CN106096720A - A kind of method that dance movement is automatically synthesized - Google Patents
A kind of method that dance movement is automatically synthesized Download PDFInfo
- Publication number
- CN106096720A CN106096720A CN201610410516.2A CN201610410516A CN106096720A CN 106096720 A CN106096720 A CN 106096720A CN 201610410516 A CN201610410516 A CN 201610410516A CN 106096720 A CN106096720 A CN 106096720A
- Authority
- CN
- China
- Prior art keywords
- action
- fragment
- music
- dance movement
- action fragment
- 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
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/008—Artificial life, i.e. computing arrangements simulating life based on physical entities controlled by simulated intelligence so as to replicate intelligent life forms, e.g. based on robots replicating pets or humans in their appearance or behaviour
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Molecular Biology (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Robotics (AREA)
- Toys (AREA)
Abstract
The invention discloses a kind of method that dance movement is automatically synthesized, comprise the steps: S1: identify the speed in music and tempo characteristic；S2: choose the action fragment meeting musical features from maneuver library, through conversion process, connects and forms continuous print dance movement.The present invention, by identifying the feature of music, chooses action fragment according to musical features, action fragment is made conversion process, and the dance movement synthesized can meet music-tempo, style；Dance movement links up, does not repeats, and has good sight.Achieve intelligent toy simply and be automatically synthesized the demand of dance movement.
Description
Technical field
The present invention relates to a kind of method that dance movement is automatically synthesized, belong to intelligent toy technical field.
Background technology
In computer graphics and the field such as robot, toy, there is the demand being automatically synthesized dance movement.Common application
Scene is such as: virtual figure image is danced with music beat on computers；Robot or toy accompanied by music beat are danced.
Common prior art such as the personage's dance movement in computer game.Common practice is for whole song,
Write dance movement.When playing melody, play the action preset.This method does not have motility, it is impossible to be automatically synthesized dance
Step action, can only pre-set action.The dance movement that the most this method makes can only be arranged in pairs or groups specific melody, applied field
Scape is single.
The additionally prior art as disclosed by Chinese patent 200910101046, the method using machine learning, selection
Join the dance movement of musical features, to be automatically synthesized dance movement.The advantage of this invention is, selected dance movement can be preferably
Ground meets music style and speed.Its shortcoming is, the technical scheme used is complicated, and operand is big, is not suitable for small machines
The equipment such as people, toy, is not suitable for the use scene high to requirement of real-time yet.
Summary of the invention
The present invention is directed to deficiencies of the prior art, it is provided that a kind of method that dance movement is automatically synthesized, simply
Realize intelligent toy and be automatically synthesized the demand of dance movement, and dance movement links up, does not repeats, sight is good.
To this end, the present invention adopts the following technical scheme that
A kind of method that dance movement is automatically synthesized, comprises the steps:
S1: identify the speed in music and tempo characteristic；
S2: choose the action fragment meeting musical features from maneuver library, through conversion process, connects formation continuous print dancing and moves
Make；
Described action fragment is a bit of action performed, and defines the body posture variation pattern of performing artist, wherein, action
The starting and ending attitude of fragment is a few reference attitude, and action fragment comprises Speed attribute, describes this section of action symbol
Closing the music of what speed, definition mode is with the velocity characteristic of music；Action fragment also comprises beat attribute, describes this section and moves
Making to be suitable for the music of what beat type, definition mode is with the tempo characteristic of music；Whether action fragment also comprises can mirror image
Attribute；Described reference attitude refers to, certain several body posture is defined as benchmark, the starting and ending appearance of everything fragment
State is all the one in these several reference attitudes.
Further, in step s 2, the step choosing action fragment from maneuver library is:
S2-1: according to the velocity characteristic identified in music, filter out the action fragment in the range of Speed attribute value is positioned at certain；
S2-2: according to the tempo characteristic identified in music, then filter out some beat attributes action movie equal to music beat
Section；
S2-3: randomly select one in the action fragment filtered out, and the beginning attitude of this action fragment is equal to performing artist
The end attitude of previous action.
