CN107300976A - A kind of gesture identification household audio and video system and its operation method - Google Patents
A kind of gesture identification household audio and video system and its operation method Download PDFInfo
- Publication number
- CN107300976A CN107300976A CN201710685075.1A CN201710685075A CN107300976A CN 107300976 A CN107300976 A CN 107300976A CN 201710685075 A CN201710685075 A CN 201710685075A CN 107300976 A CN107300976 A CN 107300976A
- Authority
- CN
- China
- Prior art keywords
- gesture
- module
- audio
- control module
- video camera
- 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
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/017—Gesture based interaction, e.g. based on a set of recognized hand gestures
-
- 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
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/16—Sound input; Sound output
-
- 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
- G06V10/443—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 by matching or filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/20—Movements or behaviour, e.g. gesture recognition
- G06V40/28—Recognition of hand or arm movements, e.g. recognition of deaf sign language
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Human Computer Interaction (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Multimedia (AREA)
- Data Mining & Analysis (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- Psychiatry (AREA)
- Social Psychology (AREA)
- Evolutionary Biology (AREA)
- Audiology, Speech & Language Pathology (AREA)
- User Interface Of Digital Computer (AREA)
Abstract
The present invention discloses a kind of gesture identification household audio and video system, including pickup module, control module, audio-visual devices and video camera, and the control module is connected with pickup module, audio-visual devices and video camera respectively;Gesture recognition module is provided with the video camera, the gesture recognition module is connected with control module.Invention additionally discloses a kind of operation method of gesture identification household audio and video system.The gesture identification household audio and video system is to realize that the pattern being combined using voice and gesture accurately controls audio-visual devices.
Description
Technical field
The present invention relates to household audio and video system, and in particular to a kind of gesture identification household audio and video system and its operation method.
Background technology
In March, 2017, association has issued 65i3, and 65i3 is an intelligent television that can be chatted, and realizes complete language
Sound is manipulated, the integrated far field voices of 65i3, near field remote controller voice, and it can accomplish to recognize, understand and respond.65i3 eliminates shadow
The extras of sound equipment, such as remote control, which increase the comfort of Consumer's Experience, reduce the cost of equipment.In addition, mesh
Before have also appeared a set of suitable for the gesture operation instruction set of smart home environment and its recognition methods, it is to be directed to household internal
The gesture operation scheme that all equipment is proposed, its provide a set of gesture operation instruction set suitable for smart home environment and
Its recognition methods based on computer vision, its instruction set includes general operation method gesture and shortcut operating gesture,
A kind of utilization binocular camera is proposed under general operation mode the method for judging apparatus to be controlled is pointed to position of human eye and finger.
China's smart home starting very late, studies not deep enough, technology is ripe not enough, and the development of Intelligent home theater is also
In the presence of some it is obvious the problem of and defect.Although above-mentioned 65i3 is Voice command, but the different region of culture background
Language differs greatly, so can not smoothly promote away very much.The gesture operation instruction set of above-mentioned smart home environment
And its binocular camera used in recognition methods needs to be tracked identification to human eye, face, finger, gesture many places, it is impossible to
Ensure the quality and complexity of its image procossing, therefore the validity of instruction can not be ensured.In addition, the hand of smart home environment
The controlled furniture mentioned in gesture operational order collection and its recognition methods is more, and the gesture limitednumber of the mankind, it is impossible to all
Fitment has detailed control instruction.Gesture of the same race has different control instructions to a variety of families so that two kinds of furniture are not
It is convenient to use operation simultaneously, " misunderstanding of machine " can be formed, so as to Consumer's Experience can be caused not good.
The content of the invention
The present invention one of purpose be to provide a kind of gesture identification household audio and video system, use voice to realize
Audio-visual devices are accurately controlled with the pattern that gesture is combined.
To solve above-mentioned purpose, the present invention is adopted the following technical scheme that:
A kind of gesture identification household audio and video system, including pickup module, control module, audio-visual devices and video camera, it is described
Control module is connected with pickup module, audio-visual devices and video camera respectively;The pickup module is used for recognition start-up voice signal,
Starting-up signal is sent after recognizing successfully to control module;The control module is used for the starting-up signal for receiving pickup module, then
Start-up command is sent to audio-visual devices and video camera;The control module is used for the signal for receiving video camera, is then set to audio-visual
Preparation goes out operational order;Gesture recognition module is provided with the video camera, the gesture recognition module is connected with control module;Institute
Stating gesture recognition module is used to recognize the images of gestures signal that video camera is absorbed, and recognition result is sent to control module.
