CN109241909A - A kind of long-range dance movement capture evaluating system based on intelligent terminal - Google Patents
A kind of long-range dance movement capture evaluating system based on intelligent terminal Download PDFInfo
- Publication number
- CN109241909A CN109241909A CN201811036491.XA CN201811036491A CN109241909A CN 109241909 A CN109241909 A CN 109241909A CN 201811036491 A CN201811036491 A CN 201811036491A CN 109241909 A CN109241909 A CN 109241909A
- Authority
- CN
- China
- Prior art keywords
- component
- movement
- dance movement
- dance
- standard
- 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.)
- Withdrawn
Links
Classifications
-
- 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
- G06V40/23—Recognition of whole body movements, e.g. for sport training
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Strategic Management (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Educational Administration (AREA)
- Evolutionary Computation (AREA)
- Development Economics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Social Psychology (AREA)
- Tourism & Hospitality (AREA)
- Human Computer Interaction (AREA)
- Psychiatry (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Game Theory and Decision Science (AREA)
- Evolutionary Biology (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Multimedia (AREA)
- General Business, Economics & Management (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Image Analysis (AREA)
Abstract
The present invention provides a kind of, and the long-range dance movement based on intelligent terminal captures evaluating system, comprising: intelligent terminal component, network communication component, remote computation component, limb action identification algorithm component, dance movement evaluating system, dancing standard diaphragm plate, human-computer interaction component.Operation of the present invention is convenient, dancer only needs a mobile phone, the intelligent terminals such as tablet computer, the dance movement of dancer can be acquired at the first time and be recognized with limbs, and the standard dance movement parameter that movement segment therein and dancing standard diaphragm plate are stored is subjected to matching marking, it can intuitively reflect that dancer acts the difference between standard operation and provides dancer and digitize the display terminal suggested, not only dancer can be allowed to get information about auto- defect, the dancing equipment of examining for the levels that can also be used as standard carries out marking grading to dancing standard operation, with good moral and commercial promise.The present invention has operability and versatility well, has and is widely popularized meaning.
Description
Technical field
The present invention relates to dance education fields, and in particular, to a kind of long-range dance movement capture based on intelligent terminal
Evaluating system.
Background technique
The teaching of dance movement at present be in such a way that the teacher that teaches instructs in words and by deeds, it is intuitive and by teaching person carry out language and
The interaction of limbs, based on movement explanation and Knowledge delivery, the utilization of skill and grasp strong depend-ence teacher personal experience and
Overall qualities are still short of the long-range standardization of one kind, digitized Dancing Teaching assessment system, cannot achieve trans-regional wave
The standardization of movement teaching and assessment marking.
Currently without the explanation or report for finding technology similar to the present invention, it is also not yet collected into money similar both at home and abroad
Material.
Summary of the invention
Aiming at the above shortcomings existing in the prior art, the object of the present invention is to provide a kind of based on the long-range of intelligent terminal
Dance movement captures evaluating system, which is capable of providing the long-range standardization of one kind, digitized Dancing Teaching assessment technology,
Realize the trans-regional standardization for waving movement teaching and assessment marking.
The present invention is achieved by the following technical solutions.
A kind of long-range dance movement capture evaluating system based on intelligent terminal, comprising: intelligent terminal component, network communication
Component, remote computation component, limb action identification algorithm component, dance movement evaluation and test component, dancing standard diaphragm plate and man-machine
Interactive component；Wherein:
The intelligent terminal component carries out dance movement videograph, and the dance movement video information of capture is passed through net
Network communication component is sent to remote computation component, and the dance movement video of acquisition is passed through limb action by the remote computation component
Identification algorithm component carries out limbs identification, is presented after generating limbs track and kinematic parameter by human-computer interaction component；Or,
The intelligent terminal component carries out dance movement videograph, and the dance movement video information of capture is sent to limb action
Identification algorithm component carries out limbs identification by limb action identification algorithm component, generates limbs track and kinematic parameter and leads to
It crosses network communication component and is sent to remote computation component, the remote computation component leads to the limbs track of acquisition and kinematic parameter
Man-machine interactive component is crossed to be presented；
The limb action identification algorithm component by deep learning algorithm by dancer's limbs in dance movement video into
Row identification, the identification are included at least to upper limb, lower limb, finger, foot, head, trunk and the identification in the joint for being included,
Generate the rectangular co-ordinate or pole coordinate parameter of limbs and joint and the motion profile of limbs and joint during dancing, i.e. limb
Body track and kinematic parameter；
The limbs track and kinematic parameter that the dance movement evaluation and test component retrieval limb action identification algorithm component generates
In some movement segment and carry out digitlization matching with dancing standard diaphragm plate, when in entire limbs track and kinematic parameter
After difference movement segments match one by one with dancing standard diaphragm plate, provide movement segment in current limbs track and kinematic parameter with
Movement difference between dancing standard diaphragm plate, and it is sent to human-computer interaction component；
The dancing standard diaphragm plate contains several standard dance movement parameters in dance movement；
The current dancing standard diaphragm plate database that is applicable in of the human-computer interaction component settings, show current limbs track with
Movement difference between movement segment in kinematic parameter and dancing standard diaphragm plate, and movement difference is indicated to dancer.
