CN105868753B - The recognition methods of blue license plate color and device - Google Patents
The recognition methods of blue license plate color and device Download PDFInfo
- Publication number
- CN105868753B CN105868753B CN201610207212.6A CN201610207212A CN105868753B CN 105868753 B CN105868753 B CN 105868753B CN 201610207212 A CN201610207212 A CN 201610207212A CN 105868753 B CN105868753 B CN 105868753B
- Authority
- CN
- China
- Prior art keywords
- license plate
- infrared
- lighting sources
- supplementary lighting
- light
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/10—Image acquisition
- G06V10/12—Details of acquisition arrangements; Constructional details thereof
- G06V10/14—Optical characteristics of the device performing the acquisition or on the illumination arrangements
- G06V10/143—Sensing or illuminating at different wavelengths
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/10—Image acquisition
- G06V10/12—Details of acquisition arrangements; Constructional details thereof
- G06V10/14—Optical characteristics of the device performing the acquisition or on the illumination arrangements
- G06V10/141—Control of illumination
-
- 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
- G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
Abstract
This application discloses a kind of recognition methods of blue license plate color and devices, which comprises when illumination brightness is lower than given luminance, opens light filling source；The light filling source includes near-infrared supplementary lighting sources and infrared supplementary lighting sources；The operating mode for switching the double filter IR-cut of infrared ray of the video camera, so that visible light and infrared light pass through simultaneously；Near-infrared supplementary lighting sources and infrared supplementary lighting sources open the license plate color for having the vehicle of blue license plate in identification image simultaneously.The disclosure can identify the color of blue license plate by the processing to picture frame, can not identify blue license plate color when to solving the problems, such as in the related technology using infrared light compensating lamp.
Description
Technical field
This application involves the recognition methods of color recognizing for vehicle id field more particularly to a kind of blue license plate color and devices.
Background technique
With the development of monitoring technology, the application of road monitoring is carried out on night road based on white light light compensating lamp and video camera
It is more and more.White light can make license plate develop the color well, therefore be convenient for the identification of license plate color, but the concealment of white light compensating lamp
Difference, and the sight of driver can be interfered, lead to traffic safety hidden danger.Therefore, infrared light compensating lamp+video camera scheme meet the tendency of and
Raw, the program solves the problems, such as light pollution and concealment, however since black and white tone is presented in license plate under infrared light compensating lamp,
It will lead to the problem of can not identifying blue license plate color using infrared light compensating lamp.
Summary of the invention
To overcome the problems in correlation technique, present disclose provides the recognition methods of blue license plate color and devices.
According to the first aspect of the embodiments of the present disclosure, a kind of recognition methods of blue license plate color is provided, camera shooting is applied to
Machine, the video camera include multichannel filter, and through the multichannel filter optical filtering after it is photosensitive near infrared light and infrared light
Sensor；The multichannel filter is near infrared light light transmission, it is desirable that the transmitance in the channel R is greater than the transmitance of channel B, institute
The multiple channels for stating multichannel filter are identical to the light transmittance of infrared light, and the recognition methods of the blue license plate color includes:
When illumination brightness is lower than given luminance, light filling source is opened；The light filling source include near-infrared supplementary lighting sources and
Infrared supplementary lighting sources；
The operating mode for switching the double filter IR-cut of infrared ray of the video camera, so that visible light and infrared light lead to simultaneously
It crosses；
Near-infrared supplementary lighting sources and infrared supplementary lighting sources open the license plate for having the vehicle of blue license plate in identification image simultaneously
Color.
Optionally, when the video camera is to capture camera, the near-infrared supplementary lighting sources and infrared supplementary lighting sources are simultaneously
It opens, identifies that the license plate color for having the vehicle of blue license plate in image includes:
When detecting the target vehicle, based on the near-infrared supplementary lighting sources and infrared supplementary lighting sources in the light filling source
It carries out quick-fried sudden strain of a muscle light filling to capture target vehicle, and the uncorrected data picture frame for the target vehicle captured is converted to
RGB image positions the license plate area in the RGB image, and saves after carrying out color enhancement to license plate area；When being not detected
When the target vehicle, the infrared supplementary lighting sources in the light filling source are only opened.
Optionally, when the video camera is non-candid photograph camera, the near-infrared supplementary lighting sources and infrared supplementary lighting sources are same
Shi Kaiqi identifies that the license plate color for having the vehicle of blue license plate in image includes:
The near-infrared supplementary lighting sources and infrared supplementary lighting sources are always on light filling simultaneously, acquire live uncorrected data picture frame and turn
It is changed to RGB image, positions the license plate area in the RGB image, identifying has the vehicle of the vehicle of blue license plate in the RGB image
Board color, and RGB image described after processing is converted into YUV image, and carry out live stream transmission and preservation.Optionally, described
The license plate area positioned in the RGB image includes:
Resolution ratio based on the RGB image establishes corresponding initial calculation matrix；
Maximum value in tri- components of RGB of each pixel of the RGB image is subtracted into minimum value, and judges to be calculated
Difference whether be greater than preset threshold；
When the difference is greater than the preset threshold, by element corresponding with the pixel in the initial calculation matrix
Value be set to 1；It, will be corresponding with the pixel in the matrix when the difference is less than or equal to the preset threshold
The value of element is set to 0, the calculating matrix that obtain that treated；
By three matrixes being made of the R component of the RGB image, G component and B component respectively with the calculating matrix into
Row dot product calculates, and is positioned according to dot product calculated result to license plate.
It is optionally, described that color enhancement is carried out to license plate area, comprising:
The RGB image after dot product is calculated is converted to HSV image；
Enhance the saturation degree of the HSV image, to complete to be directed to the color enhancement of the license plate area.
