CN110336719A - A kind of long-distance intelligent appliance control method of real-time video domestic environment equipment identification interaction - Google Patents
A kind of long-distance intelligent appliance control method of real-time video domestic environment equipment identification interaction Download PDFInfo
- Publication number
- CN110336719A CN110336719A CN201910477495.XA CN201910477495A CN110336719A CN 110336719 A CN110336719 A CN 110336719A CN 201910477495 A CN201910477495 A CN 201910477495A CN 110336719 A CN110336719 A CN 110336719A
- Authority
- CN
- China
- Prior art keywords
- equipment
- image
- control
- real
- domestic environment
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
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
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
-
- 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
- H04L12/2816—Controlling appliance services of a home automation network by calling their functionalities
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/60—Control of cameras or camera modules
- H04N23/66—Remote control of cameras or camera parts, e.g. by remote control devices
- H04N23/661—Transmitting camera control signals through networks, e.g. control via the Internet
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/60—Control of cameras or camera modules
- H04N23/695—Control of camera direction for changing a field of view, e.g. pan, tilt or based on tracking of objects
Abstract
The invention discloses a kind of long-distance intelligent appliance control method of real-time video domestic environment equipment identification interaction, this method comprises: S1, using IP Camera, acquire the multi-angle image in domestic environment, and pre-process to image；S2, using online equipment Shape Classification device, pretreated image is matched with the model in the classifier, just positioning is done to facility information present in domestic environment, extracts just localization region image, the input as equipment recognition classifier；S3, online device class device model is called to identify using deep learning matching algorithm to the image；S4, the remote control mode learnt in advance according to the device class identified, calling, remotely control the equipment；S5, the remote control result of electrical equipment is fed back by real-time video to control terminal.The present invention can accurately identify household scene, and real-time perfoming controls, and fast implement the customization identification and long-range control of personalized domestic environment scene.
Description
Technical field
The present invention relates in smart home long-distance video identification and interactive controlling and video mode recognizer technology neck
The long-distance intelligent appliance control method of domain more particularly to a kind of identification interaction of real-time video domestic environment equipment.
Background technique
With the application of mobile network and smart home technology, in a network environment, the operation of long-range home equipment is realized
As a current research hotspot.Control based on wireless network intelligent household and Computer Vision Recognition smart home,
There is relatively broad application in remote interaction, the fields such as nursing of helping the disabled.
Summary of the invention
The technical problem to be solved in the present invention is that for the defects in the prior art, providing a kind of real-time video household ring
The long-distance intelligent appliance control method of border equipment identification interaction.
The technical solution adopted by the present invention to solve the technical problems is:
The present invention provides a kind of long-distance intelligent appliance control method of real-time video domestic environment equipment identification interaction, realizes
In domestic environment scene, the electric appliance in domestic environment, equipment are identified using web camera, and according to recognition result
The control interface for opening corresponding equipment, carries out the long-range control of equipment electric appliance, while control result is carried out in real-time video
Feedback, method includes the following steps:
S1, using the IP Camera based on WIFI network, monitor household scene, acquire the multi-angle figure in domestic environment
Picture, and image is pre-processed, comprising: gray processing, binaryzation, marginalisation operation；
S2, using online equipment Shape Classification device, pretreated image is matched with the model in the classifier, it is right
Facility information present in domestic environment does just positioning, extracts just localization region image, the input as equipment recognition classifier；
S3, the first localization region image to extraction, call online device class device model, are matched and are calculated using deep learning
Method identifies the image；
S4, deep learning matching algorithm identify the electrical equipment in domestic environment in real time, according to the equipment class identified
Not, the remote control mode learnt in advance is called, which is remotely controlled；
S5, the remote control result of electrical equipment is fed back by real-time video to control terminal, obtains the reality of electrical equipment
When state value, and remotely adjust cam movement, obtain multi-angle image, complete control process.
Further, step S1 of the invention method particularly includes:
S11, on the video image of extraction, carry out the shape processing of image, edge detection done to image first, the company of extraction
Continuous edge；
S12, in the profile of continuous boundary extracted region equipment, mark opens the angle point of contour area, is done using corner location
Geometric correction obtains the specification figure of the equipment.
