CN114630396A - Intelligent lamp Bluetooth configuration method and system based on image recognition - Google Patents
Intelligent lamp Bluetooth configuration method and system based on image recognition Download PDFInfo
- Publication number
- CN114630396A CN114630396A CN202111676151.5A CN202111676151A CN114630396A CN 114630396 A CN114630396 A CN 114630396A CN 202111676151 A CN202111676151 A CN 202111676151A CN 114630396 A CN114630396 A CN 114630396A
- Authority
- CN
- China
- Prior art keywords
- intelligent
- picture
- lamp
- model
- intelligent lamp
- 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
- 238000000034 method Methods 0.000 title claims abstract description 63
- 238000012549 training Methods 0.000 claims description 18
- 238000004590 computer program Methods 0.000 claims description 16
- 238000007781 pre-processing Methods 0.000 claims description 12
- 238000013473 artificial intelligence Methods 0.000 abstract description 10
- 238000004891 communication Methods 0.000 abstract description 6
- 238000005516 engineering process Methods 0.000 abstract description 6
- 230000008569 process Effects 0.000 description 13
- 238000013527 convolutional neural network Methods 0.000 description 11
- 238000010586 diagram Methods 0.000 description 11
- 230000009471 action Effects 0.000 description 3
- 230000003993 interaction Effects 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W48/00—Access restriction; Network selection; Access point selection
- H04W48/16—Discovering, processing access restriction or access information
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- 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
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L12/00—Data switching networks
- H04L12/28—Data switching networks characterised by path configuration, e.g. LAN [Local Area Networks] or WAN [Wide Area Networks]
- H04L12/2803—Home automation networks
- H04L12/2807—Exchanging configuration information on appliance services in a home automation network
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M1/00—Substation equipment, e.g. for use by subscribers
- H04M1/72—Mobile telephones; Cordless telephones, i.e. devices for establishing wireless links to base stations without route selection
- H04M1/724—User interfaces specially adapted for cordless or mobile telephones
- H04M1/72403—User interfaces specially adapted for cordless or mobile telephones with means for local support of applications that increase the functionality
- H04M1/72409—User interfaces specially adapted for cordless or mobile telephones with means for local support of applications that increase the functionality by interfacing with external accessories
- H04M1/72412—User interfaces specially adapted for cordless or mobile telephones with means for local support of applications that increase the functionality by interfacing with external accessories using two-way short-range wireless interfaces
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/80—Services using short range communication, e.g. near-field communication [NFC], radio-frequency identification [RFID] or low energy communication
Abstract
The invention provides an intelligent lamp Bluetooth configuration method based on image recognition, which is arranged in an intelligent terminal and comprises the following steps: acquiring an intelligent lamp picture through an intelligent terminal camera; inputting the picture into a target model of the identification lamp, and identifying the model of the intelligent lamp in the picture; according to the model of intelligent lamp, carry out the bluetooth configuration connection. According to the Bluetooth configuration method of the intelligent lamp based on image recognition, the artificial intelligence recognition algorithm is built in the intelligent mobile phone through the image recognition technology and the artificial intelligence, the lamp product type can be recognized through the camera of the intelligent mobile phone without internet network communication and cloud service, and the Bluetooth configuration method has the advantages of being high in speed, accurate in recognition, free of requirements on network environment and the like.
Description
Technical Field
The invention relates to the field of intelligent home furnishing, in particular to an intelligent lamp Bluetooth configuration method and system based on image recognition.
Background
Along with popularization of the internet of things technology and the AI technology, in the smart home industry, how to make smart home devices more intelligent to improve user experience of using smart homes is a demand to be solved urgently. The first step is to guide the smart home devices (such as gateways and electrical appliances) to access the network.
