KR20210150862A - Method, system and non-transitory computer-readable recording medium for recognizing a gesture - Google Patents

Abstract

According to one aspect of the present invention, provided is a method for recognizing gestures. The method includes the steps of: providing a guide message to a target user; determining whether a head gesture performed by the target user is a valid gesture by referring to the direction in which the face and/or the gaze of the target user is oriented and the direction or the position associated with the guide message; and determining the intention of the target user by referring to the target user's head gesture determined to be the valid gesture. Accordingly, the present invention can easily and accurately inform a criterion for determining that the head gesture of the target user is a valid gesture.

Description

A method for recognizing a gesture, a system and a non-transitory computer-readable recording medium

The present invention relates to a method, system, and non-transitory computer-readable recording medium for recognizing a gesture.

In recent years, technologies for controlling objects or executing commands by recognizing a user's gesture in various usage environments such as mobile devices, tablets, laptops, PCs, home appliances, and automobiles have been introduced.

In this regard, as an example of the prior art, the technology disclosed in Korean Patent Application Laid-Open No. 2015-138831 may be exemplified. A sensor for detecting a gesture of a user carrying a portable device, identifying the detected gesture, and A control unit for determining an external device corresponding to the gesture based on the identified gesture, determining a command for controlling the determined external device, and a communication unit for transmitting a command signal corresponding to the command to the external device, Before performing a gesture corresponding to a specific command, a trigger signal or an activation signal is executed to start recognition of the user's gesture command, and the trigger signal includes a touch or tap on the touch screen of the smart watch or a portable device that includes a specific gesture. The device has been introduced.

However, according to the techniques introduced so far, including the prior art as described above, only one single criterion, that is, a preset criterion, is used as a method of triggering gesture recognition or starting and ending gesture recognition, and this criterion is dynamically applied. There is no interest in the technology that makes it different. In other words, without considering the user's situation or the properties of the object to be controlled, preset conditions must be satisfied in order to trigger gesture recognition, so there is a problem that a cumbersome or difficult to trigger situation often occurs in terms of user experience. .

Accordingly, the present inventor(s) proposes that the head gesture performed by the target user is a valid gesture with reference to the direction or location determined according to the direction or the position to which at least one of the target user's face and gaze is directed and the guide message provided to the target user. By allowing recognition to be determined, we propose a novel and advanced technology capable of quickly, accurately and efficiently performing gesture recognition.

An object of the present invention is to solve all the problems of the prior art described above.

Another object of the present invention is to dynamically change a criterion for determining that a head gesture of a target user is a valid gesture according to a guide message.

Another object of the present invention is to provide a guide message through a message delivery device associated with a target user to easily and accurately inform a criterion for determining a head gesture of a target user as a valid gesture.

A representative configuration of the present invention for achieving the above object is as follows.

According to an aspect of the present invention, there is provided a method for recognizing a gesture, comprising: providing a guide message to a target user; referring to a direction to which at least one of the target user's face and gaze is directed and a direction or location associated with the guide message to determine whether the head gesture performed by the target user is a valid gesture, and determining the intention of the target user by referring to the head gesture of the target user determined to be the valid gesture. this is provided

According to another aspect of the present invention, there is provided a system for recognizing a gesture, a guide message management unit providing a guide message to a target user, a direction to which at least one of a face and a gaze of the target user is directed, and a direction or position associated with the guide message A valid gesture management unit that determines whether the head gesture performed by the target user is a valid gesture with reference to, and a user who determines the intention of the target user by referring to the target user's head gesture determined to be a valid gesture A system is provided that includes an intent management unit.

In addition to this, another method for implementing the present invention, another system, and a non-transitory computer-readable recording medium for recording a computer program for executing the method are further provided.

According to the present invention, a criterion for determining that a head gesture of a target user is a valid gesture according to a guide message can be dynamically changed.

In addition, according to the present invention, by providing the guide message through the message delivery device associated with the target user, it is possible to easily and accurately inform the criteria for determining the head gesture of the target user as a valid gesture.

