CN110532860A - The modulation of visible light bar code and recognition methods based on RGB LED lamp - Google Patents
The modulation of visible light bar code and recognition methods based on RGB LED lamp Download PDFInfo
- Publication number
- CN110532860A CN110532860A CN201910648924.5A CN201910648924A CN110532860A CN 110532860 A CN110532860 A CN 110532860A CN 201910648924 A CN201910648924 A CN 201910648924A CN 110532860 A CN110532860 A CN 110532860A
- Authority
- CN
- China
- Prior art keywords
- rgb led
- image
- modulation
- visible light
- bar code
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- 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
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/56—Extraction of image or video features relating to colour
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04B—TRANSMISSION
- H04B10/00—Transmission systems employing electromagnetic waves other than radio-waves, e.g. infrared, visible or ultraviolet light, or employing corpuscular radiation, e.g. quantum communication
- H04B10/11—Arrangements specific to free-space transmission, i.e. transmission through air or vacuum
- H04B10/114—Indoor or close-range type systems
- H04B10/116—Visible light communication
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04B—TRANSMISSION
- H04B10/00—Transmission systems employing electromagnetic waves other than radio-waves, e.g. infrared, visible or ultraviolet light, or employing corpuscular radiation, e.g. quantum communication
- H04B10/50—Transmitters
- H04B10/516—Details of coding or modulation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/12—Classification; Matching
Abstract
The invention discloses a kind of modulation of visible light bar code and recognition methods based on RGB LED lamp, this method comprises: in transmitting terminal, utilize PWM modulation, three pulse signals that input phase is poor, duty ratio, frequency are different, the red, green, blue lamp bead for controlling RGB LED respectively issue flicker frequency, the different light of brightness, the different RGB LED of realization imparting exclusive ID；In receiving end, RGB LED image is shot using CMOS camera, area, the fringe number, light and shade striped duty ratio feature of RGB LED image are extracted through image procossing；By extracted RGB LED feature, classifier is established using machine learning；The feature for extracting RGB LED image to be determined, judges generic using classifier, realizes the detection and identification of striations.This method simple possible can be realized by the way that existing lamps and lanterns combination smart phone is transformed, have a vast market value.
Description
Technical field
The present invention relates to LED vision-based detections and identification technology field, and in particular to a kind of based on the visible of RGB LED lamp
The modulation of striations code and recognition methods.
Background technique
Internet of Things is the important component of generation information technology, and the important development stage in " informationization " epoch.
Its English name is: " Internet of things (IoT) ".As its name suggests, Internet of Things is exactly the connected internet of object object.This
There is two layers of meaning: first, the core of Internet of Things and basis are still internet, it is extension and extension based on the internet
Network；Second, its user terminal extends and extends between any article and article, information exchange and communication are carried out, that is,
Object object mutually ceases.Internet of Things communicates cognition technology by Intellisense, identification technology and general fit calculation etc., is widely used in network
In fusion, also therefore it is referred to as the third wave that world information industry develops after computer, internet.Internet of Things is current
A kind of most most popular way of realization is exactly by assigning different two dimensional codes (QR Code).
The entrance that two dimensional code is applied as a kind of mobile phone, has been obtained and is widely applied, and becomes connection online and offline
(O2O) effective means.However two-dimensional code scanning is not only cumbersome, especially night and light condition bad situation outdoors
Under, two-dimensional code scanning is difficult to carry out；And transmission range is short, and it is few to carry information content.Therefore, market in urgent need one kind can satisfy specific
The mobile phone entry technique of environmental demand is as supplement, it is seen that optic communication (VLC) becomes preferred technology.Meanwhile it living in people
Today that rhythm is constantly promoted, many business premises attract the important means of the stream of people using lighting engineering as night, at present
There are many developers not only to rest on Lighting Design itself, and wish using lamps and lanterns as business entrances, in light in addition
Hold, attracts consumer.
Summary of the invention
The purpose of the present invention is to solve drawbacks described above in the prior art, provide a kind of based on RGB LED lamp
The modulation of visible light bar code and recognition methods.