In the process of configuring the intelligent lamp by the traditional Bluetooth, the intelligent lamp always sends broadcast information to the outside under the condition that the intelligent lamp is not configured, in the process of configuring the intelligent lamp by the traditional Bluetooth, the intelligent mobile phone screens configurable information after searching all broadcast information, the Bluetooth is connected with certain configurable information, and the intelligent lamp can be configured by positioning a specific lamp when flickering.
The traditional configuration process has the defects that when all configurable lamps are searched, a plurality of lamps of different types appear, and a user needs to try connection one by one to enable the lamps to flash to position the lamps. The interaction process is complicated, the user experience is poor, and under the condition that the lamps are more, the consumed time is longer.
Disclosure of Invention
The invention mainly aims to overcome the defects in the prior art, and provides an intelligent lamp Bluetooth configuration method based on image recognition.
The invention adopts the following technical scheme:
an intelligent lamp Bluetooth configuration method based on image recognition is built in an intelligent terminal and comprises the following steps:
acquiring an intelligent lamp picture through an intelligent terminal camera;
responding to the shooting of the intelligent terminal, inputting the shot intelligent lamp picture into a target model of the identification lamp, and identifying the model of the intelligent lamp in the picture;
and carrying out Bluetooth configuration connection according to the model of the intelligent lamp.
Specifically, the target model specifically includes:
the picture training sample library is a coco picture library;
acquiring the metaset data of the picture by using an opencv library,
converting the trained model for identifying the specific lamp into a target model pb file through a TensorFlow Lite framework;
and implanting the target model pb file into the intelligent terminal.
Specifically, the models that identify specific lamps include, but are not limited to, R-CNN, Fast R-CNN, FPN, YOLO, SSD, and RetinaNet.
Specifically, after acquireing the intelligent lamp picture through the intelligent terminal camera, still include:
preprocessing the picture, specifically: and (4) cutting, rotating, amplifying or reducing the picture.
In another aspect, an embodiment of the present invention provides an intelligent lamp bluetooth configuration system based on image recognition, which is built in an intelligent terminal, and includes:
a picture acquisition unit: acquiring an intelligent lamp picture through an intelligent terminal camera;
intelligent lamp model identification unit: responding to the shooting of the intelligent terminal, inputting the shot intelligent lamp picture into a target model of the identification lamp, and identifying the model of the intelligent lamp in the picture;
a Bluetooth configuration unit: and carrying out Bluetooth configuration connection according to the model of the intelligent lamp.
The method is characterized in that the target model specifically comprises the following steps:
the picture training sample library is a coco picture library;
acquiring the metadata of the picture by using an opencv library,
converting the trained model for identifying the specific lamp into a target model pb file through a TensorFlow Lite framework;
and implanting the target model pb file into the intelligent terminal.
Specifically, the models that identify specific luminaires include, but are not limited to, R-CNN, Fast R-CNN, Faster R-CNN, FPN, YOLO, SSD, and RetinaNet.
Specifically, the image processing device further comprises an image preprocessing unit, specifically:
an image preprocessing unit: preprocessing the picture, specifically: and (4) cutting, rotating, amplifying or reducing the picture.
An embodiment of the present invention provides an electronic device, including: the intelligent lamp Bluetooth configuration method based on image recognition comprises a memory, a processor and a computer program which is stored on the memory and can run on the processor, wherein the processor executes the computer program to realize the steps of the intelligent lamp Bluetooth configuration method based on image recognition.
In another aspect, the present invention provides a computer-readable storage medium, in which a computer program is stored, and when the computer program is executed by a processor, the steps of the bluetooth configuration method for intelligent lamps based on image recognition are implemented.
As can be seen from the above description of the present invention, compared with the prior art, the present invention has the following advantages:
(1) the invention provides an intelligent lamp Bluetooth configuration method based on image recognition, which is internally arranged in an intelligent terminal and obtains an intelligent lamp picture through an intelligent terminal camera; inputting the picture into a target model of the identification lamp, and identifying the model of the intelligent lamp in the picture; performing Bluetooth configuration connection according to the type of the intelligent lamp; according to the scheme provided by the invention, the artificial intelligence recognition algorithm is built in the smart phone by combining the image recognition technology with artificial intelligence, the lamp product type can be recognized by the camera of the smart phone without internet network communication and cloud service, and the method has the advantages of high speed, accuracy in recognition, no requirement on network environment and the like.
