Equipment evaluation method and device, equipment and storage medium

Abstract

The invention discloses an equipment evaluation method and device, equipment and a storage medium. Simulated eyeball movement is controlled according to theoretical positions corresponding to a plurality of continuous test points, and an actual eye movement direction vector during simulated eyeball movement is acquired through to-be-tested eye movement tracking equipment; determining a theoretical rotation matrix between the adjacent test points according to the theoretical position, and determining an actual rotation matrix between the adjacent test points according to the actual eye movement direction vector; and calculating a relative angle error matrix between the theoretical rotation matrix and the actual rotation matrix, and evaluating the to-be-detected eye movement tracking device according to the relative angle error matrix. According to the method and the device, the relative angle error matrix between the theoretical rotation matrix and the actual rotation matrix of the adjacent test points is determined through the relative position difference matrix error calculation mode, so that the to-be-tested eye movement tracking equipment is evaluated according to the relative angle error matrix, and the precision of the to-be-tested eye movement tracking equipment is accurately evaluated.

Description

Technical Field

[0001] This application relates to the field of eye-tracking technology, and in particular to a device evaluation method, apparatus, device, and storage medium. Background Technology

[0002] Eye tracking (ET) technology is becoming increasingly prevalent in the fields of virtual reality (VR), augmented reality (AR), and human-computer interaction. Evaluating the accuracy of ET systems is a crucial aspect of product development and quality control. Traditional methods for testing the accuracy of ET devices primarily rely on simple mechanical devices and absolute position measurements. However, these methods suffer from cumulative mechanical errors, making it difficult to accurately assess the true performance of ET devices. Summary of the Invention

[0003] The main objective of this application is to provide a device evaluation method, apparatus, equipment, and storage medium, which aims to solve the technical problem that traditional measurement methods suffer from mechanical cumulative errors, making it difficult to accurately evaluate the true performance of eye-tracking devices.

[0004] To achieve the above objectives, this application provides a method for evaluating equipment, which includes the following steps: The simulated eye movement is controlled based on the theoretical positions corresponding to multiple consecutive test points, and the actual eye movement direction vector during the simulated eye movement is obtained through the eye movement tracking device under test. The theoretical rotation matrix between adjacent test points is determined based on the theoretical position, and the actual rotation matrix between adjacent test points is determined based on the actual eye movement direction vector. Calculate the relative angle error matrix between the theoretical rotation matrix and the actual rotation matrix, and evaluate the eye-tracking device under test based on the relative angle error matrix.

[0005] Optionally, calculating the relative angle error matrix between the theoretical rotation matrix and the actual rotation matrix, and evaluating the eye-tracking device under test based on the relative angle error matrix, includes: Calculate the relative angle error matrix between the theoretical rotation matrix and the actual rotation matrix, and determine the relative angle error value based on the relative angle error matrix; The eye-tracking device under test is evaluated based on the relative angle error value.

[0006] Optionally, evaluating the eye-tracking device under test based on the relative angle error value includes: The preset dynamic threshold is compared with the relative angle error value to obtain the comparison result. The preset dynamic threshold is a threshold that is dynamically adjusted according to the current test angular velocity. The eye-tracking device under test is evaluated based on the comparison results.

[0007] Optionally, evaluating the eye-tracking device under test based on the comparison results includes: If the relative angle error value is greater than the preset dynamic threshold, the measurement accuracy of the eye-tracking device under test is determined to be unqualified. If the relative angle error value is not greater than the preset dynamic threshold, the measurement accuracy of the eye-tracking device under test is determined to be qualified.

[0008] Optionally, the relative angle error value includes the relative angle error value of the left eye and the relative angle error value of the right eye, and the evaluation of the eye-tracking device under test based on the relative angle error value includes: The relative angle error value of the left eye is compared with the relative angle error of the right eye to obtain the binocular comparison result; The eye-tracking device under test is evaluated based on the binocular comparison results.

[0009] Optionally, evaluating the eye-tracking device under test based on the binocular contrast results includes: If there is a difference in the binocular comparison results, the binocular coordination ability of the eye-tracking device under test is determined to be abnormal. If there is a difference in the comparison results of the two eyes, it is determined that the binocular coordination ability of the eye-tracking device under test is normal.

[0010] Optionally, before controlling the simulated eye movement based on the theoretical positions corresponding to multiple consecutive test points, the method further includes: The movement trajectory of the simulated eyeball is planned based on preset step length, preset speed, and preset spatial range to obtain the stopping position information; The theoretical position corresponding to each test point is determined based on the dwell position information.

