CN108153421A - Body feeling interaction method, apparatus and computer readable storage medium - Google Patents
Body feeling interaction method, apparatus and computer readable storage medium Download PDFInfo
- Publication number
- CN108153421A CN108153421A CN201711428309.0A CN201711428309A CN108153421A CN 108153421 A CN108153421 A CN 108153421A CN 201711428309 A CN201711428309 A CN 201711428309A CN 108153421 A CN108153421 A CN 108153421A
- Authority
- CN
- China
- Prior art keywords
- body feeling
- feeling interaction
- coordinate
- node
- bone information
- 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/011—Arrangements for interaction with the human body, e.g. for user immersion in virtual reality
Abstract
The invention discloses a kind of body feeling interaction method, including:Based on depth camera, the bone information of current human is obtained;The bone information is calculated based on preset rules, obtains corresponding result of calculation;Corresponding body feeling interaction action command is determined, and respond to the body feeling interaction action command according to the result of calculation.The invention also discloses a kind of body feeling interaction device and computer readable storage mediums.The present invention improves the human body attitude during human-computer interaction and the accuracy of action perception.
Description
Technical field
The present invention relates to human-computer interaction technique field more particularly to a kind of body feeling interaction method, apparatus and computer-readable
Storage medium.
Background technology
With the rapid proliferation of smart television, body feeling interaction increasingly attracts attention, wherein, the body based on depth camera
The demand for feeling interaction is also increasing.At present, there are many smart television for supporting body-sensing interactive device, various bases in the market
Also occur therewith in the body feeling interaction application and game of depth camera.
In body-sensing interactive process, how to perceive the posture of human body and action is one of key technology, passes through depth camera
Machine and the relevant technologies can extract human skeleton information, so as to perceive the posture of human body and action, in human body attitude and move
Make to need to use relevant matches technology, i.e. human body attitude and the measuring similarity of action in perception.It is but traditional similar
Degree measure is largely all based on Euclid distance criterion, and this measure is easily influenced by exceptional value, and is not had
In view of characteristics such as scale invariability and translation invariances, therefore the accuracy measured can be affected.
Invention content
It is a primary object of the present invention to provide a kind of body feeling interaction method, apparatus and computer readable storage medium, purport
User's posture and the measuring similarity accuracy of action by exceptional value, scale invariability and are put down during body feeling interaction is solved
The technical issues of motion immovability influences.
To achieve the above object, the present invention provides a kind of body feeling interaction method, and the body feeling interaction method includes:
Based on depth camera, the bone information of current human is obtained;
The bone information is calculated based on preset rules, obtains corresponding result of calculation;
Corresponding body feeling interaction action command is determined, and the body feeling interaction action command is made according to the result of calculation
Go out to respond.
Optionally, the body feeling interaction method, which is characterized in that it is described based on depth camera, obtain the bone of current human
Include after the step of bone information:
Space coordinates are established based on the bone information, wherein, the bone information includes each node of current human
Information;
It determines the position of each node in the bone information, and determines that each node is corresponding in the space coordinates
Node coordinate.
Optionally, the body feeling interaction method, which is characterized in that described to be carried out based on preset rules to the bone information
Before the step of calculating, obtaining corresponding result of calculation, further include:
Obtain the standard nodes coordinate in the corresponding bone information of preset standard posture action.
Optionally, the body feeling interaction method, which is characterized in that described to be carried out based on preset rules to the bone information
The step of calculating, obtaining corresponding result of calculation includes:
The node coordinate is converted based on preset rules, obtains transformation results;
Joint entropy calculating is carried out based on the transformation results, obtains similarity value.
Optionally, the body feeling interaction method, which is characterized in that described to be carried out based on preset rules to the node coordinate
The step of converting, obtaining transformation results includes:
Based on the standard nodes coordinate, to the node coordinate into row degradation affine transformation, degeneration affine transformation is obtained
Node coordinate afterwards;
According to preset reference mode coordinate, relative coordinate transformation is carried out to the node coordinate after the degeneration affine transformation
It calculates, obtains counterpart node coordinate.
Optionally, the body feeling interaction method, which is characterized in that it is described based on the standard nodes coordinate, to the section
Point coordinates after the step of obtaining the node coordinate after degeneration affine transformation, is further included into row degradation affine transformation:
Based on the reference mode coordinate in the corresponding bone information of the preset standard posture action, to the standard
Node coordinate carries out relative coordinate transformation calculations, obtains relative standard's node coordinate.
Optionally, the body feeling interaction method, which is characterized in that described to carry out joint entropy meter based on the transformation results
The step of calculating, obtaining similarity value includes:
Based on the counterpart node coordinate and relative standard's node coordinate, joint entropy calculating is carried out, obtains similarity
Value.