Preferably, the intelligent terminal component is using in smart phone, tablet computer, laptop, desktop computer
Any one.
Preferably, the network communication component is using following any one or any multiple network communication mode:
- 3G, 4G or 5G mobile network；
- WIFI wireless network；
Cable network.
Preferably, the remote computation component is using in smart phone, tablet computer, laptop, desktop computer
Any one.
Preferably, the limb action identification algorithm component operates on intelligent terminal component, or, operating in remote computation
On component.
Preferably, the deep learning algorithm that limb action identification algorithm component uses is based on TensorFlow or Caffe
Under deep learning neural network algorithm, carry out that real-time video flows down or the limbs track of existing video file and kinematic parameter are raw
At.
Preferably, limbs track generated and kinematic parameter at least cover the shoulder joint of dancer, elbow joint, wrist joint,
The kinematic parameter of hip joint, knee joint and ankle-joint.
Preferably, limb action identification algorithm component can recognize the dance movement of at least one dancer.
Preferably, each standard dance movement parameter includes following any one information:
Each joint shaft according to the movement velocity of time reference, position, acceleration and angular acceleration traffic flow information；
Each joint shaft according to the movement velocity of time reference, position, acceleration and angular acceleration traffic flow information, with
And image corresponding with traffic flow information, picture and music information.
Preferably, the dance movement assessment component includes: dancing standard diaphragm plate database interface, dance movement training calculation
Method module, dance movement matching algorithm module and dance movement assessment algorithm module, in which:
The dancing standard diaphragm plate database interface uses search engine, transfers institute in dancing standard diaphragm plate database in real time
The standard dance movement parameter included simultaneously matches with a certain movement segment of dancer and provides the value of the confidence and confidence interval；
The dance movement training algorithm module carries out convolution by the standard dance movement parameter of the same movement of magnanimity
Neural metwork training trains mathematical model, and in this, as the matching diaphragm plate of a certain specific action segment；
A series of dancer movement segment is segmented by the dance movement matching algorithm module, and will be dynamic after segmentation
Make mathematical model and the retrieval of dancing standard diaphragm plate database interface that segment is trained by dance movement training algorithm module
Standard dance movement is matched, and matching process includes the matching of joint angles parameter, the matching of moving end parameter, joint motions ginseng
Number matching and/or Image Matching；
Dance movement and dancing standard diaphragm plate in the dance movement assessment algorithm module movement segment a certain to dancer
The matching result of standard dance movement parameter in database is weighted marking, points out that dancer acts segment by score value
Degree up to standard, and point out that dancer acts the difference in segment between each limbs joint and standard operation, i.e. movement segment and dancing
Movement difference between standard diaphragm plate.
Preferably, the human-computer interaction component is using any one following display structure:
It is shown using any display screen in resistive touch screen, capacitive touch screen, inductive touch；
It is shown using any display terminal in LCD, CRT, LED, OLED, projection；
The human-computer interaction component is indicated movement difference to dancer by way of image, voice and/or text.
A kind of long-range dance movement based on intelligent terminal provided by the invention captures evaluating system,
Compared with prior art, the present invention has the following beneficial effects:
A kind of long-range dance movement based on intelligent terminal that the configuration of the present invention is simple provides captures evaluating system, and operation is just
Victory, dancer only need the intelligent terminals such as mobile phone, a tablet computer, can at the first time be acquired the dance movement of dancer
It is recognized with limbs, and movement segment therein match with the standard dance movement parameter that dancing standard diaphragm plate is stored and is beaten
Point, it can intuitively reflect that dancer acts the difference between standard operation and provides dancer and digitize the display terminal suggested,
Not only dancer can be allowed to get information about auto- defect, the dancing that can also be used as standard examines for the levels equipment to dancing standard
Movement carries out marking grading, has good moral and commercial promise.The present invention has operability and versatility well,
With being widely popularized meaning.
