CN109255295A - Dance spectrum generation method, device, equipment and the storage medium of view-based access control model - Google Patents
Dance spectrum generation method, device, equipment and the storage medium of view-based access control model Download PDFInfo
- Publication number
- CN109255295A CN109255295A CN201810880336.XA CN201810880336A CN109255295A CN 109255295 A CN109255295 A CN 109255295A CN 201810880336 A CN201810880336 A CN 201810880336A CN 109255295 A CN109255295 A CN 109255295A
- Authority
- CN
- China
- Prior art keywords
- dancing
- dancer
- target
- video data
- dance
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
- G06T7/246—Analysis of motion using feature-based methods, e.g. the tracking of corners or segments
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/41—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items
- G06V20/42—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items of sport video content
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/46—Extracting features or characteristics from the video content, e.g. video fingerprints, representative shots or key frames
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Psychiatry (AREA)
- Social Psychology (AREA)
- Human Computer Interaction (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Image Analysis (AREA)
Abstract
The embodiment of the present invention provides dance spectrum generation method, device, equipment and the storage medium of a kind of view-based access control model.The method of the embodiment of the present invention completes the video data of target dancing by obtaining dancer；According to the video data, the limbs form of the dancer in the minimum rhythm unit of each of described target dancing is determined；According to the corresponding limbs shape information of dance spectrum symbol, determine the corresponding dance spectrum symbol of the limbs form of the dancer in the minimum rhythm unit of each of described target dancing, generate the corresponding dance spectrum of the target dancing, it is not necessary that infrared sensor is arranged with dancer, without the multiple infrared sensing lamps of arrangement, the acquisition of video data need to only can be completed using universal photographic device, the dance spectrum of target dancing can be automatically generated by the calculating of view-based access control model, it is more convenient, and greatly reduce cost.
Description
Technical field
The present embodiments relate to dance spectral technology field more particularly to a kind of view-based access control model dance spectrum generation method, device,
Equipment and storage medium.
Background technique
Dance spectrum is the clerking of dancing, and just as music score records melody, dance spectrum is a kind of one for recording dancing
Kind symbol.Both at home and abroad there are many kinds of used dance spectrums on the books, such as positioning mode dance spectrum, color rise movement shorthand, Labanotation.
Wherein Labanotation is most widely used at present, record dance spectrum form the most accurate, and Labanotation uses the symbol of various images,
Accurately, the posture of dancing and various human actions, space motion route, rhythm of action are analyzed and recorded nimblely and are exerted oneself
Amount.
Traditional Labanotation automatic creation system, need one record place on arrange multiple infrared sensing lamps,
And infrared sensor is set on the human body main joint point of dancer, during dancer jumps one section of dancing in ground on the scene, reception is set
The standby data for receiving each infrared sensor, simulate human body main joint in the motion profile in space, and generate Labanotation.But
It is that the equipment cost of traditional Labanotation automatic creation system is up to millions of, and cost is too high.
Summary of the invention
The embodiment of the present invention provides dance spectrum generation method, device, equipment and the storage medium of a kind of view-based access control model, to solve
The equipment cost of certainly traditional Labanotation automatic creation system is up to millions of, the too high problem of cost.
The one aspect of the embodiment of the present invention is to provide a kind of dance spectrum generation method of view-based access control model, comprising:
Obtain the video data that dancer completes target dancing；
According to the video data, the limbs shape of the dancer in the minimum rhythm unit of each of described target dancing is determined
State；
According to the corresponding limbs shape information of dance spectrum symbol, institute in the minimum rhythm unit of each of described target dancing is determined
The corresponding dance spectrum symbol of limbs form for stating dancer, generates the corresponding dance spectrum of the target dancing.
The other side of the embodiment of the present invention is to provide a kind of dance spectrum generating means of view-based access control model, comprising:
Data acquisition module completes the video data of target dancing for obtaining dancer；
Processing module, for determining institute in the minimum rhythm unit of each of described target dancing according to the video data
State the limbs form of dancer；
Dance spectrum generation module, for determining the every of the target dancing according to the corresponding limbs shape information of dance spectrum symbol
The corresponding dance of limbs form of the dancer composes symbol in a minimum rhythm unit, generates the corresponding dance spectrum of the target dancing.
The other side of the embodiment of the present invention is to provide a kind of dance spectrum generating device, comprising:
Memory, processor, and it is stored in the computer journey that can be run on the memory and on the processor
Sequence,
The processor realizes method described above when running the computer program.
The other side of the embodiment of the present invention is to provide a kind of dance spectrum generation system equipment, comprising:
Multiple photographic devices, in acquisition dancer completion target dancing during dancer completes the target dancing
The shooting angle of video data, the multiple photographic device is all different, figure captured by two adjacent photographic devices
As partly overlapping；
Memory, processor, and it is stored in the computer journey that can be run on the memory and on the processor
Sequence,
The processor realizes method described above when running the computer program.
The other side of the embodiment of the present invention is to provide a kind of computer readable storage medium, is stored with computer journey
Sequence,
The computer program realizes method described above when being executed by processor.
Dance spectrum generation method, device, equipment and the storage medium of view-based access control model provided in an embodiment of the present invention, pass through acquisition
The video data of dancer's completion target dancing；According to the video data, the minimum rhythm list of each of described target dancing is determined
The limbs form of the dancer in position；According to the corresponding limbs shape information of dance spectrum symbol, each of described target dancing is determined
The corresponding dance of the limbs form of the dancer composes symbol in minimum rhythm unit, generates the corresponding dance spectrum of the target dancing, nothing
Infrared sensor need to be set with dancer, without multiple infrared sensing lamps are arranged, only need to be using universal photographic device
The acquisition of achievable video data is composed by the dance that the calculating of view-based access control model can automatically generate target dancing, more convenient fast
Victory, and greatly reduce cost.