The purpose of the present invention can be reached by adopting the following technical scheme that:
It is a kind of based on RGB LED lamp visible light bar code modulation and recognition methods, the visible light bar code modulation with
Recognition methods the following steps are included:
S1, in transmitting terminal, in the way of PWM modulation, three pulse signals that input phase is poor, duty ratio, frequency are different,
The red, green, blue lamp bead for controlling RGB LED respectively issue flicker frequency, brightness difference and there are the visible lights of phase difference
Signal is realized and assigns the exclusive ID of different RGB LED；
S2, striation print image is obtained, is mentioned through image procossing using CMOS camera shooting RGB LED image in receiving end
Take four the LED lamp area, bright fringe number, light and shade striped duty ratio and coefficient of phase difference features of RGB LED image；
S3, extracted RGB LED characteristic is trained using machine learning, establishes linear classifier；
S4, the feature for extracting RGB LED image to be determined judge affiliated class using the linear classifier that training finishes
Not, the detection and identification of striations are realized.
Further, the extraction process of the LED lamp area of RGB LED image is as follows in the step S2:
By RGB LED image binaryzation, the edge LED is detected by connected domain, obtains the radius of divided LED, calculates LED
Lamps and lanterns area.
Further, the extraction process of the bright fringe number of RGB LED image is as follows in the step S2:
The rectangular area of LED is partitioned into from RGB LED image, and according to isolated three picture of R, G, B triple channel；
By three picture binaryzations；
Three binaryzation pictures are subjected to Refinement operation, measure the white stripes number in picture.
Further, the extraction process of the light and shade striped duty ratio of RGB LED image is as follows in the step S2:
It is partitioned into the rectangular area of LED from RGB LED image, is taken in the middle position in the image level direction being partitioned into
One direction straight down, through the count vector of whole image, record the number of pixels that pixel value is 0 and 1 on this vector,
Obtain light and shade striped duty ratio.
Further, the process that coefficient of phase difference is calculated in the step S2 is as follows:
Three binaryzation pictures are placed under the same coordinate system, the middle position in image level direction takes a direction vertical
Downwards, through the vector of whole image, remember vertical seat corresponding to i-th of stripe centerline that the first picture intersects with this vector
It is designated as d1, the corresponding ordinate of i+1 stripe centerline that the second picture intersects with this vector is d2, third picture with
The corresponding ordinate of the i-th+2 stripe centerlines of this vector intersection is d3, calculating coefficient of phase difference is
Further, line is established using the extracted RGB LED characteristic of machine learning training in the step S3
Property classifier process is as follows:
Several optimal hyperlanes are designed in feature space by linear SVM (SVM), distinguish different samples
This, establishes linear classifier；Fisher algorithm makes sample after vector projection, as far as possible by finding several optimal vectors
By inhomogeneous sample separation, similar sample it is close as far as possible.
The present invention has the following advantages and effects with respect to the prior art:
(1) the invention proposes a kind of concepts of optical bar code, replace traditional two dimensional code, In using optical bar code dimension code technology
While illumination is realized with communicating integral, the information content for increasing the transmission range of information, having expanded transmission becomes a kind of new
Access network technology, the deficiency supplemented with conventional two-dimensional code under the conditions of dark, remote.
(2) present invention realizes the foundation of optical bar code using RGB LED, increases the characteristics of image that can be used to identify, effectively
Ground increases the number of LED-ID, has expanded the library LED-ID.
(3) machine learning, deep learning algorithm are applied in VLC system by the present invention, different from traditional simple number
The decoded mode of word, but the library LED-ID classifier is established using machine learning algorithm and can be realized under good training set
The detection of the precise and high efficiency LED-ID different from identification.
Detailed description of the invention
Fig. 1 is RGB LED-ID detection and identification schematic diagram in the embodiment of the present invention；
Fig. 2 is that part signal modulates schematic diagram in the embodiment of the present invention；
Fig. 3 is the schematic diagram for passing through image procossing Refinement operation in the embodiment of the present invention；
Fig. 4 is to separately win the schematic diagram for taking phase difference in the middle part of the embodiment of the present invention.