Detailed description of the invention
Upon reading the detailed description of non-limiting embodiments with reference to the following drawings, other feature of the invention,
Objects and advantages will become more apparent upon:
Fig. 1 is the structural schematic diagram of one embodiment of the present invention；
In figure: 01- intelligent terminal component, 02- network communication component, 03- remote computation component, the identification of 04- limb action
Algorithm component, 05- limb action identification algorithm component, 06- dancing standard diaphragm plate, 07- human-computer interaction component.
Specific embodiment
The present invention is described in detail combined with specific embodiments below.Following embodiment will be helpful to the technology of this field
Personnel further understand the present invention, but the invention is not limited in any way.It should be pointed out that the ordinary skill of this field
For personnel, without departing from the inventive concept of the premise, various modifications and improvements can be made.These belong to the present invention
Protection scope.
Embodiment
Present embodiments provide a kind of long-range dance movement capture evaluating system based on intelligent terminal, comprising: intelligence is eventually
Component, dancing mark are evaluated and tested in end pieces, network communication component, remote computation component, limb action identification algorithm component, dance movement
Quasi- diaphragm plate, human-computer interaction component.Wherein:
The intelligent terminal component is that one kind has computing capability, can run operating system and include that at least one is taken the photograph
As the calculating equipment of head, for carrying out dance movement videograph and (can according to certain compressed format the video information of capture
According to demand set) form sent by network communication component, can also pass through limb action identification algorithm component general
The dancing video of acquisition carries out limbs identification, generates limbs track and kinematic parameter, and limbs track and kinematic parameter are passed through
Network communication component is sent；
The network communication component is by the intelligent terminal component dance movement video acquired or the limb action data of identification
(limbs track and kinematic parameter) is sent to remote computation component；
The remote computation component is a kind of machine with certain computing capability, can receive the acquisition of intelligent terminal component
Dance movement video the dance movement video of acquisition is carried out by limbs identification by limb action identification algorithm component, generate limb
Body track and kinematic parameter, and presented by human-computer interaction component also can receive limbs track and kinematic parameter and straight
Man-machine interactive component was connected to be presented；
The limb action identification algorithm component is a kind of intelligent algorithm, by deep learning algorithm by dance movement video
Interior human limb recognizes, including at least the components such as upper limb, lower limb, finger, foot, head, trunk and comprising pass
Section, generates the rectangular co-ordinate or pole coordinate parameter of limbs and joint, and generates the limbs during dancing, oint motion trajectory,
That is limbs track and kinematic parameter；
Some movement segment during the limbs track that component will acquire and kinematic parameter is evaluated and tested in the dance movement
Digitlization matching is carried out with dancing standard diaphragm plate, when the different movement segments and dancing mark in entire limbs track and kinematic parameter
After quasi- diaphragm plate matches one by one, provides current limbs track and the dance movement in kinematic parameter parameter and the movement between diaphragm plate is poor
It is different, and propose discriminant amendment；
The dancing standard diaphragm plate is several standard dance movement parameters contained in dance movement, each mark
Quasi- dance movement parameter is including at least each joint shaft according to the movement velocity of time reference, position, acceleration, angular acceleration etc.
Data flow also may include in this corresponding image, picture and music information；
The human-computer interaction component is a kind of display terminal for having human-computer interaction function, is currently applicable in for setting
Diaphragm plate library, and for showing the difference in movement segment and dancing standard diaphragm plate in dancer's motion process, and pass through image, language
The modes such as sound, text will act difference and indicate to dancer.
Network communication component can be 3G, 4G, 5G mobile network, it may also be said to be WIFI, cable network；
Further, the remote computation component can be smart phone, tablet computer, laptop, desktop computer
One of Deng；
Further, the limb action identification algorithm component may operate on intelligent terminal component, can also run
On remote computation component；
Further, deep learning algorithm used by the limb action identification algorithm component can be based on
TensorFlow is also possible to carry out under real-time video flowing based on the deep learning neural network algorithm under Caffe
The identification of dance movements limbs and limbs joint motion profile generate, and can also carry out dance movements limb to one section of existing video file
Body identification and limbs joint motion profile generate；
Further, the limb action identification algorithm component at least covers the shoulder joint of human body, elbow joint, wrist pass
Section, hip joint, knee joint and ankle-joint kinematic parameter；
Further, the limb action identification algorithm component can recognize the dancing of a people and the above dancer of a people
Movement；
Preferably, the dance movement processing component includes: dancing standard diaphragm plate database interface, dance movement training calculation
Method module, dance movement matching algorithm module and dance movement assessment algorithm module, in which:
The dancing standard diaphragm plate database interface is exactly a kind of search engine, transfers dancing standard diaphragm plate database in real time
Middle included dance movement parameter simultaneously matches with the current dance movement of dancer and provides the value of the confidence and confidence interval；
The dance movement training algorithm module carries out convolution by the standard dance movement parameter of the same movement of magnanimity
Neural metwork training trains mathematical model, and in this, as the matching diaphragm plate of a certain specific action segment；
A series of dancer's dance movement segment is exactly segmented by the dance movement matching algorithm, and segmentation is dynamic
Make the standard of the mathematical model trained by dance movement training algorithm module and the retrieval of dancing standard diaphragm plate database interface
Dance movement is matched, and matching process includes but is not limited to the matching of joint angles parameter, the matching of moving end parameter, joint fortune
Dynamic parameter matching, Image Matching etc.；
The dance movement assessment algorithm is exactly dance movement and the dancing standard diaphragm plate number that will provide a certain segment of dancer
It is weighted marking according to the matching result of the standard dance movement in library, the journey up to standard of dancer's dance movement is pointed out by score value
Degree, and point out the difference of each limbs joint and standard operation in dancer's dance movement.