Further, in step s 2, the conversion process of described action fragment is: make new advances choosing after step S2-3
After action fragment, according to the velocity characteristic T2 identified in its Speed attribute value T1, with music, this action fragment is done speed change
Processing, speed change ratio is T1/T2；
Further, after selecting new element fragment after step S2-3, if this action fragment can mirror image, then
Mirror image processing is done in this action, as next action fragment, after being spliced to the action fragment of transformed process.
Further, the variable-speed processing of described action fragment refers to, the overall time of action fragment is accelerated in proportion or
Slack-off.
Further, the mirror image processing of described action fragment refers to, by action fragment along about actor body axis
Mirror image, becomes a new action fragment.
Further, in the method for attachment of said two action fragment, after the end attitude of previous action is equal to, one moves
The beginning attitude made.
The present invention is by identifying the feature of music, and chooses action fragment according to musical features, convert action fragment
Processing, the dance movement synthesized can meet music-tempo, style；And dance movement links up, do not repeats, have and well view and admire
Property.By defining several reference actions, make the splicing between action fragment smooth, do not have factitious attitude to suddenly change, the most raw
Hard action switching；By choosing action fragment from maneuver library, and splice through speed change, mirror image etc., make the dancing of synthesis move
Make abundanter, be not simple repetition.Compared to prior art, the present invention also has the advantage that operand is little, it is adaptable to minicomputer
Application on the low-speed devices such as device people, toy.Achieve the demand being automatically synthesized dance movement simply.
Accompanying drawing explanation
Fig. 1 is the workflow diagram of the present invention；
Fig. 2 is the schematic description of the feature in maneuver library of the present invention to action fragment；
Fig. 3 is the schematic description of the feature of reference actions in the present invention.
Detailed description of the invention
In order to make those skilled in the art be better understood from the present invention program, below in conjunction with in the embodiment of the present invention
Accompanying drawing, carries out clear, complete description to the technical scheme in the embodiment of the present invention.
As it is shown in figure 1, the method that the dance movement of the present invention is automatically synthesized, comprise the steps:
S1: identify the speed in music and tempo characteristic: wherein, the metric form of speed is " clap/minute ", and beat refers to 2/4
The beat types such as bat, 3/4 bat；Identification to musical features can use the prior art of association area, is not repeated herein；By knowing
Other musical features, corresponds to the dance movement being automatically synthesized on the speed of music, beat, it is ensured that dance movement is in accordance with music；
S2: choose the action fragment meeting musical features from maneuver library, through conversion process, connects formation continuous print dancing and moves
Make；
Maneuver library contains some default action fragments, and wherein, action fragment is a bit of action performed, and defines table
The body posture variation pattern of person's of drilling (virtual image on robot, toy or computer), wherein, action fragment initial and
Terminating attitude is a few reference attitude, and action fragment comprises Speed attribute, describes what speed this section of action meets
Music, definition mode is with the velocity characteristic of music；Action fragment also comprises beat attribute, describes what this section of action be suitable for
The music of beat type, definition mode is with the tempo characteristic of music；Whether action fragment also comprises can mirror image attribute；Described benchmark
Attitude refers to, certain several body posture is defined as benchmark, and the starting and ending attitude of everything fragment is all that these are several
One in reference attitude.
The action fragment describing mode to actor body attitude, it is possible to use the existing method in this area, such as, at 3D
In modeling software, parts each to actor body define a series of key frames, and each key frame defines duration, joint rotates
Direction etc., by these modes, can be with the attitudes vibration of health in a series of definition a period of times.
In step s 2, the concrete steps choosing action fragment from maneuver library can be:
S2-1: according to the velocity characteristic identified in music, filter out the action fragment in the range of Speed attribute value is positioned at certain；
S2-2: according to the tempo characteristic identified in music, then filter out some beat attributes action movie equal to music beat
Section；
S2-3: randomly select one in the action fragment filtered out, and the beginning attitude of this action fragment is equal to performing artist
The end attitude of previous action.
In step s 2, the conversion process of described action fragment is: selecting new element fragment after step S2-3
Afterwards, according to the velocity characteristic T2 identified in its Speed attribute value T1, with music, this action fragment is done variable-speed processing, become
Speed ratio example is T1/T2, is formed；
After selecting new element fragment after step S2-3, if this action fragment can mirror image, then by this action
Do mirror image processing, as next action fragment, after being spliced to the action fragment of transformed process.