(2) According to the Bluetooth configuration method of the intelligent lamp based on image recognition, the intelligent lamp can be accurately configured in the process of configuring the intelligent lamp through Bluetooth, the phenomenon that irrelevant Bluetooth information of a user is searched in the process of configuring the lamp is avoided, and the use experience of the user is optimized.
Drawings
Fig. 1 is a flowchart of a bluetooth configuration method for an intelligent lamp based on image recognition according to an embodiment of the present invention;
fig. 2 is another flowchart of a bluetooth configuration method for an intelligent lamp based on image recognition according to an embodiment of the present invention;
fig. 3 is a schematic diagram illustrating a result of searching for a configured luminaire in a conventional configured intelligent luminaire according to an embodiment of the present invention;
fig. 4 is a structural diagram of an intelligent lamp bluetooth configuration system based on image recognition according to an embodiment of the present invention;
fig. 5 is a schematic diagram of an embodiment of an electronic device according to an embodiment of the present invention;
fig. 6 is a schematic diagram of an embodiment of a computer-readable storage medium according to an embodiment of the present invention.
The invention is described in further detail below with reference to the figures and specific examples.
Detailed Description
The invention provides an intelligent lamp Bluetooth configuration method based on image recognition, which is characterized in that an artificial intelligence recognition algorithm is built in an intelligent mobile phone through an image recognition technology and by combining artificial intelligence, the lamp product type can be recognized through a camera of the intelligent mobile phone without internet network communication and cloud service, and the method has the advantages of high speed, accurate recognition, no requirement on network environment and the like.
Fig. 1 and fig. 2 are flowcharts of an intelligent lamp bluetooth configuration method based on image recognition according to an embodiment of the present invention, specifically: the method is arranged in an intelligent terminal and comprises the following steps:
s101: acquiring an intelligent lamp picture through an intelligent terminal camera;
the intelligent terminal is an intelligent mobile phone, and intelligent equipment with a photographing function such as a notebook computer and a tablet personal computer can be selected in practice;
the intelligent lamp control method includes the steps that the intelligent lamp can be controlled through the intelligent terminal in the intelligent home, however, Bluetooth configuration connection is needed to be carried out firstly, and when a user determines the intelligent lamp to be controlled, the user only needs to use a camera of the intelligent terminal to shoot a picture of the intelligent lamp;
s102: responding to the shooting of the intelligent terminal, inputting the shot intelligent lamp picture into a target model of the identification lamp, and identifying the model of the intelligent lamp in the picture;
responding to the shooting of the intelligent terminal, inputting the shot intelligent lamp picture into a target model of the identification lamp, wherein the target model is a common target identification model, such as network models of R-CNN, Fast R-CNN, Faster R-CNN, FPN, YOLO, SSD, RetinaNet and the like;
the embodiment of the invention adopts a Faster-RCNN network model, provides an RPN (region Proposal networks) region generation network, uses a neural network generation region to replace a selective search method in the RCNN, saves the time of region search, and realizes end-to-end training;
a sliding window is used on the last convolutional layer (i.e., the feature extraction layer) for prediction. The 256-dimensional characteristic diagram obtained by checking the convolution of 3x3 is subjected to sliding convolution, the characteristic diagram is divided into two paths, the two paths are respectively used for utilizing 1 x 1/convolution, the last path outputs the probability of all the intelligent lamps and non-targets (backgrounds) of anchors, and the other path outputs four parameters related to anchors box, including the central coordinates x and y of the box, the width w and the length h of the box. And outputting whether k anchors contain intelligent lamps and position information or not every time of sliding convolution. Therefore, the final output of the RPN is position information that one path corresponds to 2k classification (whether intelligent lamps are included) and the other path corresponds to 4k anchors.