Preferably, the video camera is Kinect video cameras.
Extracted preferably, the gesture recognition module includes image pre-processing module, Hand Gesture Segmentation module, gesture feature
Module and gesture matching module, described image pretreatment module, Hand Gesture Segmentation module, gesture feature extraction module and gesture matching
Module is sequentially connected.
Preferably, the Hand Gesture Segmentation module includes skin color segmentation module and contours segmentation module, the skin color segmentation
Module and the connection of contours segmentation module.In skin color segmentation module based in skin color segmentation and contours segmentation module based on hand
Both can smoothly exchange for shape contour segmentation, i.e., pretreated image, which can be introduced into skin color segmentation module, to carry out being based on skin
Color is split, and the rear contours segmentation module that enters carries out, based on the segmentation of hand shape contour, being also introduced into the progress of contours segmentation module
It is rear to be based on skin color segmentation into progress in skin color segmentation module based on the segmentation of hand shape contour.
More than one gesture is included preferably, being provided with the gesture matching module in gesture library, the gesture library,
The different operational order of each gesture correspondence, the operational order is used to send to control module.
Preferably, comprising 14 different gestures in the gesture library, it is first that 14 different gestures correspond to upper one respectively
Song or a upper channel, upper one first song or a upper channel, reduction one-level volume, increase one-level volume, reduction Pyatyi sound
Amount, increase Pyatyi volume, popup menu carry out system setting, determine the option chosen, select a upper option, select next choosing
The operational order of item, the Jing Yin, video that release is Jing Yin, pause is being played and shutdown.
It is a further object of the present invention to provide a kind of operation method of gesture identification household audio and video system.
Convolutional neural networks are used in a kind of operation method of gesture identification household audio and video system, the operation method.
Preferably, comprising the following steps:
1) pickup module receives and identifies the voice signal of start, and starting-up signal is sent after recognizing successfully to control module,
Control module sends start-up command to audio-visual devices and video camera;
2) video camera receives and identifies images of gestures, and recognition result is sent after recognizing successfully to control module, control module
Operational order is sent to audio-visual devices.
Preferably, the step 2) in, video camera is received after images of gestures, and the depth image in images of gestures is entered
Row identification, comprises the following steps:
A) line noise filter operation is entered to depth image;
B) depth image after being operated to noise filtering is split;
C) depth image feature is extracted on depth image after singulation and is used as sample;
D) the depth image feature samples of extraction and the data in gesture library are carried out into one-to-many contrast to match, matched
Corresponding operational order.
Preferably, the depth image in the step b) after noise filtering is operated is utilized based on the colour of skin and based on hand
Two methods of portion's shape contour are split to it.
The beneficial effects of the invention are as follows:
1. gesture identification household audio and video system of the present invention is by provided with pickup module and gesture recognition module, combining voice
With two kinds of operating methods of gesture, as long as user can just adjust audio-visual devices state by the change of gesture, such as volume is added and subtracted,
Converted channel, music pause, system is set, shutdown etc. sequence of operations, and it is controlled flexibly and accuracy is high, user's body
Test effect good;
2. the operation method of gesture identification household audio and video system of the present invention uses convolutional neural networks and gesture is carried out
Training and identification, the operation method are high to the precision of gesture identification, and stability is good;
3. gesture identification household audio and video system of the present invention completely disengages from the limitation of remote control, being manufactured into for extras is saved
This, is conducive to market development.
Brief description of the drawings
Fig. 1 is gesture identification household audio and video system structured flowchart provided in an embodiment of the present invention.
Fig. 2 is gesture recognition module structured flowchart in gesture identification household audio and video system provided in an embodiment of the present invention.
Fig. 3 is gesture identification household audio and video system workflow diagram provided in an embodiment of the present invention.
Fig. 4 is the schematic diagram of each unit of neutral net in the embodiment of the present invention.
Fig. 5 is the schematic diagram of a neutral net with a hidden layer in the embodiment of the present invention.