Optionally, the infrared supplementary lighting sources include the first infrared supplementary lighting sources and the second infrared supplementary lighting sources, wherein institute
The central wavelength for stating the first infrared supplementary lighting sources is different from the central wavelength of the second infrared supplementary lighting sources.
According to the second aspect of an embodiment of the present disclosure, a kind of identification device of blue license plate color is provided, described device is answered
For video camera, the video camera includes multichannel filter, and near infrared light and red after multichannel filter optical filtering
The sensor of outer light sensation light；The multichannel filter is near infrared light light transmission, it is desirable that the transmitance in the channel R is greater than channel B
Multiple channels of transmitance, the multichannel filter are identical to the light transmittance of infrared light, the identification dress of the blue license plate color
It sets and includes:
Opening module, for opening light filling source when illumination brightness is lower than given luminance；The light filling source includes near-infrared
Supplementary lighting sources and infrared supplementary lighting sources；
Switching module, the operating mode of the double filter IR-cut of infrared ray for switching the video camera, so that visible light
Pass through simultaneously with infrared light；
Identification module, being opened in identification image simultaneously for near-infrared supplementary lighting sources and infrared supplementary lighting sources has blue license plate
Vehicle license plate color.
Optionally, when the video camera is to capture camera, the identification module includes:
First detection sub-module, for being mended based on the near-infrared in the light filling source when detecting the target vehicle
Radiant and infrared supplementary lighting sources carry out quick-fried sudden strain of a muscle light filling and capture to target vehicle, and by the target vehicle captured
Uncorrected data picture frame is converted to RGB image, positions the license plate area in the RGB image, and carry out color increasing to license plate area
It is saved after strong；When the target vehicle is not detected, the infrared supplementary lighting sources in the light filling source are only opened.
Optionally, when the video camera is non-candid photograph camera, the identification module includes:
Second detection sub-module is always on light filling simultaneously for the near-infrared supplementary lighting sources and infrared supplementary lighting sources, acquires
Live uncorrected data picture frame is simultaneously converted to RGB image, positions the license plate area in the RGB image, identifies in the RGB image
There is the license plate color of the vehicle of blue license plate, and RGB image described after processing is converted into YUV image, and carry out live stream biography
Defeated and preservation.
Optionally, first detection sub-module or the second detection sub-module are specifically used for:
Resolution ratio based on the RGB image establishes corresponding initial calculation matrix；
Maximum value in tri- components of RGB of each pixel of the RGB image is subtracted into minimum value, and judges to be calculated
Difference whether be greater than preset threshold；
When the difference is greater than the preset threshold, by element corresponding with the pixel in the initial calculation matrix
Value be set to 1；It, will be corresponding with the pixel in the matrix when the difference is less than or equal to the preset threshold
The value of element is set to 0, the calculating matrix that obtain that treated；
By three matrixes being made of the R component of the RGB image, G component and B component respectively with the calculating matrix into
Row dot product calculates, and is positioned according to dot product calculated result to license plate.
Optionally, first detection sub-module is specifically used for:
The RGB image after the dot product is calculated is converted to HSV image；
Enhance the saturation degree of the HSV image, to complete to be directed to the color enhancement of the license plate area.
Optionally, the infrared supplementary lighting sources include the first infrared supplementary lighting sources and the second infrared supplementary lighting sources, wherein institute
The central wavelength for stating the first infrared supplementary lighting sources is different from the central wavelength of the second infrared supplementary lighting sources.
As seen from the above-described embodiment, by illumination brightness be lower than given luminance in the case where open the light filling source and
IR-cut is switched to visible light and infrared luminous energy while the operating mode passed through, so that the video camera is in near-infrared light filling light
There is the license plate color of the vehicle of blue license plate when source and infrared supplementary lighting sources are opened simultaneously in identification image, to solve related skill
The problem of can not identifying blue license plate color when infrared light compensating lamp is used in art.
It should be understood that above general description and following detailed description be only it is exemplary and explanatory, not
The disclosure can be limited.
Detailed description of the invention
The drawings herein are incorporated into the specification and forms part of this specification, and shows the implementation for meeting the disclosure
Example, and together with specification for explaining the principles of this disclosure.
Fig. 1 is the flow chart for the recognition methods that the disclosure one implements a kind of blue license plate color exemplified.
Fig. 2 is a kind of sensitometric curve of the sensor to different wave length of video camera.
Fig. 3 is the hardware block diagram of the device of the identification of blue license plate color in the embodiment of the present disclosure.
Fig. 4 is a kind of disclosure block diagram of the identification device of blue license plate color shown according to an exemplary embodiment.
Specific embodiment
Example embodiments are described in detail here, and the example is illustrated in the accompanying drawings.Following description is related to
When attached drawing, unless otherwise indicated, the same numbers in different drawings indicate the same or similar elements.Following exemplary embodiment
Described in embodiment do not represent all implementations consistent with this disclosure.On the contrary, they be only with it is such as appended
The example of the consistent device and method of some aspects be described in detail in claims, the disclosure.
In the related art, it generallys use infrared light compensating lamp and light filling is carried out to video camera, there is no light pollution using infrared light
And the characteristic that concealment is strong, to solve the problems, such as light pollution caused by carrying out light filling video camera using white light light compensating lamp.Then,
Since black and white tone is presented in license plate under infrared light compensating lamp, will cause using infrared light compensating lamp can not identify blue license plate face
The problem of color.
In the embodiments of the present disclosure, can by illumination brightness be lower than given luminance in the case where open light filling source and
IR-cut is switched to visible light and infrared luminous energy while the operating mode passed through so that video camera in near-infrared supplementary lighting sources and
There is the license plate color of the vehicle of blue license plate when infrared supplementary lighting sources are opened simultaneously in identification image, to solve in the related technology
The problem of using that can not identify blue license plate color when infrared light compensating lamp.
