Method for performing hand tracking, and wearable electronic device for supporting same

Abstract

A wearable electronic device according to one embodiment may comprise: a camera including a first camera and a second camera; a display; at least one processor; and a memory for storing instructions. When executed by the at least one processor, the instructions can cause the wearable electronic device to: acquire the location of the hand of a user on the basis of at least one first image acquired through the first camera; acquire the gaze point of the user on the basis of at least one second image acquired through the second camera; identify whether the location of the hand corresponds to the gaze point; acquire, on the basis that the location of the hand corresponds to the gaze point, a skeleton including key points related to the hand; and perform an operation related to the hand on the basis of the acquired skeleton.

Description

Method for performing hand tracking and wearable electronic device supporting the same

[0001] The present disclosure relates to a method for performing hand tracking and a wearable electronic device supporting the same.

[0002] The variety of services and additional features offered through wearable electronic devices, such as augmented reality glasses (AR glasses), virtual reality glasses (VR glasses), and head-mounted displays (HMDs), is steadily increasing. To enhance the utility of these wearable electronic devices and satisfy the needs of diverse users, telecommunications service providers and wearable electronic device manufacturers are competitively developing wearable electronic devices to offer a variety of features and differentiate themselves from competitors. Consequently, the various functions offered through wearable electronic devices are also becoming increasingly sophisticated.

[0003] Wearable electronic devices can interact with a user through various methods. For example, a wearable electronic device can track a user's hand (hand position and / or hand movement) and perform gesture recognition based on the tracked hand (and / or gestures representing a virtual hand corresponding to the hand) (hereinafter referred to as "hand tracking").

[0004] The above information may be provided as background art to aid in understanding the present disclosure. No claim or determination is made as to whether any of the above-described matters constitute prior art related to the present disclosure.

[0005] Hand tracking may include multiple actions. For example, hand tracking may include: acquiring the position of a hand within an image (or depth map) acquired via a camera (or sensor); acquiring a skeleton associated with the hand based on the hand's position; recognizing a gesture made by the hand; and / or rendering a virtual hand corresponding to the hand.

[0006] When an input for hand tracking is received, the wearable electronic device performs the multiple operations included in hand tracking. In this case, the wearable electronic device may consume a significant amount of power by performing the multiple operations included in hand tracking regardless of user interaction or the user's intention (or interest).

[0007] The present disclosure relates to a method for performing hand tracking and a wearable electronic device supporting the same, which can perform hand tracking by considering a user's gaze point (and / or a position of an object).

[0008] The technical problems to be solved by the present disclosure are not limited to the technical problems mentioned above, and other technical problems not mentioned can be clearly understood by a person having ordinary skill in the technical field to which the present invention belongs from the description below.

[0009] According to one embodiment, a wearable electronic device may include a camera including a first camera and a second camera, a display, at least one processor, and a memory storing instructions. The instructions, when executed by the at least one processor, may cause the wearable electronic device to acquire a position of a hand of a user based on at least one first image acquired through the first camera. The instructions, when executed by the at least one processor, may cause the wearable electronic device to acquire a gaze point of the user based on at least one second image acquired through the second camera. The instructions, when executed by the at least one processor, may cause the wearable electronic device to determine whether a position of the hand corresponds to the gaze point. The instructions, when executed by the at least one processor, may cause the wearable electronic device to acquire a skeleton including key points associated with the hand based on whether the position of the hand corresponds to the gaze point. The above instructions, when executed by the at least one processor, may cause the wearable electronic device to perform a motion associated with the hand based on the acquired skeleton.

[0010] A method for performing hand tracking in a wearable electronic device according to one embodiment may include an operation of acquiring a position of a hand of a user based on at least one first image acquired through a first camera of the wearable electronic device. The method may include an operation of acquiring a gaze point of the user based on at least one second image acquired through a second camera of the wearable electronic device. The method may include an operation of determining whether the position of the hand corresponds to the gaze point. The method may include an operation of acquiring a skeleton including key points related to the hand based on whether the position of the hand corresponds to the gaze point. The method may include an operation of performing an action related to the hand based on the acquired skeleton.

[0011] In one embodiment, a non-transitory computer-readable storage medium having recorded thereon computer-executable instructions, wherein the computer-executable instructions, when executed by at least one processor of a wearable electronic device, cause the wearable electronic device to obtain a position of a hand of a user based on at least one first image acquired through a first camera of the wearable electronic device. The computer-executable instructions, when executed by the at least one processor, cause the wearable electronic device to obtain a gaze point of the user based on at least one second image acquired through a second camera of the wearable electronic device. The computer-executable instructions, when executed by the at least one processor, cause the wearable electronic device to determine whether the position of the hand corresponds to the gaze point. The computer-executable instructions, when executed by the at least one processor, may cause the wearable electronic device to obtain a skeleton including key points associated with the hand based on the position of the hand corresponding to the gaze point. The computer-executable instructions, when executed by the at least one processor, may cause the wearable electronic device to perform an action associated with the hand based on the obtained skeleton.

[0012] According to one embodiment of the present disclosure, a method for performing hand tracking and a wearable electronic device supporting the same can reduce power consumption of the wearable electronic device by performing hand tracking by considering a gaze point (and / or a position of an object).

[0013] FIG. 1 is a block diagram of an electronic device within a network environment according to one embodiment.

[0014] FIG. 2 is a perspective view illustrating the internal configuration of a wearable electronic device according to an embodiment of the present disclosure.

[0015] FIG. 3A is a diagram illustrating a front side of a wearable electronic device according to one embodiment.

[0016] FIG. 3b is a drawing showing the back of a wearable electronic device according to one embodiment.

[0017] FIG. 4 is a block diagram of a wearable electronic device according to one embodiment.

[0018] FIG. 5 is a flowchart illustrating a method for performing hand tracking according to one embodiment.

[0019] FIG. 6 is a diagram illustrating a method for obtaining the position of a user's hand according to one embodiment.

[0020] FIG. 7 is a diagram illustrating a method for obtaining a user's gaze point according to one embodiment.

[0021] FIG. 8 is a drawing for explaining an operation of obtaining a skeleton according to one embodiment.

[0022] FIG. 9 is a diagram illustrating an operation of rendering a virtual hand according to one embodiment.

[0023] FIG. 10 is a flowchart illustrating a method for performing hand tracking according to one embodiment.

[0024] FIG. 11 is a flowchart illustrating a method for performing hand tracking according to one embodiment.

[0025] FIG. 12 is a diagram illustrating a method for performing hand tracking according to one embodiment.

[0026] FIG. 13 is a flowchart illustrating a method for performing hand tracking according to one embodiment.

[0027] FIG. 1 is a block diagram of an electronic device (101) within a network environment (100), according to one embodiment.

[0028] Referring to FIG. 1, in a network environment (100), an electronic device (101) may communicate with an electronic device (102) via a first network (198) (e.g., a short-range wireless communication network), or may communicate with at least one of an electronic device (104) or a server (108) via a second network (199) (e.g., a long-range wireless communication network). According to one embodiment, the electronic device (101) may communicate with the electronic device (104) via the server (108). According to one embodiment, the electronic device (101) may include a processor (120), a memory (130), an input module (150), an audio output module (155), a display module (160), an audio module (170), a sensor module (176), an interface (177), a connection terminal (178), a haptic module (179), a camera module (180), a power management module (188), a battery (189), a communication module (190), a subscriber identification module (196), or an antenna module (197). In some embodiments, the electronic device (101) may omit at least one of these components (e.g., the connection terminal (178)), or may have one or more other components added. In some embodiments, some of these components (e.g., the sensor module (176), the camera module (180), or the antenna module (197)) may be integrated into one component (e.g., the display module (160)).

[0029] The processor (120) may, for example, execute software (e.g., a program (140)) to control at least one other component (e.g., a hardware or software component) of the electronic device (101) connected to the processor (120) and perform various data processing or calculations. According to one embodiment, as at least a part of the data processing or calculations, the processor (120) may store commands or data received from other components (e.g., a sensor module (176) or a communication module (190)) in a volatile memory (132), process the commands or data stored in the volatile memory (132), and store result data in a non-volatile memory (134). According to one embodiment, the processor (120) may include a main processor (121) (e.g., a central processing unit or an application processor) or a secondary processor (123) (e.g., a graphics processing unit, a neural processing unit (NPU), an image signal processor, a sensor hub processor, or a communication processor)) that can operate independently or together therewith. For example, if the electronic device (101) includes a main processor (121) and a secondary processor (123), the secondary processor (123) may be configured to use less power than the main processor (121) or to be specialized for a specified function. The secondary processor (123) may be implemented separately from the main processor (121) or as a part thereof.

[0030] The auxiliary processor (123) may control at least a portion of functions or states associated with at least one component (e.g., a display module (160), a sensor module (176), or a communication module (190)) of the electronic device (101), for example, on behalf of the main processor (121) while the main processor (121) is in an inactive (e.g., sleep) state, or together with the main processor (121) while the main processor (121) is in an active (e.g., application execution) state. In one embodiment, the auxiliary processor (123) (e.g., an image signal processor or a communication processor) may be implemented as a part of another functionally related component (e.g., a camera module (180) or a communication module (190)). In one embodiment, the auxiliary processor (123) (e.g., a neural network processing unit) may include a hardware structure specialized for processing artificial intelligence models. The artificial intelligence models may be generated through machine learning. This learning can be performed, for example, on the electronic device (101) itself where the artificial intelligence model is executed, or can be performed through a separate server (e.g., server (108)). The learning algorithm can include, for example, supervised learning, unsupervised learning, semi-supervised learning, or reinforcement learning, but is not limited to the examples described above. The artificial intelligence model can include multiple artificial neural network layers.The artificial neural network may be one of a deep neural network (DNN), a convolutional neural network (CNN), a recurrent neural network (RNN), a restricted Boltzmann machine (RBM), a deep belief network (DBN), a bidirectional recurrent deep neural network (BRDNN), a deep Q-network, or a combination of two or more of the above, but is not limited to the examples described above. In addition to, or alternatively to, a hardware structure, an artificial intelligence model may include a software structure.