Further, step S2 of the invention method particularly includes:
S21, classifier study: in the pretreatment stage of classifier study, plurality of devices sample is used to classify as training
Device input carries out classifier study, and the classifier study stage decomposes input sample using multiple features, in the first fixed of segmentation
In bit image, there are erroneous detections and false retrieval, and to avoid mistakes and omissions, which is input to Shape Classification device；The classifier makes
It is obtained with on-line study, specific acquisition methods are: in initial phase, the image shape of the known device shot in advance being handled
As a result it is stored as matching template, which includes the multi-angle result of more equipment；
S22, the shape to be identified obtained in real time, are input in the Shape Classification device, carry out classifier knowledge to the shape
Not, using the maximum probability result of identification as anticipation equipment；
S23, it is extended 10% pixel in the shape edges region, the contour area of acquisition is known as device class device
Other input picture.
Further, step S3 of the invention method particularly includes:
S31, multi-feature extraction, including edge, angle point, text and icon characteristics key value are done to the equipment image of input；
S32, multiple features are normalized, construction feature vector multi-dimensional matrix；
S33, the multi-dimensional matrix, which are input in equipment recognition classifier, carries out pattern match with template, and output recognition result is made
For final judgement result.
Further, step S4 of the invention method particularly includes:
The recognition result for the electrical equipment that S41, marker recognition go out, calls the control of the equipment in remote control data library
Parameter；
S42, pass through transmission of video control parameter, as long-range control triggering code；
S43, control result image is compressed to by byte code stream by IP network, remote control terminal is transferred to, as control
As a result it feeds back.
Further, step S5 of the invention method particularly includes:
The cradle head control of S51, telecommunication network camera comprising angle adjustment, focus adjustment, to picture in holder image
Image carries out feature extraction, and by the incoming identification hardware of the feature of extraction, which is integrated in holder；
S52, the IP Camera realize that online vision facilities contours extract and pattern matching process, algorithm integration are being set
In standby, remote server participation is not needed；
S53, remotely pass through IP agreement, transmit remote-control code, which is on-line study acquisition, is stored in IP camera shooting
In machine storage；
S54, remote control interface are generated in real time by IP Camera internal algorithm, and carry out control routine mapping, are realized
Remote control.
The beneficial effect comprise that: the long-distance intelligent of real-time video domestic environment equipment identification interaction of the invention
Appliance control method can carry out intelligent recognition to household appliance by video camera, and pop up response under domestic environment
Control interface realize long-range control to equipment.The invention is directed to the intelligent recognition and control of domestic environment, is particularly suitable for house
In have old solitary people or handicapped person, can be used wireless video carry out remote wireless control, improve the intelligent control of household
Horizontal and self-care ability.It is with a wide range of applications, can obtain in disability patient fields such as the intelligent control of accessory of helping the disabled
Preferable social benefit.
Detailed description of the invention
Present invention will be further explained below with reference to the attached drawings and examples, in attached drawing:
Fig. 1 is the algorithm overall flow figure of the embodiment of the present invention；
Fig. 2 is the flow chart of the home equipment recognizer of the embodiment of the present invention.
Specific embodiment
In order to make the objectives, technical solutions, and advantages of the present invention clearer, with reference to the accompanying drawings and embodiments, right
The present invention is further elaborated.It should be appreciated that described herein, specific examples are only used to explain the present invention, not
For limiting the present invention.
The long-distance intelligent appliance control method of the real-time video domestic environment equipment identification interaction of the embodiment of the present invention, is realized
In domestic environment scene, the electric appliance in domestic environment, equipment are identified using web camera, and according to recognition result
The control interface for opening corresponding equipment, carries out the long-range control of equipment electric appliance, while control result is carried out in real-time video
Feedback, method includes the following steps:
S1, using the IP Camera based on WIFI network, monitor household scene, acquire the multi-angle figure in domestic environment
Picture, and image is pre-processed, comprising: gray processing, binaryzation, marginalisation operation；
S11, on the video image of extraction, carry out the shape processing of image, edge detection done to image first, the company of extraction
Continuous edge；
S12, in the profile of continuous boundary extracted region equipment, mark opens the angle point of contour area, is done using corner location
Geometric correction obtains the specification figure of the equipment.
