Wearable device for detecting eye movement of a user

Abstract

Embodiments of the present disclosure relate to a wearable device for detecting eye movement of a user. A wearable device for detecting eye movement of a user has: a first movement sensor having electrodes aligned with each other along a first movement axis; a second movement sensor having electrodes aligned with each other along a second movement axis transverse to the first movement axis; and a control circuit coupled to the electrodes and configured to: obtain an electrostatic charge change signal indicative of a difference between electrostatic charge changes detected by the electrodes of the mobile sensor; detecting an event indicative of a respective displacement of the eye along the axis of movement; and determining movement of the eye based on the event confirmation.

Description

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application claims priority to Italian Application No. 102023000017643, filed on August 28, 2023, which is hereby incorporated by reference in its entirety. Technical Field

[0003] The present disclosure relates to a wearable device for detecting eye movement of a user. In addition, the present disclosure relates to a wearable optical support device including the device, a detection method for detecting eye movement of a user, and a corresponding computer program product. Background Art

[0004] As is known, different current applications require monitoring activities, more specifically, monitoring the eye movements of a person. For example, eye tracking is useful in smart glasses based applications, where it is important to know the direction of the gaze of the person wearing the smart glasses and to obtain commands provided by the person (e.g., voluntary blinks, etc.). For example, eye tracking can activate advanced functions for adjusting the focus of a camera lens or quick reading functions such as zoom and panorama operations.

[0005] Generally speaking, eye tracking requires monitoring a person's eye movements to associate these movements with corresponding controls / functions, thus allowing a person to control an electronic device without using gestures or voice commands. For example, eye movements can be grouped based on the following eye positions considered in a person's eye reference frame: center, top, bottom, right, left, upper left, upper right, lower left, and lower right.

[0006] Solutions that allow eye movement to be monitored are known. For example, electrooculography (EOG) is a technique that measures the corneal-retinal potential (CRP) present between the front (e.g., including the cornea) and the back (e.g., including the retina) of the human eye. The eye acts as an electric dipole, with the front pole at the cornea being the positive pole and the back pole at the retina being the negative pole.

[0007] EOG is a commonly used measurement method because CRP is higher in intensity than the electrical potentials typically monitored in other detection techniques (e.g., the electrical potentials involved in electroencephalograms, i.e., EEG signals), and because the eyes are located outside the skull, there is no bone structure to attenuate the electrical signals they generate. In EOG, to measure eye movements, multiple electrodes are placed around the eyes and in contact with the facial skin; for example, five electrodes are distributed around the eyes and on the forehead.

[0008] In more detail, when the eye rotates around its own center of rotation (e.g., substantially at the center of the same eyeball and eye socket), it generates a CRP change that is detected by the electrodes. In an embodiment, when the eyelid is closed, the cornea moves in one direction, and when the eyelid is open, the cornea moves in the opposite direction, generating a CRP change that is identifiable and can be associated with the blink. The signal generated by a blink generally has a low frequency, for example, between 1 Hz and about 13 Hz.

[0009] However, this known measurement technique has the following problems: measurement noise due to alternating current at 50 Hz or 60 Hz, which may be present in the environment where the measurement is performed; noise due to head and body movement during measurement; artifacts in the measurement caused by the operation of electrical equipment present near the electrodes; measurement errors caused by contraction of facial or neck muscles or sliding of the electrodes on the skin due to sweating and blinking. In general, EOG is a complex measurement technique with low measurement sensitivity. Summary of the invention

[0010] The present disclosure aims to provide a wearable device for detecting eye movements of a user, a wearable optical support device including the device, a detection method for detecting eye movements of a user, and a corresponding computer program product, which overcome the shortcomings of the prior art.

[0011] According to the present invention, a wearable device for detecting eye movements of a user, an optical support device that is wearable and includes the device, a detection method for detecting eye movements of a user, and a corresponding computer program product are as defined in the attached claims. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] For a better understanding of the invention, preferred embodiments will now be described, by way of non-limiting examples only, with reference to the accompanying drawings, in which:

[0013] Figure 1 is a block diagram schematically illustrating a device for detecting eye movement of a user according to one embodiment;

[0014] Figure 2 Schematically shows a wearing device according to an embodiment Figure 1 the user of the device;

[0015] Figure 3 and Figure 4 It shows that the Figure 1 a pair of glasses of equipment;

[0016] Figure 5 Schematic diagram showing the user's eyes relative to Figure 1Three examples of possible locations of electrodes for the device in;

[0017] Figure 6 The user's visual system is schematically shown;

[0018] Figure 7 Shows Figure 6 Details of the visual scheme;

[0019] FIG. 8A to FIG. 8D It is shown that according to the corresponding situation, the Figure 1 A corresponding curve graph of the trend of the power detected by the mobile sensor of the device over time;

[0020] Fig. 9 is a schematic diagram showing a method of performing a Figure 1 A block diagram of a detection method performed by a device;

[0021] Fig.10 and Fig.11 Shows Figure 1 corresponding and further embodiments of the apparatus;

[0022] Fig.12 is a flow chart of an embodiment method for detecting eye movement;

[0023] Fig.13 is a block diagram of an embodiment device;

[0024] Fig.14 is a flow chart of an embodiment detection method, which can be Fig.13 is implemented in a device; and

[0025] Fig.15 is a flow chart of an embodiment detection method, which can be Fig.13 is implemented in the device.