[0031] The memory (130) can store various data used by at least one component (e.g., processor (120) or sensor module (176)) of the electronic device (101). The data can include, for example, software (e.g., program (140)) and input data or output data for commands related thereto. The memory (130) can include volatile memory (132) or non-volatile memory (134).

[0032] The program (140) may be stored as software in the memory (130) and may include, for example, an operating system (142), middleware (144), or an application (146).

[0033] The input module (150) can receive commands or data to be used in a component of the electronic device (101) (e.g., a processor (120)) from an external source (e.g., a user) of the electronic device (101). The input module (150) can include, for example, a microphone, a mouse, a keyboard, a key (e.g., a button), or a digital pen (e.g., a stylus pen).

[0034] The audio output module (155) can output audio signals to the outside of the electronic device (101). The audio output module (155) can include, for example, a speaker or a receiver. The speaker can be used for general purposes, such as multimedia playback or recording playback. The receiver can be used to receive incoming calls. In one embodiment, the receiver can be implemented separately from the speaker or as part of the speaker.

[0035] The display module (160) can visually provide information to an external party (e.g., a user) of the electronic device (101). The display module (160) may include, for example, a display, a holographic device, or a projector and a control circuit for controlling the device. In one embodiment, the display module (160) may include a touch sensor configured to detect a touch, or a pressure sensor configured to measure the intensity of a force generated by the touch.

[0036] The audio module (170) can convert sound into an electrical signal, or vice versa, convert an electrical signal into sound. According to one embodiment, the audio module (170) can acquire sound through the input module (150), output sound through the sound output module (155), or an external electronic device (e.g., electronic device (102)) (e.g., speaker or headphone) directly or wirelessly connected to the electronic device (101).

[0037] The sensor module (176) can detect the operating status (e.g., power or temperature) of the electronic device (101) or the external environmental status (e.g., user status) and generate an electrical signal or data value corresponding to the detected status. According to one embodiment, the sensor module (176) can include, for example, a gesture sensor, a gyro sensor, a barometric pressure sensor, a magnetic sensor, an acceleration sensor, a grip sensor, a proximity sensor, a color sensor, an IR (infrared) sensor, a biometric sensor, a temperature sensor, a humidity sensor, or an illuminance sensor.

[0038] The interface (177) may support one or more designated protocols that may be used to directly or wirelessly connect the electronic device (101) with an external electronic device (e.g., the electronic device (102)). In one embodiment, the interface (177) may include, for example, a high definition multimedia interface (HDMI), a universal serial bus (USB) interface, an SD card interface, or an audio interface.

[0039] The connection terminal (178) may include a connector through which the electronic device (101) may be physically connected to an external electronic device (e.g., electronic device (102)). According to one embodiment, the connection terminal (178) may include, for example, an HDMI connector, a USB connector, an SD card connector, or an audio connector (e.g., a headphone connector).

[0040] A haptic module (179) can convert electrical signals into mechanical stimuli (e.g., vibration or movement) or electrical stimuli that a user can perceive through tactile or kinesthetic sensations. In one embodiment, the haptic module (179) can include, for example, a motor, a piezoelectric element, or an electrical stimulation device.

[0041] The camera module (180) can capture still images and videos. According to one embodiment, the camera module (180) may include one or more lenses, image sensors, image signal processors, or flashes.

[0042] The power management module (188) can manage power supplied to the electronic device (101). According to one embodiment, the power management module (188) can be implemented, for example, as at least a part of a power management integrated circuit (PMIC).

[0043] A battery (189) may power at least one component of the electronic device (101). In one embodiment, the battery (189) may include, for example, a non-rechargeable primary battery, a rechargeable secondary battery, or a fuel cell.

[0044] The communication module (190) may support the establishment of a direct (e.g., wired) communication channel or a wireless communication channel between the electronic device (101) and an external electronic device (e.g., electronic device (102), electronic device (104), or server (108)), and the performance of communication through the established communication channel. The communication module (190) may operate independently from the processor (120) (e.g., application processor) and may include one or more communication processors that support direct (e.g., wired) communication or wireless communication. According to one embodiment, the communication module (190) may include a wireless communication module (192) (e.g., a cellular communication module, a short-range wireless communication module, or a global navigation satellite system (GNSS) communication module) or a wired communication module (194) (e.g., a local area network (LAN) communication module, or a power line communication module). Among these communication modules, the corresponding communication module can communicate with an external electronic device (104) via a first network (198) (e.g., a short-range communication network such as Bluetooth, wireless fidelity (WiFi) direct, or infrared data association (IrDA)) or a second network (199) (e.g., a long-range communication network such as a legacy cellular network, a 5G network, a next-generation communication network, the Internet, or a computer network (e.g., a LAN or WAN)). These various types of communication modules can be integrated into a single component (e.g., a single chip) or implemented as multiple separate components (e.g., multiple chips). The wireless communication module (192) can verify or authenticate the electronic device (101) within a communication network such as the first network (198) or the second network (199) by using subscriber information (e.g., an international mobile subscriber identity (IMSI)) stored in the subscriber identification module (196).

[0045] The wireless communication module (192) can support 5G networks and next-generation communication technologies following the 4G network, such as NR access technology (new radio access technology). The NR access technology can support high-speed transmission of high-capacity data (eMBB (enhanced mobile broadband)), minimization of terminal power and connection of multiple terminals (mMTC (massive machine type communications)), or high reliability and low latency (URLLC (ultra-reliable and low-latency communications)). The wireless communication module (192) can support, for example, a high-frequency band (e.g., mmWave band) to achieve a high data transmission rate. The wireless communication module (192) can support various technologies for securing performance in a high-frequency band, such as beamforming, massive multiple-input and multiple-output (MIMO), full dimensional MIMO (FD-MIMO), array antenna, analog beam-forming, or large scale antenna. The wireless communication module (192) can support various requirements specified in the electronic device (101), an external electronic device (e.g., the electronic device (104)), or a network system (e.g., the second network (199)). According to one embodiment, the wireless communication module (192) can support a peak data rate (e.g., 20 Gbps or more) for eMBB realization, a loss coverage (e.g., 164 dB or less) for mMTC realization, or a U-plane latency (e.g., 0.5 ms or less for downlink (DL) and uplink (UL), or 1 ms or less for round trip) for URLLC realization.

[0046] The antenna module (197) can transmit or receive signals or power to or from an external device (e.g., an external electronic device). In one embodiment, the antenna module (197) may include an antenna including a radiator formed of a conductor or a conductive pattern formed on a substrate (e.g., a PCB). In one embodiment, the antenna module (197) may include a plurality of antennas (e.g., an array antenna). In this case, at least one antenna suitable for a communication method used in a communication network, such as the first network (198) or the second network (199), may be selected from the plurality of antennas by, for example, the communication module (190). A signal or power may be transmitted or received between the communication module (190) and an external electronic device through the selected at least one antenna. In some embodiments, in addition to the radiator, another component (e.g., a radio frequency integrated circuit (RFIC)) may be additionally formed as a part of the antenna module (197).

[0047] According to various embodiments, the antenna module (197) may form a mmWave antenna module. According to one embodiment, the mmWave antenna module may include a printed circuit board, an RFIC disposed on or adjacent a first side (e.g., a bottom side) of the printed circuit board and capable of supporting a designated high frequency band (e.g., a mmWave band), and a plurality of antennas (e.g., an array antenna) disposed on or adjacent a second side (e.g., a top side or a side side) of the printed circuit board and capable of transmitting or receiving signals in the designated high frequency band.

[0048] At least some of the above components can be interconnected and exchange signals (e.g., commands or data) with each other via a communication method between peripheral devices (e.g., a bus, GPIO (general purpose input and output), SPI (serial peripheral interface), or MIPI (mobile industry processor interface)).

[0049] According to one embodiment, commands or data may be transmitted or received between the electronic device (101) and an external electronic device (104) via a server (108) connected to a second network (199). Each of the external electronic devices (102 or 104) may be the same or a different type of device as the electronic device (101). According to one embodiment, all or part of the operations executed in the electronic device (101) may be executed in one or more of the external electronic devices (102, 104, or 108). For example, when the electronic device (101) is to perform a certain function or service automatically or in response to a request from a user or another device, the electronic device (101) may, instead of or in addition to executing the function or service itself, request one or more external electronic devices to perform the function or at least a part of the service. One or more external electronic devices that receive the request may execute at least a portion of the requested function or service, or an additional function or service related to the request, and transmit the result of the execution to the electronic device (101). The electronic device (101) may process the result as is or additionally and provide it as at least a portion of a response to the request. For this purpose, cloud computing, distributed computing, mobile edge computing (MEC), or client-server computing technology may be used, for example. The electronic device (101) may provide an ultra-low latency service by using distributed computing or mobile edge computing, for example. In another embodiment, the external electronic device (104) may include an Internet of Things (IoT) device. The server (108) may be an intelligent server utilizing machine learning and / or a neural network. According to one embodiment, the external electronic device (104) or the server (108) may be included in the second network (199).The electronic device (101) can be applied to intelligent services (e.g., smart home, smart city, smart car, or healthcare) based on 5G communication technology and IoT-related technology.

