CN109657590A - A kind of method, apparatus and storage medium detecting information of vehicles - Google Patents
A kind of method, apparatus and storage medium detecting information of vehicles Download PDFInfo
- Publication number
- CN109657590A CN109657590A CN201811512123.8A CN201811512123A CN109657590A CN 109657590 A CN109657590 A CN 109657590A CN 201811512123 A CN201811512123 A CN 201811512123A CN 109657590 A CN109657590 A CN 109657590A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- license plate
- area image
- model
- matched
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/50—Extraction of image or video features by performing operations within image blocks; by using histograms, e.g. histogram of oriented gradients [HoG]; by summing image-intensity values; Projection analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
- G06V30/14—Image acquisition
- G06V30/148—Segmentation of character regions
- G06V30/153—Segmentation of character regions using recognition of characters or words
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Traffic Control Systems (AREA)
- Image Analysis (AREA)
Abstract
The embodiment of the invention discloses a kind of method, apparatus and storage medium for detecting information of vehicles, the method is applied to make an inspection tour vehicle or outpost or mobile holder, camera is carried on the tour vehicle or the outpost or the mobile holder, which comprises acquires the realtime graphic taken in the camera shooting visual angle;According to preset auto model from the realtime graphic, determine and the matched vehicle characteristics area image of auto model;According to preset license plate model from the vehicle characteristics area image, the vehicle license plate characteristic area image with license plate Model Matching is determined;The vehicle license plate characteristic area image is split, character picture is obtained;The character picture is calculated based on deep neural network, obtains license plate number.The embodiment of the present invention can be improved the recognition efficiency and recognition accuracy of information of vehicles.
Description
Technical field
The present invention relates to technical field of vehicle more particularly to a kind of method, apparatus and storage medium for detecting information of vehicles.
Background technique
Information of vehicles detection system security protection, traffic administration, Car park payment field using more and more extensive, traditional vehicle
Although what board identifying system can be rough identifies information of vehicles, discrimination is low and recognition speed is slow, especially in vehicle
When quantity is excessive or car speed is very fast, the recognition efficiency and recognition accuracy of traditional identification license plate system are lower, it is seen then that pass
The vehicle license plate system of system is poor to environmental suitability, can not be suitable for the dynamic detection scene of high speed.
Summary of the invention
Based on this, for the recognition efficiency and the lower skill of recognition accuracy for solving identification license plate system traditional in the prior art
Art problem, spy propose a kind of method for detecting information of vehicles.
A method of detection information of vehicles, the method is applied to make an inspection tour vehicle or outpost or mobile holder, described to patrol
Depending on carrying camera on vehicle or the outpost or the mobile holder, which comprises
Acquire the realtime graphic taken in the camera shooting visual angle;
According to preset auto model from the realtime graphic, determine and the matched vehicle characteristics region of auto model
Image;
According to preset license plate model from the vehicle characteristics area image, the license plate with license plate Model Matching is determined
Feature regional images;
The vehicle license plate characteristic area image is split, character picture is obtained;
The character picture is calculated based on deep neural network, obtains license plate number.
In one of the embodiments, it is described determine with after the matched vehicle characteristics area image of auto model, institute
State method further include:
Type of vehicle analysis carried out to the vehicle characteristics area image based on type of vehicle sorter network, it is determining with it is described
The matched type of vehicle of vehicle characteristics area image.
In one of the embodiments, it is described according to preset license plate model from the vehicle characteristics area image, really
After making the vehicle license plate characteristic area image with license plate Model Matching, the method also includes:
License plate type analysis, the determining and license plate are carried out to the vehicle license plate characteristic area image based on license plate sorter network
The matched license plate type of feature regional images.
In one of the embodiments, it is described determine with after the matched vehicle characteristics area image of auto model, institute
State method further include:
Color character analysis is carried out to the vehicle characteristics area image based on license plate sorter network, determines that the vehicle is special
Levy automotive colors feature corresponding to area image.
In addition, to solve the recognition efficiency and the lower technology of recognition accuracy of identification license plate system traditional in the prior art
Problem, spy propose a kind of for detecting the device of information of vehicles.
It is a kind of for detecting the device of information of vehicles, described device includes:
Module is obtained, for acquiring the realtime graphic taken in camera shooting visual angle;
Processing module, for the recognition efficiency and the lower technology of recognition accuracy according to preset traditional identification license plate system
Problem, spy propose a kind of for detecting the device of information of vehicles.