Detailed description of the invention
Fig. 1 is that the dance for the view-based access control model that the embodiment of the present invention one provides composes generation method flow chart；
Fig. 2 is the schematic diagram of the dance spectrum symbol for the Labanotation that the embodiment of the present invention one provides；
Fig. 3 is that the dance of view-based access control model provided by Embodiment 2 of the present invention composes generation method flow chart；
Fig. 4 is the structural schematic diagram of the dance spectrum generating means for the view-based access control model that the embodiment of the present invention three provides；
Fig. 5 is the structural schematic diagram for the dance spectrum generating device that the embodiment of the present invention five provides；
Fig. 6 is the structural schematic diagram that the dance spectrum that the embodiment of the present invention six provides generates system equipment.
Specific embodiment
Example embodiments are described in detail here, and the example is illustrated in the accompanying drawings.Following description is related to
When attached drawing, unless otherwise indicated, the same numbers in different drawings indicate the same or similar elements.Following exemplary embodiment
Described in embodiment do not represent all embodiments consistent with the embodiment of the present invention.On the contrary, they be only with
The example of device and method as detailed in the attached claim, some aspects of the invention are consistent.
Term " first " involved in the embodiment of the present invention, " second " etc. are used for description purposes only, and should not be understood as referring to
Show or imply relative importance or implicitly indicates the quantity of indicated technical characteristic.In the description of following embodiment,
The meaning of " plurality " is two or more, unless otherwise specifically defined.
These specific embodiments can be combined with each other below, may be at certain for the same or similar concept or process
It is repeated no more in a little embodiments.Below in conjunction with attached drawing, the embodiment of the present invention is described.
Embodiment one
Fig. 1 is that the dance for the view-based access control model that the embodiment of the present invention one provides composes generation method flow chart；Fig. 2 is that the present invention is implemented
The schematic diagram of the dance spectrum symbol for the Labanotation that example one provides.The embodiment of the present invention is directed to traditional Labanotation automatic creation system
Equipment cost it is up to millions of, the too high problem of cost, provide view-based access control model dance spectrum generation method.In the present embodiment
Method is applied to dance spectrum generating device, and dance spectrum generating device can be the computer equipment etc. with processing capacity, at other
In embodiment, this method applies also for other equipment, and the present embodiment is schematically illustrated by taking computer equipment as an example.Such as figure
Shown in 1, specific step is as follows for this method:
Step S101, the video data that dancer completes target dancing is obtained.
In the present embodiment, the photographic device of the video data for shooting dancer's dancing, camera shooting dress can be preset
It sets and can be one or more depth camera or photographic device is also possible to the different common camera shooting of multiple shooting angle
Machine.During dancer completes target dancing, photographic device acquires dancer and completes the video data of target dancing, and is sent to
Dance spectrum generating device.
Dance spectrum generating device can complete the view of target dancing with the dancer that real-time reception photographic device is acquired and sent in real time
Frequency evidence；Alternatively, can receive the video data for completing target dancing by the dancer that photographic device is collected in advance.
Optionally, a kind of feasible embodiment that dancer completes the video data of target dancing is obtained are as follows: receive at least
The dancer that one depth camera device is sent completes the video data of target dancing, and video data is at least one depth camera dress
Set the video data collected with depth information during dancer completes target dancing.
Optionally, obtain the feasible embodiment of another kind that dancer completes the video data of target dancing are as follows: obtain from
The dancer of multiple and different angle shots completes the video data of target dancing.
Step S102, according to video data, the limbs form of dancer in the minimum rhythm unit of each of target dancing is determined.
In practical applications, every section of dancing all corresponds to a kind of known dancing rhythm, and whole section of dancing can be divided into continuously
Multiple minimum rhythm units.The minimum rhythm unit, which refers to, quantifies the smallest length unit of duration in dance spectrum, namely
Refer to the minimum time segment for constituting dancing beat, the unit that can be dancing is clapped.
For example, quantifying the most basic length unit of duration in Labanotation is small bat, in Labanotation most
Small rhythm unit is small bat.
In the present embodiment, the video data of target dancing is completed according to dancer, carries out three-dimensional reconstruction, and available dancer exists
3 d human motion track during completion target dancing, that is to say that available dancer is more during completing target dancing
The limbs form of a different moments.For example, the video data of target dancing can be completed according to dancer, using SFM
(Structure from Motion) algorithm carries out three-dimensional reconstruction, obtains dancer's three-dimensional space during completing target dancing
Human body motion track.
Optionally, a moment can be chosen from each minimum rhythm unit according to the cadence information of target dancing, it will
Limbs form limbs form as the minimum rhythm unit in dancer of the dancer at the moment.
It optionally, can be according to the cadence information of target dancing, when choosing at least two from each minimum rhythm unit
It carves, the limbs form according to dancer at this at least two moment is calculated using averaging, seeking the prediction algorithms such as intermediate value
The limbs form of dancer in the minimum rhythm unit.
Step S103, according to the corresponding limbs shape information of dance spectrum symbol, the minimum rhythm list of each of target dancing is determined
The corresponding dance of the limbs form of dancer composes symbol in position, generates the corresponding dance spectrum of target dancing.
In the present embodiment, available preset dance spectrum rule, dance spectrum rule includes that the dance of dance spectrum composes symbol, each dance spectrum
The corresponding limbs shape information of symbol, and the spectrum face format of dance spectrum.
In the step, for the minimum rhythm unit of each of target dancing, dancer in the minimum rhythm unit is being obtained
After limbs form, by the corresponding limbs shape information of the limbs form of dancer in the minimum rhythm unit and each dance spectrum symbol into
Row matching determines the dance spectrum symbol that the limbs form of dancer in limbs shape information and the minimum rhythm unit matches, and root
The corresponding dance of the minimum rhythm unit is recorded according to the spectrum face format of dance spectrum and composes symbol, and it is corresponding to generate the minimum rhythm unit
Dance spectrum.After generating the corresponding dance spectrum of the minimum rhythm unit of each of target dancing, it is corresponding complete that target dancing can be obtained
Dance spectrum.