[0026] In the embodiment, the drawings are shown with reference to a three-axis Cartesian coordinate system defined by an X-axis, a Y-axis, and a Z-axis that are orthogonal to each other.

[0027] The following description uses the same reference numerals to indicate elements that are common to the different embodiments. DETAILED DESCRIPTION

[0028] Figure 1 A device 10 for detecting an activity of a person's eyes, in particular one or more eye movements, is shown.

[0029] As further described below, device 10 allows eye tracking to be performed and can be used to control functions of an electronic device (e.g., a screen, TV, PC) external to device 10 and operatively coupled to the electronic device. As further described below, device 10 can be worn by a person (hereinafter also referred to as a user) in a manner that allows the movement of his / her eyes to be detected. Figure 1 As shown, the device 10 includes a main control circuit 21, a first motion sensor 20a and a second motion sensor 20b.

[0030] According to an exemplary embodiment, the main control circuit 21 (such as a microprocessor, a microcontroller or a dedicated computing circuit) is an electronic control circuit, which may include a data storage circuit 21b (such as a memory, for example a non-volatile memory) coupled to each other for storing the acquired data and a processing circuit 21a for processing the acquired data.

[0031] For example, the processing circuit 21a may include a feature extraction module and a classifier module (e.g., a "decision tree" or a "support vector machine"). In a manner not shown and known per se, the main control circuit 21 may also include one or more of the following components: an electrical energy storage module (e.g., a battery), a power management module for electrical energy management, an interface analog front-end module with a first motion sensor 20a and a second motion sensor 20b, or a communication module (e.g., a radio communication based on Bluetooth technology).

[0032] The first movement sensor 20a and the second movement sensor 20b are also referred to as the first movement sensor 20a and the second movement sensor 20b hereinafter. In an embodiment, the first movement sensor 20a and the second movement sensor 20b are electrically coupled to the main control circuit 21. As shown below with reference Figures 2 to 4 As further described, the first motion sensor 20a and the second motion sensor 20b are placed at the eyes of a person to detect cornea-retinal potential (CRP) of the eyes of the person.

[0033] In an embodiment, the first movement sensor 20a is configured to detect eye movement of the user along a first movement axis, and the second movement sensor 20b is configured to detect eye movement of the user along a second movement axis that is transverse (orthogonal in an embodiment) to the first movement axis.

[0034] Thereafter, consider an exemplary and non-limiting situation in which a user's eye movements along a first movement axis correspond to vertical movements of the user's gaze (i.e., eye movements from bottom to top, and eye movements from top to bottom), and the user's eye movements along a second movement axis correspond to horizontal movements of the user's gaze (i.e., eye movements from left to right, and eye movements from right to left).

[0035] In other words, the first movement axis corresponds to the vertical axis of the user's eye, and the second movement axis corresponds to the horizontal axis of the user's eye. Figure 2 A first axis of movement is shown with the reference numeral 40 and a second axis of movement is shown with the reference numeral 42 .

[0036] In an embodiment, consider exemplarily a front view of a user's face, such as in Figure 2 , the first movement axis 40 is parallel to the longitudinal axis (or symmetry axis) 44 of the user's face, and the second movement axis 42 is parallel to or coincident with the transverse axis 46 of the user's face. For example, the longitudinal axis 44 passes through the user's forehead and chin and is equidistant from the user's eyes 50, while the transverse axis 46 is orthogonal to the longitudinal axis 44 and passes through both eyes 50 of the user.

[0037] In more detail, each of the first and second motion sensors 20 a and 20 b includes a sensor control circuit 15 and two or more corresponding electrodes electrically coupled to the sensor control circuit 15 .

[0038] exist Figure 1 In the embodiment exemplarily considered in the figure, the first electrode and the second electrode for each first motion sensor 20a and the second motion sensor 20b are exemplarily considered, and the first electrode and the second electrode are respectively represented by figure marks 22a and 22b; however, the number of electrodes for each first motion sensor 20a and the second motion sensor 20b can be more (for example, four electrodes, as described below).

[0039] The first electrode 22a and the second electrode 22b of the first motion sensor 20a are spaced apart from each other along a first motion axis, and the first electrode 22a and the second electrode 22b of the second motion sensor 20b are spaced apart from each other along a second motion axis, as described below.

[0040] In an embodiment, the first motion sensor 20a and the second motion sensor 20b are respective electrostatic charge change sensors capable of detecting the CRP of a human eye.

[0041] In use, each of the first electrode 22a and the second electrode 22b detects a corresponding electrostatic charge change caused by the user's eye movement, as described below, and generates a corresponding detection signal S indicative of the electrostatic charge change. R .