It is a kind of for detecting the device of information of vehicles, described device includes:
Module is obtained, for acquiring the realtime graphic taken in camera shooting visual angle;
Processing module, for from the realtime graphic, determining to match with auto model according to preset auto model
Vehicle characteristics area image;According to preset license plate model from the vehicle characteristics area image, determine and license plate mould
The matched vehicle license plate characteristic area image of type;The vehicle license plate characteristic area image is split, character picture is obtained;Based on depth
Neural network calculates the character picture, obtains license plate number.
The processing module is being determined and the matched vehicle characteristics administrative division map of auto model in one of the embodiments,
As after, it is also used to:
Type of vehicle analysis carried out to the vehicle characteristics area image based on type of vehicle sorter network, it is determining with it is described
The matched type of vehicle of vehicle characteristics area image.
The auto model of the processing module is from the realtime graphic in one of the embodiments, determines and vehicle
The vehicle characteristics area image of Model Matching;According to preset license plate model from the vehicle characteristics area image, determine
Out with the vehicle license plate characteristic area image of license plate Model Matching;The vehicle license plate characteristic area image is split, character figure is obtained
Picture;The character picture is calculated based on deep neural network, obtains license plate number.
The processing module is being determined and the matched vehicle characteristics administrative division map of auto model in one of the embodiments,
As after, it is also used to:
Type of vehicle analysis carried out to the vehicle characteristics area image based on type of vehicle sorter network, it is determining with it is described
The matched type of vehicle of vehicle characteristics area image.
In one of the embodiments, the processing module according to preset license plate model from the vehicle characteristics region
In image, after determining the vehicle license plate characteristic area image with license plate Model Matching, it is also used to:
License plate type analysis, the determining and license plate are carried out to the vehicle license plate characteristic area image based on license plate sorter network
The matched license plate type of feature regional images.
The processing module is being determined and the matched vehicle characteristics administrative division map of auto model in one of the embodiments,
As after, it is also used to:
Color character analysis is carried out to the vehicle characteristics area image based on license plate sorter network, determines that the vehicle is special
Levy automotive colors feature corresponding to area image.
In addition, lower for the recognition efficiency and recognition accuracy of traditional identification license plate system in the prior art to solve
Technical problem, spy propose a kind of control equipment.
It is a kind of for detecting the device of information of vehicles, described for detecting the device of information of vehicles includes processor and storage
Device, the processor execute the computer program of the memory storage to realize the Information Regulating method.
In addition, lower for the recognition efficiency and recognition accuracy of traditional identification license plate system in the prior art to solve
Technical problem, spy propose a kind of computer readable storage medium comprising instruction, when run on a computer, so that
Computer executes method described in any embodiment in the various embodiments described above.
Implement the embodiment of the present invention, will have the following beneficial effects:
It, can be by according to preset vehicle after the method, apparatus and storage medium of above-mentioned detection information of vehicles
Model is determined and the matched vehicle characteristics area image of auto model from the realtime graphic of acquisition;According to preset vehicle
Board model determines the vehicle license plate characteristic area image with license plate Model Matching from the vehicle characteristics area image;To described
Vehicle license plate characteristic area image is split, and obtains character picture;The character picture is calculated based on deep neural network,
And then obtain license plate number.As it can be seen that this mode can by the feature by comprehensively, really reflecting vehicle that candid photograph is arrived,
Then with the matching of preset license plate model, preset auto model, and then improve information of vehicles recognition efficiency and identification it is quasi-
True rate.
Detailed description of the invention
It to describe the technical solutions in the embodiments of the present invention more clearly, below will be to needed in the embodiment
Attached drawing is briefly described, it should be apparent that, drawings in the following description are only some embodiments of the invention, for ability
For the those of ordinary skill of domain, without creative efforts, it can also be obtained according to these attached drawings other attached
Figure.
Fig. 1 is a kind of schematic diagram of a scenario for detecting information of vehicles disclosed in one embodiment;
Fig. 2 is a kind of flow diagram for the method for detecting information of vehicles disclosed in one embodiment;
Fig. 3 is a kind of schematic diagram of a scenario for detecting information of vehicles disclosed in one embodiment;
Fig. 4 is a kind of schematic diagram of a scenario for detecting information of vehicles disclosed in one embodiment;
Fig. 5 is a kind of for detecting the structural schematic diagram of the device of information of vehicles disclosed in one embodiment;
Fig. 6 is a kind of for detecting the structural schematic diagram of the device of information of vehicles disclosed in one embodiment.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that the described embodiment is only a part of the embodiment of the present invention, instead of all the embodiments.Based on this
Embodiment in invention, every other reality obtained by those of ordinary skill in the art without making creative efforts
Example is applied, shall fall within the protection scope of the present invention.