Embodiment
The technical scheme provided with reference to Fig. 1-5 couples of present invention is illustrated in more detail.
The embodiment of the present invention provides a kind of gesture identification household audio and video system, as shown in figure 1, the gesture identification home theater
System includes pickup module, control module, audio-visual devices and Kinect video cameras, control module respectively with pickup module, audio-visual
Equipment and video camera connection.
Pickup module is used for recognition start-up voice signal, and starting-up signal is sent after recognizing successfully to control module.
Control module is used for the starting-up signal for receiving pickup module, and then audio-visual devices and Kinect video cameras are sent out
Machine is instructed;Control module is used for the signal for receiving Kinect video cameras, then sends operational order to audio-visual devices.
By using Kinect video cameras, the gesture identification household audio and video system in the embodiment of the present invention is set to obtain hand
The depth information of gesture image, and 3D processing can be carried out to image, gesture motion can be more accurately judged, for closely
Difference division can be carried out with remote gesture, will be intelligent than using general video camera.As shown in figure 1, Kinect takes the photograph
Gesture recognition module is provided with shadow machine, gesture recognition module is connected with control module;Gesture recognition module is used to recognize Kinect
The images of gestures signal that video camera is absorbed, recognition result is sent to control module.As shown in Fig. 2 gesture recognition module bag
Include image pre-processing module, Hand Gesture Segmentation module, gesture feature extraction module and gesture matching module, image pre-processing module,
Hand Gesture Segmentation module, gesture feature extraction module and gesture matching module are sequentially connected.Image pre-processing module be used for pair
The images of gestures that Kinect video cameras are received is pre-processed, and preprocessing process is exactly to carry out image enhaucament by removing noise,
The sensor of Kinect video cameras is due to using laser speckle technique, thus the depth information obtained usually makes an uproar comprising very big
Sound, this can produce no small influence for follow-up data processing and experiment, therefore be needed in pretreatment stage to depth image
Carry out the filtering operation of noise.
Hand Gesture Segmentation module includes skin color segmentation module and contours segmentation module, skin color segmentation module and contours segmentation module
Connection.Hand Gesture Segmentation has based on skin color segmentation and splits two methods based on hand shape contour, and two methods are individually operated
All there is very big deficiency, the segmentation that can make images of gestures with reference to two methods will not both have been influenceed by background color, again
Can accurately it be split according to hand shape contour, i.e., Hand Gesture Segmentation has merged two kinds of decision methods, it is to avoid single is sentenced
Determining the limitation of method causes the problem of machine recognition accuracy rate is low.Image pre-processing module, skin color segmentation module, contours segmentation
Module and gesture feature extraction module are sequentially connected, and pretreated image, which is introduced into skin color segmentation module, to carry out being based on the colour of skin
Segmentation, enters back into contours segmentation module and carries out, based on the segmentation of hand shape contour, finally carrying out gesture feature extraction.Hand Gesture Segmentation
In the division based on skin color segmentation should be noted is exactly that the colour of skin of differentiation from background color and different ethnic groups is distinguished.Gesture
Segmentation module can remove a part of hand redundancy, retain important information, in case feature extraction is used.Obtain gesture figure
As the feature of depth intervals will consider the division in interval, in the case of comprising whole images of gestures information, appropriate balance
Each interval length and total interval number so that distinguish obvious as far as possible, just can so extract the depth of images of gestures
The feature of information.
It is provided with gesture matching module in gesture library, gesture library comprising 14 different gestures, each gesture correspondence is different
Operational order, the operational order is used to send to control module, more perfect by setting various gestures action to form
Gesture library, operational order rotation species is more, and the gesture in the gesture library is designed according to people's habits and customs, simple to operate
Flexibly, easily it is accepted.14 different gestures correspond to respectively upper one first song or a upper channel, a upper head songs or
A upper channel, reduction one-level volume, increase one-level volume, the Pyatyi volume that reduces, increase Pyatyi volume, popup menu system
System sets, determine the option chosen, the upper option of selection, selection the next option, Jing Yin, release is Jing Yin, suspend what is played
Video and the operational order of shutdown.The corresponding operational order of gesture such as following table:
As shown in figure 3, the workflow of gesture identification household audio and video system is:The voice that pickup module first receives start refers to
Order, collection receives images of gestures after Kinect video cameras are opened, and image pre-processing module is located in advance to the images of gestures of reception
Reason, Hand Gesture Segmentation module is split to pretreated images of gestures, and gesture feature extraction module is to the gesture figure after segmentation
As carrying out feature extraction, the feature gesture feature corresponding with the matching in the gesture library trained after extraction is matched into
After work(, corresponding operational order is exported, after it fails to match, Kinect video cameras resurvey reception images of gestures, and the match is successful
Corresponding operational order is exported to control module afterwards, and control module finally sends corresponding operational order to audio-visual devices.
