Summary of the invention
The first object of the present invention is to provide a kind of efficient vehicle identification method.
The second object of the present invention is to provide the computer installation for realizing above-mentioned vehicle identification method.
The third object of the present invention is to provide the computer readable storage medium for realizing above-mentioned vehicle identification method.
In order to realize that the first above-mentioned purpose, vehicle identification method provided by the invention include acquisition low definition video letter
Number, image recognition is carried out to low definition vision signal, is judged with the presence or absence of license plate image in low definition vision signal, such as
It is to acquire high definition video signal, image recognition is carried out to high definition video signal, is known from high definition video signal
Not Chu license plate number information.
By above scheme as it can be seen that this programme first passes through acquisition low definition vision signal, low definition vision signal is judged
In there are high definition video signal is just acquired after license plate image signal, license plate is then identified from high definition video signal
The information of number achievees the purpose that efficient identification goes out the information of license plate number letter.
Further embodiment is that acquisition low definition vision signal includes: that the clarity of photographic device is set as first
Clarity, acquisition high definition video signal includes: that the clarity of photographic device is set as the second clarity, the second clarity
Pixel be higher than the first clarity pixel.
As it can be seen that acquisition low definition vision signal and acquisition high definition video signal can be and filled by the same camera shooting
Acquisition is set, since this photographic device is set with the first clarity and the second clarity, so low definition video need to be acquired
When signal, then photographic device is set as the first clarity, when need to acquire high definition video signal, then set photographic device
For the second clarity, allow to easily acquire the vision signal of different clarity.
Further embodiment is, before acquiring high definition video signal, also executes: photographic device receives adjusting clarity and sets
The instruction of definite value, and the clarity of photographic device is set as the second clarity from the first clarity.
As it can be seen that the clarity of photographic device is reset before being acquired high definition video signal.
Further embodiment is that acquisition low definition vision signal includes: video acquired in the first photographic device of acquisition
Signal, acquisition high definition video signal include: vision signal acquired in the second photographic device of acquisition, wherein the second camera shooting
The clarity of device is higher than the clarity of the first photographic device.
As it can be seen that this programme can also be acquired the vision signal of different clarity by two photographic devices, reach fast
The purpose of speed acquisition low definition vision signal and high definition video signal.
Further embodiment is, before acquiring high definition video signal, also executes: the second photographic device receives starting and refers to
It enables.
As it can be seen that needing to send enabling signal to the second photographic device before acquisition high definition video signal.
Further embodiment is to carry out image recognition to high definition video signal, know from high definition video signal
Not Chu license plate number information, comprising: by the image in high definition video signal carry out cutting form multiple subgraphs, to every
One subgraph carries out character recognition respectively, and the character of multiple subgraph equipment is formed to the information of license plate number.
As it can be seen that multiple subgraphs are formed by carrying out cutting to the image in high definition video signal, to each Zhang Zi
Image carries out character recognition respectively, reaches the mesh of the information for the license plate number being recognized accurately in high definition clarity vision signal
's.
Further embodiment is, the image in high definition video signal be subjected to cutting form multiple subgraphs include:
Only the image of license plate area is cut, each subgraph after cutting includes at least one character.
As it can be seen that making each Zhang Zitu in multiple subgraphs formed after cutting to the mode of the image cutting of license plate area
As including at least a character, further reach the information for the license plate number being recognized accurately in high definition clarity vision signal
Purpose.
Further embodiment is to carry out image recognition to high definition video signal, know from high definition video signal
Not Chu the information of license plate number include obtaining three or more in high definition video signal images, respectively to multiple images into
Line character identification, the one group character most using the identical amount of images of character that identifies is as license plate number.
As it can be seen that carrying out word to multiple images respectively by will acquire three or more in high definition video signal images
Symbol identification, the one group character most using the identical amount of images of character that identifies further increase identification as license plate number
Accuracy rate.
In order to realize above-mentioned second purpose, the present invention also provides computer installation further include processor and memory,
Memory is stored with computer program, and each step of above-mentioned vehicle identification method is realized when computer program is executed by processor
Suddenly.
In order to realize above-mentioned third purpose, the present invention also provides computer readable storage medium on be stored with computer
Program, the computer program realize each step of above-mentioned vehicle identification method when being executed by processor.
Specific embodiment
The present invention provides a kind of vehicle identification method, and low definition vision signal and high definition video can acquired by applying
On the terminal device of signal, typically apply on the terminal devices such as computer.Computer installation of the invention can be above-mentioned
Electronic equipment, computer readable storage medium can be the various storage mediums with data storage function, as FLAASH,
The nonvolatile memories such as EEPROM.