It should be noted that term " includes " and " tool in description and claims of this specification and above-mentioned attached drawing
Have " and their any deformations, it is intended that it covers and non-exclusive includes.Such as contain the mistake of a series of steps or units
Journey, method, system, product or equipment are not limited to listed step or unit, but optionally further comprising do not list
The step of or unit, or optionally further comprising other step or units intrinsic for these process, methods, product or equipment.
The embodiment of the invention discloses it is a kind of detect information of vehicles method, apparatus and storage medium, can by comprehensively,
Really reflect the feature of vehicle that candid photograph is arrived, then with the matching of preset license plate model, preset auto model, in turn
Improve the recognition efficiency and recognition accuracy of information of vehicles.Attached drawing is combined below to be described in detail.
Referring to Fig. 1, Fig. 1 is a kind of schematic diagram of a scenario for detecting information of vehicles disclosed in one embodiment.
As shown in Figure 1, including vehicle, camera, the device for detecting information of vehicles and the cloud on road surface in the scene
Server etc..It, can be with it should be noted that can also include but is not limited to component shown in FIG. 1 in scene shown in FIG. 1
Including other components, for example make an inspection tour vehicle, mobile holder or roadside unit etc..
Wherein, can be on board unit for detecting the device of information of vehicles, also can include but is not limited to smart phone,
Laptop, personal computer (Personal Computer, PC), personal digital assistant (Personal Digital
Assistant, PDA), each class of electronic devices such as mobile internet device (Mobile Internet Device, MID).
Wherein, camera can be moving camera, EO-1 hyperion camera etc., and EO-1 hyperion camera can be in very wide spectral band model
Image is continuously acquired in enclosing, high spectrum image has higher spectral resolution than multispectral image, and usual precision can reach 2
~3nm.The high light spectrum image-forming imaging technique novel as one kind, the basic principle is that, the surface of different substances is to different waves
The spectrum (or electromagnetic wave) of section has different reflectivity and refractive index.It, can be according to different reflection spectrum images based on this
Obtain the more characteristic informations of object to be measured.During imaging, the wave band of spectrum is got thinner, and obtained material property is just
It is more, it can reflect object features situation from different characteristic angles.Therefore, high light spectrum image-forming can sufficiently reflect vehicle or vehicle
The spectral information at each position of board, the vehicle for enabling the realtime graphic taken comprehensively, really to reflect that candid photograph is arrived
Feature so as to higher with preset license plate model, the matching degree of preset auto model, and then improves the identification effect of information of vehicles
Rate and recognition accuracy.
Referring to Fig. 2, Fig. 2 is a kind of flow diagram for the method for detecting information of vehicles disclosed in one embodiment.Such as
Shown in Fig. 2, the method for the detection information of vehicles be may comprise steps of:
Step S201, the realtime graphic taken in the camera shooting visual angle is acquired.
In the embodiment of the present invention, camera can be moving camera, be capable of high speed, candid photograph to dynamic image in real time, tool
Frequency, software or hardware setting the application of body shooting are without limitation.
Step S202, it according to preset auto model from the realtime graphic, determines and the matched vehicle of auto model
Feature regional images.
Specifically, preset auto model can be and count to obtain based on mass data, include the part circulated on the market
Or the auto model of whole patterns.
Step S203, it according to preset license plate model from the vehicle characteristics area image, determines and license plate model
Matched vehicle license plate characteristic area image.
Wherein, preset license plate model can be counts to obtain based on mass data, the part comprising circulating on the market or
The license plate model of full format.For example, square, rectangle or circle etc..Thus can use the geometrical characteristic of license plate with
And the edge statistics of histogram feature in license plate area determines actually active license plate area (i.e. vehicle license plate characteristic administrative division map
Picture).
In some embodiments, the vehicle license plate characteristic administrative division map can be determined according to the algorithm in image characteristics extraction field
Picture, for example, by using histograms of oriented gradients (Histogram of Oriented Gradient, HOG) feature, local binary mould
Formula (Local Binary Pattern, LBP) feature, Haar characteristics algorithm, the present invention is not to the determining vehicle license plate characteristic administrative division map
The algorithm of picture limits.
Step S204, the vehicle license plate characteristic area image is split, obtains character picture.
Step S205, the character picture is calculated based on deep neural network, obtains license plate number.
In the embodiment of the present invention, by from the realtime graphic of acquisition, being determined according to preset auto model and vehicle
The vehicle characteristics area image of Model Matching;According to preset license plate model from the vehicle characteristics area image, determine
With the vehicle license plate characteristic area image of license plate Model Matching;The vehicle license plate characteristic area image is split, character picture is obtained;
The character picture is calculated based on deep neural network, and then obtains license plate number.As it can be seen that this mode can be by complete
Face, the feature for really reflecting the vehicle that candid photograph is arrived, so that the matching degree of its preset license plate model, preset auto model
It is higher, and then improve the recognition efficiency and recognition accuracy of information of vehicles.