The embodiment of the invention adopts a four-step training method:
1) training the RPN network independently, wherein the network parameters are loaded by a pre-training model;
2) and (3) training the Fast-RCNN network independently, and taking the output candidate region of the RPN in the first step as the input of the detection network. Specifically, the RPN outputs a candidate frame, intercepts an original image through the candidate frame, passes the intercepted image through conv-pool for several times, and then outputs two branches through roi-pool and fc, wherein one branch is target classification softmax, and the other branch is bbox regression. By now, the two networks do not share parameters, but are trained separately;
3) training the RPN again, wherein the parameters of the public part of the fixed network only update the parameters of the unique part of the RPN;
4) the result of that RPN again fine-tunes the Fast-RCNN network, fixing the parameters of the network common part, and updating only the parameters of the unique part of Fast-RCNN.
S103: according to the model of intelligent lamp, carry out the bluetooth configuration connection.
Performing Bluetooth configuration connection according to the identified model of the intelligent lamp; the speed is high, and the identification is accurate;
fig. 3 is a schematic diagram of a result of searching for and configuring a lamp in a traditional configuration intelligent lamp, where multiple lamps of different types appear, and a user needs to try to connect one by one, so that the lamp can be positioned by a lamp flashing party. The interaction process is complicated, the user experience is poor, and the consumed time is long.
It is important to point out that the method of the embodiment of the invention does not need internet network communication and cloud service, wherein the target model and the picture training sample library are coco picture libraries; acquiring the metaset data of the picture by using an opencv library,
converting the trained model for identifying the specific lamp into a target model pb file through a TensorFlow Lite framework; and implanting the target model pb file into the intelligent terminal.
Due to the lightweight characteristic of the android mobile phone artificial intelligence library, the model can be transplanted into the smart mobile phone and can be used in the same way under the offline condition.
Specifically, after acquireing the intelligent lamp picture through the intelligent terminal camera, still include:
preprocessing the picture, specifically: the picture is cut, rotated, enlarged or reduced, so that a sample set can be increased, and the accuracy of the model is improved.
Referring to fig. 4, another aspect of the embodiment of the present invention provides an intelligent lamp bluetooth configuration system based on image recognition, which is built in an intelligent terminal, and includes:
the picture acquisition unit 401: acquiring an intelligent lamp picture through an intelligent terminal camera;
the intelligent terminal is an intelligent mobile phone, and intelligent equipment with a photographing function such as a notebook computer and a tablet personal computer can be selected in practice;
can realize the control to the intelligent lamp through intelligent terminal in the intelligence house, but need carry out the bluetooth configuration at first and connect, confirm the intelligent lamp that needs control when the user, only need utilize the camera of intelligent terminal to shoot the photo of this intelligent lamp.
Intelligent lamp model identification unit 402: inputting the picture into a target model of the identification lamp, and identifying the model of the intelligent lamp in the picture;
responding to the shooting of the intelligent terminal, inputting the shot intelligent lamp picture into a target model of the identification lamp, wherein the target model is a common target identification model, such as network models of R-CNN, Fast R-CNN, Faster R-CNN, FPN, YOLO, SSD, RetinaNet and the like;
the embodiment of the invention adopts a Faster-RCNN network model, provides an RPN (region Proposal networks) region generation network, uses a neural network generation region to replace a selective search method in the RCNN, saves the time of region search and realizes end-to-end training;
a sliding window is used on the last convolutional layer (i.e., the feature extraction layer) for prediction. The 256-dimensional characteristic diagram obtained by checking the convolution of 3x3 is subjected to sliding convolution, the characteristic diagram is divided into two paths, the two paths are respectively used for utilizing 1 x 1/convolution, the last path outputs the probability of all the intelligent lamps and non-targets (backgrounds) of anchors, and the other path outputs four parameters related to anchors box, including the central coordinates x and y of the box, the width w and the length h of the box. And outputting whether k anchors contain intelligent lamps and position information or not every time of sliding convolution. Therefore, the final output of the RPN is position information that one path corresponds to 2k classification (whether intelligent lamps are included) and the other path corresponds to 4k anchors.