Preferably, the human-computer interaction component can be comprising one of resistance, capacitor, inductive touch, can also
To be inputted by mouse-keyboard etc., shown by display terminals such as LCD, CRT, LED, OLED, projections.
The technical solution of the present embodiment is described in further detail with reference to the accompanying drawing.
As shown in Figure 1, a kind of long-range dance movement based on intelligent terminal provided in this embodiment captures evaluating system, packet
Include: intelligent terminal component 01, network communication component 02, remote computation component 03, limb action identification algorithm component 04, dancing are dynamic
Make evaluation and test component 05, dancing standard diaphragm plate 06, human-computer interaction component 07.Wherein: intelligent terminal component 01 is that one kind has calculating
Ability, calculating equipment that is that operating system can be run and including at least one camera, for carrying out dance movement video note
It records and the video information of capture is sent according to the form of certain compressed format by network communication component 02, can also lead to
It crosses limb action identification algorithm component 04 and the dancing video of acquisition is subjected to limbs identification, generate limbs track and kinematic parameter,
And limbs track and kinematic parameter are sent by network communication component 02.Intelligent terminal component 01 can be intelligent hand
One of machine, tablet computer, laptop, desktop computer etc.；Network communication component 02 acquires intelligent terminal component 01
Dance movement video or the limb action data of identification be sent to remote computation component 03.Network communication component 02 can be
3G, 4G, 5G mobile network, it may also be said to be WIFI wireless network, cable network；Remote computation component 03 is a kind of with certain
The machine of computing capability, the dance movement video that can receive the acquisition of intelligent terminal component 01 pass through limb action identification algorithm portion
The dancing video of acquisition is carried out limbs identification by part 04, generates limbs track and kinematic parameter, and pass through human-computer interaction component 07
It is presented, limbs track and kinematic parameter can also be received and is directly presented by human-computer interaction component 07.Long-range meter
Calculating component 03 can be one of smart phone, tablet computer, laptop, desktop computer etc.；Limb action identification is calculated
Method component 04 is a kind of intelligent algorithm, is recognized the human limb in video by deep learning algorithm, is included at least upper
The components such as limb, lower limb, finger, foot, head, trunk and comprising joint, generate limbs and joint rectangular co-ordinate or pole
Coordinate parameters, and generate the limbs during dancing, oint motion trajectory.Limb action identification algorithm component 04 may operate in
On intelligent terminal component 01, also it may operate on remote computation component 03.Used by limb action identification algorithm component 04
Deep learning algorithm, which can be, to be also possible to based on TensorFlow based on the deep learning neural network algorithm under Caffe, can
It is generated with carrying out the identification of the dance movements limbs under real-time video flowing and limbs joint motion profile, it can also be existing to one section
Video file carries out the identification of dance movements limbs and limbs joint motion profile generates.Limb action identification algorithm component 04 is at least
Cover the shoulder joint of human body, elbow joint, wrist joint, hip joint, knee joint and ankle-joint kinematic parameter.Limb action identification is calculated
Method component 04 can recognize the dance movement of a people and the above dancer of a people；The dance that the dance movement evaluation and test component 05 will acquire
Some segment and dancing standard diaphragm plate 06 during person's kinematic parameter carry out digitlization matching, will be in entire motion process
After difference movement segment and dancing standard diaphragm plate 06 match, the difference between current dancer's kinematic parameter and diaphragm plate is provided, and mention
Discriminant amendment out.Dance movement evaluating system 05 includes: dancing standard diaphragm plate database interface, dance movement matching algorithm and dance
Step movement assessment algorithm, in which: dancing standard diaphragm plate database interface is exactly a kind of search engine, transfers dancing standard film in real time
The dance movement parameter included in plate database simultaneously matches with the current dance movement of dancer and provides the value of the confidence and confidence
Section；
A series of dancer's dance movement is exactly segmented by dance movement matching algorithm, and fragmentation action is passed through dance
The standard dance movement for stepping mathematical model and the retrieval of dancing standard diaphragm plate database interface that action training algorithm trains carries out
Matching, matching process include but is not limited to joint angles parameter matching, moving end parameter matching, joint kinematic parameter matching,
Image Matching etc.；
Dance movement assessment algorithm is exactly dance movement and the dancing standard diaphragm plate database that will provide a certain segment of dancer
In the matching result of standard dance movement be weighted marking, the degree up to standard of dancer's dance movement is pointed out by score value,
And point out the difference of each limbs joint and standard operation in dancer's dance movement；
Dancing standard diaphragm plate 06 is several standard dance movement parameters contained in dance movement, each standard
Dance movement is including at least each joint shaft according to data such as the movement velocity of time reference, position, acceleration, angular acceleration
Stream, also may include in this corresponding image, picture and music information.