In some embodiments of the application, may recognize that other information of vehicles, for example, identify type of vehicle,
License plate type and automotive colors feature.It is introduced individually below:
In some embodiments, determine with after the matched vehicle characteristics area image of auto model, the method
Further include:
Type of vehicle analysis carried out to the vehicle characteristics area image based on type of vehicle sorter network, it is determining with it is described
The matched type of vehicle of vehicle characteristics area image.For example, type of vehicle can be car, offroad vehicle, bus, ambulance,
Fire fighting truck, police car and school bus etc..Vehicle size, vehicle body shape, the special installation of vehicle body, special marking or Special Graphs can be combined
Case determines type of vehicle.For example, detecting that roof has the sudden and violent flashing light of red indigo plant, that can be determined as police car.In another example detecting vehicle
Body has the special markings such as campus figure brightness or campus title, that can be determined as school bus.
In some embodiments, according to preset license plate model from the vehicle characteristics area image, determine and vehicle
After the vehicle license plate characteristic area image of board Model Matching, the method also includes:
License plate type analysis, the determining and license plate are carried out to the vehicle license plate characteristic area image based on license plate sorter network
The matched license plate type of feature regional images.For example, license plate type can be blue board, yellow card, new energy board, army's board.
In some embodiments, it is described determine with after the matched vehicle characteristics area image of auto model, the side
Method further include:
Color character analysis is carried out to the vehicle characteristics area image based on license plate sorter network, determines that the vehicle is special
Levy automotive colors feature corresponding to area image.For example, automotive colors feature can be yellow, black, silver color etc., do not limit specifically
It is fixed, it can be used for later period crime tracking, convenient for quickly positioning.
For ease of understanding, below by taking two specific application scenarios as an example.
As shown in figure 3, the device for detecting information of vehicles is mountable in inspection car, to what is berthed in parking position
Vehicle is recorded in real time, and information is uploaded background server in real time, for hind computation parking fee.Parking can also be disobeyed to roadside
It collects evidence, and forensic information is uploaded into backstage in real time and is recorded.
As shown in figure 4, the device for detecting information of vehicles is mountable in fixed bayonet, so that this is used to detect vehicle letter
The device of breath can record all vehicular traffic information efficiently, in real time, low precision slow compared to the speed of traditional identifying system
The shortcomings that, the present invention has preferable improvement, is highly suitable for traffic monitoring, evidence obtaining violating the regulations and crime tracking.
As it can be seen that collecting image by high resolution camera, different information, energy are calculated by deep neural network
Enough achieve the effect that handle in real time, has better precision, higher reliability and robustness compared to such as traditional algorithm.
Referring to Fig. 5, Fig. 5 shows for a kind of structure for detecting the device 50 of information of vehicles disclosed in one embodiment
It is intended to.As shown in Figure 5, wherein device 50 described in Fig. 5 can be used for executing the described detection information of vehicles of Fig. 2-Fig. 4
Method in some or all of step, specifically refer to the associated description in Fig. 2-Fig. 4, details are not described herein.Such as Fig. 5 institute
Show, which may include:
Module 501 is obtained, for acquiring the realtime graphic taken in camera shooting visual angle;
Processing module 502, for from the realtime graphic, being determined and auto model according to preset auto model
The vehicle characteristics area image matched;According to preset license plate model from the vehicle characteristics area image, determine and license plate
The vehicle license plate characteristic area image of Model Matching;The vehicle license plate characteristic area image is split, character picture is obtained;Based on depth
Degree neural network calculates the character picture, obtains license plate number.
As an alternative embodiment, the processing module 502 is being determined and the matched vehicle spy of auto model
After levying area image, it is also used to:
Type of vehicle analysis carried out to the vehicle characteristics area image based on type of vehicle sorter network, it is determining with it is described
The matched type of vehicle of vehicle characteristics area image.
As an alternative embodiment, the processing module 502 according to preset license plate model from the vehicle
In feature regional images, after determining the vehicle license plate characteristic area image with license plate Model Matching, it is also used to:
License plate type analysis, the determining and license plate are carried out to the vehicle license plate characteristic area image based on license plate sorter network
The matched license plate type of feature regional images.
As an alternative embodiment, the processing module 502 is being determined and the matched vehicle spy of auto model
After levying area image, it is also used to:
Color character analysis is carried out to the vehicle characteristics area image based on license plate sorter network, determines that the vehicle is special
Levy automotive colors feature corresponding to area image.
