CN110443167B - Intelligent recognition method and intelligent interaction method for traditional culture gestures and related devices - Google Patents

Abstract

The embodiment of the application provides an intelligent recognition method, an intelligent interaction method and a related device of traditional culture gestures, wherein the intelligent recognition method comprises the following steps: acquiring a video image of a current user in a target acquisition area, and establishing a coordinate system corresponding to the current user based on position information of the user in the video image; identifying the corresponding human skeleton key point coordinates of the current user according to the coordinate system; and determining the preset values of the traditional culture gesture characteristics by using the human skeleton key point coordinates of the current user, judging whether the values of the traditional culture gesture characteristics meet the corresponding preset conditions, and if so, determining that the current user makes the corresponding traditional culture gesture. The method and the device can automatically recognize the traditional culture gestures, the intelligent degree and the efficiency of the recognition process are high, the accuracy and the reliability of recognition results of the traditional culture gestures can be effectively improved, and the accuracy and the intelligent degree of user interaction can be effectively improved.

Description

Intelligent recognition method and intelligent interaction method for traditional culture gestures and related devices

Technical Field

The application relates to the technical field of data processing, in particular to an intelligent recognition method and an intelligent interaction method for traditional culture gestures and a related device.

Background

The traditional cultural gesture is a traditional Chinese meeting etiquette which can embody the humanity of China, and can be widely applied as a proper communication etiquette in the modern society. The line gift manners such as the fist line gift, the bent waist line gift and the arched gift can be collectively called as traditional cultural gestures. With the rapid development of society, the combination of traditional culture and modern technology has become an inarchable development trend, especially the interaction mode of traditional culture gestures.

At present, most of existing gesture interaction modes focus on how to utilize a computer network to perform networking of the internet of things and remote seamless connection technology to perform data interaction, and most of detection of key points of human skeletons involved in the gesture interaction modes also focuses on how to identify and extract key point information and geometric coordinate point characteristics, and the gesture interaction modes are not suitable for behavior identification of traditional cultural gestures.

Therefore, how to design a behavior recognition mode aiming at the traditional culture gestures is a problem to be solved urgently.

Disclosure of Invention

The intelligent recognition method and the intelligent interaction method for the traditional culture gestures and the related device can automatically recognize the traditional culture gestures, are high in intelligentization degree and efficiency in the recognition process, can effectively improve accuracy and reliability of recognition results of the traditional culture gestures, and can further effectively improve accuracy and intelligentization degree of interaction with users making the traditional culture gestures according to the recognition results.

In order to solve the technical problem, the application provides the following technical scheme:

in a first aspect, the present application provides a method for intelligently recognizing a traditionally-cultural gesture, including:

acquiring a video image of a current user in a target acquisition area, and establishing a coordinate system corresponding to the current user based on position information of the user in the video image;

identifying the corresponding human skeleton key point coordinates of the current user according to the coordinate system;

and determining values of preset traditional culture gesture characteristics by using the human skeleton key point coordinates of the current user, judging whether the values of the traditional culture gesture characteristics meet respective corresponding preset conditions, and if so, determining that the current user makes a corresponding traditional culture gesture.

Further, the cultural traditional gesture features include: human nose neck is apart from and the both shoulders is apart from aspect ratio between aspect ratio, wrist distance and the elbow distance, two wrist vectors and contained angle, two elbow vectors between the x axis unit vector in the coordinate system with contained angle, right hand elbow to the direction vector of right wrist between the x axis unit vector in the coordinate system with inner product between the y axis unit vector in the coordinate system to and, the direction vector of left elbow to left wrist with inner product between the y axis unit vector in the coordinate system.

Further, whether the value of each of the traditional culture gesture features satisfies the corresponding preset condition includes:

judging whether the aspect ratio between the nose neck distance and the double shoulder distance is smaller than or equal to a preset judgment threshold value of the ratio between the nose neck distance and the double shoulder distance so as to determine whether the current user performs head lowering;

judging whether the aspect ratio between the wrist distance and the elbow distance is smaller than or equal to a preset judgment threshold value of the distance ratio between the double wrists and the double elbows or not so as to determine whether the current user makes the action of closing the two hands and separating the elbows outwards;

judging whether an included angle between the two wrist vectors and an x-axis unit vector in the coordinate system is smaller than or equal to a preset threshold value of included angles between double wrists and a horizontal line or not, and judging whether an included angle between the two elbow vectors and the x-axis unit vector in the coordinate system is smaller than or equal to a preset threshold value of included angles between double elbows and a horizontal line or not, so as to determine whether the current user performs a boxing holding salute action with horizontally symmetrical double hand positions or not;

judging whether the inner product between the direction vector from the right elbow to the right wrist and the y-axis unit vector in the coordinate system is larger than 0, and judging whether the inner product between the direction vector from the left elbow to the left wrist and the y-axis unit vector in the coordinate system is larger than 0 to determine whether the current user makes an action with the wrist position higher than the elbow position.

Further, if yes, determining that the current user is making or has made a traditionally-cultural gesture, including:

if learn current user and made simultaneously through the judgement the action of low head both hands fold and the elbow moves to the outside separation the action that both hands position presents horizontal symmetry's boxing of embracing expert and the action that the wrist position is higher than the elbow position corresponds, then confirm that current user is at or has made traditional culture gesture.

In a second aspect, the present application provides an intelligent interaction method for traditional culture gestures, including:

and if the intelligent recognition method of the traditional culture gesture is applied to determine that the current user makes the corresponding traditional culture gesture, judging whether the frequency of the user making the traditional culture gesture in a preset recognition period exceeds a preset value, and if so, triggering a preset interaction event corresponding to the traditional culture gesture.

Further, the triggering preset interaction events corresponding to the traditionally-cultured gestures comprises:

sending a playing instruction to corresponding multimedia equipment so that the multimedia equipment plays pre-stored video content or music content according to the playing instruction;

and/or the presence of a gas in the gas,

and sending a starting instruction to the corresponding lighting system so that the lighting system controls the lamps in the corresponding area to be lightened or twinkled according to the starting instruction.

In a third aspect, the present application provides an intelligent recognition device for traditionally-cultural gestures, comprising:

the video data acquisition module is used for acquiring a video image of a current user in a target acquisition area and establishing a coordinate system corresponding to the current user based on position information of the user in the video image;

the human skeleton key point identification module is used for identifying the corresponding human skeleton key point coordinates of the current user according to the coordinate system;

and the traditional culture gesture interaction behavior recognition module is used for determining values of all preset traditional culture gesture characteristics by applying the human skeleton key point coordinates of the current user, judging whether the values of all the traditional culture gesture characteristics meet respective corresponding preset conditions, and if so, determining that the current user makes a corresponding traditional culture gesture.

In a fourth aspect, the present application provides an intelligent interaction device for traditional cultural gestures, comprising:

and the traditional culture gesture interaction event triggering module is used for judging whether the frequency of the traditional culture gesture made by the user in a preset identification period exceeds a preset value or not if the current user makes the corresponding traditional culture gesture by applying the intelligent identification method of the traditional culture gesture, and triggering a preset interaction event corresponding to the traditional culture gesture if the frequency of the traditional culture gesture made by the user in the preset identification period exceeds the preset value.

In a fifth aspect, the present application provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the intelligent recognition method for the traditionally-cultural gesture or implements the steps of the intelligent interaction method for the traditionally-cultural gesture when executing the program.