It is the flow chart for the recognition methods that the disclosure one implements a kind of blue license plate color exemplified, the reality referring to Fig. 1
Example is applied applied to video camera, comprising the following steps:
Step 101: when illumination brightness is lower than given luminance, opening light filling source；The light filling source includes near-infrared light filling
Light source and infrared supplementary lighting sources.
Above-mentioned video camera may include multichannel filter, and near infrared light and infrared light after the optical filtering of multichannel filter
Photosensitive sensor；Wherein, it when selecting sensor for video camera, needs to require the sensor that can identify near-infrared light filling light
Source and infrared supplementary lighting sources.Multiple channels of above-mentioned multichannel filter need the transmitance near infrared light different, wherein more
The channel R of channel filter is greater than transmitance of the channel B near infrared light, the purpose done so to the transmitance of near infrared light
Primarily to allow R component to pass through as far as possible while inhibiting passing through for B component, and multiple channels pair of the multichannel filter
The light transmittance of infrared light is identical.
During being monitored using video camera to road, when illumination brightness is lower than given luminance, it can open
Light filling source.Wherein, in this example, light filling source may include near-infrared supplementary lighting sources and infrared supplementary lighting sources.In light filling source
Introducing near-infrared supplementary lighting sources may insure normally to identify blue license plate color；Infrared light filling light is introduced in light filling source
Source can further increase light filling effect and concealment on the basis of normally identify to blue license plate color.Wherein,
For same video camera, when in the near-infrared supplementary lighting sources and infrared supplementary lighting sources fetching wavelength range in light filling source
When wavelength value, above-mentioned video camera can obtain preferable picture frame in light filling source light filling, so as to preferably identify blue
The color of license plate.The chip used due to different video cameras is different, when near-infrared supplementary lighting sources in light filling source and red
When outer supplementary lighting sources take the wavelength value in wave-length coverage corresponding with above-mentioned video camera, the above-mentioned available preferable figure of video camera
As frame.
It should be noted that above-mentioned given luminance depending on environment or can be customized by the user setting, such as 10LUX
(lux), the disclosure does not limit this.
It in this example, can for the near-infrared supplementary lighting sources in light filling source and when infrared supplementary lighting sources designated wavelength range
The wavelength model of near-infrared supplementary lighting sources in light filling source is determined to the sensitometric curve of different wave length with the sensor in conjunction with video camera
It encloses.
Referring to fig. 2, Fig. 2 is a kind of sensitometric curve of the sensor to different wave length of video camera.In conjunction with Fig. 2 it is found that wavelength
Range is the near infrared light between 750 nanometers to 770 nanometers, usually insensitive to human eye, smaller to the interference of driver, and
Wavelength is located at the near infrared light within the scope of this, and sensor can preferably differentiate the RGB component in color image, thus more just
The color of blue license plate is restored during image processing in video camera.
Therefore, in a kind of embodiment shown, 750 nanometers to 770 nanometers can be chosen and be used as near-infrared light filling light
The designated wavelength range in source.
It in this example,, can be in order to improve light filling amount when being near-infrared supplementary lighting sources after specifying wave-length coverage
Infrared supplementary lighting sources are added in light filling source.The infrared supplementary lighting sources may include specified wavelength the first infrared supplementary lighting sources and
Second infrared supplementary lighting sources, wherein the specified wavelength of the specified wavelength of the first infrared supplementary lighting sources and the second infrared supplementary lighting sources
It is different.
Continuing with referring to fig. 2, the infrared light that central wavelength is 830 nanometers is usually insensitive to human eye, does to driver
Disturb smaller, and the sensor of video camera can be preferably photosensitive to its, so that the picture frame captured has higher brightness.
It therefore, can be using the infrared light that central wavelength is 830 nanometers as designated wavelength range in a kind of embodiment shown
First feux rouges supplementary lighting sources.
However, in practical applications, central wavelength is that 830 nanometers of infrared light usually has slight red aeration phenomenon, i.e.,
It will appear the feux rouges that can be perceived by the human eye around light.Therefore, in order to improve the concealment of the infrared light and further increase
Light filling effect may be incorporated into the second infrared supplementary lighting sources of specified wavelength in this example.
In the embodiment shown, the infrared light that central wavelength is 980 nanometers can be chosen to be above-mentioned second
Infrared supplementary lighting sources.Central wavelength is that 980 nanometers of infrared light is insensitive to human eye, without red aeration phenomenon, therefore in infrared benefit
The infrared light that central wavelength is 980 nanometers is added in radiant, the concealment of infrared supplementary lighting sources can be improved, to entire road
Scene carries out light filling, reduces the luminance difference of license plate and background, so that license plate is not easy overexposure.It is received simultaneously using 830 nanometers and 980
The infrared light of rice is compared with being used only 830 nanometers, and under the scene for requiring to issue brightness, the former is due to there is 980 nano wave lengths
Infrared light mixing, red aeration phenomenon is much smaller.
It should be noted that the three of the above light source in light filling source can be placed in the same light filling unit when realizing,
Can also be separated, in this example without being particularly limited to.
Step 102: switching the operating mode of the double filter IR-cut of infrared ray of the video camera, so that visible light and infrared
Light passes through simultaneously.
In this example, after opening above-mentioned light filling source, video camera can switch IR-cut, and (Infrared cut, infrared ray are double
Filter) operating mode so that visible light and infrared light pass through simultaneously, wherein the filter of the IR-cut of video camera can be more
Channel filter.Herein it should be noted that step 101 and step 102 sequence interchangeable, be not necessarily to by the present embodiment to
Sequence out executes.
