Posture recognition method and device, electronic equipment and storage medium

Abstract

The invention provides a posture recognition method and device, electronic equipment and a storage medium. The method comprises the following steps: acquiring inertial measurement data and a multi-view image of a user at the current moment; inputting the inertial measurement data and the multi-view image into a multi-modal posture detection model to obtain human body posture information of the user at the current moment; wherein the multi-modal attitude detection model is used for performing multi-modal information fusion on the inertial measurement data and the multi-view image. According to the method disclosed by the invention, accurate human body motion capture can be realized through the augmented reality head-mounted equipment.

Description

Technical Field

[0001] The present disclosure relates to the technical field of intelligent terminals, and in particular to a gesture recognition method, device, electronic device and storage medium. Background Art

[0002] Extended Reality (XR) refers to the combination of reality and virtuality through computers to create a virtual environment for human-computer interaction. With the development of XR technology and the gradual improvement of virtual world construction, the realization of full-body motion capture has become a key technology for real XR device wearers to interact with the virtual world. Summary of the invention

[0003] This summary is provided to introduce concepts in a brief form that will be described in detail in the detailed description below. This summary is not intended to identify key features or essential features of the claimed technical solution, nor is it intended to limit the scope of the claimed technical solution.

[0004] The present disclosure provides a gesture recognition method, device, electronic device and storage medium.

[0005] The present disclosure adopts the following technical solutions.

[0006] In some embodiments, the present disclosure provides a gesture recognition method, applied to an extended reality head mounted device, comprising:

[0007] Obtain the user's current inertial measurement data and multi-view images;

[0008] Inputting the inertial measurement data and the multi-view images into a multi-modal posture detection model to obtain the human body posture information of the user at the current moment;

[0009] The multimodal attitude detection model is used to perform multimodal information fusion on the inertial measurement data and the multi-view images.

[0010] In some embodiments, the present disclosure provides a gesture recognition device, comprising:

[0011] An acquisition module is used to acquire the user's current inertial measurement data and multi-view images;

[0012] A processing module, used for inputting the inertial measurement data and the multi-view images into a multi-modal posture detection model to obtain the human body posture information of the user at the current moment;

[0013] The multimodal attitude detection model is used to perform multimodal information fusion on the inertial measurement data and the multi-view images.

[0014] In some embodiments, the present disclosure provides an electronic device, comprising: at least one memory and at least one processor;

[0015] The memory is used to store program codes, and the processor is used to call the program codes stored in the memory to execute the above method.

[0016] In some embodiments, the present disclosure provides a computer-readable storage medium, wherein the computer-readable storage medium is used to store program code, and when the program code is executed by a processor, the processor is prompted to perform the above method.

[0017] The gesture recognition method provided by the embodiment of the present disclosure is applied to an extended reality head-mounted device, by obtaining the inertial measurement data and multi-view images of the user at the current moment; inputting the inertial measurement data and the multi-view images into a multi-modal gesture detection model to obtain the human body posture information of the user at the current moment; wherein the multi-modal gesture detection model is used to perform multi-modal information fusion on the inertial measurement data and the multi-view images. It can be seen that the method of the present disclosure can realize accurate human motion capture through an extended reality head-mounted device. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the accompanying drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and that components and elements are not necessarily drawn to scale.

[0019] Figure 1 This is one of the flowcharts of the gesture recognition method according to the embodiment of the present disclosure.

[0020] Figure 2 This is the second flowchart of the gesture recognition method of the embodiment of the present disclosure.

[0021] Figure 3 This is the third flowchart of the gesture recognition method of the embodiment of the present disclosure.

[0022] Figure 4 This is the fourth flowchart of the gesture recognition method of the embodiment of the present disclosure.

[0023] Figure 5 It is a schematic diagram of the structure of an electronic device according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0024] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments described herein, which are instead provided for a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.

[0025] It should be understood that the various steps described in the method embodiments of the present disclosure can be performed in sequence and / or in parallel. In addition, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present disclosure is not limited in this respect.