In a sixth aspect, the present application provides a computer readable storage medium having stored thereon a computer program which, when being executed by a processor, carries out the steps of the method for intelligent recognition of traditionally cultural gestures or the steps of the method for intelligent interaction of traditionally cultural gestures.

According to the technical scheme, the intelligent recognition method, the intelligent interaction method and the related device for the traditional culture gestures collect the video image of the current user in the target collection area, and establish the coordinate system corresponding to the current user based on the position information of the user in the video image; identifying the corresponding human skeleton key point coordinates of the current user according to the coordinate system; the method comprises the steps of determining values of preset traditional culture gesture characteristics by applying human skeleton key point coordinates of a current user, judging whether the values of the traditional culture gesture characteristics meet respective corresponding preset conditions, if so, determining that the current user makes a corresponding traditional culture gesture, comprehensively utilizing innovative multidimensional characteristics to perform three-dimensional intelligent recognition on traditional culture gesture interactive behaviors, automatically recognizing the traditional culture gesture on site, and effectively improving the accuracy and reliability of a recognition result of the traditional culture gesture, namely greatly improving the accuracy and efficiency of the recognition of the traditional culture gesture interactive behaviors; and then can effectively improve and carry out interactive accuracy nature and intelligent degree according to this recognition result and the user of making traditional culture gesture to and can effectively improve the ceremonial sense and the convenience in the human-computer interaction terminal equipment use of traditional culture gesture, strengthened the culture of making traditional culture gesture and belonged to the sense and the immersive experience.

Drawings

In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.

Fig. 1 is a schematic structural diagram of an intelligent recognition and interaction system for traditional cultural gestures according to the present application.

Fig. 2 is a schematic flow chart of the intelligent recognition method for the traditional culture gesture according to the present application.

Fig. 3 is a schematic identification diagram of coordinates of key points of human bones in the embodiment of the present application.

Fig. 4 is a flowchart illustrating astep 300 in the method for intelligently recognizing a traditionally-cultured gesture according to the embodiment of the present application.

Fig. 5 is a schematic structural diagram of an intelligent recognition device for a traditional culture gesture in an embodiment of the present application.

Fig. 6 is a flowchart illustrating an intelligent interaction method of a traditional culture gesture in an embodiment of the present application.

Fig. 7 is a schematic structural diagram of an intelligent interaction device for traditional cultural gestures in an embodiment of the present application.

FIG. 8 is a schematic structural diagram of an intelligent recognition and interaction device for traditional cultural gestures in an application example of the present application.

FIG. 9 is a flow chart illustrating a method for intelligent recognition and/or interaction of cultural gestures in an example of an application of the present application.

Fig. 10 is a schematic structural diagram of an electronic device in an embodiment of the present application.

Detailed Description

In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some embodiments of the present application, but not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.

The method and the device have the advantages that the existing gesture interaction mode is mainly focused on how to utilize a computer network to perform networking of the Internet of things and remote seamless connection technology to perform data interaction, the detection of key points of human skeleton related to the gesture interaction mode is also mainly focused on how to recognize and extract key point information and geometric coordinate point characteristics, and the method and the device are not suitable for the field recognition of traditional cultural gestures. In the existing method for extracting the face features of the face coordinate system, the aspect ratio of eyes can be extracted to perform face-related behavior recognition, and the blinking behavior features can also be recognized by detecting blinking physiological features; the method provides a technical scheme for performing behavior recognition by mining face coordinate point information, however, the mining of feature points in the method is only limited to a single aspect ratio concept, and the problems of inaccurate judgment and too single index exist. Compared with the scheme, the intelligent recognition method for the traditional culture gestures is specially suitable for recognition of the traditional culture gestures, also on the basis of feature mining of aspect ratio, human space vectors and direction information are mined, and combined multi-dimensional intelligent judgment of up to six feature points such as included angles and inner products of partial key feature points is designed.

Based on the above, the present application provides an intelligent recognition method for a traditional culture gesture, an intelligent recognition apparatus for a traditional culture gesture, an electronic device, and a computer-readable storage medium, by acquiring a video image of a current user located in a target acquisition area, and establishing a coordinate system corresponding to the current user based on position information of the user in the video image; identifying the corresponding human skeleton key point coordinates of the current user according to the coordinate system; the method comprises the steps of determining values of preset traditional culture gesture characteristics by applying human skeleton key point coordinates of a current user, judging whether the values of the traditional culture gesture characteristics meet respective corresponding preset conditions, if so, determining that the current user makes a corresponding traditional culture gesture, comprehensively utilizing innovative multidimensional characteristics to perform three-dimensional intelligent recognition on traditional culture gesture interactive behaviors, automatically recognizing the traditional culture gesture on site, and effectively improving the accuracy and reliability of a recognition result of the traditional culture gesture, namely greatly improving the accuracy and efficiency of the recognition of the traditional culture gesture interactive behaviors; and then can effectively improve and carry out interactive accuracy nature and intelligent degree according to this recognition result and the user of making traditional culture gesture to and can effectively improve the ceremonial sense and the convenience in the human-computer interaction terminal equipment use of traditional culture gesture, strengthened the culture of making traditional culture gesture and belonged to the sense and the immersive experience.

In one or more embodiments of the present application, a vector inner Product (Dot Product) is a binary operation that inputs two vectors on a real number R and returns one real-valued scalar. It is the standard inner product of euclidean space. The inner product of two vectors a ═ a1, a2, …, an ] and b ═ b1, b2, …, bn ] is defined as:

dotProduct(a,b)＝a1b1+a2b2+……+anbn。

in view of the above, an embodiment of the present application provides an intelligent recognition and interaction system for a traditional culture gesture, which is used for implementing an intelligent recognition and/or interaction method for the traditional culture gesture, the intelligent recognition and interaction system for the traditional culture gesture comprises at least one intelligent recognition device for the traditional culture gesture and at least one intelligent interaction device for the traditional culture gesture, both the intelligent recognition device for the traditional culture gesture and the intelligent interaction device for the traditional culture gesture can be a server, the intelligent recognition device for the traditional culture gesture can be afirst server 01, and the intelligent interaction device for the traditional culture gesture can be a second server 07, as shown in fig. 1, thefirst server 01 is respectively distinguished from at least one videoimage acquisition device 02, and/or 07 arranged in the same target area, A second server 07 and aclient device 05, said second server 07 being communicatively connectable to at least onemultimedia device 03, to at least one set oflighting systems 04 and to at least onemoney donation box 06, respectively. It is to be understood that thefirst server 01 and the second server 07 may be disposed independently from each other as shown in fig. 1, or may be integrally disposed as two functional modules of one server.

Based on the above content, thefirst server 01 may acquire an instruction for starting intelligent recognition of a traditional culture gesture from theclient device 02 on line, and after receiving the instruction, control the videoimage acquisition device 02 to continuously acquire video images of a user in a target acquisition area of thefirst server 01, receive a video image of a current user in the target acquisition area acquired by the videoimage acquisition device 02, and establish a coordinate system corresponding to the current user based on position information of the user in the video image; then, recognizing the corresponding human skeleton key point coordinates of the current user according to the coordinate system; determining values of preset traditional culture gesture features by using the human skeleton key point coordinates of the current user, judging whether the values of the traditional culture gesture features meet respective corresponding preset conditions, if so, determining that the current user makes a corresponding traditional culture gesture, then sending a recognition result to theclient device 05 and the second server 07 by theserver 01, and sending corresponding control instructions to themultimedia device 03, thelighting system 04 and themoney donation box 06 by the second server 07 according to the received recognition result, so that themultimedia device 03 plays pre-stored video content or music content according to the control instructions; thelighting system 04 controls the lights in the corresponding area to be turned on or to flash according to the opening instruction, and the prompting light on themoney donation box 06 is turned on or the loudspeaker on the money donation box emits a prompting sound.