When the IR-cut of video camera is switched to visible light and infrared luminous energy while the operating mode passed through, above-mentioned specified wave
The near infrared light of long range can also pass through the multichannel filter.In this example, for the ease of the reduction to blue license plate color,
It multiple channels of the multichannel filter can be different to the transmitance of the near infrared light of designated wavelength range.
Continuing with referring to fig. 2, when the wavelength of near infrared light is between 750 nanometers to 770 nanometers, the sensing of video camera
Device is different to the photosensitive degree of the RGB component of near infrared light.In order to enable sensor has B component and R component after photosensitive
There is different gray values, convenient for the reduction to blue license plate color, selects the multichannel filter to the B of the near-infrared supplementary lighting sources
The transmitance in channel is less than 15%；80% is greater than to the transmitance in the channel R of the near-infrared supplementary lighting sources；To the near-infrared light filling
The component transmitance of the Gr and Gb of light source are greater than 20% and less than 50%.
In this example, the infrared light of above-mentioned designated wavelength range can pass through above-mentioned multichannel filter.As shown in Figure 2, when
When the wavelength of infrared light is located at above-mentioned designated wavelength range, the photosensitive degree of the sensor of video camera to the RGB component of infrared light
It is approximately uniform.It is grey for the ease of the restore-zone that reflecting rate in the picture frame that will capture is less than license plate, therefore the multi-pass
Road filter is the smaller the better to the transmitance difference of the infrared light, is advisable with difference less than 5%.
Step 103: when there is target vehicle, obtaining the picture frame including the target vehicle, and based on the institute got
State the color that picture frame identifies blue license plate.
When there is target vehicle, video camera can obtain the picture frame of target vehicle in the case where the light filling of light filling source, so
The color of blue license plate is identified based on the picture frame afterwards.
In this example, video camera can be candid photograph camera.When video camera is to capture camera, mesh can have first been detected whether
Mark vehicle.When detecting target vehicle, the near-infrared supplementary lighting sources and infrared supplementary lighting sources in light filling source can be opened simultaneously,
Video camera can based in light filling source near-infrared supplementary lighting sources and infrared supplementary lighting sources carry out quick-fried sudden strain of a muscle light filling to target vehicle into
Row is captured, and the picture frame for the target vehicle captured is converted to RGB image, carries out demosaicing to the RGB image
Demosaic and AWB (Automatic white balance, automatic white balance) processing, since the treatment process is existing skill
Art, therefore details are not described herein for the disclosure；When target vehicle is not detected, the infrared light filling light in light filling source can be only opened
Source.
Capturing camera is usually to be grabbed when there is the target objects such as vehicle or people to enter monitoring range by quick-fried sudden strain of a muscle light filling mode moment
Clap the clear image of target object.Such as crossroad is for shooting the bayonet camera to make a dash across the red light.
After uncorrected data picture frame after candid photograph is converted to RGB image, video camera can position the license plate area in RGB image
Domain, and saved after carrying out color enhancement to license plate area.
In one embodiment, the process positioned to the license plate area in RGB image can be with are as follows:
Video camera establishes corresponding initial calculation matrix based on the resolution ratio of RGB image, wherein in initial calculation matrix
The initial value of each element can be set to 0, it is then possible to by the maximum value in tri- components of RGB of each pixel of RGB image
It subtracts minimum value, and judges whether the difference being calculated is greater than preset threshold, it, can will be first when difference is greater than preset threshold
The value of element corresponding with the pixel is set to 1 in beginning calculating matrix；It, can will be initial when difference is less than or equal to preset threshold
The value of element corresponding with the pixel is set to 0 in calculating matrix.After the value of pixel each in initial calculation matrix is provided with,
Calculating matrix after can be processed.Then three squares that can will be made of the R component of RGB image, G component and B component
Battle array carries out dot product calculating with above-mentioned calculating matrix respectively, and is positioned according to dot product calculated result to license plate.
In the one embodiment shown, it is assumed that the resolution ratio of RGB image is 2*2, the corresponding R component of each pixel, G
The value of component and B component can be as shown in table 1:
| The position of RGB image | R component value | G component value | B component value |
| {1,1} | 2 | 10 | 6 |
| {1,2} | 1 | 1 | 1 |
| {2,1} | 20 | 10 | 12 |
| {2,2} | 2 | 2 | 12 |
Table 1
At this point, video camera can establish the initial calculation square of a 2*2 based on the resolution ratio of RGB image as shown in Table 1
Battle array mask, wherein the initial value of each element in initial calculation matrix mask can be 0.It is then possible to by the every of RGB image
Maximum value in tri- components of RGB of a pixel subtracts minimum value.
It, can be with after the maximum value of tri- components of RGB of each pixel of RGB image as shown in Table 1 is subtracted minimum value
Obtain difference as shown in Table 2:
Table 2
It, can be with when difference is greater than preset threshold it is then possible to judge whether the difference being calculated is greater than preset threshold
The value of element corresponding with the pixel in initial calculation matrix mask is set to 1；It, can when difference is less than or equal to preset threshold
The value of element corresponding with the pixel in initial calculation matrix mask is set to 0.
Assuming that preset threshold is 6, then it is available after being provided with the value of each element in initial calculation matrix mask
Calculating matrix mask as shown in table 3:
| The position of Mask matrix | Element value |
| {1,1} | 1 |
| {1,2} | 0 |
| {2,1} | 1 |
| {2,2} | 1 |
Table 3
It is then possible to by three matrixes being made of the R component of RGB image, G component and B component respectively with above-mentioned matrix
Carry out dot product calculating.
