Automatic eye movement tracking evaluation method, device and system and storage medium

Abstract

The invention relates to an automatic eye movement tracking evaluation method, device and system and a storage medium, and the system comprises a human eye simulation model connected with a motion control module, and the human eye simulation model watches a preset fixation point in to-be-tested equipment for testing under the control of the motion control module; the method comprises the following steps: determining fixation position point information of a human eye simulation model in a test process and detection position point information in equipment to be tested; and determining the eye movement tracking accuracy of the to-be-detected device based on the gazing position point information and the corresponding detection position point information. Through the method and the device, the eye movement tracking accuracy is determined according to the watching position point information and the detection position point information of the human eye simulation model in the testing process, the actual effect of eye movement tracking can be evaluated, the influence of limitation of a user sample is avoided, and the problem that the effect of eye movement tracking cannot be effectively evaluated is solved.

Description

Technical Field

[0001] The present application relates to the field of eye movement tracking technology, and particularly to an automated eye movement tracking evaluation method, device, system, and storage medium. Background Art

[0002] Eye movement tracking, as a new type of interaction technology, has been widely applied. For example, in the field of XR (Extended Reality), the human-computer interaction implemented by eye movement tracking has become one of the interaction methods adopted by many products in the market. It mainly judges the direction aimed at by the user's vision according to the gaze direction of the user's eyes, etc., and then realizes corresponding interaction actions.

[0003] As an important interaction implementation method, the accuracy of eye movement tracking, the spatial angle resolution, etc. of eye movement tracking technology will directly affect whether correct or even precise interaction actions can be realized. On the other hand, for XR manufacturers equipped with eye movement tracking technology, generally a large number of user samples are required to internally calibrate and verify the output position results of their own eye movement modules before leaving the factory, which is easily affected by the limitations of user samples. Therefore, although there are various eye movement tracking technologies currently, there is no corresponding effective evaluation scheme for the actual effect of eye movement tracking.

[0004] In view of the problem in the related art that the effect of eye movement tracking cannot be effectively evaluated, no effective solution has been proposed yet. Summary of the Invention

[0005] Based on this, it is necessary to provide an automated eye movement tracking evaluation method, device, system, and storage medium that can effectively evaluate the effect of eye movement tracking for the above technical problems.

[0006] In a first aspect, an automated eye movement tracking evaluation method is provided in this embodiment, which is applied to an automated eye movement tracking evaluation system. The system includes: a humanoid eye model connected to a motion control module. The humanoid eye model, under the control of the motion control module, gazes at a preset gaze point in the device under test for testing. The method includes:

[0007] Determine the gaze position point information of the humanoid eye model during the test, and the detection position point information in the device under test;

[0008] Based on the gaze position point information and the corresponding detection position point information, determine the eye movement tracking accuracy of the device under test.

[0009] In some of these embodiments, the determining the eye movement tracking accuracy of the device under test based on the gaze position point information and the corresponding detection position point information includes:

[0010] Based on the field of view range of the device under test, one or more sub-field-of-view test areas are divided;

[0011] According to the fixation position point information and the detection position point information corresponding to the preset fixation point in each of the sub-field-of-view test areas, the eye movement tracking accuracy of each of the field-of-view test areas is determined;

[0012] Based on the eye movement tracking accuracy of each of the sub-field-of-view test areas, the eye movement tracking accuracy of the device under test is calculated by weighted calculation.

[0013] In some embodiments, determining the fixation position point information of the humanoid eye model and the detection position point information in the device under test during the test process includes:

[0014] According to the spatial position of the preset fixation point, controlling the humanoid eye model to fixate on the preset fixation point for testing;

[0015] According to the movement data and spatial position of the humanoid eye model during the test process, the fixation position point information is determined;

[0016] The detection position point information is obtained by performing eye movement tracking detection on the humanoid eye model through the device under test.

[0017] In some embodiments, it further includes:

[0018] According to the image information of the preset fixation point in the device under test, the spatial position of the preset fixation point is determined.

[0019] In some embodiments, it further includes:

[0020] Controlling the humanoid eye model to perform a step-by-step movement at a preset angle, and synchronously obtaining the detection position point information of the humanoid eye model;

[0021] When the detection position point information meets the preset conditions, the fixation position point information of the humanoid eye model is obtained, and based on the fixation point position information, the eye movement tracking spatial resolution of the device under test is determined.

[0022] In some embodiments, the step of when the detection position point information meets the preset conditions, obtaining the fixation position point information of the humanoid eye model, and based on the fixation point position information, determining the eye movement tracking spatial resolution of the device under test includes:

[0023] Comparing the detection position point information for each movement until the detection position point information is different from the detection position point information in the previous movement, and then obtaining the current fixation position point information of the humanoid eye model;

[0024] By comparing the current fixation position point information with the initial fixation position point information before the stepwise movement, the eye movement tracking spatial resolution of the device under test is determined.

[0025] In a second aspect, an automated eye movement tracking evaluation device is provided in this embodiment, which is applied to an automated eye movement tracking evaluation system. The system includes: a humanoid eye model connected to a motion control module. The humanoid eye model, under the control of the motion control module, fixates on a preset fixation point in the device under test for testing. The device includes: a position point information determination module and an eye movement tracking evaluation module;

[0026] The position point information determination module is configured to determine the fixation position point information of the humanoid eye model during the test, as well as the detection position point information in the device under test;

[0027] The eye movement tracking evaluation module is configured to determine the eye movement tracking accuracy of the device under test based on the fixation position point information and the corresponding detection position point information.

[0028] In a third aspect, an automated eye movement tracking evaluation system is provided in this embodiment, including: a humanoid eye model, a motion control module, and a data processor;

[0029] The motion control module is connected to the humanoid eye model and is configured to control the humanoid eye model to fixate on a preset fixation point in the device under test for testing;

[0030] The data processor is connected to the motion control module and is configured to execute the automated eye movement tracking evaluation method described in the first aspect above.

[0031] In some of the embodiments, when the device under test is an eye movement tracking module, the humanoid eye model includes a sphere, an iris simulator, and a pupil located at the center of the iris simulator.

[0032] In some of the embodiments, when the device under test is a display device integrated with an eye movement tracking module, the humanoid eye model is a humanoid eye camera or an event camera.

[0033] In a fourth aspect, a storage medium is provided in this embodiment, on which a computer program is stored. When the program is executed by a processor, it implements the automated eye movement tracking evaluation method described in the first aspect above.

[0034] Compared with the related technologies, in the automated eye movement tracking evaluation method, device, system, and storage medium provided in this embodiment, the system includes: a humanoid eye model connected to a motion control module. The humanoid eye model is controlled by the motion control module to fixate on a preset fixation point in the device under test for testing. The method includes determining the fixation position point information of the humanoid eye model during the test, as well as the detection position point information in the device under test. Based on the fixation position point information and the corresponding detection position point information, the eye movement tracking accuracy of the device under test is determined. This application uses a system including a humanoid eye model and a motion control module for testing, and determines the eye movement tracking accuracy of the device under test according to the fixation position point information of the humanoid eye model and the corresponding detection position point information during the test, which can evaluate the actual effect of eye movement tracking and is not affected by the limitations of user samples, solving the problem of being unable to effectively evaluate the effect of eye movement tracking.

[0035] Details of one or more embodiments of this application are set forth in the following drawings and description to make other features, objects, and advantages of this application more concise and understandable. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] The drawings described herein are used to provide a further understanding of this application and form a part of this application. The illustrative embodiments and descriptions thereof of this application are used to explain this application and do not constitute an improper limitation of this application. In the drawings:

[0037] Figure 1 is a hardware structure block diagram of a terminal of an automated eye movement tracking evaluation method in an embodiment;

[0038] Figure 2 is a schematic structural diagram of an automated eye movement tracking evaluation system in an embodiment;

[0039] Figures 3a - 3b is a schematic diagram of an artificial eyeball in an embodiment;

[0040] Figure 4 is a schematic diagram of the test installation of a device under test and an automated eye movement tracking evaluation system in an embodiment;

[0041] Figure 5 is a schematic structural diagram of an automated eye movement tracking evaluation system in another embodiment;

[0042] Figure 6 is a flowchart of an automated eye movement tracking evaluation method in an embodiment;

[0043] Figure 7 is a schematic diagram of a field of view division and preset fixation points in an embodiment;

[0044] Figure 8Schematic diagram of a preset angle in a step - by - step motion in an embodiment;

[0045] Figure 9 Flowchart of an automated eye movement tracking evaluation method in another embodiment;

[0046] Figure 10 Block diagram of the structure of an automated eye movement tracking evaluation device in an embodiment.

[0047] In the figure: 102, processor; 104, memory; 106, transmission device; 108, input / output device; 10, position point information determination module; 20, eye movement tracking evaluation module. Detailed implementation manners

[0048] To understand the purpose, technical solution and advantages of the present application more clearly, the present application is described and explained below with reference to the accompanying drawings and embodiments.

[0049] Unless otherwise defined, the technical terms or scientific terms involved in the present application should have the general meaning understood by those with ordinary skills in the technical field to which the present application belongs. In the present application, words such as "a", "one", "a kind of", "the", "these" and the like do not indicate a limitation in quantity, and they can be singular or plural. The terms "including", "comprising", "having" and any variants thereof involved in the present application are intended to cover non - exclusive inclusion; for example, a process, method, system, product or device including a series of steps or modules (units) is not limited to the listed steps or modules (units), but may include unlisted steps or modules (units), or may include other steps or modules (units) inherent in these processes, methods, products or devices. The terms "connected", "coupled" and the like involved in the present application do not limit to physical or mechanical connections, but may include electrical connections, whether directly or indirectly. The term "plurality" involved in the present application refers to two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" may represent: A exists alone, A and B exist simultaneously, and B exists alone. Usually, the character " / " indicates that the objects before and after are in an "or" relationship. The terms "first", "second", "third" and the like involved in the present application are only used to distinguish similar objects and do not represent a specific sorting for the objects.

[0050] The method embodiments provided in this embodiment can be executed on a terminal, a computer or a similar computing device. For example, running on a terminal, Figure 1 is the hardware block diagram of the terminal of the automated eye movement tracking evaluation method in this embodiment. As Figure 1 shown, the terminal may include one or more (Figure 1 Only one processor 102 and a memory 104 for storing data are shown. Among them, the processor 102 may include, but is not limited to, processing devices such as a microprocessor MCU or a field programmable gate array FPGA. The above terminal may further include a transmission device 106 for communication functions and an input / output device 108. Those of ordinary skill in the art can understand that Figure 1 The structure shown is only schematic and does not limit the structure of the above terminal. For example, the terminal may further include more or fewer components than those Figure 1 shown, or have a different configuration from that Figure 1 shown.

[0051] The memory 104 can be used to store computer programs. For example, software programs and modules of application software, such as the computer program corresponding to the automated eye movement tracking evaluation method in this embodiment. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, that is, implements the above method. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memories. In some instances, the memory 104 may further include a memory remotely set relative to the processor 102, and these remote memories can be connected to the terminal through a network. Examples of the above network include, but are not limited to, the Internet, an enterprise intranet, a local area network, a mobile communication network, and combinations thereof.

[0052] The transmission device 106 is used to receive or send data via a network. The above network includes a wireless network provided by the communication provider of the terminal. In one instance, the transmission device 106 includes a network adapter (Network Interface Controller, abbreviated as NIC), which can be connected to other network devices through a base station and thus communicate with the Internet. In one instance, the transmission device 106 may be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0053] Eye movement tracking, as a new type of interaction technology, has been widely used. For example, in the field of display devices such as XR (Extended Reality), the human-computer interaction realized by eye movement tracking has become one of the interaction methods adopted by many products in the market. It mainly judges the direction aimed at by the user's vision according to the gaze direction of the user's eyes, etc., and then realizes the corresponding interaction actions.

[0054] As an important method for realizing interaction, the accuracy of eye movement tracking, the spatial angular resolution, etc. of eye movement tracking will directly affect whether correct or even precise interaction actions can be achieved. On the other hand, for XR manufacturers equipped with eye movement tracking technology, generally a large number of user samples are required to internally calibrate and verify the output position results of their own eye movement modules before leaving the factory, which is easily affected by the limitations of user samples. Therefore, although there are various eye movement tracking technologies at present, there is no corresponding effective evaluation scheme for the actual effect of eye movement tracking.

[0055] In this embodiment, an automated eye movement tracking evaluation system is provided. Figure 2 It is a schematic structural diagram of the automated eye movement tracking evaluation system in this embodiment, as Figure 2 shown, the system includes: a humanoid eye model, a motion control module, and a data processor.

[0056] Among them, the motion control module is connected to the humanoid eye model and is used to control the humanoid eye model to fixate on a preset fixation point in the device under test for testing; the data processor is connected to the motion control module and is used to execute the automated eye movement tracking evaluation method.

[0057] Specifically, the humanoid eye model is used to simulate a real human eye and can specifically simulate different forms of the pupil, iris, and interpupillary distance, such as color, size, and distance. The humanoid eye model realizes three-dimensional motion (in the X-axis - Y-axis - Z-axis directions) and six-dimensional motion (in the X-axis - Y-axis - Z-axis directions and the rotation directions along the X-axis - Y-axis - Z-axis) under the drive and control of the motion control module, and moves to fixate on a preset fixation point in the device under test for testing. Among them, the motion control module can control the motion of each simulated human eye in the humanoid eye model individually or simultaneously.

[0058] It should be noted that the motion control module needs to meet certain motion stability, that is, it has positioning repeatability, can perform accurate positioning reproduction, and can simulate the binocular coordinated motion, speed, acceleration, eye rotation speed, eye fixation, and saccade motion of a real human eye, etc.

[0059] In addition, the motion control module also has a motion detection device, which can specifically be an angle encoder, a displacement encoder, a gyroscope, etc. Through the motion detection device, motion data, spatial position, and interpupillary distance and other information of the humanoid eye model can be obtained.

[0060] The device under test in this embodiment includes a separate eye tracking module and a display device integrated with an eye tracking module, such as XR, AR (Augmented Reality), VR (Virtual Reality), etc. For test applications of different devices under test, the humanoid eye model can be a pair of artificial eyeballs simulating the human eye, or a pair of cameras capable of collecting image information. The shape, color, distribution position, and density of the preset fixation points in the device under test can be set independently during actual operation, or the existing test points in the device under test can be used as the preset fixation points.

[0061] The data processor is used to determine the fixation position point information of the humanoid eye model during the test process, as well as the detection position point information in the device under test; based on the fixation position point information and the corresponding detection position point information, determine the eye movement tracking accuracy of the device under test.

[0062] Among them, the data processor is connected to the motion control module, and determines the fixation position point information of the humanoid eye model according to the motion data and spatial position of the humanoid eye model in the motion control module. The fixation position point information represents the position information when the humanoid eye model fixates on the preset fixation point during the test process, and is output by the automated eye movement tracking evaluation system. The detection position information represents the position information when the device under test detects that the humanoid eye model fixates on the preset fixation point through operations such as eye movement tracking of the humanoid eye model during the test process, and is output by the device under test.

[0063] Preset fixation points are distributed in the device under test, and the eye movement tracking accuracy of the entire device under test is determined according to the fixation position point information and the detection position point information corresponding to the preset fixation points.

[0064] Through the system provided in this embodiment, the motion control module is used to control the movement of the humanoid eye model to fixate on the preset fixation point for testing, and the data processor is used to obtain the fixation position point information and the detection position point information of the humanoid eye model during the test process respectively, and evaluate the eye movement tracking accuracy of the device under test, which can evaluate the actual effect of eye movement tracking and is not affected by the limitations of user samples, solving the problem that the effect of eye movement tracking cannot be effectively evaluated.

[0065] In some of these embodiments, when the device under test is an eye tracking module, the humanoid eye model includes a sphere, an iris simulator, and a pupil located at the center of the iris simulator.

[0066] Specifically, the humanoid eye model includes a pair of artificial eyeballs, and the distance between the two artificial eyeballs is adjustable. The sphere also has a sclera simulator for realistically simulating the human eye. The iris simulator includes a switchable filter film for simulating different iris colors, such as gray, black, brown, blue, green, red, or other colors that mimic or are similar to the human eye. Specifically, it can be a matte finish with a slight reflection that mimics the characteristics of the human eye iris. The pupil located at the center of the iris simulator has an adjustable size in the range of 1 mm - 7 mm. Figure 3a and Figure 3b are schematic diagrams of the artificial eyeballs in this embodiment, Figure 3a and Figure 3b schematically show the artificial eyeball with blue characteristics and the artificial eyeball with black characteristics respectively.

[0067] Figure 4 is a schematic diagram of the installation of the device under test and the automated eye movement tracking evaluation system in this embodiment. As Figure 4 shown, when testing a single eye movement tracking module, the device under test and the automated eye movement tracking evaluation system are installed on the test platform. The test platform can be a scale-equipped guide rail. According to the nominal eye box position and size of the device under test, the distance between the device under test and the evaluation system is adjusted. Preferably, the position of the left / right artificial eyeballs of the automated eye movement tracking evaluation system is adjusted to the center position of the eye box of the left / right eye display system of the device under test through a support device.

[0068] Through the humanoid eye model provided in this embodiment, different forms of the pupil, iris, and interpupillary distance of different users can be simulated, such as color, size, and distance. Furthermore, it can be free from the limitations of user samples, making the evaluation system more generally applicable.

[0069] In some of these embodiments, when the device under test is a display device integrated with an eye movement tracking module, the humanoid eye model is a humanoid eye camera or an event camera.

[0070] Specifically, Figure 5 is a schematic diagram of the structure of the automated eye movement tracking evaluation system in this embodiment. As Figure 5 shown, for a display device that has already integrated an eye movement tracking module, the humanoid eye model is a humanoid eye camera or an event camera, and the humanoid eye model is respectively connected to the motion control module and the data processor. Among them, Figure 5 the humanoid eye camera in

[0071] The image information of the test points in the display device can be directly collected through the humanoid eye model. Among them, the test points are used for the display device to internally calibrate and verify the output position results of its own eye movement module before leaving the factory, and can also be used as the preset fixation points of the device under test. The data processor analyzes the image information to determine the spatial position of the preset fixation point, and based on this spatial position, the motion control module controls the humanoid eye model to fixate on the preset fixation point in the device under test for testing.

[0072] It should be noted that using a humanoid eye camera can not only perform automated eye movement tracking evaluation of the device under test, but also evaluate the image quality (such as display performance like clarity and brightness uniformity) and photobiological safety indicators of the device under test. Among them, obtaining the image information of the humanoid eye camera can be achieved by the data processor analyzing the two acquired images.

[0073] In addition, when using an event camera as the humanoid eye model, only when there is a preset fixation point in the device under test, the event camera supplements the event and the image information at that moment, which has the advantage of low power consumption.

[0074] By using a humanoid eye camera or an event camera as the humanoid eye model in this embodiment, the image information of the preset fixation point can be collected through the humanoid eye model, so as to determine the spatial position of the preset fixation point, and control the movement of the humanoid eye model for testing according to the spatial position.

[0075] In this embodiment, an automated eye movement tracking evaluation method is provided, which is applied to the system in the above embodiment. Figure 6 This is the flowchart of the automated eye movement tracking evaluation method of this embodiment, as Figure 6 shown, the method includes the following steps:

[0076] Step S610, determine the fixation position point information of the humanoid eye model during the test process, and the detection position point information in the device under test.

[0077] Specifically, several preset fixation points are set in the field of view area of the device under test. Specifically, the preset fixation points can be set at different preset spatial positions, or the existing test points in the device under test can be used as the preset fixation points. Among them, the shape, color, distribution position, and density of the preset fixation points can be set independently during actual operation, and their shapes include but are not limited to planar figures such as circles, triangles, rectangles, and three-dimensional figures such as spheres, cones, and cubes.

[0078] During the test, the humanoid eye model moves under the control of the motion control module and fixates on a preset fixation point. Through the motion detection device in the motion control module, information such as the motion data, spatial position, and pupil distance of the humanoid eye model is obtained and fed back to the data processor. In the data processor, the fixation position point information of the humanoid eye model when fixating on each preset fixation point during the test is determined.

[0079] The device under test includes a separate eye movement tracking module and a display device integrated with an eye movement tracking module. The device under test is installed on a test platform or worn for testing. Through the device under test, eye movement tracking detection is performed on the movement of the humanoid eye model during the test, and the detected position point information of the humanoid eye model when fixating on each preset fixation point is output. For the test applications of different devices under test, the humanoid eye model can be a pair of artificial eyeballs simulating human eyes or a pair of cameras capable of collecting image information.

[0080] Step S620: Based on the fixation position point information and the corresponding detected position point information, determine the eye movement tracking accuracy of the device under test.

[0081] Specifically, by separately obtaining the fixation position point information and the detected position point information of the humanoid eye model when fixating on each preset fixation point, and according to the position error between the fixation position point information and the detected position point information corresponding to each preset fixation point, calculate the eye movement tracking accuracy of the entire field of view of the device under test.

[0082] Furthermore, for the field of view of the device under test, the field of view can be divided into several sub-field test areas according to the nominal field of view angle size of the device under test. Based on this, the partition calculation results of different sub-field test areas can be used to evaluate the eye movement tracking accuracy of the device under test.

[0083] It should be noted that the detected position point information can be obtained from the average result of multiple tests of a single preset fixation point.

[0084] Based on the system including the humanoid eye model and the motion control module, the above steps control the humanoid eye model to move and fixate on a preset fixation point for testing, separately obtain the fixation position point information and the detected position point information of the humanoid eye model during the test, and evaluate the eye movement tracking accuracy of the device under test. It can evaluate the actual effect of eye movement tracking and is not affected by the limitations of user samples, solving the problem of being unable to effectively evaluate the effect of eye movement tracking.

[0085] In some of the embodiments, the determination of the fixation position point information of the humanoid eye model during the test in step S610 above, and the detected position point information in the device under test, can be achieved through the following steps:

[0086] Step S611: According to the spatial position of the preset fixation point, control the humanoid eye model to fixate on the preset fixation point for testing.

[0087] Specifically, in the device under test, the preset fixation point can be set according to different preset spatial positions, or an existing test point in the device under test can be used as the preset fixation point. By transmitting the spatial position of the preset fixation point to the motion control module, the motion control module controls the movement of the humanoid eye model for testing, and the testing is completed after the humanoid eye model fixates on each preset fixation point in the device under test.

[0088] Among them, the spatial position of the preset fixation point can be determined by different preset spatial positions; in addition, the spatial position of the preset fixation point can also be determined according to the image information of the preset fixation point in the device under test.

[0089] When the humanoid eye model is a camera, the image information of the preset fixation point can be directly collected through the humanoid eye model, and the spatial position of the preset fixation point is determined by analyzing the image information.

[0090] Step S612: Determine the fixation position point information according to the motion data and spatial position of the humanoid eye model during the testing process.

[0091] Specifically, during the testing process, the humanoid eye model moves to fixate on multiple preset fixation points. Through the motion detection device in the motion control module, information such as the motion data, spatial position, and pupil distance of the humanoid eye model is obtained to determine the fixation position point information of the humanoid eye model.

[0092] Step S613: Perform eye movement tracking detection on the humanoid eye model through the device under test to obtain the detected position point information.

[0093] Specifically, install the device under test on the test platform or wear it for use, and perform eye movement tracking detection on the movement of the humanoid eye model during the testing process, and output the detected position point information when the humanoid eye model fixates on each preset fixation point.

[0094] In this embodiment, by obtaining the fixation position point information and the detected position point information of the humanoid eye model for each preset fixation point during the testing process, in subsequent embodiments, the eye movement tracking effect of the device under test is evaluated according to the detected position point information output by the device under test and the fixation position point information output by the automated eye movement tracking evaluation system.

[0095] In some of these embodiments, the above-mentioned step S620 of determining the eye movement tracking accuracy of the device under test based on the fixation position point information and the corresponding detected position point information can be achieved through the following steps:

[0096] Step S621: Based on the field of view range of the device under test, one or more sub-field-of-view test areas are divided.

[0097] Specifically, for the field of view range of the device under test, the field of view range can be divided into at least one sub-field-of-view test area according to the size of the nominal field of view angle of the device under test. For example, the range of 0° - 30° is defined as the small field of view angle test area, the range of 30° - 60° is defined as the large field of view angle test area, and the range of 60° - the maximum field of view angle (if any) is defined as the extremely large field of view angle test area, so as to obtain several sub-field-of-view test areas ZONE1, ZONE2, etc. in the device under test.

[0098] Figure 7 It is a schematic diagram of the field of view division and preset fixation points in this embodiment. As Figure 7 shown, two sub-field-of-view test areas are divided in the field of view range of the device under test, namely the small field of view angle test area and the large field of view angle test area, and preset fixation points are distributed in each sub-field-of-view test area.

[0099] Step S622: According to the fixation position point information and detection position point information corresponding to the preset fixation points in each sub-field-of-view test area, determine the eye movement tracking accuracy of each field of view test area.

[0100] Specifically, in each sub-field-of-view test area, according to the fixation position point information P r,i and the detection position point information P m,i , calculate the eye movement tracking accuracy of each sub-field-of-view test area after partitioning respectively. Among them, the eye movement tracking accuracy of each sub-field-of-view test area is represented by the mean value of the arithmetic square root of the position error of each preset fixation point. The specific calculation formula is as follows:

[0101]

[0102] Among them, j represents the sub-field-of-view test area, and Accuracy j represents the eye movement tracking accuracy of the jth sub-field-of-view test area; i represents the preset fixation point, and n represents the number of preset fixation points in the jth sub-field-of-view test area; the detection position point information P r，i (x m，i , y m，i , z m，i ) represents that when the humanoid eye model fixates on the preset fixation point i, the three-dimensional coordinates of its detection position point information are (x m，i , y m，i , z m，i ); the fixation position point information P r，i (x r，i , y r，i , z r，i)It means that when the humanoid eye model gazes at the preset fixation point i, the three-dimensional coordinates of its fixation position point information are (x r，i , y r，i , z r，i ).

[0103] Step S623: Based on the eye movement tracking accuracy of each sub-field test area, calculate the eye movement tracking accuracy of the device under test by weighted calculation.

[0104] Specifically, evaluate the eye movement tracking accuracy of the device under test according to the accuracy zoning calculation results of different sub-field test areas. Among them, within the field of view of the device under test, the sensitivity of different field of view angle ranges to the eye movement tracking accuracy is different. Specifically, different weights can be set according to the sensitivity of different sub-field test areas, and then the overall eye movement tracking accuracy of the device under test can be calculated by weighted calculation. The specific calculation formula is as follows:

[0105]

[0106]

[0107] Among them, Accuracy all represents the eye movement tracking accuracy of the device under test; j represents the sub-field test area, and Accuracy j represents the eye movement tracking accuracy of the j-th sub-field test area, and k represents the number of sub-field test areas; b j represents the weight value of the j-th sub-field test area.

[0108] It should be noted that the eye movement tracking accuracy of each sub-field test area can be directly output, or the overall eye movement tracking accuracy of the device under test after weighted calculation can be output.

[0109] In this embodiment, the method of partitioning the field of view range of the device under test is adopted. The eye movement tracking accuracy of each sub-field test area is calculated separately, different weights are set, and the eye movement tracking accuracy of the device under test is calculated by weighted calculation of the eye movement tracking accuracy of each sub-field test area, which can improve the accuracy of accuracy calculation and effectively evaluate the effect of the device under test.

[0110] In the above embodiments, a method for evaluating the eye movement tracking accuracy of the device under test is provided. Further, the spatial angle resolution of eye movement tracking will also affect whether correct or even precise interaction actions can be achieved. Therefore, in the following embodiments, the effect of eye movement tracking is evaluated from the eye movement tracking spatial resolution of the device under test.

[0111] In some of these embodiments, the above method further includes the following steps:

[0112] Step S630: Control the humanoid eye model to perform a step - by - step movement at a preset angle, and synchronously obtain the information of the detection position points of the humanoid eye model.

[0113] Specifically, before performing the step - by - step movement, obtain the initial fixation position point information and the initial fixation position point information of the humanoid eye model. Figure 8 This is a schematic diagram of the preset angle in the step - by - step movement in this embodiment. As Figure 8 shown, control the humanoid eye model to perform a step - by - step movement through the motion control module, that is, move a preset angle each time. The angle between the lines of sight of the humanoid eye model before and after the movement is the preset angle α, and synchronously obtain the information of the detection position points of the humanoid eye model through the device under test. Among them, the preset angle can be set according to the nominal resolution of the device under test. The smaller the preset angle, the higher the evaluation accuracy of the eye movement tracking spatial resolution of the device under test. Exemplarily, the preset angle is set to 1 / 10 or less of the nominal resolution.

[0114] Step S640: When the detection position point information meets the preset conditions, obtain the fixation position point information of the humanoid eye model, and determine the eye movement tracking spatial resolution of the device under test based on the fixation point position information.

[0115] Specifically, the preset condition is: compare the detection position point information for each movement until the detection position point information is different from the detection position point information in the previous movement. When the detection position point information after each movement is the same as the detection position point information in the previous movement, the detection position point information does not meet the preset conditions, and continue to control the humanoid eye model to perform a step - by - step movement at the preset angle until the detection position point information is different from the detection position point information in the previous movement, meeting the preset conditions, and obtain the current fixation position point information of the humanoid eye model.

[0116] Furthermore, determine the eye movement tracking spatial resolution of the device under test according to the current fixation position point information and the initial fixation position point information before the step - by - step movement.

[0117] When the detection position point information is different from the detection position point information in the previous movement, it means that the device under test can detect the movement of the current humanoid eye model. By comparing the current fixation position point information and the initial fixation position point information, determine the eye movement tracking spatial resolution of the device under test. Exemplarily, the spatial resolution can be evaluated by the angular deviation between the current fixation position point information and the initial fixation position point information, or by the number of display pixels corresponding to the current fixation position point information and the initial fixation position point information.

[0118] In this embodiment, through a step - by - step test method, evaluate the eye movement tracking spatial resolution of the device under test by angular resolution, providing a more perfect method for evaluating the eye movement tracking effect.

[0119] The present embodiment will be described and illustrated below through preferred embodiments.

[0120] Figure 9 is a flowchart of the automated eye movement tracking evaluation method in this embodiment. As Figure 9 shown, the method includes the following steps:

[0121] Step S910, determine the spatial position of the preset fixation point according to the image information of the preset fixation point in the device under test; or, determine the spatial position of the preset fixation point according to the preset spatial position.

[0122] Step S920, according to the spatial position of the preset fixation point in the device under test, control the humanoid eye model to fixate on the preset fixation point for testing through the motion control module.

[0123] Among them, the humanoid eye model includes a sphere, an iris simulator, and a pupil located at the center of the iris simulator. Alternatively, the humanoid eye model is a humanoid eye camera or an event camera.

[0124] Step S930, determine the fixation position point information according to the motion data and spatial position of the humanoid eye model during the test; perform eye movement tracking detection on the humanoid eye model through the device under test to obtain the detected position point information.

[0125] Step S940, divide to obtain a plurality of sub-field test areas based on the field of view range of the device under test; determine the eye movement tracking accuracy of each field test area according to the fixation position point information and the detected position point information corresponding to the preset fixation point in each sub-field test area.

[0126] Step S950, based on the eye movement tracking accuracy of each sub-field test area, calculate the eye movement tracking accuracy of the device under test by weighted calculation.

[0127] Step S960, control the humanoid eye model to perform a step-by-step movement at a preset angle, and synchronously obtain the detected position point information of the humanoid eye model.

[0128] Step S970, compare the detected position point information for each movement until the detected position point information is different from the detected position point information in the previous movement, and obtain the current fixation position point information of the humanoid eye model; determine the eye movement tracking spatial resolution of the device under test according to the current fixation position point information and the initial fixation position point information before the step-by-step movement.

[0129] Through the method provided in this embodiment, based on a system including a humanoid eye model and a motion control module, the motion control module is used to control the humanoid eye model to move and fixate on a preset fixation point for testing, and the fixation position point information and detection position point information of the humanoid eye model during the testing process are respectively obtained. Moreover, in the sub-field test area divided by the device under test, the partition calculation results of different sub-field test areas are used to evaluate the eye movement tracking accuracy of the device under test, and the step-by-step motion is used to evaluate the eye movement tracking spatial resolution of the device under test, so as to evaluate the actual effect of eye movement tracking, and it will not be affected by the limitations of user samples, solving the problem that the effect of eye movement tracking cannot be effectively evaluated.

[0130] In this embodiment, an automated eye movement tracking evaluation device is further provided. This device is used to implement the above-mentioned embodiments and preferred implementation manners, and those that have been described will not be repeated here. The following terms such as "module", "unit", "sub-unit", etc. can be a combination of software and / or hardware that can achieve a predetermined function. Although the device described in the following embodiments is preferably implemented in software, implementation in hardware, or a combination of software and hardware is also possible and contemplated.

[0131] Figure 10 is a structural block diagram of the automated eye movement tracking evaluation device in this embodiment. This device is applied to the automated eye movement tracking evaluation system in the above embodiments, as Figure 10 shown. This device includes: a position point information determination module 10 and an eye movement tracking evaluation module 20.

[0132] The position point information determination module 10 is used to determine the fixation position point information of the humanoid eye model during the testing process, as well as the detection position point information in the device under test.

[0133] The eye movement tracking evaluation module 20 is used to determine the eye movement tracking accuracy of the device under test based on the fixation position point information and the corresponding detection position point information.

[0134] Through the device provided in this embodiment, based on a system including a humanoid eye model and a motion control module, the motion control module is used to control the humanoid eye model to move and fixate on a preset fixation point for testing, and the fixation position point information and detection position point information of the humanoid eye model during the testing process are respectively obtained, and the eye movement tracking accuracy of the device under test is evaluated, so as to evaluate the actual effect of eye movement tracking, and it will not be affected by the limitations of user samples, solving the problem that the effect of eye movement tracking cannot be effectively evaluated.

[0135] In some of these embodiments, the eye movement tracking evaluation module 20 is further configured to control the humanoid eye model to perform a step-by-step movement at a preset angle, and synchronously obtain the information of the detected position points of the humanoid eye model; when the information of the detected position points meets the preset conditions, obtain the information of the fixation position points of the humanoid eye model, and determine the eye movement tracking spatial resolution of the device under test based on the fixation point position information.

[0136] It should be noted that the above-mentioned respective modules can be functional modules or program modules, and can be implemented either by software or by hardware. For the modules implemented by hardware, the above-mentioned respective modules can be located in the same processor; or the above-mentioned respective modules can also be located in different processors in any combined form.

[0137] In this embodiment, a computer device is further provided, including a memory and a processor. A computer program is stored in the memory, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.

[0138] Optionally, the above computer device may further include a transmission device and an input / output device, wherein the transmission device is connected to the above processor, and the input / output device is connected to the above processor.

[0139] It should be noted that the specific examples in this embodiment can refer to the examples described in the above embodiments and optional implementation manners, and will not be elaborated herein.

[0140] In addition, in combination with the automated eye movement tracking evaluation method provided in the above embodiments, a storage medium can also be provided to implement it in this embodiment. A computer program is stored on the storage medium; when the computer program is executed by a processor, it implements any one of the automated eye movement tracking evaluation methods in the above embodiments.

[0141] In one embodiment, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, it implements the steps in the above method embodiments.

[0142] It should be understood that the specific embodiments described here are only used to explain this application, rather than to limit it. According to the embodiments provided in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts fall within the protection scope of the present application.

[0143] Obviously, the accompanying drawings are only some examples or embodiments of the present application. For those of ordinary skill in the art, the present application can also be applied to other similar situations based on these drawings without creative efforts. Additionally, it can be understood that although the work done during this development process may be complex and time-consuming, for those of ordinary skill in the art, certain design, manufacturing, or production changes based on the technical content disclosed in the present application are only routine technical means and should not be regarded as insufficient disclosure of the present application.

[0144] The term "embodiment" in the present application means that the specific features, structures, or characteristics described in connection with the embodiments may be included in at least one embodiment of the present application. The phrase appears in various positions in the specification and does not necessarily mean the same embodiment, nor does it mean being independent or alternative to other embodiments and mutually exclusive. Those of ordinary skill in the art can clearly or implicitly understand that the embodiments described in the present application can be combined with other embodiments without conflict.

[0145] The above-described embodiments merely represent several implementation manners of the present application, and the description thereof is relatively specific and detailed, but it should not be construed as a limitation on the scope of patent protection. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present application, several modifications and improvements can still be made, and these all fall within the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the appended claims.

Claims

1. An automated eye movement tracking evaluation method, characterized in that, Applied to an automated eye movement tracking evaluation system, the system includes: a humanoid eye model connected to a motion control module, and the humanoid eye model is controlled by the motion control module to fixate on a preset fixation point in the device under test for testing; the method includes: Determine the fixation position point information of the humanoid eye model during the test, and the detection position point information in the device under test; Based on the fixation position point information and the corresponding detection position point information, determine the eye movement tracking accuracy of the device under test.

2. The automated eye movement tracking evaluation method according to claim 1, wherein The determining the eye movement tracking accuracy of the device under test based on the fixation position point information and the corresponding detection position point information includes: Based on the field of view range of the device under test, divide to obtain one or more sub-field test areas; According to the fixation position point information and the detection position point information corresponding to the preset fixation point in each sub-field test area, determine the eye movement tracking accuracy of each sub-field test area; Based on the eye movement tracking accuracy of each sub-field test area, calculate the eye movement tracking accuracy of the device under test by weighted calculation.

3. The automated eye movement tracking evaluation method according to claim 1, wherein The determining the fixation position point information of the humanoid eye model during the test, and the detection position point information in the device under test includes: According to the spatial position of the preset fixation point, control the humanoid eye model to fixate on the preset fixation point for testing; According to the motion data and spatial position of the humanoid eye model during the test, determine the fixation position point information; Through the device under test, perform eye movement tracking detection on the humanoid eye model to obtain the detection position point information.

4. The automated eye movement tracking evaluation method according to claim 3, wherein Further includes: According to the image information of the preset fixation point in the device under test, determine the spatial position of the preset fixation point.

5. The automated eye movement tracking evaluation method according to any one of claims 1 to 4, characterized in that, Further includes: Control the humanoid eye model to perform step-by-step movement at a preset angle, and synchronously obtain the detection position point information of the humanoid eye model; When the detection position point information meets the preset conditions, obtain the fixation position point information of the humanoid eye model, and based on the fixation point position information, determine the eye movement tracking spatial resolution of the device under test.

6. The automated eye movement tracking evaluation method according to claim 5, characterized in that The when the detection position point information meets the preset conditions, obtain the fixation position point information of the humanoid eye model, and based on the fixation point position information, determine the eye movement tracking spatial resolution of the device under test includes: Compare the detection position point information for each movement until the detection position point information is different from the detection position point information in the previous movement, and obtain the current fixation position point information of the humanoid eye model; According to the current fixation position point information and the initial fixation position point information before the step-by-step movement, determine the eye movement tracking spatial resolution of the device under test.

7. An automated eye movement tracking and evaluation device, characterized in that, Applied to an automated eye movement tracking evaluation system, the system includes: a humanoid eye model connected to a motion control module, and the humanoid eye model is controlled by the motion control module to fixate on a preset fixation point in the device under test for testing; the device includes: a position point information determination module and an eye movement tracking evaluation module; The position point information determination module is configured to determine the fixation position point information of the humanoid eye model and the detection position point information in the device under test during the test; The eye movement tracking evaluation module is configured to determine the eye movement tracking accuracy of the device under test based on the fixation position point information and the corresponding detection position point information.

8. An automated eye movement tracking and evaluation system, characterized in that, It includes: A humanoid eye model, a motion control module, and a data processor; The motion control module is connected to the humanoid eye model and is configured to control the humanoid eye model to fixate on a preset fixation point in the device under test for testing; The data processor is connected to the motion control module and is configured to execute the automated eye movement tracking evaluation method according to any one of claims 1 to 6.

9. The automated eye movement tracking and evaluation system according to claim 8, wherein When the device under test is an eye movement tracking module, the humanoid eye model includes a sphere, an iris simulator, and a pupil located at the center of the iris simulator.

10. The automated eye movement tracking and evaluation system according to claim 8, characterized in that, When the device under test is a display device integrated with an eye movement tracking module, the humanoid eye model is a humanoid eye camera or an event camera.

11. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the automated eye movement tracking evaluation method according to any one of claims 1 to 6.

Images