CN109344829A - A kind of Train number recognition method and device of High Speed Railway Trains - Google Patents
A kind of Train number recognition method and device of High Speed Railway Trains Download PDFInfo
- Publication number
- CN109344829A CN109344829A CN201810813119.9A CN201810813119A CN109344829A CN 109344829 A CN109344829 A CN 109344829A CN 201810813119 A CN201810813119 A CN 201810813119A CN 109344829 A CN109344829 A CN 109344829A
- Authority
- CN
- China
- Prior art keywords
- high speed
- speed railway
- railway trains
- target
- character
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 62
- 230000005236 sound signal Effects 0.000 claims description 42
- 230000004044 response Effects 0.000 claims description 36
- 238000004422 calculation algorithm Methods 0.000 claims description 22
- 238000001514 detection method Methods 0.000 claims description 21
- 230000007613 environmental effect Effects 0.000 claims description 16
- 230000011218 segmentation Effects 0.000 claims description 9
- XEEYBQQBJWHFJM-UHFFFAOYSA-N Iron Chemical compound [Fe] XEEYBQQBJWHFJM-UHFFFAOYSA-N 0.000 claims description 8
- 238000001914 filtration Methods 0.000 claims description 8
- 238000003384 imaging method Methods 0.000 claims description 8
- 238000001303 quality assessment method Methods 0.000 claims description 7
- 230000002708 enhancing effect Effects 0.000 claims description 6
- 238000009499 grossing Methods 0.000 claims description 6
- 229910052742 iron Inorganic materials 0.000 claims description 4
- 230000008447 perception Effects 0.000 claims description 2
- 238000013441 quality evaluation Methods 0.000 claims 1
- 230000015654 memory Effects 0.000 description 18
- 230000008569 process Effects 0.000 description 11
- 238000010586 diagram Methods 0.000 description 8
- 238000004590 computer program Methods 0.000 description 7
- 230000001276 controlling effect Effects 0.000 description 7
- 238000012163 sequencing technique Methods 0.000 description 4
- 238000012706 support-vector machine Methods 0.000 description 4
- 238000010191 image analysis Methods 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 239000000047 product Substances 0.000 description 3
- 238000012795 verification Methods 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 238000013459 approach Methods 0.000 description 2
- 230000015572 biosynthetic process Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000005286 illumination Methods 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 239000002245 particle Substances 0.000 description 2
- 210000003296 saliva Anatomy 0.000 description 2
- 239000013589 supplement Substances 0.000 description 2
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 1
- 230000004888 barrier function Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 229910052799 carbon Inorganic materials 0.000 description 1
- 230000010485 coping Effects 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
Classifications
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/22—Image preprocessing by selection of a specific region containing or referencing a pattern; Locating or processing of specific regions to guide the detection or recognition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
- G06V10/267—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion by performing operations on regions, e.g. growing, shrinking or watersheds
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Data Mining & Analysis (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Image Analysis (AREA)
- Train Traffic Observation, Control, And Security (AREA)
Abstract
The invention discloses a kind of Train number recognition method and devices of High Speed Railway Trains, this method comprises: control filming apparatus executes shooting operation to High Speed Railway Trains, obtain the target image for High Speed Railway Trains；It identifies at least one target area in the target image there are character content, and identifies the character content in each target area；Judge whether the combination of the character content of all target areas meets preset characters logic, which includes at least license number corresponding to different automobile types and identify included character quantity；When the combination of the character content of all target areas meets preset characters logic, the license number that the combination of the character content of all target areas is determined as High Speed Railway Trains is identified.As it can be seen that target image can be identified by implementing the embodiment of the present invention, character content is obtained, and verify to obtained character content, can fast and accurately identify the license number mark of High Speed Railway Trains in this way.
Description
Technical field
The present invention relates to Train number recognition technical fields, and in particular to a kind of the Train number recognition method and dress of High Speed Railway Trains
It sets.
Background technique
Parking lot fee collection management, the measurement of magnitude of traffic flow Con trolling index, vehicle location, automobile burglar, high way super speed are certainly
The realization of the functions such as dynamicization supervision, electronic eye used for catching red light runner, toll station all relies on Train number recognition technology.However, current
Train number recognition technology fixed both for license plate installation site and the automobile of the character standard in license number, car and truck wait vehicles
Type, it is not suitable for High Speed Railway Trains.For High Speed Railway Trains, identification High Speed Railway Trains license number identifies main
Mode is to read the electronic tag being arranged on High Speed Railway Trains, and practice discovery, High Speed Railway Trains are in the process of running at high speed
In be easy to appear the corrupted or lost situation of electronic tag, this leads to not fast and accurately identify High Speed Railway Trains
License number mark.
Summary of the invention
The embodiment of the invention discloses a kind of Train number recognition method and devices of High Speed Railway Trains, can quickly, accurately
Identify High Speed Railway Trains license number mark.
First aspect of the embodiment of the present invention discloses a kind of Train number recognition method of High Speed Railway Trains, the method packet
It includes:
It controls filming apparatus and shooting operation is executed to the High Speed Railway Trains, obtain the target of the High Speed Railway Trains
Image；
It identifies at least one target area in the target image there are character content, and identifies each target area
Character content in domain；
Judge whether the combination of the character content of all target areas meets preset characters logic, the preset characters
Logic includes at least license number corresponding to the vehicle of the High Speed Railway Trains and identifies included character quantity；
When the combination of the character content of all target areas meets the preset characters logic, by all mesh
The combination for marking the character content in region is determined as the license number mark of the High Speed Railway Trains.
As a kind of optional embodiment, in first aspect of the embodiment of the present invention, the control filming apparatus is to described
High Speed Railway Trains execute shooting operation, obtain the target image of the High Speed Railway Trains, comprising:
Perceive the environmental parameter of filming apparatus local environment；
Using the environmental parameter perceived as foundation, the shooting is adjusted by preset imaging quality assessment algorithm and is filled
The acquisition parameters set；
The filming apparatus is controlled with the acquisition parameters to execute shooting operation according to the High Speed Railway Trains, is obtained
To the target image of the High Speed Railway Trains.
As a kind of optional embodiment, in first aspect of the embodiment of the present invention, the method also includes:
Acquisition image corresponding with the High Speed Railway Trains is collected into the license number mark in the High Speed Railway Trains
Under knowledge, the image recording of the High Speed Railway Trains is formed, described image record includes at least license number mark, the high speed
The pantograph panoramic picture of railroad train and the slide plate image of the High Speed Railway Trains；
And there are before at least one target area of character content in the identification target image, the side
Method further include:
It is detected in the target image by preset detection algorithm with the presence or absence of text filed；
When detect in the target image there are it is described text filed when, execute in the identification target image
There are at least one target areas of character content；
Wherein, described text filed including the target area.
As a kind of optional embodiment, in first aspect of the embodiment of the present invention, in detecting the target image
There are it is described it is text filed after, the method also includes:
Pretreatment operation is executed to the target image, and triggers and executes in the identification target image that there are words
Accord at least one target area of content；
Wherein, the pretreatment operation include smoothing filtering operation, enhance contrast operation and the operation that highlights in
At least one；
And there are at least one target areas of character content in the identification target image, and identify each
Character content in the target area, comprising:
It identifies the license number identified areas in the target image, and Character segmentation is carried out to the license number identified areas, obtain
To there are at least one of character content target areas；
Each target area is identified by classifier, obtains the character content of each target area.