As shown in Table 1, the R component of RGB image may be constructed matrix as shown in table 4, and the G component of RGB image can be with structure
At matrix as shown in table 5, the B component of RGB image may be constructed matrix as shown in table 6:
| The position of RGB image | R component value |
| {1,1} | 2 |
| {1,2} | 1 |
| {2,1} | 20 |
| {2,2} | 2 |
Table 4
| The position of RGB image | G component value |
| {1,1} | 10 |
| {1,2} | 1 |
| {2,1} | 10 |
| {2,2} | 2 |
Table 5
| The position of RGB image | B component value |
| {1,1} | 6 |
| {1,2} | 1 |
| {2,1} | 12 |
| {2,2} | 12 |
Table 6
After three matrixes and calculating matrix mask as shown in table 3 as shown in table 4, table 5 and table 6 are done dot product calculating,
Available matrix as shown in table 7:
| The position of Mask matrix | R component value | G component value | B component value |
| {1,1} | 2 | 10 | 6 |
| {1,2} | 0 | 0 | 0 |
| {2,1} | 20 | 10 | 12 |
| {2,2} | 2 | 2 | 12 |
Table 7
The corresponding R component of each pixel, G component and B component value RGB image as shown in Table 1 after above-mentioned processing,
When the value of the corresponding R component of its each pixel, G component and B component can be as shown in table 7, the license plate area of RGB image can be shown
Show slight blue, non-license plate area can be shown as black.At this point it is possible to according to RGB image as shown in table 7 to license plate into
Row positioning.After completing to the positioning of license plate, the license plate color in RGB image after can calculating dot product is reinforced.
After completing to the positioning of license plate, the license plate color in RGB image after can calculating dot product is reinforced, one
In a embodiment, the process for carrying out color reinforcement to license plate area can be with are as follows:
RGB image after first dot product is calculated is converted to HSV image, then, enhances the saturation degree of the HSV image, with complete
At the color enhancement for being directed to license plate area.Wherein it is possible to enhance HSV figure by the way that the S component value in HSV image is set to 1
The saturation degree of picture.
In the one embodiment shown, the process that color is reinforced is specifically as follows:
RGB image after first dot product is calculated is converted to HSV image, by the corresponding R component of each pixel, G component and B points
After the value of amount RGB image as shown in table 7 is converted to HSV image, the corresponding H component of each pixel of the HSV image after conversion,
The value of S component and V component can be as shown in table 8:
| The position of Mask matrix | H component value | S component value | V component value |
| {1,1} | 150 | 0.8 | 10 |
| {1,2} | 0 | 0 | 0 |
| {2,1} | 348 | 0.5 | 20 |
| {2,2} | 240 | 0.83 | 12 |
Table 8
It should be noted that being the prior art by the process that RGB image is converted to HSV image, the disclosure is no longer superfluous herein
It states.
After RGB image is converted to HSV image, the S component in HSV image can be set to 1, when by above-mentioned HSV image
S component when being set to 1, the value of the corresponding H component of available each pixel, S component and V component HSV figure as shown in table 9
Picture:
| The position of Mask matrix | H component value | S component value | V component value |
| {1,1} | 150 | 1 | 10 |
| {1,2} | 0 | 1 | 0 |
| {2,1} | 348 | 1 | 20 |
| {2,2} | 240 | 1 | 12 |
Table 9
After the completion of the S component modification in image, modified HSV image can be converted into RGB image.By each picture
RGB figure after the value of the corresponding H component of element, S component and V component HSV image as shown in table 9 is converted into RGB image, after conversion
The value of the corresponding R component of each pixel of picture, G component and B component can be as shown in table 10:
| The position of Mask matrix | R component value | G component value | B component value |
| {1,1} | 0 | 10 | 5 |
| {1,2} | 0 | 0 | 0 |
| {2,1} | 20 | 0 | 4 |
| {2,2} | 0 | 0 | 12 |
Table 10
In conjunction with table 7 and table 10 it is found that the B component value of RGB image is relative to R component value or G after color reinforcement processing
Component value is increased, i.e., the blue portion in RGB image is enhanced.
It should be noted that being the prior art by the process that HSV image is converted to RGB image, the disclosure is no longer superfluous herein
It states.
After above-mentioned processing, the color of the license plate area in RGB image is enhanced, can show relatively clear indigo plant
Color.
In this example, video camera may be non-candid photograph camera.When video camera is non-candid photograph camera, light filling can be based on
Source be always on light filling acquisition live image frame, then handles collected live image frame for RGB image, and by the RGB
Image is based on yuv format and carries out live stream transmission.
Here non-candid photograph camera refers mainly to public security system used in the camera shooting of the regions such as cell, crossing shooting monitoring video
Machine.
Wherein, it should be noted that when carrying out live stream transmission based on yuv format, can retain in image simultaneously
Luminance component Y and color difference components UV, so that blue license plate part can show blue, non-license plate portion in the image of transmission
Colour can not be shown by dividing.
In one embodiment, the vehicle in the non-live image frame for capturing camera acquisition can be actually blue vehicle,
Since the body portion of vehicle does not smear more reflectorized material equally just like license plate part, license plate part be typically due to by
Specially treated, reflecting rate can reach 90% or more, therefore, which be passed through in the image that above-mentioned processing obtains,
Only blue license plate part can show relatively clear blue.
In the embodiments of the present disclosure, can by illumination brightness be lower than given luminance in the case where open light filling source and
IR-cut is switched to visible light and infrared luminous energy while the operating mode passed through so that video camera in near-infrared supplementary lighting sources and
There is the license plate color of the vehicle of blue license plate when infrared supplementary lighting sources are opened simultaneously in identification image, to solve in the related technology
The problem of using that can not identify blue license plate color when infrared light compensating lamp.