The embodiment of the invention adopts a four-step training method:
1) training the RPN network independently, wherein the network parameters are loaded by a pre-training model;
2) and (3) independently training the Fast-RCNN network, and taking the output candidate region of the RPN in the first step as the input of the detection network. Specifically, the RPN outputs a candidate frame, intercepts an original image through the candidate frame, passes the intercepted image through conv-pool for several times, and then outputs two branches through roi-pool and fc, wherein one branch is target classification softmax, and the other branch is bbox regression. By now, the two networks do not share parameters, but are trained separately;
3) training the RPN again, wherein the parameters of the public part of the fixed network only update the parameters of the unique part of the RPN;
4) the results of that RPN again fine-tune the Fast-RCNN network, fixing the parameters of the public part of the network, and updating only the parameters of the unique part of the Fast-RCNN.
Bluetooth configuration unit 403: and carrying out Bluetooth configuration connection according to the model of the intelligent lamp.
Performing Bluetooth configuration connection according to the identified model of the intelligent lamp; the speed is high, and the identification is accurate;
fig. 3 is a schematic diagram of a result of searching for a configured lamp in a traditional configured intelligent lamp, and when a plurality of lamps of different types appear, a user needs to try to connect one by one, so that the lamp can be positioned by a lamp flickering party. The interaction process is complicated, the user experience is poor, and the consumed time is long.
It is important to point out that the method of the embodiment of the invention does not need internet network communication and cloud service, wherein the target model and the picture training sample library are coco picture libraries; acquiring the metaset data of the picture by using an opencv library,
converting the trained model for identifying the specific lamp into a target model pb file through a TensorFlow Lite framework; and implanting the target model pb file into the intelligent terminal.
Due to the lightweight characteristic of the android mobile phone artificial intelligence library, the model can be transplanted into the smart mobile phone and used in the same way under the offline condition.
Specifically, the image processing device further comprises an image preprocessing unit, specifically:
an image preprocessing unit: preprocessing the picture, specifically: the picture is cut, rotated, amplified or reduced, so that a sample set can be increased, and the accuracy of the model is improved.
As shown in fig. 5, an electronic device 500 according to an embodiment of the present invention includes a memory 510, a processor 520, and a computer program 511 stored in the memory 520 and executable on the processor 520, where the processor 520 executes the computer program 511 to implement a bluetooth configuration method for smart lights based on image recognition according to an embodiment of the present invention.
In particular embodiments, when the processor 520 executes the computer program 511, it may implement:
an intelligent lamp Bluetooth configuration method based on image recognition is arranged in an intelligent terminal and comprises the following steps:
acquiring an intelligent lamp picture through an intelligent terminal camera;
inputting the picture into a target model of the identification lamp, and identifying the model of the intelligent lamp in the picture;
and carrying out Bluetooth configuration connection according to the model of the intelligent lamp.
Since the electronic device described in this embodiment is a device used for implementing a data processing apparatus in the embodiment of the present invention, based on the method described in this embodiment of the present invention, a person skilled in the art can understand the specific implementation manner of the electronic device in this embodiment and various variations thereof, so that how to implement the method in this embodiment of the present invention by the electronic device is not described in detail herein, and as long as the person skilled in the art implements the device used for implementing the method in this embodiment of the present invention, the device used for implementing the method in this embodiment of the present invention belongs to the protection scope of the present invention.
Referring to fig. 6, fig. 6 is a schematic diagram illustrating an embodiment of a computer-readable storage medium according to the present invention.