As a kind of optional embodiment, in first aspect of the embodiment of the present invention, the control filming apparatus is to described
High Speed Railway Trains execute shooting operation, before obtaining the target image of the High Speed Railway Trains, the method also includes:
It controls audio signal emitter and emits the audio signal of the first predeterminated frequency, and judge audio signal reception device
Whether connect in the preset time period after the audio signal that the audio signal emitter emits first predeterminated frequency
Receive response signal；
When judging to receive the response signal, judge whether the frequency of the response signal is the second predeterminated frequency
And whether the response signal carries the signal identification of the audio signal of first predeterminated frequency；
When the frequency for judging the response signal is that second predeterminated frequency and the response signal carry
When stating the signal identification of the audio signal of the first predeterminated frequency, triggering executes the control filming apparatus to the high-speed railway
Train executes shooting operation, obtains the target image of the High Speed Railway Trains.
Second aspect of the embodiment of the present invention discloses a kind of number identification device of High Speed Railway Trains, described device packet
It includes:
First control unit executes shooting operation to the High Speed Railway Trains for controlling filming apparatus, obtains described
The target image of High Speed Railway Trains；
Recognition unit, there are at least one target areas of character content in the target image for identification, and identify
Character content in each target area；
Judging unit is patrolled for judging whether the combination of character content of all target areas meets preset characters
Volume, the preset characters logic includes at least license number corresponding to the vehicle of the High Speed Railway Trains and identifies included character
Quantity；
Determination unit, for judging that the combination of character content of all target areas meets when the judging unit
When the preset characters logic, the combination of the character content of all target areas is determined as the High Speed Railway Trains
License number mark.
As a kind of optional embodiment, in second aspect of the embodiment of the present invention, the first control unit includes:
Subelement is perceived, for perceiving the environmental parameter of filming apparatus local environment；
Subelement is adjusted, the environmental parameter for perceiving using the perception subelement is foundation, by preset
Imaging quality assessment algorithm adjusts the acquisition parameters of the filming apparatus；
Subelement is controlled, for controlling the filming apparatus with the acquisition parameters as according to the High Speed Railway Trains
Shooting operation is executed, the target image of the High Speed Railway Trains is obtained.
As a kind of optional embodiment, in second aspect of the embodiment of the present invention, described device further include:
Unit is collected, for collecting acquisition image corresponding with the High Speed Railway Trains in the High Speed Railway Trains
License number mark under, form the image recording of the High Speed Railway Trains, described image record includes at least the license number
The slide plate image of mark, the pantograph panoramic picture of the High Speed Railway Trains and the High Speed Railway Trains；
Described device further include:
Detection unit works as inspection for detecting in the target image by preset detection algorithm with the presence or absence of text filed
Measure in the target image there are it is described text filed when, trigger the recognition unit and execute the identification target figure
There are at least one target areas of character content as in；
Wherein, described text filed including the target area.
As a kind of optional embodiment, in second aspect of the embodiment of the present invention, described device further include:
Pretreatment unit, for the detection unit detect in the target image there are it is described it is text filed it
Afterwards, pretreatment operation is executed to the target image；Wherein, the pretreatment operation includes smoothing filtering operation, enhancing comparison
Degree operation and at least one of the operation that highlights；
The recognition unit, specifically for detecting that there are the text areas in the target image when the detection unit
When domain and after the pretreatment unit is to target image execution pretreatment operation, identifies and exist in the target image
At least one target area of character content, and identify the character content in each target area；
And the recognition unit identifies at least one target area in the target image there are character content, and
Identify the mode of the character content in each target area specifically:
It identifies the license number identified areas in the target image, and Character segmentation is carried out to the license number identified areas, obtain
To there are at least one of character content target areas；
Each target area is identified by classifier, obtains the character content of each target area.
As a kind of optional embodiment, in second aspect of the embodiment of the present invention, described device further include:
Second control unit emits the audio signal of the first predeterminated frequency for controlling audio signal emitter；
The judging unit, be also used to judge audio signal reception device the audio signal emitter transmitting described in
Whether response signal is received in preset time period after the audio signal of first predeterminated frequency, believed when receiving the response
Number, judge whether the frequency of the response signal is whether the second predeterminated frequency and the response signal carry described first
The signal identification of the audio signal of predeterminated frequency, when judge the response signal frequency be second predeterminated frequency and
When the response signal carries the signal identification of the audio signal of first predeterminated frequency, the first control unit is triggered
It executes the control filming apparatus and shooting operation is executed to the High Speed Railway Trains, obtain the mesh of the High Speed Railway Trains
Logo image.
The third aspect of the embodiment of the present invention discloses a kind of number identification device of High Speed Railway Trains, described device device packet
It includes:
It is stored with the memory of executable program code；
The processor coupled with the memory；
The processor calls the executable program code stored in the memory, executes the embodiment of the present invention the
Step in the Train number recognition method of High Speed Railway Trains disclosed in one side.
Fourth aspect of the embodiment of the present invention discloses a kind of computer readable storage medium, stores computer program,
In, the license number that the computer program makes computer execute High Speed Railway Trains disclosed in first aspect of the embodiment of the present invention is known
Other method.
The 5th aspect of the embodiment of the present invention discloses a kind of computer program product, when the computer program product is being counted
When being run on calculation machine, so that the computer executes the Train number recognition method of High Speed Railway Trains disclosed in first aspect.
Compared with prior art, the embodiment of the present invention has the advantages that
In the embodiment of the present invention, control filming apparatus executes shooting operation to High Speed Railway Trains, obtains for high-speed iron
The target image of road train；It identifies at least one target area in the target image there are character content, and identifies each mesh
Mark the character content in region；Judge whether the combination of the character content of all target areas meets preset characters logic, this is pre-
If character logic includes at least license number corresponding to the vehicle of High Speed Railway Trains and identifies included character quantity；When all mesh
When the combination of the character content in mark region meets preset characters logic, the combination of the character content of all target areas is determined as
The license number of High Speed Railway Trains identifies.It is obtained as it can be seen that implementing the embodiment of the present invention and can shoot High Speed Railway Trains to filming apparatus
To target image identified, obtain character content, and can carry out by preset characters logic to obtained character content
Verification can fast and accurately identify the license number mark of High Speed Railway Trains in this way.
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 flow diagram of the Train number recognition method of High Speed Railway Trains disclosed by the embodiments of the present invention；
Fig. 2 is the flow diagram of the Train number recognition method of another High Speed Railway Trains disclosed by the embodiments of the present invention；
Fig. 3 is a kind of structural schematic diagram of the number identification device of High Speed Railway Trains disclosed by the embodiments of the present invention；
Fig. 4 is the structural schematic diagram of the number identification device of another High Speed Railway Trains disclosed by the embodiments of the present invention；
Fig. 5 is the structural schematic diagram of the number identification device of another High Speed Railway Trains disclosed by the embodiments of the present invention.
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 the term " includes " of the embodiment of the present invention and " having " and their any deformation, it is intended that
Be to cover it is non-exclusive include, for example, containing the process, method, system, product or equipment of a series of steps or units not
Those of be necessarily limited to be clearly listed step or unit, but may include be not clearly listed or for these processes, side
The intrinsic other step or units of method, product or equipment.
The embodiment of the invention discloses a kind of Train number recognition method and devices of High Speed Railway Trains, can be to filming apparatus
The target image that shooting High Speed Railway Trains obtain is identified, obtains character content, and can pass through preset characters logic pair
Obtained character content is verified, and can fast and accurately identify the license number mark of High Speed Railway Trains in this way.Divide below
It is not described in detail.
Embodiment one
Referring to Fig. 1, Fig. 1 is a kind of process of the Train number recognition method of High Speed Railway Trains disclosed by the embodiments of the present invention
Schematic diagram.Wherein, method described in Fig. 1 can be applied in the management system of High Speed Railway Trains.As shown in Figure 1, the height
The Train number recognition method of fast railroad train may include following operation:
101, control filming apparatus executes shooting operation to High Speed Railway Trains, obtains the target figure of High Speed Railway Trains
Picture.
