Method and apparatus for testing ar glasses

Abstract

The application provides an AR glasses testing method and device. The method comprises: determining different preset point positions needing to be tested according to collected data; simulating an artificial testing environment to test a face recognition function of the AR glasses to be tested, and the artificial testing environment comprises: controlling the AR glasses to be tested to move to different preset point positions, controlling ambient light to reach different light conditions at different preset point positions, and completing face recognition function testing at a preset point position needing to be tested under different light conditions. The AR glasses testing method and device provided by the application can accurately copy test positions, test light conditions and test postures in a test environment during face recognition function testing of the AR glasses, realize automatic testing of accurate simulation of the artificial testing environment, and enable the AR glasses to be in the simulated artificial testing environment during testing, thereby improving the accuracy of face recognition function testing of the AR glasses.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of augmented reality, and particularly relates to an AR glasses testing method and device. BACKGROUND

[0002] AR glasses are a new form of wearable electronic device. Compared with other wearable devices and mobile phones, the display screen and interaction mode of AR glasses are strongly related to the body posture and spatial position of the user, and AR glasses are in a long-term wearing state. In the existing testing process of the face recognition function of AR glasses, a static method (device flat placement) is mostly used to test the face recognition function of AR glasses.

[0003] In the existing static testing method, the face recognition function of AR glasses is tested based on the device flat placement mode. However, this method cannot accurately simulate the posture changes of people and the environmental changes under various complex conditions during testing, thereby achieving accurate testing of the face recognition function of AR glasses. SUMMARY

[0004] The present application provides an AR glasses testing device and method to solve the technical problem that the existing technology cannot accurately simulate the posture changes of people and the environmental changes under various complex conditions during testing, thereby achieving accurate testing of the face recognition function of AR glasses.

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

[0006] Collecting artificial test parameters, including: collecting data of the face recognition function at various preset postures at different preset points in a target area; determining the postures that need to be tested at different preset points according to the collected data;

[0007] Simulating an artificial test environment, and testing the face recognition function of the to-be-tested AR glasses in the simulated artificial test environment;

[0008] The simulated artificial test environment includes: placing the to-be-tested AR glasses at the intersection of a cross track, and controlling the parallel movement of the two tracks of the cross track to move the to-be-tested AR glasses at the intersection of the cross track to different preset points in a target area,

[0009] At each different preset point, the environmental light is controlled to reach different light conditions, and the face recognition function test at the posture that needs to be tested at the preset point is completed under each light condition.

[0010] In an embodiment, the data of the face recognition function of the AR glasses at different preset points in the target area is collected, including: acquiring the posture data of the AR glasses at different preset points in the target area.

[0011] The data collected is used to determine the posture to be tested at different preset points, including: taking the average of the posture data of the AR glasses at different preset points as the posture to be tested at each preset point; or, based on a clustering algorithm, clustering analysis is performed on the posture data of the AR glasses at different preset points in the target area, and the cluster center of the posture data at different preset points is taken as the posture to be tested at the preset point.

[0012] In an embodiment, the data collected is used to determine the posture to be tested at different preset points, including:

[0013] The posture to be tested at different preset points is determined from the collected data, and the posture to be tested at different preset points is determined from the collected data.

[0014] In an embodiment, the different preset points are determined based on a preset interval after the target area is divided.

[0015] In an embodiment, the various preset postures include at least one of a horizontal viewing posture, an upward viewing posture, a downward viewing posture, a left viewing posture, and a right viewing posture.

[0016] In a second aspect, the application also provides an AR glasses testing device, including: a cross rail, a three-degree-of-freedom holder, a display module, a light adjustment module, and a test control module.

[0017] The cross rail is used to carry the three-degree-of-freedom holder to move the three-degree-of-freedom holder in the target area.

[0018] The three-degree-of-freedom holder is used to simulate various postures.

[0019] The display module is fixed in front of the target area and is used to display a face image.

[0020] The light adjustment module is used to control the light change of the ambient light in the test environment.

[0021] The test control module is used to simulate a test environment to test the face recognition function of the AR glasses, and the simulation of the test environment includes:

[0022] putting the to-be-tested AR glasses on the three-degree-of-freedom holder, making the three-degree-of-freedom holder be located at a cross point of a cross track, controlling the two tracks of the cross track to move respectively and parallelly to make the to-be-tested AR glasses located at the cross point of the cross track move to different preset point positions of a target area,

[0023] controlling the light adjustment module to make ambient light reach different light conditions, and completing, under each light condition, a face recognition function test in a posture required to be tested at each preset point position.

[0024] In an embodiment, the test control module is further configured to:

[0025] control the display module to display according to a preset display brightness.

[0026] In a third aspect, the present application further provides an AR glasses testing device, comprising:

[0027] a collection module configured to collect artificial test parameters, including collecting data of a face recognition function performed at different preset point positions in a target area in various preset postures;

[0028] a posture determination module configured to determine postures required to be tested at different preset point positions according to the collected data;

[0029] a test module configured to simulate an artificial test environment and test a face recognition function of to-be-tested AR glasses in the simulated artificial test environment.

[0030] the simulated artificial test environment includes: putting the to-be-tested AR glasses on a cross point of a cross track, controlling the two tracks of the cross track to move respectively and parallelly to make the to-be-tested AR glasses located at the cross point of the cross track move to different preset point positions of a target area,

[0031] controlling ambient light to reach different light conditions, and completing, under each light condition, a face recognition function test in a posture required to be tested at each preset point position.

[0032] In a fourth aspect, the present application further provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements the AR glasses testing method according to any of the above when executing the computer program.

[0033] In a fifth aspect, the present application further provides a non-transitory computer readable storage medium having a computer program stored thereon, and the computer program is executable on a processor to implement the AR glasses testing method according to any of the above.

[0034] In a sixth aspect, the present application also provides a computer program product comprising a computer program which, when executed by a processor, implements the AR glasses testing method according to any one of the above.

[0035] The AR glasses testing method and device provided by the present application can accurately copy the test position, test light condition and test posture in the test environment during the process of testing the face recognition function of the AR glasses, thereby accurately simulating the artificial test environment and automatically testing the face recognition function of the AR glasses. The AR glasses can be in the simulated artificial test environment during the test process, and the accuracy of the face recognition function test of the AR glasses is improved. BRIEF DESCRIPTION OF DRAWINGS

[0036] In order to more clearly illustrate the technical solutions in the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description are some embodiments of the present application, and other drawings can also be obtained by those skilled in the art without creative labor.

[0037] Figure 1 The flowchart of the AR glasses testing method provided by the embodiment of the present application is shown in the figure.

[0038] Figure 2 The point position diagram provided by the embodiment of the present application is shown in the figure.

[0039] Figure 3 The structural diagram of the AR glasses testing device provided by the embodiment of the present application is shown in the figure.

[0040] Figure 4 The gimbal movement range diagram provided by the embodiment of the present application is shown in the figure.

[0041] Figure 5 The flowchart of the artificial test parameter acquisition provided by the embodiment of the present application is shown in the figure.

[0042] Figure 6 The flowchart of the AR glasses automatic test provided by the embodiment of the present application is shown in the figure.

[0043] Figure 7 The logical structure diagram of the AR glasses testing system provided by the embodiment of the present application is shown in the figure.

[0044] Figure 8 The structural diagram of the electronic device provided by the embodiment of the present application is shown in the figure. DETAILED DESCRIPTION

[0045] In order to make the purposes, technical solutions and advantages of the present application clearer, the technical solutions in the present application will be described clearly and completely below in combination with the drawings in the present application. Obviously, the described embodiments are only some of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the protection scope of the present application.

[0046] Figure 1 A flowchart of an AR glasses testing method provided by the embodiments of the present application is shown in FIG. 1. Referring to FIG. 1, Figure 1 The AR glasses testing method provided by the embodiments of the present application can include the following steps.

[0047] In step 110, artificial testing parameters are collected, including:

[0048] Data of face recognition functions in various preset postures at different preset point positions in a target area are collected.

[0049] In step 120, the postures that need to be tested at different preset point positions are determined according to the collected data.

[0050] In step 130, an artificial testing environment is simulated, and the face recognition function of the AR glasses to be tested is tested in the simulated artificial testing environment.

[0051] The simulated artificial testing environment includes: placing the AR glasses to be tested at the intersection of a cross track, and controlling the two tracks of the cross track to move respectively in parallel to move the AR glasses to be tested at the intersection of the cross track to different preset point positions in a target area,

[0052] At each different preset point position, the ambient light is controlled to reach different light conditions, and the face recognition function test in the posture that needs to be tested at each light condition is completed.

[0053] It should be noted that AR (Augmented Reality) is a technology that skillfully combines virtual information with the real world. It widely uses multimedia, three-dimensional modeling, real-time tracking and registration, intelligent interaction, sensing and other technical means. After simulating and emulating virtual information such as computer-generated text, images, three-dimensional models, music, videos, etc., it is applied to the real world, and the two kinds of information complement each other, so as to realize the "enhancement" of the real world. AR glasses generally include a camera, which can be used to acquire scene images in front of the field of view of the AR glasses and perform face recognition on the people in the scene, and interact with the wearer wearing the AR glasses.

[0054] The execution subject of the AR glasses test method provided in the application can be an electronic device, a component in the electronic device, an integrated circuit, or a chip. The electronic device can be a mobile electronic device or a non-mobile electronic device. Exemplarily, the mobile electronic device can be a mobile phone, a tablet computer, a notebook computer, a palm computer, an ultra-mobile personal computer (UMPC), a netbook, or a personal digital assistant (PDA), and the non-mobile electronic device can be a server, a network attached storage (NAS), or a personal computer (PC), which are not limited in the application.

[0055] The technical solutions of the application are described in detail below with the computer executing the AR glasses test method provided in the application as an example.

[0056] Specifically, in step 110, the artificial test parameters are collected, including collecting data of the face recognition function at different preset points in the target area in various preset postures.

[0057] The user wearing the AR glasses can be located at different preset points in the target area. For any one of the preset points, the user wearing the AR glasses can be in various different preset postures at the preset point. The data of the face recognition function of the user wearing the AR glasses in various preset postures at different preset points in the target area is collected. The data of the face recognition function is the data of the face recognition function of the AR glasses tested by the user wearing the AR glasses at the preset point in the preset posture.

[0058] Optionally, the various preset postures can be quantitatively processed. The user wearing the AR glasses is determined to be in one of the various postures, the three-degree-of-freedom data of the head of the user wearing the AR glasses in the current posture is obtained, and the three-degree-of-freedom data of the head of the user wearing the AR glasses in the current posture is taken as the posture data of the AR glasses to be tested subsequently.

[0059] In step 120, after the data of the face recognition function in various postures at different preset points in the target area is obtained, the postures required to be tested at different preset points are determined based on the collected data, and the determined postures required to be tested at different preset points are taken as the postures when the AR glasses to be tested are tested subsequently.

[0060] The data of the face recognition function at different preset poses at different preset points in the target area may not be able to complete the test of the face recognition function at all preset poses. For example, at a preset point, the face sample is displayed on the left front side, and the current pose is a preset pose of looking right, which may cause the current displayed face to be unable to be recognized. Therefore, after obtaining the data of the face recognition function at different preset poses at different preset points in the target area, the obtained data can be screened to screen out poses that can be successfully used for face recognition test as poses that need to be tested at different preset points.

[0061] In step 130, a simulated manual test environment is simulated, and the face recognition function of the to-be-tested AR glasses is tested in the simulated manual test environment; the simulated manual test environment includes: placing the to-be-tested AR glasses at the intersection of a cross track, controlling the parallel movement of the two tracks of the cross track to move the to-be-tested AR glasses at the intersection of the cross track to different preset points of a target area, at each different preset point, controlling the ambient light to reach different light conditions, and completing the face recognition function test at the pose to be tested at each light condition

[0062] In the simulated manual test environment, the to-be-tested AR glasses are controlled to move to different preset points of a target area. The preset points can be any position in the target area, and the test process at any position in the target area can be realized.

[0063] During the face recognition process of the to-be-tested AR glasses, the angle of the face image in front of the target area is different when the to-be-tested AR glasses are at different positions in the target area. Therefore, based on different positions in the target area, multiple angles can be simulated to simulate the influence of different angles on the test results when the user wears the glasses at different positions.

[0064] During the face recognition function test of the to-be-tested AR glasses, the to-be-tested AR glasses can be controlled to recognize a preset face image in front of the target area. The preset face image can be selected from an image set composed of face images of multiple different people. For the face image of each person, multiple face images of the person can be composed. During the test of the face recognition function of the to-be-tested AR glasses, the recognition accuracy of multiple face recognition images can be tested, which can improve the accuracy of the test.

[0065] During the face recognition function test of the to-be-tested AR glasses, the light of the test environment is controlled to reach different light conditions. Because the to-be-tested AR glasses are used in actual use, different ambient light will affect the use of the to-be-tested AR glasses. Therefore, based on the light adjusting module, the specific use environment of the to-be-tested AR glasses is simulated, and the to-be-tested AR glasses are tested based on different environmental conditions, which can better achieve the test effect.

[0066] Optionally, the adjustment of the light of the AR glasses test environment to be tested can be realized based on a plurality of electrodeless lamps arranged in the test environment. By adjusting the brightness of the plurality of electrodeless lamps, a plurality of environment light simulations such as overcast environment, indoor lighting environment, shopping mall lighting environment, dark summer environment, sunny summer environment, and rainy environment can be realized.

[0067] The posture of the AR glasses to be tested is controlled to be in a preset posture. In the scenario that a real user wears the AR glasses to be tested, when the user moves, the head posture will change. At this time, the posture of the AR glasses to be tested will also change, and the posture of the camera device for face recognition in the AR glasses to be tested will also change, so the face recognition effect of the AR glasses to be tested will be inevitably affected.

[0068] Generally, when wearing AR glasses, the change of the head is a three-degree-of-freedom change. The posture of the AR glasses to be tested can be fixed in a three-degree-of-freedom holder, and the posture of the need to be tested obtained from the collected data can be more comprehensive and closer to the actual situation, so that the face recognition function of the AR glasses to be tested can be tested.

[0069] The AR glasses test method provided in the embodiment of the application can accurately copy the test position, test light condition, and test posture in the test environment during the face recognition function test of the AR glasses, accurately simulate the artificial test environment, and automatically test the face recognition function of the AR glasses. In the test process, the AR glasses can be in the simulated artificial test environment, and the accuracy of the face recognition function test of the AR glasses is improved.

[0070] In one embodiment, the data of the face recognition function of different preset postures at different preset points in a target area is collected, including: obtaining posture data of a plurality of people wearing AR glasses at different preset points in a target area in various preset postures; and determining the posture to be tested at different preset points based on the collected data, including: taking the average value of the posture data of the plurality of people at each different preset point in the same preset posture as the posture to be tested of the AR glasses to be tested at each different preset point in the preset posture; or, based on a clustering algorithm, clustering analysis is performed on the posture data of the plurality of people wearing AR glasses at different preset points in a target area in various preset postures, and the cluster center of the posture data of each different preset point in various preset postures obtained in the clustering analysis is taken as the posture to be tested of the AR glasses to be tested at the preset point in the preset posture.

[0071] In the process of collecting the data of the face recognition function at different preset points in the target area, a plurality of testers can be selected, each of whom wears AR glasses and performs face recognition at different preset points in different preset postures, so as to obtain the posture data of a plurality of testers wearing AR glasses at different preset points in the target area in various preset postures. That is, for each preset point and each preset posture, a plurality of data obtained after a plurality of testers wear AR glasses can be obtained.

[0072] In an embodiment, after obtaining the posture data of a plurality of testers wearing AR glasses at each different preset point in the same preset posture, the average value of the posture data of a plurality of testers wearing AR glasses at each different preset point in the same preset posture is calculated, and the obtained average value is used as the posture to be tested for the AR glasses to be tested at each different preset point in the preset posture.

[0073] It can be understood that the posture data of different people wearing AR glasses is different. For example, for the posture of looking left while wearing AR glasses, the angle of left turning will be different when different people look left while wearing AR glasses, which will result in different left-looking posture data of different people. Therefore, when obtaining the posture to be tested for the AR glasses to be tested to look left in the preset posture, the average value of the posture data of a plurality of people wearing AR glasses to look left can be determined.

[0074] Using the average value of the posture data of a plurality of people wearing AR glasses at each different preset point in the same preset posture as the posture to be tested for the AR glasses to be tested at each different preset point in the preset posture can reduce the error caused by different postures of different people, so that the finally determined posture is more accurate.

[0075] Optionally, when calculating the average value of the data of a plurality of preset postures, the maximum value and the minimum value in the data of a plurality of preset postures can be removed to further reduce the error.

[0076] In another embodiment, when determining the posture to be tested from the obtained data of a plurality of preset postures, the posture to be tested can also be determined based on a clustering algorithm. The clustering algorithm is a statistical analysis method for studying sample classification problems, and is also an important algorithm for data mining. After obtaining the posture data of a plurality of people wearing AR glasses at different preset points in the target area in various preset postures, the posture data at different preset points in various preset postures is analyzed by clustering, and the class center of the posture data at each different preset point in various preset postures obtained in the clustering analysis is used as the posture to be tested for the AR glasses to be tested at the preset point.

[0077] For example, the k-means clustering algorithm is used to cluster and analyze the multiple posture data obtained by multiple people in the same preset posture, and the determined cluster center is used as the posture that the AR glasses in the preset point need to test.

[0078] Optionally, as Figure 2 According to the point position schematic diagram provided by the embodiment of the present application, for a target area of 3m*3m, 25 point positions in the target area can be determined according to a preset interval, and the point positions are sorted in sequence from point position 1 to point position 25. After the point positions are determined, 12 test persons are selected, and the 12 persons wear AR glasses in turn and stand at point position 1, take a preset posture, and perform face recognition on the face image displayed on the panel in front of the center of the target area. 12 posture data of the 12 persons in the preset posture at point position 1 are recorded, and the average value of the 12 posture data after removing the maximum value and the minimum value is calculated, and the calculated average value is used as the posture that needs to be tested for the preset posture at point position 1. In an embodiment, the posture that needs to be tested for the preset posture at point position 1 can also be determined by cluster analysis. For example, the cluster analysis of the 12 posture data can find the cluster center, which can be used as the posture that needs to be tested for the preset posture at point position 1. In an embodiment, five preset postures can be included: a level view posture, a look-up posture, a look-down posture, a left view posture, and a right view posture. The point positions 1 to 25 are traversed in sequence, and the posture data of each preset posture of the 25 point positions are obtained, so as to determine the posture that needs to be tested for each preset posture at different positions.

[0079] The AR glasses testing method provided by the embodiment of the present application realizes accurate acquisition of the preset posture data by acquiring the preset posture of multiple people wearing AR glasses at a preset point position, determining the posture data corresponding to the preset posture, and determining the preset posture data corresponding to the preset posture based on the average value of multiple posture data or cluster analysis of multiple posture data.

[0080] In an embodiment, the determining the posture that needs to be tested at different preset point positions according to the collected data comprises: determining the posture that can be tested for face recognition at different preset point positions in various preset postures from the collected data, and using the posture that can be tested for face recognition at different preset point positions in various preset postures as the posture that needs to be tested at different preset point positions.

[0081] The data of the face recognition function at different preset points in the target area and in various preset postures can show that the face recognition function cannot be tested in all preset postures. For example, the face sample for testing the face recognition function is displayed on the left, and the current preset posture is right view, which can cause the face in the current posture to be unable to be recognized. Therefore, after obtaining the data of the face recognition function at different preset points in the target area and in various preset postures, the obtained data can be screened to screen out preset postures that can be successfully used for face recognition test as postures that need to be tested at different preset points.

[0082] The AR glasses test method provided in the embodiments of the present application screens the obtained data of the face recognition function at different preset points in the target area and in various preset postures to screen out postures that can be successfully used for face recognition test as postures that need to be tested at different preset points, thereby improving the accuracy of subsequent face recognition function test.

[0083] In one embodiment, for the determination of the preset points in the target area, the target area can be divided based on a preset interval. For example, Figure 2 As shown in the point position schematic diagram provided in the embodiments of the present application, after the rectangular target area is equally divided according to the preset interval, a plurality of point positions that are uniformly distributed and have the same interval in the target area can be obtained.

[0084] It can be understood that the point positions that are uniformly distributed in the target area can simulate multiple angles, simulate the influence of different angles on the test results when the user wears glasses in different positions.

[0085] The AR glasses test method provided in the embodiments of the present application divides the target area based on the preset interval to determine the plurality of point positions in the target area, thereby providing a basis for determining the influence of different angles on the test results based on different positions in the subsequent face recognition test of the AR glasses.

[0086] The general head posture can include five kinds of postures, i.e., a level view posture, a look-up posture, a look-down posture, a left view posture, and a right view posture. In one embodiment, the various preset postures include at least one of the level view posture, the look-up posture, the look-down posture, the left view posture, and the right view posture. The determination of the various posture data based on the five head postures can achieve accurate simulation of the head posture.

[0087] Optionally, the change of the head is a three-degree-of-freedom change. Based on the manner in which the AR glasses to be tested are fixed in the three-degree-of-freedom holder, the change of the head in various postures of the user when wearing the glasses can be simulated. In actual testing, the AR glasses to be tested can be fixed on the three-degree-of-freedom holder, and the data of various postures to be tested obtained from various preset postures are input into the three-degree-of-freedom holder, so as to simulate various postures.

[0088] The AR glasses testing method provided in the embodiments of the present application determines at least one of the various preset postures, including the straight-ahead posture, the upward-looking posture, the downward-looking posture, the left-looking posture, and the right-looking posture, so as to accurately simulate various postures to be tested.

[0089] Figure 3 The structure schematic diagram of the AR glasses testing device provided in the embodiments of the present application is shown in FIG. 1. Referring to FIG. 1, Figure 3 The AR glasses testing device provided in the embodiments of the present application includes a cross-rail 301, a three-degree-of-freedom holder 302, a display module 303, AR glasses to be tested 304, a light adjustment module 305, and a testing control module 306.

[0090] The various parts of the AR glasses testing device are described below.

[0091] The cross-rail 301 is used to carry the three-degree-of-freedom holder 302, so as to move the three-degree-of-freedom holder 302 in a target area. In an embodiment, the cross-rail 301 is arranged in the target area and includes two intersecting rails (cross rails), each of which can move in parallel. For example, Figure 4 As shown in the holder moving range schematic diagram provided in the embodiments of the present application, the three-degree-of-freedom holder 302 is located at the intersection of the two rails. When one rail moves, the three-degree-of-freedom holder 302 can move along the other rail. The two rails move in cooperation to carry the three-degree-of-freedom holder 302 to move to any position in the X direction and the Y direction of the target area.

[0092] The three-degree-of-freedom holder 302 is used to simulate various postures.

[0093] The three-degree-of-freedom holder 302 is a 3DOF (Degree Of Free) holder, which includes three degrees of freedom of position. The 3DOF holder can simulate the free rotation of the head in different directions. Therefore, based on the three-degree-of-freedom holder 302, the rotation of the head after the user wears the glasses can be simulated.

[0094] The artificial testing parameters are collected to determine the postures to be tested at different preset points. The collection process of the artificial testing parameters is shown in FIG. 3. Figure 5 As shown in the process schematic diagram of the collection of the artificial testing parameters provided in the embodiments of the present application, the process includes:

[0095] Step 510, write a test APP, collect posture data information in a posture in a specified time period;

[0096] Step 520, find a preset number (N) of test personnel, according to the distribution of the collection points in the target area, wear AR glasses, and stand in each point in the target area in turn, and use AR glasses to look at the display module (carousel face) in each preset posture, so that the camera of the AR glasses worn by the test personnel can collect face information;

[0097] Step 530, when the test APP detects that the face in the display module can be recognized, record the posture and track position at this moment; in the above manner, each person at each point performs pitching, left and right deflection in turn, and then collects the posture and track position at each moment;

[0098] Step 540, collect and integrate all point positions and postures of the target area collected;

[0099] Step 550, find the optimal posture corresponding to the posture data at each point and each preset posture. Among them, the data of N test personnel at 1 point in five preset postures of looking straight, looking up, looking down, looking left and looking right will have N data for each preset posture. Take the average (or cluster center) of these N data (remove the maximum and minimum), and set the five average values (or five cluster centers) of position one as the five postures to be tested corresponding to the five preset postures at position one (for example, at 1 point, the preset posture is left view, and the posture to be tested obtained by the average value or cluster analysis may be a left twist of 15 degrees) ;

[0100] Step 560, traverse each collection point in the target area in turn, and record the posture to be tested at each preset posture according to step 540.

[0101] After obtaining the posture to be tested at different preset points and different preset postures, input the posture data corresponding to the posture to be tested at different preset points and different preset postures into the three-degree-of-freedom holder 302, drive the three-degree-of-freedom holder 302 to reach the angle corresponding to the posture data, and can realize the simulation process of the head movement of the AR glasses wearer in the real scene when the head moves.

[0102] Among them, different preset postures can include looking straight, looking up, looking down, looking left and looking right, etc.

[0103] The display module 303 is fixed in front of the target area and is used to display a face image.

[0104] When the target area is a rectangle, the display module 303 is located in front of the target area, and the center of the display module and the center of the target area are on a straight line.

[0105] The display module 303 is used to display a face image, and provides an image for face recognition for the to-be-tested AR glasses 304.

[0106] Optionally, an image set of face images of multiple persons can be used in the display module 303. Each person can have multiple face images. When the to-be-tested AR glasses 304 are tested, the display module 303 can adjust the face images displayed in the display module 303 according to the needs of the test.

[0107] The to-be-tested AR glasses 304 are fixed on the three-degree-of-freedom holder 302, and follow the changes of the posture of the three-degree-of-freedom holder 302, and are used for face recognition of the face images of the display module 303.

[0108] Based on fixing the to-be-tested AR glasses 304 on the three-degree-of-freedom holder 302, the to-be-tested AR glasses 304 can follow the changes of the posture of the three-degree-of-freedom holder 302, so that the to-be-tested AR glasses 304 simulate the influence of head movement on the posture of the glasses when a user wears the glasses in a real situation.

[0109] It can be understood that in the scenario that a real user wears the to-be-tested AR glasses 304, when the user moves, the head posture will change. At this time, the posture of the to-be-tested AR glasses 304 will also change, and the posture of the camera device in the to-be-tested AR glasses 304 for face recognition will also change, so it will inevitably affect the face recognition effect of the to-be-tested AR glasses 304. Based on the way of fixing the to-be-tested AR glasses 304 in the three-degree-of-freedom holder, the changes of various postures of the head when a user wears glasses are simulated, which can more comprehensively and practically test the face recognition function of the to-be-tested AR glasses 304.

[0110] The light adjusting module 305 is used to control the changes of the light of the test environment.

[0111] Since different environmental light will affect the use of the to-be-tested AR glasses 304 in the actual use process of the to-be-tested AR glasses 304. Therefore, based on the light adjusting module 305, the specific use environment of the to-be-tested AR glasses 304 is simulated, and the to-be-tested AR glasses 304 is tested under different environmental conditions, which can better achieve the test effect.

[0112] Optionally, the light adjustment module 305 can be implemented based on a plurality of electrodeless lamps arranged around the test environment. By adjusting the brightness of the plurality of electrodeless lamps, the simulation of various environmental light conditions such as overcast environment, indoor lighting environment, shopping mall lighting environment, dark summer environment, sunny summer environment, and rainy environment in the test area can be achieved.

[0113] The test control module 306 is used to simulate a test environment to test the face recognition function of the AR glasses 304. The simulation test environment includes: placing the AR glasses 304 to be tested at the intersection of the cross rail 301, controlling the parallel movement of the two rails of the cross rail 301 to move the AR glasses to be tested at the intersection of the cross rail to different preset points in the target area, and at each different preset point, controlling the light adjustment module 305 to make the environmental light reach different light conditions, and completing the face recognition function test in the posture required by the test at each light condition.

[0114] Specifically, the test control module 306 controls the rail 301 to move the three-degree-of-freedom holder 302 to the preset point in the target area. The preset point can be any position in the target area, and the test process at any position in the target area can be realized.

[0115] The test control module 306 controls the display module 303 to display a preset face image. The preset face image can be any face image in the face image data set, and the face recognition test of multiple different face images can be realized.

[0116] The test control module 306 controls the light adjustment module 305 to reach a preset light mode. The preset light mode can be the light of various environments such as overcast environment, indoor lighting environment, shopping mall lighting environment, dark summer environment, sunny summer environment, and rainy environment.

[0117] The test control module 306 controls the three-degree-of-freedom holder 302 to simulate various postures. The various preset postures include: a straight-ahead posture, a look-up posture, a look-down posture, a left-view posture, and a right-view posture.

[0118] After the simulation test environment is completed, the test control module 306 controls the AR glasses 304 to be tested to test the face recognition function.

[0119] For each module in the test environment, a corresponding test environment can be formed by any combination. For example, in the track 301, when the three-degree-of-freedom holder 302 is moved to the center of the target area, a plurality of test environments are formed by combining the test environment for all postures of the three-degree-of-freedom holder 302, the test environment for all light modes of the light adjusting module 305, and the test environment for all face images displayed by the display module 303, and the test environment for all face images displayed by the display module 303. Based on the plurality of test environments obtained, the face recognition test of the to-be-tested AR glasses 304 is performed respectively. After the test in the center of the target area is completed, the test can be moved to other positions of the target area.

[0120] In the face recognition test of the to-be-tested AR glasses 304, the automatic test can be performed based on the collected data. The flow of the automatic test is as follows Figure 6 The flow of the automatic test of the AR glasses provided by the embodiment of the present application is shown in the flowchart, and the flow includes the following steps.

[0121] In step 610, the darkroom is kept, and the to-be-tested AR glasses 304 are placed on the three-degree-of-freedom holder 302 through the clamp.

[0122] In step 620, the three-degree-of-freedom holder 302 is placed at the maximum X direction of the cross track 301 (close to the display module 303), and the to-be-tested AR glasses 304 are powered on and started.

[0123] In step 630, the display module 303 is placed at a preset position in the X direction of the three-degree-of-freedom holder 302, the display module 303 is set to be always on and to be the minimum brightness, and the height of the display module 303 is consistent with that of the to-be-tested AR glasses 304.

[0124] In step 640, the test control module 306 is connected to the three-degree-of-freedom holder 302, the cross track 301, the light adjusting module 305, the display module 303, and the to-be-tested AR glasses 304, and controls each module respectively.

[0125] In step 650, the automatic test flow is programmed and controlled, and the test control module 306 controls the to-be-tested AR glasses 304 to open the APP face recognition interface.

[0126] In step 660, the test control module 306 controls the three-degree-of-freedom holder 302 to perform face recognition at each angle (including pitch, left and right, and level view), and records the recognition conclusion in a table.

[0127] In step 670, the test control module 306 controls the display module 303 to gradually increase the brightness (100-600 nit, interval 50 nit), and performs face recognition in a cycle, and records the data at ten levels. (The last brightness is adjusted to the minimum.)

[0128] Step 680, the test control module 306 controls the light adjustment module 305 to achieve a plurality of different light conditions, and the face recognition is performed in a loop, and the data under a plurality of light conditions is recorded;

[0129] Step 690, the test control module 306 finally performs face recognition from each position on the track in a loop, and the steps of steps 650 to 680 are cycled, and finally the conclusion is recorded.

[0130] The AR glasses test device provided in the embodiment of the application realizes accurate simulation of the artificial test environment and automatic testing of the face recognition function of the AR glasses by accurately copying the test position, test light condition and test posture in the test environment during the face recognition function test of the AR glasses. The AR glasses can be in the simulated artificial test environment during the test process, and the accuracy of the face recognition function test of the AR glasses is improved.

[0131] In one embodiment, the test control module is further configured to control the display module to display at a preset display brightness.

[0132] When the display module displays the face image, the display brightness of the display module will affect the face recognition of the to-be-tested AR glasses, and therefore, the display brightness of the display module can be controlled to test the influence of different display brightnesses of the display module on the face recognition function of the to-be-tested AR glasses.

[0133] Optionally, when the display module is a tablet, the display brightness of the tablet can be controlled to be gradually increased or decreased, the range of the display brightness can be 100-600 nit, and the adjustment interval can be 50 nit.

[0134] The AR glasses test device provided in the embodiment of the application controls the display module to display at a preset display brightness, and the influence of different display brightnesses of the display module on the face recognition function of the AR glasses is determined.

[0135] Figure 7 The logical structure diagram of the AR glasses test system provided in the embodiment of the application is shown in FIG. 7. Referring to FIG. 7, Figure 7 The AR glasses test system 700 provided in the embodiment of the application includes:

[0136] The acquisition module 710 is configured to acquire artificial test parameters, including:

[0137] acquiring data of face recognition function at different preset points in the target area in various preset postures;

[0138] The posture determination module 720 is configured to determine the postures required to be tested at different preset points according to the acquired data.

[0139] a test module 730, configured to simulate an artificial test environment, and test a face recognition function of the AR glasses under the simulated artificial test environment;

[0140] The simulated artificial test environment comprises: placing the AR glasses to be tested at a cross point of a cross track, and controlling two tracks of the cross track to move respectively and in parallel to move the AR glasses to be tested at the cross point of the cross track to different preset point positions in a target area,

[0141] At each different preset point position, the ambient light is controlled to reach different light conditions, and the face recognition function test of the AR glasses in a posture required by the preset point position is completed under each light condition.

[0142] The AR glasses test system provided in the embodiments of the present application can accurately copy the test position, test light condition and test posture in the test environment during the face recognition function test of the AR glasses, accurately simulate the artificial test environment, and automatically test the face recognition function of the AR glasses. Therefore, the AR glasses can be in the simulated artificial test environment during the test, and the accuracy of the face recognition function test of the AR glasses is improved.

[0143] In one embodiment, the collection module 710 is specifically configured to:

[0144] collect data of the face recognition function in various postures at different preset point positions in the target area, comprising:

[0145] obtaining posture data of a plurality of users wearing AR glasses in various preset postures at different preset point positions in the target area;

[0146] determining the postures required for testing at different preset point positions according to the collected data, comprising:

[0147] taking an average value of the posture data of the plurality of users in each different preset point position and in a same preset posture as the posture required for testing of the AR glasses to be tested in each different preset point position and in the preset posture;

[0148] Or,

[0149] performing clustering analysis on the posture data of the plurality of users wearing AR glasses in various preset postures at different preset point positions in the target area based on a clustering algorithm, and taking a cluster center of the posture data in each different preset point position and in each preset posture obtained in the clustering analysis as the posture required for testing of the AR glasses to be tested in the preset point position.

[0150] In one embodiment, the posture determination module 720 is specifically configured to:

[0151] The step of determining the postures to be tested at different preset points based on the collected data includes:

[0152] The poses that can be used for face recognition testing at different preset locations are determined from the collected data, and these poses are used as the poses that need to be tested at different preset locations.

[0153] In one embodiment, the test module 730 is specifically used for:

[0154] The preset point is any one of multiple points;

[0155] The multiple points are determined by dividing the target area based on preset intervals.

[0156] In one embodiment, the test module 730 is further specifically used for:

[0157] Various preset postures include at least one of the following: eye-level posture, upward posture, downward posture, left-viewing posture, and right-viewing posture.

[0158] This application also provides an electronic device, such as... Figure 8 As shown, the electronic device may include: a processor 810, a communication interface 820, a memory 830, and a communication bus 840, wherein the processor 810, the communication interface 820, and the memory 830 communicate with each other via the communication bus 840. The processor 810 can call logical instructions in the memory 830 to execute AR glasses testing methods, such as:

[0159] Collect manually tested parameters, including:

[0160] Collect data on facial recognition at different preset locations within the target area under various preset postures;

[0161] Based on the collected data, determine the postures that need to be tested at different preset points;

[0162] Simulate a human testing environment to test the face recognition function of the AR glasses under test in a simulated human testing environment;

[0163] The simulated artificial testing environment includes: placing the AR glasses under test at the intersection of two intersecting tracks, and controlling the two tracks of the intersecting tracks to move parallel to each other, causing the AR glasses under test located at the intersection of the intersecting tracks to move to different preset points in the target area.

[0164] At each different preset point, the ambient light is controlled to reach different light conditions, and the face recognition function test is completed at each light condition and in the posture required for testing at the preset point.

[0165] In addition, the logical instructions in the memory 830 described above can be implemented in the form of a software function unit and sold or used as a separate product, and can be stored in a computer-readable storage medium. Based on this understanding, the technical solutions of the present application essentially or the part that contributes to the prior art or part of the technical solutions can be embodied in the form of a software product, which is stored in a storage medium and includes a number of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk or an optical disk, and various media that can store program codes.

[0166] On the other hand, the present application also provides a computer program product, which includes a computer program stored on a non-transitory computer-readable storage medium, and the computer program includes program instructions, when the program instructions are executed by a computer, the computer can execute the AR glasses test method provided by the above-mentioned method embodiments, for example, including:

[0167] Collecting artificial test parameters, including:

[0168] Collecting data of face recognition function in various preset postures at different preset points in the target area;

[0169] According to the collected data, determining the postures required for testing at different preset points;

[0170] Simulating an artificial test environment, and testing the face recognition function of the AR glasses to be tested in the simulated artificial test environment;

[0171] The simulated artificial test environment includes: placing the AR glasses to be tested at the intersection of a cross track, and controlling the parallel movement of the two tracks of the cross track to move the AR glasses to be tested at the intersection of the cross track to different preset points in the target area,

[0172] At each different preset point, the ambient light is controlled to reach different light conditions, and the face recognition function test is completed at each light condition and in the posture required for testing at the preset point.

[0173] In yet another aspect, the present application also provides a non-transitory computer readable storage medium having stored thereon a computer program, which, when executed by a processor, implements the AR glasses testing method provided by any of the above method embodiments, for example comprising:

[0174] Collecting artificial testing parameters, including:

[0175] Collecting data of the face recognition function at various preset poses at different preset point positions in the target area;

[0176] According to the collected data, determining the poses that need to be tested at different preset point positions;

[0177] Simulating an artificial testing environment, and testing the face recognition function of the AR glasses to be tested in the simulated artificial testing environment;

[0178] The simulated artificial testing environment includes: placing the AR glasses to be tested at the intersection of a cross-rail, and controlling the two rails of the cross-rail to move respectively in parallel to move the AR glasses to be tested at the intersection of the cross-rail to different preset point positions in the target area,

[0179] At each different preset point position, control the ambient light to reach different light conditions, and complete the face recognition function test at the poses that need to be tested at each light condition.

[0180] The device embodiments described above are only schematic, wherein the units shown as separate components can or can not be physically separate, and the components shown as units can or can not be physical units, i.e., can be located in one place, or can be distributed on multiple network units. Part or all of the modules can be selected according to actual needs to achieve the purpose of the present embodiment. Those skilled in the art can understand and implement without creative labor.

[0181] From the above description of the embodiments, those skilled in the art can clearly understand that the embodiments can be realized by means of software plus the necessary general hardware platforms, and of course can also be realized by hardware. Based on such understanding, the above technical solutions can be embodied in the form of software products, which can be stored in a computer readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and include a number of instructions to make a computer device (which can be a personal computer, a server, or a network device, etc.) execute the methods described in each embodiment or some parts of the embodiments.

[0182] Finally, it should be noted that the above examples are only used to illustrate the technical solutions of the present application, and are not intended to limit the same; although the present application has been described in detail with reference to the foregoing examples, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing examples, or make equivalent replacements for some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. An AR glasses test method, characterized by, The method comprises the following steps: Collecting artificial test parameters, comprising: Collecting data of face recognition function of different preset poses at different preset points in the target area; According to the collected data, determine the poses that need to be tested at different preset points; Simulate the artificial test environment, test the face recognition function of the AR glasses under test in the simulated artificial test environment; The simulated artificial test environment comprises: placing the AR glasses under test at the intersection of a cross-rail, controlling the parallel movement of the two rails of the cross-rail to make the AR glasses under test at the intersection of the cross-rail move to different preset points in the target area, At each different preset point, control the ambient light to reach different light conditions, and complete the face recognition function test at the preset pose that needs to be tested at each light condition; The collected data of face recognition function of different preset poses at different preset points in the target area comprises: obtaining the pose data of multiple people wearing AR glasses at different preset points in the target area in different preset poses; The determination of the poses that need to be tested at different preset points based on the collected data comprises: based on a clustering algorithm, clustering analysis is performed on the pose data of multiple people wearing AR glasses at different preset points in the target area in different preset poses, and the cluster center of the pose data of each different preset pose obtained in the clustering analysis is taken as the pose that needs to be tested at the preset point in the preset pose of the AR glasses under test.

2. The AR glasses testing method of claim 1, wherein, The determination of the poses that need to be tested at different preset points based on the collected data comprises: Determine the poses that can be tested for face recognition at different preset poses at different preset points from the collected data, and take the poses that can be tested for face recognition at different preset poses at different preset points as the poses that need to be tested at different preset points.

3. The AR glasses testing method of claim 1, wherein, The different preset points are determined based on a preset interval after the target area is divided.

4. The AR glasses testing method of any one of claims 1-3, wherein, The different preset poses include at least one of the following: looking straight, looking up, looking down, looking left, and looking right.

5. An AR glasses testing apparatus, characterized by, The method comprises the following steps: Cross-rail, three-degree-of-freedom holder, display module, light adjustment module, and test control module; The cross-rail is used to carry the three-degree-of-freedom holder to move the three-degree-of-freedom holder in the target area; The three-degree-of-freedom holder is used to simulate various poses; The display module is fixed in front of the target area and is used to display a face image; The light adjustment module is used to control the change of ambient light in the test environment; The test control module is used to simulate the test environment and test the face recognition function of the AR glasses under test, and the simulated test environment comprises: Placing the AR glasses under test at the intersection of a cross-rail, controlling the parallel movement of the two rails of the cross-rail to make the AR glasses under test at the intersection of the cross-rail move to different preset points in the target area, At each different preset point, control the light adjustment module to make the ambient light reach different light conditions, and complete the face recognition function test at the preset pose that needs to be tested at each light condition; The determination process of the various poses comprises: The cluster algorithm is used to cluster and analyze the posture data of the AR glasses worn by multiple people at different preset points and in different preset postures in the target area, and the cluster center of the posture data of each different preset point and in each different preset posture obtained in the cluster analysis is used as the posture to be tested of the AR glasses to be tested at the preset point in the preset posture.

6. The AR glasses testing device of claim 5, wherein, The test control module is further configured to: control the display module to display at a preset display brightness.

7. An AR glasses testing apparatus, characterized by, comprises: The acquisition module is configured to acquire artificial test parameters, including: acquiring data of a face recognition function at different preset points and in different preset postures in the target area; The posture determination module is configured to determine the posture to be tested at each different preset point based on the acquired data. The test module is configured to simulate an artificial test environment and test the face recognition function of the AR glasses to be tested in the simulated artificial test environment. The simulated artificial test environment comprises: placing the AR glasses to be tested at an intersection of a cross track, and controlling the two tracks of the cross track to move parallel to each other to move the AR glasses to be tested at the intersection of the cross track to different preset points in the target area, controlling the ambient light to reach different light conditions at each different preset point, and completing the face recognition function test at the posture to be tested at each preset point under each light condition. The acquisition module is configured to acquire artificial test parameters, including: acquiring data of a face recognition function at different preset points and in different preset postures in the target area; 8. An electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, The posture determination module is configured to determine the posture to be tested at each different preset point based on the acquired data. 9.A non-transitory computer-readable storage medium having stored thereon a computer program, characterized in that, The test module is configured to simulate an artificial test environment and test the face recognition function of the AR glasses to be tested in the simulated artificial test environment.

10. A computer program product comprising a computer program, characterized in that, The simulated artificial test environment comprises: placing the AR glasses to be tested at an intersection of a cross track, and controlling the two tracks of the cross track to move parallel to each other to move the AR glasses to be tested at the intersection of the cross track to different preset points in the target area, controlling the ambient light to reach different light conditions at each different preset point, and completing the face recognition function test at the posture to be tested at each preset point under each light condition. The acquisition module is configured to acquire artificial test parameters, including: acquiring data of a face recognition function at different preset points and in different preset postures in the target area; The posture determination module is configured to determine the posture to be tested at each different preset point based on the acquired data. The processor executes the computer program to implement the AR glasses test method of any one of claims 1-4. The computer program is executed by the processor to implement the AR glasses test method of any one of claims 1-4. The computer program is executed by the processor to implement the AR glasses test method of any one of claims 1-4.

Images