[0042] In detail, each first electrode 22a and second electrode 22b may have a metal surface, or be made of an all-metal material coated with a dielectric material, or even have a metal surface placed under the housing of the device 10. In any case, during use, each first electrode 22a and second electrode 22b is electrostatically coupled to the environment in which the device 10 is present, and more specifically to the user's eyes, which are closer to the first electrode 22a and second electrode 22b in question, to detect electrostatic charge changes induced thereto.

[0043] Each first electrode 22a and second electrode 22b may be integrated into the housing of device 10 and, for example, may be formed by a conductive track formed on or in a wafer of semiconductor material included in device 10. Alternatively, each first electrode 22a and second electrode 22b may be a metal element present in device 10. Optionally, when possible use of device 10 in a humid environment (more specifically in water) is envisaged, each first electrode 22a and second electrode 22b may be inserted into a waterproof housing, or in any case, may be shielded using one or more protective layers to prevent direct contact between first electrode 22a and second electrode 22b and water or moisture: in this case, the waterproof housing or one or more protective layers are, for example, materials that do not shield the electrostatic charge generated by the user's eyes (e.g., dielectric or insulating materials, such as plastic materials), which will be picked up by first electrode 22a and second electrode 22b. It will be apparent to a person skilled in the art that other embodiments are also possible, so that first electrode 22a and second electrode 22b are electrostatically coupled to the user's eyes during use.

[0044] In addition, according to an exemplary embodiment, the sensor control circuit 15 (such as a microprocessor, a microcontroller or a dedicated computing circuit) is an electronic control circuit, which may include: an interface circuit 17 (optional and known type) coupled to each other, the interface circuit being electrically coupled to the first electrode 22a and the second electrode 22b so that the first electrode 22a and the second electrode 22b are connected to the sensor control circuit 15 (for example, the interface circuit 17 includes an amplification circuit or an analog-to-digital converter ADC, not shown); a corresponding processing circuit 16, which is used to process the detection signal S obtained through the first electrode 22a and the second electrode 22b R and corresponding data storage circuitry 18 (such as a memory, e.g. a non-volatile memory) for storing the acquired data. For example, the sensor control circuitry 15 is integrated into the first and second movement sensors 20a, 20b.

[0045] In detail, each sensor control circuit 15 is configured to process (in a manner known per se, for example by amplification and conversion into digital form) a respective detection signal S acquired via the first electrode 22a and the second electrode 22b. R , and generates a corresponding electrostatic charge change signal S Q,1 , S Q,2 , electrostatic charge change signal S Q,1 , S Q,2 Indicates the detection signal S obtained by the first electrode 22a and the second electrode 22b of the first motion sensor 20a and the second motion sensor 20b respectively. R In an embodiment, the electrostatic charge change signal S Q,1 , S Q,2 (eg, digital type) indicates the difference between the electrostatic charge changes detected by the first electrode 22a and the second electrode 22b. Q,1 =S R,1a -S R,1b (Where S R,1a is the detection signal S obtained by the first electrode 22a of the first motion sensor 20a R , and S R,1b is the detection signal S obtained by the second electrode 22b of the first motion sensor 20a R ), and S Q,2 =S R,2a -S R,2b (Where S R,2a is the detection signal S obtained by the first electrode 22a of the second motion sensor 20b R , and S R,2b is the detection signal S obtained by the second electrode 22b of the second motion sensor 20b R ).

[0046] Figure 2 An embodiment of the device 10 is illustrated, wherein the device 10 is directly worn by a user, ie, wherein the first and second electrodes 22a, 22b of the first and second movement sensors 20a, 20b are releasably coupled (in detail, detachably joined) to the facial skin of the user.

[0047] In an embodiment, in this embodiment, the device 10 may include a corresponding coupling element 52 for each first electrode 22a and second electrode 22b of the first mobile sensor 20a and the second mobile sensor 20b. The coupling element 52 is fixed to the first electrode 22a and the second electrode 22b, and allows it to be coupled (in detail, temporarily bonded) to the facial skin of the user. In an embodiment, the coupling element 52 (e.g., a patch of a known type) each has a corresponding first surface to which the first electrode 22a and the second electrode 22b are fixed, and a second adhesive surface, when the second adhesive surface is placed in contact with the facial skin, the second adhesive surface adheres to the facial skin and releasably couples the first electrode 22a and the second electrode 22b to the facial skin of the user. To this end, the second adhesive surface has a layer of, for example, an adhesive material (e.g., glue).

[0048] like Figure 2 As shown, the first electrode 22a and the second electrode 22b of the first motion sensor 20a are aligned with and spaced apart from each other along the first motion axis 40, and extend from opposite sides of one of the two eyes 50 of the user (here, exemplarily, the left eye or the first eye 50a of the user) along the first motion axis 40. Similarly, the first electrode 22a and the second electrode 22b of the second motion sensor 20b are aligned with and spaced apart from each other along the second motion axis 42, and extend from opposite sides of the other of the two eyes 50 of the user (here, exemplarily, the right eye or the second eye 50b of the user) along the second motion axis 42.