As shown in fig. 6, the present embodiment provides a computer-readable storage medium 600, on which a computer program 611 is stored, and when the computer program 611 is executed by a processor, the method for configuring the bluetooth for intelligent lamps based on image recognition according to the present embodiment is implemented;
in particular embodiments, the computer program 611, when executed by a processor, may implement:
an intelligent lamp Bluetooth configuration method based on image recognition is built in an intelligent terminal and comprises the following steps:
acquiring an intelligent lamp picture through an intelligent terminal camera;
inputting the picture into a target model of the identification lamp, and identifying the model of the intelligent lamp in the picture;
and carrying out Bluetooth configuration connection according to the model of the intelligent lamp.
It should be noted that, in the foregoing embodiments, the descriptions of the respective embodiments have respective emphasis, and reference may be made to relevant descriptions of other embodiments for parts that are not described in detail in a certain embodiment.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The invention provides an intelligent lamp Bluetooth configuration method based on image recognition, which is internally arranged in an intelligent terminal and obtains an intelligent lamp picture through an intelligent terminal camera; inputting the picture into a target model of the identification lamp, and identifying the model of the intelligent lamp in the picture; performing Bluetooth configuration connection according to the type of the intelligent lamp; according to the scheme provided by the invention, the artificial intelligence recognition algorithm is built in the smart phone by combining the image recognition technology with artificial intelligence, the lamp product type can be recognized by the camera of the smart phone without internet network communication and cloud service, and the method has the advantages of high speed, accuracy in recognition, no requirement on network environment and the like.
According to the Bluetooth configuration method of the intelligent lamp based on image recognition, the intelligent lamp can be accurately configured in the process of configuring the intelligent lamp through Bluetooth, the phenomenon that irrelevant Bluetooth information of a user is searched in the process of configuring the lamp is avoided, and the use experience of the user is optimized.
It is noted that, in this document, relational terms such as "first" and "second," and the like, may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element. The above description is merely exemplary of the present application and is presented to enable those skilled in the art to understand and practice the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
The above description is only an embodiment of the present invention, but the design concept of the present invention is not limited thereto, and any insubstantial modifications made by using the design concept should fall within the scope of infringing the present invention.
Claims (10)
1. An intelligent lamp Bluetooth configuration method based on image recognition is arranged in an intelligent terminal, and is characterized by comprising the following steps:
acquiring an intelligent lamp picture through an intelligent terminal camera;
responding to the shooting of the intelligent terminal, inputting the shot intelligent lamp picture into a target model of the identification lamp, and identifying the model of the intelligent lamp in the picture;
and carrying out Bluetooth configuration connection according to the model of the intelligent lamp.
2. The image recognition-based Bluetooth configuration method for intelligent lamps according to claim 1, wherein the target model specifically comprises:
the picture training sample library is a coco picture library;
acquiring the metaset data of the picture by using an opencv library,
converting the trained model for identifying the specific lamp into a target model pb file through a TensorFlow Lite framework;
and implanting the target model pb file into the intelligent terminal.
3. The image recognition-based Bluetooth configuration method for intelligent lamps according to claim 2, wherein the model for recognizing specific lamps includes but is not limited to R-CNN, Fast R-CNN, FPN, YOLO, SSD and RetinaNet.
4. The image recognition-based intelligent lamp Bluetooth configuration method according to claim 1, wherein after the intelligent lamp picture is obtained through the intelligent terminal camera, the method further comprises:
preprocessing the picture, specifically: and (4) cutting, rotating, amplifying or reducing the picture.
5. The utility model provides an intelligent lamp bluetooth configuration system based on image recognition places intelligent terminal in, its characterized in that includes:
a picture acquisition unit: acquiring an intelligent lamp picture through an intelligent terminal camera;
intelligent lamp model identification unit: responding to the shooting of the intelligent terminal, inputting the shot intelligent lamp picture into a target model of the identification lamp, and identifying the model of the intelligent lamp in the picture;
a Bluetooth configuration unit: and carrying out Bluetooth configuration connection according to the model of the intelligent lamp.