[0011] Furthermore, to achieve the above objectives, this application also provides an equipment evaluation apparatus, which includes: The parameter acquisition module is used to control the simulated eye movement based on the theoretical positions corresponding to multiple consecutive test points, and to acquire the actual eye movement direction vector during the simulated eye movement through the eye tracking device under test. The parameter calculation module is used to determine the theoretical rotation matrix between adjacent test points based on the theoretical position, and to determine the actual rotation matrix between adjacent test points based on the actual eye movement direction vector. The device evaluation module is used to calculate the relative angle error matrix between the theoretical rotation matrix and the actual rotation matrix, and to evaluate the eye-tracking device under test based on the relative angle error matrix.

[0012] In addition, to achieve the above objectives, this application also proposes a device evaluation apparatus, which 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 device evaluation method as described above.

[0013] 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 when the computer program is executed by a processor, it implements the steps of the device evaluation method described above.

[0014] One or more technical solutions proposed in this application have at least the following technical effects: This application controls simulated eye movements based on the theoretical positions corresponding to multiple consecutive test points, and obtains the actual eye movement direction vector during simulated eye movements using the eye-tracking device under test. It determines the theoretical rotation matrix between adjacent test points based on the theoretical positions, and the actual rotation matrix between adjacent test points based on the actual eye movement direction vector. It calculates the relative angle error matrix between the theoretical and actual rotation matrices, and evaluates the eye-tracking device under test based on this relative angle error matrix. Compared to traditional measurement methods that suffer from accumulated mechanical errors, making it difficult to accurately evaluate the true performance of eye-tracking devices, this application determines the relative angle error matrix between the theoretical and actual rotation matrices of adjacent test points using a relative position difference matrix error calculation method. This allows for the evaluation of the eye-tracking device under test based on the relative angle error matrix, achieving accurate evaluation of the device's accuracy and effectively eliminating accumulated errors in the mechanical system. Attached Figure Description

[0015] 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.

[0016] 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.

[0017] Figure 1 This is a flowchart illustrating the first embodiment of the equipment evaluation method of this application. Figure 2This is a flowchart illustrating the second embodiment of the equipment evaluation method of this application. Figure 3 This is a flowchart illustrating the third embodiment of the equipment evaluation method of this application; Figure 4 This is a schematic diagram of the module structure of the equipment evaluation device according to an embodiment of this application; Figure 5 This is a schematic diagram of the hardware operating environment involved in the device evaluation method in this application embodiment.

[0018] The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0019] It should be understood that the specific embodiments described herein are for illustrative purposes only and are not intended to limit the scope of this application.

[0020] To better understand the technical solution of this application, a detailed description will be provided below in conjunction with the accompanying drawings and specific implementation methods.

[0021] The main solution of this application embodiment is as follows: This application controls simulated eye movement based on the theoretical positions corresponding to multiple consecutive test points, and obtains the actual eye movement direction vector when simulating eye movement through the eye tracking device under test; determines the theoretical rotation matrix between adjacent test points based on the theoretical position, and determines the actual rotation matrix between adjacent test points based on the actual eye movement direction vector; calculates the relative angle error matrix between the theoretical rotation matrix and the actual rotation matrix, and evaluates the eye tracking device under test based on the relative angle error matrix.

[0022] In this embodiment, for ease of description, the following description uses a computing service device as the execution subject.

[0023] Traditional measurement methods suffer from mechanical cumulative errors, making it difficult to accurately assess the true performance of eye-tracking devices.

[0024] This application provides a solution that determines the relative angle error matrix between the theoretical rotation matrix and the actual rotation matrix of adjacent test points by calculating the relative position difference matrix error. The eye-tracking device under test is then evaluated based on the relative angle error matrix, achieving an accurate evaluation of the accuracy of the eye-tracking device under test and effectively eliminating the cumulative error of the mechanical system.

[0025] As can be seen from the above embodiments, this application controls simulated eye movements based on the theoretical positions corresponding to multiple consecutive test points, and obtains the actual eye movement direction vector during simulated eye movements through the eye-tracking device under test; it determines the theoretical rotation matrix between adjacent test points based on the theoretical positions, and determines the actual rotation matrix between adjacent test points based on the actual eye movement direction vector; it calculates the relative angle error matrix between the theoretical rotation matrix and the actual rotation matrix, and evaluates the eye-tracking device under test based on the relative angle error matrix. Compared with traditional measurement methods that suffer from mechanical cumulative errors, making it difficult to accurately evaluate the true performance of eye-tracking devices, this application determines the relative angle error matrix between the theoretical rotation matrix and the actual rotation matrix of adjacent test points through the relative position difference matrix error calculation method, thereby evaluating the eye-tracking device under test based on the relative angle error matrix, achieving accurate evaluation of the accuracy of the eye-tracking device under test, and effectively eliminating the cumulative errors of the mechanical system.

[0026] It should be noted that the executing entity in this embodiment can be a computing service device with data processing, network communication, and program execution functions, such as a tablet computer, personal computer, or mobile phone, or an electronic device capable of performing the above functions, including a device evaluation system. The following description uses a computer as an example to illustrate this embodiment and the subsequent embodiments.

[0027] Based on this, embodiments of this application provide a device evaluation method, referring to... Figure 1 , Figure 1 This is a flowchart illustrating the first embodiment of the equipment evaluation method of this application.

[0028] In this embodiment, the equipment evaluation method includes steps S10 to S30: Step S10: Control the simulated eye movement according to the theoretical positions corresponding to multiple consecutive test points, and obtain the actual eye movement direction vector when the simulated eye movement is performed through the eye movement tracking device under test.

[0029] It should be noted that this application pre-constructs an equipment evaluation system, which includes a high-precision servo motor system and a backlash-free gear system, a physiological simulation artificial eye (simulating eyeballs including the left and right eyes), a modular head shell, and a control unit. The servo motors in the high-precision servo motor system can be high-resolution, low-backlash dual-axis independent servo motors, controlling the horizontal (yaw) and vertical (pitch) movements of the left and right eyes respectively. The physiological simulation artificial eye has adjustable parameters such as pupil diameter, iris texture, and corneal curvature, which can simulate the physiological characteristics of different human eyes. Furthermore, all geometric and optical parameters of the artificial eye (such as eyeball center, pupil center, and visual axis direction) can be preset. The parameters of the physiological simulation artificial eye, which are all adjustable and precisely known, can be used as virtual calibration parameters input into the algorithm of the eye-tracking device under test to isolate the measurement error of the device itself and effectively separate the measurement error of the eye-tracking device under test from the motion error of the external mechanical system. The modular head shell adopts a modular and adjustable head shell structure, which can quickly and accurately fix different models of eye-tracking devices under test (such as VR / AR headsets). The rapid positioning and locking mechanism ensures that the relative positional accuracy between the tested device and the artificial eye system is at the micrometer level.

[0030] Understandably, the simulated eyeball includes a simulated left eye and a simulated right eye. This application calibrates the eye-tracking device under test by injecting the pre-set parameters corresponding to the physiological simulation artificial eye into the eye-tracking device under test through a software interface, thereby obtaining the eye-tracking device after parameter calibration, and then testing the eye-tracking device after parameter calibration, thus isolating the measurement error of the eye-tracking device under test itself.

[0031] In practice, simulated eye movements are controlled based on the theoretical positions corresponding to multiple consecutive test points, and images of simulated eye movements are collected by the eye-tracking device under test. The actual eye movement direction vector during simulated eye movements is determined based on the collected images.

[0032] It should be understood that, in order to achieve the accuracy assessment of the eye-tracking device, the theoretical trajectory of eye movement is planned, and simulated eye movement is driven according to the theoretical trajectory. Before step S10, the method further includes: planning the movement trajectory of the simulated eye based on a preset step length, a preset speed, and a preset spatial range to obtain the dwell position information; and determining the theoretical position corresponding to each test point according to the dwell position information.

[0033] Among them, the preset step size refers to the theoretical angular increment of the servo motor that controls the simulated eye movement between two adjacent test points. The smaller the step size, the denser the test points. The preset speed refers to the angular velocity of the simulated eye moving from one test point to the next. The preset spatial range refers to the range of movement of the simulated eye in the horizontal (Yaw) and vertical (Pitch) directions, such as ±45° horizontally and ±30° vertically. The number of test points can be determined by the step size and spatial range.

[0034] It should be noted that a two-dimensional angular position matrix can be generated based on the preset step size and spatial range. Each position is a combination of (yaw and pitch). Alternatively, a continuous motion trajectory can be planned, and samples can be taken at certain time intervals (or spatial intervals) to obtain a series of resting positions. The theoretical position of the test point can then be determined based on the angular position of these resting positions. For comprehensive testing, the simulated eyeball will rest at each test point for a period of time so that the eye-tracking device can take measurements. The theoretical position refers to the angular position (yaw and pitch) that the simulated eyeball should reach at each test point. This theoretical position can be determined by a motion planning algorithm and sent to the servo motor control system, which will then drive the simulated eyeball to this position.

[0035] In practice, the time-angle trajectory of eye movement is planned by preset step size (angle increment), preset speed (angular velocity), and preset spatial range (angle boundary), the dwell position information is output, and these angle positions are converted into poses in three-dimensional space based on the dwell position information to obtain the theoretical position corresponding to each test point.

[0036] Step S20: Determine the theoretical rotation matrix between adjacent test points based on the theoretical position, and determine the actual rotation matrix between adjacent test points based on the actual eye movement direction vector.

[0037] It should be noted that adjacent test points refer to two preset resting positions that are adjacent in time or space when the simulated eyeball moves continuously along a preset trajectory driven by a high-precision servo motor during the test. Two sets of data are simultaneously collected at each test point, including the theoretical position and the eye movement direction vector calculated and output by the eye-tracking device based on the collected images.

[0038] Understandably, the theoretical rotation matrix between adjacent test points refers to the theoretical relative rotation matrix between two adjacent test points obtained by transforming the theoretical positions on the adjacent test points, while the actual rotation matrix between adjacent test points refers to the actual relative rotation matrix between two adjacent test points obtained by transforming the actual eye movement direction vectors corresponding to the two adjacent test points.

[0039] In the specific implementation, at each test point Collection: Theoretical Location and the eye movement direction vector output by the eye-tracking device under test Calculate the motor in two adjacent positions and The theoretical relative rotation matrix is ​​obtained by comparing the theoretical rotation matrices between the two.

[0040] ; in, It is determined by the theoretical position (angle) of the motor. The resulting rotation matrix. express -1 The transpose (for a rotation matrix, the transpose equals the inverse). The theoretical position. It can be represented as =(θ y ,θ p θy: Yaw angle, rotation about the Z-axis; θp: Pitch angle, rotation about the X-axis; assuming the roll angle is 0 to conform to the physiological characteristics of the human eye, the yaw angle θ in the theoretical angular position is... y and pitch angle θ p First rotate θ around the X-axis (pitch axis) p Then rotate θ around the Z-axis (yaw axis). y Calculate the corresponding 3D rotation matrix according to the order of eye movements, and combine the rotation matrices. For the natural order of human eye movements (first look up / look down, then turn left / turn right), the combined rotation matrix is: R motor,k =R z (θ y ) R x (θ p ).

[0041] Based on the eye movement direction vector measured by the eye tracking device under test arrive Construct the actual relative rotation matrix. This matrix The actual relative rotation matrix can be calculated from the cross product and dot product of two vectors using Rodrigues' rotation formula or quaternion methods. The calculation formula is as follows: .

[0042] Step S30: Calculate the relative angle error matrix between the theoretical rotation matrix and the actual rotation matrix, and evaluate the eye-tracking device under test based on the relative angle error matrix.

[0043] It should be noted that the relative rotation measured by eye tracking is compared with the relative rotation in motor theory to determine the relative angle error matrix, and the eye tracking device under test is evaluated based on the relative angle error matrix.

[0044] Furthermore, step S30 further includes: calculating the relative angle error matrix between the theoretical rotation matrix and the actual rotation matrix, and determining the relative angle error value based on the relative angle error matrix; and evaluating the eye-tracking device under test based on the relative angle error value.

[0045] It should be noted that in the differential error calculation, the theoretical relative rotation matrix is ​​compared with the actual measured relative rotation matrix, and the relative rotation matrix ΔR error,k Description from test point k 1 to test point k k The incremental rotation is calculated using the following formula: ΔR error,k =ΔR et,k ΔR motor,kT ; Where, ΔR et,k ΔR is the relative rotation matrix calculated from the measurement vectors of the eye-tracking (ET) device. motor,kT : The relative rotation matrix calculated from the theoretical position.

[0046] By rotating the relative angle error matrix Converted into a single rotation angle The calculation formula is as follows: ; The differential matrix measurement method completely eliminates the cumulative effect of the motor's absolute position error, making... It only reflects the measurement error of the ET device within adjacent movement steps, which greatly improves the authenticity and reliability of the test.

[0047] This embodiment controls simulated eye movements based on the theoretical positions corresponding to multiple consecutive test points, and obtains the actual eye movement direction vector during simulated eye movements using the eye-tracking device under test. It determines the theoretical rotation matrix between adjacent test points based on the theoretical positions, and the actual rotation matrix between adjacent test points based on the actual eye movement direction vector. The relative angle error matrix between the theoretical and actual rotation matrices is calculated, and the eye-tracking device under test is evaluated based on this relative angle error matrix. Compared to traditional measurement methods that suffer from accumulated mechanical errors, making it difficult to accurately evaluate the true performance of eye-tracking devices, this embodiment determines the relative angle error matrix between the theoretical and actual rotation matrices of adjacent test points using a relative position difference matrix error calculation method. This allows for the evaluation of the eye-tracking device under test based on the relative angle error matrix, achieving accurate evaluation of the device's accuracy and effectively eliminating accumulated errors in the mechanical system.

[0048] Based on the above Figure 1 The first embodiment shown illustrates a second embodiment of the device evaluation method of this application; refer to Figure 2 , Figure 2 This is a flowchart illustrating the second embodiment of the equipment evaluation method of this application. Based on the first embodiment of this application, the same or similar content as the first embodiment described above can be referred to the above description and will not be repeated hereafter.

[0049] In this embodiment, step S30 further includes: Step S301: Compare the preset dynamic threshold with the relative angle error value to obtain the comparison result.

[0050] It should be noted that the preset dynamic threshold is dynamically adjusted based on the current test angular velocity. Under high-speed motion, the allowable error can be appropriately relaxed because tracking is more difficult at high speeds. This is achieved by designing a velocity factor function f(V). k This function changes with V. k The rate of increase increases with the rate of increase (but the rate of increase may gradually slow down or increase linearly, depending on practical experience or theoretical models). The dynamic threshold is obtained by setting a static threshold T_static and combining the static threshold with the rate factor. For example, =T static *f(V k ).or =T static +g(V k ), where g(V) k ) is a speed-related compensation term.

[0051] Understandably, a static threshold T_static (e.g., 0.5 degrees) can be set, and the angular velocity V of the current test point k can be calculated in real time during the test. k (Angular velocity of motion from point k-1 to point k). According to predetermined rules, V k A velocity factor is calculated. The dynamic threshold is obtained by combining the static threshold with the velocity factor. When evaluating the error at each test point... When, it is compared with the dynamic threshold. The comparison process yields results that can be used to assess equipment accuracy. The evaluation criteria based on dynamic thresholds can be intelligently adjusted according to the test scenario to make the evaluation results more consistent with actual application requirements.

[0052] Step S302: Evaluate the eye-tracking device under test based on the comparison results.

[0053] It should be noted that the accuracy evaluation result of the eye-tracking device under test is determined by comparing the relative angle error value with the preset dynamic threshold and based on the comparison result.

[0054] Furthermore, step S302 further includes: if the relative angle error value is greater than a preset dynamic threshold, the measurement accuracy of the eye-tracking device under test is determined to be unqualified; if the relative angle error value is not greater than the preset dynamic threshold, the measurement accuracy of the eye-tracking device under test is determined to be qualified.

[0055] It should be noted that, based on the test angular velocity Dynamically adjust the allowable error threshold To improve the adaptability of the test, if the relative angle error value is greater than the preset dynamic threshold, the measurement accuracy of the eye-tracking device under test is deemed unqualified; if the relative angle error value is not greater than the preset dynamic threshold, the measurement accuracy of the eye-tracking device under test is deemed qualified.

[0056] This embodiment controls simulated eye movement based on the theoretical positions corresponding to multiple consecutive test points, and obtains the actual eye movement direction vector during simulated eye movement through the eye-tracking device under test. It determines the theoretical rotation matrix between adjacent test points based on the theoretical positions, and the actual rotation matrix between adjacent test points based on the actual eye movement direction vector. A comparison is made between the relative angle error value of a preset dynamic threshold, where the preset dynamic threshold is dynamically adjusted based on the current test angular velocity. The eye-tracking device under test is then evaluated based on the comparison results. Compared to traditional measurement methods that suffer from accumulated mechanical errors, making it difficult to accurately evaluate the true performance of eye-tracking devices, this embodiment uses a relative position difference matrix error calculation method to determine the relative angle error matrix between the theoretical and actual rotation matrices of adjacent test points. This allows for the evaluation of the eye-tracking device under test based on the preset dynamic threshold and the relative angle error matrix, achieving accurate evaluation of the device's precision and effectively eliminating accumulated errors in the mechanical system.

[0057] Based on the above Figure 1 The first embodiment shown illustrates a third embodiment of the equipment evaluation method of this application; refer to Figure 3 , Figure 3 This is a flowchart illustrating the second embodiment of the equipment evaluation method of this application. Based on the first embodiment of this application, in the third embodiment, the content that is the same as or similar to the first embodiment described above can be referred to the above description and will not be repeated hereafter.

[0058] In this embodiment, the relative angle error value includes the relative angle error value of the left eye and the relative angle error value of the right eye, and step S30 further includes: Step S301': Compare the relative angle error value of the left eye with the relative angle error of the right eye to obtain the comparison result of both eyes.

[0059] It should be noted that at each test point Data collection: Theoretical position of the left eye and the left eye movement direction vector output by the eye-tracking device Calculate the motor in two adjacent positions and The theoretical relative rotation matrix is ​​obtained by comparing the theoretical rotation matrices between the two.

[0060] ; in, It refers to the theoretical position (angle) of the left eye. The resulting rotation matrix. express The transpose (for a rotation matrix, the transpose equals the inverse). The theoretical position. It can be represented as =(θ y,L ,θ p,L ), θ y,L Yaw angle (θ) is the angle of rotation about the Z-axis. p,L Pitch angle, rotated around the X-axis, assuming roll angle is 0, consistent with human eye physiology, and the yaw angle θ in the theoretical angular position. y,L and pitch angle θ p,L First rotate θ around the X-axis (pitch axis) p,L Then rotate θ around the Z-axis (yaw axis). y,L Calculate the corresponding 3D rotation matrix according to the order of movement, and combine the rotation matrices. For the natural order of human eye movement (first look up / look down, then turn left / turn right), the combined rotation matrix is: =R z (θ y,L ) R x (θ p,L ).

[0061] Based on the eye movement direction vector measured by the eye-tracking device arrive Construct the actual relative rotation matrix. This matrix It can be calculated from the cross product and dot product of two vectors using Rodrigues' rotation formula or quaternion methods.

[0062] .

[0063] In the differential error calculation, the theoretical relative rotation matrix of the left eye is compared with the actual measured relative rotation matrix of the left eye. The left eye relative rotation matrix ΔR error,k,L Describe the left eye from the test point k The incremental rotation from point 1 to test point k is calculated using the following formula: ΔR error,k,L =ΔR et,k,L ΔR motor,kT,L ; Where, ΔR et,k,L ΔR: The left eye relative rotation matrix calculated from the measurement vectors of the eye-tracking device. motor,kT,L : The relative rotation matrix of the left eye calculated from the theoretical position.

[0064] By rotating the left eye relative angle error matrix Converted to a single left eye rotation angle The calculation formula is as follows: ; Similarly, the left and right eyes are two parallel, symmetrical, and non-interfering computational pipelines. The algorithm kernel is exactly the same; based on the above calculation method, the rotation matrix of the relative angle error of the right eye is obtained. Converted to a single right eye rotation angle The relative angle error value of the left eye relative angle error with the right eye Compare the results, and then determine the binocular coordination ability based on the comparison results.

[0065] In its specific implementation, this application can also analyze the error curves of the left and right eyes separately to determine whether there is a difference in the tracking accuracy of the eye-tracking device for a single eye. For example, it may be found that the overall accuracy of the left eye is better than that of the right eye, which may be related to the position or calibration of the internal camera of the device.

[0066] Step S302': Evaluate the eye-tracking device under test based on the binocular comparison results.

[0067] It should be noted that the binocular coordination ability of the eye-tracking device under test is evaluated by comparing the results of both eyes, and the evaluation results are obtained.

[0068] Furthermore, step S302' further includes: if the binocular comparison result shows a difference, then the binocular coordination ability of the eye-tracking device under test is determined to be abnormal; if the binocular comparison result shows a difference, then the binocular coordination ability of the eye-tracking device under test is determined to be normal.

[0069] It should be noted that the relative angle error value of the left eye is determined by... relative angle error with the right eye The presence of differences is used to determine the binocular coordination ability of the eye-tracking device under test. If there are differences in the binocular comparison results, the binocular coordination ability of the eye-tracking device under test is determined to be abnormal; if there are differences in the binocular comparison results, the binocular coordination ability of the eye-tracking device under test is determined to be normal.

[0070] This embodiment controls simulated eye movements based on the theoretical positions corresponding to multiple consecutive test points, and obtains the actual eye movement direction vector during simulated eye movements using the eye-tracking device under test. It determines the theoretical rotation matrix between adjacent test points based on the theoretical positions, and the actual rotation matrix between adjacent test points based on the actual eye movement direction vector. The relative angle error value of the left eye is compared with that of the right eye to obtain a binocular comparison result, which is then used to evaluate the eye-tracking device under test. Compared to traditional measurement methods that suffer from mechanical cumulative errors, making it difficult to accurately evaluate the true performance of eye-tracking devices, this embodiment uses a relative position difference matrix error calculation method to determine the relative angle error matrix between the theoretical rotation matrix and the actual rotation matrix of adjacent test points for both eyes. This allows for the evaluation of binocular coordination capability of the eye-tracking device under test based on the relative angle error matrix, achieving an accurate evaluation of the binocular coordination capability and effectively eliminating the cumulative errors of the mechanical system.

[0071] This application also provides an equipment evaluation apparatus, please refer to... Figure 4 The equipment evaluation device includes: The parameter acquisition module 10 is used to control the simulated eye movement according to the theoretical positions corresponding to multiple consecutive test points, and to acquire the actual eye movement direction vector when the simulated eye movement is performed through the eye movement tracking device under test. The parameter calculation module 20 is used to determine the theoretical rotation matrix between adjacent test points based on the theoretical position, and to determine the actual rotation matrix between adjacent test points based on the actual eye movement direction vector. The device evaluation module 30 is used to calculate the relative angle error matrix between the theoretical rotation matrix and the actual rotation matrix, and to evaluate the eye-tracking device under test based on the relative angle error matrix.

[0072] Furthermore, the device evaluation module 30 is also used to calculate the relative angle error matrix between the theoretical rotation matrix and the actual rotation matrix, and determine the relative angle error value based on the relative angle error matrix; and evaluate the eye-tracking device under test based on the relative angle error value.

[0073] Furthermore, the device evaluation module 30 is also used to compare the preset dynamic threshold with the relative angle error value to obtain a comparison result, wherein the preset dynamic threshold is a threshold that is dynamically adjusted according to the current test angular velocity; and to evaluate the eye-tracking device under test based on the comparison result.

[0074] Furthermore, the device evaluation module 30 is also used to determine that the measurement accuracy of the eye-tracking device under test is unqualified if the relative angle error value is greater than the preset dynamic threshold; and to determine that the measurement accuracy of the eye-tracking device under test is qualified if the relative angle error value is not greater than the preset dynamic threshold.

[0075] Furthermore, the relative angle error value includes the relative angle error value of the left eye and the relative angle error value of the right eye. The device evaluation module 30 is also used to compare the relative angle error value of the left eye with the relative angle error value of the right eye to obtain a binocular comparison result; and to evaluate the eye-tracking device under test based on the binocular comparison result.

[0076] Furthermore, the device evaluation module 30 is also used to determine that the binocular coordination ability of the eye-tracking device under test is abnormal if the binocular comparison result is different; and to determine that the binocular coordination ability of the eye-tracking device under test is normal if the binocular comparison result is different.

[0077] Furthermore, the device evaluation module 30 is also used to plan the movement trajectory of the simulated eyeball based on a preset step length, preset speed, and preset spatial range to obtain dwell position information; and to determine the theoretical position corresponding to each test point based on the dwell position information.

[0078] The device evaluation apparatus provided in this application, employing the device evaluation method described in the above embodiments, can solve the technical problem that traditional measurement methods suffer from mechanical cumulative errors, making it difficult to accurately evaluate the true performance of eye-tracking devices. Compared with the prior art, the beneficial effects of the device evaluation apparatus provided in this application are the same as those of the device evaluation method described in the above embodiments, and other technical features in the device evaluation apparatus are the same as those disclosed in the methods described in the above embodiments, and will not be repeated here.

[0079] This application provides a device evaluation apparatus, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, which are executed by the at least one processor to enable the at least one processor to perform the device evaluation method described in the first embodiment above.

[0080] The following is for reference. Figure 5The diagram illustrates a structural schematic of a device evaluation apparatus suitable for implementing embodiments of this application. The device evaluation apparatus in the embodiments of this application may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Description), PMPs (Portable Media Players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 4 The device evaluation device shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of this application.

[0081] like Figure 5 As shown, the device evaluation device may include a processing unit 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 1002 or a program loaded from a storage device 1003 into a random access memory (RAM) 1004. The RAM 1004 also stores various programs and data required for the operation of the device evaluation device. The processing unit 1001, ROM 1002, and RAM 1004 are interconnected via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to the I / O interface 1006: input devices 1007 including, for example, a touchscreen, touchpad, keyboard, mouse, image sensor, microphone, accelerometer, gyroscope, etc.; output devices 1008 including, for example, a liquid crystal display (LCD), speaker, vibrator, etc.; storage devices 1003 including, for example, magnetic tape, hard disk, etc.; and communication devices 1009. Communication device 1009 allows the device evaluation device to communicate wirelessly or wiredly with other devices to exchange data. Although the figure shows a device evaluation device with various systems, it should be understood that implementation or possession of all the systems shown is not required. More or fewer systems may be implemented alternatively.

[0082] Specifically, according to the embodiments disclosed in this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device, or installed from storage device 1003, or installed from ROM 1002. When the computer program is executed by processing device 1001, it performs the functions defined in the methods of the embodiments disclosed in this application.

[0083] The device evaluation device provided in this application, employing the device evaluation method described in the above embodiments, can solve the technical problem that traditional measurement methods suffer from mechanical cumulative errors, making it difficult to accurately evaluate the true performance of eye-tracking devices. Compared with the prior art, the beneficial effects of the device evaluation device provided in this application are the same as those of the device evaluation method provided in the above embodiments, and other technical features of this device evaluation device are the same as those disclosed in the previous embodiment method, and will not be repeated here.

[0084] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any suitable manner in one or more embodiments or examples.

[0085] The above are merely specific embodiments of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0086] This application provides a computer-readable storage medium having computer-readable program instructions (i.e., a computer program) stored thereon, the computer-readable program instructions being used to execute the device evaluation method described in the above embodiments.

[0087] The computer-readable storage medium provided in this application may be, for example, a USB flash drive, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, system, or device. The program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.

[0088] The aforementioned computer-readable storage medium may be included in the device evaluation device; or it may exist independently and not assembled into the device evaluation device.

[0089] The aforementioned computer-readable storage medium carries one or more programs that, when executed by the device evaluation device, cause the device evaluation device to: control simulated eye movements based on the theoretical positions corresponding to multiple consecutive test points, and obtain the actual eye movement direction vector during simulated eye movements using the eye-tracking device under test; determine the theoretical rotation matrix between adjacent test points based on the theoretical positions, and determine the actual rotation matrix between adjacent test points based on the actual eye movement direction vector; calculate the relative angle error matrix between the theoretical rotation matrix and the actual rotation matrix, and evaluate the eye-tracking device under test based on the relative angle error matrix.

[0090] Computer program code for performing the operations of this application can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a Local Area Network (LAN) or a Wide Area Network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0091] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0092] The modules described in the embodiments of this application can be implemented in software or hardware. The names of the modules do not necessarily limit the functionality of the unit itself.

[0093] The readable storage medium provided in this application is a computer-readable storage medium that stores computer-readable program instructions (i.e., a computer program) for executing the above-described device evaluation method, and is capable of solving the technical problem of device evaluation. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as the beneficial effects of the device evaluation method provided in the above embodiments, and will not be repeated here.

[0094] The above are only some embodiments of this application and do not limit the patent scope of this application. All equivalent structural transformations made under the technical concept of this application and using the contents of the specification and drawings of this application, or direct / indirect applications in other related technical fields, are included in the patent protection scope of this application.

Claims

1. A method for evaluating equipment, characterized in that, The method includes: The simulated eye movement is controlled based on the theoretical positions corresponding to multiple consecutive test points, and the actual eye movement direction vector during the simulated eye movement is obtained through the eye movement tracking device under test. The theoretical rotation matrix between adjacent test points is determined based on the theoretical position, and the actual rotation matrix between adjacent test points is determined based on the actual eye movement direction vector. Calculate the relative angle error matrix between the theoretical rotation matrix and the actual rotation matrix, and evaluate the eye-tracking device under test based on the relative angle error matrix.

2. The equipment evaluation method as described in claim 1, characterized in that, The step of calculating the relative angle error matrix between the theoretical rotation matrix and the actual rotation matrix, and evaluating the eye-tracking device under test based on the relative angle error matrix, includes: Calculate the relative angle error matrix between the theoretical rotation matrix and the actual rotation matrix, and determine the relative angle error value based on the relative angle error matrix; The eye-tracking device under test is evaluated based on the relative angle error value.

3. The equipment evaluation method as described in claim 2, characterized in that, The evaluation of the eye-tracking device under test based on the relative angle error value includes: The preset dynamic threshold is compared with the relative angle error value to obtain the comparison result. The preset dynamic threshold is a threshold that is dynamically adjusted according to the current test angular velocity. The eye-tracking device under test is evaluated based on the comparison results.

4. The equipment evaluation method as described in claim 3, characterized in that, The evaluation of the eye-tracking device under test based on the comparison results includes: If the relative angle error value is greater than the preset dynamic threshold, the measurement accuracy of the eye-tracking device under test is determined to be unqualified. If the relative angle error value is not greater than the preset dynamic threshold, the measurement accuracy of the eye-tracking device under test is determined to be qualified.

5. The equipment evaluation method as described in claim 2, characterized in that, The relative angle error values ​​include the relative angle error values ​​for the left eye and the right eye. The evaluation of the eye-tracking device under test based on the relative angle error values ​​includes: The relative angle error value of the left eye is compared with the relative angle error of the right eye to obtain the binocular comparison result; The eye-tracking device under test is evaluated based on the binocular comparison results.

6. The equipment evaluation method as described in claim 5, characterized in that, The evaluation of the eye-tracking device under test based on the binocular contrast results includes: If there is a difference in the binocular comparison results, the binocular coordination ability of the eye-tracking device under test is determined to be abnormal. If there is a difference in the comparison results of the two eyes, it is determined that the binocular coordination ability of the eye-tracking device under test is normal.

7. The equipment evaluation method according to any one of claims 1 to 6, characterized in that, Before controlling the simulated eye movement based on the theoretical positions corresponding to multiple consecutive test points, the method further includes: The movement trajectory of the simulated eyeball is planned based on preset step length, preset speed and preset spatial range to obtain the stopping position information; The theoretical position corresponding to each test point is determined based on the dwell position information.

8. An equipment evaluation device, characterized in that, The device includes: The parameter acquisition module is used to control the simulated eye movement based on the theoretical positions corresponding to multiple consecutive test points, and to acquire the actual eye movement direction vector during the simulated eye movement through the eye tracking device under test. The parameter calculation module is used to determine the theoretical rotation matrix between adjacent test points based on the theoretical position, and to determine the actual rotation matrix between adjacent test points based on the actual eye movement direction vector. The device evaluation module is used to calculate the relative angle error matrix between the theoretical rotation matrix and the actual rotation matrix, and to evaluate the eye-tracking device under test based on the relative angle error matrix.

9. An equipment evaluation device, characterized in that, The device evaluation device includes: a memory, a processor, and a device evaluation program stored in the memory and executable on the processor, the device evaluation program being configured to implement the device evaluation method as described in any one of claims 1 to 7.

10. A storage medium, characterized in that, The storage medium stores a device evaluation program, which, when executed by a processor, implements the steps of the device evaluation method as described in any one of claims 1 to 7.

Images