Specific embodiment
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with the embodiment of the present invention
In attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is
A part of the embodiment of the present invention, instead of all the embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art
Every other embodiment obtained without making creative work, shall fall within the protection scope of the present invention.
Embodiment
The present embodiment, which uses, discloses a kind of modulation of visible light bar code and recognition methods based on RGB LED lamp, Fig. 1
For a kind of schematic diagram of visible light bar code modulation and recognition methods based on RGB LED lamp.
Transmitting terminal in the present embodiment is made of STM32, DD311, RGB LED etc., carries out PWM modulation by STM32, is generated
The pulse signal of different cycles, duty ratio, Fig. 2 are partial modulation signal schematic representation, and the pulse signal of generation is inputted DD311 core
Piece, DD311 amplified signal, driving RGB LED issue the different high frequency light of frequency, duty ratio, RGB phase difference.
Receiving end in the present embodiment is the cmos sensor camera that routine use equipment carries, comprising: smart phone,
Laptop, tablet computer and palm equipment for surfing the net, multimedia equipment, wearable device or other kinds of terminal device,
Cmos sensor camera has roller shutter effect, and high frequency flicker light source is registered as stripe pattern.
As shown in Figure 1, a kind of modulation of visible light bar code and recognition methods based on RGB LED lamp, including walk as follows
It is rapid:
S1, in transmitting terminal, in the way of PWM modulation, three pulse signals that input phase is poor, duty ratio, frequency are different,
The red, green, blue lamp bead for controlling RGB LED respectively issue flicker frequency, brightness difference and there are the visible lights of phase difference
Signal realizes that the exclusive ID of the different RGB LED of imparting can be in the imperceptible feelings of human eye using high frequency RGB modulation system
Under condition, gives different LED and largely expand information, compared with using common white light LEDs to modulate, the ID number that greatly improves
Amount is applied in indoor visible light positioning system, can significantly increase system can area coverage, and light easy to control is photochromic, meets
The multiple functions such as the practical and colored amusement of white；
S2, striation print image is obtained, is mentioned through image procossing using CMOS camera shooting RGB LED image in receiving end
Take four the LED lamp area, bright fringe number, light and shade striped duty ratio features of RGB LED image, extracted characteristic quilt
For training classifier, or after classifier training is good, input differentiates；
Wherein, the extraction process of the LED lamp area of RGB LED image is as follows in step S2:
By RGB LED image binaryzation, the edge LED is detected by connected domain, obtains the radius of divided LED, calculates LED
Lamps and lanterns area, the information that area features contain are the distance between sensor and LED lamp, this is characterized in associated with fringe number
, distance is remoter, and fringe number is fewer, therefore has chosen two groups of parameters of fringe number and LED lamp area when selected characteristic simultaneously.
Wherein, the extraction process of the bright fringe number of RGB LED image is as follows in step S2:
The rectangular area of LED is partitioned into from RGB LED image, and according to isolated three picture of R, G, B triple channel；
By three picture binaryzations；
Three binaryzation pictures are subjected to Refinement operation, such as Fig. 3 measures the white stripes number in picture.
Wherein, the extraction process of the light and shade striped duty ratio of RGB LED image is as follows in step S2:
It is partitioned into the rectangular area of LED from RGB LED image, is taken in the middle position in the image level direction being partitioned into
One direction straight down, through the count vector of whole image, record the number of pixels that pixel value is 0 and 1 on this vector,
Obtain light and shade striped duty ratio, it is notable that striped quantity can be with LED lamp and distance change, but in distance change
During, light and shade striped duty ratio will not become, therefore simultaneous selection fringe number, LED lamp area and light and shade striped duty ratio
It is reasonable.