It should be noted that the dance spectrum that can be automatically generated in the embodiment of the present invention can be by known dance spectrum rule
Any one dance spectrum, such as Labanotation etc..
Labanotation dance spectrum symbol be it is extremely complex, for it is different types of movement have very complete description side
Formula, the present embodiment are illustrated dance spectrum symbol by taking Labanotation as an example.As shown in Fig. 2, the dance spectrum symbol of Labanotation includes
27 elemental motion symbols (also referred to as to degree symbol), the level side of human body limb form is indicated including 9 class horizontal direction symbols
To and 3 class perpendicular layers sub-symbols indicate human body act vertical extent.The shape representation side of dance spectrum symbol in Fig. 2
Degree is indicated to, fill color.In 9 direction symbol include: original position, left, right, front and rear, it is left front, right before, it is left back, right after, be with wave
The shape of spectrum symbol is indicated.3 kinds of level symbols are three movement levels of low, moderate and height, and the expression of level is to wave
Fill color in spectrum symbol is described: completely black filling indicates that low movement, black circle indicate moderate movement, diagonal line hatches table
Show high action, movement level is used to describe the size of movement range.It is by human body to the division of movement level in Labanotation
The vertical space of position movement is divided into three sub-spaces, determines its movement degree according to the amplitude of movement.
The embodiment of the present invention completes the video data of target dancing by obtaining dancer；According to video data, target is determined
The limbs form of dancer in each of dancing minimum rhythm unit；According to the corresponding limbs shape information of dance spectrum symbol, mesh is determined
The corresponding dance of limbs form for marking dancer in the minimum rhythm unit of each of dancing composes symbol, generates the corresponding dance of target dancing
Spectrum, without multiple infrared sensing lamps are arranged, need to only be filled it is not necessary that infrared sensor is arranged with dancer using universal camera shooting
The acquisition that video data can be completed is set, is composed by the dance that the calculating of view-based access control model can automatically generate target dancing, more just
Just quick, and greatly reduce cost.
Embodiment two
Fig. 3 is that the dance of view-based access control model provided by Embodiment 2 of the present invention composes generation method flow chart.In above-described embodiment one
On the basis of, in the present embodiment, obtain the video data that dancer completes target dancing, comprising: obtain and clap from multiple and different angles
The dancer taken the photograph completes the video data of target dancing.
In the present embodiment, dance spectrum automatic creation system includes dance spectrum generating device, in the multiple of default place surrounding setting
Photographic device.Dancer dances in preset place during complete target dancing, and multiple photographic devices acquisition dancers complete
The video data of target dancing, and video data is sent to dance spectrum generating device.
Wherein, the shooting angle of multiple photographic devices is all different, image portion captured by two adjacent photographic devices
Point overlapping, so as to know that (including transformation matrix includes translation matrix and rotation to two direct transformation matrixs of photographic device
Matrix).The whole coverage of multiple photographic devices can cover entirely default place.
Wherein, within a preset range, preset range can be with for the Duplication of image captured by two adjacent photographic devices
It is set according to actual needs by technical staff, the present embodiment is not specifically limited herein.
For example, preset range may be greater than 30% and less than 40%, image captured by two adjacent photographic devices
Duplication be greater than 30%, in order to reduce the quantity of photographic device, image captured by two adjacent photographic devices is set
Duplication is less than 40%.In the present embodiment, for the size of the lap of image captured by two adjacent photographic devices
It is not specifically limited.
It, can be at least the two of place surrounding in order to improve the accuracy for the limbs form for determining dancer according to video data
A circle photographic device is respectively arranged in a different height.For example, three height can be preset, in place, these three of surrounding are high
Degree sets up a circle photographic device respectively, and each circle includes multiple photographic devices, two neighboring photographic device shooting in each circle
Image section overlapping.Wherein, preset three height can be by technical staff according to mankind's mean value height, shooting angle etc.
Factor is set, and the present embodiment is not specifically limited herein.
In addition, the quantity of each circle photographic device can be set by technical staff according to the size in default place, protect
Demonstrate,prove the Duplication of image captured by two adjacent photographic devices within a preset range, the present embodiment is herein for camera shooting
The quantity of device is not specifically limited.
Photographic device in this implementation can be the video camera of any one common high definition, and the present embodiment, which does not do this, to be had
Body limits.
As shown in figure 3, specific step is as follows for this method:
Step S201, the video data that target dancing is completed from the dancer of multiple and different angle shots is obtained.
Specifically, receiving the video data that the dancer that multiple photographic devices are sent completes target dancing, video data is more
A photographic device is collected during dancer completes target dancing.
Wherein, the shooting angle of multiple photographic devices is all different, image portion captured by two adjacent photographic devices
Divide overlapping.
Step S202, according to video data, 3 d human motion track of dancer during completing target dancing is obtained.
In the present embodiment, when 3 d human motion track of dancer during completing target dancing is stated in calculating, first
Initialize the position of world coordinate system origin.Optionally, origin can be set as to place center, or origin can be set
For the optical center of any one photographic device.
In addition, three-dimensional coordinate described in the present embodiment each means the three-dimensional coordinate in world coordinate system.
In the present embodiment, according to the video data for completing target dancing from the dancer of multiple and different angle shots, three are carried out
Dimension is rebuild, and available dancer 3 d human motion track during completing target dancing that is to say that available dancer exists
Complete the limbs form at multiple and different moment during target dancing.