6. The image recognition-based intelligent lamp Bluetooth configuration system according to claim 5, wherein the target model is specifically:
the picture training sample library is a coco picture library;
acquiring the metaset data of the picture by using an opencv library,
converting the trained model for identifying the specific lamp into a target model pb file through a TensorFlow Lite framework;
and implanting the target model pb file into the intelligent terminal.
7. The image recognition-based Bluetooth configuration system for intelligent lamps as claimed in claim 6, wherein the model for recognizing specific lamps includes but is not limited to R-CNN, Fast R-CNN, FPN, YOLO, SSD and RetinaNet.
8. The intelligent lamp Bluetooth configuration system based on image recognition as claimed in claim 5, further comprising an image preprocessing unit, specifically:
an image preprocessing unit: preprocessing the picture, specifically: and (4) cutting, rotating, amplifying or reducing the picture.
9. An electronic device, comprising: memory, processor and computer program stored on the memory and executable on the processor, wherein the processor implements the method steps of any of claims 1 to 4 when executing the computer program.
10. A computer-readable storage medium, characterized in that a computer program is stored in the computer-readable storage medium, which computer program, when being executed by a processor, carries out the method steps of any one of claims 1 to 4.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111676151.5A CN114630396A (en) | 2021-12-31 | 2021-12-31 | Intelligent lamp Bluetooth configuration method and system based on image recognition |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111676151.5A CN114630396A (en) | 2021-12-31 | 2021-12-31 | Intelligent lamp Bluetooth configuration method and system based on image recognition |
Publications (1)
Publication Number | Publication Date |
---|---|
CN114630396A true CN114630396A (en) | 2022-06-14 |
Family
ID=81898562
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202111676151.5A Pending CN114630396A (en) | 2021-12-31 | 2021-12-31 | Intelligent lamp Bluetooth configuration method and system based on image recognition |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114630396A (en) |
Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20110052072A1 (en) * | 2009-08-28 | 2011-03-03 | Samsung Electronics Co. Ltd. | Apparatus and method for connecting device through image recognition in mobile terminal |
US20170113598A1 (en) * | 2015-10-22 | 2017-04-27 | Le Holdings (Beijing) Co., Ltd. | Method and device for controlling of switching on and off car lights through bluetooth technology |
CN109951889A (en) * | 2019-03-14 | 2019-06-28 | 维沃移动通信有限公司 | A kind of Internet of Things matches network method and mobile terminal |
CN110213753A (en) * | 2019-05-08 | 2019-09-06 | 杰哈思文化创意(杭州)有限公司 | Connection method, device, storage medium and the terminal of intelligent toothbrush |
CN110831116A (en) * | 2019-11-05 | 2020-02-21 | 珠海格力电器股份有限公司 | Household appliance network distribution method, storage medium and terminal |
CN111738212A (en) * | 2020-07-20 | 2020-10-02 | 平安国际智慧城市科技股份有限公司 | Traffic signal lamp identification method, device, equipment and medium based on artificial intelligence |
CN111753683A (en) * | 2020-06-11 | 2020-10-09 | 南京师范大学 | Human body posture identification method based on multi-expert convolutional neural network |
CN112308018A (en) * | 2020-11-19 | 2021-02-02 | 安徽鸿程光电有限公司 | Image identification method, system, electronic equipment and storage medium |
CN113449641A (en) * | 2021-06-29 | 2021-09-28 | 张家港江苏科技大学产业技术研究院 | Object recognition system based on cloud edge-end cooperation |
CN113469073A (en) * | 2021-07-06 | 2021-10-01 | 西安电子科技大学 | SAR image ship detection method and system based on lightweight deep learning |
-
2021
- 2021-12-31 CN CN202111676151.5A patent/CN114630396A/en active Pending
Patent Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20110052072A1 (en) * | 2009-08-28 | 2011-03-03 | Samsung Electronics Co. Ltd. | Apparatus and method for connecting device through image recognition in mobile terminal |