Based on the inventive concept same with the above method, the embodiment of the invention also provides the identification of blue license plate color dresses
The identification device of the embodiment set, the blue license plate color can be applied on video camera.Wherein, the knowledge of the blue license plate color
Other device can also be realized by software realization by way of hardware or software and hardware combining.Taking software implementation as an example,
It is by the processor where it, by computer corresponding in nonvolatile memory as the device on a logical meaning
Program instruction is read into memory what operation was formed.It is blue in the embodiment of the present disclosure as shown in table 3 for application
The hardware block diagram of the device of the identification of license plate color, in addition to processor shown in Fig. 3, network interface, memory and it is non-easily
It can also include other hardware, such as photographic device, the forwarding chip for being responsible for processing message outside the property lost memory.
As shown in figure 4, Fig. 4 is a kind of disclosure identification dress of blue license plate color shown according to an exemplary embodiment
The block diagram set, described device include: opening module 410, switching module 420 and identification module 430.
Wherein, opening module 410, for opening light filling source when illumination brightness is lower than given luminance；The light filling source packet
Include near-infrared supplementary lighting sources and infrared supplementary lighting sources；
Switching module 420, the operating mode of the double filter IR-cut of infrared ray for switching the video camera, so that visible
Light and infrared light pass through simultaneously；
Identification module 430 is opened simultaneously for near-infrared supplementary lighting sources and infrared supplementary lighting sources, identifies in image there is blue
The license plate color of the vehicle of license plate.
In an optional implementation, when the video camera is to capture camera, the identification module 430 be can wrap
It includes and (is not shown in Fig. 4):
First detection sub-module 431, for when detecting the target vehicle, based on the near-infrared in the light filling source
Supplementary lighting sources and infrared supplementary lighting sources carry out the target vehicle that quick-fried sudden strain of a muscle light filling is captured target vehicle, and will be captured
Uncorrected data picture frame be converted to RGB image, position the license plate area in the RGB image, and color is carried out to license plate area
It is saved after enhancing；When the target vehicle is not detected, the infrared supplementary lighting sources in the light filling source are only opened.
In another optional implementation, when the video camera is non-candid photograph camera, the identification module 430 can
To include (being not shown in Fig. 4):
Second detection sub-module 432 is always on light filling simultaneously for the near-infrared supplementary lighting sources and infrared supplementary lighting sources, adopts
Collect live uncorrected data picture frame and be converted to RGB image, positions the license plate area in the RGB image, identify the RGB image
In have blue license plate vehicle license plate color, and RGB image described after processing is converted into YUV image, and carry out live stream
Transmission and preservation.
In another optional implementation, the detection sub-module 431 or 432 can be specifically used for:
Resolution ratio based on the RGB image establishes corresponding initial calculation matrix；
Maximum value in tri- components of RGB of each pixel of the RGB image is subtracted into minimum value, and judges to be calculated
Difference whether be greater than preset threshold；
When the difference is greater than the preset threshold, by element corresponding with the pixel in the initial calculation matrix
Value be set to 1；It, will be corresponding with the pixel in the matrix when the difference is less than or equal to the preset threshold
The value of element is set to 0, the calculating matrix that obtain that treated；
By three matrixes being made of the R component of the RGB image, G component and B component respectively with the calculating matrix into
Row dot product calculates, and is positioned according to dot product calculated result to license plate.
In another optional implementation, first detection sub-module 431 can be specifically used for:
The RGB image after the dot product is calculated is converted to HSV image；
Enhance the saturation degree of the HSV image, to complete to be directed to the color enhancement of the license plate area.
In another optional implementation, the infrared supplementary lighting sources include that the first infrared supplementary lighting sources and second are red
Outer supplementary lighting sources, wherein the central wavelength of the first infrared supplementary lighting sources and the central wavelength of the second infrared supplementary lighting sources are not
Together.
As seen from the above-described embodiment, can by illumination brightness be lower than given luminance in the case where open light filling source and
IR-cut is switched to visible light and infrared luminous energy while the operating mode passed through so that video camera in near-infrared supplementary lighting sources and
There is the license plate color of the vehicle of blue license plate when infrared supplementary lighting sources are opened simultaneously in identification image, to solve in the related technology
The problem of using that can not identify blue license plate color when infrared light compensating lamp.
Those skilled in the art after considering the specification and implementing the invention disclosed here, will readily occur to its of the disclosure
Its embodiment.The disclosure is intended to cover any variations, uses, or adaptations of the disclosure, these modifications, purposes or
Person's adaptive change follows the general principles of this disclosure and including the undocumented common knowledge in the art of the disclosure
Or conventional techniques.The description and examples are only to be considered as illustrative, and the true scope and spirit of the disclosure are by following
Claim is pointed out.
It should be understood that the present disclosure is not limited to the precise structures that have been described above and shown in the drawings, and
And various modifications and changes may be made without departing from the scope thereof.The scope of the present disclosure is only limited by the accompanying claims.
The foregoing is merely the preferred embodiments of the disclosure, not to limit the disclosure, all essences in the disclosure
Within mind and principle, any modification, equivalent substitution, improvement and etc. done be should be included within the scope of disclosure protection.