S2, using online equipment Shape Classification device, pretreated image is matched with the model in the classifier, it is right
Facility information present in domestic environment does just positioning, extracts just localization region image, the input as equipment recognition classifier；
S21, classifier study: in the pretreatment stage of classifier study, plurality of devices sample is used to classify as training
Device input carries out classifier study, and the classifier study stage decomposes input sample using multiple features, in the first fixed of segmentation
In bit image, there are erroneous detections and false retrieval, and to avoid mistakes and omissions, which is input to Shape Classification device；The classifier makes
It is obtained with on-line study, specific acquisition methods are: in initial phase, the image shape of the known device shot in advance being handled
As a result it is stored as matching template, which includes the multi-angle result of more equipment；
S22, the shape to be identified obtained in real time, are input in the Shape Classification device, carry out classifier knowledge to the shape
Not, using the maximum probability result of identification as anticipation equipment；
S23, it is extended 10% pixel in the shape edges region, the contour area of acquisition is known as device class device
Other input picture.
S3, the first localization region image to extraction, call online device class device model, are matched and are calculated using deep learning
Method identifies the image；
S31, electric appliance in household scene are identified as typical more Classification and Identifications, using deep neural network, to default
Household image carry out classification based training, consider more class objects below:
Wherein Vi is the prime recognition result of classifier, is the task of the household scene image classification of c for total classification number,
I be index of all categories, Si be current element classification results value index and all classification results and ratio；
S32, relative probability distribution is converted by polytypic output numerical value using softmax function, wherein maximum probability
Classification be identification result；The overflow problem for considering exponential function simultaneously, using method for normalizing to preliminary classification result
Exponential number carry out the following processing:
D=max (V)
S33, in household image classification, enable x be input image, y be classification as a result, W is the parameter of classifier, then
The result of every oneclass classification:
S=Wx
For every a kind of classification results, have:
Logarithm operation is carried out to classification results:
Because logarithm operation does not change function limit, can use
Obtain trained objective function；
S34. deep neural network is used, is optimized for the objective function, obtains the learning parameter W of classification.Knowing
In the other stage, for the scene in practical camera, Operating match algorithm obtains the result of identification.
S4, deep learning matching algorithm identify the electrical equipment in domestic environment in real time, according to the equipment class identified
Not, the remote control mode learnt in advance is called, which is remotely controlled；
S41, for the electrical equipment in household, remote control coding learning device is used to its remote-controller function coding, to family
The telecontrol code for occupying equipment is parsed, and obtains infrared code character string, and all infrared code correspondences are stored as device data
Infrared control mark, to general remote control electrical appliance, use its available remote control coding of this method；
S42, the equipment to control code has been learnt can carry out the infrared of more equipment using airborne infrared launcher
Control；
The recognition result for the electrical equipment that S43, marker recognition go out, calls the infrared of the equipment in remote control data library
Control parameter；
S44, pass through transmission of video control parameter, as long-range control triggering code；Specific step are as follows: pass through long-distance cloud
Platform is realized and is interconnected with the IP of home equipment controller, and obtains the video image of home equipment；When in video image go out
When identified electrical equipment, the pop-up control menu at the long-range corresponding equipment image of video clip, point in remote interface
The menu button is hit, then is remotely sending control instruction to home controller, after home controller identifies the control instruction, by it
It is mapped as the infrared ray remotes control code for having learnt and having stored, controls corresponding device action；
S45, pass through IP network for control result image transmitting to remote control terminal, fed back as control result.
S5, the remote control result of electrical equipment is fed back by real-time video to control terminal, obtains the reality of electrical equipment
When state value, and remotely adjust cam movement, obtain multi-angle image, complete control process.
The cradle head control of S51, telecommunication network camera comprising angle adjustment, focus adjustment, to picture in holder image
Image carries out feature extraction, and by the incoming identification hardware of the feature of extraction, which is integrated in holder；
S52, the IP Camera realize that online vision facilities contours extract and pattern matching process, algorithm integration are being set
In standby, remote server participation is not needed；
S53, remotely pass through IP agreement, transmit remote-control code, which is on-line study acquisition, is stored in IP camera shooting
In machine storage；
S54, remote control interface are generated in real time by IP Camera internal algorithm, and carry out control routine mapping, are realized
Remote control.
