Eyeball tracking method and device, sight line detection method and device, equipment and storage medium

Abstract

The embodiment of the invention discloses an eyeball tracking method and device, a sight line detection method and device, equipment and a storage medium. Comprises: acquiring an initial tracking signal; acquiring a to-be-tracked signal; wherein the to-be-tracked signal is a signal acquired after the initial tracking signal; performing differential comparison on the initial tracking signal and the to-be-tracked signal, and determining a differential comparison result; determining an eyeball tracking mode corresponding to the to-be-tracked signal according to the difference comparison result, and determining an eyeball tracking result of the to-be-tracked signal; wherein different difference comparison results correspond to different eyeball tracking mode calculation amounts. According to the technical scheme provided by the embodiment of the invention, an eyeball tracking calculation mode with a relatively large calculation amount does not need to be adopted for the to-be-tracked signals obtained at all moments during eyeball tracking, so that the calculation amount and the system power consumption in an operation process are reduced on the basis of ensuring the accuracy of an eyeball tracking result of high-frame-rate equipment; and the data operation speed and the equipment operation stability are improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of eye tracking, and in particular to an eye tracking method, a gaze detection method, a device, an apparatus and a storage medium. BACKGROUND

[0002] Eye tracking, also known as fixation point tracking, is a technology that uses sensors to capture and extract eye feature information, measure eye movement, and estimate the direction of the line of sight or the position of the eye fixation point. With the popularization and use of eye tracking technology, the frame rates of the electronic devices to which the eye tracking technology is adapted are different.

[0003] Currently, when applying the eye tracking technology, each frame of eye image collected by the electronic devices needs to be subjected to feature point recognition and eye tracking calculation. For electronic devices with a high frame rate, such as high-frame-rate cameras, detecting the fixation point and / or the fixation direction for each frame of data will consume a large amount of computing resources, especially the higher the frame rate, the more computing resources are consumed, which increases the power consumption of the device, and the stability of the device in the high-power working state is correspondingly reduced, affecting the user experience. SUMMARY

[0004] The present application provides an eye tracking method, a tracking device, an apparatus and a storage medium, which reduces the data calculation amount and data processing complexity in the eye tracking process and improves the data operation speed.

[0005] In a first aspect, an embodiment of the present application provides an eye tracking method, comprising:

[0006] obtaining an initial tracking signal;

[0007] obtaining a to-be-tracked signal; wherein the to-be-tracked signal is a signal collected after the initial tracking signal;

[0008] differentially comparing the initial tracking signal and the to-be-tracked signal to determine a differential comparison result;

[0009] determining an eye tracking mode corresponding to the to-be-tracked signal according to the differential comparison result, and determining an eye tracking result of the to-be-tracked signal;

[0010] wherein the different differential comparison results correspond to different eye tracking modes with different calculation amounts.

[0011] In a second aspect, an embodiment of the present application further provides a gaze detection method, comprising:

[0012] calculating an eye tracking result of a left eye to-be-tracked signal based on the eye tracking method provided in any of the above embodiments;

[0013] The eye tracking method provided in any of the above embodiments is used to calculate the eye tracking result of the right eye to-be-tracked signal.

[0014] The gaze detection result is determined according to the eye tracking result of the left eye to-be-tracked signal and the eye tracking result of the right eye to-be-tracked signal.

[0015] In a third aspect, an embodiment of the present application further provides an eye tracking device, comprising:

[0016] The first signal acquisition module is configured to acquire an initial tracking signal.

[0017] The second signal acquisition module is configured to acquire a to-be-tracked signal, wherein the to-be-tracked signal is a signal acquired after the initial tracking signal.

[0018] The difference comparison module is configured to perform a difference comparison between the initial tracking signal and the to-be-tracked signal, and determine a difference comparison result.

[0019] The result determination module is configured to determine an eye tracking manner corresponding to the to-be-tracked signal according to the difference comparison result, and determine an eye tracking result of the to-be-tracked signal.

[0020] Different eye tracking manners corresponding to different difference comparison results have different calculation amounts.

[0021] In a fourth aspect, an embodiment of the present application further provides a gaze detection device, comprising:

[0022] The left eye result determination module is configured to calculate the eye tracking result of the left eye to-be-tracked signal by using the eye tracking method provided in any of the above embodiments.

[0023] The right eye result determination module is configured to calculate the eye tracking result of the right eye to-be-tracked signal by using the eye tracking method provided in any of the above embodiments.

[0024] The gaze result determination module is configured to determine the gaze detection result according to the eye tracking result of the left eye to-be-tracked signal and the eye tracking result of the right eye to-be-tracked signal.

[0025] In a fifth aspect, an embodiment of the present application further provides an electronic device, comprising:

[0026] at least one processor; and

[0027] a memory connected with the at least one processor in communication; wherein

[0028] The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to execute the eye tracking method or the gaze detection method of any of the embodiments of the present application.

[0029] In a sixth aspect, the embodiments of the present application further provide a storage medium containing computer executable instructions for executing the eye tracking method or the line of sight detection method of any of the embodiments of the present application when executed by a computer processor.

[0030] In the embodiments of the present application, an initial tracking signal is acquired, a to-be-tracked signal is acquired, wherein the to-be-tracked signal is a signal acquired after the initial tracking signal, the initial tracking signal and the to-be-tracked signal are compared differentially to determine a differential comparison result, an eye tracking mode corresponding to the to-be-tracked signal is determined according to the differential comparison result, and an eye tracking result of the to-be-tracked signal is determined, wherein the eye tracking modes corresponding to different differential comparison results have different computational complexity. Through the above technical solution, when the to-be-tracked signal that needs to be tracked is acquired, the to-be-tracked signal is not directly subjected to eye tracking calculation, but the initial tracking signal acquired before the to-be-tracked signal is referenced, the to-be-tracked signal and the initial tracking signal are compared differentially, different eye tracking modes with different computational complexity are selected for the to-be-tracked signal according to the differential comparison result, and the determination of the eye tracking result of the to-be-tracked signal is realized based on the selected eye tracking mode. Therefore, the eye tracking does not need to use the eye tracking calculation mode with large computational complexity for all to-be-tracked signals acquired at all times, the computational complexity and system power consumption of the operation process are reduced on the basis of ensuring the accuracy of the eye tracking result of the high frame rate device, and the data operation speed and the device operation stability are improved.