Optionally, according to video data, 3 d human motion track of dancer during completing target dancing is obtained, is had
Body can be realized in the following way:
From the video data of multiple and different angle shots, the multiple images frame of synchronization is obtained；Extract multiple images
Human body surface characteristic point in frame, human body surface characteristic point is in the picture frame that the moment appears at least two adjacent angulars；
The picture frame of at least two adjacent angulars appeared according to everyone body surface region feature point at the moment, it is special to calculate human body surface
Three-dimensional coordinate of the sign point at the moment.After the three-dimensional coordinate of owner's body surface region feature point at the moment is calculated, i.e.,
Dancer can be obtained in the limbs form at the moment.The bat of each picture frame of dancer during completing target dancing is calculated
3 d human motion track of dancer during completing target dancing can be obtained in the limbs form for taking the photograph moment dancer.
Wherein, the picture frame of two adjacent angulars refers to image captured by the photographic device of two adjacent shooting angle
The picture frame of frame, two adjacent angulars overlaps.
Specifically, at the moment to appear at least two adjacent for the human body surface characteristic point in the multiple images frame extracted
In the picture frame of angle, for any one human body surface characteristic point, according to two adjacent angulars where human body surface characteristic point
Between two photographic devices of the picture frame of the picture frame and two adjacent angulars where human body surface characteristic point of degree away from
From the depth information of human body surface characteristics point can be calculated, and human body surface characteristics point can be calculated at this
The three-dimensional coordinate at moment.
In addition, a characteristic point appears in picture frame captured by the photographic device of two different angles of synchronization,
According to the distance between the two picture frames and the two filming apparatus, the depth information and three-dimensional seat of this feature point are calculated
Calibration method specifically can realize that details are not described herein again for the present embodiment using method similar in the prior art.
Optionally, according to dancer complete target dancing video data, can also using existing three-dimensional reconstruction algorithm into
Row three-dimensional reconstruction obtains the human body motion track of dancer's three-dimensional space during completing target dancing.For example, three-dimensional reconstruction is calculated
Method can be SFM (Structure from Motion) algorithm etc..
Step S203, according to 3 d human motion track, dancer in the minimum rhythm unit of each of target dancing is determined
Limbs form.
In the present embodiment, according to 3 d human motion track, dancer in the minimum rhythm unit of each of target dancing is determined
Limbs form, can specifically realize in the following way:
For any one minimum rhythm unit of target dancing, multiple and different mesh in the minimum rhythm unit are determined
Mark the moment；Obtain the three-dimensional coordinate of the human body surface characteristic point of multiple and different object times in the minimum rhythm unit；
Calculate the HCCI combustion in the three-dimensional coordinate of multiple and different object time human body surface characteristic points；Human body surface characteristic point it is equal
It is worth the limbs form that coordinate constitutes dancer in minimum rhythm unit, the accuracy for generating dance spectrum can be improved.
Optionally, multiple and different object times in minimum rhythm unit are determined, it specifically can be real in the following way
It is existing: minimum rhythm unit to be divided into the default division numbers period, using the separation between any two period as target
Moment, available (default division numbers -1) a object time.
Optionally, due to it is different at the time of the human body surface characteristic point extracted may be different, that is to say multiple and different
Object time in, appear in an object time human body surface characteristic point may not appear in it is other one or more
Object time.It is calculating in the HCCI combustion of the three-dimensional coordinate of multiple and different object time human body surface characteristic points, it can be with
According to the quantity of the three-dimensional coordinate of human body surface characteristic point in 3 d human motion track, the mean value of human body surface characteristic point is calculated
Coordinate.
Wherein, default division numbers can be 2,3,4 or 5 etc., and default division numbers can be by technical staff according to reality
Border is set, and the present embodiment is not specifically limited herein.
For example, quantifying the most basic length unit of duration in Labanotation is small bat, in Labanotation most
Small rhythm unit is small bat.In the step, for any one small bat of target dancing, small bat is divided into 4 periods, will be appointed
The separation anticipated between two periods is as object time, 3 object times of the available small bat.It is transported according to 3 D human body
The coordinate value of each human body surface characteristic point of this 3 object times in dynamic rail mark, calculate each human body surface characteristic point this 3
The HCCI combustion of a object time.If some human body surface characteristic point is only present in 2 object times therein, calculating should
Human body surface characteristic point obtains human body surface characteristics point in the small bat in the mean value of the three-dimensional coordinate of this 2 object times
HCCI combustion.
Step 204 composes the corresponding limbs shape information of symbol according to dance, determines the minimum rhythm unit of each of target dancing
The corresponding dance of the limbs form of interior dancer composes symbol, generates the corresponding dance spectrum of target dancing.
In general, human body is divided into multiple body parts in dance spectrum, with the position of the dance spectrum each body part of symbol record
Information and posture information.In the present embodiment, the corresponding limbs shape information of dance spectrum symbol is included at least: location information and posture letter
Breath.
In the present embodiment, available preset dance spectrum rule, dance spectrum rule includes that the dance of dance spectrum composes symbol, each dance spectrum
The corresponding limbs shape information of symbol, and the spectrum face format of dance spectrum.
In the step, for the minimum rhythm unit of each of target dancing, dancer in the minimum rhythm unit is being obtained
After limbs form, by the corresponding limbs shape information of the limbs form of dancer in the minimum rhythm unit and each dance spectrum symbol into
Row matching determines the dance spectrum symbol that the limbs form of dancer in limbs shape information and the minimum rhythm unit matches, and root
The corresponding dance of the minimum rhythm unit is recorded according to the spectrum face format of dance spectrum and composes symbol, and it is corresponding to generate the minimum rhythm unit
Dance spectrum.After generating the corresponding dance spectrum of the minimum rhythm unit of each of target dancing, it is corresponding complete that target dancing can be obtained
Dance spectrum.