[0050] Electronic devices according to the various embodiments disclosed in this document may take various forms. Electronic devices may include, for example, portable communication devices (e.g., smartphones), computer devices, portable multimedia devices, portable medical devices, cameras, wearable devices, or home appliances. Electronic devices according to the embodiments of this document are not limited to the aforementioned devices.

[0051] The various embodiments of this document and the terminology used therein are not intended to limit the technical features described in this document to specific embodiments, but should be understood to include various modifications, equivalents, or substitutes of the embodiments. In connection with the description of the drawings, similar reference numerals may be used for similar or related components. The singular form of a noun corresponding to an item may include one or more of the items, unless the context clearly indicates otherwise. In this document, each of the phrases "A or B", "at least one of A and B", "at least one of A or B", "A, B, or C", "at least one of A, B, and C", and "at least one of A, B, or C" can include any one of the items listed together in the corresponding phrase among those phrases, or all possible combinations thereof. Terms such as "first," "second," or "first" or "second" may be used merely to distinguish one component from another, and do not limit the components in any other respect (e.g., importance or order). When a component (e.g., a first component) is referred to as "coupled" or "connected" to another (e.g., a second component), with or without the terms "functionally" or "communicatively," it means that the component can be connected to the other component directly (e.g., wired), wirelessly, or through a third component.

[0052] The term "module" used in various embodiments of this document may include a unit implemented in hardware, software, or firmware, and may be used interchangeably with terms such as logic, logic block, component, or circuit. A module may be an integral component, or a minimum unit or part of such a component that performs one or more functions. For example, according to one embodiment, a module may be implemented in the form of an application-specific integrated circuit (ASIC).

[0053] Various embodiments of the present document may be implemented as software (e.g., a program (140)) including one or more instructions stored in a storage medium (e.g., an internal memory (136) or an external memory (138)) readable by a machine (e.g., an electronic device (101)). For example, a processor (e.g., a processor (120)) of the machine (e.g., an electronic device (101)) may call at least one instruction among the one or more instructions stored from the storage medium and execute it. This enables the machine to operate to perform at least one function according to the at least one called instruction. The one or more instructions may include code generated by a compiler or code executable by an interpreter. The machine-readable storage medium may be provided in the form of a non-transitory storage medium. Here, 'non-transitory' simply means that the storage medium is a tangible device and does not contain signals (e.g., electromagnetic waves), and the term does not distinguish between cases where data is stored semi-permanently or temporarily on the storage medium.

[0054] According to one embodiment, the method according to various embodiments disclosed in this document may be provided as a computer program product. The computer program product may be traded between sellers and buyers as a product. The computer program product may be distributed in the form of a device-readable storage medium (e.g., compact disc read-only memory (CD-ROM)) or may be provided through an application store (e.g., Play Store). TM ) or directly between two user devices (e.g., smart phones), online distribution (e.g., downloading or uploading). In the case of online distribution, at least a portion of the computer program product may be at least temporarily stored or temporarily created in a machine-readable storage medium, such as the memory of a manufacturer's server, an application store's server, or an intermediary server.

[0055] According to various embodiments, each component (e.g., a module or a program) of the above-described components may include one or more entities, and some of the entities may be separated and placed in other components. According to various embodiments, one or more components or operations of the aforementioned components may be omitted, or one or more other components or operations may be added. Alternatively or additionally, a plurality of components (e.g., a module or a program) may be integrated into a single component. In such a case, the integrated component may perform one or more functions of each of the plurality of components identically or similarly to those performed by the corresponding component among the plurality of components prior to the integration. According to various embodiments, the operations performed by a module, program, or other component may be executed sequentially, in parallel, iteratively, or heuristically, or one or more of the operations may be executed in a different order, omitted, or one or more other operations may be added.

[0056] FIG. 2 is a perspective view illustrating the internal configuration of a wearable electronic device (200) according to one embodiment of the present disclosure.

[0057] Referring to FIG. 2, a wearable electronic device (200) according to one embodiment of the present disclosure may include at least one of a light output module (211), a display member (201), or a camera module (250).

[0058] According to one embodiment of the present disclosure, the light output module (211) may include a light source capable of outputting an image, and a lens for guiding the image to the display member (201). According to one embodiment of the present disclosure, the light output module (211) may include at least one of a liquid crystal display (LCD), a digital mirror device (DMD), a liquid crystal on silicon (LCoS), a light emitting diode (LED) on silicon (LEDoS), an organic light emitting diode (OLED), or a micro light emitting diode (micro LED).

[0059] According to one embodiment of the present disclosure, the display member (201) may include an optical waveguide (e.g., a waveguide). According to one embodiment of the present disclosure, an output image of an optical output module (211) incident on one end of the optical waveguide may be propagated inside the optical waveguide and provided to a user. According to one embodiment of the present disclosure, the optical waveguide may include at least one diffractive element (e.g., a diffractive optical element (DOE), a holographic optical element (HOE)) or at least one reflective element (e.g., a reflective mirror). For example, the optical waveguide may guide an output image of the optical output module (211) to a user's eye by using at least one diffractive element or reflective element.

[0060] According to one embodiment of the present disclosure, the camera module (250) can capture still images and / or moving images. According to one embodiment, the camera module (250) is disposed within a lens frame and can be disposed around the display member (201).

[0061] According to one embodiment of the present disclosure, the first camera module (251) can capture and / or recognize the trajectory of the user's eye (e.g., pupil, iris) or gaze. According to one embodiment of the present disclosure, the first camera module (251) can periodically or aperiodically transmit information related to the trajectory of the user's eye or gaze (e.g., trajectory information) to a processor (e.g., processor (120) of FIG. 1).

[0062] According to one embodiment of the present disclosure, the second camera module (253) can capture an external image.

[0063] According to one embodiment of the present disclosure, the third camera module (255) can be used for hand detection and tracking, and user gesture (e.g., hand movement) recognition. According to one embodiment of the present disclosure, the third camera module (255) can be used for 3 degrees of freedom (3DoF), 6DoF head tracking, position (space, environment) recognition, and / or movement recognition. According to one embodiment of the present disclosure, the second camera module (253) can also be used for hand detection and tracking, and user gesture recognition. According to one embodiment of the present disclosure, at least one of the first camera module (251) to the third camera module (255) can be replaced with a sensor module (e.g., a LiDAR sensor). For example, the sensor module can include at least one of a vertical cavity surface emitting laser (VCSEL), an infrared sensor, and / or a photodiode.

[0064] FIG. 3A is a drawing showing the front of a wearable electronic device (300) according to one embodiment.

[0065] FIG. 3b is a drawing showing the rear side of a wearable electronic device (300) according to one embodiment.

[0066] Referring to FIGS. 3A and 3B, in one embodiment, camera modules (311, 312, 313, 314, 315, 316) and / or depth sensors (317) for obtaining information related to the surrounding environment of the wearable electronic device (300) may be arranged on the first surface (310) of the housing.

[0067] In one embodiment, the camera modules (311, 312) can acquire images related to the environment surrounding the wearable electronic device.

[0068] In one embodiment, the camera modules (313, 314, 315, 316) can acquire images while the wearable electronic device is worn by a user. The camera modules (313, 314, 315, 316) can be used for hand detection and tracking, and user gesture (e.g., hand movement) recognition. The camera modules (313, 314, 315, 316) can be used for 3DoF, 6DoF head tracking, position (spatial, environmental) recognition, and / or movement recognition. In one embodiment, the camera modules (311, 312) can also be used for hand detection and tracking, and user gesture.

[0069] In one embodiment, a depth sensor (317) may be configured to transmit a signal and receive a signal reflected from a subject, and may be used for purposes such as time of flight (TOF) to determine the distance to an object. For example, instead of or in addition to the depth sensor (217), the camera modules (313, 314, 315, 316) may determine the distance to an object.

[0070] According to one embodiment, a camera module (325, 326) for facial recognition and / or a display (321) (and / or a lens) may be disposed on the second side (320) of the housing.

[0071] In one embodiment, a face recognition camera module (325, 326) adjacent to the display may be used to recognize a user's face, or may recognize and / or track both eyes of the user.

[0072] In one embodiment, the display (321) (and / or lens) may be disposed on the second side (320) of the wearable electronic device (300). In one embodiment, the wearable electronic device (300) may not include camera modules (315, 316) among the plurality of camera modules (313, 314, 315, 316). Although not illustrated in FIGS. 3A and 3B , the wearable electronic device (300) may further include at least one of the configurations illustrated in FIG. 2 .

[0073] As described above, according to one embodiment, the wearable electronic device (300) may have a form factor for being worn on a user's head. The wearable electronic device (300) may further include a strap and / or a wearing member for being secured to a body part of the user. The wearable electronic device (300) may provide a user experience based on augmented reality, virtual reality, and / or mixed reality while being worn on the user's head.

[0074] FIG. 4 is a block diagram of a wearable electronic device (401) according to one embodiment.

[0075] Referring to FIG. 4, in one embodiment, the wearable electronic device (401) may be an AR glass such as the wearable electronic device (200) of FIG. 2 or a VR glass such as the wearable electronic device (300) of FIGS. 3A and 3B.

[0076] In one embodiment, a wearable electronic device (401) may include a display (410), a camera (420), a sensor (430), a memory (440), and / or a processor (450).

[0077] In one embodiment, the display (410) may be the display module (160) of FIG. 1, the light output module (211) of FIG. 2, and / or the display (321) of FIGS. 3A and 3B.

[0078] In one embodiment, the camera (420) may be at least one of the camera module (180) of FIG. 1, the camera module (250) of FIG. 2, and / or the camera modules (311, 312, 313, 314, 315, 316, 325, 326) of FIG. 3a.

[0079] In one embodiment, the camera (420) may include a first camera (421) and a second camera (422).

[0080] In one embodiment, the first camera (421) may be a camera for tracking the user's hand. For example, based on the image acquired through the first camera (421), operations such as detecting the user's hand, acquiring the position of the user's hand, acquiring a skeleton associated with the user's hand, recognizing the user's gesture (e.g., hand movement), and / or rendering the user's hand may be performed. The operation of tracking the user's hand using the first camera (421) will be described in detail below.

[0081] In one embodiment, the first camera (421) may be a stereo camera. For example, the first camera (421) may be a stereo camera including multiple cameras (e.g., two cameras) positioned at different locations on the wearable electronic device (401) and capable of simultaneously acquiring images (e.g., two images) of the same subject. However, the present invention is not limited thereto, and the first camera (421) may also be a single camera capable of tracking a user's hand.

[0082] In one embodiment, the first camera (421) may be the second camera module (253) and / or the third camera module (255) of FIG. 2. In one embodiment, the first camera (421) may be one or more of the plurality of camera modules (313, 314, 315, 316) of FIG. 3A.

[0083] In one embodiment, the second camera (422) may be a camera for acquiring a gaze point of the user's eyes (hereinafter also referred to as a "gaze point"). For example, based on an image acquired through the second camera (422), directions in which the user's two eyes gaze (also referred to as a "gaze direction") may be acquired. Based on the acquired directions and the distance between the two eyes (also referred to as a "binocular disparity"), a gaze point (e.g., a three-dimensional coordinate of the user's eyes gazed) may be acquired (e.g., calculated) using triangulation. An operation for acquiring a gaze point using the second camera (422) will be described in detail below.

[0084] In one embodiment, the second camera (422) may be the first camera module (251) of FIG. 2 or the camera modules (325, 326) of FIG. 3b.

[0085] In one embodiment, the sensor (430) may include a first sensor (431), a second sensor (432), and / or a third sensor (433).

[0086] In one embodiment, the first sensor (431) may be a sensor for tracking a user's hand. For example, the first sensor (431) may be the depth sensor (317) of FIG. 3A. For example, the first sensor (431) may acquire (e.g., sense) data for acquiring information (e.g., a depth map or a depth image) about the distance (or depth) between the wearable electronic device (401) and the user's hand using a time-of-flight (TOF) method (e.g., direct TOF (dTOF) or indirect TOF (iTOF) using light with a certain wavelength (e.g., infrared)) or a structured light method. Based on the data acquired through the first sensor (431), an operation of detecting the user's hand (e.g., whether the hand is within the field of view of the first sensor (431)), an operation of acquiring the position of the user's hand (e.g., the center position of the back of the hand or the center position of the palm), an operation of acquiring a skeleton related to the user's hand, an operation of recognizing the user's gesture (e.g., hand movement), and / or an operation of rendering the user's hand can be performed.

[0087] In one embodiment, the second sensor (432) may be a sensor for acquiring the gaze point of the user's eyes. For example, the second sensor (432) may be a sensor capable of acquiring the directions in which the user's two eyes are gazed. For example, the second sensor (432) may be a sensor capable of acquiring the user's gaze direction by detecting the user's pupil (e.g., the center position of the pupil) and detecting the direction or amount of light, such as infrared light, reflected from the cornea of ​​the user's eyes. Based on the gaze direction and binocular disparity acquired using the second sensor (432), the gaze point may be acquired using triangulation.

[0088] In one embodiment, the third sensor (433) may be a sensor used for head tracking. For example, the third sensor (433) may be a sensor supporting 3 degrees of freedom (3DoF) (3-axis sensor) or a sensor supporting 6DoF (6-axis sensor). Based on sensor data acquired through the third sensor (433), the direction in which the user's head is facing and / or the position of the user's head may be acquired.

[0089] In FIG. 4, the sensor (430) is illustrated as including a first sensor (431), a second sensor (432), and / or a third sensor (433), but is not limited thereto. For example, the sensor (430) may further include at least one component included in the sensor module (176) of FIG. 1. For example, at least one sensor included in the sensor (430) may be included in an electronic device (e.g., a wearable electronic device) external to the wearable electronic device (401). Based on the sensing values ​​acquired from the sensors included in the electronic device external to the wearable electronic device (401), information related to at least one of a hand, a gaze, or a user's head may be acquired.

[0090] In one embodiment, the memory (440) may be the memory (130) of FIG. 1.

[0091] In one embodiment, the memory (440) may store information for performing hand tracking.

[0092] In one embodiment, the memory (440) may include a hand tracking module (441), an eye tracking module (442), a hand rendering module (443), and / or a head tracking module (444).

[0093] In one embodiment, the hand tracking module (441) may include instructions that, when executed by the processor (450), are configured to cause the wearable electronic device (401) to perform hand tracking.

[0094] In one embodiment, the eye tracking module (442) may include instructions that, when executed by the processor (450), are configured to cause the wearable electronic device (401) to perform eye tracking.

[0095] In one embodiment, the hand rendering module (443) may include instructions that, when executed by the processor (450), are configured to cause the wearable electronic device (401) to generate a virtual hand (or hand model) representing a user's hand and to display the generated virtual hand through the display (410).

[0096] The operations performed by the hand tracking module (441), the eye tracking module (442), and the hand rendering module (443) will be described in detail later with reference to FIGS. 5 to 13.

[0097] In one embodiment, the head tracking module (444) may include instructions that, when executed by the processor (450), are configured to cause the wearable electronic device (401) to obtain a direction toward which the wearable electronic device (401) (or the face of a user wearing the wearable electronic device (401)) is facing and a position of the wearable electronic device (401) within a coordinate system of a three-dimensional space (e.g., a three-dimensional real space or a three-dimensional virtual space). For example, when the wearable electronic device (401) is powered on or an application is executed on the wearable electronic device (401), a coordinate system of the three-dimensional space may be set based on the position and direction of the wearable electronic device (401) obtained through the third sensor (433). The head tracking module (444) can obtain the changed position and / or direction of the wearable electronic device (401) within the coordinate system of the three-dimensional space based on data obtained through the third sensor (433) when the position of the wearable electronic device (401) changes (e.g., when the position of the wearable electronic device (401) changes due to movement of the user wearing the wearable electronic device (401)) and / or when the direction of the wearable electronic device (401) changes (e.g., when the head of the user wearing the wearable electronic device (401) rotates) after the coordinate system of the three-dimensional space is set. The changed position and / or orientation of the wearable electronic device (401) within the coordinate system of the three-dimensional space can be used to obtain the position of the user's hand (e.g., the three-dimensional coordinates of the user's hand within the coordinate system of the three-dimensional space) and the gaze point (e.g., the three-dimensional coordinates of the point at which the user gazes within the coordinate system of the three-dimensional space).

[0098] In one embodiment, the memory (440) is illustrated in FIG. 4 as including, but not limited to, a hand tracking module (441), an eye tracking module (442), a hand rendering module (443), and / or a head tracking module (444). For example, the memory (440) may further include a gesture recognition module for recognizing a user's gestures (e.g., hand movements).

[0099] In one embodiment, the examples described above illustrate, but are not limited to, the hand tracking module (441), the eye tracking module (442), the hand rendering module (443), and / or the head tracking module (444) as software included in the memory (440). At least one of the hand tracking module (441), the eye tracking module (442), the hand rendering module (443), and / or the head tracking module (444) may be included in the wearable electronic device (401) as hardware.

[0100] In one embodiment, although the hand tracking module (441), the eye tracking module (442), the hand rendering module (443), and / or the head tracking module (444) are illustrated as independent components in FIG. 4, this is not limiting. For example, at least some of the hand tracking module (441), the eye tracking module (442), the hand rendering module (443), and / or the head tracking module (444) may be implemented as integrated modules.

[0101] In one embodiment, the processor (450) may be the processor (120) of FIG. 1.

[0102] In one embodiment, the processor (450) may control the overall operation of performing hand tracking. In one embodiment, the processor (450) may include one or more processors for performing hand tracking.

[0103] Hereinafter, with reference to FIGS. 5 to 13, the operation of the processor (450) performing hand tracking will be described.

[0104] In FIG. 4, a wearable electronic device (401) is illustrated as including, but not limited to, a display (410), a camera (420), a sensor (430), a memory (440), and / or a processor (450).

[0105] In one embodiment, the wearable electronic device (401) may not include some of the components illustrated in FIG. 4. For example, the wearable electronic device (401) may include one of a first camera (421) and a first sensor (431) as components for performing hand tracking. For example, the wearable electronic device (401) may include one of a second camera (422) and a second sensor (432) as components for performing eye tracking.

[0106] In one embodiment, the wearable electronic device (401) may further include at least one component in addition to the components illustrated in FIG. 4. For example, the wearable electronic device (401) may further include a strap and / or a wearing member for securing the wearable electronic device (401) to a body part of a user (e.g., the user's head). For example, the wearable electronic device (401) may further include at least one component (e.g., the communication module (190)) included in the electronic device (101) of FIG. 1.

[0107] FIG. 5 is a flowchart (500) for explaining a method of performing hand tracking according to one embodiment.

[0108] Referring to FIG. 5, in operation 501, in one embodiment, the processor (450) may obtain (e.g., calculate) the position of the user's hand based on an image obtained through the first camera (421) (hereinafter referred to as "the first image" or "at least one first image").

[0109] In one embodiment, the processor (450) may activate the first camera (421) based on an application being executed on the wearable electronic device (401). The processor (450) may acquire a first image (e.g., at least one first image) using the activated first camera (421).

[0110] In one embodiment, the processor (450) may activate the first camera (421) based on the wearable electronic device (401) being powered on (or turned on). The processor (450) may acquire at least one first image using the activated first camera (421).

[0111] In one embodiment, the processor (450) can acquire multiple (e.g., two) first images via a first camera (421) (e.g., a stereo camera including multiple (e.g., two) cameras positioned at different locations on the wearable electronic device (401) and capable of simultaneously acquiring multiple (e.g., two) images of the same subject).

[0112] In one embodiment, the processor (450) can acquire the position of the user's hand based on at least one first image. Hereinafter, with reference to FIG. 6, an operation of acquiring the position of the user's hand based on at least one first image will be described.

[0113] FIG. 6 is a drawing (600) for explaining a method for obtaining the position of a user's hand according to one embodiment.

[0114] Referring to FIG. 6, in one embodiment, reference numeral 610 may represent a first image (e.g., one of two first images when the first camera (421) is a stereo camera).

[0115] In one embodiment, the processor (450) may detect a user's hand (e.g., hands (621, 622)) within the first image (610) and obtain (e.g., calculate) the position (e.g., two-dimensional coordinates) of the user's hand.

[0116] In one embodiment, the processor (450) may detect the user's hand in the first image (610) using an artificial intelligence model and obtain the coordinates of the user's hand. For example, the processor (450) may input the first image (610) as input data to an artificial intelligence engine using an artificial intelligence model related to hand detection. The processor (450) may obtain, from the artificial intelligence engine, as output data, an area representing the hand in the first image (610) and a location of the hand (e.g., points (631, 632)) (e.g., the center point of the palm or the center point of the hand, etc.). In the above example, the artificial intelligence model is used to detect the user's hand and obtain the coordinates of the hand, but the present invention is not limited thereto. For example, the processor (450) may detect the user's hand in the first image (610) and obtain the coordinates of the user's hand using an algorithm related to hand detection.

[0117] In one embodiment, the processor (450) may obtain (e.g., generate) a bounding box based on the acquisition of an area representing a hand and a location of the hand (e.g., points (631, 632)) within the first image (610). For example, the processor (450) may generate a bounding box indicating an area including an area representing a hand based on the location of the hand. For example, in FIG. 6, the processor (450) may generate a bounding box (641) indicating a boundary line of an area including an area representing a hand (621) with point (631) set as a center point, and a bounding box (642) indicating a boundary line of an area including an area representing a hand (622) with point (632) set as a center point within the first image (610). In one embodiment, the area including the area representing the hand is not limited to the bounding box (e.g., bounding box (641), bounding box (642)). For example, the shape of the area including the area representing the hand may include various shapes (e.g., a circle, an ellipse, or an irregular shape) including the area representing the hand.

[0118] In one embodiment, the processor (450) may crop an area indicated by a bounding box (e.g., bounding boxes (641, 642)) from the first image (610). The cropped area may be used in an operation of obtaining a skeleton in operation 507, which will be described later.

[0119] In one embodiment, the processor (450) can obtain a three-dimensional position of the hand based on a two-dimensional position of the hand acquired from at least one first image. For example, the processor (450) can obtain two two-dimensional positions of the hand from two first images acquired through two cameras (e.g., stereo cameras). The processor (450) can obtain a three-dimensional position of the hand (e.g., three-dimensional coordinates of the hand) relative to the position and direction of the wearable electronic device (401) (e.g., based on the current position and current direction of the wearable electronic device (401) acquired using the third sensor (433)) based on the obtained two-dimensional positions of the hand and a positional difference between the two cameras (e.g., disparity between the two cameras). The processor (450) can obtain a three-dimensional position of the hand (e.g., three-dimensional coordinates of the hand within a coordinate system of the virtual space) within a coordinate system of a virtual space (e.g., real space) based on the current position and current direction of the wearable electronic device (401) and the three-dimensional position of the hand relative to the position and direction of the wearable electronic device (401).

[0120] In the examples described above, the operation of obtaining the position of the hand using a stereo camera as the first camera (421) is described, but is not limited thereto. For example, the processor (450) may obtain the position of the hand using the first sensor (431) (e.g., a depth sensor) instead of or in addition to the first camera (421). For example, the processor (450) may obtain depth information (e.g., a depth map or a depth image) through the first sensor (431). Based on the depth information, the processor (450) may determine whether the user's hand exists within the field of view of the first sensor (431) (e.g., whether the user's hand is positioned) and obtain the position of the hand (e.g., 3D coordinates of the hand within a virtual space coordinate system).

[0121] Referring back to FIG. 5, in operation 503, in one embodiment, the processor (450) may acquire a user's gaze point (or point of gaze) (hereinafter also referred to as "gaze point") based on an image acquired through the second camera (422) (hereinafter referred to as "second image" or "at least one second image"). Hereinafter, an operation of acquiring a gaze point will be described with reference to FIG. 7.

[0122] FIG. 7 is a diagram illustrating a method for obtaining a user's gaze point according to one embodiment.

[0123] Referring to FIG. 7, in one embodiment, the method for obtaining the gaze point described through FIG. 7 may be a pupil center corneal reflection (PCCR) method.

[0124] In one embodiment, corneal reflectivity may be utilized for eye tracking. For example, corneal reflectivity may be a method for obtaining at least one image of the light source reflected from the cornea and lens of the eye when an infrared light source is incident on the user's eye, thereby obtaining the direction and point of gaze.

[0125] In one embodiment, the processor (450) may acquire two second images for both eyes of the user using a second camera (422) (e.g., a 2-1 camera configured to acquire a second image for the left eye and a 2-2 camera configured to acquire a second image for the right eye). In one embodiment, the second image (710) at reference numerals 701 and 702 may represent the second image for the left eye.

[0126] In one embodiment, the processor (450) may control a light emitting unit (e.g., a light emitting diode (LED)) to cause light (e.g., infrared light) emitted (e.g., luminescence) from the light emitting unit to be incident on the user's eyes. For example, the processor (450) may control a plurality of light emitting units so that a plurality of lights emitted from each of the plurality of light emitting units are incident on the user's eyes.

[0127] In one embodiment, the processor (450) can acquire at least one second image of the user's eye through the second camera (422) while the light emitter is emitting light.

[0128] In one embodiment, the processor (450) may obtain, within at least one second image, a location of a pupil (e.g., a center point of the pupil) and a location of a glint (e.g., a glint caused by light emitted from a light emitting unit reflecting into the user's eye). For example, in reference numeral 701, the processor (450) may obtain, within the second image (710), a location of a pupil (721) of a left eye (733) (e.g., a center position of the pupil (721)) and locations of a plurality of glints (731) caused by a plurality of lights.

[0129] In one embodiment, the processor (450) may obtain a user's gaze direction (e.g., a two-dimensional gaze direction) based on the positions of the plurality of glints (731) and the position of the pupil (721). For example, in reference numeral 702, the processor (450) may obtain a gaze vector (720) representing (or corresponding to) the user's gaze direction (e.g., a two-dimensional gaze direction) based on the center positions (732) of the plurality of glints (731) and the position of the pupil (721).

[0130] In one embodiment, the position of the pupil (721) may change due to movement of the user's eyes (e.g., a change in the user's gaze direction), while the positions of the plurality of glints (731) (and the center points (732) of the plurality of glints (731)) may be positions that do not change (e.g., fixed positions) even when movement of the user's eyes occurs. Accordingly, when movement of the user's eyes occurs, the gaze vector (720) may change.

[0131] In one embodiment, although FIG. 7 describes an operation for obtaining a gaze vector (720) for the left eye (733), it is not limited thereto. In one embodiment, the processor (450) can obtain a gaze vector indicating a gaze direction (e.g., a two-dimensional gaze direction) of the right eye by performing operations identical or similar to those described through FIG. 7.

[0132] In one embodiment, the processor (450) can obtain a three-dimensional gaze direction of the left eye and a three-dimensional gaze direction of the right eye based at least in part on the gaze vector of the left eye (e.g., a gaze vector representing a two-dimensional gaze direction of the left eye) and the gaze vector of the right eye (e.g., a gaze vector representing a two-dimensional gaze direction of the right eye).

[0133] In one embodiment, as illustrated in reference numeral 703, the processor (450) may obtain a gaze point (761) (e.g., a position where the gaze direction of the left eye and the gaze direction of the right eye converge) relative to the position and direction of the wearable electronic device (401) using triangulation based on a three-dimensional gaze direction (741) of the left eye (751), a three-dimensional gaze direction (742) of the right eye (752), and an inter-ocular distance (binocular disparity) (d) (e.g., about 6.5 cm).

[0134] In one embodiment, the processor (450) may obtain a gaze point within a coordinate system of a virtual space (e.g., real space) based on the position and orientation of the wearable electronic device (401) and the gaze point relative to the position and orientation of the wearable electronic device (401).

[0135] In one embodiment, PCCR is illustrated in FIG. 7 using a plurality of light emitters and a second camera (422), but is not limited thereto. In one embodiment, the processor (450) may acquire a gaze point using a second sensor (432) instead of or in addition to the second camera (422). For example, the processor (450) may acquire a gaze point using a second sensor (432) including a light emitter that includes a scanning mirror that controls the direction of light (e.g., can change the angle at which light is directed toward the eye) and a light receiver that receives the light. The processor (450) may control the light emitter to emit light whose direction is changed through the scanning mirror. The processor (450) can obtain a location (e.g., a central location of the cornea) where light is reflected in the user's eye at a point in time when the intensity (e.g., light quantity) of light reflected in the user's eye (e.g., light obtained through the light receiving unit) is at its maximum while controlling the light emitting unit. The processor (450) can determine a direction connecting the obtained location and the central location of the user's eye as the user's gaze direction. The processor (450) can obtain a gaze point based on the gaze directions of both eyes and the distance between the two eyes.

[0136] However, the methods for obtaining the gaze point are not limited to the examples described above.

[0137] Referring back to FIG. 5, although FIG. 5 illustrates that the operation of acquiring the hand position in operation 501 is performed prior to the operation of acquiring the gaze point in operation 503, this is not limited thereto. For example, the processor (450) may perform operations 501 and 503 in parallel (or simultaneously). For example, the processor (450) may perform the operation of acquiring the gaze point in operation 503 when the hand position is acquired in operation 501 (e.g., when a hand is detected within at least one first image).

[0138] In operation 505, in one embodiment, the processor (450) may determine whether the position of the hand corresponds to the gaze point.

[0139] In one embodiment, the processor (450) may determine whether the distance between the hand position (e.g., points (631, 632) of FIG. 6) and the gaze point (e.g., gaze point (761) of FIG. 7) is less than or equal to a specified distance. For example, the processor (450) may determine whether the distance between the three-dimensional coordinates of the hand and the three-dimensional coordinates of the gaze point within the coordinate system of the virtual space is less than or equal to a specified distance.

[0140] In one embodiment, a hand position may correspond to a gaze point if the distance between the hand position and the gaze point is less than or equal to a specified distance. A hand position not corresponding to a gaze point may correspond to a hand position if the distance between the hand position and the gaze point exceeds a specified distance.

[0141] In operation 507, in one embodiment, the processor (450) may acquire a skeleton including key points associated with the hand based on whether the position of the hand corresponds to the gaze point. The operation of acquiring the skeleton in operation 507 will be described below with reference to FIG. 8.

[0142] FIG. 8 is a drawing (800) for explaining an operation of obtaining a skeleton according to one embodiment.

[0143] Referring to FIG. 8, in one embodiment, a skeleton may include key points (also referred to as “feature points,” “nodes,” or “joints”) and lines connecting the key points. For example, in FIG. 8, a skeleton (811) associated with (e.g., corresponding to) the left hand (621) may include key points (e.g., key points (821)) and lines connecting the key points (e.g., line (831)), and a skeleton (812) associated with the right hand may include key points (e.g., key points (822)) and lines connecting the key points (e.g., line (832)).

[0144] In one embodiment, the processor (450) may acquire a skeleton associated with a hand based on an artificial intelligence model related to skeleton acquisition. For example, the processor (450) may input, as input data, a bounding box (e.g., bounding boxes (641, 642) of FIG. 6) and a cropped region from at least one first image (e.g., a region cropped from at least one first image through operation 501) into an artificial intelligence engine using an artificial intelligence model related to skeleton acquisition. The processor (450) may acquire, from the artificial intelligence engine, a skeleton (e.g., skeletons (811, 812)) including key points (e.g., two-dimensional coordinates of key points or three-dimensional coordinates of key points in a coordinate system of a virtual space) as output data.

[0145] In the above example, although it is illustrated that a skeleton related to a hand is obtained using an artificial intelligence model, the present invention is not limited thereto. For example, the processor (450) may obtain a skeleton related to a hand using an algorithm related to skeleton acquisition. For example, in order to obtain a shape related to a hand, the processor (450) may extract features of parts corresponding to a hand from an input image and distinguish the poses of the hand. For example, the processor (450) may learn patterns for each part of the hand through artificial intelligence, classify the acquired images according to each pattern, classify each part of the hand, and identify the pose of the hand. According to one embodiment, the processor (450) may utilize an SVM, which is one type of algorithm and a machine learning algorithm, to find a data set that is closest to the features of the hand in the input image and output the data set as a determination result. In addition, the processor (450) can identify the pattern by distinguishing the hand movements using HMM for dynamic pattern analysis of the hand or DTW for not being affected by the speed or time of a specific movement.

[0146] Referring back to FIG. 5 , in one embodiment, the processor (450) may not perform the operation of acquiring a skeleton including key points associated with the hand based on the hand's position not corresponding to the gaze point. For example, the processor (450) may not perform the operation of acquiring the skeleton based on the distance between the hand's position and the gaze point exceeding a specified distance. For example, the processor (450) may continue to perform operations 501 and 503 without performing the operation of acquiring the skeleton based on the hand's position not corresponding to the gaze point.

[0147] In operation 509, in one embodiment, the processor (450) may perform a hand-related operation based on the acquired skeleton.

[0148] In one embodiment, the processor (450) may perform an operation to recognize a user's gesture (e.g., hand movement) based on the acquired skeleton. For example, the processor (450) may recognize a user's gesture (e.g., a grab gesture, a drag gesture using a finger, a drop gesture using a finger) using an artificial intelligence model (e.g., a gesture classification model or algorithm) related to gesture recognition based on coordinates (e.g., 3D coordinates) of key points included in the skeleton. For example, the processor (450) may perform an operation to recognize a user's gesture based on the shape of the skeleton (or a change in the shape of the skeleton).

[0149] In one embodiment, the processor (450) may perform an operation of rendering the user's hand based on the acquired skeleton. The operation of rendering the user's hand will be described below with reference to FIG. 9.

[0150] FIG. 9 is a drawing (900) for explaining an operation of rendering a virtual hand according to one embodiment.

[0151] Referring to FIG. 9, in one embodiment, the processor (450) may generate a virtual hand corresponding to a hand based on a skeleton corresponding to the hand. For example, the processor (450) may identify a hand model for hand rendering. Using the hand model, the processor (450) may generate a virtual hand corresponding to (e.g., mapped to) the acquired skeleton obtained through operation 507.

[0152] In one embodiment, the processor (450) may display the generated virtual hand at the position of the acquired skeleton (e.g., coordinates of key points included in the skeleton (e.g., 3D coordinates)) through the display (410). For example, the processor (450) may display a screen (910) including virtual hands (911, 912) (e.g., a screen for the left eye) and a screen (920) including virtual hands (921, 922) (e.g., a screen for the right eye) through the display (410), as illustrated in FIG. 9.

[0153] Referring back to FIG. 5, in one embodiment, the processor (450) may perform an operation of recognizing a user's gesture (e.g., a hand movement) and an operation of rendering a hand based on the acquired skeleton. However, the operations performed by the processor (450) based on the skeleton are not limited to the operation of recognizing a user's gesture and the operation of rendering a hand.

[0154] In one embodiment, the processor (450) may perform operations 501 and / or 503 without performing operations 505 to 507 if, during or after performing operation 507, the position of the hand is not acquired within at least one first image acquired through the first camera (421) (e.g., if the hand is not detected within the at least one first image).

[0155] FIG. 10 is a flowchart (1000) for explaining a method of performing hand tracking according to one embodiment.

[0156] In one embodiment, the operations of FIG. 10 may be operations included in operations 501 and 503 of FIG. 5.

[0157] Referring to FIG. 10, in operation 1001, in one embodiment, the processor (450) may determine whether the position of the user's hand is acquired based on at least one first image acquired through the first camera (421).

[0158] In one embodiment, operation 1001 is at least partially identical or similar to operation 501 of FIG. 5, so redundant description will be omitted.

[0159] In one embodiment, the processor (450) can determine whether the location of the user's hand is acquired by determining whether the user's hand is detected within (or from) at least one first image (e.g., whether an area corresponding to the user's hand exists within the at least one first image). For example, the processor (450) can determine that the location of the user's hand is acquired based on the detection of the user's hand within the at least one first image. For example, the processor (450) can determine that the location of the user's hand is not acquired based on the non-detection of the user's hand within the at least one first image.

[0160] In one embodiment, the processor (450) may repeatedly (or continuously) perform operation 1001 if the position of the user's hand is not obtained in operation 1001.

[0161] When the position of the user's hand is acquired in operation 1001, in one embodiment, in operation 1003, the processor (450) may acquire the user's gaze point based on at least one second image acquired through the second camera (422).

[0162] In one embodiment, the processor (450) may perform an operation of acquiring a gaze point based on at least one second image when a hand position is acquired within at least one first image. For example, the processor (450) may initiate an operation of acquiring a gaze point based on at least one second image when a hand position is acquired within at least one first image.

[0163] FIG. 11 is a flowchart (1100) for explaining a method of performing hand tracking according to one embodiment.

[0164] FIG. 12 is a drawing (1200) for explaining a method of performing hand tracking according to one embodiment.

[0165] Referring to FIGS. 11 and 12, in operation 1101, in one embodiment, the processor (450) may obtain the position of the user's hand based on an image obtained through the first camera (421).

[0166] In one embodiment, operation 1101 is at least partially identical or similar to operation 501 of FIG. 5, and therefore a detailed description thereof will be omitted.

[0167] In operation 1103, in one embodiment, the processor (450) may acquire the user's gaze point based on an image acquired through the second camera (422).

[0168] In one embodiment, operation 1103 is at least partially identical or similar to operation 503 of FIG. 5, and thus a detailed description thereof will be omitted.

[0169] In operation 1105, in one embodiment, the processor (450) may determine whether the position of the hand corresponds to the gaze point.

[0170] In one embodiment, operation 1105 is at least partially identical or similar to operation 505 of FIG. 5, and thus a detailed description thereof will be omitted.

[0171] In operation 1107, in one embodiment, the processor (450) may determine whether an object is located within a specified distance from the position of the hand. For example, if the position of the hand corresponds to the gaze point in operation 1105, the processor (450) may determine whether an object is located within a specified distance from the position of the hand.

[0172] In one embodiment, an object (also referred to as a “user interface”) may be an object that is placed in a virtual space set by the wearable electronic device (401) and can interact with a user. For example, the object may include an icon, widget, image, text, and / or window that is placed in a virtual space set by the wearable electronic device (401) and can be executed by user input. However, the object is not limited to the examples described above.

[0173] In one embodiment, in FIG. 12, reference numeral 1210 may represent a real space shown to a user wearing a wearable electronic device (401). In one embodiment, the processor (450) may display an object (1240) (e.g., a virtual object) within the real space (1210) through the display (410).

[0174] In one embodiment, in FIG. 12, the processor (450) can determine whether the distance (d2) between the position (1221) of the user's hand (1220) and the position (1241) of the object (1240) is less than or equal to a specified distance, based on the distance (d1) between the position (1221) of the user's hand (1220) (e.g., the center position of the back of the hand) and the gaze point (1231) being less than or equal to a specified distance.

[0175] In one embodiment, a specified distance (d1) compared to a position (1221) of the user's hand (1220) (e.g., the center position of the back of the hand) and a gaze point (1231) may be set to be the same as or different from a distance (d2) compared to a position (1221) of the user's hand (1220) and a position (1241) of the object (1240).

[0176] In operation 1109, in one embodiment, the processor (450) may obtain a skeleton including key points associated with the hand based on the object being located within a specified distance from the position of the hand in operation 1107.

[0177] In one embodiment, the processor (450) may perform operation 1101 (and operation 1103) without performing the operation of acquiring the skeleton based on the object not being located within a specified distance from the position of the hand in operation 1107.

[0178] In one embodiment, operation 1109 is at least partially identical or similar to operation 507 of FIG. 5, so redundant description will be omitted.

[0179] In operation 1111, in one embodiment, the processor (450) may perform an operation based on the acquired skeleton.

[0180] In one embodiment, operation 1111 is at least partially identical or similar to operation 509 of FIG. 5, and therefore a detailed description thereof will be omitted.

[0181] FIG. 13 is a flowchart (1300) for explaining a method of performing hand tracking according to one embodiment.

[0182] In one embodiment, the operations of FIG. 13 may be operations included in operations 501 and 503 of FIG. 5.

[0183] Referring to FIG. 13, in operation 1301, in one embodiment, the processor (450) may determine whether the position of the user's hand is acquired based on at least one first image acquired through the first camera (421).

[0184] In one embodiment, operation 1301 is at least partially identical or similar to operation 501 of FIG. 5, so overlapping descriptions will be omitted.

[0185] In one embodiment, the processor (450) may determine whether the location of the user's hand is acquired by determining whether the user's hand is detected within (or from) at least one of the first images. For example, the processor (450) may determine that the location of the user's hand is acquired based on the detection of the user's hand within the at least one first image. For example, the processor (450) may determine that the location of the user's hand is not acquired based on the non-detection of the user's hand within the at least one first image.

[0186] If the position of the user's hand is not acquired in operation 1301, in one embodiment, in operation 1303, the processor (450) may set the second camera (422) to acquire images (at least one second image) at a first frame rate (e.g., a first frame per second (FPS)).

[0187] In one embodiment, the processor (450) can obtain a gaze point based on at least one second image acquired at a first frame rate through a second camera (422).

[0188] If the position of the user's hand is acquired in operation 1301, in one embodiment, in operation 1305, the processor (450) may set the second camera (422) to acquire images (at least one second image) at a second frame rate (e.g., a second FPS (frame per second)) higher than the first frame rate.

[0189] In one embodiment, the processor (450) can obtain a gaze point based on at least one second image acquired at a second frame rate through a second camera (422).

[0190] In one embodiment, the processor (450) may control the second camera (422) to acquire at least one second image at a second frame rate that is higher than the first frame rate when a hand is detected within the at least one first image, thereby allowing a more accurate (or precise) gaze point to be acquired when a hand is detected within the at least one first image.

[0191] In one embodiment, the processor (450) may control the second camera (422) to acquire at least one second image at a first frame rate that is lower than the second frame rate when no hand is detected in the at least one first image, thereby reducing power consumed by the wearable electronic device (401) while no hand is detected in the at least one first image.

[0192] A wearable electronic device (401) according to one embodiment may include a camera (420) including a first camera (421) and a second camera (422), a display (410), at least one processor (450), and a memory (440) storing instructions. The instructions, when executed by the at least one processor (450), may cause the wearable electronic device (401) to acquire a position of a user's hand based on at least one first image acquired through the first camera (421). The instructions, when executed by the at least one processor (450), may cause the wearable electronic device (401) to acquire a gaze point of the user based on at least one second image acquired through the second camera (422). The above commands, when executed by the at least one processor (450), may cause the wearable electronic device (401) to determine whether the position of the hand corresponds to the gaze point. The above commands, when executed by the at least one processor (450), may cause the wearable electronic device (401) to obtain a skeleton including key points associated with the hand based on whether the position of the hand corresponds to the gaze point. The above commands, when executed by the at least one processor (450), may cause the wearable electronic device (401) to perform an action associated with the hand based on the obtained skeleton.

[0193] In one embodiment, the instructions, when executed by the at least one processor (450), may cause the wearable electronic device (401) to obtain, within the at least one first image, an area representing the hand and the position of the hand. The instructions, when executed by the at least one processor (450), may cause the wearable electronic device (401) to obtain a bounding box indicating an area including the area representing the hand based on the position of the hand.

[0194] In one embodiment, the instructions, when executed by the at least one processor (450), may cause the wearable electronic device (401) to perform an operation of acquiring the gaze point of the user based on the acquisition of the position of the hand.

[0195] In one embodiment, the instructions, when executed by the at least one processor (450), may cause the wearable electronic device (401) to obtain a location of a pupil of the user within the at least one second image. The instructions, when executed by the at least one processor (450), may cause the wearable electronic device (401) to obtain locations of glints displayed within the at least one second image by light emitted from a plurality of light-emitting units of the electronic device reflected into the eye of the user within the at least one second image. The instructions, when executed by the at least one processor (450), may cause the wearable electronic device (401) to obtain the gaze point of the user based on a center location of the glints and a location of the pupil obtained based on the locations of the glints.

[0196] In one embodiment, the instructions, when executed by the at least one processor (450), may cause the wearable electronic device (401) to determine whether the distance between the position of the hand and the gaze point is less than or equal to a specified distance.

[0197] In one embodiment, the instructions, when executed by the at least one processor (450), may cause the wearable electronic device (401) to perform an operation to acquire the skeleton based on a distance between the position of the hand and the point of gaze being less than or equal to a specified distance. The operation to acquire the skeleton may not be performed based on a distance between the position of the hand and the point of gaze exceeding a specified distance.

[0198] In one embodiment, the instructions, when executed by the at least one processor (450), may cause the wearable electronic device (401) to recognize a gesture indicated by a movement of the user's hand based on the acquired skeleton.

[0199] In one embodiment, the instructions, when executed by the at least one processor (450), may cause the wearable electronic device (401) to display a virtual hand corresponding to the hand of the user through the display (410) based on the acquired skeleton.

[0200] In one embodiment, the instructions, when executed by the at least one processor (450), may cause the wearable electronic device (401) to determine whether an object is located within a specified distance from a position of the hand based on whether the position of the hand corresponds to the gaze point. The instructions, when executed by the at least one processor (450), may cause the wearable electronic device (401) to acquire the skeleton based on whether the object is located within the specified distance from the position of the hand.

[0201] In one embodiment, the instructions, when executed by the at least one processor (450), may cause the wearable electronic device (401) to control the second camera (422) to acquire the at least one second image at a first frame rate when the position of the hand of the user is not acquired. The instructions, when executed by the at least one processor (450), may cause the wearable electronic device (401) to control the second camera (422) to acquire the at least one second image at a second frame rate higher than the first frame rate when the position of the hand of the user is acquired.

[0202] A method for performing hand tracking in a wearable electronic device (401) according to one embodiment may include an operation of acquiring a position of a user's hand based on at least one first image acquired through a first camera (421) of the wearable electronic device (401). The method may include an operation of acquiring a gaze point of the user based on at least one second image acquired through a second camera (422) of the wearable electronic device (401). The method may include an operation of determining whether the position of the hand corresponds to the gaze point. The method may include an operation of acquiring a skeleton including key points related to the hand based on whether the position of the hand corresponds to the gaze point. The method may include an operation of performing an action related to the hand based on the acquired skeleton.