[0026] The term "including" and its variations used in this document are open inclusions, i.e., "including but not limited to". The term "based on" means "based at least in part on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one other embodiment"; the term "some embodiments" means "at least some embodiments". The relevant definitions of other terms will be given in the following description. The term "responsive to" and related terms refer to a signal or event being affected to a certain extent by another signal or event, but not necessarily completely or directly affected. If event x occurs "responsive to" event y, x may be directly or indirectly responsive to y. For example, the occurrence of y may eventually lead to the occurrence of x, but there may be other intermediate events and / or conditions. In other cases, y may not necessarily lead to the occurrence of x, and x may occur even if y has not yet occurred. In addition, the term "responsive to" can also mean "at least partially responsive to".

[0027] The term "determine" broadly covers a variety of actions, which may include obtaining, calculating, computing, processing, deriving, investigating, searching (e.g., searching in a table, database, or other data structure), ascertaining, and similar actions, and may also include receiving (e.g., receiving information), accessing (e.g., accessing data in a memory) and similar actions, as well as parsing, selecting, choosing, establishing, and similar actions, etc. The relevant definitions of other terms will be given in the following description. The relevant definitions of other terms will be given in the following description.

[0028] It should be noted that the concepts such as "first" and "second" mentioned in the present disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0029] It should be noted that the modification of “one” mentioned in the present disclosure is illustrative rather than restrictive, and those skilled in the art should understand that it should be understood as “one or more” unless otherwise clearly indicated in the context.

[0030] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0031] It should be noted that the extended reality motion capture methods provided by the related technology are mainly divided into visual solutions and inertial measurement IMU (Inertial Measurement Unit) solutions. Among them, the visual solution is to calculate the two-dimensional joint position information of the human body through the fisheye image collected by the extended reality device, and then obtain the three-dimensional joint position through multi-view geometry, and finally obtain the six-degree-of-freedom (6Dof) posture result through inverse kinematics calculation. The defects of this solution are that the six-degree-of-freedom posture information cannot be directly obtained, the human body information is easily blocked, and it is difficult to obtain the whole body posture result through single-frame image information, and the first-person perspective image cannot obtain the user's upper body trunk information, and it is difficult to estimate the whole body posture. Among them, the IMU solution is to obtain IMU data through an IMU sensor worn on the user, and then analyze the user's motion information through methods such as deep learning, and output the posture result. The defects of this solution are that it is easy to cause motion error accumulation and is not suitable for long-term applications. Second, it requires manual provision of a more accurate initial posture. Third, the user needs to wear an IMU device other than the head-mounted device, such as a handheld handle, which increases the complexity of user use.

[0032] The solution provided by the embodiment of the present disclosure will be described in detail below with reference to the accompanying drawings.

[0033] like Figure 1 As shown, Figure 1 is a flow chart of a gesture recognition method according to an embodiment of the present disclosure, which includes the following steps.

[0034] Step S01: Acquire the user's current inertial measurement data and multi-view images;

[0035] In some embodiments, the present disclosure provides a method for end-to-end human body posture information capture using only an extended reality head-mounted device, without the need to wear additional sensors on other parts of the user's body.

[0036] In some embodiments, the extended reality head-mounted device of the present disclosure includes integrated 4 fisheye grayscale cameras, an inertial navigation sensor and a forward-looking three-color camera.

[0037] In some embodiments, before obtaining the inertial measurement data and multi-view fisheye grayscale image of the user at the current moment, a preprocessing operation is first performed, and the preprocessing includes camera calibration and time alignment calibration. Among them, the camera calibration includes the fisheye camera intrinsic parameter calibration and the relative external parameter calibration between each camera; the time alignment calibration refers to the time alignment process of the IMU data and the fisheye grayscale image data, specifically, through the soft synchronization alignment of the timestamp inside the head-mounted device. In addition, the preprocessing operation also includes the human body shape parameter optimization process.

[0038] In some embodiments, a multi-perspective fisheye grayscale image of the user at the current moment is collected according to multiple fisheye grayscale cameras, and the current inertial measurement data of the user's extended reality head-mounted device is collected according to an inertial navigation sensor, that is, the inertial measurement data of the user at the current moment.

[0039] Step S02: inputting the inertial measurement data and the multi-view images into a multi-modal posture detection model to obtain the human body posture information of the user at the current moment;

[0040] The multimodal attitude detection model is used to perform multimodal information fusion on the inertial measurement data and the multi-view images.

[0041] In some embodiments, the multimodal posture detection model realizes the user's full body motion capture when the application is running, and outputs the posture results in the world coordinate system. It is used to realize the high-dimensional feature fusion of multi-view fisheye grayscale images and IMU data, realize the information complementarity of visual information and IMU information under the first perspective, and obtain the full body motion characteristics of the user at the current moment.

[0042] The gesture recognition method provided by the embodiment of the present disclosure is applied to an extended reality head-mounted device, by obtaining the inertial measurement data and multi-view images of the user at the current moment; inputting the inertial measurement data and the multi-view images into a multi-modal gesture detection model to obtain the human body posture information of the user at the current moment; wherein the multi-modal gesture detection model is used to perform multi-modal information fusion on the inertial measurement data and the multi-view images. It can be seen that the method of the present disclosure can realize accurate human motion capture through an extended reality head-mounted device.

[0043] In some embodiments, the human body posture information includes the axis angles of multiple human body joints relative to their respective parent nodes and the posture information of the root node.

[0044] In some embodiments, the step of obtaining the user's current inertial measurement data and multi-view images includes:

[0045] The multi-view images of the user at the current moment are collected according to the multiple grayscale cameras of the extended reality head-mounted device, and the inertial measurement data of the user at the current moment is collected according to the inertial navigation sensor.

[0046] In some embodiments, it also includes:

[0047] The human body posture information output by the multimodal posture detection model at the previous moment is obtained, and the human body posture information of the user at the current moment is smoothed according to the human body posture information at the previous moment.

[0048] In some embodiments, it also includes:

[0049] When the multi-view image is an initial frame, the multi-view image and the internal and external parameter information of the camera of the extended reality head mounted device are input into a multi-view gesture detection model to obtain the initial human body posture information of the user when the extended reality application is turned on, and the initial human body posture information is used as input data of the multi-modal gesture detection model when the extended reality application is turned on;

[0050] The multi-view posture detection model is obtained by training a neural network model based on the multi-view image and the internal and external parameter information of the camera as input data and the human body posture information as output data.

[0051] In some embodiments, Figure 2 and Figure 3 As shown in the figure, the initialization uses a multi-view posture detection model, which is used to obtain the human body posture when the application is started and transform it into the world coordinate system as the initial value of the time series input in the subsequent posture estimation module. Among them, the user's initial posture information is determined based on the multi-view fisheye grayscale image and the internal and external parameter information of the camera. It should be noted that the initialization process is only run once when the application is started.

[0052] In some embodiments, the step of inputting the inertial measurement data and the multi-view image into a multi-modal posture detection model to obtain the human body posture information of the user at the current moment includes:

[0053] Performing multi-view feature fusion according to the multi-view images and the internal and external parameter information of the camera, and performing multi-modal information fusion on the fused result and the inertial measurement data to obtain a local posture result;

[0054] According to the local posture result and the world external parameter information, the human body posture information of the user at the current moment is determined, and the human body posture information is six-degree-of-freedom information.

[0055] In some embodiments, the world extrinsic reference information is determined based on the user's current forward-looking image information collected by a grayscale camera and / or a forward-looking color camera of the extended reality head-mounted device.

[0056] In some embodiments, Figure 4As shown in the figure, the temporal feature module GRU (Gate Recurrent Unit) is introduced in the process of posture detection to increase the smoothness of the motion timing. The input includes fisheye grayscale image, IMU data, camera internal and external parameter information and posture detection result of the previous moment, and the output is the posture result in the world coordinate system.

[0057] In some embodiments, it also includes:

[0058] During the training process of the multimodal posture detection model, the parameters of the multimodal posture detection model are reversely optimized according to the output human body posture information.

[0059] In some embodiments, Figure 2 As shown, the system cannot avoid errors in the results during calibration, positioning and posture detection, and the human body movements displayed by the posture results finally outputted occasionally show obvious unreasonable movements. To solve this problem, the embodiment of the present disclosure provides a post-optimization process, which uses a large amount of reasonable human body posture parameters collected during normal use by users to construct a motion discriminator, thereby reversely optimizing the posture detection model parameters and improving the robustness of the posture detection model. It is understandable that the post-optimization process is only used during the model training process.

[0060] The posture result output by the embodiment of the present disclosure is output in the form of standardized drivable model posture parameters, which include the axis-angle expression of 23 joint points relative to their respective parent nodes and the rotation axis intersection and translation parameters of a root node in the world coordinate system. The result can be directly converted and output as a six-degree-of-freedom posture result, and finally, the final human body driving parameters are output in combination with the posture information obtained during the initialization process.

[0061] It can be seen that the disclosed embodiment provides a complete solution for end-to-end full-body motion capture with a single augmented reality head-mounted device, which can output smooth and reasonable posture detection results in real time. In addition, the disclosed embodiment realizes the feature fusion of IMU data and visual information through a multimodal posture detection model, fills the information missing in a single sensor solution, improves the robustness of the system, and does not require a dynamic inverse operation optimization process, further improving the practicality of the system.

[0062] In some embodiments, it also includes:

[0063] According to the human body posture information, corresponding human body movements are generated and displayed in an extended reality environment.

[0064] The present disclosure also provides a gesture recognition device, including:

[0065] An acquisition module is used to acquire the user's current inertial measurement data and multi-view images;

[0066] A processing module, used for inputting the inertial measurement data and the multi-view images into a multi-modal posture detection model to obtain the human body posture information of the user at the current moment;

[0067] The multimodal attitude detection model is used to perform multimodal information fusion on the inertial measurement data and the multi-view images.

[0068] In some embodiments, the human body posture information includes the axis angles of multiple human body joints relative to their respective parent nodes and the posture information of the root node.

[0069] In some embodiments, the acquisition module is specifically used to:

[0070] The multi-view images of the user at the current moment are collected according to the multiple grayscale cameras of the extended reality head-mounted device, and the inertial measurement data of the user at the current moment is collected according to the inertial navigation sensor.

[0071] In some embodiments, the acquisition module is further specifically used for:

[0072] The human body posture information output by the multimodal posture detection model at the previous moment is obtained, and the human body posture information of the user at the current moment is smoothed according to the human body posture information at the previous moment.

[0073] In some embodiments, the processing module is further specifically used for:

[0074] When the multi-view image is an initial frame, the multi-view image and the internal and external parameter information of the camera of the extended reality head mounted device are input into a multi-view gesture detection model to obtain the initial human body posture information of the user when the extended reality application is turned on, and the initial human body posture information is used as input data of the multi-modal gesture detection model when the extended reality application is turned on;

[0075] The multi-view posture detection model is obtained by training a neural network model based on the multi-view image and the internal and external parameter information of the camera as input data and the human body posture information as output data.

[0076] In some embodiments, the processing module is specifically used to:

[0077] Performing multi-view feature fusion according to the multi-view images and the internal and external parameter information of the camera, and performing multi-modal information fusion on the fused result and the inertial measurement data to obtain a local posture result;

[0078] According to the local posture result and the world external parameter information, the human body posture information of the user at the current moment is determined, and the human body posture information is six-degree-of-freedom information.

[0079] In some embodiments, the world extrinsic reference information is determined based on the user's current forward-looking image information collected by a grayscale camera and / or a forward-looking color camera of the extended reality head-mounted device.

[0080] In some embodiments, the processing module is further specifically used for:

[0081] During the training process of the multimodal posture detection model, the parameters of the multimodal posture detection model are reversely optimized according to the output human body posture information.

[0082] In some embodiments, the processing module is further specifically used for:

[0083] According to the human body posture information, corresponding human body movements are generated and displayed in an extended reality environment.

[0084] For the embodiments of the device, since they basically correspond to the method embodiments, the relevant parts refer to the partial description of the method embodiments. The device embodiments described above are merely illustrative, wherein the modules described as separation modules may or may not be separated. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of the present embodiment. Those of ordinary skill in the art can understand and implement without paying creative work.

[0085] The method and device of the present disclosure are described above based on the embodiments and application examples. In addition, the present disclosure also provides an electronic device and a computer-readable storage medium, which are described below.

[0086] Reference below Figure 5 , which shows a schematic diagram of the structure of an electronic device (such as a terminal device or a server) 800 suitable for implementing the embodiment of the present disclosure. The terminal device in the embodiment of the present disclosure may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. The electronic device shown in the figure is only an example and should not bring any limitation to the functions and scope of use of the embodiment of the present disclosure.

[0087] The electronic device 800 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 801, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 802 or a program loaded from a storage device 808 into a random access memory (RAM) 803. In the RAM 803, various programs and data required for the operation of the electronic device 800 are also stored. The processing device 801, the ROM 802, and the RAM 803 are connected to each other via a bus 804. An input / output (I / O) interface 805 is also connected to the bus 804.

[0088] Typically, the following devices may be connected to the I / O interface 805: input devices 806 including, for example, a touch screen, a touchpad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; output devices 807 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; storage devices 808 including, for example, a magnetic tape, a hard disk, etc.; and communication devices 809. The communication device 809 may allow the electronic device 800 to communicate with other devices wirelessly or by wire to exchange data. Although the electronic device 800 with various devices is shown in the figure, it should be understood that it is not required to implement or have all the devices shown. More or fewer devices may be implemented or have alternatively.

[0089] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program contains program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device 809, or installed from a storage device 808, or installed from a ROM 802. When the computer program is executed by the processing device 801, the above-mentioned functions defined in the method of the embodiment of the present disclosure are executed.

[0090] It should be noted that the computer-readable medium disclosed above may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in combination with an instruction execution system, device or device. In the present disclosure, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, in which a computer-readable program code is carried. This propagated data signal may take a variety of forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination of the above. The computer readable signal medium may also be any computer readable medium other than a computer readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0091] In some embodiments, the client and the server may communicate using any currently known or future developed network protocol such as HTTP (HyperText Transfer Protocol), and may be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), an internet (e.g., the Internet), and a peer-to-peer network (e.g., an ad hoc peer-to-peer network), as well as any currently known or future developed network.

[0092] The computer-readable medium may be included in the electronic device, or may exist independently without being incorporated into the electronic device.

[0093] The computer-readable medium carries one or more programs. When the one or more programs are executed by the electronic device, the electronic device executes the method of the present disclosure.

[0094] Computer program code for performing the operations of the present disclosure may be written in one or more programming languages, or a combination thereof, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0095] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0096] The units involved in the embodiments described in the present disclosure may be implemented by software or hardware, wherein the name of a unit does not, in some cases, limit the unit itself.

[0097] The functions described above herein may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.

[0098] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0099] According to one or more embodiments of the present disclosure, a gesture recognition method is provided, which is applied to an extended reality head-mounted device, including:

[0100] Obtain the user's current inertial measurement data and multi-view images;

[0101] Inputting the inertial measurement data and the multi-view images into a multi-modal posture detection model to obtain the human body posture information of the user at the current moment;

[0102] The multimodal attitude detection model is used to perform multimodal information fusion on the inertial measurement data and the multi-view images.

[0103] According to one or more embodiments of the present disclosure, a method is provided, wherein the human body posture information includes the axis angles of multiple human body joints relative to their respective parent nodes and the posture information of a root node.

[0104] According to one or more embodiments of the present disclosure, a method is provided, wherein obtaining inertial measurement data and multi-view images of a user at a current moment includes:

[0105] The multi-view images of the user at the current moment are collected according to the multiple grayscale cameras of the extended reality head-mounted device, and the inertial measurement data of the user at the current moment is collected according to the inertial navigation sensor.

[0106] According to one or more embodiments of the present disclosure, a method is provided, further comprising:

[0107] The human body posture information output by the multimodal posture detection model at the previous moment is obtained, and the human body posture information of the user at the current moment is smoothed according to the human body posture information at the previous moment.

[0108] According to one or more embodiments of the present disclosure, a method is provided, further comprising:

[0109] When the multi-view image is an initial frame, the multi-view image and the internal and external parameter information of the camera of the extended reality head mounted device are input into a multi-view gesture detection model to obtain the initial human body posture information of the user when the extended reality application is turned on, and the initial human body posture information is used as input data of the multi-modal gesture detection model when the extended reality application is turned on;

[0110] The multi-view posture detection model is obtained by training a neural network model based on the multi-view image and the internal and external parameter information of the camera as input data and the human body posture information as output data.

[0111] According to one or more embodiments of the present disclosure, a method is provided, wherein the inertial measurement data and the multi-view image are input into a multi-modal posture detection model to obtain the human body posture information of the user at the current moment, including:

[0112] Performing multi-view feature fusion according to the multi-view images and the internal and external parameter information of the camera, and performing multi-modal information fusion on the fused result and the inertial measurement data to obtain a local posture result;

[0113] According to the local posture result and the world external parameter information, the human body posture information of the user at the current moment is determined, and the human body posture information is six-degree-of-freedom information.

[0114] According to one or more embodiments of the present disclosure, a method is provided, wherein the world extrinsic reference information is determined based on the forward-looking image information of the user at the current moment collected by the grayscale camera and / or the forward-looking color camera of the extended reality head-mounted device.

[0115] According to one or more embodiments of the present disclosure, a method is provided, further comprising:

[0116] During the training process of the multimodal posture detection model, the parameters of the multimodal posture detection model are reversely optimized according to the output human body posture information.

[0117] According to one or more embodiments of the present disclosure, a method is provided, further comprising:

[0118] According to the human body posture information, corresponding human body movements are generated and displayed in an extended reality environment.

[0119] According to one or more embodiments of the present disclosure, a gesture recognition device is provided, comprising:

[0120] An acquisition module is used to acquire the user's current inertial measurement data and multi-view images;

[0121] A processing module, used for inputting the inertial measurement data and the multi-view images into a multi-modal posture detection model to obtain the human body posture information of the user at the current moment;

[0122] The multimodal attitude detection model is used to perform multimodal information fusion on the inertial measurement data and the multi-view images.

[0123] According to one or more embodiments of the present disclosure, there is provided an electronic device, including: at least one memory and at least one processor;

[0124] The at least one memory is used to store program codes, and the at least one processor is used to call the program codes stored in the at least one memory to execute any one of the above methods.

[0125] According to one or more embodiments of the present disclosure, a computer-readable storage medium is provided, wherein the computer-readable storage medium is used to store program code, and when the program code is executed by a processor, the processor is prompted to execute the above method.

[0126] The above description is only a preferred embodiment of the present disclosure and an explanation of the technical principles used. Those skilled in the art should understand that the scope of disclosure involved in the present disclosure is not limited to the technical solutions formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above disclosed concept. For example, the above features are replaced with the technical features with similar functions disclosed in the present disclosure (but not limited to) by each other to form a technical solution.