1 is a diagram illustrating in detail the internal configuration of a gesture recognition system according to an embodiment of the present invention.
2 is a diagram exemplarily illustrating a situation in which a message delivery device is specified according to an embodiment of the present invention.
3 to 11 are diagrams exemplarily illustrating a process of recognizing a gesture according to an embodiment of the present invention.

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS [0012] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS [0010] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS [0010] Reference is made to the accompanying drawings, which show by way of illustration specific embodiments in which the present invention may be practiced. These embodiments are described in sufficient detail to enable those skilled in the art to practice the present invention. It should be understood that the various embodiments of the present invention are different but need not be mutually exclusive. For example, certain shapes, structures, and characteristics described herein may be implemented with changes from one embodiment to another without departing from the spirit and scope of the present invention. In addition, it should be understood that the location or arrangement of individual components within each embodiment may be changed without departing from the spirit and scope of the present invention. Accordingly, the following detailed description is not to be taken in a limiting sense, and the scope of the present invention should be taken as encompassing the scope of the claims and all equivalents thereto. In the drawings, like reference numerals refer to the same or similar elements throughout the various aspects.

Hereinafter, various preferred embodiments of the present invention will be described in detail with reference to the accompanying drawings in order to enable those of ordinary skill in the art to easily practice the present invention.

Whole system configuration

The entire system according to an embodiment of the present invention may be configured to include a communication network, the gesture recognition system 100, and a message delivery device.

First, the communication network according to an embodiment of the present invention may be configured regardless of communication aspects such as wired communication or wireless communication, and includes a local area network (LAN), a metropolitan area network (MAN), and a wide area. It may be composed of various communication networks, such as a wide area network (WAN). Preferably, the communication network referred to in this specification may be a well-known Internet or World Wide Web (WWW). However, the communication network is not necessarily limited thereto, and may include a known wired/wireless data communication network, a known telephone network, or a known wired/wireless television communication network in at least a part thereof.

For example, the communication network is a wireless data communication network, and includes radio frequency (RF) communication, Wi-Fi communication, cellular (LTE, etc.) communication, and Bluetooth communication (more specifically, Bluetooth Low Energy (BLE) communication). )), infrared communication, ultrasonic communication, etc. may be implemented in at least a part thereof.

Next, the gesture recognition system 100 according to an embodiment of the present invention may be a digital device having a memory means and a microprocessor mounted therein to have arithmetic capability. The gesture recognition system 100 may be a server system.

According to an embodiment of the present invention, the gesture recognition system 100 may be connected to each other through a message delivery device and a communication network or a predetermined processor (not shown) to be described later, and provides a guide message to a target user, and Determine whether a head gesture performed by the target user is a valid gesture with reference to a direction or location associated with a direction or a guide message and a direction toward which at least one of the user's face and gaze is directed, and the target user's head determined to be a valid gesture A function of determining the intention of the target user may be performed by referring to the gesture.

Here, the guide message according to an embodiment of the present invention may be a message in the form of at least one of sight, hearing, or smell provided to the target user through the message delivery device, for example, a visual message such as text or image , may include an audio message such as a voice, or an audiovisual message such as a video, and these messages may be provided in various implementation methods such as pop-up, banner, and floating.

The configuration and function of the gesture recognition system 100 according to the present invention will be described in more detail below. On the other hand, although described above with respect to the gesture recognition system 100, this description is exemplary, and at least some of the functions or components required for the gesture recognition system 100 may be provided by an external device (eg, a message It will be apparent to those skilled in the art that it may be implemented in a delivery device, etc.) or an external system (eg, a cloud server, etc.) or included in an external device or external system.

Next, the message delivery device (not shown) according to an embodiment of the present invention may communicate with the gesture recognition system 100 through a communication network or a predetermined processor, and may perform a function of outputting a guide message. have. For example, the message delivery device according to an embodiment of the present invention may include various types of devices such as a display capable of outputting a visual or auditory message, a speaker, and the like.

Composition of Gesture Recognition System

Hereinafter, the internal configuration of the gesture recognition system 100 that performs an important function for the implementation of the present invention and the function of each component will be described.