Wherein, the process that coefficient of phase difference is calculated in step S2 is as follows:
Three binaryzation pictures are placed under the same coordinate system, the middle position in image level direction takes a direction vertical
Downwards, through the vector of whole image, remember that the first picture intersects with this vector i-th is (quasi- for guarantee result under normal circumstances
Really, i > 4 are taken) ordinate corresponding to a stripe centerline is d1, in the i+1 striped that the second picture intersects with this vector
The corresponding ordinate of heart line is d2, the corresponding ordinate of the i-th+2 stripe centerlines that third picture intersects with this vector is
d3, calculating coefficient of phase difference isSuch as Fig. 4, increase this feature of phase coefficient, main purpose is significantly to increase
Add the number of identifiable LED ID.
S3, extracted RGB LED characteristic is trained using machine learning, establishes linear classifier；
Using the extracted RGB LED characteristic of machine learning training in step S3, linear classifier process is established
It is as follows:
Several optimal hyperlanes are designed in feature space by linear SVM (SVM), distinguish different samples
This, establishes linear classifier；Fisher algorithm makes sample after vector projection, as far as possible by finding several optimal vectors
The separation of inhomogeneous sample, similar sample is close as far as possible, two kinds of sorting algorithms used herein are classical linear
The models such as neural network also can be used in classifier algorithm, but under normal circumstances, in such a system, it can achieve using SVM
Best effect.
S4, the feature for extracting RGB LED image to be determined judge affiliated class using the linear classifier that training finishes
Not, the detection and identification of striations are realized.
In conclusion being communicated in the present embodiment on lamps and lanterns by modulation light output quantity with realizing, using RGB LED, mention
A kind of optical bar code multiple access technique by assigning different LED-ID based on machine learning is gone out.In transmitting terminal, pass through
PWM modulation mode drives RGB LED lamp to generate high frequency visible light signal；In receiving end, utilization is most of mobile whole in the market
The COMS imaging sensor shooting at end, digital camera obtains specific stripes picture by its roller shutter effect, then mobile eventually by number
The design and relevant image signal process technology for holding APP carry out capture to optical bar code and feature identify, use machine using prior
Device learning algorithm training the library LED-ID classifier lamps and lanterns are differentiated, and by APP software using optical bar code as access port,
The application message of download platform, the final real-time push function for realizing information, can connect in this way effectively as conventional two-dimensional code
The supplement for entering technology becomes a kind of important in the case where night outdoor or other two dimensional codes are unable to get the scene effectively applied
Business entrances, while expanding the transmission range of information and the information content of transmission.Push platform can real-time update visible light it is logical
The transferring content of letter pushes corresponding information according to different application places.It, can be further in combination with mobile terminal sensor
It promotes and realizes positioning, tracking, and provide commerce services more with added value based on geographical location.
The above embodiment is a preferred embodiment of the present invention, but embodiments of the present invention are not by above-described embodiment
Limitation, other any changes, modifications, substitutions, combinations, simplifications made without departing from the spirit and principles of the present invention,
It should be equivalent substitute mode, be included within the scope of the present invention.
Claims (6)
1. a kind of modulation of visible light bar code and recognition methods based on RGB LED lamp, which is characterized in that the visible light
Bar code modulation with recognition methods the following steps are included:
S1, in transmitting terminal, in the way of PWM modulation, three pulse signals that input phase is poor, duty ratio, frequency are different, respectively
The red, green, blue lamp bead for controlling RGB LED issue flicker frequency, brightness difference and there are the visible light signals of phase difference；
S2, striation print image is obtained, is extracted through image procossing using CMOS camera shooting RGB LED image in receiving end
Four the LED lamp area of RGB LED image, bright fringe number, light and shade striped duty ratio and coefficient of phase difference features；
S3, extracted RGB LED characteristic is trained using machine learning, establishes linear classifier；
S4, the feature for extracting RGB LED image to be determined judge generic using the linear classifier that training finishes, real
The detection and identification of existing striations.