[0127] In addition, although each operation is described in a specific order, this should not be understood as requiring these operations to be performed in the specific order shown or in a sequential order. Under certain circumstances, multitasking and parallel processing may be advantageous. Similarly, although some specific implementation details are included in the above discussion, these should not be interpreted as limiting the scope of the present disclosure. Some features described in the context of a separate embodiment can also be implemented in a single embodiment in combination. On the contrary, the various features described in the context of a single embodiment can also be implemented in multiple embodiments individually or in any suitable sub-combination mode.

[0128] Although the subject matter has been described in language specific to structural features and / or methodological logical actions, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. On the contrary, the specific features and actions described above are merely example forms of implementing the claims.

Claims

1. A gesture recognition method, characterized in that: Applied to extended reality head-mounted devices, including: Obtain the user's current inertial measurement data and multi-view images; Inputting the inertial measurement data and the multi-view images into a multi-modal posture detection model to obtain the human body posture information of the user at the current moment; The multimodal attitude detection model is used to perform multimodal information fusion on the inertial measurement data and the multi-view images.

2. The method according to claim 1, characterized in that The human body posture information includes the posture information of multiple human body joints relative to the axis angles of their respective parent nodes and the root node.

3. The method according to claim 1, characterized in that The obtaining of the user's current inertial measurement data and multi-view images includes: The multi-view images of the user at the current moment are collected according to the multiple grayscale cameras of the extended reality head-mounted device, and the inertial measurement data of the user at the current moment is collected according to the inertial navigation sensor.

4. The method according to claim 1, characterized in that: Also includes: The human body posture information output by the multimodal posture detection model at the previous moment is obtained, and the human body posture information of the user at the current moment is smoothed according to the human body posture information at the previous moment.

5. The method according to claim 1, characterized in that Also includes: When the multi-view image is an initial frame, the multi-view image and the internal and external parameter information of the camera of the extended reality head mounted device are input into a multi-view gesture detection model to obtain the initial human body posture information of the user when the extended reality application is turned on, and the initial human body posture information is used as input data of the multi-modal gesture detection model when the extended reality application is turned on; The multi-view posture detection model is obtained by training a neural network model based on the multi-view image and the internal and external parameter information of the camera as input data and the human body posture information as output data.

6. The method according to claim 1, characterized in that The step of inputting the inertial measurement data and the multi-view image into a multi-modal posture detection model to obtain the human body posture information of the user at the current moment includes: Performing multi-view feature fusion according to the multi-view images and the internal and external parameter information of the camera, and performing multi-modal information fusion on the fused result and the inertial measurement data to obtain a local posture result; According to the local posture result and the world external parameter information, the human body posture information of the user at the current moment is determined, and the human body posture information is six-degree-of-freedom information.

7. The method according to claim 6, characterized in that The world external reference information is determined based on the forward-looking image information of the user at the current moment collected by the grayscale camera and / or the forward-looking color camera of the extended reality head-mounted device.

8. The method according to claim 1, characterized in that Also includes: During the training process of the multimodal posture detection model, the parameters of the multimodal posture detection model are reversely optimized according to the output human body posture information.

9. The method according to claim 1, characterized in that: Also includes: According to the human body posture information, corresponding human body movements are generated and displayed in an extended reality environment.

10. A gesture recognition device, characterized in that: include: An acquisition module is used to acquire the user's current inertial measurement data and multi-view images; A processing module, used for inputting the inertial measurement data and the multi-view images into a multi-modal posture detection model to obtain the human body posture information of the user at the current moment; The multimodal attitude detection model is used to perform multimodal information fusion on the inertial measurement data and the multi-view images.

11. An electronic device, comprising: at least one memory and at least one processor; The at least one memory is used to store program code, and the at least one processor is used to call the program code stored in the at least one memory to execute the method according to any one of claims 1 to 9. 12 . A computer-readable storage medium, wherein the computer-readable storage medium is used to store program code, wherein when the program code is executed by a computer device, the computer device is prompted to execute the method according to claim 1 .

Images