In the embodiment of the present invention, specifically, after control filming apparatus is continuously shot operation to High Speed Railway Trains execution,
Available multiple images for High Speed Railway Trains, also available one section of video for High Speed Railway Trains, and mention
The image in the video is taken to obtain multiple images.Wherein, any one in multiple images which can be
Image.Preferably, which can be the image in middle position, i.e., according to the sequencing of shooting time to obtained institute
There is image to be ranked up, and shooting time a certain image in an intermediate position is determined as target image.Be conducive in this way
Improve the reliability that character content is identified from target image.
As an example it is assumed that obtaining 10 after control filming apparatus is continuously shot operation to High Speed Railway Trains execution
Image is ranked up 10 images according to the sequencing of shooting time, obtains the 1st the-the 10 image of image, wherein N
Earlier than N+1 image, N is more than or equal to 1 and less than or equal to 9 the shooting time of image, then can be true by the 5th image or the 6th image
It is set to the target image of High Speed Railway Trains.
In an alternative embodiment, control filming apparatus executes shooting operation to High Speed Railway Trains, obtains high speed
The target image of railroad train may include:
Perceive the environmental parameter of filming apparatus local environment；
Using the environmental parameter perceived as foundation, the shooting of filming apparatus is adjusted by preset imaging quality assessment algorithm
Parameter；
It is to execute shooting operation according to High Speed Railway Trains that filming apparatus, which is controlled, with acquisition parameters, obtains high-speed railway column
The target image of vehicle.
In the optional embodiment, specifically, after the environmental parameter for perceiving filming apparatus current environment, it can
To be taken pictures by the environmental parameter of preset imaging quality assessment algorithm evaluation current environment and the current of filming apparatus
Influence of the parameter to filming apparatus image quality, and according to the acquisition parameters of assessment result adjustment filming apparatus, to guarantee to shoot
The quality for the image that device is shot under the different illumination conditions of different periods (round-the-clock), and then be conducive to improve license number
The accuracy of identification.
102, it identifies that there are at least one target areas of character content in above-mentioned target image, and identifies each target area
Character content in domain.
In the embodiment of the present invention, as an alternative embodiment, identifying that there are character contents in above-mentioned target image
At least one target area, and identify the character content in each target area, may include:
License number identified areas in recognition target image, and Character segmentation is carried out to license number identified areas, obtain that there are words
Accord at least one target area of content；
Each target area is identified by classifier, obtains the character content of each target area.
In the optional embodiment, the license number identified areas identified is possible be comprising the region of license number mark.
Wherein, the license number identified areas in recognition target image, and Character segmentation is carried out to license number identified areas, it is deposited
In at least one target area of character content, may include:
Pass through very big stable extremal region algorithm (MSER), using general character dimensional parameters as foundation, detecting target image
Extremal region；
Character extremal region is filtered out from the extremal region detected by the physical parameter of character, wherein character
Physical parameter may include the length and width of character, Aspect Ratio etc.；
By morphology closed operation, the adjacent character extremal region just sifted out is linked to be candidate characters region, as knowledge
Not Chu possibility include license number mark region (i.e. license number identified areas)；
Forecasting recognition is carried out to the character in each candidate characters region, and is scored recognition result, is scored
Value, and score value is met into the highest candidate characters region of score value in all score values of default scoring threshold condition and is determined
For final character zone；
Binaryzation is carried out to final character zone by big saliva (OTSU) algorithm, it is (large scale, general by three classes character size
Logical size and small size) extremal region in the final character zone of parameter detection, obtain that there are at least one of character content
Target area.
Further, it identifies the character content in each target area, may include:
Final character zone is split by connected region domain method, obtains cut zone；
Cut zone and target area are carried out and operated, to screen suspicious character；
Identification prediction is carried out to the suspicious character filtered out using license number Character prediction classifier, analyzes suspicious character position
With size characteristic, and combine Character prediction as a result, suspicious character is ranked up, supplement omission character, obtain each target area
The character content in domain, as the license number mark tentatively identified, wherein omitting character is identified in the target area of target image
The unknown character not gone out, can be replaced by spcial character (such as *).
Wherein, the generating process of license number Character prediction classifier may include:
It determines the character sample being truncated to, character sample is zoomed into identical resolution ratio (such as 20*20)；
Histograms of oriented gradients (Histogram of Oriented Gradient, HOG) feature of calculating character sample,
The HOG feature of character sample and sample character input are trained to support vector machines (SVM) classifier, obtain above-mentioned license number
Character prediction classifier.
103, judge whether the combination of the character content of all target areas meets preset characters logic, which patrols
It collects license number corresponding to the vehicle including at least High Speed Railway Trains and identifies included character quantity.
In the embodiment of the present invention, when the judging result of step 103, which is, is, triggering executes step 104；When step 103
When judging result is no, following operation can be executed:
It obtains filming apparatus and the obtained next image of shooting operation is executed to High Speed Railway Trains, as target image,
And retriggered executes step 102-103.
Can also include following operation before executing step 103 in the embodiment of the present invention:
Determine preset characters logic.
Optionally, determine that preset characters logic may include:
Determine geographical location locating for filming apparatus, shooting direction and the period for executing above-mentioned shooting operation, according to
The geographical location, executes the period of above-mentioned shooting operation and the train of the geographical location got at shooting direction
Running time table determines the essential information of above-mentioned High Speed Railway Trains, which can include at least above-mentioned high-speed railway and arrange
Origin, approach station and the destination of vehicle；
Preset characters logic corresponding with above-mentioned High Speed Railway Trains is determined according to the essential information.It can be improved so really
The matching degree for the above-mentioned High Speed Railway Trains of preset characters logical AND made.
In the embodiment of the present invention, optionally, which can also include that the vehicle institute of High Speed Railway Trains is right
Character types included in the license number mark answered, character position and kinds of characters type institute corresponding to kinds of characters type
Corresponding character quantity.It can be further improved the accuracy of the license number mark identified in this way.Wherein, which can be with
It also may include letter type and numeric type including Chinese character type, letter type and numeric type.For example, for
For the High Speed Railway Trains of a certain vehicle, corresponding license number mark should include a use according to the sequencing of character position
In indicating that the character mark (" Zheng " of such as Zhengzhou Railway Administration) of the affiliated Railway Bureau of the High Speed Railway Trains, one for indicating train
The other letter mark (vehicle of such as motor-car is not identified as " D ") of vehicle and four codings it is digital, such as Zheng D1314.
In the embodiment of the present invention, the combined method of determination of the character content of all target areas specifically:
According to preset characters logic (for such as prefix with letter ending, suffix be that coding is digital) by the above-mentioned vehicle tentatively identified
Number segmentation is at prefix part and coded portion, and the determination character identified according to prefix part, in license number
Selection and the highest destination prefix of prefix part matching degree in prefix list, the prefix portion as the license number mark tentatively identified
Point, the combination of destination prefix and suffix portion is determined as to the combination of the character content of all target areas.
104, when the combination of the character content of all target areas meets preset characters logic, by all target areas
The combination of character content is determined as the license number mark of High Speed Railway Trains.