Convolutional neural networks are used in a kind of operation method of gesture identification household audio and video system, the operation method.Pass through
Gesture is gathered as training set, training convolutional neural networks, the difference of convolutional neural networks and general neural network is, convolution
Neutral net contains a feature extractor being made up of convolutional layer and sub-sampling layer.In a CNN convolutional layer, generally
Comprising several characteristic planes, each characteristic plane is made up of the neuron of some rectangular arrangeds, the god of same characteristic plane
Through the shared weights of member, shared weights are exactly convolution kernel here.Convolution kernel is general to be initialized in the form of random decimal matrix,
Study is obtained rational weights by convolution kernel in the training process of network.The direct benefit that shared weights are brought is that reduction network is each
Connection between layer, while reducing the risk of over-fitting again.Sub-sampling is also referred to as pond, generally there is average sub-sampling and maximum
It is worth two kinds of forms of sub-sampling.Sub-sampling is considered as a kind of special convolution process.Convolution and sub-sampling enormously simplify model
Complexity, reduces the parameter of model.Convolutional neural networks are made up of three parts, and Part I is input layer, and Part II is by n
The combination composition of individual convolutional layer and pond layer, Part III is made up of the multi-layer perception (MLP) linked entirely a grader.Nerve net
Each unit in network is as shown in figure 4, corresponding formula is as follows:
Wherein, the unit can also be referred to as Logistic regression models.When multiple units are combined and had
During hierarchy, neural network model is formed.
As shown in figure 5, it shows a neutral net with a hidden layer, this is very simple three layers of nerve
Network model, including input layer, hidden layer and output layer.It is similar can according to demand by hidden layer expand to three layers, four
Layer or more layers.Neural network model formula above is as follows:
A kind of operation method of gesture identification household audio and video system, comprises the following steps:
1) pickup module receives and identifies the voice signal of start, and starting-up signal is sent after recognizing successfully to control module,
Control module sends start-up command to audio-visual devices and Kinect video camera;
2) Kinect video camera receives and identifies images of gestures, and recognition result is sent after recognizing successfully to control module, control
Molding block sends operational order to audio-visual devices.
Above-mentioned steps 2) in, Kinect video camera is received after images of gestures, and the depth image in images of gestures is carried out
Identification, comprises the following steps:
A) line noise filter operation is entered to depth image;
B) depth image after being operated to noise filtering is split;
C) depth image feature is extracted on depth image after singulation and is used as sample;
D) the depth image feature samples of extraction and the data in gesture library are carried out into one-to-many contrast to match, matched
Corresponding operational order.
Depth image in above-mentioned steps b) after noise filtering is operated is utilized based on the colour of skin and based on hand shaped wheel
Wide two methods are split to it.
Claims (10)
1. a kind of gesture identification household audio and video system, it is characterised in that:
Including pickup module, control module, audio-visual devices and video camera, the control module respectively with pickup module, audio-visual set
The connection of standby and video camera;
The pickup module is used for recognition start-up voice signal, and starting-up signal is sent after recognizing successfully to control module;
The control module is used for the starting-up signal for receiving pickup module, then sends start to audio-visual devices and video camera and refers to
Order;The control module is used for the signal for receiving video camera, then sends operational order to audio-visual devices;
Gesture recognition module is provided with the video camera, the gesture recognition module is connected with control module;
The gesture recognition module is used to recognize the images of gestures signal that video camera is absorbed, and recognition result is sent to control mould
Block.
2. gesture identification household audio and video system according to claim 1, it is characterised in that:The video camera is taken the photograph for Kinect
Shadow machine.
