand or realize the application, rather than whole embodiments, generic principles defined herein when without departing from spirit herein or scope, can realize in other embodiments.Therefore; based on above example; for those skilled in the art; without departing from the application principle, do not making under creative work premise, it is also possible to make multiple apparent amendment and retouching; by the every other embodiment that these amendments and retouching obtain; can being applied to technical scheme, these do not affect the realization of the application, all should belong to the protection domain of the application.Therefore, the application is not intended to be limited to the embodiments shown herein, but to accord with principles disclosed herein and the consistent the widest scope of features of novelty.
It is discussed in detail present application has been above, used herein can principle and the embodiment of the application be set forth specific case, the explanation of above example is only intended to help and understands the present processes and core concept thereof, simultaneously, for one of ordinary skill in the art, according to the thought of the application, all will change in specific embodiments and applications, in sum, this specification content should not be construed as the restriction to the application.
Claims (7)
1. a vehicle identification method, it is characterised in that the method includes:
Obtain the positive feature information that vehicle frontal is corresponding；
Obtain the back side characteristic information that the described vehicle back side is corresponding；
When the characteristic information in described positive feature information and/or back side characteristic information meets pre-conditioned, extract and described meet the pre-conditioned characteristic information recognition result as described vehicle；
Wherein, described characteristic information includes car mark information, the number-plate number, car plate type and car plate color, when the characteristic information in described positive feature information and back side characteristic information meets pre-conditioned, including:
When the confidence level of described car mark information, the number-plate number, car plate type or car plate color exceedes predetermined threshold value, meet pre-conditioned；
Described acquisition vehicle back side characteristic of correspondence information particularly as follows:
Obtain the back side image of the described vehicle shot；
According to back side image described in described positive feature information identification, to obtain described back side characteristic information.
2. method according to claim 1, it is characterised in that described acquisition vehicle frontal characteristic of correspondence information particularly as follows:
Obtain the direct picture of the described vehicle shot；
According to direct picture described in vehicle feature recognition algorithm identification, to obtain described positive feature information.
3. method according to claim 1, it is characterised in that extract described meet the pre-conditioned characteristic information recognition result as described vehicle before also include:
Determine that described vehicle is not with car phenomenon, particularly as follows: determine that described vehicle frontal or back side car plate be not by other occlusions.
4. a vehicle identification system, it is characterised in that including:
First identification module, for identifying the positive feature information of vehicle；
Second identification module, for identifying the back side characteristic information of vehicle；
Processing module, the positive feature information corresponding for obtaining described vehicle frontal, and obtain the back side characteristic information that the described vehicle back side is corresponding, when the characteristic information in described positive feature information and/or back side characteristic information meets pre-conditioned, extract and described meet the pre-conditioned characteristic information recognition result as described vehicle；
Wherein, described characteristic information includes car mark information, the number-plate number, car plate type and car plate color, when the characteristic information in described positive feature information and back side characteristic information meets pre-conditioned, including:
When the confidence level of described car mark information, the number-plate number, car plate type or car plate color exceedes predetermined threshold value, meet pre-conditioned；
Described second identification module includes:
Second shooting unit, for shooting the back side image of vehicle；
Second recognition unit, for according to back side image described in described positive feature information identification, to obtain described back side characteristic information.
5. system according to claim 4, it is characterised in that described first identification module includes:
First shooting unit, for shooting the direct picture of vehicle；
First recognition unit, for according to direct picture described in vehicle feature recognition algorithm identification, to obtain described positive feature information.
6. system according to claim 4, it is characterised in that described system also includes:
First trigger module, is used for generating the first triggering signal, triggers described first identification module and starts working；
Second trigger module, is used for generating the second triggering signal, triggers described second identification module and starts working.