In the embodiment of the present invention, it should be noted that after identifying license number mark according to above-mentioned target image, may be used also
Image is opened as new target image to continue the reselection one from multiple above-mentioned images, and again for the new target image
Above-mentioned steps 102-104 is executed, the corresponding license number mark of every image in multiple above-mentioned images is obtained, it should be noted that if
It is not determined by the license number mark of a certain image, then the license number of a certain image can be identified and be set as null.This identification is every
The mode for opening the corresponding license number mark of image can not only carry out further Accuracy Verification to the license number mark identified, also
It can be identified with and mistake in the license number identified, the license number identified is identified according to the newest multiple license numbers mark identified
It is corrected, to finally obtain accurate license number mark.That is: respectively can will using multiple above-mentioned images as license number image group
Every image in the license number image group is determined as target image and executes the operation of step 102- step 104 respectively, is known
Not Chu, do not identify for the license number of null, wherein each license number mark can include prefix part and vehicle indicator section；It will
The most prefix part of frequency of occurrence is determined as final prefix in all license numbers mark identified, and will identify that all
Vehicle indicator section in license number mark forms different number set according to sequence of positions, wherein the word that each number set includes
Symbol is identical in the sequence of positions of vehicle indicator section；It is suitable that the most character of frequency of occurrence in each number set is determined as corresponding position
Final character at sequence, finally to be numbered；Final prefix and final number are combined into final license number mark.It mentions in this way
The accuracy of the high license number mark identified.
In the embodiment of the present invention, above-mentioned algorithm can reduce the recognition cycle (recognition cycle was down to 5 seconds) of license number, and improve
The recognition accuracy of license number (recognition accuracy is up to 95% or more).
It should be noted that if there are above-mentioned spcial character (such as *) in final license number mark, then illustrate Train number recognition mistake
Accidentally, it needs again to take pictures to High Speed Railway Trains.Further, the Train number recognition method of the High Speed Railway Trains can be with
Including following operation:
If in the license number mark finally determined, there are spcial characters, it is determined that the Crack cause of the spcial character；
When the Crack cause of spcial character is that the character identified has incomplete, determine that character has incomplete position；
When it is that position is located at the downside of character that character, which has incompleteness, the shooting angle of above-mentioned filming apparatus is adjusted downwards,
When character, which has incomplete position, is located at the upside of character, it is adjusted up the shooting angle of filming apparatus.It can guarantee in this way
Multiple images that filming apparatus is shot include the reliability of complete character.
As it can be seen that high speed can be shot to filming apparatus by implementing the Train number recognition method of High Speed Railway Trains described in Fig. 1
The target image that railroad train obtains is identified, obtains character content, and can be by preset characters logic to obtained word
Symbol content is verified, and can fast and accurately identify the license number mark of High Speed Railway Trains in this way.
Embodiment two
Referring to Fig. 2, Fig. 2 is the stream of the Train number recognition method of another High Speed Railway Trains disclosed by the embodiments of the present invention
Journey schematic diagram.Wherein, method described in Fig. 2 can be applied in the management system of High Speed Railway Trains.As shown in Fig. 2, should
The Train number recognition method of High Speed Railway Trains may include following operation:
201, control audio signal emitter emits the audio signal of the first predeterminated frequency.
202, judge that audio signal reception device emits the audio signal of the first predeterminated frequency in audio signal emitter
Whether response signal is received in preset time period later, when the judging result of step 202, which is, is, triggering executes step
203；When the judging result of step 202 is no, triggering can be continued and execute step 201.
203, judge whether the frequency of above-mentioned response signal is whether the second predeterminated frequency and above-mentioned response signal carry
There is the signal identification of the audio signal of the first predeterminated frequency, when the judging result of step 203, which is, is, determines above-mentioned high-speed railway
Train is close to filming apparatus and shorter with the distance between filming apparatus, and triggers and execute step 204；When step 203
When judging result is no, this process can be terminated.
204, control filming apparatus executes shooting operation to High Speed Railway Trains, obtains the target figure of High Speed Railway Trains
Picture.
205, text filed by whether there is in preset detection algorithm detection target image, when the judgement knot of step 205
Fruit is when being, triggering executes step 206；When the judging result of step 205 is no, following operation can be executed:
It obtains filming apparatus and the obtained next image of shooting operation is executed to High Speed Railway Trains, as target image,
And retriggered executes step 205.
In the embodiment of the present invention, preset detection algorithm can be very big stable extremal region algorithm (MSER), or
Grey level histogram detection algorithm, the embodiment of the present invention is without limitation.
206, when in target image there are it is text filed when, identify that there are at least the one of character content in above-mentioned target image
A target area, and identify the character content in each target area.
207, judge whether the combination of the character content of all target areas meets preset characters logic, which patrols
It collects license number corresponding to the vehicle including at least High Speed Railway Trains and identifies included character quantity.
In the embodiment of the present invention, when the judging result of step 207, which is, is, triggering executes step 208；When step 207
When judging result is no, following operation can be executed:
It obtains filming apparatus and the obtained next image of shooting operation is executed to High Speed Railway Trains, as target image,
And retriggered executes step 205.
208, when the combination of the character content of all target areas meets preset characters logic, by all target areas
The combination of character content is determined as the license number mark of High Speed Railway Trains.
In the embodiment of the present invention, the description for step 206- step 208 is please referred in embodiment one for step 102-
The detailed description of step 104, the embodiment of the present invention repeat no more.
As it can be seen that the embodiment of the present invention can be in the response signal of the audio signal, reception specific frequency that emit specific frequency
And in the case that response signal meets condition, triggering filming apparatus executes shooting operation, in this way can be in High Speed Railway Trains
Filming apparatus is controlled when closing on filming apparatus again to be shot, filming apparatus can not only be improved in this way and taken for high-speed iron
The reliability of the target image of road train, additionally it is possible to reduce the power consumption of filming apparatus.
As an alternative embodiment, after the step 208 that is finished, the Train number recognition of the High Speed Railway Trains
Method can also include following operation:
Acquisition image corresponding with High Speed Railway Trains is collected under the license number mark of High Speed Railway Trains, high speed is formed
The image recording of railroad train, the image recording include at least license number mark, High Speed Railway Trains pantograph panoramic picture with
And the slide plate image of High Speed Railway Trains.
In the optional embodiment, the image recording of formation can be uploaded to the monitor supervision platform of High Speed Railway Trains, so as to
High Speed Railway Trains are being had there are when failure (such as bow failure or slide plate failure), in time according to image analysis in supervisor
Corresponding license number mark is found according to image recording, and then finds corresponding High Speed Railway Trains, it is timely to be conducive to maintenance personal
Failure is repaired or is conducive to that corresponding train group membership is notified to take corresponding counter-measure in time.
In another alternative embodiment, when the testing result of step 205 be when, and execute step 206 it
Before, the Train number recognition method of the High Speed Railway Trains can also include following operation:
Pretreatment operation is executed to above-mentioned target image, and triggers step 206.
Wherein, which may include smoothing filtering operation, enhancing contrast operation and the operation that highlights
At least one of.
Specifically, may include: to above-mentioned target image execution pretreatment operation
The resolution ratio of above-mentioned target image is zoomed into default resolution ratio, such as 512*256；
The HOG feature of target image after analyzing resolution ratio scaling, and contracted according to the HOG feature that analysis obtains to resolution ratio
Target image after putting is exposed gain process, and by the smooth target image of gaussian filtering, to filter out noise.
As it can be seen that another optional embodiment can in recognition target image there are the target area of character content it
Before, pretreatment operation is executed to target image, which further increases the picture qualities of target image, and then improve identification
The accuracy of target area out.
It, should after being finished step 204 and before executing step 205 in another optional embodiment
The Train number recognition method of High Speed Railway Trains can also include following operation:
Judge whether the resolution ratio of target image meets default resolution condition, when being unsatisfactory for default resolution condition,
Available filming apparatus executes the next image that shooting operation obtains to High Speed Railway Trains and lays equal stress on as target image
New triggering, which executes, judges whether the resolution ratio of target image meets the operation of default resolution condition；Resolution ratio item is preset when meeting
When part, triggering executes step 205.The mode directly handled in this way high-resolution target image is conducive to raising pair
The reliability of target image processing.