Wherein, it is described for detecting the device 50 of information of vehicles to implement Fig. 5, by according to preset auto model from
In the realtime graphic of acquisition, determine and the matched vehicle characteristics area image of auto model;According to preset license plate model from
In the vehicle characteristics area image, the vehicle license plate characteristic area image with license plate Model Matching is determined;To the vehicle license plate characteristic
Area image is split, and obtains character picture;The character picture is calculated based on deep neural network, and then is obtained
License plate number.As it can be seen that this mode can by it is comprehensive, really reflect the feature of vehicle that candid photograph is arrived so that its is preset
License plate model, the matching degree of preset auto model are higher, and then improve the recognition efficiency and recognition accuracy of information of vehicles.
It is described in the embodiment of the present application respectively from the angle of modular functionality entity above and is used to detect information of vehicles
Device, below from the angle of hardware handles introduce respectively in the embodiment of the present application for detecting the device of information of vehicles.
Fig. 6 is provided by the embodiments of the present application for detecting a kind of structural schematic diagram of the device of information of vehicles, wherein can
Including at least one processor, at least one transceiver, memory, at least one bus.Wherein, at least one processor, extremely
A few transceiver and memory can be connected by bus or other means, wherein in Fig. 6 for being connected by bus.
Memory may include read-only memory and random access memory, and provide instruction and data to processor.It deposits
The a part of of reservoir can also include nonvolatile RAM (full name in English: non-volatile random
Access memory, english abbreviation: NVRAM).Memory is stored with operating system and program instruction, executable module or number
According to structure perhaps their subset or their superset, wherein program instruction may include various operational orders, for real
Existing various operations.Operating system may include various system programs, hardware based for realizing various background tasks and processing
Task.
Processor can control the operation of the device for detecting information of vehicles, and processor can also be known as central processing list
First (full name in English: central processing unit, English abbreviation: CPU).In specific application, for detecting vehicle letter
The various components of the device of breath are coupled by bus, and wherein bus can also include electricity in addition to including data/address bus
Source bus, control bus and status signal bus in addition etc..But for the sake of clear explanation, various buses can all be claimed in Fig. 6
For bus.
It should be noted that the corresponding entity device of acquisition module in the application embodiment shown in fig. 5 can be
Transceiver, the corresponding entity device of processing module can be processor.Device shown in fig. 5 can have as shown in FIG. 6
Structure, when one of device has structure as shown in FIG. 6, processor and transceiver in Fig. 6 realize that aforementioned correspondence should
The processing module and the same or similar function of transceiver module that the Installation practice of device provides, at the memory storage in Fig. 6
The program code that reason device needs to call when executing the method for above-mentioned detection information of vehicles.Wherein, which can also use reception
Device and transmitter replace, and can be same or different physical entity.When for identical physical entity, it may be collectively referred to as receiving and dispatching
Device, such as the transceiver can be radio frequency (full name in English: radio frequency, English abbreviation: RF) circuit.The storage
Device can integrate in the processor, can also be provided separately with the processor.
The method that above-mentioned each embodiment of the application discloses can be applied in processor shown in fig. 6, or as shown in Figure 6
Processor realize.For example, in some embodiments, the processor in Fig. 6 can be by calling the program of memory storage to refer to
It enables, the program code for needing to call when above-mentioned processing implement body executes the method for the detection information of vehicles in the embodiment of the present application.
For example, memory storage processor in Fig. 6 executes above-mentioned when terminal device has structure as shown in FIG. 6
The program code for needing to call when executing the method for detection information of vehicles by terminal device.Specifically, the processor energy in Fig. 6
The program code in memory is enough called to execute following operation:
The realtime graphic taken in camera shooting visual angle is acquired by transceiver;
According to preset auto model from the realtime graphic, determine and the matched vehicle characteristics region of auto model
Image;According to preset license plate model from the vehicle characteristics area image, determine and the license plate of license plate Model Matching spy
Levy area image;The vehicle license plate characteristic area image is split, character picture is obtained;Based on deep neural network to described
Character picture is calculated, and license plate number is obtained.
The above-mentioned integrated unit realized in the form of software function module, can store in a computer-readable storage
In medium.Wherein, which can store computer program, which is being executed by processor
When, it can be achieved that step in above-mentioned each embodiment of the method.Wherein, which includes computer program code, described
Computer program code can be source code form, object identification code form, executable file or certain intermediate forms etc..The meter
Calculation machine readable storage medium storing program for executing may include: can carry the computer program code any entity or device, recording medium,
USB flash disk, mobile hard disk, magnetic disk, CD, computer storage, read-only memory (ROM, Read-Only Memory), arbitrary access
Memory (RAM, Random-Access Memory), electric carrier signal, telecommunication signal and software distribution medium etc..It needs
Bright, the content that the computer readable storage medium includes can be according to making laws in jurisdiction and patent practice is wanted
It asks and carries out increase and decrease appropriate.
