Test method and device, equipment and storage medium

Abstract

The invention relates to the technical field of virtual reality, and discloses a test method, device and equipment and a storage medium, and the method comprises the steps: controlling a human eye simulation part to rotate towards a first test point through a motor, and obtaining a first rotation angle of the motor and a first tracking angle obtained by tracking the human eye simulation part through an eye movement tracking system; controlling the human eye simulating part to rotate towards a second test point through the motor, and obtaining a second rotation angle of the motor and a second tracking angle obtained by tracking the human eye simulating part through the eye movement tracking system; obtaining an eye movement relative angle difference according to the first tracking angle and the second tracking angle, and obtaining a motor theoretical relative angle difference according to the first rotation angle and the second rotation angle; and testing the eye movement tracking system based on the eye movement relative angle difference and the motor theoretical relative angle difference to generate a test result. The accumulated influence of the absolute position error of the motor can be eliminated, so that the accuracy of a test result is improved.

Description

Technical Field

[0001] This application relates to the field of virtual reality technology, and in particular to testing methods, apparatus, devices and storage media. Background Technology

[0002] Eye tracking (ET) technology has been widely applied in various fields in recent years, including virtual reality (VR), augmented reality (AR), and human-computer interaction. Eye tracking systems, by monitoring changes in the direction and position of eye movements, can provide users with a natural, efficient, and intuitive interaction method. To ensure the reliability and accuracy of eye tracking systems in practical applications, accurate and reliable testing is crucial.

[0003] Currently, eye-tracking systems are typically tested using a fixed initial point as a reference. External devices, such as motors, drive the test target (e.g., a simulated human eye) to move precisely to obtain the theoretical relative eye angle. The relative eye angle measured by the eye-tracking system is recorded, and the performance of the system is evaluated using the angle difference. However, motors inevitably develop slight positioning deviations during long-term operation or complex trajectory movements. These deviations accumulate with increasing distance or time. When a fixed initial point is used as a reference, the theoretical angle at each subsequent test point actually includes all the accumulated errors from the initial point to that point. This results in a composite indicator of the final calculated angle difference, which is a mixture of the eye-tracking system's measurement error and the motor drive system's accumulated error. This fails to accurately reflect the relative angle measurement accuracy and stability of the eye-tracking system itself, leading to distorted test results and making it difficult to accurately assess the true performance of the eye-tracking system. Summary of the Invention

[0004] The main purpose of this application is to provide a testing method, apparatus, device, and storage medium, which aims to solve the technical problem that existing eye-tracking system testing methods easily introduce the cumulative error of the motor itself into the test results of the eye-tracking system, resulting in low accuracy of the test results.

[0005] To achieve the above objectives, this application proposes a testing method applied to a testing device equipped with a motor and a human-eye component. The motor drives the human-eye component to rotate. The testing device is connected to smart glasses equipped with an eye-tracking system. The method includes: The motor controls the rotation of the bionic eye component toward the first test point, and the first rotation angle of the motor and the first tracking angle obtained by the eye-tracking system are acquired. The motor controls the anthropomorphic eye component to rotate toward the second test point, and the second rotation angle of the motor and the second tracking angle obtained by the eye-tracking system are acquired. The positions of the first test point and the second test point are different. The relative angle difference of eye movement is obtained based on the first tracking angle and the second tracking angle, and the theoretical relative angle difference of the motor is obtained based on the first rotation angle and the second rotation angle; The eye-tracking system is tested based on the relative angle difference of eye movement and the theoretical relative angle difference of motor, and the test results of the eye-tracking system are generated.

[0006] In one embodiment, the first tracking angle includes a first left-eye tracking angle and a first right-eye tracking angle, and the second tracking angle includes a second left-eye tracking angle and a second right-eye tracking angle; the step of obtaining the relative eye movement angle difference based on the first tracking angle and the second tracking angle includes: A first fused tracking angle is generated based on the first left eye tracking angle and the first right eye tracking angle; A second fusion tracking angle is generated based on the second left-eye tracking angle and the second right-eye tracking angle; The relative eye movement angle difference is obtained based on the first fusion tracking angle and the second fusion tracking angle.

[0007] In one embodiment, the step of generating a first fused tracking angle based on the first left-eye tracking angle and the first right-eye tracking angle includes: Determine the first confidence level corresponding to the first left eye tracking angle and the second confidence level corresponding to the first right eye tracking angle; The first left-eye tracking angle and the first right-eye tracking angle are fused based on the first confidence level and the second confidence level to generate a first fused tracking angle.

[0008] In one embodiment, the step of generating a second fused tracking angle based on the second left-eye tracking angle and the second right-eye tracking angle includes: Determine the third confidence level corresponding to the second left eye tracking angle and the fourth confidence level corresponding to the second right eye tracking angle; The second left-eye tracking angle and the second right-eye tracking angle are fused based on the third confidence level and the fourth confidence level to generate a second fused tracking angle.