In another specific embodiment of the invention:
To the method that the electrical equipment in domestic environment scene carries out remote wireless control Internet-based, including it is following
Step:
1, under natural lighting and scene in a home environment, the video figure of WIFI camera acquisition home equipment is used
Picture；
2, the equipment detected is identified, marks its position and type, and accordingly popped up it and control menu；In household
Equipment is identified in video image, is specifically included:
1) video image is subjected to image grayscale normalized；
2) image template for reading preset home equipment, matches the equipment in video；
3) the equipment key point of video image is calculated；
4) matching result of video image key point and template image key point is calculated；
5) according to matching result, identify whether the equipment is die plate equipment, and export result.
6) the control options menu of the equipment is corresponded in reading database, and by the control button of menu and control instruction generation
The modern conversion of code sends corresponding control instruction to equipment when user presses the control button.
3, in remote interaction interface, user interacts control to the menu of the equipment；
4, control instruction manipulates equipment by internet and household wireless network；
5, equipment running status and control result are by completing information on real-time video picture transmission to remote subscriber interface
Feedback；
6, user control simultaneously feedback control results to other equipment by control camera rotation.
The long-distance intelligent appliance control method of real-time video of embodiment of the present invention interaction, as shown in Figure 1, including following step
It is rapid:
1, pyramid decomposition is carried out to input household video image, is divided into 5 groups of pyramid scales,
Define variable dimension Gaussian function:
The scale space decomposition of household image I (x, y) are as follows:
L (x, y, σ)=G (x, y σ) * I (x, y) (2)
Wherein (x, y) is the space coordinate of image, and σ is the scale coordinate of pyramid decomposition.In view of household image midfield
Scape is complicated, uses Gaussian difference scale space to improve the dimensional stability of key point:
D (x, y, σ)=(G (x, y, k σ)-G (x, y, σ)) * I (x, y)=L (x, y, k σ)-L (x, y, σ) (3)
The Gaussian difference pyrene of image and different scale is done into convolution algorithm.
2, it is decomposed in pyramid and calculates spatial extrema point in image.Specific step an are as follows: pixel is selected, and at it
8 pixels adjacent in 3 × 3 sub-blocks do gray scale size and compare on same scale image, then again and two above and below its is adjacent
18 pixels on a space scale image do gray scale size and compare, and obtain the extreme value of scale space and two dimensional image space
Point.
3, it is accurately positioned key point on the basis of Local Extremum, Taylor expansion is calculated to DOG function (3):
Extreme point are as follows:
4, skirt response is eliminated, the Hessian matrix of picture point is calculated:
Enabling α, β is respectively the minimax characteristic value of H-matrix, α=k β,
When two characteristic values are equal, which is minimized, and enables r=10, whenWhen, retain key point.
5, the gradient of pixel is calculated:
6, according to the histogram of gradients in the 8 of key point directions, the aggregate-value of each histogram of gradients is drawn, professional etiquette of going forward side by side
Generalized obtains normalized feature, and this feature parameter is inputted deep learning network,
Realize the image classification identification of scene.
7, in household scene, Image Acquisition is carried out to the electrical equipment for needing to identify control in pretreatment stage, in reality
When cognitive phase, carry out exhaustive matching with the image in real time obtained using the image of acquisition, realize to the equipment in actual scene
Identification.
8, after completing equipment identification, the control interface options menu of the equipment is shown that in video, user can be therewith
Carry out remote interaction.
The invention has the advantages that
1, it is directed to home equipment, by the equipment Image Acquisition of pretreatment stage, control template is obtained, makes the identification of equipment
Matching has specific aim, and the calculating for reducing recognizer is time-consuming.
2, it is matched using gradient orientation histogram to reduce the rotation of real video, scaling deformation, makes accuracy of identification
It is improved.
3, by intelligent Matching device class model, corresponding control interface is called, realizes accurately setting to device parameter
It sets.
4, use long-distance video scene as the control interface phase for using cartoon character in main interface, with traditional intelligence household
Than there is intuitive visible, the control result real-time Transmission of control equipment, and domestic environment can be long-range as it can be seen that keeping control process true
It is real reliable, impression that the user experience is improved.