Human-computer interaction component 07 is a kind of display terminal for having human-computer interaction function, for setting the film being currently applicable in
Plate library, and for showing the difference in movement segment and dancing standard diaphragm plate 06 in dancer's motion process, and pass through image, language
The modes such as sound, text will act difference and indicate to dancer.Human-computer interaction component 07 can be comprising resistance, capacitor, inductance type touching
One of screen is touched, can also be inputted by mouse-keyboard etc., pass through the display terminals such as LCD, CRT, LED, OLED, projection
It is shown.
Above-described embodiment provided by the invention, structure is simple, and it is convenient to operate, and dancer only needs mobile phone, a tablet computer
The dance movement of dancer can be acquired at the first time and recognize with limbs by equal intelligent terminals, and will therein and dancing mark
The movement that quasi- diaphragm plate is stored carries out matching marking, and the difference that can intuitively reflect between dancer's movement and standard operation simultaneously mentions
The display terminal suggested is digitized for dancer, not only dancer can be allowed to get information about auto- defect, can also be used as
The dancing of standard equipment of examining for the levels carries out marking grading to dancing standard operation, has good moral and commercial promise.This
Invention has operability and versatility well, has and is widely popularized meaning.
Specific embodiments of the present invention are described above.It is to be appreciated that the invention is not limited to above-mentioned
Particular implementation, those skilled in the art can make various deformations or amendments within the scope of the claims, this not shadow
Ring substantive content of the invention.
Claims (10)
1. a kind of long-range dance movement based on intelligent terminal captures evaluating system characterized by comprising intelligent terminal portion
Component, dancing standard film are evaluated and tested in part, network communication component, remote computation component, limb action identification algorithm component, dance movement
Plate and human-computer interaction component；Wherein:
The intelligent terminal component carries out dance movement videograph, and the dance movement video information of capture is led to by network
News component is sent to remote computation component, and the remote computation component recognizes the dance movement video of acquisition by limb action
Algorithm component carries out limbs identification, is presented after generating limbs track and kinematic parameter by human-computer interaction component；Or, described
Intelligent terminal component carries out dance movement videograph, and the dance movement video information of capture is sent to limb action identification
Algorithm component carries out limbs identification by limb action identification algorithm component, generates limbs track and kinematic parameter and passes through net
Network communication component is sent to remote computation component, and the limbs track of acquisition and kinematic parameter are passed through people by the remote computation component
Machine interactive component is presented；
The limb action identification algorithm component is distinguished dancer's limbs in dance movement video by deep learning algorithm
Know, the identification is included at least to upper limb, lower limb, finger, foot, head, trunk and the identification in the joint for being included, and is generated
The motion profile of the rectangular co-ordinate or pole coordinate parameter in limbs and joint and limbs and joint during dancing, i.e. limbs rail
Mark and kinematic parameter；
In the limbs track and kinematic parameter that the dance movement evaluation and test component retrieval limb action identification algorithm component generates
Some movement segment simultaneously carries out digitlization matching with dancing standard diaphragm plate, the difference in entire limbs track and kinematic parameter
After movement segment matches one by one with dancing standard diaphragm plate, the movement segment and dancing in current limbs track and kinematic parameter are provided
Movement difference between standard diaphragm plate, and it is sent to human-computer interaction component；
The dancing standard diaphragm plate contains several standard dance movement parameters in dance movement；
The dancing standard diaphragm plate database that the human-computer interaction component settings are currently applicable in, shows current limbs track and movement
Movement difference between movement segment in parameter and dancing standard diaphragm plate, and movement difference is indicated to dancer.