In the above-described embodiments, it all emphasizes particularly on different fields to the description of each embodiment, there is no the portion being described in detail in some embodiment
Point, reference can be made to the related descriptions of other embodiments.
In several embodiments provided herein, it should be understood that disclosed device, it can be by another way
It realizes.For example, the apparatus embodiments described above are merely exemplary, such as the division of the unit, it is only a kind of
Logical function partition, there may be another division manner in actual implementation, such as multiple units or components can combine or can
To be integrated into another system, or some features can be ignored or not executed.Another point, shown or discussed is mutual
Coupling, direct-coupling or communication connection can be through some interfaces, the indirect coupling or communication connection of device or unit,
It can be electrical or other forms.
The unit as illustrated by the separation member may or may not be physically separated, aobvious as unit
The component shown may or may not be physical unit, it can and it is in one place, or may be distributed over multiple
In network unit.It can select some or all of unit therein according to the actual needs to realize the mesh of this embodiment scheme
's.
It, can also be in addition, the functional units in various embodiments of the present invention may be integrated into one processing unit
It is that each unit physically exists alone, can also be integrated in one unit with two or more units.Above-mentioned integrated list
Member both can take the form of hardware realization, can also realize in the form of software functional units.
If the integrated unit is realized in the form of SFU software functional unit and sells or use as independent product
When, it can store in a computer-readable access to memory.Based on this understanding, technical solution of the present invention substantially or
Person says that all or part of the part that contributes to existing technology or the technical solution can body in the form of software products
Reveal and, which is stored in a memory, including some instructions are used so that a computer equipment
(can be personal computer, server or network equipment etc.) executes all or part of each embodiment the method for the present invention
Step.And memory above-mentioned includes: USB flash disk, read-only memory (ROM, Read-Only Memory), random access memory
The various media that can store program code such as (RAM, Random Access Memory), mobile hard disk, magnetic or disk.
Those of ordinary skill in the art will appreciate that all or part of the steps in the various methods of above-described embodiment is can
It is completed with instructing relevant hardware by program, which can store in a computer-readable memory, memory
May include: flash disk, read-only memory (English: Read-Only Memory, referred to as: ROM), random access device (English:
Random Access Memory, referred to as: RAM), disk or CD etc..
Above to it is disclosed by the embodiments of the present invention it is a kind of detect information of vehicles method, apparatus and storage medium carried out in detail
Thin to introduce, used herein a specific example illustrates the principle and implementation of the invention, and above embodiments are said
It is bright to be merely used to help understand method and its core concept of the invention;At the same time, for those skilled in the art, foundation
Thought of the invention, there will be changes in the specific implementation manner and application range, in conclusion the content of the present specification is not
It is interpreted as limitation of the present invention.
Claims (10)
1. a kind of method for detecting information of vehicles, which is characterized in that the method is applied to make an inspection tour vehicle or outpost or mobile cloud
Camera is carried on platform, the tour vehicle or the outpost or the mobile holder, which comprises
Acquire the realtime graphic taken in the camera shooting visual angle;
According to preset auto model from the realtime graphic, determine and the matched vehicle characteristics administrative division map of auto model
Picture;
According to preset license plate model from the vehicle characteristics area image, the vehicle license plate characteristic with license plate Model Matching is determined
Area image;
The vehicle license plate characteristic area image is split, character picture is obtained;
The character picture is calculated based on deep neural network, obtains license plate number.
2. the method according to claim 1, wherein described determine and the matched vehicle characteristics area of auto model
After area image, the method also includes:
Type of vehicle analysis, the determining and vehicle are carried out to the vehicle characteristics area image based on type of vehicle sorter network
The matched type of vehicle of feature regional images.
3. method according to claim 1 or 2, which is characterized in that it is described according to preset license plate model from the vehicle
In feature regional images, after determining the vehicle license plate characteristic area image with license plate Model Matching, the method also includes:
License plate type analysis, the determining and vehicle license plate characteristic are carried out to the vehicle license plate characteristic area image based on license plate sorter network
The matched license plate type of area image.
4. method according to claim 1 or 2, which is characterized in that described to determine and the matched vehicle spy of auto model
After levying area image, the method also includes:
Color character analysis is carried out to the vehicle characteristics area image based on license plate sorter network, determines the vehicle characteristics area
Automotive colors feature corresponding to area image.