It should be understood that for those of ordinary skills, it can be modified or changed according to the above description,
And all these modifications and variations should all belong to the protection domain of appended claims of the present invention.
Claims (6)
1. a kind of long-distance intelligent appliance control method of real-time video domestic environment equipment identification interaction, which is characterized in that realize
In domestic environment scene, the electric appliance in domestic environment, equipment are identified using web camera, and according to recognition result
The control interface for opening corresponding equipment, carries out the long-range control of equipment electric appliance, while control result is carried out in real-time video
Feedback, method includes the following steps:
S1, using the IP Camera based on WIFI network, monitor household scene, acquire the multi-angle image in domestic environment,
And image is pre-processed, comprising: gray processing, binaryzation, marginalisation operation；
S2, using online equipment Shape Classification device, pretreated image is matched with the model in the classifier, to household
Facility information present in environment does just positioning, extracts just localization region image, the input as equipment recognition classifier；
S3, the first localization region image to extraction, call online device class device model, right using deep learning matching algorithm
The image is identified；
S4, deep learning matching algorithm identify the electrical equipment in domestic environment in real time, according to the device class identified, adjust
With the remote control mode learnt in advance, which is remotely controlled；
S5, the remote control result of electrical equipment is fed back by real-time video to control terminal, obtains the real-time shape of electrical equipment
State value, and cam movement is remotely adjusted, multi-angle image is obtained, control process is completed.
2. the long-distance intelligent appliance control method of real-time video domestic environment equipment identification interaction according to claim 1,
It is characterized in that, step S1 method particularly includes:
S11, on the video image of extraction, carry out image shape processing, edge detection is done to image first, extracts continuous side
Edge；
S12, in the profile of continuous boundary extracted region equipment, mark opens the angle point of contour area, does geometry using corner location
Correction, obtains the specification figure of the equipment.
3. the long-distance intelligent appliance control method of real-time video domestic environment equipment identification interaction according to claim 1,
It is characterized in that, step S2 method particularly includes:
S21, classifier study: in the pretreatment stage of classifier study, use plurality of devices sample defeated as training classifier
Enter, carries out classifier study, the classifier study stage decomposes input sample using multiple features, in the first positioning figure of segmentation
As in, there are erroneous detections and false retrieval, and to avoid mistakes and omissions, which is input to Shape Classification device；The classifier use exists
Line study obtains, and specific acquisition methods are: in initial phase, by the image shape processing result of the known device shot in advance
It is stored as matching template, which includes the multi-angle result of more equipment；
S22, the shape to be identified obtained in real time, are input in the Shape Classification device, carry out classifier identification to the shape, will
The maximum probability result of identification is as anticipation equipment；
S23, it is extended 10% pixel in the shape edges region, what the contour area of acquisition was identified as device class device
Input picture.
4. the long-distance intelligent appliance control method of real-time video domestic environment equipment identification interaction according to claim 1,
It is characterized in that, step S3 method particularly includes:
S31, multi-feature extraction, including edge, angle point, text and icon characteristics key value are done to the equipment image of input；
S32, multiple features are normalized, construction feature vector multi-dimensional matrix；
S33, the multi-dimensional matrix, which are input in equipment recognition classifier, carries out pattern match with template, and output recognition result is as most
Whole judgement result.
5. the long-distance intelligent appliance control method of real-time video domestic environment equipment identification interaction according to claim 1,
It is characterized in that, step S4 method particularly includes:
The recognition result for the electrical equipment that S41, marker recognition go out, calls the control of the equipment to join in remote control data library
Number；
S42, pass through transmission of video control parameter, as long-range control triggering code；
S43, control result image is compressed to by byte code stream by IP network, remote control terminal is transferred to, as control result
Feedback.