3. gesture identification household audio and video system according to claim 2, it is characterised in that:The gesture recognition module includes
Image pre-processing module, Hand Gesture Segmentation module, gesture feature extraction module and gesture matching module, described image pretreatment mould
Block, Hand Gesture Segmentation module, gesture feature extraction module and gesture matching module are sequentially connected.
4. gesture identification household audio and video system according to claim 3, it is characterised in that:The Hand Gesture Segmentation module includes
Skin color segmentation module and contours segmentation module, skin color segmentation module and contours segmentation the module connection.
5. gesture identification household audio and video system according to claim 4, it is characterised in that:Set in the gesture matching module
Have and more than one gesture is included in gesture library, the gesture library, the different operational order of each gesture correspondence, the operational order
For sending to control module.
6. gesture identification household audio and video system according to claim 5, it is characterised in that:14 are included in the gesture library
Different gestures, 14 different gestures correspond to upper one first song or a upper channel, upper one first song or a upper frequency respectively
Road, reduce one-level volume, increase one-level volume, the Pyatyi volume that reduces, increase Pyatyi volume, popup menu carry out system setting,
It is determined that the option chosen, the upper option of selection, selection the next option, Jing Yin, release is Jing Yin, suspend the video played and pass
The operational order of machine.
7. a kind of operation method of the gesture identification household audio and video system based on described in claim 1-6, it is characterised in that:The fortune
Make to use convolutional neural networks in method.
8. the operation method of gesture identification household audio and video system according to claim 7, it is characterised in that including following step
Suddenly:
1) pickup module receives and identifies the voice signal of start, and starting-up signal is sent after recognizing successfully to control module, control
Module sends start-up command to audio-visual devices and video camera;
2) video camera receives and identifies images of gestures, recognition result is sent after recognizing successfully to control module, control module is to shadow
Sound equipment sends operational order.
9. the operation method of gesture identification household audio and video system according to claim 8, it is characterised in that:The step 2)
In, video camera is received after images of gestures, and the depth image in images of gestures is identified, comprised the following steps:
A) line noise filter operation is entered to depth image;
B) depth image after being operated to noise filtering is split;
C) depth image feature is extracted on depth image after singulation and is used as sample;
D) the depth image feature samples of extraction and the data in gesture library are carried out into one-to-many contrast to match, matches correspondence
Operational order.
10. the operation method of gesture identification household audio and video system according to claim 9, it is characterised in that:The step
B) depth image in after noise filtering is operated is utilized based on the colour of skin and it is entered based on two methods of hand shape contour
Row segmentation.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710685075.1A CN107300976A (en) | 2017-08-11 | 2017-08-11 | A kind of gesture identification household audio and video system and its operation method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710685075.1A CN107300976A (en) | 2017-08-11 | 2017-08-11 | A kind of gesture identification household audio and video system and its operation method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107300976A true CN107300976A (en) | 2017-10-27 |
Family
ID=60131635
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710685075.1A Pending CN107300976A (en) | 2017-08-11 | 2017-08-11 | A kind of gesture identification household audio and video system and its operation method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107300976A (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108334814A (en) * | 2018-01-11 | 2018-07-27 | 浙江工业大学 | A kind of AR system gesture identification methods based on convolutional neural networks combination user's habituation behavioural analysis |
CN108717524A (en) * | 2018-04-28 | 2018-10-30 | 天津大学 | It is a kind of based on double gesture recognition systems and method for taking the photograph mobile phone and artificial intelligence system |
CN108762479A (en) * | 2018-04-02 | 2018-11-06 | 珠海格力电器股份有限公司 | A kind of method and apparatus controlled |
CN113420609A (en) * | 2021-05-31 | 2021-09-21 | 湖南森鹰智造科技有限公司 | Laser radar human body gesture recognition method, electronic device and storage medium |