1 is a diagram illustrating in detail the internal configuration of a gesture recognition system 100 according to an embodiment of the present invention.

As shown in FIG. 1 , the gesture recognition system 100 includes a guide message management unit 110 , a valid gesture management unit 120 , a user intention management unit 130 , a communication unit 140 , and a control unit 150 . can be According to an embodiment of the present invention, at least some of the guide message management unit 110 , the effective gesture management unit 120 , the user intention management unit 130 , the communication unit 140 , and the control unit 150 communicate with an external system. It may be a program module that does Such a program module may be included in the gesture recognition system 100 in the form of an operating system, an application program module, or other program modules, and may be physically stored in various known storage devices. In addition, such a program module may be stored in a remote storage device capable of communicating with the gesture recognition system 100 . Meanwhile, such a program module includes, but is not limited to, routines, subroutines, programs, objects, components, data structures, etc. that perform specific tasks or execute specific abstract data types according to the present invention.

First, the guide message management unit 110 according to an embodiment of the present invention may perform a function of providing a guide message to a target user.

Specifically, the guide message management unit 110 may provide a guide message from a message delivery device associated with the target user.

For example, referring to FIG. 2 , the guide message management unit 110 provides a guide message to the target user from the message delivery device 320 located at the closest distance to the target user based on the location of the target user. can make it happen More specifically, the guide message management unit 110 may calculate a distance between a location where a plurality of message delivery devices 310 and 320 exist and a location where the target user exists, respectively, and the shortest distance among the calculated distances. The message delivery device 320 corresponding to (eg, the Euclidean distance) may be determined as the message delivery device located at the closest distance to the target user.

As another example, the guide message management unit 110 may provide a guide message to the target user from a message delivery device located within a predetermined range based on the direction in which at least one of the target user's face and gaze is directed. More specifically, the guide message management unit 110 is a straight line 201 that is specified based on a direction in which at least one of the target user's face and gaze is directed (eg, in the direction in which at least one of the target user's face and gaze is directed). A two-dimensional or three-dimensional region 202 (eg, an area such as a circle, an ellipse, a square, a rectangle, a cone, a quadrangular pyramid) having a straight line 201 extending therefrom as a centerline or a central axis may be specified, and the The guide message may be provided to the target user by the message delivery device 320 included in the area (or the message delivery device closest to the target user among the message delivery devices included in the area).

Meanwhile, the guide message manager 110 may dynamically determine at least one of a message delivery device and a guide message delivery type that will provide the guide message with reference to context information about the target user.

For example, the guide message management unit 110 searches the case database for cases matching the same or similar information to the information about the location (or place) where the target user exists, the target, the gaze time, the level of ambient noise, etc. A corresponding case can be specified based on the result of learning through machine learning or deep learning with respect to the location (or place) where the target user exists, the subject of attention, the time of the gaze, the level of ambient noise, etc. There is a message delivery device ( For example, the nearest distance) and its delivery type (eg, providing a visual message for a noisy location and an audible message for a quiet location) can be dynamically determined.

Next, the effective gesture management unit 120 according to an embodiment of the present invention provides a head gesture performed by the target user with reference to the direction or location associated with the guide message and the direction to which at least one of the target user's face and gaze is directed. may perform a function of determining whether is a valid gesture.

For example, the effective gesture management unit 120 may determine a line (or region) that is specified based on a direction in which at least one of the target user's face and gaze is directed (or extends in a direction in which at least one of the target user's face and gaze is directed). ), when a message delivery device providing a guide message to the target user is located on the target user, at least one of the target user's face and gaze is directed in the corresponding direction, or at least one of the target user's face and gaze is directed in the corresponding direction A head gesture performed by a corresponding target user for a predetermined period of time based on a point of view may be determined as a valid gesture.

For another example, the effective gesture management unit 120 may configure at least one of the target user's face and gaze when the direction indicated (or specified) by the guide message coincides with a direction to which at least one of the target user's face and gaze is directed. It is possible to determine as a valid gesture a head gesture performed by the corresponding target user while is facing the corresponding direction or for a predetermined time based on a point in time when at least one of the target user's face and gaze is directed in the corresponding direction.