[0049] although Figure 2 A case is shown in which the first electrode 22a and the second electrode 22b of the first motion sensor 20a are placed at the left eye 50a and the first electrode 22a and the second electrode 22b of the second motion sensor 20b are placed at the right eye 50b, but it is obvious that this is for illustrative purposes, and other cases may be similarly considered, such as a case in which the first electrode 22a and the second electrode 22b of the first motion sensor 20a are placed at the right eye 50b and the first electrode 22a and the second electrode 22b of the second motion sensor 20b are placed at the left eye 50a, a case in which the first electrode 22a and the second electrode 22b of the first motion sensor 20a and the first electrode 22a and the second electrode 22b of the second motion sensor 20b are all placed at the left eye 50a, or a case in which the first electrode 22a and the second electrode 22b of the first motion sensor 20a and the first electrode 22a and the second electrode 22b of the second motion sensor 20b are all placed at the right eye 50b.

[0050] For example, the first electrode 22a of the first motion sensor 20a may be placed on the upper eyelid of the left eye 50a (e.g., at the upper orbital septum), the second electrode 22b of the first motion sensor 20a may be placed under the lower eyelid of the left eye 50a (e.g., at the lower orbital septum), the first electrode 22a of the second motion sensor 20b may be placed at the lacrimal caruncle of the right eye 50b, and the second electrode 22b of the second motion sensor 20b may be placed at the end of the right eye 50b opposite to the lacrimal caruncle along the second motion axis 42.

[0051] For illustrative purposes only, the first electrode 22a and the second electrode 22b of the first motion sensor 20a are at a first mutual distance D1 from each other along the first motion axis 40, for example, between about 5 cm and about 7 cm, and the first electrode 22a and the second electrode 22b of the second motion sensor 20b are at a second mutual distance D2 from each other along the second motion axis 42, for example, between about 6 cm and about 8 cm.

[0052] like Figure 2 As shown, the remaining components of the device 10 may also be worn by the user, similar to the first and second electrodes 22a, 22b of the first and second motion sensors 20a, 20b.

[0053] In an embodiment, the main control circuit 21 can be fixed to another coupling element 52, similar to the coupling elements described previously, for example, which can be releasably coupled to the user's body (e.g., in Figure 2 The neck is shown as an example in FIG.

[0054] In addition, and in Figure 2 In a manner not shown, each sensor control circuit 15 of the first mobile sensor 20a and the second mobile sensor 20b can be fixed to one of the coupling elements 52 of the first electrode 22a and the second electrode 22b, can be fixed to the coupling element 52 of the main control circuit 21, or can be fixed to another coupling element 52 that is detachably fixed to the user's body.

[0055] In addition, the main control circuit 21 is coupled to the first and second motion sensors 20a and 20b through an unshown electrical connection or electromagnetically (eg, a transmitter module and a receiver module respectively included in the first and second motion sensors 20a and 20b and the main control circuit 21).

[0056] Figure 3 An embodiment of device 10 is illustrated, wherein device 10 is included in an optical support apparatus 100 that is wearable on a user's face and configured to affect their vision.

[0057] In an embodiment, the optical support device 100 can be a pair of glasses or headphones (e.g., artificial headphones for gaming or augmented reality). For example, the glasses can be prescription glasses or sunglasses, or a type of smart glasses.

[0058] Hereinafter, reference will be made to the case where the optical support device 100 is a pair of glasses. However, this is done only to simplify the description and is not intended to be limiting.

[0059] In an embodiment, the optical support device 100 includes a frame 112 having a first support portion 112a and a second support portion 112b (e.g., annular shape), and the first support portion 112a and the second support portion 112b are configured to face the left eye 50a and the right eye 50b, respectively, when the user wears the optical support device 100. In detail, the frame here may mean any support structure of glasses, headphones, etc. facing the user's eyes when in use.

[0060] In an embodiment, the first supporting portion 112a and the second supporting portion 112b support or accommodate the first lens 114a and the second lens 114b.

[0061] exist Figure 3 In the embodiment of the present invention, the frame 112 carries components of the device 10 that are fixed to the frame 112. For example, the main control circuit 21 is fixed to the frame 112 and can be integrated therein.

[0062] The first and second movement sensors 20 a and 20 b are carried by the first and second support portions 112 a and 112 b of the frame 112 , and are placed near the eyes of the user when the user wears the optical support device 100 .

[0063] In the embodiment, the first electrode 22a and the second electrode 22b of the first motion sensor 20a are fixed to the first support portion 112a, aligned and spaced apart from each other along the first movement axis 40, and extend from the opposite sides of the first lens 114a along the first movement axis 40, and thus extend from the opposite sides of one of the two eyes 50 of the user (here, exemplarily, the left eye 50a of the user) when the optical support device 100 is worn. Similarly, the first electrode 22a and the second electrode 22b of the second motion sensor 20b are fixed to the second support portion 112b, aligned and spaced apart from each other along the second movement axis 42, and extend from the opposite sides of the second lens 114b along the second movement axis 42, and thus extend from the opposite sides of the two eyes 50 of the user (here, exemplarily, the right eye 50b of the user).