6. the long-distance intelligent appliance control method of real-time video domestic environment equipment identification interaction according to claim 1,
It is characterized in that, step S5 method particularly includes:
The cradle head control of S51, telecommunication network camera comprising angle adjustment, focus adjustment, to picture image in holder image
Feature extraction is carried out, and by the incoming identification hardware of the feature of extraction, which is integrated in holder；
S52, the IP Camera realize online vision facilities contours extract and pattern matching process, and algorithm integration is in equipment
In, do not need remote server participation；
S53, remotely pass through IP agreement, transmit remote-control code, which is on-line study acquisition, is stored in IP video camera and deposits
In storage；
S54, remote control interface are generated in real time by IP Camera internal algorithm, and carry out control routine mapping, are realized long-range
Remote control.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910477495.XA CN110336719B (en) | 2019-06-03 | 2019-06-03 | Remote intelligent home control method for real-time video home environment equipment identification interaction |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910477495.XA CN110336719B (en) | 2019-06-03 | 2019-06-03 | Remote intelligent home control method for real-time video home environment equipment identification interaction |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110336719A true CN110336719A (en) | 2019-10-15 |
| CN110336719B CN110336719B (en) | 2021-10-12 |
Family
ID=68141168
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910477495.XA Active CN110336719B (en) | 2019-06-03 | 2019-06-03 | Remote intelligent home control method for real-time video home environment equipment identification interaction |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110336719B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2022007707A1 (en) * | 2020-07-07 | 2022-01-13 | 华为技术有限公司 | Home device control method, terminal device, and computer-readable storage medium |
| CN114079589A (en) * | 2020-08-21 | 2022-02-22 | 深圳Tcl新技术有限公司 | Play control method, intelligent terminal and storage medium |
| CN115662104A (en) * | 2022-12-27 | 2023-01-31 | 北京珞安科技有限责任公司 | Device discovery connection method and system |
| CN117194947A (en) * | 2023-08-16 | 2023-12-08 | 惠州市庆展科技有限公司 | Smart home equipment characteristic determining method and system |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104977904A (en) * | 2014-04-04 | 2015-10-14 | 浙江大学 | Visible and controllable intelligent household control system and control method thereof |
| CN105204742A (en) * | 2015-09-28 | 2015-12-30 | 小米科技有限责任公司 | Control method and device of electronic equipment and terminal |
| CN105955040A (en) * | 2016-05-20 | 2016-09-21 | 深圳市大拿科技有限公司 | Intelligent household system according to real-time video picture visual control and control method thereof |
| CN106200433A (en) * | 2016-08-17 | 2016-12-07 | 北京小米移动软件有限公司 | Equipment long-range control method and device, electronic equipment |
| KR101695213B1 (en) * | 2016-04-19 | 2017-01-11 | 재단법인 실감교류인체감응솔루션연구단 | Remote device control system with menu device and method thereof |
| CN106569409A (en) * | 2016-10-13 | 2017-04-19 | 杭州鸿雁电器有限公司 | Graph capturing based household equipment control system, device and method |
| CN106658130A (en) * | 2017-01-12 | 2017-05-10 | 云南爱家智慧家庭科技有限公司 | Visual control method of household appliances |
| CN107368805A (en) * | 2017-07-17 | 2017-11-21 | 深圳森阳环保材料科技有限公司 | A kind of remote control based on the identification of intelligent domestic system electrical equipment |
| CN107682237A (en) * | 2017-09-14 | 2018-02-09 | 珠海格力电器股份有限公司 | A kind of method that household electrical appliances are controlled by mobile terminal, mobile terminal and storage device |
| CN109688370A (en) * | 2017-10-18 | 2019-04-26 | 中兴通讯股份有限公司 | Internet of things equipment control method, equipment and readable storage medium storing program for executing |
-
2019
- 2019-06-03 CN CN201910477495.XA patent/CN110336719B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104977904A (en) * | 2014-04-04 | 2015-10-14 | 浙江大学 | Visible and controllable intelligent household control system and control method thereof |
| CN105204742A (en) * | 2015-09-28 | 2015-12-30 | 小米科技有限责任公司 | Control method and device of electronic equipment and terminal |
| KR101695213B1 (en) * | 2016-04-19 | 2017-01-11 | 재단법인 실감교류인체감응솔루션연구단 | Remote device control system with menu device and method thereof |
| CN105955040A (en) * | 2016-05-20 | 2016-09-21 | 深圳市大拿科技有限公司 | Intelligent household system according to real-time video picture visual control and control method thereof |