Optionally, the body feeling interaction method, which is characterized in that described that corresponding body-sensing is determined according to the result of calculation
Interactive action instructs, and the step of responding to the body feeling interaction action command includes:
Judge whether the similarity value is greater than or equal to preset similarity threshold;
If the similarity value is greater than or equal to preset similarity threshold, it is determined that the posture action of the current human
It is acted for the preset standard posture, and determines corresponding body feeling interaction action command, to be acted to the body feeling interaction
Instruction responds.
In addition, to achieve the above object, the present invention also provides a kind of body feeling interaction device, the body feeling interaction device packet
It includes:Memory, processor and the body feeling interaction program that can be run on the memory and on the processor is stored in, it is described
Body feeling interaction program realizes the step of body feeling interaction method as described above when being performed by the processor.
In addition, to achieve the above object, it is described computer-readable the present invention also provides a kind of computer readable storage medium
Body feeling interaction program is stored on storage medium, the body feeling interaction program realizes body-sensing as described above when being executed by processor
The step of exchange method.
A kind of body feeling interaction method proposed by the present invention obtains the current bone information of user by depth camera, and
Based on preset rules, bone information is calculated, determines the posture corresponding to the current bone information of user and action, and according to
The corresponding body-sensing action command of determining posture action triggers, to respond to corresponding body-sensing action command.Pass through this
The body feeling interaction method proposed is invented, the human body attitude in interactive process and the accurate perception of action are realized, to user
Provide better human-computer interaction usage experience.
Description of the drawings
Fig. 1 is the apparatus structure schematic diagram of hardware running environment that the embodiment of the present invention is related to;
Fig. 2 is the flow diagram of body feeling interaction method first embodiment of the present invention;
Fig. 3 is the flow diagram of body feeling interaction method second embodiment of the present invention;
Fig. 4 is the refinement flow diagram of the step S20 in Fig. 3;
Fig. 5 is the flow diagram of body feeling interaction method 3rd embodiment of the present invention;
Fig. 6 is a kind of human skeleton model figure of 30 common nodes in the embodiment of the present invention.
The embodiments will be further described with reference to the accompanying drawings for the realization, the function and the advantages of the object of the present invention.
Specific 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:Based on depth camera, the bone information of current human is obtained;It is based on
Preset rules calculate the bone information, obtain corresponding result of calculation;It is determined according to the result of calculation corresponding
Body feeling interaction action command, and respond to the body feeling interaction action command.Technical solution through the embodiment of the present invention,
User's posture and the measuring similarity accuracy of action are solved during body feeling interaction by exceptional value, scale invariability and flat
The technical issues of motion immovability influences, realizes the human body attitude in interactive process and the accurate perception of action, to user
Provide better human-computer interaction usage experience.
As shown in Figure 1, the apparatus structure schematic diagram of hardware running environment that Fig. 1, which is the embodiment of the present invention, to be related to.
Device of the embodiment of the present invention can be PC or smart television, tablet computer, pocket computer etc. with aobvious
Show the packaged type terminal device of function.
As shown in Figure 1, the device can include:Processor 1001, such as CPU, communication bus 1002, user interface
1003, network interface 1004, memory 1005.Wherein, communication bus 1002 is used to implement the connection communication between these components.
User interface 1003 can include display screen (Display), input unit such as keyboard (Keyboard), optional user interface
1003 can also include standard wireline interface and wireless interface.Network interface 1004 can optionally connect including the wired of standard
Mouth, wireless interface (such as WI-FI interfaces).Memory 1005 can be high-speed RAM memory or the memory of stabilization
(non-volatile memory), such as magnetic disk storage.Memory 1005 optionally can also be independently of aforementioned processor
1001 storage device.
Optionally, device can also include camera, RF (Radio Frequency, radio frequency) circuit, sensor, audio
Circuit, WiFi module etc..Wherein, sensor such as optical sensor, motion sensor and other sensors.Specifically, light
Sensor may include ambient light sensor and proximity sensor.Certainly, device can also configure gyroscope, barometer, hygrometer, temperature
The other sensors such as meter, infrared ray sensor are spent, details are not described herein.
It will be understood by those skilled in the art that the restriction of the apparatus structure shown in Fig. 1 not structure twin installation, can wrap
It includes and either combines certain components or different components arrangement than illustrating more or fewer components.
As shown in Figure 1, it can lead to as in a kind of memory 1005 of computer storage media including operating system, network
Believe module, Subscriber Interface Module SIM and body feeling interaction program.
In device shown in Fig. 1, network interface 1004 is mainly used for connecting background server, is carried out with background server
Data communicate;User interface 1003 is mainly used for connecting client (user terminal), with client into row data communication;And processor
1001st, memory 1005 can be arranged in body feeling interaction device, and the body feeling interaction device is deposited by the calling of processor 1001
The body feeling interaction program stored in reservoir 1005, and perform following operate:
Based on depth camera, the bone information of current human is obtained;
The bone information is calculated based on preset rules, obtains corresponding result of calculation;
Corresponding body feeling interaction action command is determined, and the body feeling interaction action command is made according to the result of calculation
Go out to respond.
Further, processor 1001 can call the body feeling interaction program stored in memory 1005, also perform following
Operation:
Space coordinates are established based on the bone information, wherein, the bone information includes each node of current human
Information;
It determines the position of each node in the bone information, and determines that each node is corresponding in the space coordinates
Node coordinate.
Further, processor 1001 can call the body feeling interaction program stored in memory 1005, also perform following
Operation:
Obtain the standard nodes coordinate in the corresponding bone information of preset standard posture action.
Further, processor 1001 can call the body feeling interaction program stored in memory 1005, also perform following
Operation:
The node coordinate is converted based on preset rules, obtains transformation results;
Joint entropy calculating is carried out based on the transformation results, obtains similarity value.
Further, processor 1001 can call the body feeling interaction program stored in memory 1005, also perform following
Operation:
Based on the standard nodes coordinate, to the node coordinate into row degradation affine transformation, degeneration affine transformation is obtained
Node coordinate afterwards;
According to preset reference mode coordinate, relative coordinate transformation is carried out to the node coordinate after the degeneration affine transformation
It calculates, obtains counterpart node coordinate.
Further, processor 1001 can call the body feeling interaction program stored in memory 1005, also perform following
Operation:
Based on the reference mode coordinate in the corresponding bone information of the preset standard posture action, to the standard
Node coordinate carries out relative coordinate transformation calculations, obtains relative standard's node coordinate.
Further, processor 1001 can call the body feeling interaction program stored in memory 1005, also perform following
Operation:
Based on the counterpart node coordinate and relative standard's node coordinate, joint entropy calculating is carried out, obtains similarity
Value.
Further, processor 1001 can call the body feeling interaction program stored in memory 1005, also perform following
Operation:
Judge whether the similarity value is greater than or equal to preset similarity threshold;
If the similarity value is greater than or equal to preset similarity threshold, it is determined that the posture action of the current human
It is acted for the preset standard posture, and determines corresponding body feeling interaction action command, to be acted to the body feeling interaction
Instruction responds.
Scheme provided in this embodiment obtains the current bone information of user, and based on default rule by depth camera
Then, bone information is calculated, determines the posture corresponding to the current bone information of user and action, and according to determining posture
The corresponding body-sensing action command of action triggers, to respond to corresponding body-sensing action command.By proposed by the present invention
Body feeling interaction method realizes the human body attitude in interactive process and the accurate perception of action, provide the user more preferable
Human-computer interaction usage experience.
Based on above-mentioned hardware configuration, body feeling interaction embodiment of the method for the present invention is proposed.
With reference to Fig. 2, Fig. 2 is the flow diagram of body feeling interaction method first embodiment of the present invention, in this embodiment, institute
The method of stating includes:
Step S10 based on depth camera, obtains the bone information of current human;
Step S20 calculates the bone information based on preset rules, obtains corresponding result of calculation;
Step S30 determines corresponding body feeling interaction action command, and the body feeling interaction is moved according to the result of calculation
Make instruction to respond.
With the rapid proliferation of smart television, body feeling interaction technology increasingly attracts attention.The advantage of body feeling interaction technology
It is, people, can be directly using limb action come the device or ring with periphery without using the control device of any complexity
Border is interactive, gives people feeling on the spot in person.
At present, it obtains image using multiple optical cameras and infrared camera and carries out three-dimensional modeling, then acted
Identification and the identification acted using depth camera extraction human skeleton information, are the main of current body-sensing technology
Principle.Wherein, the demand of the body feeling interaction based on depth camera is increasing, and at present, there are many supports in the market
Feel the smart television of interactive device, various body feeling interaction applications and game based on depth camera also occur therewith.
In body-sensing interactive process, how to perceive the posture of human body and action is one of key technology.Based on depth camera
The body feeling interaction principle of machine is:Human skeleton and nodal information are extracted by depth camera, pass through the node of the bone
The posture of validation of information current human and action, and corresponding instruction is performed according to the action of confirmation.It needs in this process
Use relevant bone information and the matching technique of posture action, i.e. human body attitude and the measuring similarity of action.
Traditional method for measuring similarity is largely all based on Euclid distance criterion, the Europe in two and three dimensions space
Family name's distance is exactly the actual range between 2 points, by the nodal information in skeleton, calculates the distance between each node,
And posture and the action of human body are judged with this.But this measure is easily by the exceptional value caused by Equipment
It influencing, the robustness for leading to measurement is insufficient, and does not account for the characteristics such as scale invariability and translation invariance, for example, with
For the two groups of skeleton information obtained, probably due to location is different in a coordinate system by two people, it is similar so as to cause
The calculating error of degree;Equally, the distance of user and depth camera can also directly affect the scale size of skeleton information,
So as to cause the calculating error of similarity.Therefore, using traditional method for measuring similarity come confirm the posture of current human with
And action, the accuracy of measurement can be affected.
Therefore, for overcome the deficiencies in the prior art, the present invention proposes a kind of body feeling interaction method, by coordinate system
In bone node coordinate into row degradation affine transformation, obtain the node coordinate after scale and translation transformation, then by right
Node coordinate is carried out relative coordinate transformation and the measuring similarity calculating of node coordinate is carried out using joint entropy, and joint entropy is got over
Greatly, show that the similarity of the two being compared is higher, you can determine the current posture of user and action.In the present embodiment,
To explain by taking the body feeling interaction of smart television as an example.
In the present embodiment, the bone information of active user is obtained by depth camera first, taking a smart TV as an example,
Depth camera is positioned on smart television or inside smart television, when subscriber station begins with limb action before smart television
When, depth camera can capture the current limb action of user, and form the skeleton information of active user, wherein, people
Body bone information includes the information of multiple nodes, and the position corresponding to the number and node of node can be set in advance,
It is not limited.
Further, after the bone information for obtaining current human, by establishing three-dimensional system of coordinate, obtain current human's
The coordinate of each node in bone information as shown in fig. 6, illustrating a kind of human skeleton model of 30 common nodes in Fig. 6, is schemed
The English of middle mark is the corresponding English name of each node, has also marked the corresponding id of each node for ease of description, in figure and has compiled
Number, from 0 to 29, totally 30 nodes.Wherein, the 0th node is waist, and the 1st node is left side hip joint, and the 2nd node is
Left femur, the 3rd node are left tibias, and the 4th node is left side foot, and the 5th node is left side toe, and the 6th extremely
Represented by 10th node and the 1st in figure to the 5th node is one-to-one, and expression is on the right side of the lower part of the body of human body
Corresponding bone node, the 11st node are abdomen, and the 12nd node is lower back portion, and the 13rd node is upper back, the 14th
Node is thorax, and the 15th node is low portion of neck, and the 16th node is upper neck, and the 17th node is head, the 18th node
For left collarbone, the 19th node is left side humerus, and the 20th node is left side radius, and the 21st node is left side wrist, the
22 nodes are left side hand, and the 23rd node is left side finger, similarly, the 18th in the 24th to the 29th node and figure
To represented by the 23rd node be it is one-to-one, expression is corresponding bone node on the right hand of human body.
The space coordinate of 30 nodes shown in Fig. 6 can be obtained, then by each section by establishing three-dimensional system of coordinate
The transformation and calculating of point coordinates obtain the corresponding posture action of current bone information, that is, the current posture of user are determined and moves
Make corresponding body feeling interaction instruction, smart television makes corresponding response according to determining instruction.
In the present embodiment, the current bone information of user is obtained by depth camera, and based on preset rules, to bone
Bone information is calculated, and determines the posture corresponding to the current bone information of user and action, and act and touch according to determining posture
Send out body-sensing action command corresponding, to respond to corresponding body-sensing action command.It is handed over by body-sensing proposed by the present invention
Mutual method realizes the human body attitude in interactive process and the accurate perception of action, provide the user preferably man-machine
It is used interchangeably experience.
Further, with reference to Fig. 3, based on above-described embodiment, body feeling interaction method second embodiment of the present invention is proposed, at this
In embodiment, after the step S10, further include:
Step S40 establishes space coordinates based on the bone information, wherein, the bone information includes current human
Each node information;
Step S50 determines the position of each node in the bone information, and determines each node in the space coordinate
Corresponding node coordinate in system.
In the present embodiment, after the bone information that current human is obtained by depth camera, the bone letter based on acquisition
Breath establishes a three-dimensional space coordinates, and determines the corresponding seat of corresponding each node in a coordinate system in bone information
Mark.It is understood that the foundation of this space coordinates is arbitrary, by subsequent calculating, can eliminate because of foundation
It is translated caused by the difference of coordinate system and scale influences.
Further, as shown in figure 4, the step S20 includes:
Step S21 converts the node coordinate based on preset rules, obtains transformation results;
Step S22 carries out joint entropy calculating based on the transformation results, obtains similarity value.
Body feeling interaction method proposed by the present invention, posture and action similarity degree suitable for known human skeleton model
Amount, as shown in fig. 6, for a kind of human skeleton model of 30 common nodes.The present invention is suitable for various types of skeletons
Model, the number of nodes and position in model are unlimited.
Further, it before the step S20, further includes:
Step c obtains the standard nodes coordinate in the corresponding bone information of preset standard posture action.
In the present embodiment, it is bone information by obtaining current human, itself and preset standard posture is acted into institute
Corresponding bone information is compared, and judges similarity therebetween, therefore, after current human's bone information is obtained,
It also needs to obtain the corresponding bone information of preset standard posture action, specifically referring to corresponding standard nodes coordinate letter
Breath.It is understood that the number of standard nodes mentioned here and the node number in the active user's bone information obtained
It is the same, and each node location is also the same, to be compared.
Similarly, it can also be that the bone information by the different user for obtaining depth camera is compared, and judges it
Whether posture action is consistent.For example, the skeleton information that current depth camera obtains is skeleton A and skeleton B, it is right
The bone information of two people carries out joint entropy calculating, judges the similarity of the posture action of the two.
In the present embodiment, after the bone information that current human is obtained by depth camera, the bone letter based on acquisition
Breath establishes space coordinates, and determines the corresponding node coordinate of corresponding each node in a coordinate system in bone information, simultaneously
The standard nodes coordinate in the corresponding bone information of preset standard posture action is obtained, by node coordinate and standard
The transformation and calculating of node coordinate determine posture and the action of active user, and the user's posture realized in human-computer interaction is moved
That makees accurately identifies, and promotes the usage experience of user.
Further, with reference to Fig. 5, based on above-described embodiment, body feeling interaction method 3rd embodiment of the present invention is proposed, at this
In embodiment, the step S21 includes:
Step S211 based on the standard nodes coordinate, to the node coordinate into row degradation affine transformation, is degenerated
Node coordinate after affine transformation;
According to preset reference mode coordinate, phase is carried out to the node coordinate after the degeneration affine transformation by step S212
Coordinate transform is calculated, obtains counterpart node coordinate.
After the skeleton model and corresponding node coordinate for determining current human, i.e., by calculating and converting accordingly,
Specifically based on the transformation calculations that standard nodes coordinate is carried out, by calculating and converting accordingly, similarity degree is promoted
The scale invariability and translation invariance of amount improve the accuracy of measurement.
In the present embodiment, it is necessary first to each node coordinate into row degradation affine transformation, by degeneration affine transformation, draw
Enter shift factor and scale factor, so as to reduce because of the influence for the measuring similarity that scale invariability and translation invariance are brought.
The it is proposed of degeneration affine transformation concept in the present invention is the concept for distinguishing traditional affine transformation, traditional affine change
The transformation factors such as translation, scale, rotation, distortion have been changed, in the present invention, translation, ruler have only been used to the coordinate transform of each node
Two kinds of factors are spent, because of referred to herein as degeneration affine transformation.
Assuming that it is respectively A and B to need to carry out posture and act the skeleton of measuring similarity, wherein, skeleton A's
I-th of node coordinate is expressed as with vector【xi, yi, zi】, wherein, i=1,2 ... ... N, i-th of node coordinate of skeleton B
It is expressed as with vector【ai, bi, ci】, wherein, i=1,2 ... ... N.In the present embodiment, it is by the bone information to two people
Carry out similarity calculation, the similarity of posture action both judged, likewise it is possible to using skeleton B as it is preset certain
One standard posture acts corresponding bone information, the current movement postures of user A is determined by calculation, in human-computer interaction
Human action identification.
Specifically, it is as follows to the mathematical expression of i-th of node coordinate into the row degradation affine transformation of A:
Wherein, α is scale factor, β=【β1, β2, β3】TIt is shift factor.As i-th of A of the equal sign left side in above formula
Coordinate after node coordinate degeneration affine transformation.For α and β, can be directly obtained by minimum variance principle, mathematic(al) representation
It is as follows:
Wherein, yi=【x'i, y'i, z'i】T, xi=【ai, bi, ci】T, X hereiniAs i-th of node of skeleton B
Coordinate.By, into row degradation affine transformation, improving the translation invariance of measuring similarity to node coordinate.
Further, it in order to reduce error and facilitate calculating, needs to turn the node coordinate after degeneration affine transformation
Change relative coordinate into.Before relative coordinate conversion is carried out, it usually needs determine reference mode, the determining of reference mode is arbitrary
, it is not limited.
Some node is used as with reference to after node in selected skeleton model, and the seat of reference mode is subtracted with the coordinate of remaining node
Mark, you can obtain the counterpart node coordinate of the node.For example, it can select to number the chest node for 14 in Fig. 6, as reference
Node, then the solution procedure of the counterpart node coordinate of i-th of node is as follows:
Wherein, the right of above formula represents the relative coordinate of i-th of node, is sat similarly, for the node of skeleton B
Mark, it is also desirable to which relative coordinate transformation is carried out by selected reference mode.It is to be appreciated that the reference mode of two skeletons,
Refer to same node, converted by relative coordinate, improve the scale invariability of measuring similarity.
Further, in system acquisition and the coordinate information being calculated, due to equipment, image acquisition process
In usually there will be some exceptional values, the method that traditional Euclidean distance calculates similarity, in the calculating of these exceptional values often
Robustness is inadequate, therefore, in the present invention, is used as the criterion of measuring similarity by using joint entropy, reduces exceptional value and do
It disturbs, improves the robustness of measurement.
Specifically, it is as follows to the mathematic(al) representation of the relative coordinate joint entropy of skeleton A and skeleton B:
Wherein,Represent extensive Gaussian density function, mathematic(al) representation is as follows:
Wherein, Γ () represents gamma function, and λ represents form factor, and μ represents bandwidth factor, is all preset known ginseng
Number, ei=| | yi-xi||2, can be calculated by the mathematic(al) representation of above-mentioned minimum variance principle.
By the calculating of above-mentioned relative coordinate joint entropy, the value of a joint entropy can be obtained, the value is bigger, shows A and B
Between similarity it is higher.
Further, it to the similarity value being calculated, is compared with preset similarity threshold, judges whether it is big
In or equal to preset similarity threshold, if the similarity value being calculated is greater than or equal to preset similarity threshold, table
The posture action of bright current human is preset standard posture action, you can determines the body feeling interaction action corresponding to the action
Instruction, so that body feeling interaction equipment, such as smart television etc. give a response the body feeling interaction action command.
In the present embodiment, based on preset standard nodes coordinate, to the node coordinate in current human's bone information, into
Row degradation affine transformation and relative coordinate transformation, after obtaining transformation results, then carry out joint entropy metric calculation, it is final determine with
The corresponding posture action of current human's bone information, and determine corresponding body feeling interaction action command, so that smart television is to this
Body feeling interaction action command responds, and realizes more accurate interactive process, improve user and smart television into
Usage experience during row human-computer interaction.
In addition, the embodiment of the present invention also proposes a kind of computer readable storage medium, the computer readable storage medium
On be stored with body feeling interaction program, following operation is realized when the body feeling interaction program is executed by processor:
Based on depth camera, the bone information of current human is obtained;
The bone information is calculated based on preset rules, obtains corresponding result of calculation;
Corresponding body feeling interaction action command is determined, and the body feeling interaction action command is made according to the result of calculation
Go out to respond.
Further, following operation is also realized when the body feeling interaction program is executed by processor:
Space coordinates are established based on the bone information, wherein, the bone information includes each node of current human
Information;
It determines the position of each node in the bone information, and determines that each node is corresponding in the space coordinates
Node coordinate.
Further, following operation is also realized when the body feeling interaction program is executed by processor:
Obtain the standard nodes coordinate in the corresponding bone information of preset standard posture action.
Further, following operation is also realized when the body feeling interaction program is executed by processor:
The node coordinate is converted based on preset rules, obtains transformation results;
Joint entropy calculating is carried out based on the transformation results, obtains similarity value.
Further, following operation is also realized when the body feeling interaction program is executed by processor:
Based on the standard nodes coordinate, to the node coordinate into row degradation affine transformation, degeneration affine transformation is obtained
Node coordinate afterwards;
According to preset reference mode coordinate, relative coordinate transformation is carried out to the node coordinate after the degeneration affine transformation
It calculates, obtains counterpart node coordinate.
Further, following operation is also realized when the body feeling interaction program is executed by processor:
Based on the reference mode coordinate in the corresponding bone information of the preset standard posture action, to the standard
Node coordinate carries out relative coordinate transformation calculations, obtains relative standard's node coordinate.
Further, following operation is also realized when the body feeling interaction program is executed by processor:
Based on the counterpart node coordinate and relative standard's node coordinate, joint entropy calculating is carried out, obtains similarity
Value.
Further, following operation is also realized when the body feeling interaction program is executed by processor:
Judge whether the similarity value is greater than or equal to preset similarity threshold;
If the similarity value is greater than or equal to preset similarity threshold, it is determined that the posture action of the current human
It is acted for the preset standard posture, and determines corresponding body feeling interaction action command, to be acted to the body feeling interaction
Instruction responds.
Scheme provided in this embodiment obtains the current bone information of user, and based on default rule by depth camera
Then, bone information is calculated, determines the posture corresponding to the current bone information of user and action, and according to determining posture
The corresponding body-sensing action command of action triggers, to respond to corresponding body-sensing action command.By proposed by the present invention
Body feeling interaction method realizes the human body attitude in interactive process and the accurate perception of action, provide the user more preferable
Human-computer interaction usage experience.
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 elements, and
And it further includes other elements that are not explicitly listed or further includes intrinsic for this process, method, article or system institute
Element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that including this
Also there are other identical elements in the process of 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 of the present invention substantially in other words does the prior art
Going out the part of contribution can be embodied in the form of software product, which is stored in one as described above
In storage medium (such as ROM/RAM, magnetic disc, CD), including some instructions use so that 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.
It these are only the preferred embodiment of the present invention, be not intended to limit the scope of the invention, it is every to utilize this hair
The equivalent structure or equivalent flow shift that bright specification and accompanying drawing content are made directly or indirectly is used in other relevant skills
Art field, is included within the scope of the present invention.
Claims (10)
- A kind of 1. body feeling interaction method, which is characterized in that the body feeling interaction method includes the following steps:Based on depth camera, the bone information of current human is obtained;The bone information is calculated based on preset rules, obtains corresponding result of calculation;Corresponding body feeling interaction action command is determined, and the body feeling interaction action command is made back according to the result of calculation It should.
- 2. body feeling interaction method as described in claim 1, which is characterized in that it is described based on depth camera, obtain current human Bone information the step of after include:Space coordinates are established based on the bone information, wherein, the bone information includes the letter of each node of current human Breath;It determines the position of each node in the bone information, and determines each node corresponding section in the space coordinates Point coordinates.
- 3. body feeling interaction method as claimed in claim 2, which is characterized in that the preset rules that are based on are to the bone information Before the step of being calculated, obtaining corresponding result of calculation, further include:Obtain the standard nodes coordinate in the corresponding bone information of preset standard posture action.
- 4. body feeling interaction method as claimed in claim 3, which is characterized in that the preset rules that are based on are to the bone information The step of being calculated, obtaining corresponding result of calculation includes:The node coordinate is converted based on preset rules, obtains transformation results;Joint entropy calculating is carried out based on the transformation results, obtains similarity value.
- 5. body feeling interaction method as claimed in claim 4, which is characterized in that the preset rules that are based on are to the node coordinate The step of being converted, obtaining transformation results includes:Based on the standard nodes coordinate, to the node coordinate into row degradation affine transformation, after obtaining degeneration affine transformation Node coordinate;According to preset reference mode coordinate, relative coordinate transformation meter is carried out to the node coordinate after the degeneration affine transformation It calculates, obtains counterpart node coordinate.
- 6. body feeling interaction method as claimed in claim 5, which is characterized in that it is described based on the standard nodes coordinate, to institute After the step of node coordinate is stated into row degradation affine transformation, obtains the node coordinate after degeneration affine transformation, further include:Based on the reference mode coordinate in the corresponding bone information of the preset standard posture action, to the standard nodes Coordinate carries out relative coordinate transformation calculations, obtains relative standard's node coordinate.
- 7. body feeling interaction method as claimed in claim 6, which is characterized in that described to carry out joint entropy based on the transformation results The step of calculating, obtaining similarity value includes:Based on the counterpart node coordinate and relative standard's node coordinate, joint entropy calculating is carried out, obtains similarity value.
- 8. body feeling interaction method as claimed in claim 7, which is characterized in that it is described determined according to the result of calculation it is corresponding Body feeling interaction action command, and the step of responding to the body feeling interaction action command include:Judge whether the similarity value is greater than or equal to preset similarity threshold;If the similarity value is greater than or equal to preset similarity threshold, it is determined that the posture action of the current human is institute Preset standard posture action is stated, and determines corresponding body feeling interaction action command, so as to the body feeling interaction action command It responds.
- 9. a kind of body feeling interaction device, which is characterized in that the body feeling interaction device includes:It memory, processor and is stored in On the memory and the body feeling interaction program that can run on the processor, the body feeling interaction program is by the processor It is realized during execution such as the step of body feeling interaction method described in any item of the claim 1 to 8.
- 10. a kind of computer readable storage medium, which is characterized in that body-sensing friendship is stored on the computer readable storage medium Mutual program realizes such as body feeling interaction described in any item of the claim 1 to 8 when the body feeling interaction program is executed by processor The step of method.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711428309.0A CN108153421B (en) | 2017-12-25 | 2017-12-25 | Somatosensory interaction method and device and computer-readable storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711428309.0A CN108153421B (en) | 2017-12-25 | 2017-12-25 | Somatosensory interaction method and device and computer-readable storage medium |
Publications (2)
Publication Number | Publication Date |
---|---|
CN108153421A true CN108153421A (en) | 2018-06-12 |
CN108153421B CN108153421B (en) | 2021-10-01 |
Family
ID=62462172
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201711428309.0A Active CN108153421B (en) | 2017-12-25 | 2017-12-25 | Somatosensory interaction method and device and computer-readable storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108153421B (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109859324A (en) * | 2018-12-29 | 2019-06-07 | 北京光年无限科技有限公司 | A kind of motion teaching method and device based on visual human |
WO2020062998A1 (en) * | 2018-09-25 | 2020-04-02 | 上海瑾盛通信科技有限公司 | Image processing method, storage medium, and electronic device |
CN112447272A (en) * | 2019-08-30 | 2021-03-05 | 华为技术有限公司 | Prompting method for fitness training and electronic equipment |
CN112866286A (en) * | 2018-10-29 | 2021-05-28 | 深圳市瑞立视多媒体科技有限公司 | Data transmission method and device, terminal equipment and storage medium |
CN113058259A (en) * | 2021-04-22 | 2021-07-02 | 杭州当贝网络科技有限公司 | Motion sensing action recognition method and system based on game content and storage medium |
CN113058258A (en) * | 2021-04-22 | 2021-07-02 | 杭州当贝网络科技有限公司 | Method, system and storage medium for recognizing expected somatosensory action based on player game |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20110306396A1 (en) * | 2010-06-11 | 2011-12-15 | Harmonix Music Systems, Inc. | Dance Game and Tutuorial |
CN104035557A (en) * | 2014-05-22 | 2014-09-10 | 华南理工大学 | Kinect action identification method based on joint activeness |
CN104808788A (en) * | 2015-03-18 | 2015-07-29 | 北京工业大学 | Method for controlling user interfaces through non-contact gestures |
CN104881122A (en) * | 2015-05-29 | 2015-09-02 | 深圳奥比中光科技有限公司 | Somatosensory interactive system activation method and somatosensory interactive method and system |
CN107080940A (en) * | 2017-03-07 | 2017-08-22 | 中国农业大学 | Body feeling interaction conversion method and device based on depth camera Kinect |
CN107193384A (en) * | 2017-06-29 | 2017-09-22 | 云南大学 | Based on Kinect coloured images in mouse and the switching method of keyboard emulation behavior |
-
2017
- 2017-12-25 CN CN201711428309.0A patent/CN108153421B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20110306396A1 (en) * | 2010-06-11 | 2011-12-15 | Harmonix Music Systems, Inc. | Dance Game and Tutuorial |
CN104035557A (en) * | 2014-05-22 | 2014-09-10 | 华南理工大学 | Kinect action identification method based on joint activeness |
CN104808788A (en) * | 2015-03-18 | 2015-07-29 | 北京工业大学 | Method for controlling user interfaces through non-contact gestures |
CN104881122A (en) * | 2015-05-29 | 2015-09-02 | 深圳奥比中光科技有限公司 | Somatosensory interactive system activation method and somatosensory interactive method and system |
CN107080940A (en) * | 2017-03-07 | 2017-08-22 | 中国农业大学 | Body feeling interaction conversion method and device based on depth camera Kinect |
CN107193384A (en) * | 2017-06-29 | 2017-09-22 | 云南大学 | Based on Kinect coloured images in mouse and the switching method of keyboard emulation behavior |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2020062998A1 (en) * | 2018-09-25 | 2020-04-02 | 上海瑾盛通信科技有限公司 | Image processing method, storage medium, and electronic device |
CN112866286A (en) * | 2018-10-29 | 2021-05-28 | 深圳市瑞立视多媒体科技有限公司 | Data transmission method and device, terminal equipment and storage medium |
CN112866286B (en) * | 2018-10-29 | 2023-03-14 | 深圳市瑞立视多媒体科技有限公司 | Data transmission method and device, terminal equipment and storage medium |
CN109859324A (en) * | 2018-12-29 | 2019-06-07 | 北京光年无限科技有限公司 | A kind of motion teaching method and device based on visual human |
CN112447272A (en) * | 2019-08-30 | 2021-03-05 | 华为技术有限公司 | Prompting method for fitness training and electronic equipment |
CN113058259A (en) * | 2021-04-22 | 2021-07-02 | 杭州当贝网络科技有限公司 | Motion sensing action recognition method and system based on game content and storage medium |
CN113058258A (en) * | 2021-04-22 | 2021-07-02 | 杭州当贝网络科技有限公司 | Method, system and storage medium for recognizing expected somatosensory action based on player game |
Also Published As
Publication number | Publication date |
---|---|
CN108153421B (en) | 2021-10-01 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108153421A (en) | Body feeling interaction method, apparatus and computer readable storage medium | |
US11468612B2 (en) | Controlling display of a model based on captured images and determined information | |
CN109432753B (en) | Action correcting method, device, storage medium and electronic equipment | |
US9928411B2 (en) | Image processing apparatus, image processing system, image processing method, and computer program product | |
CN108229332A (en) | Bone attitude determination method, device and computer readable storage medium | |
Gültepe et al. | Real-time virtual fitting with body measurement and motion smoothing | |
CN109308438A (en) | Method for building up, electronic equipment, the storage medium in action recognition library | |
CN114495177A (en) | Scene interactive human body action and balance intelligent evaluation method and system | |
CN106681479A (en) | User interaction method and system based on virtual reality | |
US11335025B2 (en) | Method and device for joint point detection | |
TWI790369B (en) | Dimensional system | |
CN110610181A (en) | Medical image identification method and device, electronic equipment and storage medium | |
CN111556337B (en) | Media content implantation method, model training method and related device | |
CN110148191A (en) | The virtual expression generation method of video, device and computer readable storage medium | |
CN111160308B (en) | Gesture recognition method, device, equipment and readable storage medium | |
CN109859857A (en) | Mask method, device and the computer readable storage medium of identity information | |
WO2022174544A1 (en) | Action comparison method, apparatus, electronic device, storage medium, computer program product and computer program | |
CN108509924B (en) | Human body posture scoring method and device | |
Chi et al. | A new parametric 3D human body modeling approach by using key position labeling and body parts segmentation | |
US20160335807A1 (en) | Method and system for providing virtual fitting service | |
KR20190057516A (en) | Artificial intelligence total fashion styling system and method using augmented reality | |
CN105807902B (en) | Stablize the method and a kind of mobile terminal that mobile terminal screen content is shown | |
CN113569775A (en) | Monocular RGB input-based mobile terminal real-time 3D human body motion capture method and system, electronic equipment and storage medium | |
CN106200911A (en) | A kind of motion sensing control method based on dual camera, mobile terminal and system | |
WO2023035725A1 (en) | Virtual prop display method and apparatus |
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 |