[0064] For example, the first and second electrodes 22a and 22b of the first and second motion sensors 20a and 20b extend at inner surfaces of the first and second support portions 112a and 112b that face the eyes of the user when the user wears the optical support device 100.

[0065] For exemplary purposes, the first electrode 22a of the first motion sensor 20a may be carried by an upper portion of the first support portion 112a (e.g., near the upper orbital septum), the second electrode 22b of the first motion sensor 20a may be carried by a lower portion of the first support portion 112a opposite the upper portion along the first motion axis 40 (e.g., near the lower orbital septum), and the first electrode 22a of the second motion sensor 20b may be carried by a left portion of the second support portion 112b (e.g., at the bridge of the optical support device 100, and therefore at the nose of the user), and the second electrode 22b of the second motion sensor 20b may be carried by a right portion of the second support portion 112b opposite the left portion along the second motion axis 42 (e.g., at the right arm of the optical support device 100, and therefore on the opposite side of the second support portion 112b relative to the bridge of the optical support device 100).

[0066] Similar to the above, and for illustrative purposes only, the first electrode 22a and the second electrode 22b of the first motion sensor 20a can be separated from each other by a first mutual distance D1 along the first motion axis 40, for example, between about 3 cm and about 5 cm, and the first electrode 22a and the second electrode 22b of the second motion sensor 20b can be separated from each other by a second mutual distance D2 along the second motion axis 42, for example, between about 6 cm and about 8 cm.

[0067] In addition, the main control circuit 21 is coupled to the first and second motion sensors 20a and 20b through an unshown electrical connection or electromagnetically (eg, a transmitter module and a receiver module respectively included in the first and second motion sensors 20a and 20b and the main control circuit 21).

[0068] Figure 4 A different embodiment of the optical support device 100 is shown, in which the first electrode 22a and the second electrode 22b of the first motion sensor 20a and the second motion sensor 20b are not carried by the frame 112 as described above, but by the first lens 114a and the second lens 114b. In an embodiment, the first electrode 22a and the second electrode 22b are integrated in the first lens 114a and the second lens 114b.

[0069] In an embodiment, Figure 4The first and second electrodes 22a and 22b of the first and second movement sensors 20a and 20b are located radially relative to the centers of the corresponding lenses 14a and 14b. Figure 3 The first and second electrodes 22a and 22b of the first and second motion sensors 20a and 20b are formed inside the first and second electrodes 22a and 22b of the first and second motion sensors 20a and 20b.

[0070] The first electrode 22a and the second electrode 22b of the first movement sensor 20a are fixed to the first lens 114a, aligned and spaced apart from each other along the first movement axis 40, and can extend at respective ends of the first lens 114a that are opposite to each other along the first movement axis 40 (thus, in the example considered herein, they extend from opposite sides of the left eye 50a). Similarly, the first electrode 22a and the second electrode 22b of the second movement sensor 20b are fixed to the second lens 114b, aligned and spaced apart from each other along the second movement axis 42, and can extend at respective ends of the second lens 114b that are opposite to each other along the second movement axis 42 (thus, in the example considered herein, they extend from opposite sides of the right eye 50b).

[0071] In detail, the first and second electrodes 22a and 22b of the first and second motion sensors 20a and 20b may extend to inner surfaces of the first and second lenses 114a and 114b that face the eyes of the user when the user wears the optical supporting device 100.

[0072] Therefore, the first electrode 22a and the second electrode 22b of the first movement sensor 20a may be spaced apart from each other along the first movement axis 40 by a respective first mutual distance D1′ that is less than Figure 2 and Figure 3 The first mutual distance D1 in the embodiment is, for example, comprised between about 2 cm and about 4 cm, and the first electrode 22a and the second electrode 22b of the second movement sensor 20b may be spaced apart from each other along the second movement axis 42 by a corresponding second mutual distance D2' that is less than Figure 2 and Figure 3 The second mutual distance D2 is in the range of about 3 cm to about 5 cm.

[0073] Generally speaking, and if Figure 5 As shown, since the eye 50 operates as an electric dipole, the positive pole of the electric dipole is located at the cornea ( Figure 5 50' in the figure) and the negative electrode is located at the retina ( Figure 5The movement of the eye 50 generates electric field changes in the environment around the eye 50, and these electric field changes induce electrostatic charge changes, which can be detected by the first electrode 22a and the second electrode 22b. Since the first electrode 22a and the second electrode 22b are physically and electrically separated from each other, they are at different distances relative to the cornea 50' and the retina 50", and therefore detect electrostatic charge changes that are different from each other. As described below, this allows differential detection of electrostatic charge changes.