[0031] It should be understood that the content described in this part is not intended to identify key or important features of the embodiments of the present application, nor is it used to limit the scope of the present application. Other features of the present application will become apparent from the following description. BRIEF DESCRIPTION OF DRAWINGS

[0032] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced as follows. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative effort.

[0033] Figure 1 A flowchart of an eye tracking method provided for the first embodiment of the present application;

[0034] Figure 2 A flowchart of an eye tracking method provided for the second embodiment of the present application;

[0035] Figure 3 A flowchart of a line of sight detection method provided for the third embodiment of the present application;

[0036] Figure 4A structural schematic diagram of an eyeball tracking device provided for Embodiment Four of the present application;

[0037] Figure 5 A structural schematic diagram of a line-of-sight detection device provided for Embodiment Five of the present application;

[0038] Figure 6 A structural schematic diagram of an electronic device provided for Embodiment Six of the present application. DETAILED DESCRIPTION

[0039] In order to enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative efforts shall fall within the scope of protection of the present application.

[0040] It should be noted that the terms "first", "second", and the like in the specification and claims of the present application and the above-described drawings are used to distinguish similar objects, and do not necessarily indicate a specific order or a chronological sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, so that the embodiments of the present application described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product, or device that includes a series of steps or units does not necessarily have to be limited to only those steps or units clearly listed, but can include other steps or units that are not clearly listed or inherent to the process, method, product, or device.

[0041] Embodiment One

[0042] Figure 1 A flowchart of an eyeball tracking method provided for Embodiment One of the present application. The present embodiment can be applicable to selecting a suitable eyeball tracking mode for a to-be-tracked signal acquired in an eyeball tracking device. The eyeball tracking method can be executed by an eyeball tracking device, which can be implemented by software and / or hardware. The eyeball tracking device can be configured on an electronic device, which can be a device with eyeball tracking function, such as a VR, AR, and high-frame-rate camera, etc. The present embodiment does not limit this.

[0043] As shown in Figure 1 An eyeball tracking method provided by Embodiment One of the present application specifically includes the following steps:

[0044] S101, acquiring an initial tracking signal.

[0045] In the embodiment, the initial tracking signal can be understood as a data signal acquired by the device with the eye tracking function, which is used as a basis for determining the eye tracking mode of the subsequently acquired signal. Alternatively, the initial tracking signal can be an image signal that can generate an image acquired by a traditional camera, or a feature signal that can be encoded into an image acquired by a dynamic vision sensor (DVS) camera, and the embodiment of the present application does not limit this.

[0046] Specifically, when the device with the eye tracking function needs to track the newly acquired signal, the initial tracking signal stored in advance will be acquired first, so as to determine whether the eye moves in the subsequently acquired tracking signal based on the initial tracking signal. For example, the initial tracking signal can be the first signal acquired by the device with the eye tracking function for the to-be-recognized region, or any one signal acquired before the to-be-tracked signal that needs to be tracked.

[0047] S102, acquire a to-be-tracked signal.

[0048] The to-be-tracked signal is a signal acquired after the initial tracking signal.

[0049] In the embodiment, the to-be-tracked signal can be understood as a data signal acquired by the device with the eye tracking function, which needs to be tracked by the eye. It can be understood that the acquisition mode and type of the to-be-tracked signal are consistent with those of the initial tracking signal, that is, the to-be-tracked signal can be an image signal that can generate an image acquired by a traditional camera, or a feature signal that can be encoded into an image acquired by a DVS camera, and the embodiment of the present application does not limit this.

[0050] Specifically, when the device with the eye tracking function needs to track the eye, the image acquisition device or the feature acquisition device arranged therein is used to acquire the signal that can be used for eye tracking, and the acquired signal is used as the to-be-tracked signal.

[0051] It can be understood that the acquisition time of the to-be-tracked signal should be after the acquisition time of the initial tracking signal, so as to determine the eye tracking mode of the to-be-tracked signal based on the initial to-be-tracked signal subsequently.

[0052] S103, differentially compare the initial tracking signal and the to-be-tracked signal, and determine a differential comparison result.

[0053] Specifically, since the human eye often appears to be a few seconds of fixed-point fixation behavior when performing fixation behavior, the eye feature information contained in the tracking signal obtained during the fixed-point fixation behavior process is roughly consistent, therefore, in the embodiment of the application, the initial tracking signal and the to-be-tracked signal are compared in a differential manner to determine whether the human eye fixation state corresponding to the to-be-tracked signal changes compared with the initial tracking signal, and the comparison result is determined as the differential comparison result.

[0054] S104, determining the eye tracking mode corresponding to the to-be-tracked signal according to the differential comparison result, and determining the eye tracking result of the to-be-tracked signal.

[0055] Different eye tracking modes corresponding to different differential comparison results have different calculation amounts.

[0056] Specifically, since the human eye often appears to be a few seconds of fixed-point fixation behavior when performing fixation behavior, the eye feature information contained in the tracking signal obtained during the fixed-point fixation behavior process is roughly consistent, therefore, in the embodiment of the application, the initial tracking signal and the to-be-tracked signal are compared in a differential manner to determine whether the human eye fixation state corresponding to the to-be-tracked signal changes compared with the initial tracking signal, and the comparison result is determined as the differential comparison result.

[0057] The technical scheme of the embodiment comprises the following steps: obtaining an initial tracking signal; obtaining a to-be-tracked signal; wherein the to-be-tracked signal is a signal collected after the initial tracking signal; performing differential comparison on the initial tracking signal and the to-be-tracked signal to determine a differential comparison result; determining the eye tracking mode corresponding to the to-be-tracked signal according to the differential comparison result, and determining the eye tracking result of the to-be-tracked signal; wherein different eye tracking modes corresponding to different differential comparison results have different calculation amounts. By using the above technical scheme, when the to-be-tracked signal that needs to be tracked is obtained, the to-be-tracked signal is not directly tracked, but the initial tracking signal collected before the to-be-tracked signal is compared with the to-be-tracked signal in a differential manner, and different eye tracking modes with different calculation amounts are selected for the to-be-tracked signal according to the differential comparison result, and the eye tracking result of the to-be-tracked signal is determined based on the selected eye tracking mode. Therefore, when the eye is tracked, it is not necessary to use an eye tracking calculation mode with a large calculation amount for all to-be-tracked signals obtained at different times, the calculation amount and system power consumption of the operation process are reduced on the basis of ensuring the accuracy of the eye tracking result of the high-frame-rate device, and the data operation speed and the running stability of the device are improved.

[0058] Embodiment two

[0059] Figure 2 A flowchart of an eye tracking method provided for the second embodiment of the present application, the technical scheme of the embodiment of the present application is further optimized on the basis of the above-mentioned optional technical schemes, by determining the initial region of interest and the region of interest to be compared in the initial tracking signal and the tracking signal to be tracked respectively, comparing each relative position pixel point in the region of interest to be compared and the initial region of interest, obtaining the corresponding differential comparison result, and then comparing the differential comparison result with the preset differential threshold, to determine whether the eye tracking method for the tracking signal to be tracked is direct replacement with smaller calculation amount or recalculation with larger calculation amount, and then by updating the initial detection information by the detection information obtained by recalculating the tracking signal to be tracked, the sustainable low-amount eye tracking of the tracking signal to be tracked obtained subsequently is realized. Therefore, the eye tracking calculation method with large calculation amount does not need to be used for all tracking signals to be tracked obtained at all times, the calculation amount and system power consumption of the operation process are reduced on the basis of ensuring the accuracy of the eye tracking result of the high frame rate device, and the data operation speed and the device operation stability are improved.

[0060] As shown in Figure 2 , the eye tracking method provided by the second embodiment of the present application specifically includes the following steps:

[0061] S201, obtaining an initial tracking signal.

[0062] S202, determining initial detection information according to the initial tracking signal.

[0063] The initial detection information includes an initial region of interest.

[0064] In this embodiment, the initial detection information can be understood as an information set composed of intermediate information obtained in the eye tracking detection process of the initial tracking signal and the final result. The intermediate information obtained in the eye tracking detection process can include the region of interest (Region of Interest, ROI) of the initial tracking signal, that is, the initial region of interest in the embodiment of the present application. The initial region of interest can be understood as a target region in the initial tracking signal that is determined as much as possible to contain only the necessary region for determining the eye line of sight when the initial tracking signal is tracked. For example, the initial region of interest can be the region in the initial tracking signal that is cut off to the inner and outer corners on the left and right, and is cut off to the upper and lower eyelids on the upper and lower.

[0065] Specifically, since the initial tracking signal has completed the eye tracking detection, the initial detection information obtained by completing the eye tracking detection can be directly obtained according to the initial detection information. The initial detection information can include the region of interest information related to the eye movement determination in the eye tracking detection process, and the region of interest contained in the initial detection information can be determined as the initial region of interest.

[0066] Optionally, to enable the device with eye tracking function to directly acquire the initial detection information of the initial tracking signal in use, the initial detection information needs to be determined and stored before the initial detection information of the initial tracking signal is acquired. Exemplarily, the specific determination of the initial detection information can be realized through the following steps:

[0067] 1) performing eye feature detection on the initial tracking signal to determine second eye feature information.

[0068] Specifically, the initial tracking signal reflecting the eye movement is subjected to eye feature detection reflecting the eye fixation state, and the set of the extracted eye features is determined as the second eye feature information.

[0069] Exemplarily, the eye features extracted after the eye feature detection can include the pupil position, the pupil shape, the iris position, the iris shape, the eyelid position, the canthus position, the cornea position and the light spot position of the corneal reflection, and the present embodiment is not limited in this way. The second eye feature information can include one or more than one of the above-mentioned eye features, and the specific determination of the second eye feature information is determined according to different eye tracking calculation requirements or other actual requirements, and the present embodiment is not limited in this way.

[0070] 2) determining the initial region of interest of the initial tracking signal and the eye tracking result according to the second eye feature information.

[0071] Specifically, the eye feature information necessary for determining the eye line change is included in the second eye feature information, the region for eye tracking is determined in the initial tracking signal based on the second eye feature information, and the region is taken as the initial region of interest. And based on the feature information in the initial region of interest, the fixation point of the eye corresponding to the initial tracking signal and other information are estimated, and the estimated eye line and / or fixation point are determined as the eye tracking result corresponding to the initial tracking signal.

[0072] Exemplarily, the region of the initial tracking signal can be determined as the initial region of interest based on the eyelid position and the canthus position, the left and right ends are cut to the inner and outer canthus, and the upper and lower ends are cut to the upper and lower eyelids; or the overlapping part of the pupil position, the pupil shape, the iris position and the iris shape is determined as the initial region of interest; or the pupil position and the light spot position of the corneal reflection are determined as the initial region of interest, and the present embodiment is not limited in this way.

[0073] 3) storing the initial region of interest of the initial tracking signal and the eye tracking result as the initial detection information of the initial tracking signal.

[0074] Optionally, the initial region of interest is a rectangular region centered on the pupil, or a circular region centered on the pupil, or an elliptical region centered on the pupil, or a rectangular region centered on the iris, or a circular region centered on the iris, or an elliptical region centered on the iris, or all regions within the eye contour, or the edge region of the pupil, or the edge region of the iris, and the embodiments of the present application do not limit this.

[0075] S203, acquiring a to-be-tracked signal.

[0076] The to-be-tracked signal is a signal acquired after the initial tracking signal.

[0077] S204, applying the initial region of interest to the to-be-tracked signal to determine a to-be-compared region of interest.

[0078] In this embodiment, the to-be-compared region of interest can be specifically understood as a region in the to-be-tracked signal corresponding to the position of the initial region of interest of the initial tracking signal.

[0079] Specifically, since the initial tracking signal and the to-be-tracked signal are collected in the same way, it can be considered that the sizes of the regions collected by the initial tracking signal and the to-be-tracked signal are consistent. Therefore, after the position of the initial region of interest in the corresponding collection region of the initial tracking signal is determined, it can be mapped to the corresponding collection region of the to-be-tracked signal, and the obtained region is determined as the to-be-compared region of interest of the to-be-tracked signal.

[0080] S205, differentially comparing the to-be-compared region of interest with the initial region of interest to determine a differential comparison result.

[0081] Specifically, since the human eye often has a short-time fixation behavior of several seconds when performing a fixation behavior, it can be considered that the ranges of the regions of interest corresponding to the signals collected at the before and after collection time and the internal eye feature information contained therein are approximately consistent. Therefore, in the embodiments of the present application, the to-be-compared region of interest is differentially compared with the initial region of interest to determine whether the fixation state of the human eye corresponding to the to-be-tracked signal changes compared with the initial tracking signal, and the comparison result is determined as the differential comparison result. Moreover, the to-be-compared region of interest of the eye to-be-tracked signal and the initial region of interest of the initial tracking signal are differentially compared, which actually reduces the actual analysis region of the initial to-be-tracked signal and the initial tracking signal, and also achieves the effect of reducing the calculation amount and improving the calculation efficiency.

[0082] Optionally, differentially comparing the to-be-compared region of interest with the initial region of interest to determine the differential comparison result can be achieved by the following way:

[0083] 1) The gray scale values of each pixel point in the region of interest to be compared are normalized by zero mean, and a first standard value is determined.

[0084] 2) The gray scale values of each pixel point in the initial region of interest are normalized by zero mean, and a second standard value is determined.

[0085] 3) The absolute value of the difference between the second standard value and the first standard value is determined as the differential comparison result.

[0086] Specifically, regardless of the acquisition method of the initial tracking signal and the signal to be tracked, the encoding can be converted into image information. The image can be composed of multiple pixel points, and the gray scale values of each pixel point have corresponding pixel values. When comparing the region of interest to be compared and the initial region of interest, the gray scale values of each pixel point in the region of interest to be compared and the gray scale values of each pixel point in the initial region of interest are normalized by zero mean. The first standard value is obtained by normalizing the gray scale values of each pixel point in the region of interest to be compared by zero mean, and the second standard value is obtained by normalizing the gray scale values of each pixel point in the initial region of interest by zero mean. The absolute value of the difference between the second standard value and the first standard value is determined as the differential comparison result.

[0087] For example, the standard value can be determined by the following formula:

[0088]

[0089] Where N is the number of pixel points in the region of interest, x i is the pixel value of the i-th pixel point in the region of interest, μ is the average value of the gray scale values of each pixel point in the region of interest, and σ is the standard value.

[0090] Where the region of interest can be the region of interest to be compared or the initial region of interest. The standard value can be the first standard value or the second standard value. When the region of interest is the region of interest to be compared, the calculated σ is the first standard value. When the region of interest is the initial region of interest, the calculated σ is the second standard value.

[0091] Differential comparison result = | second standard value - first standard value |.

[0092] Optionally, the region of interest to be compared and the initial region of interest are differentially compared to determine the differential comparison result, which can also be achieved by the following method:

[0093] 1) The gray scale values of the pixel points at corresponding positions in the region of interest to be compared and the initial region of interest are subtracted to determine the gray scale value difference corresponding to each pixel point.

[0094] 2) The average value of each gray scale value difference is determined as the differential comparison result.

[0095] It can be understood that when the gray value difference of the corresponding pixel points in the initial interest region and the interest region to be compared is calculated, the gray value difference of all pixel points in the initial interest region and the interest region to be compared can be calculated one by one; or the pixel points in the initial interest region and the interest region to be compared can be selected according to a preset rule, and the gray value difference of the selected pixel points is calculated to obtain the corresponding gray value difference.

[0096] It can be understood that in the calculation process of the difference comparison result, the CPU or GPU can be used to calculate the difference comparison result according to the actual configuration of the device by the eye tracking method. For example, when the CPU is used for calculation, single-thread serial calculation or multi-thread parallel calculation can be used; and when the GPU is used for calculation, all pixel points that need to be calculated can be calculated at the same time to obtain the final difference comparison result. The specific calculation method can be determined according to the actual hardware configuration and data resource amount, and the embodiments of the present application do not limit this.

[0097] S206, determining whether the difference comparison result is less than or equal to a preset difference threshold, if yes, performing S207; if no, performing S208.

[0098] In this embodiment, the preset difference threshold can be understood as a threshold for determining the difference between the initial interest region and the interest region to be compared, which is set in advance according to the actual situation.

[0099] Specifically, the difference comparison result is compared with the preset difference threshold, if the difference comparison result is less than or equal to the preset difference threshold, it can be considered that the difference between the initial interest region and the interest region to be compared is small, that is, it can be considered that the collected person's eye is performing a fixed-point fixation behavior during the collection time from the initial tracking signal to the tracking signal to be tracked, and S207 is performed at this time; if the difference comparison result is greater than the preset difference threshold, it can be considered that the difference between the initial interest region and the interest region to be compared is large, that is, it can be considered that the fixation behavior of the collected person's eye has changed between the initial tracking signal and the tracking signal to be tracked, and S208 is performed at this time.

[0100] S207, determining the direct replacement as the eye tracking method corresponding to the tracking signal to be tracked, and determining the eye tracking result in the initial detection information as the eye tracking result of the tracking signal to be tracked.

[0101] Specifically, when it is determined that the collected person's eye is performing the fixation behavior during the time from the initial tracking signal to the collection of the to-be-tracked signal, that is, the difference comparison result is less than or equal to the preset difference threshold, it can be considered that the fixation direction of the collected person's eye and the like does not change greatly, and it can be considered that the calculation result of the eye tracking calculation performed on the to-be-tracked signal should be basically the same as the result of the eye tracking calculation performed on the initial tracking signal. At this time, the direct replacement is determined as the eye tracking mode corresponding to the to-be-tracked signal, and the eye tracking result in the initial detection information is determined as the eye tracking result of the to-be-tracked signal, so as to reduce unnecessary eye tracking calculation in the fixation behavior process.

[0102] S208, the re-computation is determined as the eye tracking mode corresponding to the to-be-tracked signal, the first eye feature information corresponding to the to-be-tracked signal is determined, and the eye tracking result re-computed according to the first eye feature information is determined as the eye tracking result of the to-be-tracked signal.

[0103] Specifically, when it is determined that the collected person's eye is performing the fixation behavior during the time from the initial tracking signal to the collection of the to-be-tracked signal, that is, the difference comparison result is less than or equal to the preset difference threshold, it can be considered that the fixation direction of the collected person's eye and the like does not change greatly, and it can be considered that the calculation result of the eye tracking calculation performed on the to-be-tracked signal should be basically the same as the result of the eye tracking calculation performed on the initial tracking signal. At this time, the direct replacement is determined as the eye tracking mode corresponding to the to-be-tracked signal, and the eye tracking result in the initial detection information is determined as the eye tracking result of the to-be-tracked signal, so as to reduce unnecessary eye tracking calculation in the fixation behavior process.

[0104] The eye tracking mode includes a direct replacement tracking calculation mode and a re-calculation tracking calculation mode. The direct replacement tracking calculation mode refers to determining the eye tracking result in the initial detection information as the eye tracking result of the to-be-tracked signal, and the direct replacement tracking calculation mode has a small calculation amount. The re-calculation tracking calculation mode refers to re-determining the first eye feature information corresponding to the to-be-tracked signal, and determining the eye tracking result re-calculated according to the first eye feature information as the eye tracking result of the to-be-tracked signal, and the re-calculation tracking calculation mode has a large calculation amount.

[0105] S209, storing the to-be-tracked signal as a new initial tracking signal.

[0106] S210, determining the region of interest determined according to the first eye feature information as a new initial region of interest.

[0107] S211, storing the new initial region of interest and the eye tracking result of the to-be-tracked signal as new initial detection information.

[0108] Specifically, if S208 is executed, it is proved that the gaze behavior of the collected human eye has changed when the to-be-tracked signal is collected, so it can be considered that the initial detection information corresponding to the original initial tracking signal cannot be used as a basis for determining the eye tracking mode of the to-be-tracked signal obtained subsequently. At this time, the to-be-tracked signal can be stored as a new initial tracking signal, the region of interest determined according to the first eye feature information can be determined as a new initial region of interest, and the new initial region of interest and the eye tracking result of the to-be-tracked signal can be stored as new initial detection information. The update of the initial tracking signal and the initial detection information is realized, so that when the to-be-tracked signal is obtained again subsequently, the eye tracking mode can be determined based on the new initial tracking signal.

[0109] The technical scheme of the embodiment determines the initial region of interest and the to-be-compared region of interest in the initial tracking signal and the to-be-tracked signal respectively, compares each relative position pixel point in the to-be-compared region of interest and the initial region of interest, obtains the corresponding difference comparison result, and then compares the difference comparison result with the preset difference threshold to determine whether the eye tracking mode for the to-be-tracked signal is the direct replacement with a small calculation amount or the re-calculation with a large calculation amount. Then, by updating the initial detection information with the detection information re-calculated for the to-be-tracked signal, the sustainable low-amount eye tracking for the to-be-tracked signal obtained subsequently is realized. The eye tracking does not need to use the eye tracking calculation mode with a large calculation amount for all to-be-tracked signals obtained at all times, reduces the calculation amount and system power consumption of the operation process on the basis of ensuring the accuracy of the eye tracking result of the high-frame-rate device, and improves the data operation speed and the device running stability.

[0110] Embodiment three

[0111] Figure 3 A flowchart of a line-of-sight detection method provided for embodiment three of the present application can be applicable to the case of determining the line of sight based on the eye tracking results of each eye after selecting a suitable eye tracking mode for eye tracking. The line-of-sight detection method can be executed by a line-of-sight detection device, which can be implemented by software and / or hardware. The line-of-sight detection device can be configured on an electronic device, which can be a device with eye tracking function, such as a VR, AR, and high-frame-rate camera, etc. Embodiments of the present application do not limit this.

[0112] As shown in Figure 3 , the line-of-sight detection method provided for embodiment three of the present application specifically includes the following steps:

[0113] S301, calculating the eye tracking result of the left eye to-be-tracked signal based on the eye tracking method provided in any of the above embodiments.

[0114] Specifically, the left eye in the real human eye is subjected to signal acquisition, and the acquired left eye to-be-tracked signal is subjected to eye tracking result calculation by the eye tracking method provided in any of the above embodiments to obtain the corresponding eye tracking result of the left eye to-be-tracked signal.

[0115] S302, calculating the eye tracking result of the right eye to-be-tracked signal based on the eye tracking method provided in any of the above embodiments.

[0116] Specifically, the right eye in the real human eye is subjected to signal acquisition, and the acquired right eye to-be-tracked signal is subjected to eye tracking result calculation by the eye tracking method provided in any of the above embodiments to obtain the corresponding eye tracking result of the right eye to-be-tracked signal.

[0117] S303, determining the line-of-sight detection result according to the eye tracking result of the left eye to-be-tracked signal and the eye tracking result of the right eye to-be-tracked signal.

[0118] Specifically, if both the left eye to-be-tracked signal and the right eye to-be-tracked signal use the direct replacement eye tracking mode when determining the eye tracking result, the line-of-sight detection result corresponding to the previous acquisition time can be used as the line-of-sight detection result of this time. If any one of the left eye to-be-tracked signal and the right eye to-be-tracked signal uses the recalculation eye tracking mode when determining the eye tracking result, the line-of-sight detection result needs to be recalculated according to the gaze point and other information contained in the eye tracking result of the left eye to-be-tracked signal and the eye tracking result of the right eye to-be-tracked signal to obtain the final line-of-sight detection result.

[0119] The technical scheme of the embodiment, when the to-be-tracked signal requiring eye tracking is acquired, does not directly perform eye tracking calculation on the to-be-tracked signal, but refers to an initial tracking signal acquired before the to-be-tracked signal, performs difference comparison on pixel points in a position corresponding to an initial region of interest of the to-be-tracked signal and the initial tracking signal, selects an eye tracking mode with different calculation amounts for the to-be-tracked signal according to different difference comparison results, and determines the eye tracking result of the to-be-tracked signal based on the selected eye tracking mode. Then, when binocular visual line detection is performed, the left eye to-be-tracked signal and the right eye to-be-tracked signal both of which use the direct replacement eye tracking mode do not need to be re-detected, so that the to-be-tracked signal acquired at all times does not need to use the eye tracking calculation mode with a large calculation amount during eye tracking, the calculation amount of the operation process and the system power consumption are reduced on the basis of ensuring the accuracy of the eye tracking result of the high-frame-rate device, and the data operation speed and the device operation stability are improved.

[0120] Embodiment four

[0121] Figure 4 A structure diagram of an eye tracking device provided for the fourth embodiment of the application is shown in FIG. 4. Figure 4 As shown in FIG. 4, the eye tracking device includes a first signal acquisition module 41, a second signal acquisition module 42, a difference comparison module 43, and a result determination module 44.

[0122] The first signal acquisition module 41 is configured to acquire an initial tracking signal. The second signal acquisition module 42 is configured to acquire a to-be-tracked signal. The to-be-tracked signal is a signal acquired after the initial tracking signal. The difference comparison module 43 is configured to perform difference comparison on the initial tracking signal and the to-be-tracked signal to determine a difference comparison result. The result determination module 44 is configured to determine an eye tracking mode corresponding to the to-be-tracked signal according to the difference comparison result, and determine an eye tracking result of the to-be-tracked signal. Different eye tracking modes corresponding to different difference comparison results have different calculation amounts.

[0123] The technical scheme of the embodiment, when the to-be-tracked signal requiring eye tracking is acquired, does not directly perform eye tracking calculation on the to-be-tracked signal, but refers to an initial tracking signal acquired before the to-be-tracked signal, performs difference comparison on pixel points in a position corresponding to an initial region of interest of the to-be-tracked signal and the initial tracking signal, selects an eye tracking mode with different calculation amounts for the to-be-tracked signal according to different difference comparison results, and determines the eye tracking result of the to-be-tracked signal based on the selected eye tracking mode. Then, when binocular visual line detection is performed, the left eye to-be-tracked signal and the right eye to-be-tracked signal both of which use the direct replacement eye tracking mode do not need to be re-detected, so that the to-be-tracked signal acquired at all times does not need to use the eye tracking calculation mode with a large calculation amount during eye tracking, the calculation amount of the operation process and the system power consumption are reduced on the basis of ensuring the accuracy of the eye tracking result of the high-frame-rate device, and the data operation speed and the device operation stability are improved.

[0124] Optionally, the eye tracking device further comprises:

[0125] The region of interest determining module is configured to determine initial detection information according to the initial tracking signal after the initial tracking signal is acquired; wherein the initial detection information comprises an initial region of interest; and the initial region of interest is applied to the to-be-tracked signal to determine a to-be-compared region of interest.

[0126] Optionally, the initial region of interest is a rectangular region centered on the pupil, a circular region centered on the pupil, an elliptical region centered on the pupil, a rectangular region centered on the iris, a circular region centered on the iris, an elliptical region centered on the iris, or all regions within the eye contour, or an edge region of the pupil, or an edge region of the iris.

[0127] Optionally, the difference comparison module 43 is specifically configured to: perform a difference comparison on the to-be-compared region of interest and the initial region of interest to determine a difference comparison result.

[0128] Optionally, the difference comparison on the to-be-compared region of interest and the initial region of interest to determine the difference comparison result comprises:

[0129] performing zero-mean normalization processing on the gray values of the pixel points in the to-be-compared region of interest to determine a first standard value;

[0130] performing zero-mean normalization processing on the gray values of the pixel points in the initial region of interest to determine a second standard value;

[0131] determining, as the difference comparison result, an absolute value of a difference between the second standard value and the first standard value.

[0132] Optionally, the difference comparison on the to-be-compared region of interest and the initial region of interest to determine the difference comparison result comprises:

[0133] performing a difference on the gray values of the pixel points at corresponding positions in the to-be-compared region of interest and the initial region of interest to determine a gray value difference value corresponding to each pixel point;

[0134] determining, as the difference comparison result, an average value of the gray value difference values.

[0135] Optionally, the result determining module 44 comprises:

[0136] The first result determining unit is configured to, if the difference comparison result is less than or equal to a preset difference threshold, directly replace the initial detection information to determine the eye tracking result corresponding to the to-be-tracked signal, and determine the eye tracking result of the initial detection information as the eye tracking result of the to-be-tracked signal.

[0137] The second result determination unit is configured to determine the recalculated result as the eye tracking mode corresponding to the to-be-tracked signal, determine the first eye feature information corresponding to the to-be-tracked signal, and determine the eye tracking result recalculated according to the first eye feature information as the eye tracking result of the to-be-tracked signal, if the difference comparison result is greater than the preset difference threshold.

[0138] Optionally, the eye tracking device further comprises an update storage module.

[0139] The update storage module is configured to store the to-be-tracked signal as a new initial tracking signal, determine a new initial region of interest according to the first eye feature information, and store the new initial region of interest and the eye tracking result of the to-be-tracked signal as new initial detection information after the eye tracking result recalculated according to the first eye feature information is determined as the eye tracking result of the to-be-tracked signal.

[0140] Optionally, the eye tracking device further comprises an initial information determination module.

[0141] The initial information determination module is configured to perform eye feature detection on the initial tracking signal to determine second eye feature information after the initial tracking signal is acquired, determine an initial region of interest and an eye tracking result of the initial tracking signal according to the second eye feature information, and store the initial region of interest and the eye tracking result of the initial tracking signal as initial detection information of the initial tracking signal.

[0142] The eye tracking device of the embodiment of the present application can execute the eye tracking method provided by any embodiment of the present application, and has the corresponding function modules and beneficial effects of the execution method.

[0143] Embodiment five

[0144] Figure 5 A structure schematic diagram of a line of sight detection device provided by embodiment five of the present application is shown in FIG. 5. Figure 5 As shown in FIG. 5, the line of sight detection device comprises a left eye result determination module 51, a right eye result determination module 52, and a line of sight result determination module 53.

[0145] The left eye result determination module 51 is configured to calculate the eye tracking result of the left eye to-be-tracked signal based on the eye tracking method provided by any embodiment described above; the right eye result determination module 52 is configured to calculate the eye tracking result of the right eye to-be-tracked signal based on the eye tracking method provided by any embodiment described above; and the line of sight result determination module 53 is configured to determine the line of sight detection result according to the eye tracking result of the left eye to-be-tracked signal and the eye tracking result of the right eye to-be-tracked signal.

[0146] The technical scheme of the embodiment, when the to-be-tracked signal needing to be tracked by the eyeball is acquired, does not directly perform eyeball tracking calculation on the to-be-tracked signal, but refers to an initial interest region of an initial tracking signal acquired before the to-be-tracked signal, performs differential comparison on pixel points in a position corresponding to the initial interest region in the to-be-tracked signal and the initial tracking signal, selects eyeball tracking modes with different calculation amounts for the to-be-tracked signal according to different differential comparison results, and determines the eyeball tracking result of the to-be-tracked signal based on the selected eyeball tracking mode. Then, when the binocular visual line detection is performed, the left-eye to-be-tracked signal and the right-eye to-be-tracked signal all of which adopt the direct replacement eyeball tracking mode do not need to be re-detected, so that the to-be-tracked signal acquired at all times does not need to be detected by using the eyeball tracking calculation mode with a large calculation amount during eyeball tracking, the calculation amount of the operation process and the system power consumption are reduced on the basis of ensuring the accuracy of the eyeball tracking result of the high-frame-rate device, and the data operation speed and the device operation stability are improved.

[0147] The line-of-sight detection device provided in the embodiment of the present application can execute the line-of-sight detection method provided in any embodiment of the present application, and has the corresponding function modules and beneficial effects of the execution method.

[0148] Embodiment six

[0149] Figure 6 A structural schematic diagram of an electronic device provided in the sixth embodiment of the present application. The electronic device 60 can be a digital computer in various forms, such as a laptop computer, a desktop computer, a workstation, a personal digital assistant, a server, a blade server, a mainframe computer, and other suitable computers. The electronic device 60 can also represent various forms of mobile devices, such as a personal digital assistant, a cellular phone, a smart phone, a wearable device (such as a helmet, glasses, a watch, etc.), and other similar computing devices. The components shown in this figure, their connections, and relationships, and their functions are merely examples, and are not intended to limit the implementation of the present application described and / or claimed herein.

[0150] As Figure 6As shown, the electronic device 60 includes at least one processor 61, and a memory, such as a read-only memory (ROM) 62, a random access memory (RAM) 63, etc., connected to the at least one processor 61 in communication. The memory stores computer programs executable by the at least one processor 61, and the processor 61 can perform various appropriate actions and processes according to the computer programs stored in the read-only memory (ROM) 62 or loaded from the storage unit 68 into the random access memory (RAM) 63. In the RAM 63, various programs and data required for the operation of the electronic device 60 can also be stored. The processor 61, the ROM 62, and the RAM 63 are connected to each other through a bus 64. An input / output (I / O) interface 65 is also connected to the bus 64.

[0151] Various components in the electronic device 60 are connected to the I / O interface 65, including an input unit 66, such as a keyboard, a mouse, etc., an output unit 67, such as various types of displays, a speaker, etc., a storage unit 68, such as a magnetic disk, an optical disk, etc., and a communication unit 69, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 69 allows the electronic device 60 to exchange information / data with other devices through a computer network, such as the Internet, and / or various telecommunication networks.

[0152] The processor 61 can be various general and / or special purpose processing components having processing and computing capabilities. Some examples of the processor 61 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 61 performs various methods and processes described above, such as the eye tracking method or the gaze detection method.

[0153] In some embodiments, the eye tracking method or the gaze detection method can be implemented as a computer program tangibly embodied in a computer readable storage medium, such as the storage unit 68. In some embodiments, part or all of the computer program can be loaded and / or installed onto the electronic device 60 via the ROM 62 and / or the communication unit 69. When the computer program is loaded into the RAM 63 and executed by the processor 61, one or more steps of the eye tracking method or the gaze detection method described above can be performed. Alternatively, in other embodiments, the processor 61 can be configured to perform the eye tracking method or the gaze detection method by any other appropriate means, such as by means of firmware.

[0154] The various embodiments of the systems and techniques described above can be implemented in digital electronic circuitry, integrated circuitry, a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), a system on a chip (SOC), a load programmable logic device (CPLD), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include implementation in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, which can be special or general purpose, coupled to receive data and instructions from, and to transmit data and instructions to, a storage system, at least one input device, and at least one output device.

[0155] Computer programs used to implement the processes of the application can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the computer program, when executed, can cause instructions defined in the flow charts and / or block diagrams to be implemented. The computer program can be executed entirely on a machine, partially on a machine, partially on a machine as a standalone software package and partially on a remote machine or entirely on a remote machine or server.

[0156] In the context of the present application, a computer-readable storage medium can be a tangible medium that can contain or store computer programs for use by or in connection with an instruction execution system, apparatus, or device. Computer-readable storage media can include, but are not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium can be a machine-readable signal medium. More specific examples of the machine-readable storage medium will include one or more lines of electrical connections, portable computer disks, hard disk drives, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or Flash memory), optical fibers, portable compact disc read-only memories (CD-ROMs), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0157] To provide for interaction with a user, the systems and techniques described here can be implemented on an electronic device having a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the electronic device. Other kinds of devices can be used to provide for interaction with a user as well; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form, including acoustic, speech, or tactile input.

[0158] The systems and techniques described here can be implemented in a computing system that includes a back end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front end component (e.g., a user computer having a graphical user interface or a Web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back end, middleware, or front end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0159] The computing system can include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. A server can be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system, to solve the defects of large management difficulty and weak business scalability in traditional physical host and VPS service.

[0160] It should be understood that the various forms of flow shown above can be re-ordered, added to, or deleted from without departing from the scope of the present disclosure. For example, the steps recited in the present disclosure can be executed in parallel, executed in sequence, or executed in a different order, as long as the desired results of the present disclosure are achieved, and the present disclosure is not limited herein.

[0161] The specific embodiments described above are not intended to be limiting, and persons skilled in the art will appreciate that various modifications, combinations, sub-combinations and alternatives can be made to the specific embodiments without departing from the spirit and principles of the disclosure. Accordingly, the disclosure is not limited to the specific embodiments described above, but only by the scope of the appended claims.

Claims

1. An eye tracking method, characterized by, The method comprises: acquiring an initial tracking signal; acquiring a to-be-tracked signal; wherein the to-be-tracked signal is a signal collected after the initial tracking signal; differentially comparing the initial tracking signal and the to-be-tracked signal to determine a differential comparison result; determining an eye tracking mode corresponding to the to-be-tracked signal according to the differential comparison result, and determining an eye tracking result of the to-be-tracked signal; wherein different differential comparison results correspond to different eye tracking modes.

2. The method of claim 1, wherein, After acquiring the initial tracking signal, the method further comprises: determining initial detection information according to the initial tracking signal; wherein the initial detection information comprises an initial region of interest; applying the initial region of interest to the to-be-tracked signal to determine a to-be-compared region of interest.

3. The method of claim 2, wherein, The differential comparison of the initial tracking signal and the to-be-tracked signal to determine a differential comparison result comprises: differentially comparing the to-be-compared region of interest and the initial region of interest to determine a differential comparison result.

4. The method of claim 3, wherein, The differential comparison of the initial tracking signal and the to-be-tracked signal to determine a differential comparison result comprises: performing zero-mean normalization processing on the gray value of each pixel point in the to-be-compared region of interest to determine a first standard value; performing zero-mean normalization processing on the gray value of each pixel point in the initial region of interest to determine a second standard value; determining the absolute value of the difference between the second standard value and the first standard value as the differential comparison result.

5. The method of claim 3, wherein, The differential comparison of the initial tracking signal and the to-be-tracked signal to determine a differential comparison result comprises: performing differential processing on the gray values of the pixel points at corresponding positions in the to-be-compared region of interest and the initial region of interest to determine the gray value difference value corresponding to each pixel point; determining the average value of each gray value difference value as the differential comparison result.

6. The method of claim 2, wherein, The initial region of interest is a rectangular region centered on the pupil, a circular region centered on the pupil, an elliptical region centered on the pupil, a rectangular region centered on the iris, a circular region centered on the iris, an elliptical region centered on the iris, all regions within the eye contour, or an edge region of the pupil or an edge region of the iris.

7. The method of claim 2, wherein, Determining an eye tracking mode corresponding to the to-be-tracked signal according to the differential comparison result, and determining an eye tracking result of the to-be-tracked signal, comprises: if the differential comparison result is less than or equal to a preset differential threshold, directly replacing the initial detection information to determine the eye tracking result of the to-be-tracked signal as the eye tracking result of the to-be-tracked signal; if the differential comparison result is greater than the preset differential threshold, re-computing the initial detection information to determine the eye tracking result of the to-be-tracked signal as the eye tracking result of the to-be-tracked signal.

8. The method of claim 7, wherein, after the eye tracking result recalculated according to the first eye feature information is determined as the eye tracking result of the to-be-tracked signal, further comprising: storing the to-be-tracked signal as a new initial tracking signal; determining a region of interest according to the first eye feature information as a new initial region of interest; storing the new initial region of interest and the eye tracking result of the to-be-tracked signal as new initial detection information.

9. The method according to any one of claims 1-8, characterized in that, after the initial tracking signal is obtained, further comprising: performing eye feature detection on the initial tracking signal to determine second eye feature information; determining an initial region of interest and an eye tracking result of the initial tracking signal according to the second eye feature information; storing the initial region of interest and the eye tracking result of the initial tracking signal as initial detection information of the initial tracking signal.

10. A line-of-sight detection method characterized by, comprising: calculating an eye tracking result of a left eye to-be-tracked signal based on the eye tracking method of any one of claims 1-9; calculating an eye tracking result of a right eye to-be-tracked signal based on the eye tracking method of any one of claims 1-9; determining a gaze detection result according to the eye tracking result of the left eye to-be-tracked signal and the eye tracking result of the right eye to-be-tracked signal.

11. An eye tracking device, characterized by comprising: a first signal acquisition module, configured to acquire an initial tracking signal; a second signal acquisition module, configured to acquire a to-be-tracked signal; wherein the to-be-tracked signal is a signal acquired after the initial tracking signal; a difference comparison module, configured to perform difference comparison on the initial tracking signal and the to-be-tracked signal to determine a difference comparison result; a result determination module, configured to determine an eye tracking manner corresponding to the to-be-tracked signal according to the difference comparison result, and determine an eye tracking result of the to-be-tracked signal; wherein the eye tracking manner corresponding to different difference comparison results has different calculation amounts.

12. A line-of-sight detection device, characterized by comprising: a left eye result determination module, configured to calculate an eye tracking result of a left eye to-be-tracked signal based on the eye tracking method of any one of claims 1-9; a right eye result determination module, configured to calculate an eye tracking result of a right eye to-be-tracked signal based on the eye tracking method of any one of claims 1-9; a gaze result determination module, configured to determine a gaze detection result according to the eye tracking result of the left eye to-be-tracked signal and the eye tracking result of the right eye to-be-tracked signal.

13. An electronic device, comprising: comprising: at least one processor; and a memory connected in communication with the at least one processor; wherein the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to execute the eye tracking method of any one of claims 1-9 or the gaze detection method of claim 10.

14. A storage medium containing computer-executable instructions, wherein: the computer executable instructions, when executed by a computer processor, are used to execute the eye tracking method of any one of claims 1-9 or the gaze detection method of claim 10.

Images