As it can be seen that high speed can be shot to filming apparatus by implementing the Train number recognition method of High Speed Railway Trains described in Fig. 2
The target image that railroad train obtains is identified, obtains character content, and can be by preset characters logic to obtained word
Symbol content is verified, and can fast and accurately identify the license number mark of High Speed Railway Trains in this way；Additionally it is possible to mention
High filming apparatus takes the reliability of the target image for High Speed Railway Trains, and reduces the power consumption of filming apparatus；And
Supervisor can also be convenient for haveing High Speed Railway Trains according to image analysis, and there are failure (such as bow failures or slide plate event
Barrier) when, corresponding license number is found according to image recording in time and is identified, and then finds corresponding High Speed Railway Trains, is conducive to tie up
Personnel are repaired in time to repair failure or be conducive to that corresponding train group membership is notified to take corresponding counter-measure in time；Also
The accuracy of identification object region is can be improved.
Embodiment three
Referring to Fig. 3, Fig. 3 is a kind of structure of the number identification device of High Speed Railway Trains disclosed by the embodiments of the present invention
Schematic diagram.Wherein, device described in Fig. 3 can be applied in the management system of High Speed Railway Trains.As shown in figure 3, the height
The number identification device of fast railroad train may include:
First control unit 301 executes shooting operation to High Speed Railway Trains for controlling filming apparatus, obtains high-speed iron
The target image of road train.
In the embodiment of the present invention, specifically, after control filming apparatus is continuously shot operation to High Speed Railway Trains execution,
Available multiple images for High Speed Railway Trains, also available one section of video for High Speed Railway Trains, and mention
The image in the video is taken to obtain multiple images.Wherein, any one in multiple images which can be
Image.Preferably, which can be the image in middle position, i.e., according to the sequencing of shooting time to obtained institute
There is image to be ranked up, and shooting time a certain image in an intermediate position is determined as target image.Be conducive in this way
Improve the reliability that character content is identified from target image.
Recognition unit 302, there are at least one target areas of character content in target image for identification, and identify every
Character content in a target area.
Judging unit 303, for judging whether the combination of character content of all target areas meets preset characters logic,
The preset characters logic includes at least license number corresponding to the vehicle of High Speed Railway Trains and identifies included character quantity.
Determination unit 304, for judging that it is pre- that the combination of character content of all target areas meets when judging unit 303
If when character logic, the license number that the combination of the character content of all target areas is determined as High Speed Railway Trains is identified.
Optionally, determination unit 304 can be also used for judging the character content of all target areas in judging unit 303
Combination whether meet preset characters logic before, determine preset characters logic.
Wherein it is determined that unit 304 determines that the mode of preset characters logic is specifically as follows:
Determine geographical location locating for filming apparatus, shooting direction and the period for executing above-mentioned shooting operation, according to
The geographical location, executes the period of above-mentioned shooting operation and the train of the geographical location got at shooting direction
Running time table determines the essential information of above-mentioned High Speed Railway Trains, which can include at least above-mentioned high-speed railway and arrange
Origin, approach station and the destination of vehicle；
Preset characters logic corresponding with above-mentioned High Speed Railway Trains is determined according to the essential information.It can be improved so really
The matching degree for the above-mentioned High Speed Railway Trains of preset characters logical AND made.
In the embodiment of the present invention, optionally, which can also include that the vehicle institute of High Speed Railway Trains is right
Character types included in the license number mark answered, character position and kinds of characters type institute corresponding to kinds of characters type
Corresponding character quantity.It can be further improved the accuracy of the license number mark identified in this way.Wherein, which can be with
It also may include letter type and numeric type including Chinese character type, letter type and numeric type.
In the embodiment of the present invention, it should be noted that determination unit 304 identifies that license number identifies according to above-mentioned target image
Later, the image reselected from multiple above-mentioned images can be determined as new target image, and triggers above-mentioned list
The member target image new to this does processing identical with above-mentioned target image, corresponding to obtain every image in multiple above-mentioned images
License number mark, it should be noted that if be not determined by a certain image license number mark, can be by the license number of a certain image
Mark is set as null.The mode of the corresponding license number mark of every image of this identification in this way can not only be to the license number identified
Mark carries out further Accuracy Verification, additionally it is possible to be identified with and mistake in the license number identified, according to it is newest identify it is more
A license number mark is corrected the license number mark identified, to finally obtain accurate license number mark.That is, determination unit
304 can be also used for:
Multiple above-mentioned images are determined as license number image group, and respectively determine every image in the license number image group
For target image, and finally determine that multiple above-mentioned images are corresponding, do not identify for all license numbers of null, wherein Mei Geche
Number mark can include prefix part and vehicle indicator section；
The most prefix part of frequency of occurrence is determined as final prefix in all license numbers mark that will identify that, and will know
Not Chu all license numbers mark in vehicle indicator section different number set is formed according to sequence of positions, wherein each number collects
The character that conjunction includes is identical in the sequence of positions of vehicle indicator section；
The most character of frequency of occurrence in each number set is determined as the final character at corresponding position sequence, with
To final number；
Final prefix and final number are combined into final license number mark.The license number mark identified is improved in this way
Accuracy.
As it can be seen that device described in implementing Fig. 3 can shoot the target image that High Speed Railway Trains obtain to filming apparatus
It is identified, obtains character content, and can verify by preset characters logic to obtained character content, in this way can
Fast and accurately identify the license number mark of High Speed Railway Trains.
In an alternative embodiment, as shown in figure 4, first control unit 301 may include:
Subelement 3011 is perceived, for perceiving the environmental parameter of filming apparatus local environment.
Subelement 3012 is adjusted, for perceive environmental parameter that subelement 3011 perceives as foundation, by preset
The acquisition parameters of imaging quality assessment algorithm adjustment filming apparatus.
Subelement 3013 is controlled, for controlling filming apparatus to adjust the acquisition parameters adjusted of subelement 3012 as foundation
Shooting operation is executed to High Speed Railway Trains, obtains the target image of High Speed Railway Trains.
It can also be in the environmental parameter for perceiving filming apparatus current environment as it can be seen that implementing device described in Fig. 4
Later, the preset environmental parameter of imaging quality assessment algorithm evaluation current environment and working as filming apparatus can be passed through
Before take pictures influence of the parameter to filming apparatus image quality, and the acquisition parameters of filming apparatus are adjusted according to assessment result, to protect
The quality for the image that card filming apparatus is shot under the different illumination conditions of different periods (round-the-clock), and then be conducive to mention
The accuracy of high Train number recognition.
In another alternative embodiment, as shown in figure 4, the device can also include:
Unit 305 is collected, for acquisition image corresponding with High Speed Railway Trains to be collected the vehicle in High Speed Railway Trains
Under number mark, the image recording of High Speed Railway Trains is formed, which includes at least license number mark, High Speed Railway Trains
The slide plate image of pantograph panoramic picture and High Speed Railway Trains.
In the optional embodiment, the image recording of formation can be uploaded to the monitor supervision platform of High Speed Railway Trains, so as to
High Speed Railway Trains are being had there are when failure (such as bow failure or slide plate failure), in time according to image analysis in supervisor
Corresponding license number mark is found according to image recording, and then finds corresponding High Speed Railway Trains, it is timely to be conducive to maintenance personal
Failure is repaired or is conducive to that corresponding train group membership is notified to take corresponding counter-measure in time.
In another optional embodiment, as shown in figure 4, the device can also include:
Detection unit 306, for text filed by whether there is in the above-mentioned target image of preset detection algorithm detection, when
Detect in above-mentioned target image there are it is text filed when, triggering recognition unit 302 is executed and is deposited in above-mentioned recognition target image
In at least one target area of character content.