The variable-speed processing of described action fragment refers to, is accelerated in proportion or slack-off the overall time of action fragment.
The mirror image processing of described action fragment refers to, by action fragment along left and right, actor body axis mirror image, becomes
One new action fragment.
In the method for attachment of said two action fragment, the end attitude of previous action is equal to the beginning appearance of latter action
State.Two such action energy smooth registration,
As Figure 1-3, below as a example by a robot automatically can danced with music, detailed dance movement is automatically synthesized
Method:
In the present embodiment, robot uses single-chip microcomputer (MCU) to control, and the health of robot has three mobilizable joints,
The range of movement in each joint is by a definition, and the scope of numeral is 0 to 100；The current action of robot is to compile in Fig. 2
Number it is the action fragment of 1, needs the next action of synthesis.
" music " in Fig. 1 sound outside the mike of robot interior picks up, form is PCM；" musical features is known
Not " step use prior art, identify music-tempo be 126 bats/minute, beat is 2/4 bat.
The step of " action is chosen " is:
First according to the speed 126 of music clap/minute, filter out from the maneuver library shown in Fig. 2 speed 90-150 clap/minute
In the range of action fragment, the action fragment of numbered 1 and 2 meets this condition；
Subsequently, it is 2/4 bat according to the beat of music, filters out the action equal to 2/4 bat of the action beat, the numbered action of 1,2
Fragment meets this condition；
Then, according to the end attitude " attitude B " of robot current action, filter out the action that reference attitude is attitude B, numbering
Be 2 action fragment meet this condition；
Due to the selection result only one of which action, so choosing action fragment 2 as next action.
The step of " action conversion process " is:
First according to the speed 126 of music clap/minute, and the speed of action fragment 2 be 120 bats/minute, by action fragment 2
Do quickening to process, make the time span of action fragment 2 become 120/126 ≈ 0.95 times；Action after process is " action fragment
2a”；
Then because action fragment 2 can mirror image, the attitude description of action fragment 2a is done according to robot health axis
Left and right mirror image processing, becomes " action fragment 2b "；
The step of " action splicing " is: action fragment 2a, action fragment 2b is spliced successively after current action, becomes coherent
Dance movement.
In the whole step of embodiment, robot by accepting external voice, use the present invention method, be automatically synthesized
Going out to meet the dance movement of music, then corresponding motion is made in the joint of driven machine people.Thus allow robot with music jump
Dance.
Obviously, described embodiment is only a part of embodiment of the present invention rather than whole embodiments.Based on
Embodiment in the present invention, it is every other that those of ordinary skill in the art are obtained under not making creative work premise
Embodiment, all should belong to the scope of protection of the invention.
Claims (7)
1. the method that dance movement is automatically synthesized, comprises the steps:
S1: identify the speed in music and tempo characteristic；
S2: choose the action fragment meeting musical features from maneuver library, through conversion process, connects formation continuous print dancing and moves
Make；
Described action fragment is a bit of action performed, and defines the body posture variation pattern of performing artist, wherein, action
The starting and ending attitude of fragment is a few reference attitude, and action fragment comprises Speed attribute, describes this section of action symbol
Closing the music of what speed, definition mode is with the velocity characteristic of music；Action fragment also comprises beat attribute, describes this section and moves
Making to be suitable for the music of what beat type, definition mode is with the tempo characteristic of music；Whether action fragment also comprises can mirror image
Attribute；Described reference attitude refers to, certain several body posture is defined as benchmark, the starting and ending appearance of everything fragment
State is all the one in these several reference attitudes.
The method that dance movement the most according to claim 1 is automatically synthesized, it is characterised in that: in step s 2, from action
The step choosing action fragment in storehouse is:
S2-1: according to the velocity characteristic identified in music, filter out the action fragment in the range of Speed attribute value is positioned at certain；
S2-2: according to the tempo characteristic identified in music, then filter out some beat attributes action movie equal to music beat
Section；
S2-3: randomly select one in the action fragment filtered out, and the beginning attitude of this action fragment is equal to performing artist
The end attitude of previous action.