[0074] This enables both eye movement without blinking (via the first motion sensor 20a or the second motion sensor 20b, depending on the direction of the movement of the eye 50) and the user's blinking (via the first motion sensor 20a, whose first electrode 22a and second electrode 22b are aligned with each other, parallel to the direction of the movement of the eye 50 during the blink) to be detected. In fact, with regard to blinking, it has been demonstrated that each blink corresponds to a corresponding electrostatic charge change indicating a blink.

[0075] In more detail, it has been verified that such movement of the eye 50 when blinking occurs is reflected in the corresponding electrostatic charge change signal S Q,1 In the embodiment, the first and second peaks are generated in the blink cycle, and are generated continuously with each other in a blink cycle of a duration shorter than about 50 milliseconds, and the two corresponding peaks have opposite signs relative to the baseline of the signal. In the embodiment, a zero baseline is exemplarily considered, and depending on the direction of movement of the eye 50 and the position of the first electrode 22a and the second electrode 22b, there can be a first positive peak and a second negative peak, or vice versa. These first peaks and second peaks that are continuous with each other in the blink cycle define a blink scheme (or pattern) indicating a (deliberate or unintentional) blink. More details on blink patterns and generally on the detection of intentional or unintentional blinks are provided in patent document EP4173567 of the same applicant.

[0076] In contrast, the movement of the eye 50 when the eyelids are not completely closed generates an electrostatic charge change signal S Q,1 or S Q,2 In an embodiment, the electrostatic charge change signal S is isolated from each other over time according to the movement direction of the eye 50 and the positions of the first electrode 22a and the second electrode 22b of the first motion sensor 20a and the second motion sensor 20b. Q,1 or S Q,2 This type of peak in the electrostatic charge change signal S Q,1 or S Q,2 The corresponding baseline can be positive or negative (the latter is also called the valley). FIG. 8A to FIG. 8D The electrostatic charge change signal S is provided Q,1 , S Q,2An example of such a peak in .

[0077] Generally speaking, in this discussion, movement of the eye 50 is considered to be an angular displacement of the eye 50 about its center of rotation relative to a predetermined position, which corresponds to the center position of the eye 50, that is, the center position when the user is looking straight ahead.

[0078] In more detail, Figure 6 As shown, here considering the visual axis 60, the rotation center 62 of the eye 50 and the pupil center 64 of the pupil 66 of the eye 50 are aligned along the visual axis 60. At the central position of the eye 50, the visual axis 60 coincides with the reference axis 60', which passes through the rotation center 62 and is substantially orthogonal to the face of the user. When the eye 50 rotates around its rotation center 62, the visual axis 60 deviates from the reference axis 60' to be transverse thereto and forms a rotation angle α (in detail, a solid angle defined in a reference system with polar coordinates, the origin of which is at the rotation center 62 of the eye 50). The angular displacement of the eye 50 identified by the rotation angle α corresponds to the movement of the eye 50 described previously.

[0079] Specifically, possible movements of the eye 50 may be categorized and included in a plurality of predetermined movement categories, each movement category being identified by a corresponding reference angular position of the eye 50. These reference angular positions are defined based on a vision grid 68 that is located on a reference plane 70 that is orthogonal to the reference axis 60' and is centered at an intersection 72 of the reference axis 60' and the reference plane 70.

[0080] Figure 7 An example of a visual grid 68 having a square shape is shown. In an embodiment, the visual grid 68 is Figure 7 7 is shown in a two-axis Cartesian reference system, the origin of which is at the intersection 72 and which is defined by grid axes 40' and 42', which are respectively associated with the first movement axis 40 and the second movement axis 42. In detail, the grid axes 40' and 42' are respectively parallel to the first movement axis 40 and the second movement axis 42; for example, the grid axes 40' and 42' may correspond to the projections of the first movement axis 40 and the second movement axis 42, respectively, on the reference plane 70, or in any case are parallel to these projections.

[0081] In the vision grid 68, the following reference angular positions of the eye 50 are identified, defined along the grid axis 40' according to standardized coordinates: center 75a, coinciding with intersection 72, defined by coordinates (0,0); right position 75b, defined by coordinates (1,0); upper right position 75c, defined by coordinates (1,1); top position 75d, defined by coordinates (0,1); upper left position 75e, defined by coordinates (-1,1); left position 75f, defined by coordinates (-1,0); lower left position 75g, defined by coordinates (-1,-1); bottom position 75h, defined by coordinates (0,-1); and lower right position 75i, defined by coordinates (1,-1).

[0082] In an embodiment, each reference angular position of the eye 50 (except the center position 75a) can also be identified by a corresponding value of the inclination angle β defined between the positive semi-axis of the grid axis 42' and the angular position axis 76, which connects the reference angular position under consideration with the center position 75a.

[0083] Specifically, the right position 75b is defined by β=0°, the upper right position 75c is defined by β=45°, the top position 75d is defined by β=90°, the upper left position 75e is defined by β=135°, the left position 75f is defined by β=180°, the lower left position 75g is defined by β=225°, the bottom position 75h is defined by β=270°, and the lower right position 75i is defined by β=315°.

[0084] These reference angular positions correspond to the corresponding positions of the eye 50 in the user's visual reference system, and therefore to corresponding values ​​of the rotation angle α. For example, the upper right position corresponds to when the user is looking to the upper right, and so on.

[0085] Each of these reference angular positions identifies a corresponding movement class of the eye 50 , ie, a respective set of eye angular positions.

[0086] For illustrative and non-limiting purposes only, the following categories of movement of the eye 50 are based on the tilt angle β and distance L ( Figure 70 and 22.5°≤β<67.5°; the top category includes the top position 75d and is defined by L≠0 and 67.5°≤β<112.5°; the top left category includes the top left position 75d and is defined by L≠0 and 67.5°≤β<112.5°; and the top right category includes the top right position 75c and is defined by L≠0 and 22.5°≤β<67.5°. 5e, and is defined by L≠0 and 112.5°≤β<157.5°; the left category includes the left position 75f, and is defined by L≠0 and 157.5°≤β<202.5°; the lower left category includes the lower left position 75g, and is defined by L≠0 and 202.5°≤β<247.5°; the bottom category includes the bottom position 75h, and is defined by L≠0 and 247.5°≤β<292.5°; the lower right category includes the lower right position 75i, and is defined by L≠0 and 292.5°≤β<337.5°.

[0087] However, other examples of the definition of the movement categories of the eye 50 can be similarly considered. For example, the movement categories may not be defined by angular endpoints that are angularly equidistant (i.e., they may be defined by angular ranges that are different from each other). According to another example of the definition of the movement categories of the eye 50, the same ranges of the tilt angle β described previously apply, but the center category does not include a unique center position 75a, and instead of presenting L≤L th , where L th For example, it is equal to 0.1, while the rest of the mobile categories show L>L th .

[0088] FIG. 8A to FIG. 8D The diagram shows the electrostatic charge change signal S obtained by the first motion sensor 20a and the second motion sensor 20b under different conditions. Q,1 and S Q,2 Examples of, as now shown and discussed.

[0089] In an embodiment, Fig. 8A and Figure 8B The first electrostatic charge change signal S obtained by the first electrode 22a and the second electrode 22b of the first motion sensor 20a is shown. Q,1 Therefore, the first electrostatic charge change signal S Q,1 The movement of the left eye 50a along the first movement axis 40 is indicated (ie the fact that the intersection of the visual axis 60 with the reference plane 70 is displaced along the grid axis 40' is indicated).

[0090] In more detail, Fig. 8AIt means that the user starts from the center position 75a, first moves the eye 50 downward (positive main peak K1, indicating downward movement), and then moves the eye back to the center position 75a (negative main peak K2, indicating upward movement) after a time interval Δt (e.g., measured between the maximum amplitudes of the absolute values ​​of the main peaks K1 and K2). Figure 8B Concerning the opposite case, where the user starts from the center position 75a, first moves the eye 50 upward (negative main peak K1, indicating upward movement), and then moves the eye back to the center position 75a after a time interval Δt (positive main peak K2, indicating downward movement)

[0091] Figure 8C and Fig.8D The second electrostatic charge change signal S obtained by the first electrode 22a and the second electrode 22b of the second motion sensor 20b is shown. Q,2 Therefore, the second electrostatic charge change signal S Q,2 Movement of the right eye 50b along the second movement axis 42 is indicated (ie, the intersection of the visual axis 60 with the reference plane 70 is displaced along the grid axis 42').

[0092] In more detail, Figure 8C This means that the user starts from the center position 75a, first moves the eye 50 to the left (positive main peak K1, indicating leftward movement), and then moves the eye back to the center position 75a after a time interval Δt (negative main peak K2, indicating rightward movement). Fig.8D Refers to the opposite situation, the user starts from the center position 75a, first moves the eye 50 to the right (negative main peak K1, indicating rightward movement), and then moves the eye back to the center position 75a after a time interval Δt (positive main peak K2, indicating leftward movement)

[0093] In use, the main control circuit 21 implements the detection method 150 to detect movement of the user's eye 50.

[0094] Fig. 9 An exemplary detection method 150 is shown. In an embodiment, an iteration of the detection method 150 is described below, but it is clear that the detection method 150 is of iterative type and therefore comprises the execution of a plurality of these iterations consecutive to each other.

[0095] Specifically, in step S10 (optional) of the detection method 150, the main control circuit 21 verifies the feasibility conditions for determining the movement of the eye 50, ie verifies whether the determination of the movement of the eye 50 can occur within the considered time.

[0096] If one or more certain factors or events are detected that can affect the movement of the eye 50, the feasibility condition may not be confirmed, thereby reducing its accuracy, so that the measurement may not have sufficient information. For example, this can happen when the user moves his / her head. In this case, the direction of the user's gaze depends not only on the rotation of the eye 50 in the eye socket, but also on the displacement of the head relative to the fixed inertial reference frame.