Specifically, obtaining in the minimum rhythm unit of each of target dancing after the limbs form of dancer, for target
The minimum rhythm unit of any one of dancing, can be according to the body part for being in advance divided into human body and the minimum rhythm
The limbs form of dancer in unit further determines that the location information of each body part and posture letter in the limbs form of dancer
Breath；By the location information of each body part and posture information location information corresponding with each dance spectrum symbol and posture information into
Row matching determines that the corresponding dance of each body part composes symbol in the minimum rhythm unit；According to every in the minimum rhythm unit
The corresponding dance spectrum symbol of a body part generates the dance of this part in the minimum rhythm unit and composes.Generate each of target dancing most
After the part dance spectrum of small rhythm unit, the corresponding complete dance spectrum of target dancing can be obtained.
Optionally, after obtaining the corresponding complete dance spectrum of target dancing, can also according to the whole rhythm of target dancing,
If the part dance spectrum in adjacent minimum rhythm unit is identical, the part in the adjacent minimum rhythm unit can be waved and be composed
Merge.
The embodiment of the present invention completes target dance by obtaining from multiple photographic devices from the dancer of multiple and different angle shots
The video data stepped determines the limbs form of dancer in the minimum rhythm unit of each of target dancing according to video data；According to
The corresponding limbs shape information of dance spectrum symbol determines that the limbs form of dancer in the minimum rhythm unit of each of target dancing is corresponding
Dance compose symbol, generate target dancing corresponding dance spectrum, it is multiple without arrangement it is not necessary that infrared sensor is arranged with dancer
The acquisition of video data need to only can be completed using universal photographic device, be by the calculating of view-based access control model for infrared sensing lamp
The dance spectrum of target dancing can be automatically generated, it is more convenient, and greatly reduce cost.
Embodiment three
Fig. 4 is the structural schematic diagram of the dance spectrum generating means for the view-based access control model that the embodiment of the present invention three provides.The present invention is real
The dance spectrum generating means for applying the view-based access control model of example offer can execute the place that the dance spectrum generation method embodiment of view-based access control model provides
Manage process.As shown in figure 4, the device 40 includes: data acquisition module 401, processing module 402 and dance spectrum generation module 403.
Specifically, data acquisition module 401 is used to obtain the video data that dancer completes target dancing.
Processing module 402 is used to determine the limb of dancer in the minimum rhythm unit of each of target dancing according to video data
Volume morphing.
Dance spectrum generation module 403 is used to determine each of target dancing according to the corresponding limbs shape information of dance spectrum symbol
The corresponding dance of the limbs form of dancer composes symbol in minimum rhythm unit, generates the corresponding dance spectrum of target dancing.
Device provided in an embodiment of the present invention can be specifically used for executing embodiment of the method provided by above-described embodiment one,
Details are not described herein again for concrete function.
The embodiment of the present invention completes the video data of target dancing by obtaining dancer；According to video data, target is determined
The limbs form of dancer in each of dancing minimum rhythm unit；According to the corresponding limbs shape information of dance spectrum symbol, mesh is determined
The corresponding dance of limbs form for marking dancer in the minimum rhythm unit of each of dancing composes symbol, generates the corresponding dance of target dancing
Spectrum, without multiple infrared sensing lamps are arranged, need to only be filled it is not necessary that infrared sensor is arranged with dancer using universal camera shooting
The acquisition that video data can be completed is set, is composed by the dance that the calculating of view-based access control model can automatically generate target dancing, more just
Just quick, and greatly reduce cost.
Example IV
On the basis of above-described embodiment three, in the present embodiment, processing module is also used to:
According to video data, 3 d human motion track of dancer during completing target dancing is obtained；According to three-dimensional
Human body motion track determines the limbs form of dancer in the minimum rhythm unit of each of target dancing.
Optionally, data acquisition module is also used to:
Obtain the video data that target dancing is completed from the dancer of multiple and different angle shots.
Optionally, data acquisition module is also used to:
The video data that the dancer that multiple photographic devices are sent completes target dancing is received, video data is multiple camera shootings dress
It sets collected during dancer completes target dancing；The shooting angle of multiple photographic devices is all different, two adjacent
The overlapping of image section captured by photographic device.
Optionally, processing module is also used to:
From the video data of multiple and different angle shots, the multiple images frame of synchronization is obtained；Extract multiple images
Human body surface characteristic point in frame, human body surface characteristic point is in the picture frame that the moment appears at least two adjacent angulars；
The picture frame of at least two adjacent angulars appeared according to everyone body surface region feature point at the moment, it is special to calculate human body surface
Three-dimensional coordinate of the sign point at the moment.
Optionally, processing module is also used to:
Obtain the three-dimensional coordinate of multiple and different object times in minimum rhythm unit, human body surface characteristic point；Meter
Calculate the HCCI combustion in the three-dimensional coordinate of multiple and different object time human body surface characteristic points；The mean value of human body surface characteristic point
Coordinate constitutes the limbs form of dancer in minimum rhythm unit.
Optionally, data acquisition module is also used to:
The dancer for receiving the transmission of at least one depth camera device completes the video data of target dancing, and video data is extremely
Few depth camera device video data collected with depth information during dancer completes target dancing.
Device provided in an embodiment of the present invention can be specifically used for executing embodiment of the method provided by above-described embodiment two,
Details are not described herein again for concrete function.
The embodiment of the present invention completes target dance by obtaining from multiple photographic devices from the dancer of multiple and different angle shots
The video data stepped determines the limbs form of dancer in the minimum rhythm unit of each of target dancing according to video data；According to
The corresponding limbs shape information of dance spectrum symbol determines that the limbs form of dancer in the minimum rhythm unit of each of target dancing is corresponding
Dance compose symbol, generate target dancing corresponding dance spectrum, it is multiple without arrangement it is not necessary that infrared sensor is arranged with dancer
The acquisition of video data need to only can be completed using universal photographic device, be by the calculating of view-based access control model for infrared sensing lamp
The dance spectrum of target dancing can be automatically generated, it is more convenient, and greatly reduce cost.