2. a kind of long-range dance movement based on intelligent terminal according to claim 1 captures evaluating system, feature exists
In the intelligent terminal component is using any one in smart phone, tablet computer, laptop, desktop computer.
3. a kind of long-range dance movement based on intelligent terminal according to claim 1 captures evaluating system, feature exists
In, the network communication component using following any one or any multiple network communication mode:
- 3G, 4G or 5G mobile network；
- WIFI wireless network；
Cable network.
4. a kind of long-range dance movement based on intelligent terminal according to claim 1 captures evaluating system, feature exists
In the remote computation component is using any one in smart phone, tablet computer, laptop, desktop computer.
5. a kind of long-range dance movement based on intelligent terminal according to claim 1 captures evaluating system, feature exists
In the limb action identification algorithm component further includes following any one or any multinomial feature:
It operates on intelligent terminal component, or, operating on remote computation component；
The deep learning algorithm used is carried out real based on the deep learning neural network algorithm under TensorFlow or Caffe
When video flowing under or existing video file limbs track and kinematic parameter generate；
The dance movement of at least one dancer can be recognized.
6. a kind of long-range dance movement based on intelligent terminal captures evaluating system, feature according to claim 1 or 5
It is, limbs track generated and kinematic parameter at least cover the shoulder joint of dancer, elbow joint, wrist joint, hip joint, knee pass
The kinematic parameter of section and ankle-joint.
7. a kind of long-range dance movement based on intelligent terminal according to claim 1 captures evaluating system, feature exists
In each standard dance movement parameter includes following any one information:
Each joint shaft according to the movement velocity of time reference, position, acceleration and angular acceleration traffic flow information；
Traffic flow information of each joint shaft according to the movement velocity of time reference, position, acceleration and angular acceleration, Yi Jiyu
The corresponding image of traffic flow information, picture and music information.
8. a kind of long-range dance movement based on intelligent terminal according to claim 1 captures evaluating system, feature exists
In the dance movement assessment component includes: dancing standard diaphragm plate database interface, dance movement training algorithm module, dancing
Act matching algorithm module and dance movement assessment algorithm module, in which:
The dancing standard diaphragm plate database interface uses search engine, transfers included in dancing standard diaphragm plate database in real time
Standard dance movement parameter and matched with a certain movement segment of dancer and provide the value of the confidence and confidence interval；
The dance movement training algorithm module carries out convolutional Neural by the standard dance movement parameter of the same movement of magnanimity
Network training trains mathematical model, and in this, as the matching diaphragm plate of a certain specific action segment；
A series of dancer movement segment is segmented by the dance movement matching algorithm module, and by the action movie after segmentation
The standard of mathematical model and the retrieval of dancing standard diaphragm plate database interface that section is trained by dance movement training algorithm module
Dance movement is matched, and matching process includes the matching of joint angles parameter, the matching of moving end parameter, joint kinematic parameter
Match and/or Image Matching；
Dance movement and dancing standard diaphragm plate data in the dance movement assessment algorithm module movement segment a certain to dancer
The matching result of standard dance movement parameter in library is weighted marking, points out that dancer acts the up to standard of segment by score value
Degree, and point out that dancer acts the difference in segment between each limbs joint and standard operation, that is, act segment and dancing standard
Movement difference between diaphragm plate.
9. a kind of long-range dance movement based on intelligent terminal according to claim 1 captures evaluating system, feature exists
In the human-computer interaction component is using any one following display structure:
It is shown using any display screen in resistive touch screen, capacitive touch screen, inductive touch；
It is shown using any display terminal in LCD, CRT, LED, OLED, projection.