7. system according to claim 4, it is characterised in that described processing module also includes:
Determine unit with car, be used for determining that described vehicle is not with car situation, be specially the described vehicle frontal car plate of identification or back side car plate not by other occlusions.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310718188.9A CN103617735B (en) | 2013-12-20 | 2013-12-20 | A kind of vehicle identification method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310718188.9A CN103617735B (en) | 2013-12-20 | 2013-12-20 | A kind of vehicle identification method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103617735A CN103617735A (en) | 2014-03-05 |
| CN103617735B true CN103617735B (en) | 2016-07-06 |
Family
ID=50168438
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310718188.9A Active CN103617735B (en) | 2013-12-20 | 2013-12-20 | A kind of vehicle identification method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103617735B (en) |
Families Citing this family (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104167099A (en) * | 2014-08-13 | 2014-11-26 | 青岛盛嘉信息科技有限公司 | Electronic eye |
| CN104168456A (en) * | 2014-08-13 | 2014-11-26 | 青岛盛嘉信息科技有限公司 | Parking management method |
| JP6524846B2 (en) * | 2015-08-04 | 2019-06-05 | オムロン株式会社 | Vehicle identification device and vehicle identification system provided with the same |
| CN106228179A (en) * | 2016-07-13 | 2016-12-14 | 乐视控股（北京）有限公司 | The method and system of vehicle comparison |
| CN107705572A (en) * | 2017-05-15 | 2018-02-16 | 西安艾润物联网技术服务有限责任公司 | Parking lot control method for vehicle, device, system and storage medium |
| CN107680406B (en) * | 2017-10-31 | 2018-10-12 | 深圳市小猫信息技术有限公司 | A kind of license board information acquisition system |
| WO2019084821A1 (en) * | 2017-10-31 | 2019-05-09 | 深圳市小猫信息技术有限公司 | License plate information acquisition system |
| CN111508231B (en) * | 2019-05-16 | 2021-04-27 | 杭州海康威视系统技术有限公司 | Vehicle following determination method, device and system for vehicles on the spot and electronic equipment |
| CN110491133B (en) * | 2019-08-08 | 2020-10-16 | 善泊科技(珠海)有限公司 | Vehicle information correction system and method based on confidence |
| CN110991255B (en) * | 2019-11-11 | 2023-09-08 | 智慧互通科技股份有限公司 | Method for detecting fake-licensed car based on deep learning algorithm |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH07302304A (en) * | 1986-05-05 | 1995-11-14 | Perceptics Corp | Apparatus for analysis of character of image |
| EP0585916B1 (en) * | 1992-09-03 | 2000-03-01 | Alcatel | Device for the recognition of signs on objects, in particular for characters and ciphers on number plates of vehicles |
| CN101178853A (en) * | 2006-11-07 | 2008-05-14 | 奥城同立科技开发（北京）有限公司 | Traffic roads image side direction grasp shooting method and traffic roads image side direction grasp shoot electronic policeman system |
| CN101339697A (en) * | 2008-08-14 | 2009-01-07 | 北京中星微电子有限公司 | Vehicle jaywalk checking system and method |
| CN101520841A (en) * | 2009-03-10 | 2009-09-02 | 北京航空航天大学 | Real-time and anti-interference method for positioning license plate in high-definition TV video |
| CN102289656A (en) * | 2011-05-11 | 2011-12-21 | 苏州两江科技有限公司 | Method for calculating effect of traffic flow on city pollution |
| CN102542806A (en) * | 2010-12-28 | 2012-07-04 | 沈阳聚德视频技术有限公司 | Real-time monitoring system for license plate shielding of vehicles running on speedway and control method thereof |
| CN102682608A (en) * | 2012-05-16 | 2012-09-19 | 江苏尤特斯新技术有限公司 | Method for image forensics of motor vehicle plate covering and staining behaviors |
| CN102722733A (en) * | 2012-05-31 | 2012-10-10 | 信帧电子技术（北京）有限公司 | Identification method and device of license plate types |
| CN103246876A (en) * | 2013-05-10 | 2013-08-14 | 苏州祥益网络科技有限公司 | Image feature comparison based counterfeit vehicle registration plate identification method |
| CN103324920A (en) * | 2013-06-27 | 2013-09-25 | 华南理工大学 | Method for automatically identifying vehicle type based on vehicle frontal image and template matching |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1928892A (en) * | 2006-09-20 | 2007-03-14 | 王枚 | Method and device for license plate location recognition, vehicle-logo location recognition and vehicle type |
| CN101630361A (en) * | 2008-12-30 | 2010-01-20 | 北京邮电大学 | Plate number, body color and mark identification-based equipment and plate number, body color and mark identification-based method for identifying fake plate vehicles |
| CN101872416B (en) * | 2010-05-06 | 2013-05-01 | 复旦大学 | Vehicle license plate recognition method and system of road image |