Wherein, above-mentioned text filed including above-mentioned target area.
It is further alternative in another optional embodiment, as shown in figure 4, the device can also include:
Pretreatment unit 307, for detecting in target image in detection unit 306 there are after text filed, to mesh
Logo image executes pretreatment operation, wherein pretreatment operation includes that smoothing filtering operation, enhancing contrast operation and enhancing are bright
At least one of degree operation.
Wherein, pretreatment unit 307 can be specifically used for:
The resolution ratio of above-mentioned target image is zoomed into default resolution ratio, such as 512*256；
The HOG feature of target image after analyzing resolution ratio scaling, and contracted according to the HOG feature that analysis obtains to resolution ratio
Target image after putting is exposed gain process, and by the smooth target image of gaussian filtering, to filter out noise.
Wherein, recognition unit 302, specifically for when detection unit 306 detect in target image there are it is text filed when
And after pretreatment unit 307 executes pretreatment operation to target image, there are character contents in recognition target image extremely
A few target area, and identify the character content in each target area.
As it can be seen that described in implementation Fig. 4, device can also there are the target areas of character content in recognition target image
Before, pretreatment operation is executed to target image, which further increases the picture qualities of target image, and then improve knowledge
Not Chu target area accuracy.
In another optional embodiment, there are at least the one of character content in 302 recognition target image of recognition unit
A target area, and identify that the mode of the character content in each target area is specifically as follows:
License number identified areas in recognition target image, and Character segmentation is carried out to license number identified areas, obtain that there are words
Accord at least one target area of content；
Each target area is identified by classifier, obtains the character content of each target area.
Wherein, the license number identified areas in 302 recognition target image of recognition unit, and character is carried out to license number identified areas
Segmentation, obtains being specifically as follows there are the mode of at least one of character content target area:
Pass through very big stable extremal region algorithm (MSER), using general character dimensional parameters as foundation, detecting target image
Extremal region；
Character extremal region is filtered out from the extremal region detected by the physical parameter of character, wherein character
Physical parameter may include the length and width of character, Aspect Ratio etc.；
By morphology closed operation, the adjacent character extremal region just sifted out is linked to be candidate characters region, as knowledge
Not Chu possibility include license number mark region (i.e. license number identified areas)；
Forecasting recognition is carried out to the character in each candidate characters region, and is scored recognition result, is scored
Value, and score value is met into the highest candidate characters region of score value in all score values of default scoring threshold condition and is determined
For final character zone；
Binaryzation is carried out to final character zone by big saliva (OTSU) algorithm, it is (large scale, general by three classes character size
Logical size and small size) extremal region in the final character zone of parameter detection, obtain that there are at least one of character content
Target area.
And recognition unit 302 identifies each target area by classifier, obtains the word of each target area
The mode of symbol content is specifically as follows:
Final character zone is split by connected region domain method, obtains cut zone；
Cut zone and target area are carried out and operated, to screen suspicious character；
Identification prediction is carried out to the suspicious character filtered out using license number Character prediction classifier, analyzes suspicious character position
With size characteristic, and combine Character prediction as a result, suspicious character is ranked up, supplement omission character, obtain each target area
The character content in domain, as the license number mark tentatively identified, wherein omitting character is identified in the target area of target image
The unknown character not gone out, can be replaced by spcial character (such as *).
Wherein, the generating process of license number Character prediction classifier may include:
It determines the character sample being truncated to, character sample is zoomed into identical resolution ratio (such as 20*20)；
Histograms of oriented gradients (Histogram of Oriented Gradient, HOG) feature of calculating character sample,
The HOG feature of character sample and sample character input are trained to support vector machines (SVM) classifier, obtain above-mentioned license number
Character prediction classifier.
In another optional embodiment, as shown in figure 4, the device can also include:
Second control unit 308 emits the audio signal of the first predeterminated frequency for controlling audio signal emitter.
Judging unit 303 is also used to judge that audio signal reception device is default in audio signal emitter transmitting first
Whether response signal is received in preset time period after the audio signal of frequency, when receiving response signal, judges to respond
Whether the frequency of signal is the second predeterminated frequency and response signal whether carry the first predeterminated frequency audio signal letter
Number mark, when the frequency for judging response signal is the sound that the second predeterminated frequency and response signal carry the first predeterminated frequency
When the signal identification of frequency signal, triggering first control unit 301 executes above-mentioned control filming apparatus and holds to High Speed Railway Trains
Row shooting operation obtains the target image of High Speed Railway Trains.
As it can be seen that implement device described in Fig. 4 can also transmitting specific frequency audio signal, receive specific frequency
In the case that response signal and response signal meet condition, triggering filming apparatus executes shooting operation, in this way can be in high speed
Filming apparatus is controlled when railroad train closes on filming apparatus again to be shot, filming apparatus can not only be improved in this way and take needle
To the reliability of the target image of High Speed Railway Trains, additionally it is possible to reduce the power consumption of filming apparatus.
In another optional embodiment, judging unit 303 can be also used for the license number mark that judgement finally determines
In whether there is spcial character.
Determination unit 304, can be also used in license number that judging unit 303 finally determines mark that there are spcial characters
When, it determines the Crack cause of the spcial character, when the Crack cause of spcial character is that the character identified has incomplete, determines
There is incomplete position in character.
Second control unit 308 can be also used for when it is that position is located at the downside of character that character, which has incompleteness, to downward
The shooting angle for saving above-mentioned filming apparatus is adjusted up shooting dress when character, which has incomplete position, is located at the upside of character
The shooting angle set.
As it can be seen that implementing device described in Fig. 4 can also guarantee to clap by adjusting the mode of the shooting angle of filming apparatus
Take the photograph the reliability that multiple images that device is shot include complete character.
Example IV
Referring to Fig. 5, Fig. 5 is a kind of structural representation of the Train number recognition of High Speed Railway Trains disclosed by the embodiments of the present invention
Figure.Wherein, device described in Fig. 5 can be applied in High Speed Railway Trains management system.As shown in figure 5, the device can be with
Include:
It is stored with the memory 501 of executable program code；
The processor 502 coupled with memory 501；
Processor 502 calls the executable program code stored in memory 501, executes the described high speed of Fig. 1 or Fig. 2
Step in the Train number recognition of railroad train.
Embodiment five
The embodiment of the invention discloses a kind of computer readable storage mediums, store computer program, wherein the calculating
Machine program makes computer execute the step in the Train number recognition of High Speed Railway Trains described in Fig. 1 or Fig. 2.
Embodiment six
The embodiment of the invention discloses a kind of computer program products, when the computer program product is run on computers
When, so that the computer executes the step in the Train number recognition of High Speed Railway Trains described in Fig. 1 or Fig. 2.
In various embodiments of the present invention, it should be appreciated that magnitude of the sequence numbers of the above procedures are not meant to execute suitable
Successively, the execution sequence of each process should be determined by its function and internal logic the certainty of sequence, without coping with the embodiment of the present invention
Implementation process constitutes any restriction.
In embodiment provided by the present invention, it should be appreciated that " B corresponding with A " indicates that B is associated with A, can be with according to A
Determine B.It is also to be understood that determine that B is not meant to determine B only according to A according to A, it can also be according to A and/or other information
Determine B.