Embodiment five
Fig. 5 is the structural schematic diagram for the dance spectrum generating device that the embodiment of the present invention five provides.As shown in figure 5, dance spectrum life
Forming apparatus 50 includes: processor 501, memory 502, and is stored in the meter that can be executed on memory 502 and by processor 501
Calculation machine program.
Processor 501 realizes any of the above-described embodiment of the method when executing and storing in the computer program on memory 502
The method of offer.
The embodiment of the present invention completes the video data of target dancing by obtaining dancer；According to video data, target is determined
The limbs form of dancer in each of dancing minimum rhythm unit；According to the corresponding limbs shape information of dance spectrum symbol, mesh is determined
The corresponding dance of limbs form for marking dancer in the minimum rhythm unit of each of dancing composes symbol, generates the corresponding dance of target dancing
Spectrum, without multiple infrared sensing lamps are arranged, need to only be filled it is not necessary that infrared sensor is arranged with dancer using universal camera shooting
The acquisition that video data can be completed is set, is composed by the dance that the calculating of view-based access control model can automatically generate target dancing, more just
Just quick, and greatly reduce cost.
Embodiment six
Fig. 6 is the structural schematic diagram that the dance spectrum that the embodiment of the present invention six provides generates system equipment.As shown in fig. 6, the dance
Spectrum generate system equipment 60 include: multiple photographic devices 600, for dancer complete target dancing during acquisition dancer it is complete
At the video data of target dancing, the shooting angle of multiple photographic devices 600 is all different, two adjacent photographic devices 600
Captured image section overlapping.
Processor 601, memory 602, and it is stored in the computer that can be executed on memory 602 and by processor 601
Program.
Processor 601 realizes any of the above-described embodiment of the method when executing and storing in the computer program on memory 602
The method of offer.
The embodiment of the present invention completes the video data of target dancing by obtaining dancer；According to video data, target is determined
The limbs form of dancer in each of dancing minimum rhythm unit；According to the corresponding limbs shape information of dance spectrum symbol, mesh is determined
The corresponding dance of limbs form for marking dancer in the minimum rhythm unit of each of dancing composes symbol, generates the corresponding dance of target dancing
Spectrum, without multiple infrared sensing lamps are arranged, need to only be filled it is not necessary that infrared sensor is arranged with dancer using universal camera shooting
The acquisition that video data can be completed is set, is composed by the dance that the calculating of view-based access control model can automatically generate target dancing, more just
Just quick, and greatly reduce cost.
In addition, the embodiment of the present invention also provides a kind of computer readable storage medium, it is stored with computer program, the meter
Calculation machine program realizes the method that any of the above-described embodiment of the method provides when being executed by processor.
In several embodiments provided by the present invention, it should be understood that disclosed device and method can pass through it
Its mode is realized.For example, the apparatus embodiments described above are merely exemplary, for example, the division of the unit, only
Only a kind of logical function partition, there may be another division manner in actual implementation, such as multiple units or components can be tied
Another system is closed or is desirably integrated into, or some features can be ignored or not executed.Another point, it is shown or discussed
Mutual coupling, direct-coupling or communication connection can be through some interfaces, the INDIRECT COUPLING or logical of device or unit
Letter connection can be electrical property, mechanical or other forms.
The unit as illustrated by the separation member may or may not be physically separated, aobvious as unit
The component shown may or may not be physical unit, it can and it is in one place, or may be distributed over multiple
In network unit.It can select some or all of unit therein according to the actual needs to realize the mesh of this embodiment scheme
's.
It, can also be in addition, the functional units in various embodiments of the present invention may be integrated into one processing unit
It is that each unit physically exists alone, can also be integrated in one unit with two or more units.Above-mentioned integrated list
Member both can take the form of hardware realization, can also realize in the form of hardware adds SFU software functional unit.
The above-mentioned integrated unit being realized in the form of SFU software functional unit can store and computer-readable deposit at one
In storage media.Above-mentioned SFU software functional unit is stored in a storage medium, including some instructions are used so that a computer
It is each that equipment (can be personal computer, server or the network equipment etc.) or processor (processor) execute the present invention
The part steps of embodiment the method.And storage medium above-mentioned includes: USB flash disk, mobile hard disk, read-only memory (Read-
Only Memory, ROM), random access memory (Random Access Memory, RAM), magnetic or disk etc. it is various
It can store the medium of program code.
Those skilled in the art can be understood that, for convenience and simplicity of description, only with above-mentioned each functional module
Division progress for example, in practical application, can according to need and above-mentioned function distribution is complete by different functional modules
At the internal structure of device being divided into different functional modules, to complete all or part of the functions described above.On
The specific work process for stating the device of description, can refer to corresponding processes in the foregoing method embodiment, and details are not described herein.
Those skilled in the art after considering the specification and implementing the invention disclosed here, will readily occur to of the invention its
Its embodiment.The present invention is directed to cover any variations, uses, or adaptations of the invention, these modifications, purposes or
Person's adaptive change follows general principle of the invention and including the undocumented common knowledge in the art of the present invention
Or conventional techniques.The description and examples are only to be considered as illustrative, and true scope and spirit of the invention are by following
Claims are pointed out.
It should be understood that the present invention is not limited to the precise structure already described above and shown in the accompanying drawings, and
And various modifications and changes may be made without departing from the scope thereof.The scope of the present invention is only limited by appended claims
System.
Claims (17)
1. a kind of dance of view-based access control model composes generation method characterized by comprising
Obtain the video data that dancer completes target dancing；
According to the video data, the limbs form of the dancer in the minimum rhythm unit of each of described target dancing is determined；
According to the corresponding limbs shape information of dance spectrum symbol, the dance in the minimum rhythm unit of each of described target dancing is determined
The corresponding dance of the limbs form of person composes symbol, generates the corresponding dance spectrum of the target dancing.
2. determining the target dance the method according to claim 1, wherein described according to the video data
Each of step the limbs form of the dancer in minimum rhythm unit, comprising:
According to the video data, 3 d human motion track of dancer during completing the target dancing is obtained；
According to the 3 d human motion track, the limb of the dancer in the minimum rhythm unit of each of described target dancing is determined
Volume morphing.
3. according to the method described in claim 2, it is characterized in that, it is described obtain dancer complete target dancing video data,
Include:
Obtain the video data that target dancing is completed from the dancer of multiple and different angle shots.
4. according to the method described in claim 3, it is characterized in that, described obtain is completed from the dancer of multiple and different angle shots
The video data of target dancing, comprising:
The video data that the dancer that multiple photographic devices are sent completes target dancing is received, the video data is the multiple takes the photograph
As device is collected during dancer completes the target dancing；
The shooting angle of the multiple photographic device is all different, image section captured by two adjacent photographic devices
Overlapping.
5. the method according to claim 3 or 4, which is characterized in that it is described according to the video data, obtain the dancer
3 d human motion track during completing the target dancing, comprising:
From the video data that the multiple different angle is shot, the multiple images frame of synchronization is obtained；
The human body surface characteristic point in described multiple images frame is extracted, the human body surface characteristic point appears at least at the moment
In the described image frame of two adjacent angulars；
The described image frame of at least two adjacent angulars appeared according to each human body surface characteristic point at the moment, meter
The human body surface characteristic point is calculated in the three-dimensional coordinate at the moment.
6. according to the method described in claim 5, determining institute it is characterized in that, described according to the 3 d human motion track
State the limbs form of the dancer in the minimum rhythm unit of each of target dancing, comprising:
Obtain multiple and different object times in the minimum rhythm unit, the three-dimensional of the human body surface characteristic point is sat
Mark；
Calculate the HCCI combustion of the three-dimensional coordinate of human body surface characteristic point described in the plurality of different object time；
The HCCI combustion of the human body surface characteristic point constitutes the limbs form of the dancer in the minimum rhythm unit.
7. method according to claim 1 or 2, which is characterized in that the video counts for obtaining dancer and completing target dancing
According to, comprising:
The dancer for receiving the transmission of at least one depth camera device completes the video data of target dancing, and the video data is institute
State at least one depth camera device video collected with depth information during dancer completes the target dancing
Data.
8. a kind of dance of view-based access control model composes generating means characterized by comprising
Data acquisition module completes the video data of target dancing for obtaining dancer；
Processing module, for determining the dance in the minimum rhythm unit of each of described target dancing according to the video data
The limbs form of person；
Dance spectrum generation module, for determining each of described target dancing most according to the corresponding limbs shape information of dance spectrum symbol
The corresponding dance of the limbs form of the dancer composes symbol in small rhythm unit, generates the corresponding dance spectrum of the target dancing.
9. device according to claim 8, which is characterized in that the processing module is also used to:
According to the video data, 3 d human motion track of dancer during completing the target dancing is obtained；
According to the 3 d human motion track, the limb of the dancer in the minimum rhythm unit of each of described target dancing is determined
Volume morphing.
10. device according to claim 9, which is characterized in that the data acquisition module is also used to:
Obtain the video data that target dancing is completed from the dancer of multiple and different angle shots.
11. device according to claim 10, which is characterized in that the data acquisition module is also used to:
The video data that the dancer that multiple photographic devices are sent completes target dancing is received, the video data is the multiple takes the photograph
As device is collected during dancer completes the target dancing；
The shooting angle of the multiple photographic device is all different, image section captured by two adjacent photographic devices
Overlapping.
12. device described in 0 or 11 according to claim 1, which is characterized in that the processing module is also used to:
From the video data that the multiple different angle is shot, the multiple images frame of synchronization is obtained；
The human body surface characteristic point in described multiple images frame is extracted, the human body surface characteristic point appears at least at the moment
In the described image frame of two adjacent angulars；
The described image frame of at least two adjacent angulars appeared according to each human body surface characteristic point at the moment, meter
The human body surface characteristic point is calculated in the three-dimensional coordinate at the moment.
13. device according to claim 12, which is characterized in that the processing module is also used to:
Obtain multiple and different object times in the minimum rhythm unit, the three-dimensional of the human body surface characteristic point is sat
Mark；
Calculate the HCCI combustion of the three-dimensional coordinate of human body surface characteristic point described in the plurality of different object time；
The HCCI combustion of the human body surface characteristic point constitutes the limbs form of the dancer in the minimum rhythm unit.
14. device according to claim 8 or claim 9, which is characterized in that the data acquisition module is also used to:
The dancer for receiving the transmission of at least one depth camera device completes the video data of target dancing, and the video data is institute
State at least one depth camera device video collected with depth information during dancer completes the target dancing
Data.
15. a kind of dance composes generating device characterized by comprising
Memory, processor, and it is stored in the computer program that can be run on the memory and on the processor,
The processor realizes such as method of any of claims 1-7 when running the computer program.
16. a kind of dance spectrum generates system equipment characterized by comprising
Multiple photographic devices, in the video for acquiring dancer's completion target dancing during dancer completes the target dancing
The shooting angle of data, the multiple photographic device is all different, image portion captured by two adjacent photographic devices
Divide overlapping；
Memory, processor, and it is stored in the computer program that can be run on the memory and on the processor,
The processor realizes such as method of any of claims 1-7 when running the computer program.
17. a kind of computer readable storage medium, which is characterized in that it is stored with computer program,
Such as method of any of claims 1-7 is realized when the computer program is executed by processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810880336.XA CN109255295B (en) | 2018-08-03 | 2018-08-03 | Vision-based dance score generation method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810880336.XA CN109255295B (en) | 2018-08-03 | 2018-08-03 | Vision-based dance score generation method, device, equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109255295A true CN109255295A (en) | 2019-01-22 |
| CN109255295B CN109255295B (en) | 2022-08-30 |
Family
ID=65048718
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810880336.XA Active CN109255295B (en) | 2018-08-03 | 2018-08-03 | Vision-based dance score generation method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109255295B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110660017A (en) * | 2019-09-02 | 2020-01-07 | 北京航空航天大学 | Dance music recording and demonstrating method based on three-dimensional gesture recognition |
| CN112604260A (en) * | 2020-11-16 | 2021-04-06 | 广州博冠智能科技有限公司 | Dance analysis guidance method and device for group dance |
| 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 |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070040836A1 (en) * | 2005-08-19 | 2007-02-22 | Pamela Schickler | Choreography recording and access system |
| CN101604447A (en) * | 2009-07-09 | 2009-12-16 | 上海交通大学 | No-mark human body motion capture method |
| CN103198492A (en) * | 2013-03-28 | 2013-07-10 | 沈阳航空航天大学 | Human motion capture method |
| KR20140116740A (en) * | 2013-03-25 | 2014-10-06 | 삼성전자주식회사 | Display device for dance image and method of thereof |
| CN106530353A (en) * | 2016-10-19 | 2017-03-22 | 绍兴文理学院 | Three-dimensional moving point detection method for sparse three-dimensional reconstruction of binocular vision system |
-
2018
- 2018-08-03 CN CN201810880336.XA patent/CN109255295B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070040836A1 (en) * | 2005-08-19 | 2007-02-22 | Pamela Schickler | Choreography recording and access system |
| CN101604447A (en) * | 2009-07-09 | 2009-12-16 | 上海交通大学 | No-mark human body motion capture method |
| KR20140116740A (en) * | 2013-03-25 | 2014-10-06 | 삼성전자주식회사 | Display device for dance image and method of thereof |
| CN103198492A (en) * | 2013-03-28 | 2013-07-10 | 沈阳航空航天大学 | Human motion capture method |
| CN106530353A (en) * | 2016-10-19 | 2017-03-22 | 绍兴文理学院 | Three-dimensional moving point detection method for sparse three-dimensional reconstruction of binocular vision system |
Non-Patent Citations (2)
| Title |
|---|
| 李照虎: "基于自动分割的舞谱生成平台的设计与实现", 《中国优秀硕士学位论文全文数据库（信息科技辑）》 * |
| 王征: "基于视频的三维人体重建和运动捕捉", 《中国博士学位论文全文数据库（信息科技辑）》 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110660017A (en) * | 2019-09-02 | 2020-01-07 | 北京航空航天大学 | Dance music recording and demonstrating method based on three-dimensional gesture recognition |
| CN112604260A (en) * | 2020-11-16 | 2021-04-06 | 广州博冠智能科技有限公司 | Dance analysis guidance method and device for group dance |
| 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 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109255295B (en) | 2022-08-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP6934887B2 (en) | Methods and systems for real-time 3D capture and live feedback with monocular cameras | |
| CN113012282B (en) | Three-dimensional human body reconstruction method, device, equipment and storage medium | |
| US8933928B2 (en) | Multiview face content creation | |
| CN108053437B (en) | Three-dimensional model obtaining method and device based on posture | |
| CN109242961A (en) | A kind of face modeling method, apparatus, electronic equipment and computer-readable medium | |
| CN109952760A (en) | The splicing of multiple view scene flows | |
| US11928778B2 (en) | Method for human body model reconstruction and reconstruction system | |
| CN108573527A (en) | A kind of expression picture generation method and its equipment, storage medium | |
| CN107113416A (en) | The method and system of multiple views high-speed motion collection | |
| JP5795250B2 (en) | Subject posture estimation device and video drawing device | |
| JP2011521357A5 (en) | ||
| CN109255295A (en) | Dance spectrum generation method, device, equipment and the storage medium of view-based access control model | |
| TWI785588B (en) | Image registration method and related model training methods, equipment and computer readable storage medium thereof | |
| CN104915978A (en) | Realistic animation generation method based on Kinect | |
| CN109829976A (en) | One kind performing method and its system based on holographic technique in real time | |
| CN109448105A (en) | Three-dimensional human skeleton generation method and system based on more depth image sensors | |
| CN112037310A (en) | Game character action recognition generation method based on neural network | |
| JP2018129009A (en) | Image compositing device, image compositing method, and computer program | |
| CN109523615B (en) | Data processing method and device for virtual animation character actions | |
| CN109903393A (en) | New Century Planned Textbook Scene Composition methods and device based on deep learning | |
| CN108961423A (en) | Virtual information processing method, device, equipment and storage medium | |
| CN109791704A (en) | The texture rendering based on multilayer UV mapping for free-running operation FVV application | |
| Mustafa et al. | Multi-person implicit reconstruction from a single image | |
| CN109215061A (en) | A kind of face pore tracking and system | |
| Park et al. | Template‐Based Reconstruction of Surface Mesh Animation from Point Cloud Animation |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| EE01 | Entry into force of recordation of patent licensing contract | ||
| EE01 | Entry into force of recordation of patent licensing contract |
Application publication date: 20190122 Assignee: Beijing Intellectual Property Management Co.,Ltd. Assignor: BEIJING BAIDU NETCOM SCIENCE AND TECHNOLOGY Co.,Ltd. Contract record no.: X2023110000094 Denomination of invention: Visual dance score generation method, device, device, and storage medium Granted publication date: 20220830 License type: Common License Record date: 20230818 |