The method that dance movement the most according to claim 1 is automatically synthesized, it is characterised in that: in step s 2, described dynamic
The conversion process making fragment is: after selecting new element fragment after step S2-3, according to its Speed attribute value T1, with
The velocity characteristic T2 identified in music, does variable-speed processing to this action fragment, and speed change ratio is T1/T2.
The method that dance movement the most according to claim 1 is automatically synthesized, it is characterised in that: selecting after step S2-3
Take out after new element fragment, if this action fragment can mirror image, then mirror image processing is done in this action, moves as the next one
Make fragment, after being spliced to the action fragment of transformed process.
The method that dance movement the most according to claim 1 is automatically synthesized, it is characterised in that: the speed change of described action fragment
Process refers to, is accelerated in proportion or slack-off the overall time of action fragment.
The method that dance movement the most according to claim 1 is automatically synthesized, it is characterised in that: the mirror image of described action fragment
Process refers to, by action fragment along left and right, actor body axis mirror image, becomes a new action fragment.
The method that dance movement the most according to claim 1 is automatically synthesized, it is characterised in that: said two action fragment
In method of attachment, the end attitude of previous action is equal to the beginning attitude of latter action.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610410516.2A CN106096720A (en) | 2016-06-12 | 2016-06-12 | A kind of method that dance movement is automatically synthesized |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610410516.2A CN106096720A (en) | 2016-06-12 | 2016-06-12 | A kind of method that dance movement is automatically synthesized |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106096720A true CN106096720A (en) | 2016-11-09 |
Family
ID=57229172
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610410516.2A Pending CN106096720A (en) | 2016-06-12 | 2016-06-12 | A kind of method that dance movement is automatically synthesized |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106096720A (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107594739A (en) * | 2017-09-03 | 2018-01-19 | 泉州迪特工业产品设计有限公司 | A kind of intelligence dazzles cruel footwear and its implementation |
| CN107682654A (en) * | 2017-09-30 | 2018-02-09 | 北京金山安全软件有限公司 | Video recording method, shooting device, electronic equipment and medium |
| CN108052250A (en) * | 2017-12-12 | 2018-05-18 | 北京光年无限科技有限公司 | Virtual idol deductive data processing method and system based on multi-modal interaction |
| CN108527376A (en) * | 2018-02-27 | 2018-09-14 | 深圳狗尾草智能科技有限公司 | Control method, apparatus, equipment and the medium of robot dance movement |
| CN110992449A (en) * | 2019-11-29 | 2020-04-10 | 网易（杭州）网络有限公司 | Dance action synthesis method, device, equipment and storage medium |
| CN112365568A (en) * | 2020-11-06 | 2021-02-12 | 广州小鹏汽车科技有限公司 | Audio processing method and device, electronic equipment and storage medium |
| WO2021134942A1 (en) * | 2019-12-31 | 2021-07-08 | 网易（杭州）网络有限公司 | Dance animation processing method and apparatus, electronic device, and storage medium |
| CN113590872A (en) * | 2021-07-28 | 2021-11-02 | 广州艾美网络科技有限公司 | Method, device and equipment for generating dance spectral plane |
| CN113643442A (en) * | 2021-08-06 | 2021-11-12 | 福建凯米网络科技有限公司 | Virtual object dance generation method and computer storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101524594A (en) * | 2009-04-17 | 2009-09-09 | 中国地质大学（武汉） | Anthropomorphic robot autonomously dancing along with rhythm |
| CN101615302A (en) * | 2009-07-30 | 2009-12-30 | 浙江大学 | The dance movement generation method that music data drives based on machine learning |
| CN101693371A (en) * | 2009-09-30 | 2010-04-14 | 深圳先进技术研究院 | Robot capable of dancing by following music beats |
-
2016
- 2016-06-12 CN CN201610410516.2A patent/CN106096720A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101524594A (en) * | 2009-04-17 | 2009-09-09 | 中国地质大学（武汉） | Anthropomorphic robot autonomously dancing along with rhythm |
| CN101615302A (en) * | 2009-07-30 | 2009-12-30 | 浙江大学 | The dance movement generation method that music data drives based on machine learning |
| CN101693371A (en) * | 2009-09-30 | 2010-04-14 | 深圳先进技术研究院 | Robot capable of dancing by following music beats |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107594739A (en) * | 2017-09-03 | 2018-01-19 | 泉州迪特工业产品设计有限公司 | A kind of intelligence dazzles cruel footwear and its implementation |
| CN107682654A (en) * | 2017-09-30 | 2018-02-09 | 北京金山安全软件有限公司 | Video recording method, shooting device, electronic equipment and medium |
| CN107682654B (en) * | 2017-09-30 | 2019-11-26 | 北京金山安全软件有限公司 | Video recording method, shooting device, electronic equipment and medium |
| CN108052250A (en) * | 2017-12-12 | 2018-05-18 | 北京光年无限科技有限公司 | Virtual idol deductive data processing method and system based on multi-modal interaction |
| CN108527376A (en) * | 2018-02-27 | 2018-09-14 | 深圳狗尾草智能科技有限公司 | Control method, apparatus, equipment and the medium of robot dance movement |
| CN110992449B (en) * | 2019-11-29 | 2023-04-18 | 网易（杭州）网络有限公司 | Dance action synthesis method, device, equipment and storage medium |
| CN110992449A (en) * | 2019-11-29 | 2020-04-10 | 网易（杭州）网络有限公司 | Dance action synthesis method, device, equipment and storage medium |
| WO2021134942A1 (en) * | 2019-12-31 | 2021-07-08 | 网易（杭州）网络有限公司 | Dance animation processing method and apparatus, electronic device, and storage medium |
| CN112365568A (en) * | 2020-11-06 | 2021-02-12 | 广州小鹏汽车科技有限公司 | Audio processing method and device, electronic equipment and storage medium |
| CN113590872A (en) * | 2021-07-28 | 2021-11-02 | 广州艾美网络科技有限公司 | Method, device and equipment for generating dance spectral plane |
| CN113590872B (en) * | 2021-07-28 | 2023-11-28 | 广州艾美网络科技有限公司 | Method, device and equipment for generating dancing spectrum surface |
| CN113643442A (en) * | 2021-08-06 | 2021-11-12 | 福建凯米网络科技有限公司 | Virtual object dance generation method and computer storage medium |
| CN113643442B (en) * | 2021-08-06 | 2024-05-14 | 福建凯米网络科技有限公司 | Virtual object dance generation method and computer storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106096720A (en) | A kind of method that dance movement is automatically synthesized | |
| CN108202334B (en) | Dance robot capable of identifying music beats and styles | |
| Jordà | Sonigraphical Instruments: From FMOL to the reacTable*. | |
| Hoffman et al. | Shimon: an interactive improvisational robotic marimba player | |
| Schöllig et al. | A platform for dance performances with multiple quadrocopters | |
| Hamilton et al. | Gesture-based collaborative virtual reality performance in carillon | |
| Caspersen | It starts from any point: bill and the Frankfurt ballet | |
| CN105080774A (en) | Expandable fountain controlling system and method for synchronizing music and water type | |
| CN105243682B (en) | A kind of method of limb member model, role and two-dimension cartoon making | |
| Landry et al. | Participatory design research methodologies: A case study in dancer sonification | |
| Willett et al. | Reasons for rhythm: Multimodal perspectives on musical play | |
| CN108829253A (en) | A kind of analog music commander's playback method and device | |
| CN102799749B (en) | Automatic generating method and generating system for distributed music lamplight performance scheme | |
| Copeland | Cunningham, Collage, and the computer | |
| Oh et al. | Crafting mechatronic percussion with everyday materials | |
| Kumra et al. | Dual flexible 7 dof arm robot learns like a child to dance using q-learning | |
| JP6752465B1 (en) | Computer programs and game systems | |
| Assayag | Improvising in creative symbolic interaction | |
| Demian | Disdance-new artistic environment | |
| Hamilton | Perceptually coherent mapping schemata for virtual space and musical method | |
| Saltz | Plays are games, movies are pictures: Ludic vs. pictorial representation | |
| Jung | CHOREOGRAPHIC SOUND COMPOSITION: Towards a poetics of restriction | |
| Morris | Snake in the Labyrinth: Scenes from the Machine’s Deep Q-Learning Experience | |
| Birringer et al. | Sound and Wearables | |
| Montgomery | Becoming burlesque: Performer training in contemporary burlesque |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20161109 |