Claims (10)
1. a kind of recognition methods of blue license plate color, is applied to video camera, the video camera includes multichannel filter, Yi Jijing
Multichannel filter sensor photosensitive near infrared light and infrared light after filtering；It is characterized in that, the multichannel filter
To near infrared light light transmission, it is desirable that the transmitance in the channel R is greater than the transmitance of channel B, multiple channels of the multichannel filter
Identical to the light transmittance of infrared light, the recognition methods of the blue license plate color includes:
When illumination brightness is lower than given luminance, light filling source is opened；The light filling source includes near-infrared supplementary lighting sources and infrared
Supplementary lighting sources；
The operating mode for switching the double filter IR-cut of infrared ray of the video camera, so that visible light and infrared light pass through simultaneously；
When the video camera is to capture camera, near-infrared supplementary lighting sources and infrared supplementary lighting sources are opened identify have in image simultaneously
The license plate color of the vehicle of blue license plate includes:
When detecting target vehicle, based in the light filling source near-infrared supplementary lighting sources and infrared supplementary lighting sources carry out quick-fried sudden strain of a muscle
Light filling captures target vehicle, and the uncorrected data picture frame for the target vehicle captured is converted to RGB image, fixed
License plate area in the RGB image of position, and saved after carrying out color enhancement to license plate area；When the target carriage is not detected
When, only open the infrared supplementary lighting sources in the light filling source.
2. the method according to claim 1, wherein when the video camera be non-candids photograph camera when, it is described closely it is red
Outer supplementary lighting sources and infrared supplementary lighting sources are opened simultaneously, identify that the license plate color for having the vehicle of blue license plate in image includes:
The near-infrared supplementary lighting sources and infrared supplementary lighting sources are always on light filling simultaneously, acquire live uncorrected data picture frame and are converted to
RGB image positions the license plate area in the RGB image, and identifying has the license plate face of the vehicle of blue license plate in the RGB image
Color, and RGB image described after processing is converted into YUV image, and carry out live stream transmission and preservation.
3. method according to claim 1 or 2, which is characterized in that the license plate area packet in the positioning RGB image
It includes:
Resolution ratio based on the RGB image establishes corresponding initial calculation matrix；
Maximum value in tri- components of RGB of each pixel of the RGB image is subtracted into minimum value, and judges the difference being calculated
Whether value is greater than preset threshold；
When the difference is greater than the preset threshold, by the value of element corresponding with the pixel in the initial calculation matrix
It is set to 1；When the difference is less than or equal to the preset threshold, by the element corresponding with the pixel in the matrix
Value be set to 0, the calculating matrix that obtain that treated；
Three matrixes being made of the R component of the RGB image, G component and B component are carried out a little with the calculating matrix respectively
Multiply calculating, and license plate is positioned according to dot product calculated result.
4. according to the method described in claim 3, it is characterized in that, carrying out color enhancement to license plate area, comprising:
The RGB image after dot product is calculated is converted to HSV image；
Enhance the saturation degree of the HSV image, to complete to be directed to the color enhancement of the license plate area.
5. the method according to claim 1, wherein the infrared supplementary lighting sources include the first infrared supplementary lighting sources
With the second infrared supplementary lighting sources, wherein in the central wavelength of the first infrared supplementary lighting sources and the second infrared supplementary lighting sources
Cardiac wave is long different.
6. a kind of identification device of blue license plate color, is applied to video camera, the video camera includes multichannel filter, Yi Jijing
Multichannel filter sensor photosensitive near infrared light and infrared light after filtering；It is characterized in that, the multichannel filter
To near infrared light light transmission, it is desirable that the transmitance in the channel R is greater than the transmitance of channel B, multiple channels of the multichannel filter
Identical to the light transmittance of infrared light, the identification device of the blue license plate color includes:
Opening module, for opening light filling source when illumination brightness is lower than given luminance；The light filling source includes near-infrared light filling
Light source and infrared supplementary lighting sources；
Switching module, the operating mode of the double filter IR-cut of infrared ray for switching the video camera, so that visible light and red
Outer light passes through simultaneously；
Identification module, for when the video camera is to capture camera, near-infrared supplementary lighting sources and infrared supplementary lighting sources to be opened simultaneously
It opens and identifies that the license plate color for having the vehicle of blue license plate in image includes:
First detection sub-module, for when detecting target vehicle, based in the light filling source near-infrared supplementary lighting sources and
Infrared supplementary lighting sources carry out quick-fried sudden strain of a muscle light filling and capture to target vehicle, and by the uncorrected data figure for the target vehicle captured
As frame is converted to RGB image, the license plate area in the RGB image is positioned, and save after carrying out color enhancement to license plate area；
When the target vehicle is not detected, the infrared supplementary lighting sources in the light filling source are only opened.
7. device according to claim 6, which is characterized in that when the video camera is non-candid photograph camera, the identification
Module includes:
Second detection sub-module is always on light filling for the near-infrared supplementary lighting sources and infrared supplementary lighting sources simultaneously, and acquisition is live
Uncorrected data picture frame is simultaneously converted to RGB image, positions the license plate area in the RGB image, identifies in the RGB image there is indigo plant
The license plate color of the vehicle of color license plate, and RGB image described after processing is converted into YUV image, and carry out live stream transmission and
It saves.
8. device according to claim 6 or 7, which is characterized in that the detection sub-module is specifically used for:
Resolution ratio based on the RGB image establishes corresponding initial calculation matrix；
Maximum value in tri- components of RGB of each pixel of the RGB image is subtracted into minimum value, and judges the difference being calculated
Whether value is greater than preset threshold；
When the difference is greater than the preset threshold, by the value of element corresponding with the pixel in the initial calculation matrix
It is set to 1；When the difference is less than or equal to the preset threshold, by the element corresponding with the pixel in the matrix
Value be set to 0, the calculating matrix that obtain that treated；
Three matrixes being made of the R component of the RGB image, G component and B component are carried out a little with the calculating matrix respectively
Multiply calculating, and license plate is positioned according to dot product calculated result.
9. device according to claim 8, which is characterized in that the first detection sub-module is specifically used for:
The RGB image after the dot product is calculated is converted to HSV image；
Enhance the saturation degree of the HSV image, to complete to be directed to the color enhancement of the license plate area.