| CN106200433A (en) * | 2016-08-17 | 2016-12-07 | 北京小米移动软件有限公司 | Equipment long-range control method and device, electronic equipment |
| CN106569409A (en) * | 2016-10-13 | 2017-04-19 | 杭州鸿雁电器有限公司 | Graph capturing based household equipment control system, device and method |
| CN106658130A (en) * | 2017-01-12 | 2017-05-10 | 云南爱家智慧家庭科技有限公司 | Visual control method of household appliances |
| CN107368805A (en) * | 2017-07-17 | 2017-11-21 | 深圳森阳环保材料科技有限公司 | A kind of remote control based on the identification of intelligent domestic system electrical equipment |
| CN107682237A (en) * | 2017-09-14 | 2018-02-09 | 珠海格力电器股份有限公司 | A kind of method that household electrical appliances are controlled by mobile terminal, mobile terminal and storage device |
| CN109688370A (en) * | 2017-10-18 | 2019-04-26 | 中兴通讯股份有限公司 | Internet of things equipment control method, equipment and readable storage medium storing program for executing |
Non-Patent Citations (2)
| Title |
|---|
| 李明进: "智能家居监控系统的设计与实现", 《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》 * |
| 杨连池等: "自动适配多种设备的智能遥控器设计与实现", 《物联网技术》 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2022007707A1 (en) * | 2020-07-07 | 2022-01-13 | 华为技术有限公司 | Home device control method, terminal device, and computer-readable storage medium |
| CN113970888A (en) * | 2020-07-07 | 2022-01-25 | 华为技术有限公司 | Household equipment control method, terminal equipment and computer readable storage medium |
| CN114079589A (en) * | 2020-08-21 | 2022-02-22 | 深圳Tcl新技术有限公司 | Play control method, intelligent terminal and storage medium |
| CN115662104A (en) * | 2022-12-27 | 2023-01-31 | 北京珞安科技有限责任公司 | Device discovery connection method and system |
| CN117194947A (en) * | 2023-08-16 | 2023-12-08 | 惠州市庆展科技有限公司 | Smart home equipment characteristic determining method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110336719B (en) | 2021-10-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110336719A (en) | A kind of long-distance intelligent appliance control method of real-time video domestic environment equipment identification interaction | |
| US11163978B2 (en) | Method and device for face image processing, storage medium, and electronic device | |
| CN100580691C (en) | Interactive human face identificiating system and method of comprehensive utilizing human face and humanbody auxiliary information | |
| WO2021052375A1 (en) | Target image generation method, apparatus, server and storage medium | |
| CN104732200B (en) | A kind of recognition methods of skin type and skin problem | |
| CN103425964B (en) | Image processing equipment and image processing method | |
| CN111901681B (en) | Intelligent television control device and method based on face recognition and gesture recognition | |
| CN102253995B (en) | Method and system for realizing image search by using position information | |
| CN110569817A (en) | system and method for realizing gesture recognition based on vision | |
| CN109542233A (en) | A kind of lamp control system based on dynamic gesture and recognition of face | |
| CN110674677A (en) | Multi-mode multi-layer fusion deep neural network for anti-spoofing of human face | |
| CN104346630A (en) | Cloud flower identifying method based on heterogeneous feature fusion | |
| Patel et al. | Hand gesture recognition system using convolutional neural networks | |
| Khowaja et al. | Facial expression recognition using two-tier classification and its application to smart home automation system | |
| Bang | Implementation of image based fire detection system using convolution neural Network | |
| CN111062308A (en) | Face recognition method based on sparse expression and neural network | |
| Nikam et al. | Bilingual sign recognition using image based hand gesture technique for hearing and speech impaired people | |
| CN112069979B (en) | Real-time action recognition man-machine interaction system | |
| JP3272584B2 (en) | Region extraction device and direction detection device using the same | |
| CN116524586A (en) | Dance scoring algorithm based on CNN and GCN gesture estimation and similarity matching | |
| Meshram et al. | Convolution Neural Network based Hand Gesture Recognition System | |
| Lin | Face detection by color and multilayer feedforward neural network | |
| WO2023137923A1 (en) | Person re-identification method and apparatus based on posture guidance, and device and storage medium | |
| CN108647608A (en) | A kind of implementation method of the smart home burglary-resisting system based on Identification of Images | |
| CN107729823B (en) | Online human-computer interaction method based on E-SOINN network |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |