CN107895148A - Body action identification method, device and computer-readable recording medium - Google Patents
Body action identification method, device and computer-readable recording medium Download PDFInfo
- Publication number
- CN107895148A CN107895148A CN201711103064.4A CN201711103064A CN107895148A CN 107895148 A CN107895148 A CN 107895148A CN 201711103064 A CN201711103064 A CN 201711103064A CN 107895148 A CN107895148 A CN 107895148A
- Authority
- CN
- China
- Prior art keywords
- limb action
- default
- feature
- gene sequencing
- action
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
- G06V10/757—Matching configurations of points or features
-
- 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
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16B—BIOINFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR GENETIC OR PROTEIN-RELATED DATA PROCESSING IN COMPUTATIONAL MOLECULAR BIOLOGY
- G16B30/00—ICT specially adapted for sequence analysis involving nucleotides or amino acids
Abstract
The invention discloses a kind of body action identification method, including：User's limb action is obtained, and obtains gene sequencing feature corresponding to user's limb action；Default genes of individuals sequence sets according to where the gene sequencing feature of acquisition, obtain the limb action feature with all gene sequencing feature associations in default genes of individuals sequence sets；The limb action feature of acquisition is matched with user's limb action, when confirming that the match is successful, confirms that user possesses the gene sequencing feature of the default genes of individuals sequence sets, limb action feature recognition user's limb action is corresponded to gene sequencing feature.The invention also discloses a kind of body movement recognition device and computer-readable recording medium.The present invention realizes the beneficial effect for improving limb action recognition efficiency by the way that when confirming that user possesses gene sequencing feature, limb action feature recognition user's limb action is corresponded to the gene sequencing feature.
Description
Technical field
The present invention relates to limbs to identify field, more particularly to a kind of body action identification method, device and computer-readable
Storage medium.
Background technology
Limb action language (also known as body language), refers to by the human body such as head, eye, neck, hand, elbow, arm, body, hip, foot portion
The Coordinating Activity of position passes on the thought of personage, visually a kind of communication way so as to communicating views.Speak of and expressed by limbs
During mood, we will recognize that the implication of many usual actions naturally.Such as applaud to represent excited, stamp foot and represent anger, table of rubbing hands
Show anxiety, hanging one's head, it is dejected to represent, and loosens one's grip and represents helpless, beating one's breast represents pain.Party expresses mood with these limb activities, not
People can also be picked out the mental state expressed by party's limbs as it.But high complexity and more variabilities due to human motion
So that the accuracy and high efficiency of limb action identification do not have the real requirement for fully meeting relevant industries.And possesses correlation
Gene can also exist and have limitation to limb action, such as possess the personnel of A genes, carry out a certain limb action when
Wait, order or trickle angle difference be present with other people.In the prior art, do not suggest that based on whether counter look into of limb action has
Standby related gene, and thus improve the technology contents of the identification precision of limb action identification.
The above is only used for auxiliary and understands technical scheme, does not represent and recognizes that the above is existing skill
Art.
The content of the invention
It is a primary object of the present invention to provide a kind of body action identification method, it is intended to solve due to gene expression characteristicses factor
Caused by human body limb action recognition efficiency technical problem.
To achieve the above object, the present invention provides a kind of body action identification method, including herein below：
User's limb action is obtained, and obtains gene sequencing feature corresponding to user's limb action；
Default genes of individuals sequence sets according to where the gene sequencing feature of acquisition, obtain and the default individual
Gene order concentrates the limb action feature of all gene sequencing feature associations；
The limb action feature of acquisition is matched with user's limb action, when confirming that the match is successful,
Confirm that the user possesses the gene sequencing feature of the default genes of individuals sequence sets, with corresponding to the gene sequencing feature
User's limb action described in limb action feature recognition.
Preferably, after the step of acquisition user's limb action, in addition to：
The limb action aspect ratio pair that the limb action is concentrated with default individual limb action, confirm described default
Body limb action concentrates whether include the limb action；
When confirming that the default individual limb action collection includes the limb action, acquisition user's limb is performed
Corresponding to body action the step of gene sequencing feature.
Preferably, described the step of being matched the limb action feature of acquisition with user's limb action,
Also include：
Count the limbs of user's limb action and gene sequencing feature association in the default genes of individuals sequence sets
The number of matches of motion characteristic, wherein, when confirming that the number of matches is more than predetermined number, confirm that the match is successful.
Preferably, it is described when confirming that the number of matches is more than predetermined number, after confirming the step of the match is successful, also
Including：
By the unmatched institute of limb action feature with gene sequencing feature association in the default genes of individuals sequence sets
User's limb action is stated to preserve to limb action property data base；
And establish and preserve to user's limb action feature of the default limb action characteristic and default genes of individuals
The incidence relation of gene sequencing feature in sequence sets.
Preferably, before the step of acquisition user's limb action, in addition to：
The limb action feature and the gene sequencing feature are collected, the limb action property data base is respectively created
And gene sequencing property data base；
Described default is respectively created based on the limb action property data base and the gene sequencing property data base
Body limb action collection and the default genes of individuals sequence signature collection.
Preferably, it is described to be respectively created based on the limb action property data base and the gene sequencing property data base
The step of default individual limb action collection and the default genes of individuals sequence signature collection, specifically include：
In the gene sequencing property data base being collected into, destination number gene sequencing of the selection with relevance is special
Sign, the default genes of individuals sequence signature collection of generation one；
According to the default genes of individuals sequence signature collection created, selected in the limb action property data base
The default genes of individuals sequence signature concentrates limb action feature corresponding to gene sequencing feature, generates the default individual limb
Body behavior aggregate.
Preferably, the default genes of individuals sequence signature collection that the basis has created, in the limb action feature
Select the default genes of individuals sequence signature to concentrate limb action feature corresponding to gene sequencing feature in database, generate institute
After the step of stating default individual limb action collection, in addition to：
By the default genes of individuals sequence signature collection where the gene sequencing feature and the limb action feature
The default individual limb action collection at place establishes incidence relation.
Preferably, it is described to be respectively created based on the limb action property data base and the gene sequencing property data base
After the step of default individual limb action collection and the default genes of individuals sequence signature collection, in addition to：
According to each default individual limb action collection created and each default genes of individuals sequence signature collection, divide
Jian Li there is not the incidence relation of each default individual limb action collection of identical limb action feature and have identical gene sequencing
The incidence relation of each default genes of individuals sequence signature collection of feature.
In addition, to achieve the above object, the present invention also provides a kind of body movement recognition device, it is characterised in that described
Body movement recognition device includes：Memory, processor and it is stored on the memory and can runs on the processor
Computer program, the step of body action identification method as described above is realized when the computer program is by the computing device
Suddenly.
The present invention also provides a kind of computer-readable recording medium, it is characterised in that the computer-readable recording medium
On be stored with limb action recognizer, the limb action recognizer realizes that limbs as described above move when being executed by processor
The step of making recognition methods.
A kind of body action identification method that the embodiment of the present invention proposes, by obtaining user's limb action, and obtains institute
State gene sequencing feature corresponding to user's limb action；According to the default genes of individuals where the gene sequencing feature of acquisition
Sequence sets, obtain the limb action feature with all gene sequencing feature associations in the default genes of individuals sequence sets；It will obtain
The limb action feature taken is matched with user's limb action, when confirming that the match is successful, confirms the user
Possesses the gene sequencing feature of the default genes of individuals sequence sets, with limb action feature corresponding to the gene sequencing feature
Identify user's limb action.By adding the incidence relation of gene sequencing feature and limb action, survey based on gene
The limb action of sequence characteristics is counter to be looked into, and realizes the beneficial effect for improving human body limb action recognition efficiency.
Brief description of the drawings
Fig. 1 be the hardware running environment that scheme of the embodiment of the present invention is related to terminal apparatus structure schematic diagram；
Fig. 2 is the schematic flow sheet of body action identification method first embodiment of the present invention；
Fig. 3 is the schematic flow sheet of body action identification method second embodiment of the present invention；
Fig. 4 is the refinement step schematic flow sheet of step S50 in Fig. 3.
The realization, functional characteristics and advantage of the object of the invention will be described further referring to the drawings in conjunction with the embodiments.
Embodiment
It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, it is not intended to limit the present invention.
The primary solutions of the embodiment of the present invention are：User's limb action is obtained, and obtains user's limb action
Corresponding gene sequencing feature；Default genes of individuals sequence sets according to where the gene sequencing feature of acquisition, obtain with
The limb action feature of all gene sequencing feature associations in the default genes of individuals sequence sets；The limbs of acquisition are moved
Make feature to be matched with user's limb action, when confirming that the match is successful, confirm that the user possesses described default
The gene sequencing feature of body gene order collection, with user's limb described in limb action feature recognition corresponding to the gene sequencing feature
Body acts.
Because the accuracy and high efficiency of the work identification of prior art limbs do not have the requirement for meeting relevant industries,
And the limitation of limb action is caused due to gene so that limb action identification can not meet relevant industries requirement.
The present invention provides a solution, realizes and is verified whether according to limb action in the presence of related gene expression characteristicses,
And limb action is looked into according to the gene expression characteristicses are counter, to realize the beneficial effect for improving limb action identification accuracy.
As shown in figure 1, Fig. 1 is the terminal structure schematic diagram for the hardware running environment that scheme of the embodiment of the present invention is related to.
Terminal of the embodiment of the present invention can be PC or smart mobile phone, tablet personal computer, E-book reader, portable
Computer etc. has the packaged type terminal device of display function.
As shown in figure 1, the terminal can include：Processor 1001, such as CPU, network interface 1004, user interface
1003, memory 1005, communication bus 1002.Wherein, communication bus 1002 is used to realize the connection communication between these components.
User interface 1003 can include display screen (Display), input block such as keyboard (Keyboard), optional user interface
1003 can also include wireline interface, the wave point of standard.Network interface 1004 can optionally connect including the wired of standard
Mouth, wave point (such as WI-FI interfaces).Memory 1005 can be high-speed RAM memory or stable memory
(non-volatile memory), such as magnetic disk storage.Memory 1005 optionally can also be independently of aforementioned processor
1001 storage device.
It will be understood by those skilled in the art that the restriction of the terminal structure shown in Fig. 1 not structure paired terminal, can be wrapped
Include than illustrating more or less parts, either combine some parts or different parts arrangement.
As shown in figure 1, it can lead to as in a kind of memory 1005 of computer-readable storage medium including operating system, network
Believe module, Subscriber Interface Module SIM and limb action recognizer.
In the terminal shown in Fig. 1, network interface 1004 is mainly used in connecting background server, is carried out with background server
Data communicate；User interface 1003 is mainly used in connecting client (user terminal), enters row data communication with client；And processor
1001 can be used for calling the limb action recognizer stored in memory 1005, and perform following operate：
User's limb action is obtained, and obtains gene sequencing feature corresponding to user's limb action；
Default genes of individuals sequence sets according to where the gene sequencing feature of acquisition, obtain and the default individual
Gene order concentrates the limb action feature of all gene sequencing feature associations；
The limb action feature of acquisition is matched with user's limb action, when confirming that the match is successful,
Confirm that the user possesses the gene sequencing feature of the default genes of individuals sequence sets, with corresponding to the gene sequencing feature
User's limb action described in limb action feature recognition.
Further, processor 1001 can call the limb action recognizer stored in memory 1005, also perform
Operate below：
The limb action aspect ratio pair that the limb action is concentrated with default individual limb action, confirm described default
Body limb action concentrates whether include the limb action；
When confirming that the default individual limb action collection includes the limb action, acquisition user's limb is performed
Corresponding to body action the step of gene sequencing feature.
Further, processor 1001 can call the limb action recognizer stored in memory 1005, also perform
Operate below：
Count the limbs of user's limb action and gene sequencing feature association in the default genes of individuals sequence sets
The number of matches of motion characteristic, wherein, when confirming that the number of matches is more than predetermined number, confirm that the match is successful.
Further, processor 1001 can call the limb action recognizer stored in memory 1005, also perform
Operate below：
By the unmatched institute of limb action feature with gene sequencing feature association in the default genes of individuals sequence sets
User's limb action is stated to preserve to limb action property data base；
And establish and preserve to user's limb action feature of the default limb action characteristic and default genes of individuals
The incidence relation of gene sequencing feature in sequence sets.
Further, processor 1001 can call the limb action recognizer stored in memory 1005, also perform
Operate below：
The limb action feature and the gene sequencing feature are collected, the limb action property data base is respectively created
And gene sequencing property data base；
Described default is respectively created based on the limb action property data base and the gene sequencing property data base
Body limb action collection and the default genes of individuals sequence signature collection.
Further, processor 1001 can call the limb action recognizer stored in memory 1005, also perform
Operate below：
In the gene sequencing property data base being collected into, destination number gene sequencing of the selection with relevance is special
Sign, the default genes of individuals sequence signature collection of generation one；
According to the default genes of individuals sequence signature collection created, selected in the limb action property data base
The default genes of individuals sequence signature concentrates limb action feature corresponding to gene sequencing feature, generates the default individual limb
Body behavior aggregate.
Further, processor 1001 can call the limb action recognizer stored in memory 1005, also perform
Operate below：
By the default genes of individuals sequence signature collection where the gene sequencing feature and the limb action feature
The default individual limb action collection at place establishes incidence relation.
Further, processor 1001 can call the limb action recognizer stored in memory 1005, also perform
Operate below：
According to each default individual limb action collection created and each default genes of individuals sequence signature collection, divide
Jian Li there is not the incidence relation of each default individual limb action collection of identical limb action feature and have identical gene sequencing
The incidence relation of each default genes of individuals sequence signature collection of feature.
Reference picture 2, Fig. 2 are the schematic flow sheet of body action identification method first embodiment of the present invention, and the limbs move
Include as recognition methods：
Step S10, user's limb action is obtained, and obtain gene sequencing feature corresponding to user's limb action；
According to the targeted customer for being currently needed for identifying limb action, the shadow of the targeted customer is shot by video equipment
Picture, and the limb action of the targeted customer is captured, whether the limb action is confirmed based on the limb action grabbed
For effective limb action, and when it be effective limb action to confirm the limb action, user's limb action correspondence is obtained
Gene sequencing feature, that is, confirm whether targeted customer corresponding to the limb action possesses certain gene sequencing feature.Wherein,
When the image of the targeted customer is shot by the video equipment, and capturing limb action in the image of the targeted customer,
The video equipment need to possess the relative program and function for capturing the limb action, accurately to capture the targeted customer's
Limb action.Related video equipment can include the camera of video capability, video camera etc..Confirming the targeted customer
Limb action when being effective limb action, the incidence relation according to existing limb action with corresponding gene sequencing feature,
With gene sequencing feature corresponding to acquisition of the limb action of the targeted customer in default genes of individuals sequence signature concentration
Wherein, after the step of acquisition user's limb action, in addition to：
The limb action aspect ratio pair that the limb action is concentrated with default individual limb action, confirm described default
Body limb action concentrates whether include the limb action；
When confirming that the default individual limb action collection includes the limb action, acquisition user's limb is performed
Corresponding to body action the step of gene sequencing feature.
