CN110443167A - Intelligent identification Method, intelligent interactive method and the relevant apparatus of traditional culture gesture - Google Patents

Intelligent identification Method, intelligent interactive method and the relevant apparatus of traditional culture gesture Download PDF

Info

Publication number
CN110443167A
CN110443167A CN201910665464.7A CN201910665464A CN110443167A CN 110443167 A CN110443167 A CN 110443167A CN 201910665464 A CN201910665464 A CN 201910665464A CN 110443167 A CN110443167 A CN 110443167A
Authority
CN
China
Prior art keywords
gesture
traditional culture
active user
intelligent
elbow
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
Application number
CN201910665464.7A
Other languages
Chinese (zh)
Other versions
CN110443167B (en
Inventor
唐啸
黄坤
熊文成
胡畔
向晖
陈勇
林树新
赵静
潘春晓
李林芸
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
China Construction Bank Corp
Original Assignee
China Construction Bank Corp
CCB Finetech Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by China Construction Bank Corp, CCB Finetech Co Ltd filed Critical China Construction Bank Corp
Priority to CN201910665464.7A priority Critical patent/CN110443167B/en
Publication of CN110443167A publication Critical patent/CN110443167A/en
Application granted granted Critical
Publication of CN110443167B publication Critical patent/CN110443167B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F3/00Input 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
    • G06F3/01Input arrangements or combined input and output arrangements for interaction between user and computer
    • G06F3/017Gesture based interaction, e.g. based on a set of recognized hand gestures
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/20Movements or behaviour, e.g. gesture recognition
    • G06V40/23Recognition of whole body movements, e.g. for sport training
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/20Movements or behaviour, e.g. gesture recognition
    • G06V40/28Recognition of hand or arm movements, e.g. recognition of deaf sign language

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Human Computer Interaction (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Health & Medical Sciences (AREA)
  • General Engineering & Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • General Health & Medical Sciences (AREA)
  • Psychiatry (AREA)
  • Social Psychology (AREA)
  • Multimedia (AREA)
  • User Interface Of Digital Computer (AREA)

Abstract

Intelligent identification Method, intelligent interactive method and the relevant apparatus of the embodiment of the present application offer traditional culture gesture, intelligent identification Method therein includes: the video image for the active user that acquisition is located in target pickup area, and the location information based on the user in the video image establishes coordinate system corresponding with active user;The skeleton key point coordinate of corresponding active user is identified according to coordinate system;Using the skeleton key point coordinate of active user, determine the value of pre-set each traditional culture gesture feature, judge whether the value of each traditional culture gesture feature is all satisfied corresponding preset condition, if so, determining that active user makes corresponding traditional culture gesture.The application can carry out automatic identification to traditional culture gesture, and the intelligence degree of identification process and high-efficient, and the accuracy and reliability of the recognition result of traditional culture gesture can be effectively improved, and then the accuracy and intelligence degree of user's interaction can be effectively improved.

Description

Intelligent identification Method, intelligent interactive method and the relevant apparatus of traditional culture gesture
Technical field
This application involves technical field of data processing, and in particular to the intelligent identification Method of traditional culture gesture, intelligence are handed over Mutual method and relevant apparatus.
Background technique
Traditional culture gesture is a kind of meeting ceremony of Chinese tradition that can embody Chinese humanity spirits, in modern society In, it can also be used as the appropriate contacts ceremony of one kind and be widely used.Therein armful of fist salute, bends over to make a slight bow and the row such as gift submissively Gift mode may be collectively termed as traditional culture gesture.And with society can with rapid development, traditional culture and modern science and technology It combines and also has become inundant development trend, especially the interactive mode of traditional culture gesture.
Currently, how existing gesture interaction mode mostly using computer network carries out internet of things networking and remote if focusing on Journey seamless link technology carries out data interaction, and the skeleton critical point detection being directed to also is focused on mostly and how to be identified With extraction key point information and geometric coordinate point feature, it is not particularly suited for the Activity recognition of traditional culture gesture.
Therefore, a kind of Activity recognition mode for traditional culture gesture how is designed, is a problem to be solved.
Summary of the invention
For the problems of the prior art, the application provides a kind of intelligent identification Method of traditional culture gesture, intelligence is handed over Mutual method and relevant apparatus can carry out automatic identification to traditional culture gesture, and the intelligence degree of identification process is high, efficiency Height, and the accuracy and reliability of the recognition result of traditional culture gesture can be effectively improved, and then basis can be effectively improved The accuracy and intelligence degree that the recognition result and the user for making traditional culture gesture interact.
In order to solve the above technical problems, the application the following technical schemes are provided:
In a first aspect, the application provides a kind of intelligent identification Method of traditional culture gesture, comprising:
Acquisition is located at the video image of the active user in target pickup area, and based on the user's in the video image Location information establishes coordinate system corresponding with active user;
The skeleton key point coordinate of corresponding active user is identified according to the coordinate system;
Using the skeleton key point coordinate of active user, pre-set each traditional culture gesture feature is determined Value, and judge whether the value of each traditional culture gesture feature is all satisfied corresponding preset condition, if so, Determine that active user makes corresponding traditional culture gesture.
Further, the traditional culture gesture feature include: human body nose neck away from and aspect ratio of the both shoulders away between, hand Wrist away between x-axis unit vector of the elbow in aspect ratio, two wrist vectors and the coordinate system away between angle, two The direction vector of the angle between x-axis unit vector, right hand elbow to right finesse in a elbow vector and the coordinate system and institute The inner product between the y-axis unit vector in coordinate system is stated, and, in the direction vector of left hand elbow to left finesse and the coordinate system Y-axis unit vector between inner product.
Further, whether the value for judging each traditional culture gesture feature is all satisfied corresponding pre- If condition, comprising:
Judge the nose neck away from and aspect ratio of the both shoulders away between whether be less than or equal to preset nose neck away from both shoulders away from The ratio between decision threshold, to determine whether active user makes the movement bowed;
Judge the wrist away from and aspect ratio of the elbow away between whether be less than or equal to preset both hands wrist and both hands elbow The decision threshold of ratio of distances constant, to determine whether active user makes the movement that both hands close up and elbow separates outward;
Judge whether the angle between the x-axis unit vector in described two wrist vectors and the coordinate system is less than or waits In preset both hands wrist and horizontal line angle threshold value, and, judge the x-axis list in described two elbow vectors and the coordinate system Whether the angle between bit vector is less than or equal to preset both hands elbow and horizontal line angle threshold value, whether to determine active user Make the movement embracing fist and saluting that horizontal symmetry is presented in both hands orientation;
Judge the right hand elbow to the inner product between the y-axis unit vector in the direction vector and the coordinate system of right finesse Whether be greater than 0, and, judge the left hand elbow to the y-axis unit vector in the direction vector and the coordinate system of left finesse it Between inner product whether be greater than 0, to determine whether active user makes wrist location higher than the corresponding movement in elbow position.
Further, described if so, determining active user or having made traditional culture gesture, comprising:
If judged the movement knowing active user while bowing described in being made that, the both hands close up and elbow outward The movement and the wrist location that armful fist of isolated movement, both hands orientation presentation horizontal symmetry is saluted are higher than elbow The corresponding movement in position, it is determined that active user or has made traditional culture gesture.
Second aspect, the application provide a kind of intelligent interactive method of traditional culture gesture, comprising:
If determining that active user makes corresponding traditional culture using the intelligent identification Method of the traditional culture gesture Gesture then judges that the user makes whether the number of the traditional culture gesture is more than preset value within the preset identification period, if It is then to trigger preset alternative events corresponding with the traditional culture gesture.
Further, the preset alternative events corresponding with the traditional culture gesture of triggering include:
Play instruction is sent to corresponding multimedia equipment, so that the multimedia equipment plays in advance according to the play instruction The video content or music content of storage;
And/or
Open command is sent to corresponding lighting system, so that the lighting system controls corresponding area according to the open command The lamp in domain is lighted or is flashed.
The third aspect, the application provide a kind of intelligent identification device of traditional culture gesture, comprising:
Video data acquiring module, for acquiring the video image for the active user being located in target pickup area, and base The location information of user in the video image establishes coordinate system corresponding with active user;
Skeleton key point identification module, for identifying the skeleton of corresponding active user according to the coordinate system Key point coordinate;
Traditional culture gesture interaction Activity recognition module, for the skeleton key point coordinate of application active user, really The value of fixed pre-set each traditional culture gesture feature, and judge that the value of each traditional culture gesture feature is It is no to be all satisfied corresponding preset condition, if so, determining that active user makes corresponding traditional culture gesture.
Fourth aspect, the application provide a kind of intelligent interaction device of traditional culture gesture, comprising:
Traditional culture gesture interaction event trigger module, if for the intelligent recognition side using the traditional culture gesture Method determines that active user makes corresponding traditional culture gesture, then judges that the user makes the tradition within the preset identification period Whether the number of cultural gesture is more than preset value, if so, the preset alternative events corresponding with the traditional culture gesture of triggering.
5th aspect, the application provides a kind of electronic equipment, including memory, processor and storage are on a memory and can The computer program run on a processor, the processor realize the intelligence of the traditional culture gesture when executing described program The step of energy recognition methods, alternatively, the step of realizing the intelligent interactive method of the traditional culture gesture.
6th aspect, the application provide a kind of computer readable storage medium, are stored thereon with computer program, the calculating The step of intelligent identification Method of the traditional culture gesture is realized when machine program is executed by processor, alternatively, described in realizing Traditional culture gesture intelligent interactive method the step of.
As shown from the above technical solution, the intelligent identification Method of traditional culture gesture provided by the present application, intelligent interaction side Method and relevant apparatus, acquisition are located at the video image of the active user in target pickup area, and based in the video image The location information of user establishes coordinate system corresponding with active user;The people of corresponding active user is identified according to the coordinate system Body bone key point coordinate;Using the skeleton key point coordinate of active user, pre-set each traditional culture is determined The value of gesture feature, and judge whether the value of each traditional culture gesture feature is all satisfied corresponding default item Part comprehensively utilizes the various dimensions feature of innovation to traditional text if so, determining that active user makes corresponding traditional culture gesture Change the three-dimensional intelligent recognition of gesture interaction behavior, live automatic identification, and identification process can be carried out to traditional culture gesture Intelligence degree it is high, high-efficient, and the accuracy and reliability of the recognition result of traditional culture gesture can be effectively improved, i.e., Significantly improve the accuracy and efficiency of traditional culture gesture interaction Activity recognition;And then it can effectively improve according to the identification As a result the accuracy and intelligence degree interacted with the user for making traditional culture gesture, and tradition can be effectively improved Ceremony sense and convenience in cultural gesture human-computer interaction terminal equipment use process, enhance the text for making traditional culture gesture Change sense of ownership and immersion experience.
Detailed description of the invention
In order to illustrate the technical solutions in the embodiments of the present application or in the prior art more clearly, to embodiment or will show below There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is the application Some embodiments for those of ordinary skill in the art without creative efforts, can also basis These attached drawings obtain other attached drawings.
Fig. 1 is the intelligent recognition of the traditional culture gesture of the application and the structural schematic diagram of interactive system.
Fig. 2 is the flow diagram of the intelligent identification Method of the traditional culture gesture of the application.
Fig. 3 is the mark schematic diagram of the skeleton key point coordinate in the embodiment of the present application.
Fig. 4 is the flow diagram of step 300 in the intelligent identification Method of the traditional culture gesture in the embodiment of the present application.
Fig. 5 is the structural schematic diagram of the intelligent identification device of the traditional culture gesture in the embodiment of the present application.
Fig. 6 is the flow diagram of the intelligent interactive method of the traditional culture gesture in the embodiment of the present application.
Fig. 7 is the structural schematic diagram of the intelligent interaction device of the traditional culture gesture in the embodiment of the present application.
Fig. 8 is the intelligent recognition of the traditional culture gesture in the application application example and the structural schematic diagram of interactive device.
Fig. 9 is the intelligent recognition of the traditional culture gesture in the application application example and/or the process signal of exchange method Figure.
Figure 10 is the structural schematic diagram of the electronic equipment in the embodiment of the present application.
Specific embodiment
To keep the purposes, technical schemes and advantages of the embodiment of the present application clearer, below in conjunction with the embodiment of the present application In attached drawing, technical solutions in the embodiments of the present application carries out clear, complete description, it is clear that described embodiment is Some embodiments of the present application, instead of all the embodiments.Based on the embodiment in the application, those of ordinary skill in the art Every other embodiment obtained without creative efforts, shall fall in the protection scope of this application.
In view of existing gesture interaction mode focus on mostly how using computer network carry out internet of things networking and Remote seamless interconnection technique carries out data interaction, and the skeleton critical point detection being directed to also focuses on mostly and how to know The problem of not and extracting key point information and geometric coordinate point feature, be not particularly suited for the on-site identification of traditional culture gesture, A kind of device and system carrying out Buddhism interaction using remote networking are also provided in existing gesture interaction mode, that is, are passed through After, server and terminal device, the long-range Buddhism interaction of the carry out that can not be constrained by time and location, however, the program is still not It is applicable in the live automatic identification of traditional culture gesture, and asking for the intelligent human-machine interaction that the application is able to solve can not be solved Topic.And in a kind of mode of the existing face characteristic for extracting face coordinate system, eyes aspect ratio can be extracted to carry out people The relevant Activity recognition of face can also recognize the behavioural characteristic of blink by the physiological characteristic of detection blink;This kind of mode A kind of technical solution that Activity recognition is carried out by excavating face coordinate points information is provided, however, for spy in this kind of mode The excavation of sign point is only limitted to single aspect ratio concept, there is a problem of differentiating that inaccuracy and index are excessively single.And it compares Not only it is specially adapted for traditional culture gesture in the intelligent identification Method of the program, traditional culture gesture provided herein Identification, also on the basis of the feature mining of aspect ratio, while also excavating human space vector sum directional information, and Devise the joint various dimensions intelligent distinguishing of total up to six characteristic points such as Partial key characteristic point angle and inner product.
Based on this, the application provides a kind of intelligent identification Method of traditional culture gesture, the intelligence of traditional culture gesture is known Other device, electronic equipment and computer readable storage medium, by the view for acquiring the active user being located in target pickup area Frequency image, and coordinate system corresponding with active user is established based on the location information of the user in the video image;According to described Coordinate system identifies the skeleton key point coordinate of corresponding active user;It is sat using the skeleton key point of active user Mark, determines the value of pre-set each traditional culture gesture feature, and judge each traditional culture gesture feature Whether value is all satisfied corresponding preset condition, if so, determine that active user makes corresponding traditional culture gesture, it is comprehensive The intelligent recognition three-dimensional to traditional culture gesture interaction behavior using the various dimensions feature of innovation is closed, it can be to traditional culture hand Gesture carries out live automatic identification, and the intelligence degree of identification process is high, high-efficient, and can effectively improve traditional culture gesture Recognition result accuracy and reliability, i.e., significantly improve the accuracy and effect of traditional culture gesture interaction Activity recognition Rate;And then can effectively improve according to the recognition result with make the accuracy and intelligence that the user of traditional culture gesture interacts Degree can be changed, and ceremony sense in traditional culture gesture human-computer interaction terminal equipment use process and convenient can be effectively improved Property, enhance the cultural sense of ownership for making traditional culture gesture and immersion experience.
In one or more embodiments of the application, inner product of vectors (Dot Product) is two on in-real R Vector and the binary operation for returning to a real number value scalar.It is the standard inner product of Euclidean space.Two vector a=[a1, A2 ..., an] and b=[b1, b2 ..., bn] definition of inner product are as follows:
DotProduct (a, b)=a1b1+a2b2+ ...+anbn.
For above content, the embodiment of the present application provide a kind of intelligent recognition for realizing traditional culture gesture and/or The intelligent recognition and interactive system of the traditional culture gesture of exchange method, the intelligent recognition and interactive system of the traditional culture gesture In include at least one traditional culture gesture intelligent identification device and at least one traditional culture gesture intelligent interaction fill It sets, the intelligent identification device of the traditional culture gesture and the intelligent interaction device of traditional culture gesture a kind of all can be service Device, the intelligent identification device of the traditional culture gesture are specifically as follows first server 01 and the traditional culture gesture Intelligent interaction device be specifically as follows second server 07 to distinguish, referring to Fig. 1, the first server 01 respectively with Be arranged at least one video image acquisition equipment 02, second server 07 and client device 05 in same target area it Between communicate to connect, the second server 07 can respectively at least one multimedia equipment 03, at least a set of lighting system 04 It is communicated to connect between at least one debt donations case 06.It is understood that the first server 01 and second clothes It is engaged in the setting independent of one another that device 07 can be as shown in Figure 1, also can integrate two functional modules being set as with a server.
Based on above content, the first server 01 can be online since obtaining client device 02 to traditional culture Gesture carries out the instruction of intelligent recognition, and after receiving the instruction, controls the video image acquisition equipment 02 to itself Target pickup area in the video image of user carry out continuous acquisition, the first server 01 receives the video image The video image for the active user being located in target pickup area that equipment 02 acquires is acquired, and based on the use in the video image The location information at family establishes coordinate system corresponding with active user;Then identify corresponding active user's according to the coordinate system Skeleton key point coordinate;And the skeleton key point coordinate of application active user, determine pre-set each biography The value of the cultural gesture feature of system, and it is corresponding to judge whether the value of each traditional culture gesture feature is all satisfied Preset condition, if so, determining that active user makes corresponding traditional culture gesture, then, the server 01 can should Recognition result is sent to client device 05 and second server 07, and second server 07 can be according to the identification knot received Fruit sends corresponding control instruction to the multimedia equipment 03, lighting system 04 and debt donations case 06 respectively, so that more matchmakers Body equipment 03 plays pre-stored video content or music content according to the control instruction;The lighting system 04 is according to the unlatching The lamp of instruction control corresponding region is lighted or is flashed, and the warning light on the debt donations case 06 is opened or loudspeaker thereon Issue prompt tone etc..
And on the basis of the above, the scene of frequent false triggering in order to prevent occurs, in one kind provided by the present application In the intelligent interactive method of traditional culture gesture, tradition of the above-mentioned server in one or more embodiments of application the application After the intelligent identification Method of cultural gesture determines that active user makes corresponding traditional culture gesture, also need to continue to judge the use Family makes whether the number of the traditional culture gesture is more than preset value within the preset identification period, if so, triggering is preset Alternative events corresponding with the traditional culture gesture, otherwise, by the tradition text in one or more embodiments of application the application The scene that the active user that the intelligent identification Method of change gesture determines makes corresponding traditional culture gesture is judged to frequently accidentally touching The scene of hair, and triggering processing is not carried out to alternative events.
It is understood that the client device may include smart phone, Flat electronic equipment, network machine top box, Portable computer, desktop computer, personal digital assistant (PDA), mobile unit, intelligent wearable device etc..Wherein, the intelligence Wearable device may include smart glasses, smart watches, Intelligent bracelet etc..
In practical applications, the part of the intelligent recognition of traditional culture gesture and/or interaction can be in such as above content institute The server side stated executes, and operation that can also be all is all completed in the client device.It specifically can be according to the visitor The processing capacity of family end equipment and the limitation of user's usage scenario etc. select.The application is not construed as limiting this.If all Operation all completed in the client device, the client device can also include processor.
Above-mentioned client device can have communication module (i.e. communication unit), can be led to long-range server Letter connection, realizes and transmits with the data of the server.The server may include the server of task schedule center side, It also may include the server of halfpace in other implement scenes, such as have communication linkage with task schedule central server Third-party server platform server.The server may include single computer unit, also may include multiple The server cluster of server composition or the server architecture of distributed devices.
Any suitable network protocol can be used between the server and the client device to be communicated, including In the network protocol that the application submitting day is not yet developed.The network protocol for example may include ICP/IP protocol, UDP/IP Agreement, http protocol, HTTPS agreement etc..Certainly, the network protocol for example can also include using on above-mentioned agreement RPC agreement (Remote Procedure Call Protocol, remote procedure call protocol), REST agreement (Representational State Transfer, declarative state transfer protocol) etc..
In order to carry out automatic identification to traditional culture gesture, and the intelligence degree of identification process is high, high-efficient, and The accuracy and reliability that the recognition result of traditional culture gesture can be effectively improved, in a kind of traditional culture gesture of the application Intelligent identification Method embodiment in, referring to fig. 2, the intelligent identification Method of the traditional culture gesture specifically includes as follows Content:
Step 100: acquisition is located at the video image of the active user in target pickup area, and based in the video image The location information of user establish corresponding with active user coordinate system.
It is understood that the corresponding coordinate system of the user establish mode be it is preset, in a kind of citing, For the human body uprightly stood, the lower left corner of the corresponding video image of human body can be defined as coordinate origin, from coordinate origin Laterally to the right it is the positive direction of x-axis, is laterally to the left negative direction of the x-axis;From coordinate origin vertical direction be from top to bottom y-axis just Direction is from top to bottom the negative direction of y-axis.
Step 200: the skeleton key point coordinate of corresponding active user is identified according to the coordinate system.
Wherein, referring to Fig. 3, the mark of the skeleton key point is also pre-set.The skeleton is crucial Point detection is one of basic algorithm of computer vision, is all played in the research of other related fieldss of computer vision Basic effect, such as Activity recognition, personage's tracking, Gait Recognition related fields.This method, which can detecte in picture, to be owned The primary focus of human body includes the seat of the positions such as neck, shoulder, elbow, wrist, waist, knee and ankle and above-mentioned position in human body coordinate system Mark information.The open source software that comparative maturity can be used carries out the extraction of similar characteristics, for example, industry has maturation The cooperation of the open source softwares such as OpenPose carries out skeleton critical point detection, in the realization that github has its more mature.
Step 300: using the skeleton key point coordinate of active user, determining pre-set each traditional culture hand The value of gesture feature, and judge whether the value of each traditional culture gesture feature is all satisfied corresponding default item Part, if so, determining that active user makes corresponding traditional culture gesture.
In step 300, in order to accurate to further increase the identification of traditional culture gesture by the application of multidimensional characteristic Property and reliability, the traditional culture gesture feature can be specifically made of sextuple feature, be respectively as follows:
(1) the nose neck of human body away from and aspect ratio of the both shoulders away between;
Wherein, the nose neck away from and aspect ratio 2n2sr (Nose Neck two Shoulder of the both shoulders away between Ratio) are as follows:
F (i) described above is the ith feature of above-mentioned skeleton key feature, and each F point includes it in skeleton X and y coordinates value above coordinate system;
Dist function stand be two characteristic points Euclidean distance, the distance meter of ith and jth key feature points For calculation,
The 1st parameter i of the F (i, b) indicates the index of corresponding skeleton key point feature;
2nd parameter b expression is currently x coordinate or y-coordinate, and value is respectively x and y.
(2) wrist away from and aspect ratio of the elbow away between;
Wherein, the wrist away from and aspect ratio 2w2er (two wrist two elbow ratio) of the elbow away between Are as follows:
The angle between x-axis unit vector in (3) two wrist vectors and the coordinate system;
Wherein, the angle between the x-axis unit vector in described two wrist vectors and the coordinate system is a right left side X-axis unit vector in the angle feature of wrist vector sum x-axis unit vector e1, described two wrist vectors and the coordinate system A2wx (Angle of two Wrist and X-axis) is further described below:
Appoint and take two o'clock i and j, i be directed toward j vector we be known as vector (F (i), F (j)):
Vector (F (i), F (j))=(F (j, x)-F (i, x), F (j, y)-F (i, y))
Therefore, the vector v ector (F (m), F (n)) of two o'clock m and n, m direction n are as follows:
Vector (F (m), F (n))=(F (n, x)-F (m, x), F (n, y)-F (m, y));
The inner product operation for defining two vectors is dp (p, q)=dotProduct (p, q);
Inner product formula according to vector ij and vector mn is available:
dotProduct(vector(F(i),F(j)),vector(F(m),F(n)))
=cos (theta (ij, mn)) × dist (F (i)-F (j)) × dist (F (m), F (n))
=(F (j, x)-F (i, x)) × (F (n, x)-F (m, x))+(F (j, y)-F (i, y)) × (F (n, y)-F (m, y))
And then obtain the angle theta (ij, mn) of vector ij and mn are as follows:
So far vector angle elaboration finishes;
Defining x-axis unit vector simultaneously is e1=(0,1);
Y-axis unit vector is e2=(1,0);
Therefore it can further derive that a2wx (Angle of two Wrist and X-axis) is following result:
The angle between x-axis unit vector in (4) two elbow vectors and the coordinate system;
Wherein, the angle between the x-axis unit vector in described two elbow vectors and the coordinate system is a right left side X-axis unit vector in the angle feature of elbow vector sum x-axis unit vector e1, described two elbow vectors and the coordinate system Between angle a2wx (Angle of two Wrist and X-axis) are as follows:
A2ex defines similar with a2wx with the process derived, then this does not repeat.
(5) right hand elbow is to the inner product between the y-axis unit vector in the direction vector and the coordinate system of right finesse;
The right hand elbow is to the inner product between the y-axis unit vector in the direction vector and the coordinate system of right finesse Dprewy (dot product of Right Elbow Wrist and y-axis) are as follows:
Dprewy=dotProduct (vector (F (9), F (11)), e2).
(6) left hand elbow is to the inner product between the y-axis unit vector in the direction vector and the coordinate system of left finesse;
Wherein, the left hand elbow is between the y-axis unit vector in the direction vector and the coordinate system of left finesse Product dplewy (dot product of Left Elbow Wrist and y-axis) are as follows:
Dplewy=dotProduct (vector (F (10), F (12)), e2).
To sum up, for the embodiment of the present application after obtaining skeleton key point coordinate information, depth has excavated traditional culture The direction for the space vector that gesture interaction movement is presented and characteristic point position information, propose for traditional culture gesture interaction behavior Wrist away from elbow away from aspect ratio 2w2er (two wrist two elbow ratio), nose neck away from both shoulders away from aspect ratio Angle a2wx (the Angle of 2n2sr (Nose Neck two Shoulder Ratio), right left finesse vector sum x-axis unit vector Of two Wrist and X-axis), angle a2wx (the Angle of two of right left hand elbow vector sum x-axis unit vector Wrist and X-axis), inner product dprewy (the dot product of right hand elbow to right finesse direction vector and y-axis unit vector Of Right Elbow Wrist and y-axis), the inner product of left hand elbow to left finesse direction vector and y-axis unit vector Numerous six innovative traditional cultures such as dplewy (dot product of Left Elbow Wrist and y-axis) Gesture interaction Activity recognition characteristic index;The various dimensions feature of the above-mentioned innovation referred to is comprehensively utilized to traditional culture gesture interaction The three-dimensional intelligent recognition of behavior significantly improves the accuracy and efficiency problem of traditional culture gesture interaction Activity recognition; By using the method, the instrument in the intelligence traditional culture gesture human-computer interaction terminal equipment use process such as electronics donation box is improved Formula sense and convenience have enhanced the sense of ownership and immersion experience of tourist and believers.
In order to further increase the accuracy for determining whether user makes traditional culture gesture, in the traditional culture of the application In one embodiment of the intelligent identification Method of gesture, referring to fig. 4, in addition to step 301 in the step 300: application is current to be used The skeleton key point coordinate at family determines the value of pre-set each traditional culture gesture feature, judgement thereafter Journey specifically includes the following content for executing or being executed side by side with random order:
Step 302: judge the nose neck away from and aspect ratio of the both shoulders away between whether be less than or equal to preset nose neck away from With both shoulders away from the ratio between decision threshold, to determine whether active user makes the movement bowed.
Step 303: judge the wrist away from and aspect ratio of the elbow away between whether be less than or equal to preset both hands wrist and The decision threshold of the ratio of distances constant of both hands elbow, to determine whether active user makes that both hands close up and that elbow separates outward is dynamic Make.
Step 304: judging whether is angle between the x-axis unit vector in described two wrist vectors and the coordinate system Less than or equal to preset both hands wrist and horizontal line angle threshold value, and, judge described two elbow vectors and the coordinate system In x-axis unit vector between angle whether be less than or equal to preset both hands elbow and horizontal line angle threshold value, with determination work as Whether preceding user makes the movement embracing fist and saluting that horizontal symmetry is presented in both hands orientation.
Step 305: judge the right hand elbow to the y-axis unit vector in the direction vector and the coordinate system of right finesse it Between inner product whether be greater than 0, and, judge the left hand elbow to the y-axis list in the direction vector and the coordinate system of left finesse Whether the inner product between bit vector is greater than 0, to determine it is corresponding higher than elbow position dynamic whether active user makes wrist location Make.
It is corresponding, it also include step 306 after the step 305: if know active user through judgement while making Horizontal symmetrical is presented in the movement bowed, the movement that the both hands close up and elbow separates outward, the both hands orientation Property embrace the movement saluted of fist and the wrist location is higher than the corresponding movement in elbow position, it is determined that active user or Person has made traditional culture gesture.
For software view, in order to carry out automatic identification, and the intelligence of identification process to traditional culture gesture Degree is high, high-efficient, and can effectively improve the accuracy and reliability of the recognition result of traditional culture gesture, and the application provides A kind of traditional culture gesture of all or part of the content in the intelligent identification Method for realizing the traditional culture gesture The embodiment of intelligent identification device, referring to Fig. 5, the intelligent identification device of the traditional culture gesture specifically includes in following Hold:
Video data acquiring module 003, for acquiring the video image for the active user being located in target pickup area, and Location information based on the user in the video image establishes coordinate system corresponding with active user.
Skeleton key point identification module 004, for identifying the human body of corresponding active user according to the coordinate system Bone key point coordinate.
Traditional culture gesture interaction Activity recognition module 005, for applying the skeleton key point coordinate of active user, It determines the value of pre-set each traditional culture gesture feature, and judges the value of each traditional culture gesture feature Whether corresponding preset condition is all satisfied, if so, determining that active user makes corresponding traditional culture gesture.
The embodiment of the intelligent identification device of traditional culture gesture provided by the embodiments of the present application specifically can be used for executing The process flow of the embodiment of the intelligent identification Method of traditional culture gesture in above-described embodiment, function are no longer superfluous herein It states, is referred to the detailed description of the intelligent identification Method embodiment of above-mentioned traditional culture gesture.
As can be seen from the above description, the intelligent identification device of traditional culture gesture provided by the embodiments of the present application, comprehensive utilization The various dimensions feature of the innovation intelligent recognition three-dimensional to traditional culture gesture interaction behavior, can carry out traditional culture gesture Live automatic identification, and the intelligence degree of identification process is high, high-efficient, and can effectively improve the identification of traditional culture gesture As a result accuracy and reliability significantly improves the accuracy and efficiency of traditional culture gesture interaction Activity recognition;Into And can effectively improve according to the recognition result with make the accuracy and intelligence that the user of traditional culture gesture interacts Degree, and ceremony sense and convenience in traditional culture gesture human-computer interaction terminal equipment use process can be effectively improved, Enhance the cultural sense of ownership for making traditional culture gesture and immersion experience.
In order to carry out automatic identification and interaction, and identification and the interactive intelligent journey with regard to process to traditional culture gesture Degree is high, high-efficient, and can effectively improve the identification of traditional culture gesture and the accuracy and reliability of interaction results, Jin Erneng Enough effectively improve according to the recognition result with make the accuracy and intelligence degree that the user of traditional culture gesture interacts, In a kind of embodiment of the intelligent interactive method of traditional culture gesture of the application, referring to Fig. 6, the traditional culture gesture Intelligent interactive method executes after the intelligent identification Method of the traditional culture gesture, specifically includes following content:
Step 400: if determining that active user makes corresponding biography using the intelligent identification Method of the traditional culture gesture Culture of uniting gesture, then judge that the user makes whether the number of the traditional culture gesture is more than default within the preset identification period Value, if so, thening follow the steps 500.
Step 500: the preset alternative events corresponding with the traditional culture gesture of triggering.
In order to further increase according to the recognition result with make the accuracy that the user of traditional culture gesture interacts And intelligence degree, in one embodiment of the intelligent interactive method of the traditional culture gesture of the application, the traditional culture It specifically include at least one in following step 501 and step 502 in the step 500 of the intelligent interactive method of gesture.
Wherein, step 501: play instruction is sent to corresponding multimedia equipment, so that the multimedia equipment is according to this Play instruction plays pre-stored video content or music content.
Step 502: open command is sent to corresponding lighting system, so that the lighting system is according to the open command control The lamp of corresponding region processed is lighted or is flashed.
For software view, in order to carry out automatic identification and interaction, and identification and interaction to traditional culture gesture It is high, high-efficient with regard to the intelligence degree of process, and can effectively improve traditional culture gesture identification and interaction results it is accurate Property and reliability, the application provide all or part in a kind of intelligent interactive method for realizing the traditional culture gesture The embodiment of the intelligent interaction device of the traditional culture gesture of content, referring to Fig. 7, the intelligent interaction of the traditional culture gesture is filled Setting specifically includes following content:
Traditional culture gesture interaction event trigger module 006, if for knowing using the intelligence of the traditional culture gesture Other method determines that active user makes corresponding traditional culture gesture, then judges that the user makes this within the preset identification period Whether the number of traditional culture gesture is more than preset value, if so, the preset interaction corresponding with the traditional culture gesture of triggering Event.
In order to further illustrate this programme, the application also provides a kind of intelligent recognition dress using above-mentioned traditional culture gesture It sets and the intelligent interaction device of traditional culture gesture realizes the intelligent identification Method and traditional culture of corresponding traditional culture gesture The specific application example of the intelligent interactive method of gesture, by account in full donations case be electronics donation box for and target therein Pickup area is the places such as vihara, and referring to Fig. 8, the intelligent recognition and interactive device of traditional culture gesture specifically include: For carrying the electronics donation box core background service module 001 of basic service, wifi, network communication and backstage interaction, being used for Set head and shoulder it is wide than threshold value and palm elbow away from than threshold value etc. parameter setting module 002, for acquiring face and human body attitude Image data video data acquiring module 003, for extract skeleton key point information skeleton key point know Other module 004, traditional culture gesture interaction Activity recognition module 005 and traditional culture gesture interaction event trigger module 006.
The intelligent recognition and exchange method of the traditional culture gesture specifically include following content:
(1) administrator opens electronics donation box core background service module 001, for being responsible for processing electronics donation box industry The relevant kernel service of logic of being engaged in;It is responsible for other each submodule initialization blocks simultaneously.
(2) parameter setting module 002, comprising completing the relevant parameter of entire intelligent interaction identification core function, including biography Skeleton key point and the relevant parameter of detection in cultural 005 Activity recognition module of gesture interaction Activity recognition module of uniting, It specifically includes:
Th_2n2sr be nose neck away from both shoulders away from the ratio between decision threshold;
Th_2w2er is the decision threshold of the ratio of distances constant of both hands wrist and both hands elbow;
Th_a2wx is both hands wrist and horizontal line angle threshold value;
Th_a2ex both hands elbow and horizontal line angle threshold value;
The periodic traditional culture gesture time decision of T_loop;
Activation threshold value etc. of the th_bow traditional culture gesture within the T_loop period.
Combination algorithm principle carries out the specific physical meaning of the parameter one by one for rear extended meeting in subsequent corresponding process It introduces, does not repeat herein.
(3) video data acquiring module 003 shows traditional culture gesture motion, camera for user before camera Data acquisition is carried out, the image data of face and human body attitude is acquired.
(4) skeleton key point identification module 004, for obtaining the view provided from video data acquiring module 003 Frequency evidence carries out skeleton critical point detection.
The skeleton critical point detection is one of basic algorithm of computer vision, in other of computer vision Basic effect, such as Activity recognition, personage's tracking, Gait Recognition related fields are all played in the research of related fields. This method can detecte the primary focus that owner in picture mentions, comprising positions such as neck, shoulder, elbow, wrist, waist, knee, ankles, and Coordinate information of the above-mentioned position in human body coordinate system.The open source software that comparative maturity can be used carries out the extraction of similar characteristics, example Such as, there is the cooperation of the open source softwares such as mature OpenPose in industry, carries out skeleton critical point detection, has it in github More mature realization;
Skeleton critical point detection therein has the new technology and profession much to emerge one after another in industry and academia Paper, the precision and accuracy rate of continuous refresh feature point Detection and Extraction, this application example is using OpenPose as people in the application Face characteristic point extracts the main method realized, it can detecte 15,18 or 25 key features of face with extraction module.
The human body uprightly stood, lower-left are defined for the coordinate information of the human body coordinate system for subsequent unified calculation Angle is coordinate origin, is laterally to the right the positive direction of x-axis, is laterally to the left negative direction of the x-axis;Vertical direction is y-axis from top to bottom Positive direction, be from top to bottom the negative direction of y-axis.
Traditional culture gesture interaction Activity recognition module 005 obtains the people from skeleton key point identification module 004 Body bone key point coordinate information carries out traditional culture gesture interaction Activity recognition;
For example aforementioned six character of innovation of the traditional culture gesture interaction behavior, i.e. the nose neck of human body away from and both shoulders Aspect ratio 2n2sr, wrist away between away from and aspect ratio 2w2er, two wrist vectors and the coordinate system of the elbow away between In x-axis unit vector between angle a2wx, the folder between the x-axis unit vector in two elbow vectors and the coordinate system Angle a2wx, right hand elbow to right finesse direction vector and the coordinate system in y-axis unit vector between inner product dprewy with And left hand elbow is to the inner product dplewy between the y-axis unit vector in the direction vector and the coordinate system of left finesse.
Described six features of traditional culture gesture interaction behavior, when executing above-mentioned movement, there are following significant changes:
2n2sr, 2w2er numerical value can become smaller, a2wx, and a2ex can be in zero crossings;Dprewy and dplewy is greater than 0.
The reason of 2n2sr becomes smaller be, bows there are when traditional culture gesture interaction gesture, head can exist Movement causes image nose and neck distance obviously to become smaller, but both shoulders are away from remaining unchanged.
The reason of 2w2er becomes smaller is that, there are when traditional culture gesture interaction gesture, both hands close up, both hands The distance of wrist is very close to while elbow separates outward, and both hands wrist and the ratio of distances constant of both hands elbow is caused obviously to become smaller.
The a2wx, a2ex can be in the reason of zero crossings, due to upright symmetry, embrace fist there is no one hand and salute Scene, both hands orientation present horizontal symmetry, so with horizontal sextant angle very little.
The reason of dprewy and dplewy is greater than 0 is, there are when traditional culture gesture interaction gesture, wrist The ordinate at place can be greater than the ordinate where elbow, cause elbow wrist vector sum e2 vector angle absolute less than 90 degree Value, and then inner product is caused to be greater than 0.
Therefore when there are traditional culture gesture interaction gesture, the application design is if lower threshold value is to above-mentioned significant change feature It extracts and determines with various dimensions:
Th_2n2sr be nose neck away from both shoulders away from the ratio between decision threshold;
Th_2w2er is the decision threshold of the ratio of distances constant of both hands wrist and both hands elbow;
Th_a2wx is both hands wrist and horizontal line angle threshold value;
Th_a2ex both hands elbow and horizontal line angle threshold value.
Therefore, the traditional culture gesture interaction behavior meets following decision condition simultaneously:
2n2sr≤th_2n2sr
2w2er≤th_2w2er
abs(a2wx)≤th_a2wx
a2ex≤th_a2ex
dprewy>0
dplewy>0
For a traditional culture gesture interaction gestures detection success events, it is defined as event_bow_once.
Above-mentioned abs () function representation takes absolute value to data.
Preferably, above-mentioned there are the scene of frequent false triggering in order to prevent, event_bow_once do not represent once at The final detection result of the traditional culture gesture behavior of function.
The traditional culture gesture time decision of our delimiting periods is T_loop.
Within the T_loop period, the number for triggering event_bow_once is defined as cnt_event_bow.
Within the T_loop period, it is to successfully trigger a traditional culture hand that cnt_event_bow, which is more than or equal to th_bow, Gesture interbehavior event_bow.
The th_bow is activation threshold value of the traditional culture gesture within the T_loop period.
(5) traditional culture gesture interaction Activity recognition module 005 is when event_bow finally meets and triggers, meeting Call traditional culture gesture interaction event trigger module 006.
(6) traditional culture gesture interaction event trigger module 006 executes the intelligent recognition successor of traditional culture gesture Including but not limited to, for the tourist or heart believers for being directed toward above-mentioned traditional culture gesture interaction, electronic curtain culture Jie is carried out It continues, contributes channel and open and prompt, show the figure of buddha enshrined and worship and scripture information, play Buddhism background music, show distinctive ancestor Teach the figure of buddha or Bodhisattva interactive multimedia information etc..
In a kind of concrete example, the electronics donation box terminal of certain bank is used with tourist and believers, in electronics donation box For carrying out traditional culture gesture before camera, referring to Fig. 9, it is specifically described the interaction flow of above-mentioned specific application example:
1. administrator opens electronics donation box core background service module 001;The electronics donation box core background service Module is responsible for the relevant kernel service of processing electronics donation box service logic;At the beginning of being responsible for each submodule of other S002-S007 simultaneously Beginningization;
2. submodule initialization package containing parameter setup module 002 described in identifies core comprising completing entire intelligent interaction The relevant parameter of function, including the skeleton key point and detection phase in traditional culture gesture interaction Activity recognition module 005 The parameter of pass, specifically includes:
Th_2n2sr be nose neck away from both shoulders away from the ratio between decision threshold, the application be arranged th_2n2sr=0.15;
Th_2w2er is the decision threshold of the ratio of distances constant of both hands wrist and both hands elbow, and th_2w2er=0.1 is arranged in the application;
Th_a2wx is both hands wrist and horizontal line angle threshold value, and π/9 th_a2wx=are arranged in the application;
Th_a2ex both hands elbow and horizontal line angle threshold value;π/9 th_a2ew=are arranged in the application;
The periodic traditional culture gesture time decision of T_loop;T_loop=10s is arranged in the application;
Th_bow=2 is arranged in activation threshold value of the th_bow traditional culture gesture within the T_loop period, the application;
3. tourist carries out continuous traditional culture gesture motion before electronics donation box camera;Video data acquiring module Camera in 003 carries out data acquisition to this tourist, acquires the image data of face and human body attitude;
4. skeleton key point identification module 004 obtains the video data provided from video data acquiring module 003, Carry out skeleton critical point detection;
5. traditional culture gesture interaction Activity recognition module 005 is obtained from skeleton key point identification module 004 Skeleton key point coordinate information carries out traditional culture gesture interaction Activity recognition.
6. traditional culture gesture interaction Activity recognition module 005 finally meets cnt_event_bow in event_bow and is greater than When equal to th_bow, traditional culture gesture interaction event trigger module 006 can be called;It is assumed herein that user connects in 10s Continuous traditional culture gesture 3 times, and by system detection, it triggers event_bow_once three times, successfully triggers event_bow event.
7. the intelligent recognition successor packet of the execution traditional culture gesture of traditional culture gesture interaction event trigger module 006 It includes but is not limited to, for the tourist or heart believers for being directed toward above-mentioned traditional culture gesture interaction, carry out electronic curtain culture introduction, It contributes channel to open and prompt, shows the figure of buddha enshrined and worship and scripture information, play Buddhism background music, show distinctive religion Buddhist Picture or Bodhisattva interactive multimedia information etc.;
By taking Internet of Things wisdom place lighting system and interaction of multimedia information as an example, tells about S006 and make a slight bow event trigger module Actual efficacy.
S006 event trigger module of making a slight bow is receiving the event_ from traditional culture gesture interaction Activity recognition module 005 Bow event;
The multimedia play software that the event can trigger the network connection of electronics donation box executes music operation, simultaneously meeting So that the lamp system that Current electronic donation box region is connected by Internet of Things is flashed or is lighted;
Above-mentioned music operation, is used to generate random number, the model of random number comprising a random number randNum generator Enclose 1≤randNum of satisfaction≤musicMax;
MusicMax is the number of the Buddhism background music of designated storage location in database or file system;Because broadcasting Putting device can be according to random number, the randNum head background music of broadcasting memory system;
Above-mentioned lamp system flashing or lighting operation, include multiple electronics donation box equipment, and each electronics donation box leads to Cross the lighting system of Internet of Things configuration region;When the electronics donation box of tourist or believers in the A of region triggers event_ The Internet of Things lamp system execution of bow event, then region A agreement jurisdiction is lighted or flashing operation;
So far, by Internet of Things wisdom place lighting system and interaction of multimedia information, so that behavior and the place of people Wisdom perception reaches intelligent linkage, enhances the audiovisual entertainment interest of tourist, while also enhancing the presence of believers, ginseng With sense, sense of ownership, the convenience of human-computer interaction is improved.
In addition, about the human body key point recognizer component mentioned in the application, the method for mainstream is pointed out in the application The method of this neural network deep learning removes the line for extracting image certainly based on traditional computer vision Feature Engineering It manages feature and local message carries out the identification of human body key point and a kind of optinal plan, but the latter is due to traditional characteristic limitation And performance is bad, has no longer been gradually the main method of the human body key point identification of mainstream.
For hardware view, in order to carry out automatic identification, and the intelligence of identification process to traditional culture gesture Degree is high, high-efficient, and can effectively improve the accuracy and reliability of the recognition result of traditional culture gesture, and then can have Effect improve according to the recognition result with make the accuracy and intelligence degree that the user of traditional culture gesture interacts, this Shen The intelligent interaction side of a kind of intelligent identification Method for realizing the traditional culture gesture and/or traditional culture gesture please be provided The embodiment of the electronic equipment of all or part of the content in method, the electronic equipment specifically includes following content:
Processor (processor), memory (memory), communication interface (Communications Interface) and Bus;Wherein, the processor, memory, communication interface complete mutual communication by the bus;The communication interface It is set for realizing the intelligent identification device of traditional culture gesture, the intelligent interaction device of traditional culture gesture, video image acquisition Information transmission between the relevant devices such as standby, multimedia equipment, debt donations case, lighting system and user terminal;The electronics Equipment can be desktop computer, tablet computer and mobile terminal etc., and the present embodiment is without being limited thereto.In the present embodiment, the electricity Sub- equipment is referred to the intelligent recognition of embodiment traditional culture gesture and/or the embodiment of exchange method, and, traditional culture The intelligent recognition of gesture and/or the embodiment of interactive device are implemented, and content is incorporated in this, and it is no longer superfluous to repeat place It states.
Figure 10 is the schematic block diagram that the system of the electronic equipment 9600 of the embodiment of the present application is constituted.As shown in Figure 10, the electricity Sub- equipment 9600 may include central processing unit 9100 and memory 9140;Memory 9140 is coupled to central processing unit 9100. It is worth noting that, the Figure 10 is exemplary;Other kinds of structure can also be used, to supplement or replace the structure, with Realize telecommunications functions or other function.
In one embodiment, the intelligent recognition and/or interactive function of traditional culture gesture can be integrated into central processing unit In 9100.Wherein, it is control as follows to can be configured as progress for central processing unit 9100:
Step 100: acquisition is located at the video image of the active user in target pickup area, and based in the video image The location information of user establish corresponding with active user coordinate system.
Step 200: the skeleton key point coordinate of corresponding active user is identified according to the coordinate system.
Step 300: using the skeleton key point coordinate of active user, determining pre-set each traditional culture hand The value of gesture feature, and judge whether the value of each traditional culture gesture feature is all satisfied corresponding default item Part, if so, determining that active user makes corresponding traditional culture gesture.
Step 400: if determining that active user makes corresponding biography using the intelligent identification Method of the traditional culture gesture Culture of uniting gesture, then judge that the user makes whether the number of the traditional culture gesture is more than default within the preset identification period Value, if so, thening follow the steps 500.
Step 500: the preset alternative events corresponding with the traditional culture gesture of triggering.
As can be seen from the above description, the electronic equipment that embodiments herein provides, comprehensively utilizes the various dimensions feature of innovation The intelligent recognition three-dimensional to traditional culture gesture interaction behavior can carry out live automatic identification to traditional culture gesture, and The intelligence degree of identification process is high, high-efficient, and can effectively improve the recognition result of traditional culture gesture accuracy and Reliability significantly improves the accuracy and efficiency of traditional culture gesture interaction Activity recognition;And then it can effectively improve According to the recognition result with make the accuracy and intelligence degree that the user of traditional culture gesture interacts, and can have Effect improves the ceremony sense and convenience in traditional culture gesture human-computer interaction terminal equipment use process, enhances and makes traditional text Change the cultural sense of ownership and immersion experience of gesture.
In another embodiment, the intelligent recognition of traditional culture gesture and/or interactive device can be with central processings 9100 separate configuration of device, such as can configure the intelligent recognition of traditional culture gesture and/or interaction to and central processing unit The chip of 9100 connections, the intelligent recognition and/or interactive function of traditional culture gesture are realized by the control of central processing unit.
As shown in Figure 10, which can also include: communication module 9110, input unit 9120, at audio Manage device 9130, display 9160, power supply 9170.It is worth noting that, electronic equipment 9600 is also not necessary to include Figure 10 Shown in all components;In addition, electronic equipment 9600 can also include the component being not shown in Figure 10, can refer to existing Technology.
As shown in Figure 10, central processing unit 9100 is otherwise referred to as controller or operational controls, may include microprocessor Or other processor devices and/or logic device, the central processing unit 9100 receive each of input and controlling electronic devices 9600 The operation of a component.
Wherein, memory 9140, such as can be buffer, flash memory, hard disk driver, removable medium, volatile memory, non- One of volatile memory or other appropriate devices or more.Above-mentioned information related with failure can be stored, additionally The program executed for information about can be stored.And the program of the memory 9140 storage can be performed in central processing unit 9100, with Realize information storage or processing etc..
Input unit 9120 provides input to central processing unit 9100.The input unit 9120 is, for example, key or touches defeated Enter device.Power supply 9170 is used to provide electric power to electronic equipment 9600.Display 9160 is for carrying out the display such as image and text The display of object.The display may be, for example, LCD display, and but it is not limited to this.
The memory 9140 can be solid-state memory, for example, read-only memory (ROM), random access memory (RAM), SIM card etc..The memory that may also is that, saves information when power is off, can be selectively erased And more data are equipped with, the example of the memory is sometimes referred to as EPROM etc..Memory 9140 can also be some other type Device.Memory 9140 includes buffer storage 9141 (sometimes referred to as buffer).Memory 9140 may include using/ Function storage unit 9142, the applications/functions storage unit 9142 is for storing application program and function program or for passing through center Processor 9100 executes the process of the operation of electronic equipment 9600.
Memory 9140 can also include data store 9143, the data store 9143 for storing data, such as Contact person, numerical data, picture, sound and/or any other data used by electronic equipment.The driving journey of memory 9140 Sequence storage unit 9144 may include electronic equipment for communication function and/or other function for executing electronic equipment (such as Messaging application, address list application etc.) various drivers.
Communication module 9110 is the transmitter receiver 9110 sent and received signal via antenna 9111.Communicate mould Block (transmitter receiver) 9110 is coupled to central processing unit 9100, and to provide input signal and receive output signal, this can be with The case where with normal mobile communication terminal, is identical.
Based on the different communication technologys, in same electronic equipment, multiple communication modules 9110 can be set, such as honeycomb Network module, bluetooth module and/or Wireless LAN module etc..Communication module (transmitter receiver) 9110 is also via audio Processor 9130 is coupled to loudspeaker 9131 and microphone 9132, to provide audio output via loudspeaker 9131, and receives and From the audio input of microphone 9132, to realize common telecommunications functions.Audio processor 9130 may include any suitable Buffer, decoder, amplifier etc..In addition, audio processor 9130 is additionally coupled to central processing unit 9100, so that can Can record in the machine by microphone 9132, and allow to play the sound stored in the machine by loudspeaker 9131 Sound.
Embodiments herein also provides the traditional culture that can be realized that the executing subject in above-described embodiment is server A kind of computer readable storage medium of Overall Steps, described computer-readable in the intelligent recognition and/or exchange method of gesture Computer program is stored on storage medium, which realizes the execution master in above-described embodiment when being executed by processor Body is the intelligent recognition of the traditional culture gesture of server or client and/or the Overall Steps of exchange method, for example, the place Reason device realizes following step when executing the computer program:
Step 100: acquisition is located at the video image of the active user in target pickup area, and based in the video image The location information of user establish corresponding with active user coordinate system.
Step 200: the skeleton key point coordinate of corresponding active user is identified according to the coordinate system.
Step 300: using the skeleton key point coordinate of active user, determining pre-set each traditional culture hand The value of gesture feature, and judge whether the value of each traditional culture gesture feature is all satisfied corresponding default item Part, if so, determining that active user makes corresponding traditional culture gesture.
Step 400: if determining that active user makes corresponding biography using the intelligent identification Method of the traditional culture gesture Culture of uniting gesture, then judge that the user makes whether the number of the traditional culture gesture is more than default within the preset identification period Value, if so, thening follow the steps 500.
Step 500: the preset alternative events corresponding with the traditional culture gesture of triggering.
As can be seen from the above description, the computer readable storage medium that embodiments herein provides, comprehensively utilizes innovation The various dimensions feature intelligent recognition three-dimensional to traditional culture gesture interaction behavior can carry out scene to traditional culture gesture certainly Dynamic identification, and the intelligence degree of identification process is high, high-efficient, and the recognition result of traditional culture gesture can be effectively improved Accuracy and reliability significantly improves the accuracy and efficiency of traditional culture gesture interaction Activity recognition;And then it can Effectively improve according to the recognition result with make the accuracy and intelligence degree that the user of traditional culture gesture interacts, with And ceremony sense and convenience in traditional culture gesture human-computer interaction terminal equipment use process can be effectively improved, it enhances and does The cultural sense of ownership of traditional culture gesture and immersion experience out.
It should be understood by those skilled in the art that, the embodiment of the present invention can provide as method, apparatus or computer program Product.Therefore, complete hardware embodiment, complete software embodiment or reality combining software and hardware aspects can be used in the present invention Apply the form of example.Moreover, it wherein includes the computer of computer usable program code that the present invention, which can be used in one or more, The computer program implemented in usable storage medium (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.) produces The form of product.
The present invention be referring to according to the method for the embodiment of the present invention, the process of equipment (device) and computer program product Figure and/or block diagram describe.It should be understood that every one stream in flowchart and/or the block diagram can be realized by computer program instructions The combination of process and/or box in journey and/or box and flowchart and/or the block diagram.It can provide these computer programs Instruct the processor of general purpose computer, special purpose computer, Embedded Processor or other programmable data processing devices to produce A raw machine, so that being generated by the instruction that computer or the processor of other programmable data processing devices execute for real The device for the function of being specified in present one or more flows of the flowchart and/or one or more blocks of the block diagram.
These computer program instructions, which may also be stored in, is able to guide computer or other programmable data processing devices with spy Determine in the computer-readable memory that mode works, so that it includes referring to that instruction stored in the computer readable memory, which generates, Enable the manufacture of device, the command device realize in one box of one or more flows of the flowchart and/or block diagram or The function of being specified in multiple boxes.
These computer program instructions also can be loaded onto a computer or other programmable data processing device, so that counting Series of operation steps are executed on calculation machine or other programmable devices to generate computer implemented processing, thus in computer or The instruction executed on other programmable devices is provided for realizing in one or more flows of the flowchart and/or block diagram one The step of function of being specified in a box or multiple boxes.
Specific embodiment is applied in the present invention, and principle and implementation of the present invention are described, above embodiments Explanation be merely used to help understand method and its core concept of the invention;At the same time, for those skilled in the art, According to the thought of the present invention, there will be changes in the specific implementation manner and application range, in conclusion in this specification Appearance should not be construed as limiting the invention.

Claims (10)

1. a kind of intelligent identification Method of traditional culture gesture characterized by comprising
Acquisition is located at the video image of the active user in target pickup area, and the position based on the user in the video image Information establishes coordinate system corresponding with active user;
The skeleton key point coordinate of corresponding active user is identified according to the coordinate system;
Using the skeleton key point coordinate of active user, taking for pre-set each traditional culture gesture feature is determined Value, and judge whether the value of each traditional culture gesture feature is all satisfied corresponding preset condition, if so, really Determine active user and makes corresponding traditional culture gesture.
2. the intelligent identification Method of traditional culture gesture according to claim 1, which is characterized in that the traditional culture hand Gesture feature include: human body nose neck away from and aspect ratio of the both shoulders away between, wrist away from and aspect ratio of the elbow away between, two hands The angle between x-axis unit vector, two elbow vectors in wrist vector and the coordinate system and the x-axis list in the coordinate system Angle between bit vector, between the y-axis unit vector in the direction vector and the coordinate system of right hand elbow to right finesse in Product, and, the inner product between y-axis unit vector in the direction vector of left hand elbow to left finesse and the coordinate system.
3. the intelligent identification Method of traditional culture gesture according to claim 2, which is characterized in that each institute of judgement Whether the value for stating traditional culture gesture feature is all satisfied corresponding preset condition, comprising:
Judge the nose neck away from and aspect ratio of the both shoulders away between whether be less than or equal to preset nose neck away from both shoulders away from the ratio between Decision threshold, to determine whether active user makes the movement bowed;
Judge the wrist away from and aspect ratio of the elbow away between whether be less than or equal to the distance of preset both hands wrist and both hands elbow The ratio between decision threshold, to determine whether active user makes the movement that both hands close up and elbow separates outward;
It is pre- to judge whether the angle between the x-axis unit vector in described two wrist vectors and the coordinate system is less than or equal to If both hands wrist and horizontal line angle threshold value, and, judge x-axis unit in described two elbow vectors and the coordinate system to Whether the angle between amount is less than or equal to preset both hands elbow and horizontal line angle threshold value, to determine whether active user makes The movement of horizontal symmetry embracing fist and saluting is presented in both hands orientation;
Judge the right hand elbow to the inner product between the y-axis unit vector in the direction vector and the coordinate system of right finesse whether Greater than 0, and, judge the left hand elbow between the y-axis unit vector in the direction vector and the coordinate system of left finesse Whether inner product is greater than 0, to determine whether active user makes wrist location higher than the corresponding movement in elbow position.
4. the intelligent identification Method of traditional culture gesture according to claim 3, which is characterized in that described if so, really Determine active user or make traditional culture gesture, comprising:
If judged to know active user while being made that the movement bowed, the both hands close up and elbow separates outward Movement, the both hands orientation present horizontal symmetry embrace the movement saluted of fist and the wrist location is higher than elbow position Corresponding movement, it is determined that active user or has made traditional culture gesture.
5. a kind of intelligent interactive method of traditional culture gesture characterized by comprising
If the intelligent identification Method of the application such as described in any item traditional culture gestures of Claims 1-4 determines that active user does Corresponding traditional culture gesture out then judges that the user identifies that the number that the traditional culture gesture is made in the period is preset No is more than preset value, if so, the preset alternative events corresponding with the traditional culture gesture of triggering.
6. the intelligent interactive method of traditional culture gesture according to claim 5, which is characterized in that the triggering is preset Alternative events corresponding with the traditional culture gesture include:
Play instruction is sent to corresponding multimedia equipment, is pre-stored so that the multimedia equipment is played according to the play instruction Video content or music content;
And/or
Open command is sent to corresponding lighting system, so that the lighting system controls corresponding region according to the open command Lamp is lighted or is flashed.
7. a kind of intelligent identification device of traditional culture gesture characterized by comprising
Video data acquiring module, for acquiring the video image for the active user being located in target pickup area, and being based on should The location information of user in video image establishes coordinate system corresponding with active user;
Skeleton key point identification module, the skeleton for identifying corresponding active user according to the coordinate system are crucial Point coordinate;
Traditional culture gesture interaction Activity recognition module determines pre- for the skeleton key point coordinate of application active user The value for each traditional culture gesture feature being first arranged, and judge whether the value of each traditional culture gesture feature is equal Meet corresponding preset condition, if so, determining that active user makes corresponding traditional culture gesture.
8. a kind of intelligent interaction device of traditional culture gesture characterized by comprising
Traditional culture gesture interaction event trigger module, if for application such as the described in any item traditional cultures of Claims 1-4 The intelligent identification Method of gesture determines that active user makes corresponding traditional culture gesture, then judges the user in preset identification Whether the number that the traditional culture gesture is made in the period is more than preset value, if so, triggering the preset and traditional culture hand The corresponding alternative events of gesture.
9. a kind of electronic equipment including memory, processor and stores the calculating that can be run on a memory and on a processor Machine program, which is characterized in that the processor realizes Claims 1-4 described in any item tradition texts when executing described program The step of changing the intelligent identification Method of gesture, alternatively, realizing the intelligent interaction of traditional culture gesture described in claim 5 or 6 The step of method.
10. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the computer program quilt The step of intelligent identification Method of the described in any item traditional culture gestures of Claims 1-4 is realized when processor executes, or Person, the step of realizing the intelligent interactive method of traditional culture gesture described in claim 5 or 6.
CN201910665464.7A 2019-07-23 2019-07-23 Intelligent recognition method and intelligent interaction method for traditional culture gestures and related devices Active CN110443167B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910665464.7A CN110443167B (en) 2019-07-23 2019-07-23 Intelligent recognition method and intelligent interaction method for traditional culture gestures and related devices

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910665464.7A CN110443167B (en) 2019-07-23 2019-07-23 Intelligent recognition method and intelligent interaction method for traditional culture gestures and related devices

Publications (2)

Publication Number Publication Date
CN110443167A true CN110443167A (en) 2019-11-12
CN110443167B CN110443167B (en) 2022-05-17

Family

ID=68431227

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910665464.7A Active CN110443167B (en) 2019-07-23 2019-07-23 Intelligent recognition method and intelligent interaction method for traditional culture gestures and related devices

Country Status (1)

Country Link
CN (1) CN110443167B (en)

Cited By (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110955243A (en) * 2019-11-28 2020-04-03 新石器慧通(北京)科技有限公司 Travel control method, travel control device, travel control apparatus, readable storage medium, and mobile device
CN111626136A (en) * 2020-04-29 2020-09-04 惠州华阳通用电子有限公司 Gesture recognition method, system and equipment
CN112056873A (en) * 2020-09-29 2020-12-11 广州翼安科技有限公司 Display device for animation production
CN113494802A (en) * 2020-05-28 2021-10-12 海信集团有限公司 Intelligent refrigerator control method and intelligent refrigerator
CN113657226A (en) * 2021-08-06 2021-11-16 上海有个机器人有限公司 Customer interaction method, device, medium and mobile equipment
CN113807154A (en) * 2020-06-12 2021-12-17 神州共享(北京)文化传媒有限公司 Man-machine interaction system of digital exhibition hall
CN116328276A (en) * 2021-12-22 2023-06-27 成都拟合未来科技有限公司 Gesture interaction method, system, device and medium based on body building device
CN116360603A (en) * 2023-05-29 2023-06-30 中数元宇数字科技(上海)有限公司 Interaction method, device, medium and program product based on time sequence signal matching
CN117008733A (en) * 2023-09-21 2023-11-07 海马云(天津)信息技术有限公司 Gesture action correction method and device for virtual digital person

Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20140079297A1 (en) * 2012-09-17 2014-03-20 Saied Tadayon Application of Z-Webs and Z-factors to Analytics, Search Engine, Learning, Recognition, Natural Language, and Other Utilities
US20150103004A1 (en) * 2013-10-16 2015-04-16 Leap Motion, Inc. Velocity field interaction for free space gesture interface and control
CN106020440A (en) * 2016-05-05 2016-10-12 西安电子科技大学 Emotion interaction based Peking Opera teaching system
CN107102727A (en) * 2017-03-17 2017-08-29 武汉理工大学 Dynamic gesture study and recognition methods based on ELM neutral nets
CN107463887A (en) * 2017-07-20 2017-12-12 四川长虹电器股份有限公司 Train driver gesture intelligence inspection system and intelligent inspection method
CN207115327U (en) * 2017-01-23 2018-03-16 深圳市妙严科技有限公司 A kind of virtual family hall for worshipping Buddha system
WO2018151503A2 (en) * 2017-02-16 2018-08-23 (주)더블유알티랩 Method and apparatus for gesture recognition
CN109598198A (en) * 2018-10-31 2019-04-09 深圳市商汤科技有限公司 The method, apparatus of gesture moving direction, medium, program and equipment for identification
CN109919039A (en) * 2019-02-14 2019-06-21 上海磐启微电子有限公司 A kind of static gesture identification method based on palm and finger characteristic

Patent Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20140079297A1 (en) * 2012-09-17 2014-03-20 Saied Tadayon Application of Z-Webs and Z-factors to Analytics, Search Engine, Learning, Recognition, Natural Language, and Other Utilities
US20150103004A1 (en) * 2013-10-16 2015-04-16 Leap Motion, Inc. Velocity field interaction for free space gesture interface and control
CN106020440A (en) * 2016-05-05 2016-10-12 西安电子科技大学 Emotion interaction based Peking Opera teaching system
CN207115327U (en) * 2017-01-23 2018-03-16 深圳市妙严科技有限公司 A kind of virtual family hall for worshipping Buddha system
WO2018151503A2 (en) * 2017-02-16 2018-08-23 (주)더블유알티랩 Method and apparatus for gesture recognition
CN107102727A (en) * 2017-03-17 2017-08-29 武汉理工大学 Dynamic gesture study and recognition methods based on ELM neutral nets
CN107463887A (en) * 2017-07-20 2017-12-12 四川长虹电器股份有限公司 Train driver gesture intelligence inspection system and intelligent inspection method
CN109598198A (en) * 2018-10-31 2019-04-09 深圳市商汤科技有限公司 The method, apparatus of gesture moving direction, medium, program and equipment for identification
CN109919039A (en) * 2019-02-14 2019-06-21 上海磐启微电子有限公司 A kind of static gesture identification method based on palm and finger characteristic

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
MUNEEBA RAJA等: "WiBot! In-Vehicle Behaviour and Gesture Recognition Using Wireless Network Edge", 《2018 IEEE 38TH INTERNATIONAL CONFERENCE ON DISTRIBUTED COMPUTING SYSTEMS》 *
方华 等: "基于kinect骨骼***的手势识别研究", 《计算机光盘软件与应用》 *

Cited By (13)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110955243B (en) * 2019-11-28 2023-10-20 新石器慧通(北京)科技有限公司 Travel control method, apparatus, device, readable storage medium, and mobile apparatus
CN110955243A (en) * 2019-11-28 2020-04-03 新石器慧通(北京)科技有限公司 Travel control method, travel control device, travel control apparatus, readable storage medium, and mobile device
CN111626136B (en) * 2020-04-29 2023-08-18 惠州华阳通用电子有限公司 Gesture recognition method, system and equipment
CN111626136A (en) * 2020-04-29 2020-09-04 惠州华阳通用电子有限公司 Gesture recognition method, system and equipment
CN113494802A (en) * 2020-05-28 2021-10-12 海信集团有限公司 Intelligent refrigerator control method and intelligent refrigerator
CN113807154A (en) * 2020-06-12 2021-12-17 神州共享(北京)文化传媒有限公司 Man-machine interaction system of digital exhibition hall
CN112056873A (en) * 2020-09-29 2020-12-11 广州翼安科技有限公司 Display device for animation production
CN113657226A (en) * 2021-08-06 2021-11-16 上海有个机器人有限公司 Customer interaction method, device, medium and mobile equipment
CN113657226B (en) * 2021-08-06 2024-07-02 上海有个机器人有限公司 Customer interaction method, device, medium and mobile equipment
CN116328276A (en) * 2021-12-22 2023-06-27 成都拟合未来科技有限公司 Gesture interaction method, system, device and medium based on body building device
CN116360603A (en) * 2023-05-29 2023-06-30 中数元宇数字科技(上海)有限公司 Interaction method, device, medium and program product based on time sequence signal matching
CN117008733A (en) * 2023-09-21 2023-11-07 海马云(天津)信息技术有限公司 Gesture action correction method and device for virtual digital person
CN117008733B (en) * 2023-09-21 2023-12-12 海马云(天津)信息技术有限公司 Gesture action correction method and device for virtual digital person

Also Published As

Publication number Publication date
CN110443167B (en) 2022-05-17

Similar Documents

Publication Publication Date Title
CN110443167A (en) Intelligent identification Method, intelligent interactive method and the relevant apparatus of traditional culture gesture
CN105431813B (en) It is acted based on biometric identity home subscriber
CN112379812B (en) Simulation 3D digital human interaction method and device, electronic equipment and storage medium
CN105190484B (en) Personal holographic billboard
CN104777911B (en) A kind of intelligent interactive method based on holographic technique
CN104170318B (en) Use the communication of interaction incarnation
CN102789313B (en) User interaction system and method
CN105264460B (en) Hologram object is fed back
CN104049721B (en) Information processing method and electronic equipment
CN112070015B (en) Face recognition method, system, device and medium fusing occlusion scene
KR101945082B1 (en) Method for transmitting media contents, apparatus for transmitting media contents, method for receiving media contents, apparatus for receiving media contents
CN105931645A (en) Control method of virtual reality device, apparatus, virtual reality device and system
CN111669515B (en) Video generation method and related device
CN105374055A (en) Image processing method and device
CN109923524A (en) It is used using soft memory objective management memory
CN109508687A (en) Man-machine interaction control method, device, storage medium and smart machine
CN108525305A (en) Image processing method, device, storage medium and electronic equipment
KR101743763B1 (en) Method for providng smart learning education based on sensitivity avatar emoticon, and smart learning education device for the same
CN103544724A (en) System and method for realizing fictional cartoon character on mobile intelligent terminal by augmented reality and card recognition technology
CN105518579A (en) Information processing device and information processing method
CN110119700A (en) Virtual image control method, virtual image control device and electronic equipment
CN108519816A (en) Information processing method, device, storage medium and electronic equipment
KR20130027081A (en) Intuitive computing methods and systems
CN208969451U (en) A kind of intelligent home control system
CN108563327B (en) Augmented reality method, device, storage medium and electronic equipment

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
TR01 Transfer of patent right

Effective date of registration: 20220920

Address after: 25 Financial Street, Xicheng District, Beijing 100033

Patentee after: CHINA CONSTRUCTION BANK Corp.

Address before: 25 Financial Street, Xicheng District, Beijing 100033

Patentee before: CHINA CONSTRUCTION BANK Corp.

Patentee before: Jianxin Financial Science and Technology Co.,Ltd.

TR01 Transfer of patent right