[0203] In one embodiment, the operation of obtaining the position of the user's hand may include an operation of obtaining an area representing the hand and the position of the hand within the at least one first image. The operation of obtaining the position of the user's hand may include an operation of obtaining a bounding box indicating an area including the area representing the hand based on the position of the hand.

[0204] In one embodiment, the action of obtaining the user's gaze point may include performing the action of obtaining the user's gaze point based on the position of the hand being obtained.

[0205] In one embodiment, the operation of obtaining the user's gaze point may include obtaining a position of a pupil of the user within the at least one second image. The operation of obtaining the user's gaze point may include obtaining positions of glints displayed within the at least one second image by light emitted from a plurality of light-emitting units of the electronic device reflected into an eye of the user within the at least one second image. The operation of obtaining the user's gaze point may include obtaining the user's gaze point based on a center position of the glints and a position of the pupil obtained based on the positions of the glints.

[0206] In one embodiment, the act of determining whether the position of the hand corresponds to the gaze point may include the act of determining whether the distance between the position of the hand and the gaze point is less than or equal to a specified distance.

[0207] In one embodiment, the action of acquiring the skeleton may include performing the action of acquiring the skeleton based on a distance between the position of the hand and the gaze point being less than or equal to a specified distance. The action of acquiring the skeleton may not be performed based on a distance between the position of the hand and the gaze point exceeding a specified distance.

[0208] In one embodiment, the action of performing the hand-related action may include an action of recognizing a gesture indicated by the movement of the user's hand based on the acquired skeleton.

[0209] In one embodiment, the action of performing the hand-related action may include an action of displaying a virtual hand corresponding to the hand of the user through the display (410) of the wearable electronic device (401) based on the acquired skeleton.

[0210] In one embodiment, the action of performing the hand-related action may include an action of determining whether an object is located within a specified distance from a position of the hand, based on whether the position of the hand corresponds to the gaze point. The action of performing the hand-related action may include an action of obtaining the skeleton, based on whether the object is located within the specified distance from the position of the hand.

[0211] In one embodiment, the method may further include an operation of controlling the second camera (422) to acquire the at least one second image at a first frame rate when the position of the hand of the user is not acquired. The method may further include an operation of controlling the second camera (422) to acquire the at least one second image at a second frame rate higher than the first frame rate when the position of the hand of the user is acquired.

[0212] In one embodiment, a non-transitory computer-readable storage medium having computer-executable instructions recorded thereon may cause the wearable electronic device (401) to obtain a position of a hand of a user based on at least one first image acquired through a first camera (421) of the wearable electronic device (401), when executed by at least one processor (450) of the wearable electronic device (401). The computer-executable instructions may cause the wearable electronic device (401) to obtain a gaze point of the user based on at least one second image acquired through a second camera (422) of the wearable electronic device (401). The computer-executable instructions, when executed by at least one processor (450) of the wearable electronic device (401), may cause the wearable electronic device (401) to determine whether the position of the hand corresponds to the gaze point. The computer-executable instructions, when executed by at least one processor (450) of the wearable electronic device (401), may cause the wearable electronic device (401) to obtain a skeleton including key points associated with the hand based on whether the position of the hand corresponds to the gaze point. The computer-executable instructions, when executed by at least one processor (450) of the wearable electronic device (401), may cause the wearable electronic device (401) to perform an action associated with the hand based on the obtained skeleton.

[0213] Additionally, the structure of the data used in the embodiments of the present disclosure described above can be recorded on a computer-readable recording medium through various means. The computer-readable recording medium includes storage media such as magnetic storage media (e.g., ROM, floppy disk, hard disk, etc.) and optical reading media (e.g., CD-ROM, DVD, etc.).

Claims

1. In a wearable electronic device (401), A camera (420) including a first camera (421) and a second camera (422); display (410); At least one processor (450); and Contains a memory (440) for storing commands, The above instructions, when executed by the at least one processor (450), cause the wearable electronic device (401) to: Based on at least one first image acquired through the first camera (421), the position of the user's hand is acquired, Based on at least one second image acquired through the second camera (422), the gaze point of the user is acquired, Check whether the position of the above hand corresponds to the above gaze point, Based on the position of the hand corresponding to the gaze point, a skeleton including key points related to the hand is obtained, and A wearable electronic device (401) that causes a hand-related movement to be performed based on the acquired skeleton.

2. In paragraph 1, The above instructions, when executed by the at least one processor (450), cause the wearable electronic device (401) to: In the at least one first image, obtaining an area representing the hand and the position of the hand, and A wearable electronic device (401) that causes a bounding box to be obtained that indicates an area including an area representing the hand based on the position of the hand.

3. In paragraph 1 or 2, The above instructions, when executed by the at least one processor (450), cause the wearable electronic device (401) to: A wearable electronic device (401) that causes an action to be performed to acquire the gaze point of the user based on acquiring the position of the hand.

4. In any one of paragraphs 1 to 3, The above instructions, when executed by the at least one processor (450), cause the wearable electronic device (401) to: Obtaining the position of the pupil of the user within at least one of the second images, In the at least one second image, positions of glints displayed in the at least one second image are obtained by reflecting light emitted from a plurality of light-emitting units of the wearable electronic device (401) to the user's eyes, and A wearable electronic device (401) that causes the user's gaze point to be acquired based on the center position of the glints and the position of the pupil acquired based on the positions of the glints.

5. In any one of paragraphs 1 to 4, The above instructions, when executed by the at least one processor (450), cause the wearable electronic device (401) to: A wearable electronic device (401) that causes the user to determine whether the distance between the position of the hand and the gaze point is less than or equal to a specified distance.

6. In any one of paragraphs 1 to 5, The above instructions, when executed by the at least one processor (450), cause the wearable electronic device (401) to: Causing an action to acquire the skeleton to be performed based on the distance between the position of the hand and the gaze point being less than or equal to a specified distance. A wearable electronic device (401) in which an action of acquiring the skeleton is not performed based on a distance between the position of the hand and the point of gaze exceeding a specified distance.

7. In any one of paragraphs 1 to 6, The above instructions, when executed by the at least one processor (450), cause the wearable electronic device (401) to: A wearable electronic device (401) that causes the user to recognize a gesture indicated by the movement of the hand based on the acquired skeleton.

8. In any one of paragraphs 1 to 7, The above instructions, when executed by the at least one processor (450), cause the wearable electronic device (401) to: A wearable electronic device (401) that causes a virtual hand corresponding to the hand of the user to be displayed through the display (410) based on the acquired skeleton.

9. In any one of paragraphs 1 to 8, The above instructions, when executed by the at least one processor (450), cause the wearable electronic device (401) to: Based on whether the position of the hand corresponds to the gaze point, it is determined whether an object is located within a specified distance from the position of the hand, and A wearable electronic device (401) that causes the skeleton to be acquired based on the object being located within the specified distance from the position of the hand.

10. In any one of paragraphs 1 to 9, The above instructions, when executed by the at least one processor (450), cause the wearable electronic device (401) to: If the position of the hand of the user is not obtained, controlling the second camera (422) so that the second camera (422) obtains the at least one second image at a first frame rate, and A wearable electronic device (401) that causes the second camera (422) to acquire the at least one second image at a second frame rate higher than the first frame rate when the position of the hand of the user is acquired.

11. A method for performing hand tracking in a wearable electronic device (401), An operation of acquiring a position of a user's hand based on at least one first image acquired through a first camera (421) of the wearable electronic device (401); An operation of acquiring a gaze point of the user based on at least one second image acquired through a second camera (422) of the wearable electronic device (401); An action to check whether the position of the above hand corresponds to the above gaze point; An operation of obtaining a skeleton including key points related to the hand based on the position of the hand corresponding to the gaze point; and A method including a motion for performing a motion related to the hand based on the acquired skeleton.

12. In paragraph 11, The action of obtaining the position of the user's hand is: An operation of obtaining an area representing the hand and the position of the hand within at least one of the first images; and A method comprising an action of obtaining a bounding box indicating an area including an area representing the hand based on the position of the hand.

13. In clause 11 or 12, The action of obtaining the user's gaze point is: A method comprising: performing an action of acquiring the gaze point of the user based on acquiring the position of the hand.

14. In any one of paragraphs 11 to 13, The action of obtaining the user's gaze point is: An operation of obtaining a position of a pupil of the user within at least one of the second images; An operation of obtaining positions of glints displayed in the at least one second image by reflecting light emitted from a plurality of light-emitting units of the wearable electronic device (401) to the user's eyes within the at least one second image; and A method comprising an action of obtaining the gaze point of the user based on the center position of the glints and the position of the pupil obtained based on the positions of the glints.

15. A non-transitory computer-readable storage medium having computer-executable instructions recorded thereon, wherein the computer-executable instructions, when executed by at least one processor (450) of a wearable electronic device (401), cause the wearable electronic device (401) to: Based on at least one first image acquired through the first camera (421) of the wearable electronic device (401), the position of the user's hand is acquired, Obtaining the user's gaze point based on at least one second image acquired through the second camera (422) of the wearable electronic device (401), Check whether the position of the above hand corresponds to the above gaze point, Based on the position of the hand corresponding to the gaze point, a skeleton including key points related to the hand is obtained, and A non-transitory computer-readable storage medium causing a hand-related motion to be performed based on the acquired skeleton.

Images