Vehicle identification method first embodiment:
Preferred terminal device is the terminal devices such as desktop computer or server in the present embodiment, referring to Fig. 1, this method
Step S1 is first carried out, acquires low definition vision signal, image recognition is carried out to low definition vision signal.Wherein, it acquires
Low definition vision signal includes that the clarity of photographic device is set the first clarity of position.In this way, to photographic device setting the
Clarity vision signal is acquired after one clarity.
Preferably, the clarity of photographic device is set as second clearly when acquiring high definition video signal in this implementation
Degree, and the pixel of the second clarity is higher than the first clarity.
Then, step S2 is executed, judges low definition vision signal with the presence or absence of license plate image.If there are vehicles for low definition
Board image thens follow the steps S3, and photographic device receives the instruction for adjusting clarity definite value, and by the clarity of camera from first
Clarity is set as the second clarity.In this way, being acquired low definition by the way that photographic device is first set as the first clarity
Photographic device after identifying license plate image, then is set as the second clarity and is acquired high definition video letter by vision signal
Number, it is acquired high definition video signal relative to photographic device is directly set as the second clarity, the present embodiment reduces
Flow consumed by photographic device acquisition vision signal, increases recognition efficiency.And in the present embodiment, from low vision signal
Identify that license plate image can be used the mode of image difference method and identify license plate image in low vision signal.
Finally, executing step S4, high definition video signal is acquired, license plate number is identified from high definition video signal
The information of code.Wherein, identify that license plate number information includes from high definition video signal, it will be in high definition video signal
Image carry out cutting form multiple subgraphs, character recognition is carried out to each subgraph respectively, multiple subgraphs are identified
Character formed license plate number information.In such manner, it is possible to accurately get the information of license plate number.It, will and in the present embodiment
Image in high definition video signal carries out cutting and forms multiple subgraphs to include only cutting the image of license plate area,
Each subgraph after cutting includes at least one character, can to effectively being cut to the image of license plate area, and
And each subgraph after cutting is made to include at least one character.
Preferably, it during the character multiple subgraphs identified forms the information of license plate number, can be filled by identification
It sets such as OCR each subgraph after the image cutting of license plate area is carried out identifying word corresponding to each subgraph
Symbol, the character that then terminal device identifies multiple subgraphs form the information of license plate number.And the present embodiment is to fine definition
Vision signal carries out image recognition, identifies that the information of license plate number further includes from high definition video signal, obtains high definition
Three or more images in clear degree vision signal carry out character recognition to multiple images respectively, identical with the character identified
One group of most character of amount of images further improves the accurate of the information of the license plate number identified as license plate number
Property.
It can be seen that the present embodiment first pass through by the clarity of photographic device be set as the first clarity be acquired it is low clear
Clear degree vision signal after identifying license plate image, then sets the second gradient for the clarity of photographic device and is acquired height
Clarity vision signal finally identifies the information of license plate number from high definition video signal, reaches efficient identification and goes out vehicle
License plate number purpose.
Vehicle identification method second embodiment:
Preferred terminal device is the terminal devices such as desktop computer or server, referring to fig. 2, this method in the present embodiment
Step S11 is first carried out, acquires low definition vision signal, image recognition is carried out to low definition vision signal.Wherein, it acquires
Low definition vision signal includes vision signal acquired in the first photographic device of acquisition, and acquisition high definition video signal includes
Vision signal acquired in the second photographic device is acquired, and the clarity of the second photographic device is higher than the clear of the first photographic device
Degree.In this way, acquiring low definition vision signal by the first photographic device respectively, fine definition is acquired by the second photographic device
Vision signal achievees the purpose that the different clarity vision signals of convenient acquisition.
Then, step S12 is executed, judges low definition vision signal with the presence or absence of license plate image.If low definition exists
License plate image thens follow the steps S13, and the second photographic device receives enabled instruction.The present embodiment first passes through the acquisition of the first photographic device
Low definition vision signal after identifying license plate image, then gives the transmission enabled instruction of the second photographic device, passes through the second camera shooting and fill
Acquisition high-definition video information is set, finally identifies the information of license plate number.The present embodiment is taken the photograph relative to direct by second
As device acquisition high definition video information, video flow consumed by the second photographic device acquisition vision signal is reduced, is increased
Recognition efficiency.And in the present embodiment, identify that license plate image can be used the mode of image difference method and know from low vision signal
It Chu not license plate image in low vision signal.
Finally, executing step S14, high definition video signal is acquired, license plate is identified from high definition video signal
The information of number.Wherein, identify that license plate number information includes from high definition video signal, by high definition video signal
In image carry out cutting form multiple subgraphs, character recognition is carried out to each subgraph respectively, multiple subgraphs are known
Other character forms the information of license plate number.In such manner, it is possible to accurately get the information of license plate number.And in the present embodiment,
Image in high definition video signal is carried out cutting to form multiple subgraphs including only cutting the image of license plate area
Cut, each subgraph after cutting includes at least one character, can to effectively being cut to the image of license plate area,
And making each subgraph after cutting includes at least one character.