In addition, each functional unit in various embodiments of the present invention can integrate in one processing unit, it is also possible to
Each unit physically exists alone, and can also be integrated in one unit with two or more units.Above-mentioned integrated unit
Both it can take the form of hardware realization, can also realize in the form of software functional units.If above-mentioned integrated unit with
The form of SFU software functional unit realizes and that when sold or used as an independent product can store can obtain in a computer
Memory in.Based on this understanding, the portion that technical solution of the present invention substantially in other words contributes to the prior art
Point or the technical solution it is all or part of, can be embodied in the form of software products, the computer software product
It is stored in a memory, including several requests are used so that a computer equipment (can be personal computer, server
Or network equipment etc., specifically can be the processor in computer equipment) execute each embodiment above method of the invention
Some or all of step.
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 be stored in a computer readable storage medium, storage
Medium include read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory,
RAM), programmable read only memory (Programmable Read-only Memory, PROM), erasable programmable is read-only deposits
Reservoir (Erasable Programmable Read Only Memory, EPROM), disposable programmable read-only memory (One-
Time Programmable Read-Only Memory, OTPROM), the electronics formula of erasing can make carbon copies read-only memory
(Electrically-Erasable Programmable Read-Only Memory, EEPROM), CD-ROM (Compact
Disc Read-Only Memory, CD-ROM) or other disc memories, magnetic disk storage, magnetic tape storage or can
For carrying or any other computer-readable medium of storing data.
A kind of Train number recognition method and device of High Speed Railway Trains disclosed by the embodiments of the present invention has been carried out in detail above
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 Train number recognition method of High Speed Railway Trains, which is characterized in that the described method includes:
It controls filming apparatus and shooting operation is executed to the High Speed Railway Trains, obtain the target figure of the High Speed Railway Trains
Picture；
It identifies at least one target area in the target image there are character content, and identifies in each target area
Character content；
Judge whether the combination of the character content of all target areas meets preset characters logic, the preset characters logic
License number corresponding to vehicle including at least the High Speed Railway Trains identifies included character quantity；
When the combination of the character content of all target areas meets the preset characters logic, by all target areas
The combination of the character content in domain is determined as the license number mark of the High Speed Railway Trains.
2. the Train number recognition method of High Speed Railway Trains according to claim 1, which is characterized in that the control shooting dress
It sets and shooting operation is executed to the High Speed Railway Trains, obtain the target image of the High Speed Railway Trains, comprising:
Perceive the environmental parameter of filming apparatus local environment；
Using the environmental parameter perceived as foundation, the filming apparatus is adjusted by preset imaging quality assessment algorithm
Acquisition parameters；
The filming apparatus is controlled with the acquisition parameters to execute shooting operation according to the High Speed Railway Trains, obtains institute
State the target image of High Speed Railway Trains.
3. the Train number recognition method of High Speed Railway Trains according to claim 1 or 2, which is characterized in that the method is also
Include:
Acquisition image corresponding with the High Speed Railway Trains is collected under the license number mark of the High Speed Railway Trains,
The image recording of the High Speed Railway Trains is formed, described image record includes at least license number mark, the high-speed railway
The pantograph panoramic picture of train and the slide plate image of the High Speed Railway Trains；
And there are before at least one target area of character content in the identification target image, the method is also
Include:
It is detected in the target image by preset detection algorithm with the presence or absence of text filed；
When detect in the target image there are it is described text filed when, execute and exist in the identification target image
At least one target area of character content；
Wherein, described text filed including the target area.
4. according to the method described in claim 3, it is characterized in that, there are the text areas in detecting the target image
After domain, the method also includes:
Pretreatment operation is executed to the target image, and triggers and executes in the identification target image that there are in character
At least one target area held；
Wherein, the pretreatment operation include smoothing filtering operation, enhancing contrast operation and highlight operation in extremely
Few one kind；
And there are at least one target areas of character content in the identification target image, and identify each described
Character content in target area, comprising:
It identifies the license number identified areas in the target image, and Character segmentation is carried out to the license number identified areas, deposited
In at least one target area of character content；
Each target area is identified by classifier, obtains the character content of each target area.
5. method according to claim 1-4, which is characterized in that the control filming apparatus is to the high-speed iron
Road train executes shooting operation, before obtaining the target image of the High Speed Railway Trains, the method also includes:
It controls audio signal emitter and emits the audio signal of the first predeterminated frequency, and judge audio signal reception device in institute
It states and whether is received in the preset time period after audio signal emitter emits the audio signal of first predeterminated frequency
Response signal；
When judging to receive the response signal, judge the response signal frequency whether be the second predeterminated frequency and
Whether the response signal carries the signal identification of the audio signal of first predeterminated frequency；
When the frequency for judging the response signal is that second predeterminated frequency and the response signal carry described the
When the signal identification of the audio signal of one predeterminated frequency, triggering executes the control filming apparatus to the High Speed Railway Trains
Shooting operation is executed, the target image of the High Speed Railway Trains is obtained.
6. a kind of number identification device of High Speed Railway Trains, which is characterized in that described device includes:
First control unit executes shooting operation to the High Speed Railway Trains for controlling filming apparatus, obtains the high speed
The target image of railroad train；
Recognition unit, there are at least one target areas of character content in the target image for identification, and identify each
Character content in the target area；
Judging unit, for judging whether the combination of character content of all target areas meets preset characters logic, institute
It states license number corresponding to vehicle of the preset characters logic including at least the High Speed Railway Trains and identifies included character quantity；
Determination unit, for judging that it is described that the combination of character content of all target areas meets when the judging unit
When preset characters logic, the combination of the character content of all target areas is determined as to the license number of the High Speed Railway Trains
Mark.
7. device according to claim 6, which is characterized in that the first control unit includes:
Subelement is perceived, for perceiving the environmental parameter of filming apparatus local environment；
Subelement is adjusted, the environmental parameter for perceiving using the perception subelement passes through preset imaging as foundation
Quality evaluation algorithm adjusts the acquisition parameters of the filming apparatus；
Subelement is controlled, for controlling the filming apparatus with the acquisition parameters as according to High Speed Railway Trains execution
Shooting operation obtains the target image of the High Speed Railway Trains.
8. device according to claim 6 or 7, which is characterized in that described device further include:
Unit is collected, for acquisition image corresponding with the High Speed Railway Trains to be collected the institute in the High Speed Railway Trains
State under license number mark, form the image recording of the High Speed Railway Trains, described image record include at least license number mark,
The pantograph panoramic picture of the High Speed Railway Trains and the slide plate image of the High Speed Railway Trains；
Described device further include:
Detection unit, for being detected in the target image by preset detection algorithm with the presence or absence of text filed, when detecting
In the target image there are it is described text filed when, trigger the recognition unit and execute in the identification target image
There are at least one target areas of character content；
Wherein, described text filed including the target area.
9. device according to claim 8, which is characterized in that described device further include:
Pretreatment unit, for the detection unit detect in the target image there are it is described it is text filed after, it is right
The target image executes pretreatment operation；Wherein, the pretreatment operation includes smoothing filtering operation, enhancing contrast operation
And at least one of the operation that highlights；
The recognition unit, specifically for when the detection unit detect in the target image there are it is described text filed when
And after the pretreatment unit executes pretreatment operation to the target image, identify that there are characters in the target image
At least one target area of content, and identify the character content in each target area；
And the recognition unit identifies at least one target area in the target image there are character content, and identifies
The mode of character content in each target area specifically:
It identifies the license number identified areas in the target image, and Character segmentation is carried out to the license number identified areas, deposited
In at least one target area of character content；
Each target area is identified by classifier, obtains the character content of each target area.