CN115631753A (en) * | 2022-12-23 | 2023-01-20 | 无锡迪富智能电子股份有限公司 | Intelligent remote controller for toilet and use method thereof |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102824092A (en) * | 2012-08-31 | 2012-12-19 | 华南理工大学 | Intelligent gesture and voice control system of curtain and control method thereof |
CN103092337A (en) * | 2011-11-07 | 2013-05-08 | 三星电子株式会社 | Electronic apparatus and method for controlling thereof |
CN106331874A (en) * | 2016-08-31 | 2017-01-11 | 浙江创佳数字技术有限公司 | Set top box control method and devices |
CN207408909U (en) * | 2017-08-11 | 2018-05-25 | 五邑大学 | A kind of gesture identification household audio and video system |
-
2017
- 2017-08-11 CN CN201710685075.1A patent/CN107300976A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103092337A (en) * | 2011-11-07 | 2013-05-08 | 三星电子株式会社 | Electronic apparatus and method for controlling thereof |
CN102824092A (en) * | 2012-08-31 | 2012-12-19 | 华南理工大学 | Intelligent gesture and voice control system of curtain and control method thereof |
CN106331874A (en) * | 2016-08-31 | 2017-01-11 | 浙江创佳数字技术有限公司 | Set top box control method and devices |
CN207408909U (en) * | 2017-08-11 | 2018-05-25 | 五邑大学 | A kind of gesture identification household audio and video system |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108334814A (en) * | 2018-01-11 | 2018-07-27 | 浙江工业大学 | A kind of AR system gesture identification methods based on convolutional neural networks combination user's habituation behavioural analysis |
CN108334814B (en) * | 2018-01-11 | 2020-10-30 | 浙江工业大学 | Gesture recognition method of AR system |
CN108762479A (en) * | 2018-04-02 | 2018-11-06 | 珠海格力电器股份有限公司 | A kind of method and apparatus controlled |
CN108717524A (en) * | 2018-04-28 | 2018-10-30 | 天津大学 | It is a kind of based on double gesture recognition systems and method for taking the photograph mobile phone and artificial intelligence system |
CN108717524B (en) * | 2018-04-28 | 2022-05-06 | 天津大学 | Gesture recognition system based on double-camera mobile phone and artificial intelligence system |
CN113420609A (en) * | 2021-05-31 | 2021-09-21 | 湖南森鹰智造科技有限公司 | Laser radar human body gesture recognition method, electronic device and storage medium |
CN115631753A (en) * | 2022-12-23 | 2023-01-20 | 无锡迪富智能电子股份有限公司 | Intelligent remote controller for toilet and use method thereof |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107300976A (en) | A kind of gesture identification household audio and video system and its operation method | |
CN106625678B (en) | robot expression control method and device | |
CN109522083B (en) | Page intelligent response interaction system and method | |
CN103353935B (en) | A kind of 3D dynamic gesture identification method for intelligent domestic system | |
US20210249012A1 (en) | Systems and methods for operating an output device | |
CN107862315B (en) | Subtitle extraction method, video searching method, subtitle sharing method and device | |
US20180032031A1 (en) | Methods and systems for photorealistic human holographic augmented reality communication with interactive control in real-time | |
CN107204032A (en) | A kind of threedimensional model rapid modeling system and method based on immersion VR | |
CN110519636A (en) | Voice messaging playback method, device, computer equipment and storage medium | |
CN106054627B (en) | Control method and device based on gesture recognition and air conditioner | |
CN112668492B (en) | Behavior recognition method for self-supervision learning and skeleton information | |
CN106462646A (en) | Control device, control method, and computer program | |
US20190073798A1 (en) | Photorealistic human holographic augmented reality communication with interactive control in real-time using a cluster of servers | |
CN110059593A (en) | A kind of human facial expression recognition method based on feedback convolutional neural networks | |
US20220217266A1 (en) | Multimedia data processing method and apparatus | |
CN111126280A (en) | Gesture recognition fusion-based aphasia patient auxiliary rehabilitation training system and method | |
WO2021173789A1 (en) | Augmented reality guest recognition systems and methods | |
CN108681398A (en) | Visual interactive method and system based on visual human | |
CN108415561A (en) | Gesture interaction method based on visual human and system | |
CN106250832A (en) | A kind of national recognition methods based on integrated convolutional neural networks | |
CN109760067B (en) | Intelligent robot system and equipment capable of playing cards | |
CN207408909U (en) | A kind of gesture identification household audio and video system | |
CN111185903B (en) | Method and device for controlling mechanical arm to draw portrait and robot system | |
EP3983932A1 (en) | A biometric verification framework that utilizes a convolutional neural network for feature matching | |
CN104020957B (en) | Digital types of facial makeup in Beijing operas stereoprojection interactive system |
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 |