2. the modulation of visible light bar code and recognition methods, feature according to claim 1 based on RGB LED lamp exists
In the extraction process of the LED lamp area of RGB LED image is as follows in the step S2:
By RGB LED image binaryzation, the edge LED is detected by connected domain, obtains the radius of divided LED, calculates LED lamp
Area.
3. the modulation of visible light bar code and recognition methods, feature according to claim 1 based on RGB LED lamp exists
In the extraction process of the bright fringe number of RGB LED image is as follows in the step S2:
The rectangular area of LED is partitioned into from RGB LED image, and according to isolated three picture of R, G, B triple channel；
By three picture binaryzations；
Three binaryzation pictures are subjected to Refinement operation, measure the white stripes number in picture.
4. the modulation of visible light bar code and recognition methods, feature according to claim 1 based on RGB LED lamp exists
In the extraction process of the light and shade striped duty ratio of RGB LED image is as follows in the step S2:
It is partitioned into the rectangular area of LED from RGB LED image, takes one in the middle position in the image level direction being partitioned into
Direction straight down, through the count vector of whole image, record the number of pixels that pixel value is 0 and 1 on this vector, obtain
Light and shade striped duty ratio.
5. the modulation of visible light bar code and recognition methods, feature according to claim 1 based on RGB LED lamp exists
In the process for calculating coefficient of phase difference in the step S2 is as follows:
Three binaryzation pictures are placed under the same coordinate system, the middle position in image level direction take a direction vertically to
Under, through the vector of whole image, remember ordinate corresponding to i-th of stripe centerline that the first picture intersects with this vector
For d1, the corresponding ordinate of i+1 stripe centerline that the second picture intersects with this vector is d2, third picture and this
The corresponding ordinate of the i-th+2 stripe centerlines of vector intersection is d3, calculating coefficient of phase difference is
6. the modulation of visible light bar code and recognition methods, feature according to claim 1 based on RGB LED lamp exists
In establishing linear classifier process such as using the extracted RGB LED characteristic of machine learning training in the step S3
Under:
Several optimal hyperlanes are designed in feature space by linear SVM, are distinguished different samples, are established line
Property classifier.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910648924.5A CN110532860A (en) | 2019-07-18 | 2019-07-18 | The modulation of visible light bar code and recognition methods based on RGB LED lamp |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910648924.5A CN110532860A (en) | 2019-07-18 | 2019-07-18 | The modulation of visible light bar code and recognition methods based on RGB LED lamp |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110532860A true CN110532860A (en) | 2019-12-03 |
Family
ID=68660266
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910648924.5A Pending CN110532860A (en) | 2019-07-18 | 2019-07-18 | The modulation of visible light bar code and recognition methods based on RGB LED lamp |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110532860A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111490823A (en) * | 2020-04-22 | 2020-08-04 | 深圳市南科信息科技有限公司 | Visible light imaging communication decoding method based on convolutional neural network |
| CN112528697A (en) * | 2020-12-04 | 2021-03-19 | 深圳市南科信息科技有限公司 | LED light stripe code detection method based on discrete Fourier transform |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103383446A (en) * | 2013-04-09 | 2013-11-06 | 北京半导体照明科技促进中心 | Indoor positioning method, device and system based on visible light and light source |
| CN104316989A (en) * | 2014-10-07 | 2015-01-28 | 北京理工大学 | Design method of indoor LED visible light communication holographic monochromatic reflector |
| CN107169952A (en) * | 2017-03-07 | 2017-09-15 | 广东顺德中山大学卡内基梅隆大学国际联合研究院 | A kind of fringe counting method and information detecting method positioned for visual light imaging |
| CN108023640A (en) * | 2018-01-09 | 2018-05-11 | 华南理工大学 | A kind of visible light communication system based on flat lamp and mobile terminal camera |