On the basis of the above content, in order to prevent a frequently false triggering scene from occurring, in the intelligent interaction method for a traditional culture gesture provided by the present application, after the server determines that a current user makes a corresponding traditional culture gesture by applying the intelligent recognition method for a traditional culture gesture in one or more embodiments of the present application, it is further required to continuously determine whether the number of times that the user makes the traditional culture gesture within a preset recognition period exceeds a preset value, if so, a preset interaction event corresponding to the traditional culture gesture is triggered, otherwise, a scene that the current user makes the corresponding traditional culture gesture determined by applying the intelligent recognition method for a traditional culture gesture in one or more embodiments of the present application is determined as a frequently false triggering scene, and the interaction event is not triggered.

It is understood that the client devices may include smart phones, tablet electronic devices, network set-top boxes, portable computers, desktop computers, Personal Digital Assistants (PDAs), in-vehicle devices, smart wearable devices, and the like. Wherein, intelligence wearing equipment can include intelligent glasses, intelligent wrist-watch, intelligent bracelet etc..

In practical applications, part of the intelligent recognition and/or interaction of the traditionally-cultural gestures may be performed on the server side as described above, or all operations may be performed in the client device. The selection may be specifically performed according to the processing capability of the client device, the limitation of the user usage scenario, and the like. This is not a limitation of the present application. The client device may further include a processor if all operations are performed in the client device.

The client device may have a communication module (i.e., a communication unit), and may be communicatively connected to a remote server to implement data transmission with the server. The server may include a server on the task scheduling center side, and in other implementation scenarios, the server may also include a server on an intermediate platform, for example, a server on a third-party server platform that is communicatively linked to the task scheduling center server. The server may include a single computer device, or may include a server cluster formed by a plurality of servers, or a server structure of a distributed apparatus.

The server and the client device may communicate using any suitable network protocol, including network protocols not yet developed at the filing date of the present application. The network protocol may include, for example, a TCP/IP protocol, a UDP/IP protocol, an HTTP protocol, an HTTPS protocol, or the like. Of course, the network Protocol may also include, for example, an RPC Protocol (Remote Procedure Call Protocol), a REST Protocol (Representational State Transfer Protocol), and the like used above the above Protocol.

In order to automatically recognize the traditional culture gesture, the intelligent degree of the recognition process is high, the efficiency is high, and the accuracy and the reliability of the recognition result of the traditional culture gesture can be effectively improved, in the embodiment of the intelligent recognition method of the traditional culture gesture, referring to fig. 2, the intelligent recognition method of the traditional culture gesture specifically comprises the following contents:

step 100: the method comprises the steps of collecting a video image of a current user in a target collection area, and establishing a coordinate system corresponding to the current user based on position information of the user in the video image.

It can be understood that the establishment manner of the coordinate system corresponding to the user is preset, and in an example, for a standing human body, the lower left corner of the video image corresponding to the human body may be defined as an origin of coordinates, which is a positive direction of an x-axis from the origin of coordinates laterally to the right, and a negative direction of the x-axis from the lateral left; the positive direction of the y axis is from the bottom to the top in the vertical direction of the origin of coordinates, and the negative direction of the y axis is from the top to the bottom.

Step 200: and identifying the corresponding human skeleton key point coordinates of the current user according to the coordinate system.

Wherein, referring to fig. 3, the identification of the key points of the human skeleton is preset. The human skeleton key point detection is one of basic algorithms of computer vision, and plays a basic role in the research of other related fields of computer vision, such as behavior recognition, person tracking, gait recognition and other related fields. The method can detect main key points of all human bodies in the picture, including parts such as neck, shoulder, elbow, wrist, waist, knee, ankle and the like, and coordinate information of the parts in a human body coordinate system. The extraction of similar characteristics can be performed by adopting relatively mature open source software, for example, mature open source software such as OpenPose and the like in the industry are matched to detect key points of human bones, and the mature realization is realized in github.

Step 300: and determining values of preset traditional culture gesture characteristics by using the human skeleton key point coordinates of the current user, judging whether the values of the traditional culture gesture characteristics meet respective corresponding preset conditions, and if so, determining that the current user makes a corresponding traditional culture gesture.

Instep 300, in order to further improve the recognition accuracy and reliability of the traditional cultural gesture through the application of the multidimensional features, the traditional cultural gesture features may specifically be composed of six-dimensional features, which are respectively:

(1) the aspect ratio between the distance between the nose and neck and the distance between the shoulders of the human body;

wherein an aspect Ratio 2n2sr (Nose New two Shoulder Ratio) between the nasal Neck distance and the Shoulder distance is:

said F (i) is the ith feature of said human skeletal key feature, and each F point contains its x and y coordinate values on the human skeletal coordinate system;

the dist function represents the euclidean distance of two feature points, the distance between the ith and jth key feature points being calculated as an example,

the 1 st parameter i of the F (i, b) represents the index of the corresponding human skeleton key point characteristic;

the 2 nd parameter b represents the current x coordinate or y coordinate, and the values are x and y respectively.

(2) The aspect ratio between the wrist distance and elbow distance;

wherein an aspect ratio 2w2er (two Wrist two electric rates) between the wrist distance and the elbow distance is:

(3) the included angle between the two wrist vectors and the x-axis unit vector in the coordinate system;

wherein the Angle between the two Wrist vectors and the X-axis unit vector in the coordinate system is characterized by the Angle between one right-left Wrist vector and the X-axis unit vector e1, the two Wrist vectors and the X-axis unit vector a2wx (Angle of two Wrist and X-axis) in the coordinate system are further described as follows:

the vector that takes two points i and j, i pointing to j, is called vector (f (i), f (j)):

vector(F(i),F(j))＝(F(j,x)-F(i,x),F(j,y)-F(i,y))

thus, the vector (f (m), f (n)) for two points m and n, m pointing to n is:

vector(F(m),F(n))＝(F(n,x)-F(m,x),F(n,y)-F(m,y))；

defining the inner product operation of two vectors as dp (p, q) ═ dotP product (p, q);

according to the inner product formula of the vector ij and the vector mn, the following can be obtained:

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))

further, the angle theta (ij, mn) between the vectors ij and mn is:

completing the explanation of the vector included angle;

defining the x-axis unit vector as e1 ═ 0, 1;

the Y-axis unit vector is (1,0) e 2;

it can therefore be further deduced that a2wx (Angle of two Wrist and X-axis) is the following:

(4) the included angle between the two elbow vectors and the x-axis unit vector in the coordinate system;

wherein an Angle between the two elbow vectors and an X-axis unit vector in the coordinate system is an Angle feature of one right-left elbow vector and an X-axis unit vector e1, and an Angle of two Wrist and X-axis between the two elbow vectors and an X-axis unit vector in the coordinate system a2wx (Angle of two Wrist and X-axis) is:

the process of a2ex definition and derivation is similar to that of a2wx, and is not repeated here.

(5) An inner product between a direction vector of the right elbow to the right wrist and a y-axis unit vector in the coordinate system;

the inner product dprewy (dot product of Right Elbow Wrist and y-axis) between the Right Elbow to Right Wrist direction vector and the y-axis unit vector in the coordinate system is:

dprewy＝dotProduct(vector(F(9),F(11)),e2)。

(6) an inner product between a left elbow to left wrist direction vector and a y-axis unit vector in the coordinate system;

wherein an inner product dplewy (dot product of Left Elbow Wrist and y-axis) between the Left Elbow to Left Wrist direction vector and the y-axis unit vector in the coordinate system is:

dplewy＝dotProduct(vector(F(10),F(12)),e2)。

in summary, after coordinate information of key points of human bones is obtained, direction and feature point position information of space vectors presented by traditional culture gesture interaction actions are deeply mined, Wrist distance and Elbow distance aspect Ratio 2w2er (two wrote edition Ratio), Nose Neck distance and double Shoulder distance aspect Ratio 2n2sr (Nose new wrote book edition Ratio), included Angle a2wx of Right and Left Wrist vectors and X-axis unit vectors (Angle of two wrote edition and X-axis), included Angle a2wx of Right and Left Elbow vectors and X-axis unit vectors (Angle of two wrote edition and X-axis), and inner product of Right and Left Elbow to Right Wrist direction vectors and y-axis unit vectors (index of Right and Left Wrist direction vectors) are proposed for traditional culture gesture interaction actions, and a plurality of inner product of Right and Left Elbow and Left Wrist direction vectors (index of Right and Left Wrist direction vectors) are proposed Recognizing characteristic indexes by traditional culture gesture interaction behaviors; the innovative multidimensional characteristics are comprehensively utilized to carry out three-dimensional intelligent recognition on the traditional culture gesture interactive behaviors, so that the problems of accuracy and efficiency of the traditional culture gesture interactive behavior recognition are greatly improved; by the method, the ceremonial sense and the convenience of the intelligent traditional culture gesture human-computer interaction terminal equipment such as the electronic gongdu box in the using process are improved, and the attribution sense and the immersion experience of tourists and the people are enhanced.

In order to further improve the accuracy of determining whether the user makes the traditionally-cultural gesture, in one embodiment of the intelligent recognition method for traditionally-cultural gesture of the present application, referring to fig. 4, thesteps 300 are, in addition to step 301: the method comprises the following steps of determining preset values of various traditional culture gesture characteristics by applying the human skeleton key point coordinates of the current user, wherein the subsequent judgment process specifically comprises the following contents executed in parallel or in any sequence:

step 302: and judging whether the aspect ratio between the nose neck distance and the double shoulder distance is smaller than or equal to a preset judgment threshold value of the ratio between the nose neck distance and the double shoulder distance so as to determine whether the current user performs head lowering.

Step 303: and judging whether the aspect ratio between the wrist distance and the elbow distance is smaller than or equal to a judgment threshold of the distance ratio between the preset double wrists and the preset double elbows so as to determine whether the current user makes the action of closing the two hands and separating the elbows to the outside.

Step 304: judge two wrist vectors with whether contained angle between the x axle unit vector in the coordinate system is less than or equal to two wrist and the horizontal line contained angle threshold of predetermineeing, and, judge two elbow vectors with whether contained angle between the x axle unit vector in the coordinate system is less than or equal to two elbow and the horizontal line contained angle threshold of predetermineeing to confirm whether current user makes the action that both hands position presents the boxer of horizontal symmetry.

Step 305: judging whether the inner product between the direction vector from the right elbow to the right wrist and the y-axis unit vector in the coordinate system is greater than 0, and judging whether the inner product between the direction vector from the left elbow to the left wrist and the y-axis unit vector in the coordinate system is greater than 0, so as to determine whether the current user makes an action with a wrist position higher than the elbow position.

Correspondingly, thestep 305 further includes a step 306: if learn current user and made simultaneously through the judgement the action of low head both hands fold and the elbow moves to the outside separation the action that both hands position presents horizontal symmetry's boxing of embracing expert and the action that the wrist position is higher than the elbow position corresponds, then confirm that current user is at or has made traditional culture gesture.

From the software aspect, in order to carry out automatic identification to traditional culture gesture, and the intelligent degree of identification process is high, efficient to can effectively improve the accuracy and the reliability of the recognition result of traditional culture gesture, this application provides one kind and is used for realizing the embodiment of the intelligent recognition device of traditional culture gesture of whole or partial content in the intelligent recognition method of traditional culture gesture, refer to fig. 5, the intelligent recognition device of traditional culture gesture specifically includes following content:

and the videodata acquisition module 003 is used for acquiring a video image of the current user in the target acquisition area, and establishing a coordinate system corresponding to the current user based on the position information of the user in the video image.

And the human skeleton keypoint identification module 004 is used for identifying the corresponding human skeleton key point coordinates of the current user according to the coordinate system.

The traditional culture gesture interactionbehavior recognition module 005 is used for determining values of preset traditional culture gesture features by applying the human skeleton key point coordinates of the current user, judging whether the values of the traditional culture gesture features meet corresponding preset conditions, and if so, determining that the current user makes a corresponding traditional culture gesture.

The embodiment of the intelligent recognition device for the traditional culture gesture provided in the embodiment of the application can be specifically used for executing the processing flow of the embodiment of the intelligent recognition method for the traditional culture gesture in the embodiment, and the functions of the intelligent recognition device for the traditional culture gesture are not repeated herein and can refer to the detailed description of the embodiment of the intelligent recognition method for the traditional culture gesture.

From the above description, the intelligent recognition device for the traditional culture gestures provided by the embodiment of the application comprehensively utilizes innovative multidimensional characteristics to perform three-dimensional intelligent recognition on the traditional culture gesture interactive behaviors, can perform on-site automatic recognition on the traditional culture gestures, has high intelligent degree and high efficiency in the recognition process, and can effectively improve the accuracy and reliability of the recognition result of the traditional culture gestures, namely greatly improve the accuracy and efficiency of the recognition of the traditional culture gesture interactive behaviors; and then can effectively improve and carry out interactive accuracy nature and intelligent degree according to this recognition result and the user of making traditional culture gesture to and can effectively improve the ceremonial sense and the convenience in the human-computer interaction terminal equipment use of traditional culture gesture, strengthened the culture of making traditional culture gesture and belonged to the sense and the immersive experience.

In order to automatically recognize and interact the traditional culture gesture, the recognition and interaction process has high intelligent degree and high efficiency, the accuracy and the reliability of the recognition and interaction result of the traditional culture gesture can be effectively improved, and the accuracy and the intelligent degree of interaction with the user making the traditional culture gesture according to the recognition result can be effectively improved, in the embodiment of the intelligent interaction method of the traditional culture gesture, referring to fig. 6, the intelligent interaction method of the traditional culture gesture is executed after the intelligent recognition method of the traditional culture gesture, and specifically comprises the following contents:

step 400: if the intelligent recognition method for the traditional culture gestures determines that the current user makes the corresponding traditional culture gestures, whether the times that the user makes the traditional culture gestures in the preset recognition period exceeds a preset value is judged, and if yes, thestep 500 is executed.

Step 500: and triggering a preset interaction event corresponding to the traditional culture gesture.

In order to further improve the accuracy and the intelligence degree of interaction with the user making the traditionally-cultural gesture according to the recognition result, in an embodiment of the intelligently-interacting method for traditionally-cultural gesture of the present application, thestep 500 of the intelligently-interacting method for traditionally-cultural gesture specifically includes at least one of the following steps 501 and 502.

Wherein, step 501: and sending a playing instruction to the corresponding multimedia equipment so that the multimedia equipment plays the pre-stored video content or music content according to the playing instruction.

Step 502: and sending a starting instruction to the corresponding lighting system so that the lighting system controls the lamps in the corresponding area to be lightened or twinkled according to the starting instruction.

From the software aspect, in order to be able to automatically recognize and interact the traditional culture gesture, and the recognition and the interaction are high in degree of intelligence and efficiency with respect to the process, and can effectively improve the accuracy and reliability of the recognition and the interaction result of the traditional culture gesture, the application provides an embodiment of an intelligent interaction device for realizing the traditional culture gesture of all or part of the contents in the intelligent interaction method for the traditional culture gesture, and referring to fig. 7, the intelligent interaction device for the traditional culture gesture specifically comprises the following contents:

and the legacy culture gesture interactionevent triggering module 006 is configured to determine whether the number of times that the user makes the legacy culture gesture within a preset recognition period exceeds a preset value if the current user makes the corresponding legacy culture gesture is determined by applying the smart recognition method for the legacy culture gesture, and trigger a preset interaction event corresponding to the legacy culture gesture if the current user makes the corresponding legacy culture gesture.

In order to further explain this scheme, this application still provides an intelligent recognition device who uses above-mentioned traditional culture gesture and the intelligent interaction device of traditional culture gesture realize the intelligent recognition method of corresponding traditional culture gesture and the concrete application example of the intelligent interaction method of traditional culture gesture, use the box of donation of full money as the electron moral box for example, and place such as target collection region wherein is buddhist temple, see figure 8, the intelligent recognition and the interaction device of traditional culture gesture specifically include: the electronic Gong and De box comprises an electronic Gong and De box core background service module 001 for bearing basic service, wifi, network communication and background interaction, a parameter setting module 002 for setting a head-to-shoulder ratio threshold value, a palm-to-elbow ratio threshold value and the like, a videodata acquisition module 003 for acquiring image data of human faces and human body postures, a human bone keypoint recognition module 004 for extracting human bone key point information, a traditional culture gesture interactivebehavior recognition module 005 and a traditional culture gesture interactiveevent triggering module 006.

The intelligent recognition and interaction method of the traditional culture gestures specifically comprises the following contents:

firstly, an administrator starts an electronic merit box core background service module 001 for handling core services related to business logic of the electronic merit box; and is also responsible for initializing other sub-modules.

(II) parameter setting module 002 contains the parameters relevant to complete the whole intelligent interactive recognition core function, including the human skeleton key points and the parameters relevant to detection in the traditional culture gesture interactivebehavior recognition module 005 behavior recognition module, specifically including:

th _2n2sr is a determination threshold value of the ratio of the distance between the nose and neck and the distance between the shoulders;

th _2w2er is a determination threshold value of the ratio of the distances between the wrists and the elbows;

th _ a2wx is the threshold value of the included angle between the wrists and the horizontal line;

th _ a2ex elbow and horizon angle thresholds;

t _ loop is used for periodically judging the time of the traditional culture gesture;

th _ bow trigger threshold for a T _ loop time period, etc.

The specific physical meanings of the parameters are introduced one by one in the following corresponding flows by combining with the algorithm principle, which is not described herein again.

And the videodata acquisition module 003 is used for displaying traditional culture gesture actions by a user in front of the camera, acquiring data by the camera and acquiring image data of human faces and human body postures.

And the (IV) human skeleton keypoint identification module 004 is used for acquiring the video data provided by the videodata acquisition module 003 to detect human skeleton key points.

The human skeleton key point detection is one of basic algorithms of computer vision, and plays a basic role in the research of other related fields of computer vision, such as behavior recognition, character tracking, gait recognition and other related fields. The method can detect all the proposed main key points in the picture, including the parts of the neck, the shoulder, the elbow, the wrist, the waist, the knee, the ankle and the like, and the coordinate information of the parts in the human body coordinate system. Similar features can be extracted by adopting relatively mature open source software, for example, mature open source software such as OpenPose and the like in the industry are matched to detect key points of human bones, and the mature realization is realized in github;

the human skeleton key point detection has a plurality of new techniques and professional papers with endless layers in the industry and academia, the precision and the accuracy of feature point detection and extraction are continuously refreshed, the application example takes OpenPose as a main method for extracting the human face feature point in the application, and an extraction module can detect 15, 18 or 25 key features of the human face.

Aiming at the coordinate information of the human body coordinate system, for subsequent unified calculation, a human body standing upright is defined, the lower left corner is a coordinate origin, the transverse right side is the positive direction of an x axis, and the transverse left side is the negative direction of the x axis; the vertical direction is the positive direction of the y axis from bottom to top and the negative direction of the y axis from top to bottom.

The traditional culture gesture interactionbehavior recognition module 005 acquires coordinate information of the human skeleton key points from the human skeleton keypoint recognition module 004, and performs traditional culture gesture interaction behavior recognition;

the traditional cultural gesture interaction behavior is characterized by six innovative features as described in the foregoing, namely an aspect ratio 2n2sr between the distance between the neck and shoulders of the human body, an aspect ratio 2w2er between the distance between the wrist and the elbow, an included angle a2wx between two wrist vectors and the x-axis unit vector in the coordinate system, an included angle a2wx between two elbow vectors and the x-axis unit vector in the coordinate system, an inner product dprewy between the direction vector from the right elbow to the right wrist and the y-axis unit vector in the coordinate system, and an inner product dplewy between the direction vector from the left elbow to the left wrist and the y-axis unit vector in the coordinate system.

The traditional culture gesture interaction behavior has six characteristics, and when the actions are executed, the following remarkable changes exist:

2n2sr,2w2er would become smaller, a2wx, a2ex would be near zero; dprewy and dplewy are greater than 0.

The reason why the 2n2sr is reduced is that when the traditional and cultural gesture interaction gesture exists, the head can be in a head-lowering action, so that the distance between the nose and the neck of the image is obviously reduced, but the distance between the shoulders is kept unchanged.

The reason why 2w2er becomes smaller is that when there is a traditional cultural gesture interaction gesture, the two hands are closed, the distance between the two wrists is very close, and the elbows are separated to the outside, resulting in the ratio of the distance between the two wrists and the two elbows becoming significantly smaller.

The reason why the a2wx and a2ex are close to the zero point is that due to the vertical symmetry, the scene of boxing ceremony in one hand does not exist, and the orientation of two hands has horizontal symmetry and therefore has a small included angle with the horizontal.

The reason why dprewy and dplewy are larger than 0 is that when the traditional culture gesture interaction gesture exists, the ordinate of the wrist is larger than the ordinate of the elbow, so that the included angle between the elbow and wrist vector and the e2 vector is smaller than the absolute value of 90 degrees, and the inner product is larger than 0.

Therefore, when the traditional culture gesture interaction gesture exists, the following thresholds are designed to extract and judge the obvious change characteristics:

th _2n2sr is a determination threshold value of the ratio of the distance between the nose and neck and the distance between the shoulders;

th _2w2er is a determination threshold value of the ratio of the distances between the wrists and the elbows;

th _ a2wx is the threshold value of the included angle between the wrists and the horizontal line;

th _ a2ex elbow and horizontal line angle thresholds.

Therefore, the traditional cultural gesture interaction behavior simultaneously satisfies the following determination conditions:

2n2sr≤th_2n2sr

2w2er≤th_2w2er

abs(a2wx)≤th_a2wx

a2ex≤th_a2ex

dprewy>0

dplewy>0

a successful event is detected for a single traditional cultural gesture interaction gesture, defined as event _ bow _ once.

The abs () function described above represents taking the absolute value of the data.

Preferably, to prevent the above scenario where there are frequent false triggers, event _ bow _ once does not represent the final detection result of a successful traditionally-cultural gesture behavior.

We define a periodic, traditional cultural gesture decision time as T _ loop.

The number of times of triggering event _ bow _ once within the T _ loop period is defined as cnt _ event _ bow.

During the T _ loop period, cnt _ event _ bow is equal to or greater than th _ bow for successfully triggering a traditionally cultural gesture interaction event _ bow.

The th _ bow is the trigger threshold of the traditional culture gesture in the T _ loop time period.

And (v) the traditional cultural gesture interactionbehavior recognition module 005 calls the traditional cultural gesture interactionevent triggering module 006 when the event _ bow is finally satisfied and triggered.

(VI) the follow-up event of the intelligent recognition that the traditional culture gesture is carried out by the traditional culture gesture interactionevent triggering module 006 includes but is not limited to, to pointing to the interactive visitor or the confidence of above-mentioned traditional culture gesture, carry out electronic screen culture introduction, the donation channel is opened and is indicateed, demonstrates the statue of Buddha and the literary composition information of offering, plays Buddhism background music, shows specific religion statue of Buddha or the mutual multimedia information of bodhisattva, etc.

In a specific example, taking an example that a visitor and a carrier use an electronic utility box terminal of a certain bank and perform a traditional culture gesture before a camera of the electronic utility box, referring to fig. 9, an interaction flow of the above specific application example is specifically described:

1. the administrator starts the core background service module 001 of the electronic merit box; the electronic merit case core background service module is responsible for processing the core service related to the business logic of the electronic merit case; meanwhile, the method is responsible for initializing other sub-modules S002-S007;

2. the sub-module initialization comprises a parameter setting module 002, comprises parameters related to the completion of the whole intelligent interactive recognition core function, and comprises human skeleton key points and detection related parameters in a traditional culture gesture interactivebehavior recognition module 005, and specifically comprises the following steps:

th _2n2sr is a determination threshold value of the ratio of the distance between the nose and the neck and the distance between the shoulders, and the application sets th _2n2sr to 0.15;

th _2w2er is a determination threshold value of the ratio of the distances between the wrists and the elbows, and th _2w2er is set to 0.1;

th _ a2wx is an included angle threshold value between the double wrists and the horizontal line, and th _ a2wx is pi/9;

th _ a2ex elbow and horizon angle thresholds; the application sets th _ a2ew ═ pi/9;

t _ loop is used for periodically judging the time of the traditional culture gesture; the application sets T _ loop to 10 s;

the triggering threshold of the th _ bow traditional culture gesture in the T _ loop time period is set to be 2 in th _ bow;

3. the tourists carry out continuous traditional culture gesture actions before the camera of the electronic gongda box; the camera in the videodata acquisition module 003 acquires data of the tourist and acquires image data of human faces and human body postures;

4. the human skeleton keypoint identification module 004 acquires video data provided by the videodata acquisition module 003 to detect human skeleton key points;

5. the traditional culture gesture interactionbehavior recognition module 005 acquires coordinate information of the human skeleton key points from the human skeleton keypoint recognition module 004, and performs traditional culture gesture interaction behavior recognition.

6. The traditional cultural gesture interactionbehavior recognition module 005 calls the traditional cultural gesture interactionevent triggering module 006 when the event _ bow finally satisfies that cnt _ event _ bow is greater than or equal to th _ bow; assume here that the user continues the traditional culture gesture 3 times within 10s and is detected by the system, triggering event _ bow _ once three times, successfully triggering event _ bow event.

7. Theevent triggering module 006 for traditional culture gesture interaction performs intelligent recognition of subsequent events of traditional culture gestures, including but not limited to, electronic screen culture introduction, donation channel opening and prompting, exhibition of offered Buddha and scripture information, playing of Buddhism background music, exhibition of specific religious Buddha or Buddha interaction multimedia information, and the like, for tourists or people with confidence pointing to the traditional culture gesture interaction;

the practical efficacy of the S006 multimedia event trigger module is described by taking the example of the interaction between the lighting system of the Internet of things smart place and the multimedia information.

S006 event triggering module receiving event _ bow event from the gestureinteraction identification module 005 of traditional culture;

the event can trigger multimedia playing software connected with the electronic merit box through the network to execute music playing operation, and simultaneously, an illuminating lamp system connected with the area where the current electronic merit box is located through the Internet of things can flicker or light up;

the music playing operation comprises a random number randNum generator for generating a random number, wherein the range of the random number satisfies 1< randNum < music max;

musicMax is the number of Buddhism background music in a database or file system in a specified storage location; because the player can play the first randNum background music of the storage system according to the random number;

the lighting lamp system flickers or lights up, and comprises a plurality of electronic merit boxes, wherein each electronic merit box is configured with a lighting system in the area through the Internet of things; when a tourist or a letter of the public is in an electronic goods box in the area A to trigger an event _ bow, lighting or flickering an IoT lamp system appointed to be administered by the area A;

therefore, through thing networking wisdom place point lamp system and multimedia information interaction for the wisdom perception of people's action and place reaches intelligent linkage, has strengthened visitor's seeing and hearing amusement interest, has also strengthened the sense of reality of people, has participated in simultaneously, belongs to the sense, has promoted human-computer interaction's convenience.

In addition, regarding the human key point identification component mentioned in the present application, the mainstream method is the method of neural network deep learning of the kind indicated in the present application, and certainly, based on the traditional computer vision feature engineering, it is an alternative to extract texture features and local information of an image to perform human key point identification, but the latter is gradually no longer the main method of human key point identification of the mainstream due to the traditional feature limitation and poor performance.

From the hardware aspect, in order to be able to automatically recognize the traditionally-cultural gesture, the intelligent degree of the recognition process is high, the efficiency is high, the accuracy and the reliability of the recognition result of the traditionally-cultural gesture can be effectively improved, and the accuracy and the intelligent degree of interaction with the user who makes the traditionally-cultural gesture according to the recognition result can be effectively improved, the application provides an embodiment of the electronic device for realizing all or part of the contents in the intelligent recognition method of the traditionally-cultural gesture and/or the intelligent interaction method of the traditionally-cultural gesture, and the electronic device specifically comprises the following contents:

a processor (processor), a memory (memory), a communication Interface (Communications Interface), and a bus; the processor, the memory and the communication interface complete mutual communication through the bus; the communication interface is used for realizing information transmission among related equipment such as an intelligent recognition device of a traditional culture gesture, an intelligent interaction device of a traditional culture gesture, video image acquisition equipment, multimedia equipment, a money donation box, a lighting system, a user terminal and the like; the electronic device may be a desktop computer, a tablet computer, a mobile terminal, and the like, but the embodiment is not limited thereto. In this embodiment, the electronic device may refer to the embodiment of the intelligent recognition and/or interaction method of the traditional culture gesture and the embodiment of the intelligent recognition and/or interaction apparatus of the traditional culture gesture, which are incorporated herein and repeated herein.