More specifically, when directed to face a predetermined direction by the content of the voice guide message, at least one of the target user's face and gaze while at least one of the target user's face and gaze is directed in the above-indicated direction A head gesture performed by the corresponding target user for a predetermined period of time based on a time point in which the is directed in the direction may be determined as a valid gesture.

Next, the user intention management unit 130 according to an embodiment of the present invention performs a function of determining the intention of the target user with reference to the head gesture of the target user determined to be a valid gesture by the effective gesture management unit 120 . can do.

For example, referring to FIG. 3 , the user intention management unit 130 may determine an intention corresponding to a pattern that matches or is similar to the pattern of the head gesture of the target user determined to be a valid gesture as the intention of the target user. More specifically, the user intention management unit 130 means a nod gesture, that is, O, yes or down, when the user moves his/her head in the up-down order, and tilts his/her head left-right-left. -Moving right or right-left-right-left means a shake gesture, that is, X, no, or cancel, and moving the head in the right-left order means a right gesture, that is It means next, moving the head in the left-right order means a left gesture, that is, previous, and moving the head in the up-down order means an up gesture, that is, up ), and tilting the head to the left means lean left gesture, i.e. decrease, and tilting the head to the right means lean right gesture, i.e. increase. You can determine the user's intentions.

Meanwhile, the user intention management unit 130 may refer to a lookup table (not shown) regarding an intention corresponding to a pattern of a head gesture in order to determine the intention of the target user, and this lookup table is obtained when a predetermined condition is satisfied. It can be updated periodically or in real time. Meanwhile, the user intention management unit 130 may perform learning based on a pattern of head gestures of each target user or a plurality of target users, and may determine the intention of the target user based on the learning result. That is, the user intention management unit 130 may use a variety of known learning algorithms to determine the intention corresponding to the pattern of the target user, for example, learning based on the image about the pattern of the target user's head gesture. A Convolutional Neural Network (CNN) algorithm to perform, or a Support Vector Machine (SVM) algorithm for performing learning based on a feature specified from a pattern of a target user's head gesture, etc. may be used. have.

Meanwhile, further, the user intention management unit 130 may specify a control command intended by the target user with reference to the intention of the target user determined as above, and execute the control command.

On the other hand, the communication unit 140 according to an embodiment of the present invention may perform a function of enabling data transmission/reception to/from the guide message management unit 110 , the effective gesture management unit 120 , and the user intention management unit 130 . have.

Finally, the control unit 150 according to an embodiment of the present invention controls the flow of data between the guide message management unit 110 , the effective gesture management unit 120 , the user intention management unit 130 , and the communication unit 140 . can be done That is, the control unit 150 according to the present invention controls the data flow to/from the outside of the gesture recognition system 100 or the data flow between each component of the gesture recognition system 100, so that the guide message management unit 110, The effective gesture management unit 120 , the user intention management unit 130 , and the communication unit 140 may be controlled to perform their own functions, respectively.

first embodiment

4 to 7 are diagrams exemplarily illustrating a situation in which a guide message including text and an image is provided to a target user.

4 to 7 , first, through the first message delivery device 510 located within a predetermined range with respect to the direction 411 toward which at least one of the face and the gaze of the first target user 410 is directed, One guide message is provided (see FIG. 4 ), and at least one of the face and the gaze of the second target user 420 is directed through the second message delivery device 520 located within a predetermined range based on the direction 421 . A second guide message is provided (refer to FIG. 5 ), and a third message delivery device 530 positioned within a predetermined range based on a direction 431 toward which at least one of the face and the gaze of the third target user 430 is directed. A third guide message is provided through (see FIG. 6 ), and the fourth message delivery device 540 is located within a predetermined range based on the direction 441 of at least one of the face and the gaze of the fourth target user 440 . A fourth guide message may be provided through (see FIG. 7 ). For example, such a guide message could be a visual message "Are you sure? Shake to Cancel or Nod to Confirm" (or "Are you sure? Shake to Cancel or Nod to Confirm").

Next, a direction 411 toward which at least one of the face and gaze of the first target user 410 is directed and a direction 511 in which the first guide message is displayed (eg, a normal direction of the first guide message) are determined. With reference, it may be determined whether the head gesture performed by the first target user 410 is a valid gesture, the direction 421 toward which at least one of the face and the gaze of the second target user 420 is directed and the second guide message Whether the head gesture performed by the second target user 420 is a valid gesture may be determined with reference to the display direction 521 (eg, the normal direction of the second guide message), and the third target user The third target user 430 with reference to the direction 431 in which at least one of the face and the gaze of the 430 is directed and the direction 531 in which the third guide message is displayed (eg, the normal direction of the third guide message) ) may be determined whether the head gesture performed by For example, it may be determined whether the head gesture performed by the fourth target user 440 is a valid gesture with reference to the normal direction of the fourth guide message).

For example, a gesture performed by the first target user 410 in a state in which at least one of the face and the gaze of the first target user 410 faces a direction opposite to the direction 511 in which the first guide message is displayed It can be determined as a valid gesture, and is performed by the second target user 420 with at least one of the face and the gaze of the second target user 420 facing a direction opposite to the direction 521 in which the second guide message is displayed. may be determined as a valid gesture, and the third target user 430 in a state in which at least one of the face and the gaze of the third target user 430 faces in a direction opposite to the direction 531 in which the third guide message is displayed. A gesture performed by the user may be determined as a valid gesture, and at least one of a face and a gaze of the fourth target user 440 faces a direction opposite to the direction 541 in which the fourth guide message is displayed. The gesture made by 440 may be determined as a valid gesture.

More specifically, in a state in which at least one of the face and the gaze of the first target user 410 faces the direction opposite to the direction 511 in which the first guide message is displayed, the shaking gesture is performed by the first target user 410 If performed, the corresponding shaking gesture may be determined as a valid gesture, and if the nod gesture is performed by the first target user 410 , the corresponding nod gesture may be determined as a valid gesture, and among the face and gaze of the second target user 420 . In a state in which at least one of the second guide messages faces in a direction opposite to the direction 521 in which the second guide message is displayed, if a shaking gesture is performed by the second target user 420 , the corresponding shaking gesture may be determined as a valid gesture, and the second target When the nod gesture is performed by the user 420 , the nod gesture may be determined as a valid gesture, and at least one of the face and the gaze of the third target user 430 is opposite to the direction 531 in which the third guide message is displayed. In the direction facing state, if a shaking gesture is performed by the third target user 430 , the shaking gesture may be determined as a valid gesture, and if the nod gesture is performed by the third target user 430 , the nod gesture is valid It may be determined as a gesture, and in a state in which at least one of the face and gaze of the fourth target user 440 faces the direction opposite to the direction 541 in which the fourth guide message is displayed, shaking by the fourth target user 440 When the gesture is performed, the corresponding shaking gesture may be determined as a valid gesture, and if the nod gesture is performed by the fourth target user 440 , the corresponding nod gesture may be determined as a valid gesture.

Then, the intention of each target user 410 , 420 , 430 , 440 may be determined with reference to the head gesture of each target user 410 , 420 , 430 , 440 determined to be the above valid gesture.

For example, if the shaking gesture of the first to fourth target users 410, 420, 430, and 440 is determined as a valid gesture, it may be determined that the intention of the corresponding target user 410, 420, 430, 440 is cancellation. If the nod gesture of the first to fourth target users 410 , 420 , 430 , and 440 is determined as a valid gesture, the intention of the corresponding target user 410 , 420 , 430 , 440 may be determined to be consent.

second embodiment

8 is a diagram exemplarily illustrating a situation in which a guide message including a voice is provided to a target user.

Referring to FIG. 8 , first, a guide through a message delivery device 850 (eg, a speaker) located within a predetermined range with respect to a direction 811 in which at least one of a face and a gaze of a target user 810 is directed. A message may be provided. For example, such a guide message could be an audible message "Should I turn up the volume?"

Next, referring to the direction 812 in which at least one of the face and gaze of the target user 810 is directed and the direction in which the guide message is provided or the location of the speaker 850 providing the guide message, the target user 810 is It may be determined whether the head gesture performed by .

For example, it is performed by the target user 810 in a state where the speaker 850 providing the guide message is present on an extension of the direction 812 in which at least one of the face and the gaze of the target user 810 is directed. may be determined as a valid gesture.

More specifically, in a state in which the speaker 850 providing the guide message exists on the extension of the direction 812 in which at least one of the face and the gaze of the target user 810 is directed, by the target user 810 When the right tilt gesture is performed, the corresponding right tilt gesture may be determined as a valid gesture.

Then, the intention of the target user 810 may be determined with reference to the head gesture of the target user 810 determined to be the above valid gesture.

For example, if the right tilting gesture of the target user 810 is determined as a valid gesture, it may be determined that the intention of the target user 810 is to increase the volume.

third embodiment

9 and 10 are diagrams exemplarily illustrating another situation in which a guide message including a voice is provided to a target user.

Referring to FIG. 9 , first, a guide through a message delivery device 950 (eg, a speaker) located within a predetermined range based on a direction 911 in which at least one of the face and gaze of the target user 910 is directed. A message may be provided. For example, such a guide message may be an audible message "Nod to the door video (intercom) to open the door" (or "Nod to the door video to open the door").

Then, the head gesture performed by the target user 910 with reference to the direction 912 toward which at least one of the face and the gaze of the target user 910 is directed and the direction or location indicated by the content of the guide message above. It may be determined whether is a valid gesture.

For example, the target user 910 in a state in which the door video (intercom) 960 indicated in the guide message exists on the extension line of the direction 912 in which at least one of the target user 910's face and gaze is directed. ) may be determined as a valid gesture.

More specifically, in a state in which the door video 960 indicated in the content of the guide message exists on the extension line of the direction 912 in which at least one of the target user's face and gaze is directed, the corresponding target user 910 ), when a nod gesture is performed, the nod gesture may be determined as a valid gesture.

Then, the intention of the target user 910 may be determined with reference to the head gesture of the target user 910 determined to be the above valid gesture.

For example, if the nod gesture of the target user 910 is determined to be a valid gesture, the intention of the target user 910 may be determined to be consent (ie, open a door).

Meanwhile, referring to FIG. 10 , according to an embodiment of the present invention, a guide message according to the present invention is provided in a device that performs other conventional functions, or a function other than the function of providing a guide message by a message delivery device is added. can also be done

For example, when a call function is conventionally executed in the intercom (ie, a device that performs other conventional functions) 1060, a guide message (eg, such The guide message may be a visual message “Shall we open?” (or “Open?”).) is provided to the target user 1010 , or the message delivery device 1060 further performs the function of an intercom so that the calling function is increased. When executed, a guide message including text related to a corresponding call function may be provided to the target user 1010 in the message delivery device. In this case, the gesture performed by the target user 1010 is valid while the intercom 1060 providing the guide message is present on an extension line in the direction in which at least one of the target user 1010's face and gaze is directed. It may be determined as a gesture. More specifically, the nod gesture is performed by the target user 1010 in a state where the intercom 1060 providing the guide message is present on an extension line in the direction in which at least one of the face and the gaze of the target user 1010 is directed. Otherwise, the nod gesture may be determined as a valid gesture, and the intention of the corresponding target user 1010 may be determined to be acceptance (ie, opening the door).

4th embodiment

11 is a diagram illustrating another situation in which a guide message including a voice is provided to a target user.

Referring to FIG. 11 , first, a plurality of message delivery devices 1120 , 1121 , 1122 , 1123 positioned within a predetermined range with respect to the direction 1111 in which at least one of the face and the gaze of the target user 1110 are directed (examples) For example, a guide message may be provided through a speaker). For example, such a guide message could be an audible message "Should I set to sleep mode?" In this case, at least one of the face and the gaze of the target user 1110 is adjusted as sound elements such as output and phase of the voice providing the guide message are adjusted in the plurality of message delivery devices 1120 , 1121 , 1122 , and 1123 . The sound image of the guide message (that is, a virtual point where the sound is recognized as output or the sound is focused on a display (specifically, a specific position of the display) located within a predetermined range with respect to the direction 1111 is directed. point) can be located.