| CN102982311B (en) * | 2012-09-21 | 2016-03-30 | 公安部第三研究所 | Based on automobile video frequency Feature Extraction System and the method for video structural description |
-
2013
- 2013-12-20 CN CN201310718188.9A patent/CN103617735B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH07302304A (en) * | 1986-05-05 | 1995-11-14 | Perceptics Corp | Apparatus for analysis of character of image |
| EP0585916B1 (en) * | 1992-09-03 | 2000-03-01 | Alcatel | Device for the recognition of signs on objects, in particular for characters and ciphers on number plates of vehicles |
| CN101178853A (en) * | 2006-11-07 | 2008-05-14 | 奥城同立科技开发（北京）有限公司 | Traffic roads image side direction grasp shooting method and traffic roads image side direction grasp shoot electronic policeman system |
| CN101339697A (en) * | 2008-08-14 | 2009-01-07 | 北京中星微电子有限公司 | Vehicle jaywalk checking system and method |
| CN101520841A (en) * | 2009-03-10 | 2009-09-02 | 北京航空航天大学 | Real-time and anti-interference method for positioning license plate in high-definition TV video |
| CN102542806A (en) * | 2010-12-28 | 2012-07-04 | 沈阳聚德视频技术有限公司 | Real-time monitoring system for license plate shielding of vehicles running on speedway and control method thereof |
| CN102289656A (en) * | 2011-05-11 | 2011-12-21 | 苏州两江科技有限公司 | Method for calculating effect of traffic flow on city pollution |
| CN102682608A (en) * | 2012-05-16 | 2012-09-19 | 江苏尤特斯新技术有限公司 | Method for image forensics of motor vehicle plate covering and staining behaviors |
| CN102722733A (en) * | 2012-05-31 | 2012-10-10 | 信帧电子技术（北京）有限公司 | Identification method and device of license plate types |
| CN103246876A (en) * | 2013-05-10 | 2013-08-14 | 苏州祥益网络科技有限公司 | Image feature comparison based counterfeit vehicle registration plate identification method |
| CN103324920A (en) * | 2013-06-27 | 2013-09-25 | 华南理工大学 | Method for automatically identifying vehicle type based on vehicle frontal image and template matching |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103617735A (en) | 2014-03-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103617735B (en) | A kind of vehicle identification method and system | |
| CN110501018B (en) | Traffic sign information acquisition method for high-precision map production | |
| CA2885019C (en) | Robust windshield detection via landmark localization | |
| CN101436348B (en) | Electronic policeman system and information identification method applied to the same | |
| US11380104B2 (en) | Method and device for detecting illegal parking, and electronic device | |
| US9704060B2 (en) | Method for detecting traffic violation | |
| JP6942733B2 (en) | Counterfeit detection of optically active articles using security elements | |
| CN103778787B (en) | Automobile false deck recognition logic determination methods | |
| CN110443225A (en) | A kind of actual situation Lane detection method and device thereof based on statistics of pixel eigenvalue | |
| CN104408475B (en) | A kind of licence plate recognition method and car license recognition equipment | |
| CN107016362B (en) | Vehicle weight recognition method and system based on vehicle front windshield pasted mark | |
| CN106169244A (en) | The guidance information utilizing crossing recognition result provides device and method | |
| CN105740855A (en) | Front and rear license plate detection and recognition method based on deep learning | |
| US20180107892A1 (en) | Dual embedded optical character recognition (ocr) engines | |
| CN101630361A (en) | Plate number, body color and mark identification-based equipment and plate number, body color and mark identification-based method for identifying fake plate vehicles | |
| CN109344805A (en) | Traffic offence picture intelligence preliminary hearing method and device | |
| CN108133599A (en) | A kind of slag-soil truck video frequency identifying method and system | |
| CN109657674A (en) | A kind of vehicles identifications determine method and device | |
| CN104978746A (en) | Running vehicle body color identification method | |
| Gao et al. | On‐line vehicle detection at nighttime‐based tail‐light pairing with saliency detection in the multi‐lane intersection | |
| CN105354573A (en) | Container license plate identification method and system | |
| Boumediene et al. | Vehicle detection algorithm based on horizontal/vertical edges | |
| CN108765955B (en) | Intelligent automobile state detection sharing method and system based on license plate recognition | |
| Deng et al. | An integrated forward collision warning system based on monocular vision | |
| Amirgaliyev et al. | License plate verification method for automatic license plate recognition systems |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant |