An AR tracking method, device, AR equipment and storage medium

Abstract

The application discloses an AR tracking method and device, an AR device and a storage medium. The method is applied to the AR device and comprises the following steps: acquiring the first object posture in a target scene in real time through an inertial measurement unit (IMU) built in the AR device; when it is determined that the object in the target scene is in an abnormal state according to the first object posture, acquiring an RGB image sequence of the target scene; sending the RGB image sequence to a server, so that the server determines the second object posture in the target scene based on the RGB image sequence; receiving the second object posture sent by the server, and performing model rendering on the object based on the second object posture to generate a corresponding first target model, so as to perform AR tracking on the object based on the first target model. Through the technical scheme provided in the embodiment of the application, for the AR device with high frame rate requirements and low computing performance, the accuracy of AR tracking can be effectively ensured without occupying a large amount of GPU resources.

Description

Technical Field

[0001] This invention relates to the field of AR technology, and in particular to an AR tracking method, apparatus, AR device, and storage medium. Background Technology

[0002] With the popularization and commercialization of AR technology, a large number of related AR applications such as metaverse and digital twins have emerged on the market. Most of these AR applications require real-time estimation of target pose and tracking of objects, which is a very important and challenging technology for AR.

[0003] Currently, most AR devices use deep neural network models to determine the target pose in order to perform AR tracking based on the target pose. However, this method requires a lot of GPU resources to calculate the target pose, but commonly used AR devices in reality do not have a lot of GPU resources, resulting in low computing performance. Summary of the Invention

[0004] This invention provides an AR tracking method, apparatus, AR device, and storage medium, which can effectively ensure the accuracy of AR tracking for AR devices with high frame rate requirements and low computing performance without consuming a large amount of GPU resources.

[0005] According to one aspect of the present invention, an AR tracking method is provided, applied to an AR device, comprising:

[0006] The AR device uses its built-in inertial measurement unit (IMU) to acquire the attitude of the first object in the target scene in real time.

[0007] When it is determined that an object in the target scene is in an abnormal state based on the first object's pose, an RGB image sequence of the target scene is obtained;

[0008] The RGB image sequence is sent to the server so that the server can determine the pose of the second object in the target scene based on the RGB image sequence.

[0009] The system receives the second object pose sent by the server, performs model rendering on the object based on the second object pose, generates a corresponding first target model, and performs AR tracking on the object based on the first target model.

[0010] According to another aspect of the present invention, an AR tracking device is provided for use in an AR device, comprising:

[0011] The first object posture determination module is used to obtain the posture of the first object in the target scene in real time through the inertial measurement unit (IMU) built into the AR device.

[0012] The image sequence acquisition module is used to acquire an RGB image sequence of the target scene when it is determined that an object in the target scene is in an abnormal state based on the first object pose.

[0013] The second object pose determination module is used to send the RGB image sequence to the server so that the server can determine the pose of the second object in the target scene based on the RGB image sequence.

[0014] The AR tracking module is used to receive the pose of the second object sent by the server, and to perform model rendering on the object based on the pose of the second object to generate a corresponding first target model, so as to perform AR tracking on the object based on the first target model.

[0015] According to another aspect of the present invention, an AR device is provided, the AR device comprising:

[0016] At least one processor; and

[0017] A memory communicatively connected to the at least one processor; wherein,

[0018] The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the AR tracking method according to any embodiment of the present invention.

[0019] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions for causing a processor to execute and implement the AR tracking method according to any embodiment of the present invention.

[0020] The AR tracking scheme of this invention includes: acquiring the pose of a first object in a target scene in real time through the inertial measurement unit (IMU) built into the AR device; when it is determined that the object in the target scene is in an abnormal state based on the first object pose, acquiring an RGB image sequence of the target scene; sending the RGB image sequence to a server so that the server determines the pose of a second object in the target scene based on the RGB image sequence; receiving the second object pose sent by the server, and performing model rendering on the object based on the second object pose to generate a corresponding first target model, and performing AR tracking on the object based on the first target model. Through the technical solution provided by this invention, for AR devices with high frame rate requirements and low computational performance, the accuracy of AR tracking can be effectively guaranteed without consuming a large amount of GPU resources.

[0021] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0022] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0023] Figure 1 This is a flowchart of an AR tracking method provided according to Embodiment 1 of the present invention;

[0024] Figure 2 This is a flowchart of an AR tracking method provided according to Embodiment 2 of the present invention;

[0025] Figure 3 This is a schematic diagram of the structure of an AR tracking device according to Embodiment 3 of the present invention;

[0026] Figure 4 This is a schematic diagram of the structure of an AR device that implements the AR tracking method of this invention. Detailed Implementation

[0027] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0028] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0029] Example 1

[0030] Figure 1 The flowchart illustrates an AR tracking method provided in Embodiment 1 of the present invention. This embodiment is applicable to situations where AR tracking of objects is performed using an AR device. The method can be executed by an AR tracking device, which can be implemented in hardware and / or software and can be configured within the AR device. Figure 1 As shown, the method includes:

[0031] S110: The inertial measurement unit (IMU) built into the AR device acquires the attitude of the first object in the target scene in real time.

[0032] The AR device can be a head-mounted AR device such as AR glasses or an AR helmet, or it can be an electronic device with AR functionality. The AR device includes an inertial measurement unit (IMU). In this embodiment of the invention, in response to an AR tracking event being triggered, the AR device uses its built-in IMU to acquire the pose of a first object in the target scene in real time. The target scene can be any scene that the AR device can observe.

[0033] S120. When it is determined that an object in the target scene is in an abnormal state based on the posture of the first object, the RGB image sequence of the target scene is obtained.

[0034] In this embodiment of the invention, since the inertial measurement unit (IMU) may have certain measurement deviations, the first object posture obtained by the IMU may be inaccurate. The system determines whether the object in the target scene is in an abnormal state based on the first object posture; if so, it acquires an RGB image sequence of the target scene in real time. For example, the first object posture can be analyzed based on a pre-set state determination algorithm to determine whether the object in the target scene is in an abnormal state. It should be noted that this embodiment of the invention does not limit the state determination algorithm. An abnormal state may include a tracking loss state or an incorrect posture state. The AR device has a built-in camera; when it is determined that the object in the target scene is in a tracking loss state or an incorrect posture state based on the first object posture, the built-in camera captures an RGB image sequence of the target scene in real time.

[0035] Optionally, the abnormal state includes an incorrect pose state; determining that an object in the target scene is in an abnormal state based on the first object pose includes: determining the volume offset of the object in the target scene based on the current first object pose and the previous first object pose; when the volume offset is greater than a preset threshold, determining that the object in the target scene is in an incorrect pose state. Specifically, the first object pose includes the vertices of a 3D bounding box, and a 3D volume can be constructed based on the vertices of the 3D bounding box. Since the first object pose changes in displacement in each frame, the volume offset of the object can be determined by comparing the current first object pose with the previous first object pose. Specifically, a first volume corresponding to the current first object pose and a second volume corresponding to the previous first object pose are determined respectively, and the difference between the first volume and the second volume is taken as the volume offset of the object. When the volume offset is greater than a preset threshold, it can be determined that the object in the target scene is in an incorrect pose state; when the volume offset is less than a preset threshold, it can be determined that the object in the target scene is in a correct pose state.

[0036] Optionally, the abnormal state includes a tracking loss state; determining that an object in the target scene is in an abnormal state based on the first object's pose includes: when the object in the target scene is determined to be in an incorrect pose state based on the first object's pose, acquiring the pose data of the AR device in real time; when the object in the target scene is determined to be in an incorrect pose state based on the pose data, determining that the object in the target scene is in a tracking loss state. Specifically, when the object in the target scene is determined to be in an incorrect pose state based on the first object's pose, acquiring the pose data of the AR device in real time, calculating the pose offset of the AR device based on the current pose data and the previous pose data, determining that the object in the target scene is in an incorrect pose state when the pose offset is greater than a preset pose threshold, and determining that the object in the target scene is in a correct pose state when the pose offset is less than the preset pose threshold. When both the first object's pose and the AR device's pose data determine that the object in the target scene is in an incorrect pose state, it can be further determined that the object in the target scene is in a tracking loss state.

[0037] S130. The RGB image sequence is sent to the server so that the server can determine the pose of the second object in the target scene based on the RGB image sequence.

[0038] In this embodiment of the invention, the AR device sends an RGB image sequence to a server. When the server receives the RGB image sequence from the AR device, it analyzes the RGB image sequence to determine the pose of a second object in the target scene. Optionally, sending the RGB image sequence to the server so that the server can determine the pose of the second object in the target scene based on the RGB image sequence includes: sending the RGB image sequence to the server so that the server inputs the RGB image sequence into a pre-trained object pose estimation model, and determines the pose of the second object in the target scene based on the output of the object pose estimation model. The object pose estimation model is a pose estimation model trained based on a pre-defined machine learning model. The server sends the received RGB image sequence to the object pose estimation model so that the object pose estimation model analyzes the RGB image sequence and determines the pose of the second object in the target scene based on the output of the object pose estimation model. For example, the object pose estimation model can be a 6DoF object pose estimation model. It is understood that the first object pose model is a coarsely estimated object pose by the AR device through an inertial measurement unit (IMU), and the second object pose model is a precise object pose determined based on the RGB image sequence.

[0039] S140. Receive the second object pose sent by the server, and perform model rendering on the object based on the second object pose to generate a corresponding first target model, so as to perform AR tracking on the object based on the first target model.

[0040] In this embodiment of the invention, the AR device receives a second object pose sent by the server, and performs model rendering on the objects in the target scene based on the second object pose to generate a corresponding first target model. A pre-defined model rendering method can be used to render the model based on the second object pose to generate the first target model. Then, AR technology is used to perform AR tracking on the objects in the target scene based on the first target model.

[0041] Optionally, it also includes: when it is determined that the object in the target scene is in the correct posture state based on the first object posture, performing model rendering on the object based on the first object posture to generate a corresponding second target model, and then performing AR tracking on the object based on the second target model. The advantage of this setup is that it effectively ensures the timeliness of AR tracking while maintaining its accuracy. Specifically, when it is determined that the object in the target scene is in the correct posture state based on the first object posture, it means that the first object posture obtained by the inertial measurement unit (IMU) is relatively accurate. There is no need to acquire RGB image sequences and send them to the server for analysis to re-determine the object posture. Model rendering can be performed directly based on the first object posture to generate the second target model, and AR tracking of the object in the target scene can be performed using AR technology based on the second target model.

[0042] The AR tracking method of this invention includes: acquiring the pose of a first object in a target scene in real time using an inertial measurement unit (IMU) built into the AR device; when it is determined that an object in the target scene is in an abnormal state based on the first object pose, acquiring an RGB image sequence of the target scene; sending the RGB image sequence to a server so that the server determines the pose of a second object in the target scene based on the RGB image sequence; receiving the second object pose sent by the server, and performing model rendering on the object based on the second object pose to generate a corresponding first target model, and performing AR tracking on the object based on the first target model. Through the technical solution provided by this invention, for AR devices with high frame rate requirements and low computational performance, the accuracy of AR tracking can be effectively guaranteed without consuming a large amount of GPU resources.

[0043] Example 2

[0044] Figure 2 This is a flowchart of an AR tracking method provided in Embodiment 2 of the present invention, as shown below. Figure 2 As shown, the method includes:

[0045] S210: The inertial measurement unit (IMU) built into the AR device acquires the attitude of the first object in the target scene in real time.

[0046] S220. Determine whether the object in the target scene is in a tracking loss state or an incorrect posture state based on the first object's posture. If so, execute S230; otherwise, execute S250.

[0047] S230. Obtain the RGB image sequence of the target scene and send the RGB image sequence to the server so that the server can determine the pose of the second object in the target scene based on the RGB image sequence.

[0048] S240. Receive the second object pose sent by the server, and perform model rendering on the object based on the second object pose to generate a corresponding first target model, so as to perform AR tracking on the object based on the first target model.

[0049] S250. Based on the pose of the first object, perform model rendering on the object to generate a corresponding second target model, and perform AR tracking on the object based on the second target model.

[0050] The AR tracking method provided in this invention can effectively ensure the accuracy of AR tracking for AR devices with high frame rate requirements and low computing performance without consuming a large amount of GPU resources.

[0051] Example 3

[0052] Figure 3 This is a schematic diagram of the structure of an AR tracking device provided in Embodiment 3 of the present invention. Figure 3 As shown, the device includes:

[0053] The first object posture determination module 310 is used to obtain the posture of the first object in the target scene in real time through the inertial measurement unit (IMU) built into the AR device.

[0054] The image sequence acquisition module 320 is used to acquire an RGB image sequence of the target scene when it is determined that an object in the target scene is in an abnormal state based on the first object pose.

[0055] The second object pose determination module 330 is used to send the RGB image sequence to the server so that the server can determine the pose of the second object in the target scene based on the RGB image sequence.

[0056] AR tracking module 340 is used to receive the second object pose sent by the server, and to perform model rendering on the object based on the second object pose to generate a corresponding first target model, so as to perform AR tracking on the object based on the first target model.

[0057] Optionally, the device further includes:

[0058] The model rendering module is used to render the object based on the first object's pose when it is determined that the object in the target scene is in the correct pose state based on the first object's pose, and generate a corresponding second target model, so as to perform AR tracking on the object based on the second target model.

[0059] Optionally, the second object pose determination module is used for:

[0060] The RGB image sequence is sent to the server so that the server inputs the RGB image sequence into a pre-trained object pose estimation model and determines the pose of the second object in the target scene based on the output of the object pose estimation model.

[0061] Optionally, the abnormal state includes a tracking loss state or an incorrect pose state.

[0062] Optionally, the abnormal state includes an incorrect posture state;

[0063] The image sequence acquisition module is used for:

[0064] The volume offset of the object in the target scene is determined based on the current first object pose and the previous first object pose;

[0065] When the volume offset is greater than a preset threshold, it is determined that the object in the target scene is in an incorrect posture state.

[0066] Optionally, the abnormal state includes a tracking loss state;

[0067] The image sequence acquisition module is used for:

[0068] When it is determined that an object in the target scene is in an incorrect posture state based on the first object's posture, the AR device's pose data is acquired in real time.

[0069] When it is determined from the pose data that an object in the target scene is in an incorrect pose state, it is determined that the object in the target scene is in a tracking loss state.

[0070] The AR tracking device provided in the embodiments of the present invention can execute the AR tracking method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the method execution.

[0071] Example 4

[0072] Figure 4 A schematic diagram of an AR device 10, which can be used to implement embodiments of the present invention, is shown. The AR device is intended to represent various forms of digital computers, such as laptops, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframes, and other suitable computers. The AR device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0073] like Figure 4 As shown, the AR device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 can also store various programs and data required for the operation of the AR device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0074] Multiple components in the AR device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, optical disk, etc.; and a communication unit 19, such as a network card, modem, wireless transceiver, etc. The communication unit 19 allows the AR device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0075] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as AR tracking methods.

[0076] In some embodiments, the AR tracking method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on the AR device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the AR tracking method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the AR tracking method by any other suitable means (e.g., by means of firmware).

[0077] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0078] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0079] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0080] To provide user interaction, the systems and techniques described herein can be implemented on an AR device having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the AR device. Other types of devices can also be used to provide user interaction; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or haptic feedback); and input from the user can be received in any form (including sound input, voice input, or haptic input).

[0081] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0082] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0083] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0084] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. An AR tracking method, characterized in that, Applied to AR devices, including: The AR device uses its built-in inertial measurement unit (IMU) to acquire the attitude of the first object in the target scene in real time. When it is determined that an object in the target scene is in an abnormal state based on the first object's pose, an RGB image sequence of the target scene is acquired; wherein, the abnormal state includes a tracking loss state or an incorrect pose state; The RGB image sequence is sent to the server so that the server can determine the pose of the second object in the target scene based on the RGB image sequence. The system receives the second object pose sent by the server, and performs model rendering on the object based on the second object pose to generate a corresponding first target model, so as to perform AR tracking on the object based on the first target model. The abnormal state includes an incorrect posture state; Determining that an object in the target scene is in an abnormal state based on the first object's pose includes: The volume offset of the object in the target scene is determined based on the current first object pose and the previous first object pose; When the volume offset is greater than a preset threshold, it is determined that the object in the target scene is in an incorrect posture state; The abnormal states include tracking loss states; Determining that an object in the target scene is in an abnormal state based on the first object's pose includes: When it is determined that an object in the target scene is in an incorrect posture state based on the first object's posture, the AR device's pose data is acquired in real time. When it is determined from the pose data that an object in the target scene is in an incorrect pose state, it is determined that the object in the target scene is in a tracking loss state. The determination that an object in the target scene is in an incorrect pose state based on the pose data includes: The pose offset of the AR device is calculated based on the current pose data and the previous pose data. When the pose offset is greater than a preset pose threshold, it is determined that the object in the target scene is in an incorrect pose state.

2. The method according to claim 1, characterized in that, Also includes: When it is determined that the object in the target scene is in the correct pose state based on the first object pose, the object is model rendered based on the first object pose to generate a corresponding second target model, and AR tracking of the object is performed based on the second target model.

3. The method according to claim 1, characterized in that, Sending the RGB image sequence to the server, so that the server can determine the pose of a second object in the target scene based on the RGB image sequence, includes: The RGB image sequence is sent to the server so that the server inputs the RGB image sequence into a pre-trained object pose estimation model and determines the pose of the second object in the target scene based on the output of the object pose estimation model.

4. An AR tracking device, characterized in that, Applied to AR devices, including: The first object posture determination module is used to obtain the posture of the first object in the target scene in real time through the inertial measurement unit (IMU) built into the AR device. The image sequence acquisition module is used to acquire an RGB image sequence of the target scene when it is determined that an object in the target scene is in an abnormal state based on the first object pose; wherein, the abnormal state includes a tracking loss state or an incorrect pose state; The second object pose determination module is used to send the RGB image sequence to the server so that the server can determine the pose of the second object in the target scene based on the RGB image sequence. The AR tracking module is used to receive the second object pose sent by the server, and to perform model rendering on the object based on the second object pose to generate a corresponding first target model, so as to perform AR tracking on the object based on the first target model; The abnormal state includes an incorrect posture state; The image sequence acquisition module is used for: The volume offset of the object in the target scene is determined based on the current first object pose and the previous first object pose; When the volume offset is greater than a preset threshold, it is determined that the object in the target scene is in an incorrect posture state; The abnormal states include tracking loss states; The image sequence acquisition module is used for: When it is determined that an object in the target scene is in an incorrect posture state based on the first object's posture, the AR device's pose data is acquired in real time. When it is determined from the pose data that an object in the target scene is in an incorrect pose state, it is determined that the object in the target scene is in a tracking loss state. The determination that an object in the target scene is in an incorrect pose state based on the pose data includes: The pose offset of the AR device is calculated based on the current pose data and the previous pose data. When the pose offset is greater than a preset pose threshold, it is determined that the object in the target scene is in an incorrect pose state.

5. The apparatus according to claim 4, characterized in that, Also includes: The model rendering module is used to render the object based on the first object's pose when it is determined that the object in the target scene is in the correct pose state based on the first object's pose, and generate a corresponding second target model, so as to perform AR tracking on the object based on the second target model.

6. An AR device, characterized in that, The AR device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor to enable the at least one processor to perform the AR tracking method according to any one of claims 1-3.

7. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause a processor to execute the AR tracking method according to any one of claims 1-3.

Images