During confirming that the limb action of the targeted customer is effective limb action, by the limbs of the targeted customer
The limb action aspect ratio pair that action is concentrated with default individual limb action, by way of comparing limb action, described in confirmation
Default individual limb action concentrates the limb action for whether including the targeted customer, to confirm the limb of the targeted customer
Whether body action is effective limb action.If the default individual limb action concentrates the limbs for including the targeted customer to move
Make, the limb action for confirming the targeted customer is effective limb action.
Step S20, the default genes of individuals sequence sets according to where the gene sequencing feature of acquisition, obtain with it is described
The limb action feature of all gene sequencing feature associations in default genes of individuals sequence sets；
The default genes of individuals sequence signature collection according to where the gene sequencing feature, obtain the default individual
Gene sequence characteristic concentrates the corresponding limb action feature of all gene sequencing features.It is described to obtain the default genes of individuals sequence
In row feature set the corresponding limb action of all gene sequencing features be characterized as based on the gene sequencing feature that has created with
The incidence relation of the corresponding limb action feature, obtains limb action feature corresponding to the gene sequencing feature in turn.
Step S30, the limb action feature of acquisition is matched with user's limb action, confirming to match
During success, confirm that the user possesses the gene sequencing feature of the default genes of individuals sequence sets, it is special with the gene sequencing
User's limb action described in limb action feature recognition corresponding to sign.
The correspondence of gene sequencing feature in the default genes of individuals sequence sets got the limb action is special
Sign, is matched with user's limb action respectively, and when confirming that the match is successful, confirms that the user possesses the default individual
The gene sequencing feature of gene order collection.And limb action feature recognition corresponding to the gene sequencing feature possessed with the user
The content of user's limb action.Wherein, the matching operation, because the gene sequencing feature has multiple, and each base
Because the limb action feature is also to be multiple corresponding to sequencing feature, respectively by limbs corresponding to the single gene sequencing feature
Motion characteristic is matched with user's limb action one by one, and in user's limb action and the gene sequencing feature
When the number of matches of corresponding limb action feature is more than preset matching threshold value, it is special to confirm that the user possesses the gene sequencing
Sign.And specific matching process, as described below：
I.e. described the step of being matched the limb action feature of acquisition with user's limb action, also wrap
Include：
Count the limbs of user's limb action and gene sequencing feature association in the default genes of individuals sequence sets
The number of matches of motion characteristic, wherein, when confirming that the number of matches is more than predetermined number, confirm that the match is successful.
By the limbs of gene sequencing feature association in user's limb action and the default genes of individuals sequence sets
During the operation that motion characteristic is matched one by one, it is corresponding with the single gene sequencing feature to count user's limb action
The number of matches of the limb action feature, i.e., described user's limb action quantity consistent with the limb action feature,
When confirming that the number of matches is more than predetermined number, the institute of user's limb action and the gene sequencing feature association is confirmed
The success of limb action characteristic matching is stated, i.e., described user's limb action possesses the gene sequencing feature.The predetermined number, it is
The matching threshold of the gene sequencing characteristic matching set.Because of the corresponding limb associated by the different gene sequencing features
The quantity of body motion characteristic is inconsistent, then the predetermined number is relevant with corresponding gene sequencing feature, can be in application process
In determined in a manner of percentage, or other modes determine.
Further, statistics user's limb action and gene sequencing in the default genes of individuals sequence sets are special
Levy the number of matches of the limb action feature of association, and when confirming that the number of matches is more than predetermined number, confirm to match into
After the step of work(, in addition to：
By the unmatched institute of limb action feature with gene sequencing feature association in the default genes of individuals sequence sets
User's limb action is stated to preserve to limb action property data base；
And establish and preserve to user's limb action feature of the default limb action characteristic and default genes of individuals
The incidence relation of gene sequencing feature in sequence sets.
In the limb action and the limb action characteristic matching of the gene sequencing feature association for confirming the targeted customer
After success, confirm that the targeted customer possesses the gene sequencing feature, under this precondition, by presently described targeted customer
Limb action be added to corresponding limb action characteristic storage region, and by the limb action of the targeted customer and the base
Because sequencing feature establishes incidence relation.To supplement the corresponding limb action feature of the gene sequencing feature, later stage identification is improved
The precision of user's limb action.
In the present embodiment, user's limb action is obtained, it is base after effective limb action to confirm user's limb action
In the limb action created and the incidence relation of gene sequencing feature, it is special to obtain gene sequencing corresponding to the limb action
Sign, other limb action features being associated are looked into so that the gene sequencing feature got is counter, and the limb action is special
Sign matches with targeted customer's limb action, and confirms that the targeted customer possesses the gene sequencing spy after the match is successful
Sign.With the incidence relation of gene sequencing feature and limb action feature, add into limbs identification operation, improve user's limbs and move
Make the efficiency identified.
Further, reference picture 3, Fig. 3 be body action identification method second embodiment of the present invention schematic flow sheet, base
Before the step of first embodiment shown in above-mentioned Fig. 2, acquisition user's limb action, in addition to：
Step S40, the limb action feature and the gene sequencing feature are collected, limb action characteristic is respectively created
According to storehouse and gene sequencing property data base；
The gene sequencing for collecting the limb action feature occurred in modern society, and its mankind to find and detect is special
Sign, by the limb action characteristic storage being collected into corresponding database area, the number of the prosperous limb action feature
According to library storage mechanism.And the gene sequencing feature that will be detected, corresponding database area is collected into, forms existing base
Because the data area of feature is sequenced.The database storage mechanism, can be the various databases of data storage in the prior art
Manifestation mode, such as Oracle, SQLServer, mySQL etc..
Step S50, institute is respectively created based on the limb action property data base and the gene sequencing property data base
State default individual limb action collection and the default genes of individuals sequence signature collection；
According to the limb action property data base and gene sequencing property data base being created to, with the base of generation
Because in sequencing property data base, genes of individuals sequence is preset in the relevant gene sequencing feature of extraction destination number, generation one
Row feature set.Wherein, in the gene sequencing feature in existing society, it has been found that have the gene sequencing feature for possessing correlation.
And the gene sequencing feature included is concentrated according to the default genes of individuals sequence signature generated, the gene sequencing is special
Levy the corresponding limb action feature having confirmed that and generate a default individual limbs corresponding to the default genes of individuals sequence signature collection
Behavior aggregate.Incidence relation be present with the default individual limb action collection in its described default genes of individuals sequence signature collection.
Step S60, according to each default individual limb action collection created and each default genes of individuals sequence
Feature set, the incidence relation for each default individual limb action collection for having identical limb action feature is established respectively and is had identical
The incidence relation of each default genes of individuals sequence signature collection of gene sequencing feature.
According to each default genes of individuals sequence signature collection and its each default individual limb action collection created, each described
Default genes of individuals sequence signature is concentrated, and each default genes of individuals sequence signature collection that will be provided with identical gene sequencing feature is established
Incidence relation；And concentrated in each default individual limb action, it will be provided with each described default of identical limb action feature
Body limb action collection establishes a connection, to form annexation between each default gene sequencing feature set and each described
Preset the annexation between individual limb action collection.
In the present embodiment, by collecting existing limb action feature and its gene sequencing feature, respectively described in generation
Limb action property data base and gene sequencing property data base, and the limb action property data base and base based on generation
Because of each default genes of individuals feature set and each default individual limb action collection corresponding to sequencing characteristic structure, and according to having sent out
Existing gene sequencing feature and the incidence relation of corresponding limb action feature, establish the default genes of individuals sequence signature respectively
Collection and the annexation of the default individual limb action collection, by gene sequencing feature and corresponding limb action feature association,
Realize the beneficial effect of technological improvement gene sequencing feature added to limb action identification.
Reference picture 4, Fig. 4 are the refinement process step schematic diagram of step S50 in Fig. 3, described special based on the limb action
The default individual limb action collection and the default individual is respectively created in sign database and the gene sequencing property data base
The step of gene sequence characteristic collection, specifically include：
Step S51, in the gene sequencing property data base being collected into, destination number base of the selection with relevance
Because feature, the default genes of individuals sequence signature collection of generation one is sequenced；
Step S52, according to the default genes of individuals sequence signature collection created, in the limb action characteristic
Select the default genes of individuals sequence signature to concentrate limb action feature corresponding to gene sequencing feature in storehouse, generate described pre-
If individual limb action collection.
Step S53, by the default genes of individuals sequence signature collection where the gene sequencing feature and the limbs
The default individual limb action collection where motion characteristic establishes incidence relation.
In the gene sequencing property data base being created to, choose the destination number gene for possessing incidence relation and survey
Sequence characteristics, generate a default genes of individuals sequence signature collection.And in this way, by the gene sequencing property data base
In all gene sequencing feature generate each default genes of individuals sequence signature collection respectively.It is described default based on what is generated
Genes of individuals sequence signature collection and corresponding default individual limb action collection, will be provided with the gene sequencing feature of incidence relation
The default limb action where the default genes of individuals sequence signature collection and the limb action feature where collecting is special
Incidence relation is established in collection.
Based on the default genes of individuals sequence signature collection generated and individual limb action collection is preset, will be provided with respectively identical
Each default genes of individuals sequence signature collection of the gene sequencing feature establish a connection；And it will be provided with identical institute
Each default individual limb action collection for stating limb action feature establishes a connection.
As described above, each default genes of individuals sequence signature collection and its each default individual limbs that have generated move
Make the incidence relation that collection possesses correlation, to form the mutual pass based on gene sequencing feature and its corresponding limb action feature
Connection relation, to realize by limb action feature corresponding to the lookup of gene sequencing feature, and the limb action feature is corresponding
Search the technique effect of gene sequencing feature.
In addition, the embodiment of the present invention also proposes a kind of computer-readable recording medium, the computer-readable recording medium
On be stored with limb action recognizer, following operation is realized when the limb action recognizer is executed by processor：
User's limb action is obtained, and obtains gene sequencing feature corresponding to user's limb action；
Default genes of individuals sequence sets according to where the gene sequencing feature of acquisition, obtain and the default individual
Gene order concentrates the limb action feature of all gene sequencing feature associations；
The limb action feature of acquisition is matched with user's limb action, when confirming that the match is successful,
Confirm that the user possesses the gene sequencing feature of the default genes of individuals sequence sets, with corresponding to the gene sequencing feature
User's limb action described in limb action feature recognition.
Further, following operation is also realized when the limb action recognizer is executed by processor：
The limb action aspect ratio pair that the limb action is concentrated with default individual limb action, confirm described default
Body limb action concentrates whether include the limb action；
When confirming that the default individual limb action collection includes the limb action, acquisition user's limb is performed
Corresponding to body action the step of gene sequencing feature.
Further, following operation is also realized when the limb action recognizer is executed by processor：
Count the limbs of user's limb action and gene sequencing feature association in the default genes of individuals sequence sets
The number of matches of motion characteristic, wherein, when confirming that the number of matches is more than predetermined number, confirm that the match is successful.
Further, following operation is also realized when the limb action recognizer is executed by processor：
By the unmatched institute of limb action feature with gene sequencing feature association in the default genes of individuals sequence sets
User's limb action is stated to preserve to limb action property data base；
And establish and preserve to user's limb action feature of the default limb action characteristic and default genes of individuals
The incidence relation of gene sequencing feature in sequence sets.
Further, following operation is also realized when the limb action recognizer is executed by processor：
The limb action feature and the gene sequencing feature are collected, the limb action property data base is respectively created
And gene sequencing property data base；
Described default is respectively created based on the limb action property data base and the gene sequencing property data base
Body limb action collection and the default genes of individuals sequence signature collection.
Further, following operation is also realized when the limb action recognizer is executed by processor：
In the gene sequencing property data base being collected into, destination number gene sequencing of the selection with relevance is special
Sign, the default genes of individuals sequence signature collection of generation one；
According to the default genes of individuals sequence signature collection created, selected in the limb action property data base
The default genes of individuals sequence signature concentrates limb action feature corresponding to gene sequencing feature, generates the default individual limb
Body behavior aggregate.
Further, following operation is also realized when the limb action recognizer is executed by processor：
By the default genes of individuals sequence signature collection where the gene sequencing feature and the limb action feature
The default individual limb action collection at place establishes incidence relation.
Further, following operation is also realized when the limb action recognizer is executed by processor：
According to each default individual limb action collection created and each default genes of individuals sequence signature collection, divide
Jian Li there is not the incidence relation of each default individual limb action collection of identical limb action feature and have identical gene sequencing
The incidence relation of each default genes of individuals sequence signature collection of feature.
It should be noted that herein, term " comprising ", "comprising" or its any other variant are intended to non-row
His property includes, so that process, method, article or system including a series of elements not only include those key elements, and
And also include the other element being not expressly set out, or also include for this process, method, article or system institute inherently
Key element.In the absence of more restrictions, the key element limited by sentence "including a ...", it is not excluded that including this
Other identical element also be present in the process of key element, method, article or system.
The embodiments of the present invention are for illustration only, do not represent the quality of embodiment.
Through the above description of the embodiments, those skilled in the art can be understood that above-described embodiment side
Method can add the mode of required general hardware platform to realize by software, naturally it is also possible to by hardware, but in many cases
The former is more preferably embodiment.Based on such understanding, technical scheme is substantially done to prior art in other words
Going out the part of contribution can be embodied in the form of software product, and the computer software product is stored in one as described above
In storage medium (such as ROM/RAM, magnetic disc, CD), including some instructions to cause a station terminal equipment (can be mobile phone,
Computer, server, air conditioner, or network equipment etc.) perform method described in each embodiment of the present invention.
The preferred embodiments of the present invention are these are only, are not intended to limit the scope of the invention, it is every to utilize this hair
The equivalent structure or equivalent flow conversion that bright specification and accompanying drawing content are made, or directly or indirectly it is used in other related skills
Art field, is included within the scope of the present invention.
Claims (10)
1. a kind of body action identification method, it is characterised in that the limb action identification comprises the following steps：
User's limb action is obtained, and obtains gene sequencing feature corresponding to user's limb action；
Default genes of individuals sequence sets according to where the gene sequencing feature of acquisition, obtain and the default genes of individuals
The limb action feature of all gene sequencing feature associations in sequence sets；
The limb action feature of acquisition is matched with user's limb action, when confirming that the match is successful, confirmed
The user possesses the gene sequencing feature of the default genes of individuals sequence sets, with limbs corresponding to the gene sequencing feature
Motion characteristic identifies user's limb action.
2. body action identification method as claimed in claim 1, it is characterised in that described the step of obtaining user's limb action
Afterwards, in addition to：
The limb action aspect ratio pair that the limb action is concentrated with default individual limb action, confirms the default individual limb
Whether the limb action is included in body behavior aggregate；
When confirming that the default individual limb action collection includes the limb action, perform acquisition user's limbs and move
Corresponding to work the step of gene sequencing feature.
3. body action identification method as claimed in claim 1, it is characterised in that the limb action by acquisition is special
The step of sign is matched with user's limb action, in addition to：
Count the limb action of user's limb action and gene sequencing feature association in the default genes of individuals sequence sets
The number of matches of feature, wherein, when confirming that the number of matches is more than predetermined number, confirm that the match is successful.
4. body action identification method as claimed in claim 3, it is characterised in that described to be more than in the confirmation number of matches
During predetermined number, after confirming the step of the match is successful, in addition to：
By the unmatched use of limb action feature with gene sequencing feature association in the default genes of individuals sequence sets
Family limb action is preserved to limb action property data base；
And establish and preserve to user's limb action feature of the default limb action characteristic and default genes of individuals sequence
Concentrate the incidence relation of gene sequencing feature.
5. the body action identification method as described in any one of Claims 1-4, it is characterised in that acquisition user's limbs
Before the step of action, in addition to：
The limb action feature and the gene sequencing feature are collected, the limb action property data base and base is respectively created
Because property data base is sequenced；
The default individual limb is respectively created based on the limb action property data base and the gene sequencing property data base
Body behavior aggregate and the default genes of individuals sequence signature collection.
6. body action identification method as claimed in claim 5, it is characterised in that described to be based on the limb action characteristic
The default individual limb action collection and the default genes of individuals is respectively created according to storehouse and the gene sequencing property data base
The step of sequence signature collection, specifically include：
In the gene sequencing property data base being collected into, destination number gene sequencing feature of the selection with relevance,
The default genes of individuals sequence signature collection of generation one；
According to the default genes of individuals sequence signature collection created, in the limb action property data base described in selection
Default genes of individuals sequence signature concentrates limb action feature corresponding to gene sequencing feature, generates the default individual limbs and moves
Work collects.
7. body action identification method as claimed in claim 6, it is characterised in that the basis has created described default individual
Body gene sequence characteristic collection, the default genes of individuals sequence signature is selected to concentrate base in the limb action property data base
Because sequencing feature corresponding to limb action feature, generate the default individual limb action collection the step of after, in addition to：
By where the default genes of individuals sequence signature collection where the gene sequencing feature and the limb action feature
The default individual limb action collection establish incidence relation.
8. body action identification method as claimed in claim 5, it is characterised in that described to be based on the limb action characteristic
The default individual limb action collection and the default genes of individuals is respectively created according to storehouse and the gene sequencing property data base
After the step of sequence signature collection, in addition to：
According to each default individual limb action collection created and each default genes of individuals sequence signature collection, build respectively
Found the incidence relation for each default individual limb action collection for having identical limb action feature and have identical gene sequencing feature
Each default genes of individuals sequence signature collection incidence relation.
9. a kind of body movement recognition device, it is characterised in that the body movement recognition device includes：Memory, processor
And the computer program that can be run on the memory and on the processor is stored in, the computer program is by the place
Manage and realized when device performs as any one of claim 1 to 8 the step of body action identification method.