10. a kind of long-range dance movement based on intelligent terminal captures evaluating system according to claim 1 or described in 10, special
Sign is that the human-computer interaction component is indicated movement difference to dancer by way of image, voice and/or text.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811036491.XA CN109241909A (en) | 2018-09-06 | 2018-09-06 | A kind of long-range dance movement capture evaluating system based on intelligent terminal |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811036491.XA CN109241909A (en) | 2018-09-06 | 2018-09-06 | A kind of long-range dance movement capture evaluating system based on intelligent terminal |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109241909A true CN109241909A (en) | 2019-01-18 |
Family
ID=65060783
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811036491.XA Withdrawn CN109241909A (en) | 2018-09-06 | 2018-09-06 | A kind of long-range dance movement capture evaluating system based on intelligent terminal |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109241909A (en) |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110705418A (en) * | 2019-09-25 | 2020-01-17 | 西南大学 | Taekwondo kicking motion video capture and scoring system based on deep LabCut |
| CN111126239A (en) * | 2019-12-19 | 2020-05-08 | 武汉西山艺创文化有限公司 | Facial expression capturing system and method based on 5G communication |
| CN111182181A (en) * | 2019-12-26 | 2020-05-19 | 武汉西山艺创文化有限公司 | Wireless virtual device and system based on 5G communication |
| CN111191536A (en) * | 2019-12-19 | 2020-05-22 | 武汉西山艺创文化有限公司 | Motion capture system and method based on 5G communication technology |
| CN111274448A (en) * | 2020-01-16 | 2020-06-12 | 石河子大学 | Dance education evaluation system and method for musics major |
| CN111803885A (en) * | 2020-07-11 | 2020-10-23 | 郭坤 | Intelligent exercise method based on international standard dance |
| CN112100436A (en) * | 2020-09-29 | 2020-12-18 | 新东方教育科技集团有限公司 | Dance segment recognition method, dance segment recognition device and storage medium |
| CN113012504A (en) * | 2021-02-24 | 2021-06-22 | 宜春职业技术学院（宜春市技术工人学校） | Multi-person dance teaching interactive projection method, device and equipment |
| CN113257055A (en) * | 2021-05-11 | 2021-08-13 | 山东体育学院 | Intelligent dance pace learning device and method |
| CN113283384A (en) * | 2021-06-17 | 2021-08-20 | 贝塔智能科技(北京)有限公司 | Taiji interaction system based on limb recognition technology |
| CN113332689A (en) * | 2021-05-24 | 2021-09-03 | 湖南师范大学 | Sports dance interest learning device beneficial to psychological health of college students and control method |
| CN115131866A (en) * | 2022-07-14 | 2022-09-30 | 南京八点八数字科技有限公司 | Adopt stage action expression sampling system of AI technique |
| US20220358310A1 (en) * | 2021-05-06 | 2022-11-10 | Kuo-Yi Lin | Professional dance evaluation method for implementing human pose estimation based on deep transfer learning |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150099252A1 (en) * | 2013-10-03 | 2015-04-09 | Autodesk, Inc. | Enhancing movement training with an augmented reality mirror |
| CN106648118A (en) * | 2017-01-25 | 2017-05-10 | 宇龙计算机通信科技(深圳)有限公司 | Virtual teaching method based on augmented reality, and terminal equipment |
| CN106778639A (en) * | 2016-12-23 | 2017-05-31 | 常州纺织服装职业技术学院 | A kind of exercise data search method based on the description of attitude relative space-time characteristic statisticses |
| CN107122752A (en) * | 2017-05-05 | 2017-09-01 | 北京工业大学 | A kind of human action comparison method and device |
| CN107909060A (en) * | 2017-12-05 | 2018-04-13 | 前海健匠智能科技（深圳）有限公司 | Gymnasium body-building action identification method and device based on deep learning |
-
2018
- 2018-09-06 CN CN201811036491.XA patent/CN109241909A/en not_active Withdrawn
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150099252A1 (en) * | 2013-10-03 | 2015-04-09 | Autodesk, Inc. | Enhancing movement training with an augmented reality mirror |
| CN106778639A (en) * | 2016-12-23 | 2017-05-31 | 常州纺织服装职业技术学院 | A kind of exercise data search method based on the description of attitude relative space-time characteristic statisticses |
| CN106648118A (en) * | 2017-01-25 | 2017-05-10 | 宇龙计算机通信科技(深圳)有限公司 | Virtual teaching method based on augmented reality, and terminal equipment |
| CN107122752A (en) * | 2017-05-05 | 2017-09-01 | 北京工业大学 | A kind of human action comparison method and device |
| CN107909060A (en) * | 2017-12-05 | 2018-04-13 | 前海健匠智能科技（深圳）有限公司 | Gymnasium body-building action identification method and device based on deep learning |
Cited By (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110705418B (en) * | 2019-09-25 | 2021-11-30 | 西南大学 | Taekwondo kicking motion video capture and scoring system based on deep LabCut |
| CN110705418A (en) * | 2019-09-25 | 2020-01-17 | 西南大学 | Taekwondo kicking motion video capture and scoring system based on deep LabCut |