10. device according to claim 6, which is characterized in that the infrared supplementary lighting sources include the first infrared light filling light
Source and the second infrared supplementary lighting sources, wherein the central wavelength of the first infrared supplementary lighting sources and the second infrared supplementary lighting sources
Central wavelength is different.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610207212.6A CN105868753B (en) | 2016-04-05 | 2016-04-05 | The recognition methods of blue license plate color and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610207212.6A CN105868753B (en) | 2016-04-05 | 2016-04-05 | The recognition methods of blue license plate color and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105868753A CN105868753A (en) | 2016-08-17 |
| CN105868753B true CN105868753B (en) | 2019-10-18 |
Family
ID=56626971
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610207212.6A Active CN105868753B (en) | 2016-04-05 | 2016-04-05 | The recognition methods of blue license plate color and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105868753B (en) |
Families Citing this family (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111770281A (en) * | 2018-07-30 | 2020-10-13 | 华为技术有限公司 | Time division multiplexing supplementary lighting imaging device and method |
| CN109389111A (en) * | 2018-10-24 | 2019-02-26 | 浙江宇视科技有限公司 | Image acquisition and processing method, device and computer readable storage medium |
| CN109672828B (en) * | 2019-01-04 | 2021-09-07 | 深圳英飞拓科技股份有限公司 | Low-illumination lifting device and method based on light path white balance |
| CN110490042B (en) * | 2019-05-31 | 2022-02-11 | 杭州海康威视数字技术股份有限公司 | Face recognition device and entrance guard's equipment |
| CN110378289B (en) * | 2019-07-19 | 2023-05-16 | 王立之 | Reading and identifying system and method for vehicle identification code |
| CN111489558B (en) * | 2019-11-11 | 2022-05-20 | 深圳市海洋王照明工程有限公司 | License plate recognition method and system |
| CN113498237B (en) * | 2020-03-20 | 2023-03-28 | 杭州海康威视数字技术股份有限公司 | Driving current control method and mixed light supplement control method for multispectral light supplement lamp |
| CN111860539A (en) * | 2020-07-20 | 2020-10-30 | 济南博观智能科技有限公司 | License plate color recognition method, device and medium |
| CN112133101B (en) * | 2020-09-22 | 2021-11-26 | 杭州海康威视数字技术股份有限公司 | Method and device for enhancing license plate area, camera device, computing equipment and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN202217288U (en) * | 2011-07-21 | 2012-05-09 | 江南大学 | Time sharing multicolor light complement license plate identification system |
| CN202887451U (en) * | 2012-10-26 | 2013-04-17 | 青岛海信网络科技股份有限公司 | Infrared light and visible light filling blended electronic police system |
| CN103645594A (en) * | 2013-08-01 | 2014-03-19 | 广东本致数码科技有限公司 | Multispectral infrared surveillance camera supplementary lighting method |
| CN104966071A (en) * | 2015-07-03 | 2015-10-07 | 武汉烽火众智数字技术有限责任公司 | Infrared light supplement based night license plate detection and recognition method and apparatus |
-
2016
- 2016-04-05 CN CN201610207212.6A patent/CN105868753B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN202217288U (en) * | 2011-07-21 | 2012-05-09 | 江南大学 | Time sharing multicolor light complement license plate identification system |
| CN202887451U (en) * | 2012-10-26 | 2013-04-17 | 青岛海信网络科技股份有限公司 | Infrared light and visible light filling blended electronic police system |
| CN103645594A (en) * | 2013-08-01 | 2014-03-19 | 广东本致数码科技有限公司 | Multispectral infrared surveillance camera supplementary lighting method |
| CN104966071A (en) * | 2015-07-03 | 2015-10-07 | 武汉烽火众智数字技术有限责任公司 | Infrared light supplement based night license plate detection and recognition method and apparatus |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105868753A (en) | 2016-08-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105868753B (en) | The recognition methods of blue license plate color and device | |
| CN110519489B (en) | Image acquisition method and device | |
| CN107534735B (en) | Image processing method, device and the terminal of terminal | |
| CN105812674B (en) | A kind of color correct method, monitoring method and the device of signal lamp | |
| CN108055452A (en) | Image processing method, device and equipment | |
| CN105391953A (en) | Image-capturing method and image-capturing device | |
| CN109804619A (en) | Image processing apparatus, image processing method and camera | |
| CN110490187B (en) | License plate recognition device and method | |
| CN107077630A (en) | Transparent marking, the method for synthesizing and detecting transparent marking, clear mark and the method for synthesizing and detecting clear mark | |
| CN107292860A (en) | A kind of method and device of image procossing | |
| CN108712608A (en) | Terminal device image pickup method and device | |
| CN207491128U (en) | A kind of RGB+IR image capture devices | |
| CN108717691B (en) | Image fusion method and device, electronic equipment and medium | |
| CN110490811B (en) | Image noise reduction device and image noise reduction method | |
| CN107945135A (en) | Image processing method, device, storage medium and electronic equipment | |
| CN109191403A (en) | Image processing method and device, electronic equipment, computer readable storage medium | |
| CN108419028A (en) | Image processing method, device, computer readable storage medium and electronic equipment | |
| JP2017112401A (en) | Imaging device, apparatus and method for image processing, and program | |
| CN108024054A (en) | Image processing method, device and equipment | |
| WO2018145508A1 (en) | Image processing method and device | |
| CN105635532B (en) | imaging method, image sensor, imaging device and electronic device | |
| CN106534677A (en) | Image overexposure optimization method and device | |
| CN110493532A (en) | A kind of image processing method and system | |
| CN107920205B (en) | Image processing method, device, storage medium and electronic equipment | |
| CN106375316B (en) | A kind of method of video image processing and equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |