KR20230087865A - System for controlling avatar using artificial intelligence hand position recognition - Google Patents

Abstract

The present invention includes an image processing module that senses a user's hand motion and generates user's hand motion data; an avatar operation module for operating an avatar created in advance according to a control signal received from the outside; and a processor that generates motion information of an avatar corresponding to motion data of the user's hand and operates the avatar based on the generated motion information of the avatar. , Since avatar control commands can be generated from still images with simple calculations without performing heavy artificial intelligence calculations such as the existing LSTM (Long Short Term Memory) deep learning method, it is possible to provide an avatar controller using hand position recognition. It works.

Description

Avatar control system using artificial intelligence hand position recognition {SYSTEM FOR CONTROLLING AVATAR USING ARTIFICIAL INTELLIGENCE HAND POSITION RECOGNITION}

The present invention relates to an avatar control system using artificial intelligence hand position recognition.

Recently, as augmented reality technology develops, technologies for converging the real world and the virtual world are being developed. For example, a virtual education system, a screen golf system, and a virtual experience simulation system will be representative examples thereof.

These virtual systems are configured to control the corresponding content in response to a motion when a user makes a motion in a state in which a content image is output using a display device such as a touch board.

These virtual systems can recognize hands or faces by using a tool called mediapipe. In addition, these tools can recognize the joints of the knuckles and the whole hand.

However, although it is easy to grasp the position of the hand in a still image, there is a limit to recognizing motion only with the position of the hand, so posture estimation is sometimes performed using artificial intelligence techniques such as LSTM.

However, performing pose estimation calculation in real time in a situation where more than 60 frames per second are displayed on the screen has a problem in that the load on the system is high.

Registered Patent Publication No. 10-1189633 (Public date: 2012. 10. 10)

An object of the embodiments of the present invention to improve the above problems is an artificial intelligence hand capable of generating an avatar control command with simple calculation from a still image without performing heavy artificial intelligence calculation such as the existing LSTM (Long Short Term Memory) method To provide an avatar control system using location recognition.

In order to achieve the above object, an avatar control system using artificial intelligence hand position recognition according to an embodiment of the present invention includes an image processing module that detects a user's hand motion and generates user's hand motion data; an avatar operation module for operating an avatar created in advance according to a control signal received from the outside; and a processor generating motion information of the avatar corresponding to the user's hand motion data and operating the avatar based on the generated motion information of the avatar.

The image processing module may include: an image generator for capturing a user and generating image frames divided into X-axis (left and right sides of the screen), Y-axis (upper and lower sides of the screen), and Z-axis (depth of the screen); a hand position generating unit generating coordinate values corresponding to the position of the user's hand in the image frame; and a motion data generating unit that calculates a movement direction of the coordinate values and generates preset hand motion data of the user based on the movement direction of the calculated coordinate values.

The motion data generation unit calculates the movement direction using the coordinate values of the user's left hand, right hand, or both the left and right hands, and when only the user's left hand moves left and right, the user's motion on the X axis corresponding to the left and right movement information. When only the user's right hand is moved up and down, the user's motion data for the Z axis corresponding to the up and down movement information is generated, and when the user's left and right hands are moved up and down in a gathered state, up and down It is characterized in that the user's motion data for the Y-axis corresponding to the movement information is generated.

The motion data generator may determine that the user's left and right hands are in a closed state when the distance between the user's left and right hands is smaller than the size of an object representing the user's hands.

The motion data generating unit may generate motion data of the user indicating a stop motion when the user's left and right hands are moved to a preset area in a closed state.

An avatar control system using artificial intelligence hand position recognition according to an embodiment of the present invention is able to perform avatar control commands with simple calculations in still images without performing heavy artificial intelligence calculations such as the existing LSTM (Long Short Term Memory) deep learning method. Since it can be created, it is possible to provide an avatar controller using hand position recognition.

1 is a block diagram schematically showing an avatar control system using artificial intelligence hand position recognition according to an embodiment of the present invention.
FIG. 2 is a diagram showing the configuration of a region for motion recognition in the image generator of the image processing module of FIG. 1 .
FIG. 3 is a diagram for explaining an algorithm for determining whether a user's two hands make vowels in the motion data generation unit of the image processing module of FIG. 1 .
FIG. 4 is a diagram for defining user's hand motion data in the motion data generation unit of the image processing module of FIG. 1 .
5A to 5D are diagrams illustrating examples of generating motion data of a user's hand in the motion data generation unit of the image processing module of FIG. 1 .
6 is a flowchart illustrating the operation of an avatar control system using artificial intelligence hand position recognition according to an embodiment of the present invention.

The present invention as described above will be described in detail through the accompanying drawings and embodiments.

It should be noted that technical terms used in the present invention are only used to describe specific embodiments and are not intended to limit the present invention. In addition, technical terms used in the present invention should be interpreted in terms commonly understood by those of ordinary skill in the art to which the present invention belongs, unless specifically defined otherwise in the present invention, and are excessively inclusive. It should not be interpreted in a positive sense or in an excessively reduced sense. In addition, when the technical terms used in the present invention are incorrect technical terms that do not accurately express the spirit of the present invention, they should be replaced with technical terms that those skilled in the art can correctly understand. In addition, general terms used in the present invention should be interpreted as defined in advance or according to context, and should not be interpreted in an excessively reduced sense.

Also, singular expressions used in the present invention include plural expressions unless the context clearly dictates otherwise. In the present invention, terms such as "consisting of" or "comprising" should not be construed as necessarily including all of the various elements or steps described in the invention, and some of the elements or steps are included. It should be construed that it may not be, or may further include additional components or steps.

In addition, terms including ordinal numbers such as first and second used in the present invention may be used to describe components, but components should not be limited by the terms. Terms are used only to distinguish one component from another. For example, a first element may be termed a second element, and similarly, a second element may be termed a first element, without departing from the scope of the present invention.

Hereinafter, a preferred embodiment according to the present invention will be described in detail with reference to the accompanying drawings, but the same or similar components are assigned the same reference numerals regardless of reference numerals, and redundant description thereof will be omitted.

In addition, in describing the present invention, if it is determined that a detailed description of a related known technology may obscure the gist of the present invention, the detailed description will be omitted. In addition, it should be noted that the accompanying drawings are only for easily understanding the spirit of the present invention, and should not be construed as limiting the spirit of the present invention by the accompanying drawings.

1 is a block diagram schematically illustrating an avatar control system using artificial intelligence hand position recognition according to an embodiment of the present invention, and FIG. 2 is a region for motion recognition in an image generator of an image processing module of FIG. 1 3 is a diagram for explaining an algorithm for determining whether the user's two hands make vowels in the motion data generation unit of the image processing module of FIG. 1, and FIG. 4 is a diagram of the image processing module of FIG. 5A to 5D are diagrams for defining motion data of a user's hand in a motion data generation unit, and FIGS. It is a flowchart showing the operation of the avatar control system using artificial intelligence hand position recognition according to an embodiment of the present invention.

As shown in FIG. 1, an avatar control system using artificial intelligence hand position recognition according to an embodiment of the present invention is a system capable of generating an avatar control command from a still image by simple calculation, and for this purpose, an image processing module ( 10), an avatar operation module 20 and a processor 30.

Although not shown, the avatar control system using artificial intelligence hand position recognition according to an embodiment of the present invention may further include an avatar creation module and an output module.

The avatar generation module generates an avatar of a user in a virtual reality environment. In this specification, an avatar (avatar) means a virtual character that can be controlled according to a user's command in virtual reality implemented as a virtual space by computer programming rather than actual reality. The appearance of the avatar may be a human shape having a similar appearance to the user in order to improve the user's sense of immersion and provide smooth bio-feedback, but is not limited to a specific shape.

In one embodiment, an avatar may be automatically generated based on the user's hand motion data. For example, a motion change of a user's hand may be detected in a still image, and an avatar's posture or motion may be changed accordingly. In this way, appropriately changing the shape or attitude of the avatar in the virtual environment according to the user's hand motion data can improve the sense of presence and immersion in virtual reality.

As will be described later, the avatar created in the virtual reality environment performs an operation corresponding to a command determined based on user's hand motion data. Using this, the user can control the virtual reality avatar to perform a specific motion by sending a control signal corresponding to the hand motion data even if the user does not actually perform the motion, and can perform an evaluation protocol or training protocol provided by the program. there is.

The output module is an output device such as a TV, monitor, or HMD for outputting in real time an image of an avatar performing an action. In one embodiment, the output module is a light emitting diode (LED), an organic light emitting device (OLED), a light emitting polymer (LEP), an electroluminescent device (EL), a field emission device (FED), or a polymer light emitting device (PLED). It can be composed of a display to which this is applied.

In addition, the output module may be configured as a Head Mounted Display (HMD) device that can be worn on the head. The HMD device is a next-generation display device that can be worn on a user's head and view a screen through a display corresponding to both eyes. In general, the user's head movement can be synchronized through the rotation value including the IMU sensor. Through this, the user can feel a greater sense of immersion than viewing with a conventional monitor device in an augmented reality or virtual reality environment.

The image processing module 10 is a device that detects a user's hand motion and generates user's hand motion data, and includes an image generator 11, a hand position generator 12, and a motion data generator 13. do.

The image generating unit 11 may use a conventional camera, and as shown in FIG. 2, it is a device for generating an image frame based on a still image by photographing a user, and includes X-axis (left and right sides of the screen), Y It is a device that creates image frames divided into axes (top and bottom of the screen) and Z-axis (depth of the screen).

The hand position generating unit 12 is a device that generates coordinate values corresponding to the position of the user's hand among the image frames generated by the image generating unit 11 . Specifically, the hand position generating unit 12 captures an image of the user's hand from among image frames composed of still images, and generates coordinate values (ie, hand coordinates) corresponding to the motion of the hand. At this time, the coordinates of the hand include a finger joint and a wrist joint, so that the overall size of the hand and the length of the fingers can be checked. In addition, the hand position generating unit 12 generates coordinate values by tracking the movement of the hand by tracking the movement of the fingertip and each joint point.

The hand position generation unit 12 is based on a pre-processing unit (not shown) defining a connection relationship between image frames transmitted from the image generation unit 11 and learning information pre-learned from pre-processed image frames. A hand recognizing unit (not shown) recognizing a hand, adjusting coordinates for the recognized hand, and calculating movement coordinates of the hand from displacement between image frames based on previously learned learning information ( not shown).

Here, in recognizing the hand, it is preferable to first perform hand learning, store the learned result, and recognize the hand from the stored learning information. On the other hand, along with the recognition of the hand, learning and recognition of the head, torso, arms, legs, etc. are also performed, and through these recognition, it can be used to accurately determine the position of the hand.

In the hand position generating unit 12 configured as described above, in recognizing the hand and calculating the coordinates, the presence or absence of the hand is checked at a previously predicted position using an estimation technique for estimating motion. In each image frame, the hand is estimated and searched through the hand motion estimation method, and the movement coordinates of the searched hand are calculated. That is, motion estimation is performed by extracting a motion vector component of the hand from the previous image frame and a motion vector component of the hand from the current image frame, and thus the position of the hand in the next image frame can be estimated. In addition, this estimation is made by pre-learned learning information. If a hand does not exist at the estimated location, a radius is set around the estimated location, and a hand search is performed within the radius. If the arm is searched at this time, the position of the hand is more easily estimated based on the structure of the human body.

The motion data generation unit 13 calculates the movement direction of the coordinate values generated by the hand position generation unit 12, and generates preset user's hand motion data based on the movement direction of the calculated coordinate values. am.

The motion data generation unit 13 receives the coordinate values generated by the hand position generation unit 12 and processes changes such as the movement position, and also generates an event (control) from the movement position change, The hand shape is recognized from the coordinates and the user's hand motion data is generated.

That is, the motion data generating unit 13 receives the coordinate values generated by the hand position generating unit 12, processes them through the processor 30, and processes the coordinate values corresponding to the user's command (i.e., the avatar control signal). determine the hand motion data of Related information, such as an analysis algorithm or a lookup table, necessary for determining a command may be stored in a memory together with a hand position-based control program.

Also, the motion data generator 13 performs frequency filtering on the avatar control signal through the processor 30 . A low-pass filter can be used to remove high-frequency noise, a band-pass filter can be used to select a specific frequency range, or a specific frequency range can be removed. A bandstop filter may be used.

The motion data generator 13 extracts a feature vector based on data power calculated by including a log value and a variance value for a corresponding frequency of the filtered signal. For example, the processor 30 may quantitatively analyze the proportion occupied by a signal component of a specific frequency on signal data based on Fast Fourier Transform (FFT).

In addition, by applying a signal processing function to the avatar control signal, the feature vector can be extracted by calculating the mean, deviation, root mean square (RMS), skewness, kurtosis, and dominant frequency (DF). It is used to determine the corresponding user's command.

Meanwhile, the motion data generation unit 13 may generate a plurality of classifiers through a classifier generation module when preprocessing of the avatar control signal is completed. The processor 30 may generate a classifier based on a plurality of classification algorithms. A plurality of classifiers classify the user's hand motion data and determine whether the data corresponds to a specific class.

Based on this, the motion data generating unit 13 selects an operation corresponding to the real-time user's hand motion data among a plurality of operations and finally determines a user's command. Specifically, the processor 30 may calculate each motion of the input real-time user's hand motion data as an output value such as probability or score based on the classifier, and the processor 30 may calculate the value having the highest probability or score. You can determine the command by selecting an action with .

According to embodiments, various types of commands may be stored in advance to correspond to user's hand motion data. For example, a command such as sitting/standing, or a joint-related movement such as lifting a foot up and down, bending or extending a knee, in addition to a command for simply moving an avatar in front, back, left, and right may be designated as a command. According to the present invention, various kinds of hand position signals of a user can be obtained simultaneously, and various and natural types of motions can be implemented in virtual reality by matching them with detailed motion commands. The signal processing algorithm for recognizing the user's intention for each command and reducing the malfunction rate is as described above.

To explain again, as shown in FIG. 4, the motion data generator 13 defines the user's operation command according to the user's hand position, and the user's left hand (L), right hand (R), or left hand ( L) and the right hand (R) coordinate values are used to calculate the movement direction.

In detail, the motion data generating unit 13 defines the coordinate axis movement direction as follows.

X-axis : the direction of moving left and right on the screen, + when going to the right

Y-axis : the direction of movement up and down on the screen, + when up

Z-axis : the direction of movement to the depth of the screen, + when it comes to the direction of the viewer

X-axis direction control

Adjust by moving your left hand left and right (if your left hand is at -X, move to the left, and if your left hand is at +X, move to the right)

Y-axis direction control

Adjust by moving your hands up and down with your hands together (move up when both hands are on +Y, move down when they are on -Y).

Z-axis direction control

Adjust by moving your right hand up and down (when the right hand is positioned at +Z, it moves to the front of the screen, and when it is positioned at -Z, it moves to the back of the screen).

stop motion

If you move to the stop zone with your hands together, you will stop.

As shown in FIG. 5A , the motion data generation unit 13 generates motion data of the user on the X axis corresponding to left and right movement information when only the user's left hand is moved left and right.

Also, as shown in FIG. 5B , when only the user's right hand moves up and down, the motion data generation unit 13 generates motion data of the user on the Z axis corresponding to the up and down movement information.

In addition, as shown in FIG. 5C, when the user's left and right hands move up and down in a closed state, the motion data generation unit 13 generates motion data of the user on the Y axis corresponding to up and down movement information. generate

Meanwhile, the motion data generator 13 determines that the user's left and right hands are in a closed state when the distance between the user's left and right hands is smaller than the size of the object representing the user's hands. That is, as shown in FIG. 3 and Equation 1, the motion data generator 13 determines that the two hands are brought together when the distance d between the two hands is smaller than the size (2 * r) of the object representing the hand. do.

[Equation 1]

d < 2*r

As shown in FIG. 5D, the motion data generation unit 13 generates motion data of the user indicating a stop operation when the user's left and right hands are moved to a preset area (stop) in a closed state. .

The avatar operation module 20 is a device that operates an avatar created in advance according to a control signal received from the outside. That is, the avatar operation module 20 operates the avatar generated by the avatar generation module based on the control signal received from the processor 30 and outputs the avatar through the output module.

The avatar operation module 20 receives a command determined by the processor 30 and controls the avatar to perform an operation corresponding to the command through the processor 30 . The user's motion intention is converted into a state and determined as a command. (e.g. left and right, back and forth, up and down, etc.)

Meanwhile, the size of rotation and the speed of operation may be different even in the same operation, and may be adjusted according to the amplitude of the control signal in addition to the state of the command. For example, if a control signal having a specific frequency is sensed and the signal of the corresponding frequency and part matches the command to “move forward” the avatar, the avatar operation module 20 controls the avatar to move forward. At this time, as the amplitude of the control signal increases, the avatar advances at a faster speed, and as the amplitude decreases, the avatar advances more slowly.

The processor 30 generates avatar motion information corresponding to the user's hand motion data generated by the image processing module 10, and operates the avatar through the avatar motion module based on the generated motion information of the avatar. let it

As shown in FIG. 6, the avatar control system using artificial intelligence hand position recognition according to an embodiment of the present invention configured as described above generates a hand position of a user's image frame captured by the image generator 11. By capturing through the unit 12, coordinate values corresponding to the position of the hand are recognized (S10).

Then, after calculating the distance between both hands through the motion data generation unit 12 (S20), if it is determined as one hand, the position of the left and right hand is calculated (S30), and if it is determined that the left and right movement is performed, the processor 30 ), the avatar is moved left and right (S31), and if it is determined that the avatar is moved forward and backward, the avatar is moved forward and backward through the processor 30 (S32).

In addition, after calculating the distance between both hands through the motion data generation unit 12 (S20), if it is determined that the two hands are the same, the position of the up and down hands is calculated (S40), and if it is determined that the movement is up and down, the avatar through the processor 30 Moves up and down (S41).

According to the avatar control system using artificial intelligence hand position recognition according to an embodiment of the present invention configured as described above, it is possible to perform simple AI calculations in still images without performing heavy artificial intelligence calculations such as the existing LSTM (Long Short Term Memory) deep learning method. Since avatar control commands can be generated by calculation, it is possible to provide an avatar controller using hand position recognition.

Meanwhile, an antifouling coating layer made of an antifouling coating composition may be applied to the surface of the image processing module 10 to effectively prevent adhesion and removal of contaminants.

The antifouling coating composition contains sodium sesquicarbonate and butyl carbitol in a molar ratio of 1:0.01 to 1:2, and the total content of sodium sesquicarbonate and butyl carbitol is 1 to 10% by weight based on the total aqueous solution. .

The molar ratio of the sodium sesquicarbonate and butyl carbitol is preferably 1:0.01 to 1:2. If the molar ratio is out of the above range, the coating property of the antifouling coating layer is lowered or the moisture adsorption on the surface increases after coating. There is a problem that the coating film is removed.

The sodium sesquicarbonate and butyl carbitol are preferably 1 to 10% by weight of the total aqueous solution of the composition. If the content is less than 1% by weight, the coating property of the antifouling coating layer is reduced, and if it exceeds 10% by weight, the coating film Crystallization is likely to occur due to an increase in thickness.

On the other hand, as a method of applying the composition for antifouling coating on the surface of the image processing module 10, it is preferable to apply it by a spray method. In addition, the final coating film thickness on the surface of the image processing module 10 is preferably 700 to 2500 Å, more preferably 900 to 2000 Å. If the thickness of the coating film is less than 700 Å, there is a problem of deterioration in the case of high-temperature heat treatment, and if it exceeds 2500 Å, there is a disadvantage in that crystallization of the coated surface is easy to occur.

In addition, this antifouling coating composition can be prepared by adding 0.1 mole of sodium sesquicarbonate and 0.05 mole of butyl carbitol to 1000 ml of distilled water and then stirring.

The reason why the ratio of the constituent components and the thickness of the coating film were numerically limited as described above was that the present inventors showed the optimal antifouling coating effect at the ratio as a result of analyzing the test results while repeating several failures.

A coating agent for heat dissipation is applied to the surface of the processor 30 to prevent the surface of the processor 30 from being excessively heated because heat emitted from the processor 30 is not sufficiently dissipated, and the heat can be effectively released.

This coating composition for heat dissipation contains 58% by weight of potassium silicate, 11% by weight of chromium oxide, 13% by weight of graphite, 8% by weight of silicon nitride, 3% by weight of sodium hydroxide (NaOH), 3% by weight of titanium oxide, 2% by weight of polyamide wax, It consists of 2% by weight of 3-aminopropyl trimethoxysilane.

Potassium silicate acts as a binder resin, chromium oxide acts as a wear resistance, graphite has excellent thermal conductivity and electrical properties, silicon nitride improves strength and prevents cracking, sodium hydroxide acts as a dispersant, and titanium oxide acts as a weather resistance. For this purpose, polyamide wax serves as an anti-settling function, and 3-aminopropyl trimethoxysilane serves as an adhesion enhancer.

The reason for limiting the constituent materials and components and limiting the numerical values of the mixing ratios as described above is that, as a result of the present inventors' analysis through test results while repeating several failures, the optimal effect in the constituent components and numerically limited ratios was obtained. showed up

The surface of the avatar operation module 20 may be coated with a fragrance material for the environment mixed with a functional oil that helps in sterilizing function and relieving user's stress.

The mixing ratio of the fragrance material and the functional oil is 95 to 97% by weight of the fragrance material and 3 to 5% by weight of the functional oil, and the functional oil is 50% by weight of Angelica oil and Citronella oil. ) 50% by weight.

Here, the functional oil is preferably mixed in an amount of 3 to 5% by weight based on the fragrance material. If the mixing ratio of the functional oil is less than 3% by weight, the effect is insignificant, and if the mixing ratio of the functional oil exceeds 3 to 5% by weight, the effect is not greatly improved, but economical efficiency is poor. Angelica oil has a good effect on stress relief, tension relief, and sterilization, and citronella oil psychologically purifies and uplifts the mind, and has excellent effects on headaches, depression, and neuralgia. Therefore, as the fragrance material mixed with such functional oil is coated on the surface of the avatar operation module 20, effects such as sterilizing the surface of the avatar operation module 20 and reducing the stress of the user can be obtained. .

The reason for limiting the components and limiting the numerical value of the mixing ratio for the environmental fragrance material and functional oil is that the present inventors have repeatedly failed several times and analyzed the test results to find that the above components and numerically limited ratio are optimal showed the effect of

Meanwhile, a rubber vibration absorbing unit may be further installed at the lower end of the image processing module 10 .

The vibration absorbing part may be made of a rubber material, and the raw material content of the vibration absorbing part is 60% by weight of rubber, 8% by weight of dibutylthiourea, 6% by weight of calcium stearate, 19% by weight of carbon black, 3C (N- 3% by weight of PHENYL-N'-ISOPROPYL-P-PHENYLENEDIAMINE) and 4% by weight of organic peroxide were mixed.

Dibutylthiourea is added to improve vulcanization acceleration, calcium stearate is added to act as a softener, and carbon black is added to increase or improve wear resistance, thermal conductivity, and the like.

3C (N-PHENYL-N'-ISOPROPYL-P-PHENYLENEDIAMINE) is added as an antioxidant, and organic peroxide is added to act as an accelerator.

Therefore, in the present invention, since elasticity, toughness, and rigidity of the vibration absorbing part are increased, durability is improved, and thus the life of the vibration absorbing part is increased.

The tensile strength of the rubber material is formed at 155Kg/㎠.

The reason for limiting the components and components of the rubber material and limiting the numerical values of the mixing ratio is that, as a result of the inventor's analysis through test results while repeating several failures, the optimal effect in the constituent components and numerically limited ratios showed up

In the above, preferred embodiments according to the present invention have been shown and described. However, the present invention is not limited to the above-described embodiments, and various modifications can be made by anyone having ordinary knowledge in the technical field to which the present invention belongs without departing from the gist of the present invention appended within the scope of the claims. .

10: image processing module 11: image generator
12: hand position generation unit 13: motion data generation unit
20: avatar motion module 30: processor

Claims (5)

an image processing module that detects a user's hand motion and generates user's hand motion data;
an avatar operation module for operating an avatar created in advance according to a control signal received from the outside; and
Avatar control system using artificial intelligence hand position recognition, characterized in that it comprises a processor for generating motion information of the avatar corresponding to the user's hand motion data and operating the avatar based on the generated motion information of the avatar. .
According to claim 1,
The image processing module,
an image generation unit that captures a user and generates image frames divided into X-axis (left and right sides of the screen), Y-axis (top and bottom of the screen), and Z-axis (depth of the screen);
a hand position generating unit generating coordinate values corresponding to the position of the user's hand in the image frame; and
Avatar control using artificial intelligence hand position recognition, characterized in that it comprises a motion data generation unit that calculates the movement direction of the coordinate value and generates preset user's hand motion data based on the movement direction of the calculated coordinate value. system.
According to claim 2,
The motion data generator
The movement direction is calculated using the coordinate values of the user's left hand, right hand, or left and right hands,
When only the user's left hand is moved left and right, the user's motion data for the X axis corresponding to the left and right movement information is generated;
When only the user's right hand is moved up and down, the user's motion data for the Z axis corresponding to the up and down movement information is generated;
An avatar control system using artificial intelligence hand position recognition, characterized in that when the user's left and right hands move up and down in a gathered state, the user's motion data for the Y axis corresponding to the up and down movement information is generated.
According to claim 3,
The motion data generator
Avatar control system using artificial intelligence hand position recognition, characterized in that if the distance between the user's left and right hands is smaller than the size of the object representing the user's hand, it is determined that the user's left and right hands are in a gathered state.
According to claim 3,
The motion data generator
An avatar control system using artificial intelligence hand position recognition, characterized in that when the user's left and right hands are moved to a preset area in a gathered state, the user's motion data indicating a stop motion is generated.

Images