10. according to the described in any item devices of claim 6-9, which is characterized in that described device further include:
Second control unit emits the audio signal of the first predeterminated frequency for controlling audio signal emitter；
The judging unit is also used to judge that audio signal reception device emits described first in the audio signal emitter
Whether response signal is received in preset time period after the audio signal of predeterminated frequency, when receiving the response signal,
Judge whether the frequency of the response signal is whether the second predeterminated frequency and the response signal carry described first in advance
If the signal identification of the audio signal of frequency, when judging the frequency of the response signal for second predeterminated frequency and institute
When stating the signal identification for the audio signal that response signal carries first predeterminated frequency, triggers the first control unit and hold
The row control filming apparatus executes shooting operation to the High Speed Railway Trains, obtains the target of the High Speed Railway Trains
Image.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810813119.9A CN109344829B (en) | 2018-07-23 | 2018-07-23 | Train number identification method and device for high-speed railway train |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810813119.9A CN109344829B (en) | 2018-07-23 | 2018-07-23 | Train number identification method and device for high-speed railway train |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109344829A true CN109344829A (en) | 2019-02-15 |
| CN109344829B CN109344829B (en) | 2021-05-18 |
Family
ID=65291287
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810813119.9A Active CN109344829B (en) | 2018-07-23 | 2018-07-23 | Train number identification method and device for high-speed railway train |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109344829B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110852234A (en) * | 2019-11-05 | 2020-02-28 | 成都铁安科技有限责任公司 | Train number identification method and system |
| CN110895797A (en) * | 2019-04-04 | 2020-03-20 | 王俊芝 | Intelligent network transceiving platform |
| CN113378646A (en) * | 2021-05-18 | 2021-09-10 | 上海平奥供应链管理有限公司 | Freight train information identification system and identification method |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2003022494A (en) * | 2001-07-10 | 2003-01-24 | Fujitsu Ltd | Character on moving body recognition system |
| US20050169500A1 (en) * | 2004-01-30 | 2005-08-04 | Fujitsu Limited | Method of and apparatus for setting image-capturing conditions, and computer program |
| CN104730515A (en) * | 2015-03-26 | 2015-06-24 | 北京交通大学 | Device for measuring distance between trains by means of sound signals |
| CN105550654A (en) * | 2015-12-15 | 2016-05-04 | 成都交大光芒科技股份有限公司 | High-speed train image acquisition system, and real-time train number detection system and method |
| CN105991932A (en) * | 2015-02-09 | 2016-10-05 | 联想(北京)有限公司 | Data processing method and electronic equipment |
| CN107144227A (en) * | 2017-04-21 | 2017-09-08 | 南京理工大学 | A kind of municipal rail train pantograph pan on-line thickness testing and method |
-
2018
- 2018-07-23 CN CN201810813119.9A patent/CN109344829B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2003022494A (en) * | 2001-07-10 | 2003-01-24 | Fujitsu Ltd | Character on moving body recognition system |
| US20050169500A1 (en) * | 2004-01-30 | 2005-08-04 | Fujitsu Limited | Method of and apparatus for setting image-capturing conditions, and computer program |
| CN105991932A (en) * | 2015-02-09 | 2016-10-05 | 联想(北京)有限公司 | Data processing method and electronic equipment |
| CN104730515A (en) * | 2015-03-26 | 2015-06-24 | 北京交通大学 | Device for measuring distance between trains by means of sound signals |
| CN105550654A (en) * | 2015-12-15 | 2016-05-04 | 成都交大光芒科技股份有限公司 | High-speed train image acquisition system, and real-time train number detection system and method |
| CN107144227A (en) * | 2017-04-21 | 2017-09-08 | 南京理工大学 | A kind of municipal rail train pantograph pan on-line thickness testing and method |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110895797A (en) * | 2019-04-04 | 2020-03-20 | 王俊芝 | Intelligent network transceiving platform |
| CN110852234A (en) * | 2019-11-05 | 2020-02-28 | 成都铁安科技有限责任公司 | Train number identification method and system |
| CN110852234B (en) * | 2019-11-05 | 2023-09-08 | 成都盛锴科技有限公司 | Train number identification method and system |
| CN113378646A (en) * | 2021-05-18 | 2021-09-10 | 上海平奥供应链管理有限公司 | Freight train information identification system and identification method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109344829B (en) | 2021-05-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2019105342A1 (en) | Method and apparatus for detecting fake license plates of vehicles, readable storage medium, and electronic device | |
| CN105702048B (en) | Highway front truck illegal road occupation identifying system based on automobile data recorder and method | |
| US11361556B2 (en) | Deterioration diagnosis device, deterioration diagnosis system, deterioration diagnosis method, and storage medium for storing program | |
| CN110298300B (en) | Method for detecting vehicle illegal line pressing | |
| CN104268596B (en) | A kind of Car license recognition device and its detection method of license plate and system | |
| CN107305627A (en) | A kind of automobile video frequency monitoring method, server and system | |
| CN104282154B (en) | A kind of overload of vehicle monitoring system and method | |
| CN109637151A (en) | A kind of recognition methods that highway Emergency Vehicle Lane is driven against traffic regulations | |
| CN109344886B (en) | Occlusion number plate distinguishing method based on convolutional neural network | |
| JP5931662B2 (en) | Road condition monitoring apparatus and road condition monitoring method | |
| KR101834838B1 (en) | System and method for providing traffic information using image processing | |
| CN105608431A (en) | Vehicle number and traffic flow speed based highway congestion detection method | |
| CN109344829A (en) | A kind of Train number recognition method and device of High Speed Railway Trains | |
| CN108986472A (en) | One kind turns around vehicle monitoring method and device | |
| CN107909009A (en) | A kind of obstacle detection method and device based on road surface study | |
| CN111369801B (en) | Vehicle identification method, device, equipment and storage medium | |
| CN113011331B (en) | Method and device for detecting whether motor vehicle gives way to pedestrians, electronic equipment and medium | |
| CN112507760B (en) | Method, device and equipment for detecting violent sorting behaviors | |
| CN106571040A (en) | Suspicious vehicle confirmation method and equipment | |
| CN110223505A (en) | A kind of determination method and device of pedestrian running red light behavior | |
| US20140037141A1 (en) | Method for evaluating a plurality of time-offset pictures, device for evaluating pictures, and monitoring system | |
| Suttiponpisarn et al. | Detection of wrong direction vehicles on two-way traffic | |
| CN111383248A (en) | Method and device for judging red light running of pedestrian and electronic equipment | |
| CN112991769A (en) | Traffic volume investigation method and device based on video | |
| CN116311166A (en) | Traffic obstacle recognition method and device and electronic equipment |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right |
Denomination of invention: A train number recognition method and device for high-speed railway trains Effective date of registration: 20220718 Granted publication date: 20210518 Pledgee: Guangdong Development Bank Limited by Share Ltd. Guangzhou branch Pledgor: GUANGZHOU KEII ELECTRO OPTICS TECHNOLOGY Co.,Ltd. Registration number: Y2022440000174 |
|
| PE01 | Entry into force of the registration of the contract for pledge of patent right | ||
| PC01 | Cancellation of the registration of the contract for pledge of patent right |
Date of cancellation: 20230830 Granted publication date: 20210518 Pledgee: Guangdong Development Bank Limited by Share Ltd. Guangzhou branch Pledgor: GUANGZHOU KEII ELECTRO OPTICS TECHNOLOGY Co.,Ltd. Registration number: Y2022440000174 |
|
| PC01 | Cancellation of the registration of the contract for pledge of patent right | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right |
Denomination of invention: A method and device for identifying train numbers on high-speed railways Effective date of registration: 20231117 Granted publication date: 20210518 Pledgee: Guangdong Development Bank Limited by Share Ltd. Guangzhou branch Pledgor: GUANGZHOU KEII ELECTRO OPTICS TECHNOLOGY Co.,Ltd. Registration number: Y2023980065425 |
|
| PE01 | Entry into force of the registration of the contract for pledge of patent right |