5. a kind of for detecting the device of information of vehicles, which is characterized in that described device includes:
Module is obtained, for acquiring the realtime graphic taken in camera shooting visual angle;
Processing module, for from the realtime graphic, being determined according to preset auto model and the matched vehicle of auto model
Feature regional images;According to preset license plate model from the vehicle characteristics area image, determine and license plate model
The vehicle license plate characteristic area image matched;The vehicle license plate characteristic area image is split, character picture is obtained;Based on depth nerve
Network calculates the character picture, obtains license plate number.
6. device according to claim 5, which is characterized in that the processing module determine it is matched with auto model
After vehicle characteristics area image, it is also used to:
Type of vehicle analysis, the determining and vehicle are carried out to the vehicle characteristics area image based on type of vehicle sorter network
The matched type of vehicle of feature regional images.
7. device according to claim 5 or 6, which is characterized in that the processing module is according to preset license plate model
From the vehicle characteristics area image, after determining the vehicle license plate characteristic area image with license plate Model Matching, it is also used to:
License plate type analysis, the determining and vehicle license plate characteristic are carried out to the vehicle license plate characteristic area image based on license plate sorter network
The matched license plate type of area image.
8. device according to claim 5 or 6, which is characterized in that the processing module is being determined and auto model
After the vehicle characteristics area image matched, it is also used to:
Color character analysis is carried out to the vehicle characteristics area image based on license plate sorter network, determines the vehicle characteristics area
Automotive colors feature corresponding to area image.
9. a kind of for detecting the device of information of vehicles, which is characterized in that described device includes:
At least one processor, memory and transceiver;
Wherein, the memory is used to control the transmitting-receiving operation of the transceiver for storing program code, the processor, with
And it executes for calling the program code in the memory such as the described in any item methods of Claims 1-4.
10. a kind of computer readable storage medium, which is characterized in that it includes instruction, when run on a computer, so that
Computer executes the method as described in claim 1-4 is any.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811512123.8A CN109657590A (en) | 2018-12-11 | 2018-12-11 | A kind of method, apparatus and storage medium detecting information of vehicles |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811512123.8A CN109657590A (en) | 2018-12-11 | 2018-12-11 | A kind of method, apparatus and storage medium detecting information of vehicles |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109657590A true CN109657590A (en) | 2019-04-19 |
Family
ID=66112959
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811512123.8A Pending CN109657590A (en) | 2018-12-11 | 2018-12-11 | A kind of method, apparatus and storage medium detecting information of vehicles |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109657590A (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111126336A (en) * | 2019-12-31 | 2020-05-08 | 潍柴动力股份有限公司 | Sample collection method, device and equipment |
CN111126271A (en) * | 2019-12-24 | 2020-05-08 | 高新兴科技集团股份有限公司 | Bayonet snap-shot image vehicle detection method, computer storage medium and electronic device |
CN111311696A (en) * | 2020-02-12 | 2020-06-19 | 大连海事大学 | License plate authenticity detection method based on hyperspectral unmixing technology |
CN111353444A (en) * | 2020-03-04 | 2020-06-30 | 上海眼控科技股份有限公司 | Marker lamp monitoring method and device, computer equipment and storage medium |
CN112560551A (en) * | 2019-09-25 | 2021-03-26 | 西门子(中国)有限公司 | System, method and device for license plate recognition |
JPWO2021166097A1 (en) * | 2020-02-19 | 2021-08-26 |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101398894A (en) * | 2008-06-17 | 2009-04-01 | 浙江师范大学 | Automobile license plate automatic recognition method and implementing device thereof |
CN102043945A (en) * | 2010-11-23 | 2011-05-04 | 聊城大学 | License plate character recognition method based on real-time vehicle tracking and binary index classification |
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 |
CN103871079A (en) * | 2014-03-18 | 2014-06-18 | 南京金智视讯技术有限公司 | Vehicle tracking method based on machine learning and optical flow |
CN104063712A (en) * | 2014-06-27 | 2014-09-24 | 杭州科度科技有限公司 | Vehicle information extraction method and system thereof |
CN106446895A (en) * | 2016-10-28 | 2017-02-22 | 安徽四创电子股份有限公司 | License plate recognition method based on deep convolutional neural network |
CN107729801A (en) * | 2017-07-11 | 2018-02-23 | 银江股份有限公司 | A kind of vehicle color identifying system based on multitask depth convolutional neural networks |