Preferably, it during the character multiple subgraphs identified forms the information of license plate number, can be filled by identification
It sets such as OCR each subgraph after the image cutting of license plate area is carried out identifying word corresponding to each subgraph
Symbol, the character that then terminal device identifies multiple subgraphs form the information of license plate number.And the present embodiment is to fine definition
Vision signal carries out image recognition, identifies that the information of license plate number further includes from high definition video signal, obtains high definition
Three or more images in clear degree vision signal carry out character recognition to multiple images respectively, identical with the character identified
One group of most character of amount of images further improves the accurate of the information of the license plate number identified as license plate number
Property.
It can be seen that the present embodiment first passes through the first photographic device acquisition low definition vision signal, license plate figure is identified
High definition video signal is acquired as after, then through the second photographic device, license plate number is identified from high definition video signal
The information of code reaches the purpose of the license plate number of efficient identification vehicle.
Computer installation embodiment:
The computer installation of the present embodiment include processor, memory and storage in memory and can be in processor
The computer program of upper operation, such as the computer processing for realizing above- mentioned information processing method.Processor executes meter
Each step of above-mentioned vehicle identification method is realized when calculation machine program.
For example, computer program can be divided into one or more modules, one or more module, which is stored in, is deposited
It in reservoir, and is executed by processor, to complete modules of the invention.One or more modules can be can complete it is specific
The series of computation machine program instruction section of function, the instruction segment is for describing execution of the computer program in terminal device
Journey.
It should be noted that terminal device can be desktop PC, notebook, palm PC and cloud server etc.
Calculate equipment.Terminal device may include, but be not limited only to, processor, memory.It will be understood by those skilled in the art that this hair
Bright schematic diagram is only the example of terminal device, does not constitute the restriction to terminal device, may include than illustrate it is more or
Less component perhaps combines certain components or different components, such as terminal device can also be set including input and output
Standby, network access equipment, bus etc..
Processor alleged by the present invention can be central processing unit (Central Processing Unit, CPU), may be used also
To be other general processors, digital signal processor (Digital Signal Processor, DSP), specific integrated circuit
(Application Specific Integrated Circuit, ASIC), ready-made programmable gate array (Field-
Programmable Gate Array, FPGA) either other programmable logic device, discrete gate or transistor logic,
Discrete hardware components etc..General processor can be microprocessor or the processor is also possible to any conventional processor
Deng processor is the control centre of terminal device, utilizes the various pieces of various interfaces and the entire terminal device of connection.
Memory can be used for storing computer program and/or module, and processor is stored in memory by operation or execution
Interior computer program and/or module, and the data being stored in memory are called, realize the various functions of terminal device.
Memory can mainly include storing program area and storage data area, wherein storing program area can storage program area, at least one
Application program needed for function (such as sound-playing function, image player function etc.) etc.;Storage data area can be stored according to hand
Machine uses created data (such as audio data, phone directory etc.) etc..In addition, memory may include high random access
Memory can also include nonvolatile memory, such as hard disk, memory, plug-in type hard disk, intelligent memory card (Smart
Media Card, SMC), secure digital (Secure Digital, SD) card, flash card (Flash Card), at least one disk
Memory device, flush memory device or other volatile solid-state parts.
Computer readable storage medium:
If the integrated module of terminal device be realized in the form of SFU software functional unit and as the sale of independent product or
In use, can store in a computer readable storage medium.Based on this understanding, the present invention realizes above-mentioned implementation
All or part of the process in example method, can also instruct relevant hardware to complete, the computer by computer program
Program can be stored in computer readable storage medium, and the computer program is when being executed by processor, it can be achieved that above-mentioned vehicle
Each step of recognition methods.
Wherein, computer program includes computer program code, and computer program code can be source code form, object
Code form, executable file or certain intermediate forms etc..Computer-readable medium may include: that can carry computer program
Any entity or device of code, recording medium, USB flash disk, mobile hard disk, magnetic disk, CD, computer storage, read-only memory
(ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, electricity
Believe signal and software distribution medium etc..It should be noted that the content that computer-readable medium includes can be managed according to the administration of justice
Local legislation and the requirement of patent practice carry out increase and decrease appropriate, such as in certain jurisdictions, according to legislation and patent
Practice, computer-readable medium does not include electric carrier signal and telecommunication signal.
It should be noted that the above is only a preferred embodiment of the present invention, but the design concept invented is not limited thereto,
All insubstantial modifications made using this design to the present invention, are also entered within protection scope of the present invention.