Then, referring to the direction 1112 in which at least one of the face and the gaze of the target user 910 is directed and the location (ie, the location of the sound image) 1124 where the above guide message is provided, the target user 1110 is sent to the target user 1110 . It may be determined whether the head gesture made by the user is a valid gesture.

For example, in a state in which the position 1124 of the above sound image or a display providing a corresponding guide message exists on an extension of the direction 1112 in which at least one of the face and the gaze of the target user 1110 is directed, the corresponding target user The gesture made by 1110 may be determined as a valid gesture.

More specifically, in a state in which the location 1124 of the above sound image or the display providing the guide message exists on an extension of the direction 1112 in which at least one of the face and the gaze of the target user 1110 is directed, the corresponding target When a nod gesture is performed by the user 1110 , the nod gesture may be determined as a valid gesture.

Then, the intention of the target user 1110 may be determined with reference to the head gesture of the target user 1110 determined to be the above valid gesture.

For example, if the nod gesture of the target user 1110 is determined to be a valid gesture, the intention of the target user 1110 may be determined to be acceptance (ie, performing a sleep mode).

The embodiments according to the present invention described above may be implemented in the form of program instructions that can be executed through various computer components and recorded in a computer-readable recording medium. The computer-readable recording medium may include program instructions, data files, data structures, etc. alone or in combination. The program instructions recorded on the computer-readable recording medium may be specially designed and configured for the present invention or may be known and used by those skilled in the computer software field. Examples of the computer-readable recording medium include hard disks, magnetic media such as floppy disks and magnetic tapes, optical recording media such as CD-ROMs and DVDs, and magneto-optical media such as floppy disks. medium), and hardware devices specially configured to store and execute program instructions, such as ROM, RAM, flash memory, and the like. Examples of program instructions include not only machine language codes such as those generated by a compiler, but also high-level language codes that can be executed by a computer using an interpreter or the like. A hardware device may be converted into one or more software modules to perform processing in accordance with the present invention, and vice versa.

In the above, the present invention has been described with reference to specific matters such as specific components and limited embodiments and drawings, but these are provided to help a more general understanding of the present invention, and the present invention is not limited to the above embodiments, and the present invention is not limited to the above embodiments. Those of ordinary skill in the art to which the invention pertains can make various modifications and changes from these descriptions.

Therefore, the spirit of the present invention should not be limited to the above-described embodiments, and the scope of the spirit of the present invention is not limited to the scope of the scope of the present invention. will be said to belong to

100: gesture recognition system
110: guide message management unit
120: effective gesture management unit
130: user intent management unit
140: communication department
150: control unit

Claims (7)

A method for recognizing a gesture, comprising:
providing a guide message to the target user;
determining whether the head gesture performed by the target user is a valid gesture by referring to a direction to which at least one of the target user's face and gaze is directed and a direction or location associated with the guide message; and
determining the intention of the target user with reference to the head gesture of the target user determined to be the valid gesture
Way. According to claim 1,
In the step of providing the guide message, the guide message is provided by a message delivery device associated with the target user.
Way. 3. The method of claim 2,
The message delivery device is a device located at the closest distance to the target user.
Way. 3. The method of claim 2,
The message delivery device is a device located within a predetermined range based on a direction in which at least one of the target user's face and gaze is directed.
Way. According to claim 1,
In the step of determining whether the gesture is valid, a head gesture performed by the target user while at least one of a face and a gaze of the target user faces a direction specified by the guide message is determined as the valid gesture
Way. A non-transitory computer-readable recording medium on which a computer program for executing the method according to claim 1 is recorded. A system for recognizing gestures, comprising:
A guide message management unit that provides a guide message to the target user;
An effective gesture management unit that determines whether the head gesture performed by the target user is a valid gesture with reference to a direction to which at least one of the target user's face and gaze is directed and a direction or position associated with the guide message, and
and a user intention manager that determines the intention of the target user with reference to the head gesture of the target user determined to be the valid gesture.
system.

Images