Fig. 10 is a schematic block diagram of a system configuration of anelectronic device 9600 according to an embodiment of the present application. As shown in fig. 10, theelectronic device 9600 can include acentral processor 9100 and amemory 9140; thememory 9140 is coupled to thecentral processor 9100. Notably, this fig. 10 is exemplary; other types of structures may also be used in addition to or in place of the structure to implement telecommunications or other functions.

In an embodiment, smart recognition and/or interaction functionality of the traditionally-cultural gestures may be integrated into thecentral processor 9100. Thecentral processor 9100 may be configured to control as follows:

step 100: the method comprises the steps of collecting a video image of a current user in a target collection area, and establishing a coordinate system corresponding to the current user based on position information of the user in the video image.

Step 200: and identifying the corresponding human skeleton key point coordinates of the current user according to the coordinate system.

Step 300: and determining values of preset traditional culture gesture characteristics by using the human skeleton key point coordinates of the current user, judging whether the values of the traditional culture gesture characteristics meet respective corresponding preset conditions, and if so, determining that the current user makes a corresponding traditional culture gesture.

Step 400: if the intelligent recognition method for the traditional culture gestures determines that the current user makes the corresponding traditional culture gestures, whether the times that the user makes the traditional culture gestures in the preset recognition period exceeds a preset value is judged, and if yes, thestep 500 is executed.

Step 500: and triggering a preset interaction event corresponding to the traditional culture gesture.

From the above description, the electronic device provided by the embodiment of the application comprehensively utilizes innovative multidimensional characteristics to perform three-dimensional intelligent recognition on the traditional culture gesture interactive behaviors, can perform on-site automatic recognition on the traditional culture gesture, has high intelligent degree and high efficiency in the recognition process, and can effectively improve the accuracy and reliability of the recognition result of the traditional culture gesture, namely greatly improve the accuracy and efficiency of the traditional culture gesture interactive behavior recognition; and then can effectively improve and carry out interactive accuracy nature and intelligent degree according to this recognition result and the user of making traditional culture gesture to and can effectively improve the ceremonial sense and the convenience in the human-computer interaction terminal equipment use of traditional culture gesture, strengthened the culture of making traditional culture gesture and belonged to the sense and the immersive experience.

In another embodiment, the smart recognition and/or interaction means of the traditionally-cultural gesture may be configured separately from thecentral processor 9100, for example, the smart recognition and/or interaction of the traditionally-cultural gesture may be configured as a chip connected to thecentral processor 9100, and the smart recognition and/or interaction function of the traditionally-cultural gesture is realized through the control of the central processor.

As shown in fig. 10, theelectronic device 9600 may further include: acommunication module 9110, aninput unit 9120, anaudio processor 9130, adisplay 9160, and apower supply 9170. It is noted that theelectronic device 9600 also does not necessarily include all of the components shown in fig. 10; in addition, theelectronic device 9600 may further include components not shown in fig. 10, which can be referred to in the prior art.

As shown in fig. 10, acentral processor 9100, sometimes referred to as a controller or operational control, can include a microprocessor or other processor device and/or logic device, whichcentral processor 9100 receives input and controls the operation of the various components of theelectronic device 9600.

Thememory 9140 can be, for example, one or more of a buffer, a flash memory, a hard drive, a removable media, a volatile memory, a non-volatile memory, or other suitable device. The information relating to the failure may be stored, and a program for executing the information may be stored. And thecentral processing unit 9100 can execute the program stored in thememory 9140 to realize information storage or processing, or the like.

Theinput unit 9120 provides input to thecentral processor 9100. Theinput unit 9120 is, for example, a key or a touch input device.Power supply 9170 is used to provide power toelectronic device 9600. Thedisplay 9160 is used for displaying display objects such as images and characters. The display may be, for example, an LCD display, but is not limited thereto.

Thememory 9140 can be a solid state memory, e.g., Read Only Memory (ROM), Random Access Memory (RAM), a SIM card, or the like. There may also be a memory that holds information even when power is off, can be selectively erased, and is provided with more data, an example of which is sometimes referred to as an EPROM or the like. Thememory 9140 could also be some other type of device.Memory 9140 includes a buffer memory 9141 (sometimes referred to as a buffer). Thememory 9140 may include an application/function storage portion 9142, the application/function storage portion 9142 being used for storing application programs and function programs or for executing a flow of operations of theelectronic device 9600 by thecentral processor 9100.

Thememory 9140 can also include adata store 9143, thedata store 9143 being used to store data, such as contacts, digital data, pictures, sounds, and/or any other data used by an electronic device. Thedriver storage portion 9144 of thememory 9140 may include various drivers for the electronic device for communication functions and/or for performing other functions of the electronic device (e.g., messaging applications, contact book applications, etc.).

Thecommunication module 9110 is a transmitter/receiver 9110 that transmits and receives signals via anantenna 9111. The communication module (transmitter/receiver) 9110 is coupled to thecentral processor 9100 to provide input signals and receive output signals, which may be the same as in the case of a conventional mobile communication terminal.

Based on different communication technologies, a plurality ofcommunication modules 9110, such as a cellular network module, a bluetooth module, and/or a wireless local area network module, may be provided in the same electronic device. The communication module (transmitter/receiver) 9110 is also coupled to aspeaker 9131 and amicrophone 9132 via anaudio processor 9130 to provide audio output via thespeaker 9131 and receive audio input from themicrophone 9132, thereby implementing ordinary telecommunications functions. Theaudio processor 9130 may include any suitable buffers, decoders, amplifiers and so forth. In addition, theaudio processor 9130 is also coupled to thecentral processor 9100, thereby enabling recording locally through themicrophone 9132 and enabling locally stored sounds to be played through thespeaker 9131.

Embodiments of the present application further provide a computer-readable storage medium capable of implementing all steps of the method for intelligently recognizing and/or interacting the traditional culture gesture of which the execution subject is the server in the above embodiments, where the computer-readable storage medium stores thereon a computer program, and when the computer program is executed by a processor, the computer program implements all steps of the method for intelligently recognizing and/or interacting the traditional culture gesture of which the execution subject is the server or the client in the above embodiments, for example, the processor implements the following steps when executing the computer program:

step 100: the method comprises the steps of collecting a video image of a current user in a target collection area, and establishing a coordinate system corresponding to the current user based on position information of the user in the video image.

Step 200: and identifying the corresponding human skeleton key point coordinates of the current user according to the coordinate system.

Step 300: and determining values of preset traditional culture gesture characteristics by using the human skeleton key point coordinates of the current user, judging whether the values of the traditional culture gesture characteristics meet respective corresponding preset conditions, and if so, determining that the current user makes a corresponding traditional culture gesture.

Step 400: if the intelligent recognition method for the traditional culture gestures determines that the current user makes the corresponding traditional culture gestures, whether the times that the user makes the traditional culture gestures in the preset recognition period exceeds a preset value is judged, and if yes, thestep 500 is executed.

Step 500: and triggering a preset interaction event corresponding to the traditional culture gesture.