10. a kind of computer-readable recording medium, it is characterised in that be stored with limbs on the computer-readable recording medium and move
Make recognizer, the limb as any one of claim 1 to 8 is realized when the limb action recognizer is executed by processor
The step of body action identification method.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711103064.4A CN107895148B (en) | 2017-11-08 | 2017-11-08 | Limb action recognition method and device and computer readable storage medium |
| PCT/CN2018/092852 WO2019091125A1 (en) | 2017-11-08 | 2018-06-26 | Body movement recognition method and apparatus, and computer readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711103064.4A CN107895148B (en) | 2017-11-08 | 2017-11-08 | Limb action recognition method and device and computer readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107895148A true CN107895148A (en) | 2018-04-10 |
| CN107895148B CN107895148B (en) | 2021-02-05 |
Family
ID=61804902
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711103064.4A Active CN107895148B (en) | 2017-11-08 | 2017-11-08 | Limb action recognition method and device and computer readable storage medium |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN107895148B (en) |
| WO (1) | WO2019091125A1 (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2019091125A1 (en) * | 2017-11-08 | 2019-05-16 | 深圳市科迈爱康科技有限公司 | Body movement recognition method and apparatus, and computer readable storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101532049A (en) * | 2008-03-14 | 2009-09-16 | 上海芯超生物科技有限公司 | Genetic chip for guiding children personalized education and detection sets and method thereof |
| US20130225662A1 (en) * | 2008-11-17 | 2013-08-29 | Veracyte, Inc. | Methods and compositions of molecular profiling for disease diagnostics |
| CN105213155A (en) * | 2015-10-29 | 2016-01-06 | 刘珩先 | A kind of artificial intelligence motion's auxiliary facilities |
| CN105739688A (en) * | 2016-01-21 | 2016-07-06 | 北京光年无限科技有限公司 | Man-machine interaction method and device based on emotion system, and man-machine interaction system |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10638092B2 (en) * | 2016-03-31 | 2020-04-28 | Konica Minolta Laboratory U.S.A., Inc. | Hybrid camera network for a scalable observation system |
| CN106022208A (en) * | 2016-04-29 | 2016-10-12 | 北京天宇朗通通信设备股份有限公司 | Human body motion recognition method and device |
| CN106293099A (en) * | 2016-08-19 | 2017-01-04 | 北京暴风魔镜科技有限公司 | Gesture identification method and system |
| CN107103311A (en) * | 2017-05-31 | 2017-08-29 | 西安工业大学 | A kind of recognition methods of continuous sign language and its device |
| CN107330418B (en) * | 2017-07-12 | 2021-06-01 | 深圳市铂越科技有限公司 | Robot system |
| CN107895148B (en) * | 2017-11-08 | 2021-02-05 | 深圳市科迈爱康科技有限公司 | Limb action recognition method and device and computer readable storage medium |
-
2017
- 2017-11-08 CN CN201711103064.4A patent/CN107895148B/en active Active
-
2018
- 2018-06-26 WO PCT/CN2018/092852 patent/WO2019091125A1/en active Application Filing
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101532049A (en) * | 2008-03-14 | 2009-09-16 | 上海芯超生物科技有限公司 | Genetic chip for guiding children personalized education and detection sets and method thereof |
| US20130225662A1 (en) * | 2008-11-17 | 2013-08-29 | Veracyte, Inc. | Methods and compositions of molecular profiling for disease diagnostics |
| CN105213155A (en) * | 2015-10-29 | 2016-01-06 | 刘珩先 | A kind of artificial intelligence motion's auxiliary facilities |
| CN105739688A (en) * | 2016-01-21 | 2016-07-06 | 北京光年无限科技有限公司 | Man-machine interaction method and device based on emotion system, and man-machine interaction system |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2019091125A1 (en) * | 2017-11-08 | 2019-05-16 | 深圳市科迈爱康科技有限公司 | Body movement recognition method and apparatus, and computer readable storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107895148B (en) | 2021-02-05 |
| WO2019091125A1 (en) | 2019-05-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20230155969A1 (en) | Context sensitive avatar captions | |
| CN110349081B (en) | Image generation method and device, storage medium and electronic equipment | |
| CN111191599B (en) | Gesture recognition method, device, equipment and storage medium | |
| US9779527B2 (en) | Method, terminal device and storage medium for processing image | |
| CN109949412B (en) | Three-dimensional object reconstruction method and device | |
| CN107633207A (en) | AU characteristic recognition methods, device and storage medium | |
| CN110163806A (en) | A kind of image processing method, device and storage medium | |
| CN112100337B (en) | Emotion recognition method and device in interactive dialogue | |
| CN107784114A (en) | Recommendation method, apparatus, terminal and the storage medium of facial expression image | |
| CN107463124A (en) | Intelligent air equipment and its control method, device, server, storage medium | |
| CN108108649A (en) | Auth method and device | |
| CN109213732A (en) | A kind of method, mobile terminal and computer readable storage medium improving photograph album classification | |
| KR102455966B1 (en) | Mediating Apparatus, Method and Computer Readable Recording Medium Thereof | |
| CN109145926A (en) | Similar pictures recognition methods and computer equipment | |
| CN111209812A (en) | Target face picture extraction method and device and terminal equipment | |
| WO2021223738A1 (en) | Method, apparatus and device for updating model parameter, and storage medium | |
| CN110349232A (en) | Generation method, device, storage medium and the electronic equipment of image | |
| CN107704514A (en) | A kind of photo management method, device and computer-readable recording medium | |
| CN107809654A (en) | System for TV set and TV set control method | |
| CN112488914A (en) | Image splicing method, device, terminal and computer readable storage medium | |
| CN107886559A (en) | Method and apparatus for generating picture | |
| CN110147742A (en) | A kind of key independent positioning method, device and terminal | |
| CN114615455A (en) | Teleconference processing method, teleconference processing device, teleconference system, and storage medium | |
| CN108921084A (en) | A kind of image classification processing method, mobile terminal and computer readable storage medium | |
| CN107895148A (en) | Body action identification method, device and computer-readable recording medium |
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 |