[0009] In one embodiment, the step of testing the eye-tracking system based on the relative eye movement angle difference and the theoretical relative motor angle difference, and generating test results for the eye-tracking system, includes: The relative angle error between the first test point and the second test point is determined based on the eye movement relative angle difference and the motor theoretical relative angle difference. The eye-tracking system is tested based on the relative angle error and the preset dynamic error threshold, and the test results of the eye-tracking system are generated.

[0010] In one embodiment, before the step of testing the eye-tracking system based on the relative angle error and a preset dynamic error threshold to generate test results for the eye-tracking system, the method further includes: Determine the angular velocity between the first test point and the second test point; The preset dynamic error threshold is determined based on the angular velocity, the basic static threshold, and the velocity sensitivity coefficient.

[0011] In one embodiment, the step of determining the angular velocity between the first test point and the second test point includes: Obtain the first acquisition time of the first test point and the second acquisition time of the second test point; The test time interval between the first test point and the second test point is determined based on the first acquisition time and the second acquisition time. The angular velocity between the first test point and the second test point is determined based on the theoretical relative angle difference of the motor and the test time interval.

[0012] Furthermore, to achieve the above objectives, this application also proposes a testing apparatus, the apparatus comprising: The data acquisition module is used to control the rotation of the humanoid eye component towards the first test point by a motor, and to acquire the first rotation angle of the motor and the first tracking angle obtained by tracking the humanoid eye component through the eye-tracking system. The data acquisition module is used to control the humanoid eye component to rotate toward the second test point via the motor, and to acquire the second rotation angle of the motor and the second tracking angle obtained by tracking the humanoid eye component through the eye-tracking system, wherein the first test point and the second test point are at different positions; An angle difference determination module is used to obtain the relative angle difference of eye movement based on the first tracking angle and the second tracking angle, and to obtain the theoretical relative angle difference of the motor based on the first rotation angle and the second rotation angle; The testing module is used to test the eye-tracking system based on the relative angle difference of eye movement and the theoretical relative angle difference of motor, and generate test results for the eye-tracking system.

[0013] In addition, to achieve the above objectives, this application also proposes a testing device, the device comprising: a motor and a human-eye component, wherein the motor is used to drive the human-eye component to rotate; The device further includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the test method as described above.

[0014] In addition, to achieve the above objectives, this application also proposes a storage medium, which is a computer-readable storage medium, on which a computer program is stored, and which, when executed by a processor, implements the steps of the test method described above.

[0015] This application provides a testing method, apparatus, device, and storage medium. The method is applied to a testing device with a motor and a human-eye component. The motor drives the human-eye component to rotate. The testing device is connected to smart glasses equipped with an eye-tracking system. The method includes: controlling the human-eye component to rotate toward a first test point via the motor, and obtaining a first rotation angle of the motor and a first tracking angle obtained by tracking the human-eye component via the eye-tracking system; controlling the human-eye component to rotate toward a second test point via the motor, and obtaining a second rotation angle of the motor and a second tracking angle obtained by tracking the human-eye component via the eye-tracking system, wherein the first test point and the second test point are at different positions; obtaining a relative eye movement angle difference based on the first tracking angle and the second tracking angle, and obtaining a theoretical relative angle difference of the motor based on the first rotation angle and the second rotation angle; testing the eye-tracking system based on the relative eye movement angle difference and the theoretical relative angle difference of the motor, and generating a test result for the eye-tracking system.

[0016] The testing equipment of this application can acquire the first rotation angle of the motor and the first tracking angle obtained by the eye-tracking system when the anthropomorphic eye component rotates towards the first test point, and acquire the second rotation angle of the motor and the second tracking angle obtained by the eye-tracking system when the anthropomorphic eye component rotates towards the second test point. Then, it calculates the relative angle difference of eye movement based on the first and second tracking angles, and calculates the theoretical relative angle difference of the motor based on the first and second rotation angles. Finally, it can test the eye-tracking system based on the relative angle difference of eye movement and the theoretical relative angle difference of the motor. Compared with the angle difference calculated in existing testing methods, which is a mixture of measurement error of the eye-tracking system and cumulative error of the motor, this application can determine the theoretical relative angle difference of the motor between the two test points based on the difference between the first rotation angle measured at the first test point and the second rotation angle measured at the second test point. It can then test the eye-tracking system based on the theoretical relative angle difference of the motor and the relative angle difference of eye movement of the eye-tracking system at different test points, thereby eliminating the cumulative influence of the absolute position error of the motor and improving the accuracy and reliability of the test results. Attached Figure Description

[0017] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0018] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0019] Figure 1 This is a schematic diagram of the test equipment structure for the hardware operating environment involved in the embodiments of this application; Figure 2 This is a flowchart illustrating the first embodiment of the testing method of this application; Figure 3 This is a flowchart illustrating the second embodiment of the testing method of this application; Figure 4 This is a flowchart illustrating the third embodiment of the testing method of this application; Figure 5 This is a structural block diagram of the test device of this application.

[0020] The purpose, features, and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0021] It should be understood that the specific embodiments described herein are merely illustrative of the technical solutions of this application and are not intended to limit this application.

[0022] Reference Figure 1 , Figure 1 This is a schematic diagram of the test equipment structure for the hardware operating environment involved in the embodiments of this application.

[0023] like Figure 1 As shown, the test device may include: a processor 1001, such as a central processing unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. The communication bus 1002 is used to enable communication between these components. The user interface 1003 may be connected to a display screen; optionally, the user interface 1003 may include a standard wired interface or a wireless interface. In this application, the wired interface of the user interface 1003 may be a USB interface. The network interface 1004 may optionally include a standard wired interface or a wireless interface (such as a Wireless-Fidelity (Wi-Fi) interface). The memory 1005 may be high-speed random access memory (RAM) or non-volatile memory (NVM), such as a disk storage device. The memory 1005 may also optionally be a storage device independent of the aforementioned processor 1001.

[0024] Those skilled in the art will understand that Figure 1 The structure shown does not constitute a limitation on the test equipment and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0025] like Figure 1 As shown, the memory 1005, which is identified as a computer storage medium, may include an operating system, a network communication module, a user interface module, and a test program.

[0026] exist Figure 1 In the test device shown, the network interface 1004 is mainly used to connect to the backend server and communicate with the backend server; the user interface 1003 is mainly used to connect to the user equipment; the test device calls the test program stored in the memory 1005 through the processor 1001 and executes the steps of the test method provided in the embodiments of this application.

[0027] It's worth noting that eye-tracking (ET) technology has been widely applied in various fields in recent years, including virtual reality (VR), augmented reality (AR), and human-computer interaction. Eye-tracking systems, by monitoring changes in the direction and position of eye movements, can provide users with a natural, efficient, and intuitive interaction method. To ensure the reliability and accuracy of eye-tracking systems in practical applications, accurate and reliable testing is crucial. Currently, eye-tracking systems are typically tested using a fixed initial point as a reference. External devices, such as motors, drive the test target (e.g., a simulated human eye) to move precisely to obtain the theoretical relative eye angle. The relative eye angle measured by the eye-tracking system is recorded, and the performance of the system is evaluated using the angle difference. However, motors inevitably develop slight positioning deviations during long-term operation or complex trajectory movements. These deviations accumulate with increasing distance or time. When a fixed initial point is used as a reference, the theoretical angle at each subsequent test point actually includes all the accumulated errors from the initial point to that point. This results in a composite indicator of the final calculated angle difference, which is a mixture of the eye-tracking system's measurement error and the motor drive system's accumulated error. This fails to accurately reflect the relative angle measurement accuracy and stability of the eye-tracking system itself, leading to distorted test results and making it difficult to accurately assess the true performance of the eye-tracking system.

[0028] Therefore, to address the aforementioned shortcomings, this embodiment provides a testing method. In this embodiment, the testing equipment can acquire the first rotation angle of the motor and the first tracking angle obtained by the eye-tracking system when the anthropomorphic eye component rotates towards the first test point. Similarly, when the anthropomorphic eye component rotates towards the second test point, it can acquire the second rotation angle of the motor and the second tracking angle obtained by the eye-tracking system. Then, the relative angle difference of eye movement is calculated based on the first and second tracking angles, and the theoretical relative angle difference of the motor is calculated based on the first and second rotation angles. Finally, the eye-tracking system can be tested based on the relative angle difference of eye movement and the theoretical relative angle difference of the motor. Compared to existing testing methods where the calculated angle difference is a mixture of measurement errors from the eye-tracking system and cumulative errors from the motor, this embodiment can determine the theoretical relative angle difference of the motor between the two test points based on the difference between the first rotation angle measured at the first test point and the second rotation angle measured at the second test point. Furthermore, the eye-tracking system can be tested based on the theoretical relative angle difference of the motor and the relative angle difference of eye movement at different test points, thereby eliminating the cumulative influence of the absolute position error of the motor and improving the accuracy and reliability of the test results.

[0029] For ease of understanding, the following is combined with Figures 2 to 4The testing methods provided in the embodiments of this application will be described in detail.

[0030] Reference Figure 2 , Figure 2 This is a flowchart illustrating the first embodiment of the testing method of this application. The first embodiment of the testing method of this application is presented as follows: Figure 2 As shown, in this embodiment, the method is applied to a testing device with a motor and a human-eye component. The motor drives the human-eye component to rotate. The testing device is connected to smart glasses equipped with an eye-tracking system. The specific method includes: Step S10: Control the humanoid eye component to rotate toward the first test point by the motor, and obtain the first rotation angle of the motor and the first tracking angle obtained by the eye-tracking system tracking the humanoid eye component.

[0031] It is understood that the method of this embodiment can be applied to the aforementioned testing equipment, which can be any device with data processing, program execution, and data acquisition functions, such as an artificial head; this embodiment does not impose any limitations on this. In practical use, the testing equipment may be equipped with components such as motors, artificial eye parts, and control units, which can simulate the movement of a real eye and record measurement data from the eye-tracking system to evaluate its performance.

[0032] It is also understood that the motor can be a component in the testing equipment used to drive the movement of the artificial eye component, which can be a component used to simulate the movement of a real human eye. In actual use, the motor can drive the artificial eye component to move according to a preset trajectory and speed, simulating the movement of a real eye, including rapid eye movement, smooth tracking, and fixation.

[0033] It should be understood that the aforementioned eye-tracking system can be a technical system used to monitor and record eye movement direction, position changes, and gaze point in real time. It can be installed on smart glasses or other wearable devices to capture eye movement data and convert it into analyzable signals or angular information. In practical use, smart glasses can serve as the carrier of the eye-tracking system, ensuring its stable operation. Simultaneously, the smart glasses can connect to testing equipment via data interfaces (such as USB, Bluetooth, etc.) to receive and transmit data from the eye-tracking system during testing.

[0034] It should be noted that the first test point mentioned above can be a randomly selected target position that the eye-tracking system needs to track. It can be defined by spatial coordinates (such as x, y, z values ​​in a three-dimensional coordinate system) or angles (such as horizontal and vertical angles relative to a certain reference direction). For example, the first test point can be defined as deflected 10 degrees in the horizontal direction and 5 degrees in the vertical direction. This embodiment does not impose any restrictions on this.

[0035] It should also be noted that the aforementioned first rotation angle can be the angle rotated by the motor-controlled human eye component from the initial position (reference point) to the first test point, that is, the relative angle between the first test point and the reference point measured by the motor. During the test, the motor can precisely rotate to the designated first test point according to preset control instructions (such as through computer program control) and record the corresponding rotation angle to obtain the first rotation angle.

[0036] Furthermore, the aforementioned first tracking angle can be the relative angle of eye movement measured by the eye-tracking system when the humanoid eye component points to the first test point, that is, the relative angle between the first test point and the reference point measured by the eye-tracking system. In this embodiment, the eye-tracking system can capture the movement of the eye (or humanoid eye component) through its sensors (such as a camera or infrared sensor) and calculate the relative angle between the first test point and the reference point to obtain the first tracking angle.

[0037] Step S20: Control the humanoid eye component to rotate toward the second test point by the motor, and obtain the second rotation angle of the motor and the second tracking angle obtained by the eye tracking system tracking the humanoid eye component. The positions of the first test point and the second test point are different.

[0038] It should be noted that the aforementioned second test point can be another target location that the eye-tracking system needs to track, and it can be another test point adjacent to or close to the first test point. In this embodiment, the second test point, like the first test point, can also be defined by spatial coordinates or angles.

[0039] It should also be noted that the aforementioned second rotation angle can be the angle rotated by the motor-controlled human eye component from the initial position (reference point) to the second test point, that is, the relative angle between the second test point and the reference point measured by the motor. During the test, the motor can precisely rotate to the designated position of the second test point according to the preset control command, and record the corresponding rotation angle to obtain the second rotation angle.

[0040] Furthermore, the aforementioned second tracking angle can be the relative angle of eye movement measured by the eye-tracking system when the humanoid eye component points to the second test point, that is, the relative angle between the second test point and the reference point measured by the eye-tracking system. In this embodiment, the eye-tracking system can capture the movement of the eye (or humanoid eye component) through its sensors (such as a camera or infrared sensor) and calculate the relative angle between the second test point and the reference point to obtain the second tracking angle.

[0041] In practical applications, the testing equipment first places the bionic eye component (or the eye being tested) in its initial position (reference point), records the initial state, and initializes the eye-tracking system and motor control system, ensuring they operate synchronously. Then, the testing equipment controls the bionic eye component to rotate to the first test point via a motor, recording the rotation angle when the motor reaches the first test point, thus obtaining the first rotation angle of the motor. Simultaneously, the eye-tracking system measures and records the first tracking angle. Furthermore, the testing equipment can also control the bionic eye component to rotate from the initial position (reference point) to a second test point via a motor, recording the rotation angle when the motor reaches the second test point, thus obtaining the second rotation angle of the motor. Simultaneously, the eye-tracking system measures and records the second tracking angle.

[0042] Step S30: Obtain the relative angle difference of eye movement based on the first tracking angle and the second tracking angle, and obtain the theoretical relative angle difference of motor based on the first rotation angle and the second rotation angle.

[0043] It should be understood that the aforementioned relative eye movement angle difference can be the change in eye movement angle between the first test point and the second test point, as measured by the eye-tracking system. This can be obtained by calculating the difference between the eye-tracking angles at the first and second test points (i.e., the difference between the first tracking angle and the second tracking angle). For example, if the first tracking angle measured at the first test point k is... The second tracking angle measured at the second test point k-1 is At this time, the relative angle difference of eye movement The calculation formula can be:

[0044] It should also be understood that the aforementioned theoretical relative angle difference of the motor can be the actual change in the angle of rotation of the motor between the first test point and the second test point, which can be obtained by calculating the difference in the motor rotation angle at the first test point and the second test point (i.e., the difference between the first rotation angle and the second rotation angle). For example, if the first rotation angle measured at the first test point k is... The second rotation angle measured at the second test point k-1 is At this time, the theoretical relative angle difference of the motor The calculation formula can be:

[0045] Step S40: Test the eye-tracking system based on the relative angle difference of eye movement and the theoretical relative angle difference of motor, and generate the test results of the eye-tracking system.

[0046] Understandably, the test results of an eye-tracking system can be used to evaluate the accuracy and stability of the eye-tracking system under different test conditions. These results may include, but are not limited to, the error value at each test point, the pass / fail judgment (including pass and fail), and a summary of the overall performance (such as average error, maximum error, minimum error).

[0047] In practical applications, testing equipment can evaluate the accuracy and stability of an eye-tracking system by comparing the relative eye-tracking angle difference with the theoretical relative angle difference of the motor, thus obtaining the test results of the eye-tracking system. Since the theoretical relative angle difference of the motor depends only on the difference between the first and second test points, the cumulative effect of the motor's absolute position error can be eliminated, allowing the system to focus on the relative accuracy of the eye-tracking system between adjacent positions.

[0048] In this embodiment, the testing equipment can acquire the first rotation angle of the motor and the first tracking angle obtained by the eye-tracking system when the anthropomorphic eye component rotates towards the first test point. Similarly, when the anthropomorphic eye component rotates towards the second test point, it acquires the second rotation angle of the motor and the second tracking angle obtained by the eye-tracking system. Then, it calculates the relative angle difference based on the first and second tracking angles, and calculates the theoretical relative angle difference of the motor based on the first and second rotation angles. Finally, it tests the eye-tracking system based on the relative angle difference of the eye movement and the theoretical relative angle difference of the motor. Compared to existing testing methods where the calculated angle difference is a mixture of measurement errors from the eye-tracking system and cumulative errors from the motor, this embodiment determines the theoretical relative angle difference of the motor between the first and second test points based on the difference between the first rotation angle measured at the first test point and the second rotation angle measured at the second test point. By testing the eye-tracking system based on the theoretical relative angle difference of the motor and the relative angle difference of the eye movement at different test points, the cumulative effect of the motor's absolute position error can be eliminated, thereby improving the accuracy and reliability of the test results.

[0049] Reference Figure 3 , Figure 3 This is a flowchart illustrating the second embodiment of the testing method of this application. Based on the first embodiment described above, a second embodiment of the testing method of this application is proposed.

[0050] Considering that when testing an eye-tracking system, relying solely on monocular data can lead to inaccurate test results due to poor monocular data quality (e.g., inaccurate data due to eye occlusion, light interference, or sensor malfunction), thus failing to accurately reflect the overall performance of the eye-tracking system, this embodiment defines the first tracking angle as including a first left-eye tracking angle and a first right-eye tracking angle, and the second tracking angle as including a second left-eye tracking angle and a second right-eye tracking angle. The step of obtaining the relative eye movement angle difference based on the first and second tracking angles includes: Step S31: Generate a first fusion tracking angle based on the first left eye tracking angle and the first right eye tracking angle.

[0051] It should be understood that the aforementioned first left eye tracking angle can be the angle of the left eye relative to the reference point measured by the eye tracking system at the first test point; correspondingly, the aforementioned first right eye tracking angle can be the angle of the right eye relative to the reference point measured by the eye tracking system at the first test point.

[0052] It should also be understood that the aforementioned first fused tracking angle can be a composite angle obtained by fusing the first left-eye tracking angle and the first right-eye tracking angle. In this embodiment, the testing device can fuse the first left-eye tracking angle and the first right-eye tracking angle based on the confidence level of the left and right eye data to improve the robustness and accuracy of the measurement.

[0053] Furthermore, in order to improve the accuracy of the measurement data, step S31 includes: determining a first confidence level corresponding to the first left eye tracking angle and a second confidence level corresponding to the first right eye tracking angle; and fusing the first left eye tracking angle and the first right eye tracking angle based on the first confidence level and the second confidence level to generate a first fused tracking angle.

[0054] Understandably, the aforementioned first confidence level can be an indicator reflecting the reliability of the first left-eye tracking data; correspondingly, the aforementioned second confidence level can be an indicator reflecting the reliability of the first right-eye tracking data. In practical use, the eye-tracking system, after measuring the first left-eye tracking angle and the first right-eye tracking angle, can output a score related to the pupil detection quality. This score can reflect the accuracy and reliability of pupil detection. After detecting the pupils of the left and right eyes, the system can assign a quality score to each pupil, and these scores can be directly used as the confidence level of the measured first left-eye tracking angle and the first right-eye tracking angle.

[0055] In practical applications, if the eye-tracking system measures the first left-eye tracking angle relative to the reference point at the first test point as follows: Its corresponding first confidence level is The first right eye tracking angle relative to the reference point, measured at the first test point, is: Its corresponding second confidence level is Then, the first left-eye tracking angle and the first right-eye tracking angle can be weighted and fused based on the first confidence level and the second confidence level to obtain the first fused tracking angle. The corresponding calculation formula can be:

[0056] Step S32: Generate a second fusion tracking angle based on the second left eye tracking angle and the second right eye tracking angle.

[0057] It should be understood that the aforementioned second left eye tracking angle can be the angle of the left eye relative to the reference point measured by the eye tracking system at the second test point; correspondingly, the aforementioned second right eye tracking angle can be the angle of the right eye relative to the reference point measured by the eye tracking system at the second test point.

[0058] It should also be understood that the aforementioned second fused tracking angle can be a composite angle obtained by fusing the second left-eye tracking angle and the second right-eye tracking angle. In this embodiment, the testing device can fuse the second left-eye tracking angle and the second right-eye tracking angle based on the confidence level of the left and right eye data to improve the robustness and accuracy of the measurement.

[0059] Further, step S32 includes: determining a third confidence level corresponding to the second left-eye tracking angle and a fourth confidence level corresponding to the second right-eye tracking angle; fusing the second left-eye tracking angle and the second right-eye tracking angle based on the third confidence level and the fourth confidence level to generate a second fused tracking angle.

[0060] Understandably, the aforementioned third confidence level can be an indicator reflecting the reliability of the second left-eye tracking data; correspondingly, the aforementioned fourth confidence level can be an indicator reflecting the reliability of the second right-eye tracking data. In practical use, the methods for obtaining the third and fourth confidence levels can be the same as those for obtaining the first and second confidence levels.

[0061] In practical applications, if the eye-tracking system measures the second left-eye tracking angle relative to the reference point at the second test point as follows: Its corresponding third confidence level is The second right eye tracking angle relative to the reference point, measured at the second test point, is: Its corresponding fourth confidence level is Then, the second left-eye tracking angle and the second right-eye tracking angle can be weighted and fused based on the third and fourth confidence levels to obtain the second fused tracking angle. The corresponding calculation formula can be:

[0062] Step S33: Obtain the relative eye movement angle difference based on the first fusion tracking angle and the second fusion tracking angle.

[0063] It should be noted that after determining the first fusion tracking angle and the second fusion tracking angle, the testing device can calculate the difference between the first fusion tracking angle and the second fusion tracking angle to obtain the relative eye movement angle difference between the first test point and the second test point. The corresponding calculation formula can be:

[0064] Reference Figure 4 , Figure 4 This is a flowchart illustrating the third embodiment of the testing method of this application. Based on the above embodiments, the third embodiment of the testing method of this application is proposed.

[0065] Currently, traditional testing methods typically determine the error of an eye-tracking system by subtracting the relative angle difference between eye movements and the theoretical relative angle difference between the motor, and then use a static error threshold to judge the pass / fail status of the eye-tracking system. However, different testing scenarios (such as different eye movement speeds, different gaze areas, etc.) usually have different accuracy requirements for eye-tracking systems. If a static error threshold is used for pass / fail judgment, it cannot adapt to these dynamically changing needs, which may lead to overly strict or lenient performance evaluations of the eye-tracking system in some scenarios. For example, in high-speed motion scenarios, the error of the eye-tracking system may increase, and a static error threshold may lead to misjudgment (such as misjudging normal error as unqualified), thus failing to accurately determine whether the eye-tracking system meets the requirements of practical applications. Therefore, in order to improve the adaptability and accuracy of the test, in this embodiment, step S40 includes: Step S41: Determine the relative angle error between the first test point and the second test point based on the relative angle difference of eye movement and the relative angle difference of motor theory.

[0066] It is understandable that the aforementioned relative angle error can be the difference between the relative angle change measured by the eye-tracking system and the theoretical relative angle change of the motor between the first test point and the second test point, which can be used to evaluate the accuracy of the eye-tracking system.

[0067] In this embodiment, if the relative eye movement angle difference between the first test point and the second test point measured by the eye-tracking system is... The theoretical relative angle difference between the first and second test points of the motor is Then, by measuring the relative angle difference of eye movements, The relative angle difference between the motor theory and the actual angle. By subtracting the values, the relative angle error between the first and second test points can be obtained. The corresponding calculation formula can be:

[0068] Step S42: Test the eye-tracking system based on the relative angle error and the preset dynamic error threshold, and generate the test results of the eye-tracking system.

[0069] It should be noted that the aforementioned preset dynamic error threshold can be used to evaluate whether the performance of the eye-tracking system meets the required error range. In actual use, the preset dynamic error threshold can be dynamically adjusted according to the test conditions, thereby adapting to the dynamic requirements of system accuracy in different test scenarios (such as different speeds and different areas).

[0070] In this embodiment, the testing device can determine whether the eye-tracking system is qualified by comparing the relative angle error with a preset dynamic error threshold. For example, when the relative angle error... ≤Preset dynamic error threshold If the eye-tracking system passes the test, it is considered to have passed; otherwise, it is considered to have failed.

[0071] Furthermore, to better adapt to the accuracy requirements of eye-tracking systems in different scenarios, the following steps are included before step S42: Step S421: Determine the angular velocity between the first test point and the second test point.

[0072] It should be understood that the angular velocity mentioned above can be the rate of change of the angle of rotation of the motor at the first test point and the second test point, which can reflect the speed of rotation of the motor during the test.

[0073] Furthermore, to accurately calculate the time interval between the two test points and provide an accurate time reference for the calculation of angular velocity, ensuring that the calculation results are more reliable, step S421 in this embodiment includes: acquiring the first acquisition time of the first test point and the second acquisition time of the second test point; determining the test time interval between the first test point and the second test point based on the first acquisition time and the second acquisition time; and determining the angular velocity between the first test point and the second test point based on the theoretical relative angle difference of the motor and the test time interval.

[0074] It is understood that the aforementioned first acquisition time can be the time when the eye-tracking system or motor control system arrives at the first test point and acquires data; correspondingly, the aforementioned second acquisition time can be the time when the eye-tracking system or motor control system arrives at the second test point and acquires data. In this embodiment, both the first acquisition time and the second acquisition time can be a timestamp.

[0075] It is also understood that the aforementioned test time interval can be the time interval between collecting data from the first test point and collecting data from the second test point, that is, the time difference between the first acquisition time and the second acquisition time. Specifically, if the first acquisition time is... The second collection time is Then the test time interval is... .

[0076] In this embodiment, the angular velocity between the first test point and the second test point The relative angle difference can be obtained through the motor theory Divide by the test interval The calculation yields the following formula:

[0077] Step S422: Determine the preset dynamic error threshold based on the angular velocity, the basic static threshold, and the velocity sensitivity coefficient.

[0078] It should be noted that the aforementioned basic static threshold can be a pre-set, fixed error tolerance range, which can be used to evaluate the performance of the eye-tracking system under low-speed or static conditions. In practical use, the basic static threshold can be pre-set according to the accuracy requirements of the eye-tracking system and experimental conditions. For example, if the eye-tracking system requires an error of no more than 2° at low speeds, then the basic static threshold can be set to 2°.

[0079] It should also be noted that the aforementioned velocity sensitivity coefficient can be a parameter used to adjust the error threshold as a function of angular velocity, and it determines the degree to which angular velocity affects the error threshold. Generally speaking, the larger the velocity sensitivity coefficient, the greater the influence of angular velocity on the adjustment of the error threshold. In practical applications, the velocity sensitivity coefficient can be determined experimentally or empirically. For example, if experiments show that the error threshold needs to increase more rapidly at high speeds, the value of the velocity sensitivity coefficient can be increased; conversely, if the error threshold is not sensitive to changes in velocity, the value of the velocity sensitivity coefficient can be decreased.

[0080] In practical applications, the preset dynamic error threshold can be calculated based on the angular velocity of the motor at the first and second test points, the basic static threshold, and the speed sensitivity coefficient. By combining the influence of the basic static threshold and angular velocity, it can adapt to the dynamic accuracy requirements of different test scenarios. In this embodiment, the preset dynamic error threshold... The calculation formula can be:

[0081] In the formula, It is the basic static threshold. It is the speed sensitivity coefficient. It is angular velocity.

[0082] Furthermore, this application also proposes a testing device, which includes a motor and a human-eye component, wherein the motor is used to drive the human-eye component to rotate; The device further includes: a memory, a processor, and a test program stored in the memory and executable on the processor, wherein the test program, when executed by the processor, implements the steps of the test method as described above.

[0083] Furthermore, embodiments of this application also propose a storage medium storing a test program, which, when executed by a processor, implements the steps of the test method described above.

[0084] In addition, refer to Figure 5 , Figure 5 This is a structural block diagram of the test device for this application. Figure 5 As shown in the embodiments of this application, a testing apparatus is also proposed, which includes: The data acquisition module 501 is used to control the humanoid eye component to rotate toward the first test point by a motor, and to acquire the first rotation angle of the motor and the first tracking angle obtained by tracking the humanoid eye component through the eye-tracking system. The data acquisition module 501 is used to control the humanoid eye component to rotate toward the second test point through the motor, and to acquire the second rotation angle of the motor and the second tracking angle obtained by tracking the humanoid eye component through the eye-tracking system. The first test point and the second test point are at different positions. Angle difference determination module 502 is used to obtain the eye movement relative angle difference based on the first tracking angle and the second tracking angle, and to obtain the motor theoretical relative angle difference based on the first rotation angle and the second rotation angle; The test module 503 is used to test the eye-tracking system based on the relative angle difference of eye movement and the theoretical relative angle difference of motor, and generate test results of the eye-tracking system.

[0085] In this embodiment, the testing equipment can acquire the first rotation angle of the motor and the first tracking angle obtained by the eye-tracking system when the anthropomorphic eye component rotates towards the first test point. Similarly, when the anthropomorphic eye component rotates towards the second test point, it acquires the second rotation angle of the motor and the second tracking angle obtained by the eye-tracking system. Then, it calculates the relative angle difference based on the first and second tracking angles, and calculates the theoretical relative angle difference of the motor based on the first and second rotation angles. Finally, it tests the eye-tracking system based on the relative angle difference of the eye movement and the theoretical relative angle difference of the motor. Compared to existing testing methods where the calculated angle difference is a mixture of measurement errors from the eye-tracking system and cumulative errors from the motor, this embodiment determines the theoretical relative angle difference of the motor between the first and second test points based on the difference between the first rotation angle measured at the first test point and the second rotation angle measured at the second test point. By testing the eye-tracking system based on the theoretical relative angle difference of the motor and the relative angle difference of the eye movement at different test points, the cumulative effect of the motor's absolute position error can be eliminated, thereby improving the accuracy and reliability of the test results.

[0086] Other embodiments or specific implementations of the testing device described in this application can be found in the above-described method embodiments, and will not be repeated here.

[0087] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or system. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or system that includes that element.

[0088] The sequence numbers of the embodiments in this application are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0089] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as a read-only memory image (ROM) / random access memory (RAM), magnetic disk, optical disk), and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0090] The above are merely preferred embodiments of this application and do not limit the patent scope of this application. Any equivalent structural or procedural transformations made using the content of this application's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of this application.

Claims

1. A testing method, characterized in that, The method is applied to a testing device with a motor and a human-eye-like component, the motor driving the human-eye-like component to rotate, the testing device being connected to smart glasses equipped with an eye-tracking system, and the method comprising: The motor controls the rotation of the bionic eye component toward the first test point, and the first rotation angle of the motor and the first tracking angle obtained by the eye-tracking system are acquired. The motor controls the anthropomorphic eye component to rotate toward the second test point, and the second rotation angle of the motor and the second tracking angle obtained by the eye-tracking system are acquired. The positions of the first test point and the second test point are different. The relative angle difference of eye movement is obtained based on the first tracking angle and the second tracking angle, and the theoretical relative angle difference of the motor is obtained based on the first rotation angle and the second rotation angle; The eye-tracking system is tested based on the relative angle difference of eye movement and the theoretical relative angle difference of motor, and the test results of the eye-tracking system are generated.

2. The method as described in claim 1, characterized in that, The first tracking angle includes a first left-eye tracking angle and a first right-eye tracking angle, and the second tracking angle includes a second left-eye tracking angle and a second right-eye tracking angle; the step of obtaining the relative eye movement angle difference based on the first tracking angle and the second tracking angle includes: A first fused tracking angle is generated based on the first left eye tracking angle and the first right eye tracking angle; A second fusion tracking angle is generated based on the second left-eye tracking angle and the second right-eye tracking angle; The relative eye movement angle difference is obtained based on the first fusion tracking angle and the second fusion tracking angle.

3. The method as described in claim 2, characterized in that, The step of generating the first fused tracking angle based on the first left-eye tracking angle and the first right-eye tracking angle includes: Determine the first confidence level corresponding to the first left eye tracking angle and the second confidence level corresponding to the first right eye tracking angle; The first left-eye tracking angle and the first right-eye tracking angle are fused based on the first confidence level and the second confidence level to generate a first fused tracking angle.

4. The method as described in claim 2, characterized in that, The step of generating a second fused tracking angle based on the second left-eye tracking angle and the second right-eye tracking angle includes: Determine the third confidence level corresponding to the second left eye tracking angle and the fourth confidence level corresponding to the second right eye tracking angle; The second left-eye tracking angle and the second right-eye tracking angle are fused based on the third confidence level and the fourth confidence level to generate a second fused tracking angle.

5. The method according to any one of claims 1 to 4, characterized in that, The step of testing the eye-tracking system based on the relative eye movement angle difference and the theoretical relative motor angle difference, and generating test results for the eye-tracking system, includes: The relative angle error between the first test point and the second test point is determined based on the eye movement relative angle difference and the motor theoretical relative angle difference. The eye-tracking system is tested based on the relative angle error and the preset dynamic error threshold, and the test results of the eye-tracking system are generated.

6. The method as described in claim 5, characterized in that, Before the step of testing the eye-tracking system based on the relative angle error and a preset dynamic error threshold, and generating the test results of the eye-tracking system, the method further includes: Determine the angular velocity between the first test point and the second test point; The preset dynamic error threshold is determined based on the angular velocity, the basic static threshold, and the velocity sensitivity coefficient.

7. The method as described in claim 6, characterized in that, The step of determining the angular velocity between the first test point and the second test point includes: Obtain the first acquisition time of the first test point and the second acquisition time of the second test point; The test time interval between the first test point and the second test point is determined based on the first acquisition time and the second acquisition time. The angular velocity between the first test point and the second test point is determined based on the theoretical relative angle difference of the motor and the test time interval.

8. A testing device, characterized in that, The device includes: The data acquisition module is used to control the rotation of the humanoid eye component towards the first test point by a motor, and to acquire the first rotation angle of the motor and the first tracking angle obtained by tracking the humanoid eye component through the eye-tracking system. The data acquisition module is used to control the humanoid eye component to rotate toward the second test point via the motor, and to acquire the second rotation angle of the motor and the second tracking angle obtained by tracking the humanoid eye component through the eye-tracking system, wherein the first test point and the second test point are at different positions; An angle difference determination module is used to obtain the relative angle difference of eye movement based on the first tracking angle and the second tracking angle, and to obtain the theoretical relative angle difference of the motor based on the first rotation angle and the second rotation angle; The testing module is used to test the eye-tracking system based on the relative angle difference of eye movement and the theoretical relative angle difference of motor, and generate test results for the eye-tracking system.

9. A testing device, characterized in that, The device includes: a motor and a human-eye-like component, wherein the motor is used to drive the human-eye-like component to rotate; The device further includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the test method as described in any one of claims 1 to 7.

10. A storage medium, characterized in that, The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, it implements the steps of the test method as described in any one of claims 1 to 7.

Images