| CN111126239A (en) * | 2019-12-19 | 2020-05-08 | 武汉西山艺创文化有限公司 | Facial expression capturing system and method based on 5G communication |
| CN111191536A (en) * | 2019-12-19 | 2020-05-22 | 武汉西山艺创文化有限公司 | Motion capture system and method based on 5G communication technology |
| CN111182181A (en) * | 2019-12-26 | 2020-05-19 | 武汉西山艺创文化有限公司 | Wireless virtual device and system based on 5G communication |
| CN111274448A (en) * | 2020-01-16 | 2020-06-12 | 石河子大学 | Dance education evaluation system and method for musics major |
| CN111803885A (en) * | 2020-07-11 | 2020-10-23 | 郭坤 | Intelligent exercise method based on international standard dance |
| CN112100436A (en) * | 2020-09-29 | 2020-12-18 | 新东方教育科技集团有限公司 | Dance segment recognition method, dance segment recognition device and storage medium |
| CN112100436B (en) * | 2020-09-29 | 2021-07-06 | 新东方教育科技集团有限公司 | Dance segment recognition method, dance segment recognition device and storage medium |
| WO2022068823A1 (en) * | 2020-09-29 | 2022-04-07 | 新东方教育科技集团有限公司 | Dance segment recognition method, dance segment recognition apparatus, and storage medium |
| US11837028B2 (en) | 2020-09-29 | 2023-12-05 | New Oriental Education & Technology Group Inc. | Dance segment recognition method, dance segment recognition apparatus, and storage medium |
| CN113012504A (en) * | 2021-02-24 | 2021-06-22 | 宜春职业技术学院（宜春市技术工人学校） | Multi-person dance teaching interactive projection method, device and equipment |
| US20220358310A1 (en) * | 2021-05-06 | 2022-11-10 | Kuo-Yi Lin | Professional dance evaluation method for implementing human pose estimation based on deep transfer learning |
| US11823496B2 (en) * | 2021-05-06 | 2023-11-21 | Kuo-Yi Lin | Professional dance evaluation method for implementing human pose estimation based on deep transfer learning |
| CN113257055A (en) * | 2021-05-11 | 2021-08-13 | 山东体育学院 | Intelligent dance pace learning device and method |
| CN113332689A (en) * | 2021-05-24 | 2021-09-03 | 湖南师范大学 | Sports dance interest learning device beneficial to psychological health of college students and control method |
| CN113283384A (en) * | 2021-06-17 | 2021-08-20 | 贝塔智能科技(北京)有限公司 | Taiji interaction system based on limb recognition technology |
| CN115131866A (en) * | 2022-07-14 | 2022-09-30 | 南京八点八数字科技有限公司 | Adopt stage action expression sampling system of AI technique |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109241909A (en) | A kind of long-range dance movement capture evaluating system based on intelligent terminal | |
| CN103136986B (en) | Sign Language Recognition Method and system | |
| CN111738220B (en) | Three-dimensional human body posture estimation method, device, equipment and medium | |
| CN110163059B (en) | Multi-person posture recognition method and device and electronic equipment | |
| US10061389B2 (en) | Gesture recognition system and gesture recognition method | |
| CN108983636B (en) | Man-machine intelligent symbiotic platform system | |
| CN108509026B (en) | Remote maintenance support system and method based on enhanced interaction mode | |
| CN102822862B (en) | Calculation element interface | |
| CN104616028B (en) | Human body limb gesture actions recognition methods based on space segmentation study | |
| CN102854983A (en) | Man-machine interaction method based on gesture recognition | |
| CN110428486B (en) | Virtual interaction fitness method, electronic equipment and storage medium | |
| CN103150019A (en) | Handwriting input system and method | |
| CN103226388A (en) | Kinect-based handwriting method | |
| CN102024151A (en) | Training method of gesture motion recognition model and gesture motion recognition method | |
| Yin et al. | Toward natural interaction in the real world: Real-time gesture recognition | |
| CN115543089A (en) | Virtual human emotion interaction system and method based on five-dimensional emotion model | |
| CN102222342A (en) | Tracking method of human body motions and identification method thereof | |
| CN110084192A (en) | Quick dynamic hand gesture recognition system and method based on target detection | |
| CN109145802A (en) | More manpower gesture man-machine interaction methods and device based on Kinect | |
| CN110109532A (en) | A kind of human action Compare System obtaining system based on human body attitude | |
| CN108958620A (en) | A kind of dummy keyboard design method based on forearm surface myoelectric | |
| Li et al. | Hand gesture recognition and real-time game control based on a wearable band with 6-axis sensors | |
| CN101923433A (en) | Man-computer interaction mode based on hand shadow identification | |
| Yan et al. | Human-object interaction recognition using multitask neural network | |
| CN107292295A (en) | Hand Gesture Segmentation method and device |
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 | ||
| WW01 | Invention patent application withdrawn after publication | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20190118 |