AR (Augmented Reality) glasses testing method, system, equipment and medium

By building multiple scenario test models, using the SDK function of AR glasses to conduct comprehensive testing of AR glasses, solving the problem of narrow testing coverage in the existing technology, ensuring the stability and user experience of AR applications.

CN118913622APending Publication Date: 2024-11-08HANGZHOU YIXIAN XIANJIN TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410859827.1
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-06-28
Publication Date
2024-11-08

AI Technical Summary

Technical Problem

The lack of comprehensive algorithmic testing methods in existing AR glasses technology has led to a narrow test coverage and the inability to effectively evaluate the functional performance of AR glasses.

Method used

By building a scene test model, including interactive test scenarios, flat test scenarios, camera preview test scenarios, spatial tracking test scenarios, image recognition test scenarios, object recognition test scenarios, spatial positioning test scenarios and real-time rendering test scenarios, SDK using AR glasses The function tests these scenes, obtains the test results of the AR silver mirror algorithm, and ensures the accurate superposition of virtual content and real scenes.

Benefits of technology

A comprehensive test of the AR glasses algorithm is realized, covering key functional points, ensuring the stability of AR applications and user experience quality, improving the accuracy and efficiency of the algorithm in various scenarios, and solving the problem of narrow testing coverage.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118913622A_ABST
    Figure CN118913622A_ABST
Patent Text Reader

Abstract

The invention relates to an AR glasses test method, system, device and medium, and the method comprises the steps: constructing a scene test model through an SDK function of AR glasses; the scene test model comprises an interaction test scene, a plane test scene, a camera preview test scene, a space tracking test scene, a picture recognition test scene, an object recognition test scene, a space positioning test scene and a real-time rendering test scene; and in response to the received test request, testing each scene in the test scene model, and obtaining an AR silver mirror algorithm test result. Through the SDK function of the AR glasses, the scene test model is constructed, and the scene test model is installed to the AR glasses, thereby achieving the testing of the AR glasses algorithm. The problem that the test coverage is narrow when the AR glasses algorithm is tested in the prior art is solved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of AR glasses testing technology, and in particular to an AR glasses testing method, system, device and medium. Background Art

[0002] Currently, augmented reality (AR) glasses technology is developing rapidly and is widely used in many fields, from gaming and entertainment to industrial design, to education and medical care, with increasingly rich application scenarios.

[0003] However, the existing AR glasses technology is more common in a wide range of application scenarios, lacking a specific test method for AR glasses algorithms. When testing AR glasses algorithms, there is a problem of narrow test coverage. Summary of the invention

[0004] The embodiments of the present application provide an AR glasses testing method, system, device and medium to at least solve the problem of narrow test coverage when testing AR glasses algorithms in the related art.

[0005] In a first aspect, an embodiment of the present application provides an AR glasses testing method, the method comprising:

[0006] Build a scene test model, which is used to test AR glasses functional scenarios; AR glasses functional scenarios include interactive test scenarios, plane test scenarios, camera preview test scenarios, spatial tracking test scenarios, image recognition test scenarios, object recognition test scenarios, spatial positioning test scenarios, and real-time rendering test scenarios;

[0007] In response to receiving the test request, each scene in the AR glasses functional scene is tested according to the scene test model to obtain the AR silver mirror algorithm test result, wherein the test includes verifying whether the virtual content and the real scene in each scene are accurately superimposed.

[0008] In one embodiment, each scene in the AR glasses functional scene is tested according to the scene test model to obtain the AR silver mirror algorithm test results, including:

[0009] Test the interactive test scenario according to the interactive operation information in the AR space and obtain the interactive test scenario test result;

[0010] Testing the spatial tracking test scene according to the information of the test object in motion in the AR space, and obtaining the test result of the spatial tracking test scene;

[0011] Test the real-time rendering test scene according to the real-time rendering information in the AR space, and obtain the test result of the real-time rendering test scene;

[0012] Test the object recognition scene according to the test object information in the AR space and obtain the object recognition scene test result;

[0013] Test the camera preview test scene according to the camera display screen in the AR space, and obtain the camera preview test scene test result;

[0014] Test the plane test scene according to the plane information of the object in the AR space, and obtain the test result of the plane test scene;

[0015] Test the image recognition test scene according to the image information in the AR space, and obtain the test result of the image recognition test scene;

[0016] Test the spatial positioning test scene according to the position relationship of objects in the AR space, and obtain the test result of the spatial positioning test scene;

[0017] The test results of the AR silver mirror algorithm are determined based on the test results of the interactive test scene, the plane test scene, the camera preview test scene, the spatial tracking test scene, the image recognition test scene, the object recognition test scene, the spatial positioning test scene and the real-time rendering test scene.

[0018] In one embodiment, testing the interaction test scenario according to the interaction operation information in the AR space and obtaining the interaction test scenario test result includes:

[0019] Performing a first interactive operation on a test object in an interactive test scene through a gesture and / or a handle, and obtaining test object feedback information of the first interactive operation, where the first interactive operation includes selecting, grabbing, moving, and scaling;

[0020] Perform a second interactive operation on the operation interface in the interactive test scenario through gestures and / or a handle, and obtain operation interface feedback information of the second interactive operation, where the second interactive operation includes selecting, scrolling a slider, and clicking a handle button;

[0021] In response to the test object feedback information and the operation interface feedback information meeting the preset standard information, it is determined that the interactive test scenario test is normal.

[0022] In one embodiment, the space tracking test scene is tested according to the information of the test object in motion in the AR space, and the test result of the space tracking test scene includes:

[0023] Set up the test object in the AR space;

[0024] Observe the state of the test object in a motion state, wherein the motion state includes a translational motion state, a circular motion state, and a random motion state, and the test object state includes an anchoring state, a tearing state, a dragging state, and a scaling state;

[0025] In response to the state of the test object meeting the preset standard state, it is determined that the spatial tracking test scene test is normal.

[0026] In one embodiment, a real-time rendering test scene is tested according to real-time rendering information in an AR space, and the real-time rendering test scene test result includes:

[0027] By moving the observation position in the AR space, determine whether the scene scanned in the field of view can be rendered. If it can be rendered, determine whether the rendering model is integrated with the real scene, and determine the rendering performance overhead status within a preset period of time;

[0028] When the rendering model is integrated with the real scene and the rendering performance overhead state meets the preset state, it is determined that the real-time rendering test scene test is normal.

[0029] In one embodiment, testing an object recognition scene according to the test object information in the AR space and obtaining the object recognition scene test result includes:

[0030] Set up the test object in the AR space;

[0031] Observe whether the test object can be recognized. If the test object is recognized, observe whether the test object overlaps with the 3D model.

[0032] When the test object and the 3D model are overlapped, it is determined that the object recognition scene test is normal.

[0033] In one embodiment, testing an object recognition scene according to test object information in an AR space includes:

[0034] Set up the test object in the AR space;

[0035] Observe whether the test object can be recognized. If the test object is recognized, observe whether the test object overlaps with the 3D model.

[0036] When the test object and the 3D model overlap, confirm that the object recognition scene test is normal

[0037] In one embodiment, testing the camera preview test scene according to the camera display screen in the AR space includes:

[0038] In response to receiving a camera preview instruction, determining whether a camera image is displayed in the AR space;

[0039] In response to receiving a camera preview closing instruction, determining whether to close the camera display screen in the AR space;

[0040] When a camera preview instruction is received and the camera screen is displayed in the AR space, and when a camera preview closing instruction is received and the camera display screen is closed, it is determined that the camera preview test scene test is normal.

[0041] In one embodiment, before constructing the scenario test model, the method further includes:

[0042] Create a project based on the AR development platform in Unity;

[0043] Import Unity resources into the project, or add the SDK through Unity's manager to integrate the Unity SDK for AR glasses into the project. The SDK includes the files or scripts required to implement AR functions.

[0044] In one embodiment, constructing a scenario test model includes:

[0045] According to the AR glasses functions in the project, configure corresponding test scripts and test logic for each functional scenario;

[0046] Compile the configured functional scenes and generate the scene test model of AR glasses through Unity.

[0047] In a second aspect, an embodiment of the present application provides an AR glasses testing system, the system further comprising a scene test model building module and a test module; wherein:

[0048] Build a scene test model module, which is used to build a scene test model. The scene test model is used to test the AR glasses functional scenes; wherein the AR glasses functional scenes include interactive test scenes, plane test scenes, camera preview test scenes, space tracking test scenes, image recognition test scenes, object recognition test scenes, space positioning test scenes and real-time rendering test scenes;

[0049] The test module is used to test each scene in the test scene model in response to receiving a test request, and obtain the AR silver mirror algorithm test result, wherein the test includes verifying whether the virtual content and the real scene in each scene are accurately superimposed.

[0050] In a third aspect, an embodiment of the present application provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, an AR glasses testing method as described in the first aspect above is implemented.

[0051] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements an AR glasses testing method as described in the first aspect above.

[0052] The AR glasses testing method, system, device and medium provided by the embodiments of the present application have at least the following technical effects.

[0053] Through the SDK function of AR glasses, a scene test model is constructed; the scene test model includes an interactive test scene, a plane test scene, a camera preview test scene, a spatial tracking test scene, an image recognition test scene, an object recognition test scene, a spatial positioning test scene, and a real-time rendering test scene; in response to receiving a test request, each scene in the test scene model is tested to obtain the test results of the AR silver mirror algorithm. Through the SDK function of AR glasses, a scene test model is constructed, and the scene test model is installed on AR glasses to implement the testing of AR glasses algorithms. This solves the problem of narrow test coverage when testing AR glasses algorithms in related technologies.

[0054] Details of one or more embodiments of the present application are set forth in the following drawings and description to make other features, objects, and advantages of the present application more readily apparent. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0056] Figure 1 is a flow chart of an AR glasses testing method according to an exemplary embodiment;

[0057] Figure 2 is a flowchart of step S102 according to an exemplary embodiment;

[0058] Figure 3 is a flowchart of step S1021 according to an exemplary embodiment;

[0059] Figure 4 is a flowchart of step S1022 according to an exemplary embodiment;

[0060] Figure 5 is a flowchart of step S1023 according to an exemplary embodiment;

[0061] Figure 6 is a flowchart of step S1024 according to an exemplary embodiment;

[0062] Figure 7is a flowchart of step S1025 according to an exemplary embodiment.

[0063] Figure 8 A structural block diagram of an AR glasses testing system according to an exemplary embodiment;

[0064] Fig. 9 A structural block diagram of an electronic device is shown according to an exemplary embodiment. DETAILED DESCRIPTION

[0065] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application is described and illustrated below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not intended to limit the present application. Based on the embodiments provided in the present application, all other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of the present application.

[0066] Obviously, the drawings described below are only some examples or embodiments of the present application. For ordinary technicians in this field, the present application can also be applied to other similar scenarios based on these drawings without creative work. In addition, it can also be understood that although the efforts made in this development process may be complicated and lengthy, for ordinary technicians in this field related to the content disclosed in this application, some changes in design, manufacturing or production based on the technical content disclosed in this application are just conventional technical means, and should not be understood as insufficient content disclosed in this application.

[0067] Reference to "embodiments" in this application means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those of ordinary skill in the art that the embodiments described in this application may be combined with other embodiments without conflict.

[0068] Unless otherwise defined, the technical terms or scientific terms involved in this application should be understood by people with ordinary skills in the technical field to which this application belongs. The words "one", "a", "a", "the" and the like involved in this application do not indicate a quantitative limitation, and may represent the singular or plural. The terms "include", "comprise", "have" and any of their variations involved in this application are intended to cover non-exclusive inclusions; for example, a process, method, system, product or device that includes a series of steps or modules (units) is not limited to the listed steps or units, but may also include steps or units that are not listed, or may also include other steps or units inherent to these processes, methods, products or devices. The words "connect", "connected", "coupled" and the like involved in this application are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. The "multiple" involved in this application refers to two or more. "And / or" describes the association relationship of associated objects, indicating that there may be three relationships, for example, "A and / or B" can represent: A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the objects before and after are in an "or" relationship. The terms "first", "second", "third", etc. involved in this application are only used to distinguish similar objects and do not represent a specific ordering of the objects.

[0069] In a first aspect, the present application provides an AR glasses testing method. Figure 1 This is a flowchart of AR glasses testing, such as Figure 1 As shown, the method is applied to a head mounted display device, and a camera module is arranged at an optical exit pupil position of the head mounted display device; the method comprises:

[0070] Step S101, construct a scene test model, the scene test model is used to test the AR glasses functional scenes; wherein, the AR glasses functional scenes include interactive test scenes, plane test scenes, camera preview test scenes, spatial tracking test scenes, image recognition test scenes, object recognition test scenes, spatial positioning test scenes and real-time rendering test scenes.

[0071] Step S102, in response to receiving the test request, test each scene in the AR glasses functional scene according to the scene test model to obtain the AR silver mirror algorithm test result, wherein the test includes verifying whether the virtual content and the real scene in each scene are accurately superimposed.

[0072] In summary, an AR glasses testing method provided in an embodiment of the present application constructs a scene test model through the SDK function of AR glasses; the scene test model includes an interactive test scene, a plane test scene, a camera preview test scene, a space tracking test scene, an image recognition test scene, an object recognition test scene, a space positioning test scene, and a real-time rendering test scene; in response to receiving a test request, each scene in the test scene model is tested to obtain the AR silver mirror algorithm test result. Through the SDK function of AR glasses, a scene test model is constructed, and the scene test model is installed on AR glasses, thereby realizing the testing of AR glasses algorithms. This solves the problem of narrow test coverage when testing AR glasses algorithms in related technologies.

[0073] In one embodiment, before step S101, the AR glasses testing method further includes:

[0074] Create a project based on the AR development platform in Unity;

[0075] Import Unity resources into the project, or add the SDK through Unity's manager to integrate the Unity SDK for AR glasses into the project. The SDK includes the files or scripts required to implement AR functions.

[0076] Optionally, first, you need to install appropriate development tools, such as Unity Hub and a specified version of Unity (such as 2021.3.X), and configure the development environment for the Android platform. Next, import the dedicated Unity SDK for AR glasses into the project, which can be done by directly importing the unitypackage file (unity resource) or using Unity Package Manager (Unity's manager) to add a Git repository link. This step ensures that the development environment has all the necessary components to implement AR functions.

[0077] By integrating the SDK using Unity Package Manager and Git URL, project dependency management is more automated and transparent, which is conducive to long-term development and iteration. By integrating the Unity SDK for AR glasses into the project, the basic framework for subsequent AR function testing is laid.

[0078] In one embodiment, step S101, construct a scene test model, the scene test model is used to test the AR glasses functional scene; wherein the AR glasses functional scene includes an interactive test scene, a plane test scene, a camera preview test scene, a space tracking test scene, a picture recognition test scene, an object recognition test scene, a space positioning test scene and a real-time rendering test scene. Specifically including:

[0079] According to the AR glasses functions in the project, configure corresponding test scripts and test logic for each functional scenario;

[0080] Compile the configured functional scenes and generate the scene test model of AR glasses through Unity.

[0081] Optionally, according to the SDK documentation and function set provided by the AR glasses, design and implement a series of test scenarios. These scenarios are designed to verify the core functions of the AR application, such as interactive test scenarios, plane test scenarios, camera preview test scenarios, spatial tracking test scenarios, image recognition test scenarios, object recognition test scenarios, spatial positioning test scenarios, and real-time rendering test scenarios. Through the Unity editor, virtual elements (3D models, UI interfaces, etc.) can be intuitively arranged in the real-world environment to simulate the scene that the user will interact with. Each test scene will be given a specific behavior logic. According to the API provided by the SDK, write code to control the enabling of AR functions, parameter adjustment, user interaction response, etc., for testing AR functions. After completing the scene configuration and script writing, the project will be compiled through Unity, and this process integrates all resources and scripts into an executable file or application package. For AR glasses, this usually means generating an installation package (scenario test model) for a specific platform (such as Android or iOS), including various scene models for testing AR functions.

[0082] Through the scenario test model constructed in step S101, the test data is recorded and analyzed, the problems of the algorithm in actual operation are observed, and the problems are quickly fed back to the development team, so as to promote the optimization of code and design and improve the overall quality and stability of the application.

[0083] Figure 2 is a flowchart of step S102 according to an exemplary embodiment, such as Figure 2 As shown, step S102, in response to receiving a test request, tests are performed on each scene in the test scene model to obtain the AR silver mirror algorithm test results. Specifically, the following steps are included:

[0084] Step S1021: Test the interactive test scene according to the interactive operation information in the AR space, and obtain the interactive test scene test result;

[0085] Step S1022: testing the space tracking test scene according to the test object information in the moving state in the AR space, and obtaining the test result of the space tracking test scene;

[0086] Step S1023: testing the real-time rendering test scene according to the real-time rendering information in the AR space, and obtaining a test result of the real-time rendering test scene;

[0087] Step S1024: testing the object recognition scene according to the test object information in the AR space to obtain the object recognition scene test result;

[0088] Step S1025: Test the camera preview test scene according to the camera display screen in the AR space, and obtain the camera preview test scene test result;

[0089] Step S1026: testing the plane test scene according to the object plane information in the AR space, and obtaining the plane test scene test result;

[0090] Step S1027: testing the image recognition test scene according to the image information in the AR space, and obtaining the image recognition test scene test result;

[0091] Step S1028: testing the spatial positioning test scene according to the position relationship of the objects in the AR space, and obtaining the test result of the spatial positioning test scene;

[0092] Step S1029, determine the AR silver mirror algorithm test results based on the interactive test scene test results, the plane test scene test results, the camera preview test scene test results, the space tracking test scene test results, the image recognition test scene test results, the object recognition scene test results, the space positioning test scene test results and the real-time rendering test scene test results.

[0093] In step S102, in response to receiving the test request, each scene in the test scene model is tested to obtain the test results of the AR silver mirror algorithm. The key functional points in AR applications are covered, including interactive operations, spatial tracking, real-time rendering, object recognition, camera preview, plane detection, image recognition and spatial positioning, and a comprehensive AR glasses algorithm test is achieved, which is conducive to ensuring the stability of AR applications and the quality of user experience, as well as ensuring the accuracy and efficiency of the algorithm in various scenarios.

[0094] Figure 3 is a flowchart of step S1021 according to an exemplary embodiment, as shown in Figure 3 As shown, the above step S1021 tests the interactive test scene according to the interactive operation information in the AR space to obtain the interactive test scene test result. Specifically, it includes the following steps:

[0095] Step S10211: Perform a first interactive operation on a test object in the interactive test scene through a gesture and / or a handle, and obtain test object feedback information of the first interactive operation, where the first interactive operation includes selecting, grabbing, moving, and scaling;

[0096] Step S10212: performing a second interactive operation on the operation interface in the interactive test scenario through gestures and / or a handle, and obtaining operation interface feedback information of the second interactive operation, where the second interactive operation includes selecting, scrolling a slider, and clicking a handle button;

[0097] Step S10213: In response to the test object feedback information and the operation interface feedback information meeting the preset standard information, it is determined that the interactive test scenario test is normal.

[0098] Optionally, multiple test objects, 3-4 optional, and a UI interface are placed in the interactive test scene, and the first interactive operation is performed on the test object through gestures or handles, wherein the test object includes a virtually constructed object such as an AR block, and the first interactive operation includes conventional operations such as selection, grabbing, moving, and scaling, and the buttons on the UI interface can also be operated. During the test process, you first need to wear AR glasses with this scene demo (scene test model) installed, open the application, and when the scene is initialized, determine whether the display, spatial position, and UI interface display of each AR block are correct. Stretch out your hands, observe the fit between your hands and the virtual hand model, stretch out your hands, interact with the AR block in front of your field of vision, and perform conventional operations such as selection, grabbing, moving, and scaling to see if they are normal. Use the handle to operate the slider and button to see if it is normal, and whether the information returned in the UI interface is correct when the buttons on the handle are clicked or touched. Use AR glasses to project, record, and capture the screen, and observe whether the display on the screen correctly superimposes the virtual model and the real scene. The interactive test scene test is normal when the display, spatial position, and UI interface of each AR block are correct, the fit between the hands and the virtual hand model is normal, and the interactive feedback information of the AR block in front of the field of view meets the preset standard information.

[0099] The interactivity of the AR glasses application is tested by step S1021 to ensure the interactive function of the AR glasses.

[0100] Figure 4 is a flowchart of step S1022 according to an exemplary embodiment, as shown in Figure 4 As shown, the above step S1022, testing the space tracking test scene according to the test object information in the moving state in the AR space, and obtaining the test result of the space tracking test scene; specifically includes the following steps:

[0101] Step S10221: Setting a test object in the AR space;

[0102] Step S10222, observing the state of the test object in a motion state, wherein the motion state includes a translational motion state, a circling motion state, and a random motion state, and the test object state includes an anchoring state, a tearing state, a dragging state, and a scaling state;

[0103] Step S10223: In response to the state of the test object meeting the preset standard state, determining that the spatial tracking test scene test is normal.

[0104] Optionally, AR cubes placed in the AR space are used as representatives of virtual content (test objects) to simulate various dynamic objects that may be encountered in actual applications. These cubes are designed to have 6 degrees of freedom (6DoF) tracking, that is, they can move along the X, Y, and Z axes and rotate around these three axes, so as to test the spatial tracking performance of AR glasses in all directions. By observing the performance of AR cubes in different motion states (such as translation, rotation, and random motion), the test covers various scenarios that users may encounter in daily use. This not only tests the tracking stability of AR glasses in a static environment, but also challenges its adaptability in a dynamic and complex environment. By monitoring the anchoring state of AR cubes (i.e., whether the virtual object is stably attached to a certain position in the real world), the tearing state (sudden displacement of the virtual object caused by tracking loss), the dragging feeling (delay or discontinuity of the following action), and other abnormal states (such as jitter, scaling errors), the standard state for judging whether the spatial tracking performance meets the preset standard state is established. Combined with screen projection, screen recording, screenshots and other means, the fusion effect of virtual content and real scenes is verified from different angles to ensure the consistency and authenticity of the AR experience. This comprehensive testing approach helps to identify and correct subtle deviations in spatial tracking, optimizing the user experience.

[0105] Through step S1022, it is ensured that AR glasses can provide high-precision tracking effects in various motion states, reduce the jitter, tearing or dragging of virtual objects, and improve the smoothness and immersion of user experience. The test covers a variety of motion modes and scene changes to ensure that AR applications can work stably in different environments and conditions, enhancing the versatility and reliability of the technology.

[0106] Figure 5 is a flowchart of step S1023 according to an exemplary embodiment, as shown in Figure 5 As shown, the above step S1023 tests the real-time rendering test scene according to the real-time rendering information in the AR space to obtain the real-time rendering test scene test result. Specifically, it includes the following steps:

[0107] Step S10231: in the AR space, by moving the observation position, determine whether the scene scanned in the field of view can be rendered. If it can be rendered, determine whether the rendering model is integrated with the real scene, and determine the rendering performance overhead status within a preset period of time;

[0108] Step S10232: When the rendering model is integrated with the real scene and the rendering performance overhead state meets the preset state, it is determined that the real-time rendering test scene test is normal.

[0109] Optionally, during the test, you first need to wear AR glasses with a real-time rendering test scene installed, open the application, determine whether the scene initialization is normal, and move the observation position in the AR space to determine whether the scene scanned in the field of view can be rendered. If it can be rendered, determine whether the rendering model is integrated with the real scene, and determine the rendering performance overhead status within a preset period of time (within 20 minutes). Subsequently, export the mesh rendered point cloud and open it with software to observe whether the rendering result is consistent with the real scene. Evaluate the rendering stability under long-term operation to avoid rendering quality degradation or tracking drift problems caused by exhaustion of computing resources. When the rendering model is integrated with the real scene, and the rendering performance overhead status meets the preset status, it is determined that the real-time rendering test scene test is normal.

[0110] By testing whether the real-time rendering is integrated with the scene through step S1023, and by testing the performance overhead within a preset time period, the bottleneck in the rendering process can be identified and optimized, thereby reducing unnecessary computing consumption, extending battery life, and improving the usability of the device.

[0111] Figure 6 is a flow chart of step S1024 according to an exemplary embodiment, as shown in Figure 6 As shown, the above step S1024 tests the object recognition scene according to the test object information in the AR space to obtain the object recognition scene test result. Specifically, it includes the following steps:

[0112] Step S10241: Setting a test object in the AR space;

[0113] Step S10242: Observe whether the test object can be recognized. If the test object is recognized, observe whether the test object overlaps with the 3D model.

[0114] Step S10243: When the test object and the 3D model overlap, determine that the object recognition scene test is normal.

[0115] Optionally, in order to verify the object recognition ability of AR glasses, specific test objects or marking patterns are arranged in the AR space in advance as test samples. When the user wears AR glasses and approaches the test object, the camera captures the image and is processed by the object recognition algorithm. The algorithm quickly analyzes the features in the image based on the trained model, matches it with the object model in the database, and realizes recognition. After successful recognition, the system triggers the loading and rendering of the corresponding 3D model. Once the object is successfully identified, the system attempts to align the preset 3D model to the position and size of the actual object. Observe whether the test object coincides with the 3D model. When the test object coincides with the 3D model, it is determined that the object recognition scene test is normal.

[0116] The object recognition scene test results are obtained through step S1024, which is conducive to the subsequent adjustment of the object recognition scene test results and improves the user experience.

[0117] Figure 7 is a flowchart of step S1025 according to an exemplary embodiment, such as Figure 7 As shown, the above step S1025 tests the camera preview test scene according to the camera display screen in the AR space to obtain the camera preview test scene test result. Specifically, it includes the following steps:

[0118] Step S10251: In response to receiving a camera preview instruction, determining whether a camera image is displayed in the AR space;

[0119] Step S10252: In response to receiving a camera preview closing instruction, determining whether the camera display screen is closed in the AR space;

[0120] Step S10253: When a camera preview instruction is received and the camera screen is displayed in the AR space, and when a camera preview closing instruction is received and the camera display screen is closed, it is determined that the camera preview test scene test is normal.

[0121] Optionally, when receiving a start preview command sent by the user through an interface operation, it activates the built-in RGB camera of the AR glasses, starts capturing the real-time video stream, and renders it to a specified area of ​​the AR space. When the user issues a stop preview command, the application needs to respond quickly, stop the camera's video stream capture and rendering, and release related system resources. Through the successful execution of the above two steps, it is confirmed that the camera preview function can be turned on and off as needed, indicating that the integration at the hardware and software levels is working properly and the user interface communicates correctly with the underlying service.

[0122] The camera preview test scene test result is obtained through step S1025, which is conducive to the subsequent adjustment of the camera preview test scene and improves the user experience.

[0123] In one embodiment, step S1026, testing the plane test scene according to the object plane information in the AR space, and obtaining the plane test scene test result. Specifically includes:

[0124] Optionally, first observe whether the initialization of the plane test scene is normal. Under normal circumstances, scan the desktop, ground and other planes in the space to observe whether the plane can be detected and the virtual plane model can be displayed. If so, the plane is identified and the test results of the plane test scene are obtained. If not, the parameters related to the plane test scene need to be readjusted.

[0125] In one embodiment, step S1027, testing the image recognition test scene according to the image information in the AR space, and obtaining the image recognition test scene test result. Specifically includes:

[0126] Optionally, pre-register the image to be identified in the system as a marker. Move the 2D image to be detected into the field of view to observe whether the image can be identified normally, whether the marker display is normal after successful identification, and whether the size and position of the marker coincide with the 2D image. Switch between automatic identification and manual identification to test whether the identification can be performed according to the settings. When the marker display is normal, the size and position of the marker coincide with the 2D image, and whether the identification can be performed according to the settings, obtain the result of the image recognition test scene test as normal.

[0127] Step S1028: Test the spatial positioning test scene according to the position relationship of the objects in the AR space, and obtain the test result of the spatial positioning test scene. Specifically including:

[0128] Optionally, the spatial positioning test scene can perform visual positioning of the spatial environment. Before the test, the 3D spatial scene to be identified needs to be modeled and the cloud positioning service needs to be deployed, and the cloud positioning service address needs to be configured in the unity project. During the test, you first need to wear AR glasses with the scene test model installed, open the application, and determine whether the scene initialization is normal. Wear glasses to visually locate the 3D spatial scene, observe whether the spatial scene can be recognized normally, whether the 3D virtual content display after successful recognition is normal, and whether the model size and position fit the actual scene. The error in this embodiment is reasonable within 20cm. Manually click the repositioning button to observe whether it works. When the scene initialization is normal, the 3D virtual content display is normal, the model size and position fit the actual scene, and the manual click of the repositioning button takes effect, it is determined that the spatial positioning test scene test is normal. It is worth noting that the cloud positioning service needs to collect a certain spatial scene, perform 3D modeling, and deploy the modeling results on the server as a cloud positioning server for testing.

[0129] In one embodiment, the test includes verifying whether the virtual content and the real scene in each scene are accurately superimposed. Specifically, it includes: using AR glasses to project, record, and take screenshots, and observing whether the display on the screen correctly superimposes the virtual model and the real scene. Testing the superposition effect of AR content and real scenes by projecting, recording, and taking screenshots can not only ensure the performance and stability of AR applications from a technical level, but also improve the overall immersion and acceptance from the perspective of user experience.

[0130] In summary, an AR glasses testing method provided in an embodiment of the present application, in summary, an AR glasses testing method provided in an embodiment of the present application, constructs a scene test model through the SDK function of AR glasses; the scene test model includes an interactive test scene, a plane test scene, a camera preview test scene, a space tracking test scene, a picture recognition test scene, an object recognition test scene, a space positioning test scene and a real-time rendering test scene; in response to receiving a test request, each scene in the test scene model is tested to obtain the AR silver mirror algorithm test result. Through the SDK function of AR glasses, a scene test model is constructed, and the scene test model is installed on AR glasses to realize the testing of AR glasses algorithms. It solves the problem of narrow test coverage when testing AR glasses algorithms in related technologies.

[0131] In a second aspect, an embodiment of the present application provides an AR glasses testing system. Figure 8 FIG. 1 is a block diagram of an AR glasses testing system according to an exemplary embodiment. Figure 8 As shown, the system also includes a scenario test model building module 810 and a test module 880; wherein:

[0132] The scene test model building module 810 is used to build a scene test model, and the scene test model is used to test the AR glasses functional scenes; wherein, the AR glasses functional scenes include interactive test scenes, plane test scenes, camera preview test scenes, spatial tracking test scenes, image recognition test scenes, object recognition test scenes, spatial positioning test scenes and real-time rendering test scenes.

[0133] The test module 880 is used to test each scene in the test scene model in response to receiving a test request, and obtain the AR silver mirror algorithm test result, wherein the test includes verifying whether the virtual content and the real scene in each scene are accurately superimposed.

[0134] In summary, the present application provides an AR glasses testing system. By constructing a scene test model module 810 and a test module 880, the problem of narrow test coverage when testing AR glasses algorithms in related technologies is solved. Specifically, a scene test model is constructed through the SDK function of AR glasses; the scene test model includes an interactive test scene, a plane test scene, a camera preview test scene, a space tracking test scene, an image recognition test scene, an object recognition test scene, a space positioning test scene, and a real-time rendering test scene; in response to receiving a test request, each scene in the test scene model is tested to obtain the test results of the AR silver mirror algorithm. Through the SDK function of AR glasses, a scene test model is constructed, and the scene test model is installed on the AR glasses to realize the testing of the AR glasses algorithm. The problem of narrow test coverage when testing AR glasses algorithms in related technologies is solved.

[0135] It should be noted that the AR glasses testing system provided in this embodiment is used to implement the above-mentioned implementation mode, and the descriptions that have been made will not be repeated. As used above, the terms "module", "unit", "sub-unit", etc. can implement a combination of software and / or hardware for predetermined functions. Although the devices described in the above embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0136] In a third aspect, an embodiment of the present application provides an electronic device, Fig. 9 FIG. 1 is a block diagram of an electronic device according to an exemplary embodiment. Fig. 9 As shown, the electronic device may include a processor 91 and a memory 92 storing computer program instructions.

[0137] Specifically, the processor 91 may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiments of the present application.

[0138] Among them, the memory 92 may include a large-capacity memory for data or instructions. By way of example and not limitation, the memory 92 may include a hard disk drive (HDD), a floppy disk drive, a solid-state drive (SSD), a flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a universal serial bus (USB) drive, or a combination of two or more of these. Where appropriate, the memory 92 may include a removable or non-removable (or fixed) medium. Where appropriate, the memory 92 may be inside or outside a data processing device. In a specific embodiment, the memory 92 is a non-volatile memory. In a specific embodiment, the memory 92 includes a read-only memory (ROM) and a random access memory (RAM). Where appropriate, the ROM may be a mask-programmed ROM, a programmable ROM (Programmable Read-Only Memory, PROM for short), an erasable PROM (Erasable ProgrammableRead-Only Memory, EPROM for short), an electrically erasable PROM (Electrically Erasable ProgrammableRead-Only Memory, EEPROM for short), an electrically alterable ROM (Electrically Alterable Read-Only Memory, EAROM for short) or a flash memory (FLASH) or a combination of two or more of these. Under appropriate circumstances, the RAM can be a static random access memory (SRAM) or a dynamic random access memory (DRAM), wherein the DRAM can be a fast page mode dynamic random access memory (FPMDRAM), an extended data output dynamic random access memory (EDODRAM), a synchronous dynamic random access memory (SDRAM), etc.

[0139] The memory 92 may be used to store or cache various data files required for processing and / or communication, as well as possible computer program instructions executed by the processor 91 .

[0140] The processor 91 implements any one of the AR glasses testing methods in the above embodiments by reading and executing computer program instructions stored in the memory 92.

[0141] In one embodiment, an AR glasses testing device may further include a communication interface 93 and a bus 90. Fig. 9 As shown, the processor 91, the memory 92, and the communication interface 93 are connected via a bus 90 and communicate with each other.

[0142] The communication interface 93 is used to implement communication between the modules, devices, units and / or equipment in the embodiment of the present application. The communication port 93 can also implement data communication with other components such as: external devices, image / data acquisition equipment, databases, external storage, and image / data processing workstations.

[0143] The bus 90 includes hardware, software, or both, and couples the components of an AR glasses testing device to each other. The bus 90 includes, but is not limited to, at least one of the following: a data bus, an address bus, a control bus, an expansion bus, and a local bus. By way of example and not limitation, bus 90 may include an Accelerated Graphics Port (AGP) or other graphics bus, an Extended Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), a Hyper Transport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an InfiniBand interconnect, a Low Pin Count (LPC) bus, a memory bus, a Micro Channel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local Bus (VLB) bus, or other suitable buses or a combination of two or more of these. Where appropriate, bus 90 may include one or more buses. Although embodiments of the present application describe and illustrate a particular bus, the present application contemplates any suitable bus or interconnect.

[0144] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium having a program stored thereon. When the program is executed by a processor, an AR glasses testing method provided in the first aspect is implemented.

[0145] The readable storage medium may include but is not limited to: a portable disk, a hard disk, a random access memory, a read-only memory, an erasable programmable read-only memory, an optical storage device, a magnetic storage device or any suitable combination of the above.

[0146] In a possible implementation, the present invention can also be implemented in the form of a program product, which includes program code. When the program product is run on a terminal device, the program code is used to enable the terminal device to execute the steps of an AR glasses testing method provided in the first aspect.

[0147] Among them, the program code for executing the present invention can be written in any combination of one or more programming languages, and the program code can be executed completely on the user device, partially on the user device, as an independent software package, partially on the user device and partially on a remote device, or completely on the remote device.

[0148] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0149] The above embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the attached claims.

Claims

1. A method for testing AR glasses, characterized in that: Methods include: Construct a scene test model, which is used to test AR glasses functional scenes; wherein the AR glasses functional scenes include interactive test scenes, plane test scenes, camera preview test scenes, spatial tracking test scenes, image recognition test scenes, object recognition test scenes, spatial positioning test scenes, and real-time rendering test scenes; In response to receiving a test request, each scene in the AR glasses functional scene is tested according to the scene test model to obtain an AR silver mirror algorithm test result, wherein the test includes verifying whether the virtual content and the real scene in each scene are accurately superimposed.

2. The method according to claim 1, characterized in that: The method of testing each scene in the AR glasses functional scene according to the scene test model to obtain the AR silver mirror algorithm test result includes: Testing the interactive test scenario according to the interactive operation information in the AR space, and obtaining an interactive test scenario test result; Testing the space tracking test scene according to the test object information in a moving state in the AR space, and obtaining a test result of the space tracking test scene; Testing the real-time rendering test scene according to the real-time rendering information in the AR space, and obtaining a test result of the real-time rendering test scene; Testing the object recognition scene according to the test object information in the AR space to obtain the object recognition scene test result; Testing the camera preview test scene according to the camera display screen in the AR space, and obtaining a camera preview test scene test result; Testing the plane test scene according to the object plane information in the AR space, and obtaining a plane test scene test result; Testing the image recognition test scene according to the image information in the AR space, and obtaining a test result of the image recognition test scene; Testing the spatial positioning test scene according to the position relationship of objects in the AR space, and obtaining a test result of the spatial positioning test scene; Based on the test results of the interactive test scene, the plane test scene, the camera preview test scene, the spatial tracking test scene, the image recognition test scene, the object recognition scene, the spatial positioning test scene and the real-time rendering test scene, the AR silver mirror algorithm test results are determined.

3. The method according to claim 2, characterized in that The testing of the interactive test scenario according to the interactive operation information in the AR space and obtaining the interactive test scenario test result includes: Performing a first interactive operation on a test object in the interactive test scene through a gesture and / or a handle, and obtaining test object feedback information of the first interactive operation, wherein the first interactive operation includes selecting, grabbing, moving, and scaling; Performing a second interactive operation on the operation interface in the interactive test scenario through gestures and / or a handle, and obtaining operation interface feedback information of the second interactive operation, wherein the second interactive operation includes selecting, scrolling a slider, and clicking a handle button; In response to the test object feedback information and the operation interface feedback information meeting preset standard information, it is determined that the interactive test scenario test is normal.

4. The method according to claim 2, characterized in that: The spatial tracking test scene is tested according to the test object information in the moving state in the AR space, and the test result of the spatial tracking test scene includes: Setting a test object in the AR space; Observe the state of the test object in a motion state, wherein the motion state includes a translational motion state, a circling motion state, and a random motion state, and the test object state includes an anchoring state, a tearing state, a dragging state, and a scaling state; In response to the state of the test object meeting a preset standard state, it is determined that the spatial tracking test scene test is normal.

5. The method according to claim 2, characterized in that: The real-time rendering test scene is tested according to the real-time rendering information in the AR space, and the test result of the real-time rendering test scene includes: By moving the observation position in the AR space, determining whether the scene scanned in the field of view can be rendered, and if it can be rendered, determining whether the rendering model is integrated with the real scene, and determining the rendering performance overhead status within a preset time period; In the case where the rendering model is integrated with the real scene and the rendering performance overhead state meets a preset state, it is determined that the real-time rendering test scene test is normal.

6. The method according to claim 2, characterized in that The testing of the object recognition scene according to the test object information in the AR space to obtain the object recognition scene test result includes: Setting a test object in the AR space; Observe whether the test object can be identified, and if the test object is identified, observe whether the test object overlaps with the 3D model; In a state where the test object and the 3D model overlap, it is determined that the object recognition scene test is normal.

7. The method according to claim 2, characterized in that The step of testing the camera preview test scene according to the camera display screen in the AR space and obtaining the camera preview test scene test result includes: In response to receiving a camera preview instruction, determining whether a camera image is displayed in the AR space; In response to receiving the instruction to close the camera preview, determining whether to close the camera display screen in the AR space; When a camera preview instruction is received and the camera screen is displayed in the AR space, and when a camera preview closing instruction is received and the camera display screen is closed, it is determined that the camera preview test scene test is normal.

8. The method according to claim 1, characterized in that Before building the scenario test model, the method also includes: Create a project based on the AR development platform in Unity; Import Unity resources into the project, or add the SDK through Unity's manager to integrate the Unity SDK for AR glasses into the project. The SDK includes the files or scripts required to implement AR functions.

9. The method according to claim 8, characterized in that Build a scenario test model, including: According to the AR glasses functions in the project, configure corresponding test scripts and test logic for each functional scenario; Compile the configured functional scenes and generate the scene test model of AR glasses through Unity.

10. An AR glasses testing system, characterized in that: The system also includes a scenario test model building module and a test module; wherein: The scene test model building module is used to build a scene test model, and the scene test model is used to test the AR glasses functional scene; wherein the AR glasses functional scene includes an interactive test scene, a plane test scene, a camera preview test scene, a space tracking test scene, a picture recognition test scene, an object recognition test scene, a space positioning test scene and a real-time rendering test scene; The test module is used to test each scene in the test scene model in response to receiving a test request, and obtain the AR silver mirror algorithm test result, wherein the test includes verifying whether the virtual content and the real scene in each scene are accurately superimposed.