From the above description, the computer-readable storage medium provided by the embodiment of the application comprehensively utilizes innovative multidimensional characteristics to perform three-dimensional intelligent recognition on the traditional culture gesture interactive behaviors, can perform on-site automatic recognition on the traditional culture gesture, has high intellectualization degree and high efficiency in the recognition process, and can effectively improve the accuracy and reliability of the recognition result of the traditional culture gesture, i.e., greatly improve the accuracy and efficiency of the traditional culture gesture interactive behavior recognition; and then can effectively improve and carry out interactive accuracy nature and intelligent degree according to this recognition result and the user of making traditional culture gesture to and can effectively improve the ceremonial sense and the convenience in the human-computer interaction terminal equipment use of traditional culture gesture, strengthened the culture of making traditional culture gesture and belonged to the sense and the immersive experience.

As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, apparatus, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.

The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (devices), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

The principle and the implementation mode of the invention are explained by applying specific embodiments in the invention, and the description of the embodiments is only used for helping to understand the method and the core idea of the invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present invention.

Claims (9)

1. An intelligent recognition method for traditional culture gestures is characterized by comprising the following steps:

acquiring a video image of a current user in a target acquisition area, and establishing a coordinate system corresponding to the current user based on position information of the user in the video image;

identifying the corresponding human skeleton key point coordinates of the current user according to the coordinate system;

the method comprises the steps of determining values of preset traditional culture gesture features by applying human skeleton key point coordinates of a current user, judging whether the values of the traditional culture gesture features meet respective corresponding preset conditions, if so, judging that the current user simultaneously performs head lowering, closing two hands and separating elbows outwards, performing boxing salute with horizontally symmetrical hand positions and performing corresponding actions with wrist positions higher than elbow positions, and determining that the current user is performing or has performed traditional culture gestures;

the traditional cultural gesture features include: the aspect ratio between the distance between the nose and neck and the distance between the shoulders of the human body;

and judging whether the values of the traditional culture gesture characteristics meet the corresponding preset conditions or not, wherein the judgment comprises the following steps:

and judging whether the aspect ratio between the nose neck distance and the double shoulder distance is smaller than or equal to a preset judgment threshold value of the ratio between the nose neck distance and the double shoulder distance so as to determine whether the current user performs head lowering.

2. The intelligent recognition method of traditionally cultural gestures according to claim 1, characterized in that the traditionally cultural gesture features further comprise: an aspect ratio between a wrist distance and an elbow distance, an angle between two wrist vectors and an x-axis unit vector in the coordinate system, an angle between two elbow vectors and an x-axis unit vector in the coordinate system, an inner product between a direction vector of a right elbow to a right wrist and a y-axis unit vector in the coordinate system, and an inner product between a direction vector of a left elbow to a left wrist and a y-axis unit vector in the coordinate system;

wherein, the wrist is apart from being the distance between left wrist and the right wrist, the elbow is apart from being the distance between left elbow and the right elbow, two wrist vectors are the direction vector of right wrist to left wrist, two elbow vectors are the direction vector of right elbow to left elbow.

3. The intelligent recognition method of the cultural tradition gesture according to claim 2, wherein the determining whether the value of each cultural tradition gesture feature satisfies a corresponding preset condition further comprises:

judging whether the aspect ratio between the wrist distance and the elbow distance is smaller than or equal to a preset judgment threshold value of the distance ratio between the double wrists and the double elbows or not so as to determine whether the current user makes the action of closing the two hands and separating the elbows outwards;

judging whether an included angle between the two wrist vectors and an x-axis unit vector in the coordinate system is smaller than or equal to a preset threshold value of included angles between double wrists and a horizontal line or not, and judging whether an included angle between the two elbow vectors and the x-axis unit vector in the coordinate system is smaller than or equal to a preset threshold value of included angles between double elbows and a horizontal line or not, so as to determine whether the current user performs a boxing holding salute action with horizontally symmetrical double hand positions or not;

judging whether the inner product between the direction vector from the right elbow to the right wrist and the y-axis unit vector in the coordinate system is greater than 0, and judging whether the inner product between the direction vector from the left elbow to the left wrist and the y-axis unit vector in the coordinate system is greater than 0, so as to determine whether the current user makes an action with a wrist position higher than the elbow position.

4. An intelligent interaction method for traditional culture gestures is characterized by comprising the following steps:

if the method for intelligently recognizing the traditionally-cultural gesture according to any one of claims 1 to 3 is applied to determine that the current user makes the corresponding traditionally-cultural gesture, whether the number of times that the user makes the traditionally-cultural gesture within a preset recognition period exceeds a preset value is judged, and if so, a preset interaction event corresponding to the traditionally-cultural gesture is triggered.

5. The intelligent interaction method of the traditionally-cultural gesture, as recited in claim 4, wherein the triggering of the preset interaction event corresponding to the traditionally-cultural gesture comprises:

sending a playing instruction to corresponding multimedia equipment so that the multimedia equipment plays pre-stored video content or music content according to the playing instruction;

and/or the presence of a gas in the gas,

and sending a starting instruction to the corresponding lighting system so that the lighting system controls the lamps in the corresponding area to be lightened or flash according to the starting instruction.

6. An intelligent recognition device for traditional culture gestures, comprising:

the video data acquisition module is used for acquiring a video image of a current user in a target acquisition area and establishing a coordinate system corresponding to the current user based on position information of the user in the video image;

the human skeleton key point identification module is used for identifying the corresponding human skeleton key point coordinates of the current user according to the coordinate system;

the traditional culture gesture interactive behavior recognition module is used for applying the coordinates of human skeleton key points of a current user, determining values of all preset traditional culture gesture characteristics, judging whether the values of all traditional culture gesture characteristics meet respective corresponding preset conditions, if so, judging that the current user simultaneously makes a head lowering action, a hand folding action with hands separated outwards from elbows, a boxed fortune with horizontally symmetrical hand positions and a corresponding action with a wrist position higher than the elbow position, and determining that the current user is making or has made a traditional culture gesture;

the traditional cultural gesture features include: the aspect ratio between the distance between the nose and neck and the distance between the shoulders of the human body; the traditional culture gesture interaction behavior recognition module judges whether the values of the traditional culture gesture characteristics meet the corresponding preset conditions, and is specifically used for:

and judging whether the aspect ratio between the nose neck distance and the double shoulder distance is smaller than or equal to a preset judgment threshold value of the ratio between the nose neck distance and the double shoulder distance so as to determine whether the current user performs head lowering.

7. An intelligent interaction device for traditional cultural gestures, comprising:

a traditional culture gesture interaction event triggering module, configured to determine whether the number of times that the user makes the traditional culture gesture within a preset recognition period exceeds a preset value if it is determined that the current user makes the corresponding traditional culture gesture by applying the intelligent recognition method for traditional culture gesture according to any one of claims 1 to 3, and if so, trigger a preset interaction event corresponding to the traditional culture gesture.

8. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor, when executing the program, carries out the steps of the method for intelligent recognition of traditionally cultural gestures as claimed in any one of claims 1 to 3 or the steps of the method for intelligent interaction of traditionally cultural gestures as claimed in claim 4 or 5.

9. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method for intelligent recognition of a traditionally cultural gesture according to any one of claims 1 to 3, or the steps of the method for intelligent interaction of a traditionally cultural gesture according to claim 4 or 5.

Images