| US20180212684A1 (en) * | 2012-12-27 | 2018-07-26 | Panasonic Intellectual Property Corporation Of America | Transmitting method, transmitting apparatus, and program |
-
2019
- 2019-07-18 CN CN201910648924.5A patent/CN110532860A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20180212684A1 (en) * | 2012-12-27 | 2018-07-26 | Panasonic Intellectual Property Corporation Of America | Transmitting method, transmitting apparatus, and program |
| CN103383446A (en) * | 2013-04-09 | 2013-11-06 | 北京半导体照明科技促进中心 | Indoor positioning method, device and system based on visible light and light source |
| CN104316989A (en) * | 2014-10-07 | 2015-01-28 | 北京理工大学 | Design method of indoor LED visible light communication holographic monochromatic reflector |
| CN107169952A (en) * | 2017-03-07 | 2017-09-15 | 广东顺德中山大学卡内基梅隆大学国际联合研究院 | A kind of fringe counting method and information detecting method positioned for visual light imaging |
| CN108023640A (en) * | 2018-01-09 | 2018-05-11 | 华南理工大学 | A kind of visible light communication system based on flat lamp and mobile terminal camera |
Non-Patent Citations (1)
| Title |
|---|
| JINGYI LI等: ""The Optical Barcode Detection and Recognition Method Based on Visible Light Communication Using Machine Learning"", 《APPLIED SCIENCES》 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111490823A (en) * | 2020-04-22 | 2020-08-04 | 深圳市南科信息科技有限公司 | Visible light imaging communication decoding method based on convolutional neural network |
| CN111490823B (en) * | 2020-04-22 | 2021-03-19 | 深圳市南科信息科技有限公司 | Visible light imaging communication decoding method based on convolutional neural network |
| CN112528697A (en) * | 2020-12-04 | 2021-03-19 | 深圳市南科信息科技有限公司 | LED light stripe code detection method based on discrete Fourier transform |
| CN112528697B (en) * | 2020-12-04 | 2023-05-23 | 深圳市南科信息科技有限公司 | LED light stripe code detection method based on discrete Fourier transform |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103309473B (en) | There is high-res and the high sensitive moving detector of multiple color light source | |
| WO2018041136A1 (en) | Optical communication device and system and corresponding information transferring and receiving method | |
| CN106529512B (en) | Living body faces verification method and device | |
| EP3520390B1 (en) | Recolorization of infrared image streams | |
| WO2017157034A1 (en) | Method, device, and storage medium for identifying two-dimensional code | |
| WO2022052475A1 (en) | Image capture processing method, apparatus and device, storage medium, and program product | |
| CN102567727A (en) | Method and device for replacing background target | |
| CN105425209B (en) | Multispectral visible light positioning system for indoor positioning | |
| CN110346116B (en) | Scene illumination calculation method based on image acquisition | |
| WO2019214643A1 (en) | Method for guiding autonomously movable machine by means of optical communication device | |
| CN110532860A (en) | The modulation of visible light bar code and recognition methods based on RGB LED lamp | |
| CN108288289A (en) | A kind of LED visible detection methods and its system for visible light-seeking | |
| WO2019120156A1 (en) | Optical tag-based positioning method and system | |
| WO2019214642A1 (en) | System and method for guiding autonomous machine | |
| CN109472767B (en) | Stage lamp missing state analysis system | |
| CN109325926B (en) | Automatic filter implementation method, storage medium, device and system | |
| WO2020062875A1 (en) | Optical communication device and method for transmitting and receiving information | |
| CN109410594A (en) | A kind of Vehicle License Plate Recognition System and method | |
| CN103729624B (en) | A kind of light measuring method and photometric system based on skin color model | |
| CN108429886A (en) | A kind of photographic method and terminal | |
| CN114296556A (en) | Interactive display method, device and system based on human body posture | |
| CN109040598A (en) | Image processing method, device, computer readable storage medium and electronic equipment | |
| Zhang et al. | The optical fringe code modulation and recognition algorithm based on visible light communication using convolutional neural network | |
| CN110378207B (en) | Face authentication method and device, electronic equipment and readable storage medium | |
| CN107543131B (en) | A kind of LED lamp with AR function |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20191203 |
|
| RJ01 | Rejection of invention patent application after publication |