US20170113598A1 (en) * | 2015-10-22 | 2017-04-27 | Le Holdings (Beijing) Co., Ltd. | Method and device for controlling of switching on and off car lights through bluetooth technology |
CN109951889A (en) * | 2019-03-14 | 2019-06-28 | 维沃移动通信有限公司 | A kind of Internet of Things matches network method and mobile terminal |
CN110213753A (en) * | 2019-05-08 | 2019-09-06 | 杰哈思文化创意(杭州)有限公司 | Connection method, device, storage medium and the terminal of intelligent toothbrush |
CN110831116A (en) * | 2019-11-05 | 2020-02-21 | 珠海格力电器股份有限公司 | Household appliance network distribution method, storage medium and terminal |
CN111753683A (en) * | 2020-06-11 | 2020-10-09 | 南京师范大学 | Human body posture identification method based on multi-expert convolutional neural network |
CN111738212A (en) * | 2020-07-20 | 2020-10-02 | 平安国际智慧城市科技股份有限公司 | Traffic signal lamp identification method, device, equipment and medium based on artificial intelligence |
CN112308018A (en) * | 2020-11-19 | 2021-02-02 | 安徽鸿程光电有限公司 | Image identification method, system, electronic equipment and storage medium |
CN113449641A (en) * | 2021-06-29 | 2021-09-28 | 张家港江苏科技大学产业技术研究院 | Object recognition system based on cloud edge-end cooperation |
CN113469073A (en) * | 2021-07-06 | 2021-10-01 | 西安电子科技大学 | SAR image ship detection method and system based on lightweight deep learning |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US11436449B2 (en) | Method and electronic apparatus for processing image and training image tag classification model | |
KR101796401B1 (en) | Method, apparatus and server for image scene determination | |
CN109145766B (en) | Model training method and device, recognition method, electronic device and storage medium | |
US11276419B2 (en) | Synchronized sound generation from videos | |
US10621245B2 (en) | Webpage data analysis method and device | |
CN108875487B (en) | Training of pedestrian re-recognition network and pedestrian re-recognition based on training | |
CN108664526B (en) | Retrieval method and device | |
CN110334271A (en) | A kind of search result optimization method, system, electronic equipment and storage medium | |
Collinaszy et al. | Implementation of intelligent software using IBM Watson and Bluemix | |
CN109446443A (en) | A kind of tag update method, apparatus, equipment and storage medium | |
CN110728284A (en) | Edge calculation firework identification method based on deep learning and intelligent terminal | |
US11073975B1 (en) | Synthetic image generation in response to user creation of image | |
JP2019117556A (en) | Information processing apparatus, information processing method and program | |
CN112906554B (en) | Model training optimization method and device based on visual image and related equipment | |
CN112001300B (en) | Building monitoring method and device based on cross entropy according to position and electronic equipment | |
CN103929460A (en) | Method for obtaining state information of contact and mobile device | |
CN116522565B (en) | BIM-based power engineering design power distribution network planning method and computer equipment | |
CN114630396A (en) | Intelligent lamp Bluetooth configuration method and system based on image recognition | |
US11232616B2 (en) | Methods and systems for performing editing operations on media | |
CN107729439A (en) | Obtain the methods, devices and systems of multi-medium data | |
CN113138796A (en) | Code generation method and device, electronic equipment and storage medium | |
KR102474436B1 (en) | An apparatus for processing video and image search of natural languages based on caption data and a method for operating it | |
KR102502575B1 (en) | Apparatus, method and program for providing product trend prediction service | |
CN112001301B (en) | Building monitoring method and device based on global cross entropy weighting and electronic equipment | |
CN111143626B (en) | Method, apparatus, device and computer readable storage medium for identifying group |
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 |