-
2018
- 2018-12-11 CN CN201811512123.8A patent/CN109657590A/en active Pending
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101398894A (en) * | 2008-06-17 | 2009-04-01 | 浙江师范大学 | Automobile license plate automatic recognition method and implementing device thereof |
CN102043945A (en) * | 2010-11-23 | 2011-05-04 | 聊城大学 | License plate character recognition method based on real-time vehicle tracking and binary index classification |
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 |
CN103871079A (en) * | 2014-03-18 | 2014-06-18 | 南京金智视讯技术有限公司 | Vehicle tracking method based on machine learning and optical flow |
CN104063712A (en) * | 2014-06-27 | 2014-09-24 | 杭州科度科技有限公司 | Vehicle information extraction method and system thereof |
CN106446895A (en) * | 2016-10-28 | 2017-02-22 | 安徽四创电子股份有限公司 | License plate recognition method based on deep convolutional neural network |
CN107729801A (en) * | 2017-07-11 | 2018-02-23 | 银江股份有限公司 | A kind of vehicle color identifying system based on multitask depth convolutional neural networks |
Non-Patent Citations (2)
Title |
---|
王海姣 等: "基于边缘颜色聚类和神经网络的车牌类型识别", 《计算机工程与应用》 * |
陈相勤: "车牌识别技术在校园测速及门及收费系统中的应用", 《江苏科技信息》 * |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112560551A (en) * | 2019-09-25 | 2021-03-26 | 西门子(中国)有限公司 | System, method and device for license plate recognition |
CN111126271A (en) * | 2019-12-24 | 2020-05-08 | 高新兴科技集团股份有限公司 | Bayonet snap-shot image vehicle detection method, computer storage medium and electronic device |
CN111126271B (en) * | 2019-12-24 | 2023-08-29 | 高新兴科技集团股份有限公司 | Bayonet snap image vehicle detection method, computer storage medium and electronic equipment |
CN111126336A (en) * | 2019-12-31 | 2020-05-08 | 潍柴动力股份有限公司 | Sample collection method, device and equipment |
CN111126336B (en) * | 2019-12-31 | 2023-07-21 | 潍柴动力股份有限公司 | Sample collection method, device and equipment |
CN111311696A (en) * | 2020-02-12 | 2020-06-19 | 大连海事大学 | License plate authenticity detection method based on hyperspectral unmixing technology |
CN111311696B (en) * | 2020-02-12 | 2023-07-25 | 大连海事大学 | License plate authenticity detection method based on hyperspectral unmixing technology |
JPWO2021166097A1 (en) * | 2020-02-19 | 2021-08-26 | ||
JP7505542B2 (en) | 2020-02-19 | 2024-06-25 | 日本電気株式会社 | Image Processing Device |
CN111353444A (en) * | 2020-03-04 | 2020-06-30 | 上海眼控科技股份有限公司 | Marker lamp monitoring method and device, computer equipment and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109657590A (en) | A kind of method, apparatus and storage medium detecting information of vehicles | |
Baran et al. | A smart camera for the surveillance of vehicles in intelligent transportation systems | |
CN110738150B (en) | Camera linkage snapshot method and device and computer storage medium | |
CN103400500B (en) | Vehicle information data acquisition device and method | |
CN106127107A (en) | The model recognizing method that multi-channel video information based on license board information and vehicle's contour merges | |
CN109255959A (en) | A kind of vehicle supervision method and system | |
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 | |
CN108133599A (en) | A kind of slag-soil truck video frequency identifying method and system | |
CN107301779A (en) | A kind of identity identifying method and detection device | |
CN111523352A (en) | Method for intelligently and rapidly identifying illegal modified vehicle and monitoring system thereof | |
CN111368612A (en) | Overman detection system, personnel detection method and electronic equipment | |
CN110310378A (en) | A kind of open type parking ground parking charge method and system based on double mirror | |
CN109448147A (en) | A kind of unlicensed vehicle parking charging method and parking charge system | |
CN114170565A (en) | Image comparison method and device based on unmanned aerial vehicle aerial photography and terminal equipment | |
CN111985304A (en) | Patrol alarm method, system, terminal equipment and storage medium | |
CN111931644A (en) | Method, system and equipment for detecting number of people on vehicle and readable storage medium | |
US8164426B1 (en) | System and method for producing and distributing digital images including data identifying subjects being photographed | |
CN113945219A (en) | Dynamic map generation method, system, readable storage medium and terminal equipment | |
Hsieh et al. | A real-time mobile vehicle license plate detection and recognition for vehicle monitoring and management | |
CN113129581A (en) | Vehicle information transmission system and method, storage medium, and electronic device | |
CN111241918A (en) | Vehicle anti-tracking method and system based on face recognition | |
CN113496597B (en) | Overspeed snapshot method, system and storage medium based on laser speed measurement | |
CN116453205A (en) | Method, device and system for identifying stay behavior of commercial vehicle | |
CN107886581A (en) | A kind of safe and reliable Roadside Parking electronic charging management system | |
CN111161542B (en) | Vehicle identification method and device |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190419 |