[0097] In an embodiment, the verification of the feasibility condition includes verifying whether the user's head moves relative to a fixed inertial reference frame, for example, based on measurements performed by one or more inertial sensors (for example, accelerometers or gyroscopes in MEMS-type embodiments). In detail, these inertial sensors can also be included in the device 10, can be electrically coupled or operatively coupled to the main control circuit 21, and can be carried by the frame 112 or releasably coupled to the user's head, similar to what has been described previously.

[0098] In more detail, the verification of head movement is performed in a manner known per se, for example, by acquiring inertial data indicating whether head movement of the user has occurred from one or more inertial sensors, and determining whether head movement has occurred based on the inertial data. This can occur in a manner known per se, for example, using machine learning techniques implemented by the feature extraction and classifier modules described previously.

[0099] For example, more details on how the verification can be performed can be found in the document “Using Inertial Sensors to Determine Head Motion—A Review”, Severin Ionut-Cristian and Dobrea Dan-Marius, Journal of Imaging, 2021.

[0100] If head movement is detected, the iteration stops and the method does not proceed to the subsequent steps. In other words, in this case, the determination of the movement of the eye 50 is not performed, because it may not be accurate enough.

[0101] Alternatively, if no head movement is detected, the method proceeds to the steps described subsequently.

[0102] In step S10, the type of head movement or user activity can also be determined by head motion tracking and environment perception techniques known per se. In this case, it is possible to prevent subsequent steps from being performed when a predetermined head movement (e.g., very fast or predetermined type of movement) or predetermined activity (e.g., running, etc.) of the user is detected to be more likely to invalidate subsequent measurements, and it is possible to allow these steps to be performed in the opposite case.

[0103] In step S12 after step S10, the main control circuit 21 obtains the first electrostatic charge change signal S from the first motion sensor 20a and the second motion sensor 20b respectively. Q,1 and the second electrostatic charge change signal S Q,2 The first electrostatic charge change signal S Q,1 indicates the movement of the eye 50 along the first movement axis 40, and the second electrostatic charge change signal S Q,2 The movement of the eye 50 is indicated along a second movement axis 42 transverse to the first movement axis 40. In other words, the movement of the eye 50 is decomposed herein along two axes transverse to each other and analyzed below based on this decomposition.

[0104] In step S14 after step S12, the main control circuit 21 uses the electrostatic charge change signal S Q,1 and S Q,2 Initially, one or more possible events indicative of movement of the eye 50 along the first axis of movement 40 or the second axis of movement 42, respectively, are detected (ie, identified).

[0105] In an embodiment, this is accomplished by verifying the electrostatic charge change signal S Q,1 and S Q,2 This is achieved by showing one or more peaks indicating the corresponding displacement of the eye 50 along the first movement axis 40 and the second movement axis 42, respectively. These peaks are, for example, FIG. 8A to FIG. 8D The main peaks K1 and K2 are shown in FIG.

[0106] In more detail, this can be done in the following way.

[0107] First, the electrostatic charge change signal S Q,1 and S Q,2 The filtering is performed to remove the contribution induced by low-frequency alternating electric fields that may be present in the environment surrounding the device 10. In fact, the alternating electric field, if any, induces corresponding charge variations on the first and second motion sensors 20a, 20b, electrostatic charge variation signals S at different frequencies (for example, at the frequency of the alternating current, i.e. 50 Hz or 60 Hz, depending on the country in which one is located) Q,1 , S Q,2 In an embodiment, the filtering performed may be of the low-pass type with a cut-off frequency lower than a first threshold frequency (e.g., equal to about 25 Hz), or of the band-pass type with a lower cut-off frequency higher than a second threshold frequency (lower than the first threshold frequency and, for example, equal to about 1 Hz) and an upper cut-off frequency lower than the first threshold frequency and, for example, equal to 20 Hz, or of the notch type with a lower cut-off frequency, for example, equal to 40 Hz and an upper cut-off frequency higher than about 70 Hz.

[0108] In addition, the electrostatic charge change signal S Q,1 and S Q,2 The respective electrostatic charge variation signal S is processed to remove the respective offset of the latter, specifically, the respective baseline of the latter (i.e., a reference value, which is not necessarily constant over time and may vary at a very low frequency such as about 0.2 Hz, for example) is subtracted from each of them. Q,1 and S Q,2 Around it develops; for example, an average value). In this way, in the following, the electrostatic charge change signal S about the zero baseline can be considered Q,1 and S Q,2 , and does not take into account any offset.

[0109] In addition, the electrostatic charge change signal S can be processed in a known manner. Q,1 and S Q,2 , to identify any peak value (i.e., positive peak value or negative peak value). In detail, it is possible to identify the electrostatic charge change signal S Q,1 and S Q,2 The number of peaks (if any) of the electrostatic charge change signal S can be determined, and for each peak, the corresponding maximum value and the corresponding time position (or moment) of the maximum value can be identified. This is done in a manner known per se. For example, more details about the identification mode of such peaks can be found in the patent document US20220366768 of the applicant. Alternatively, the electrostatic charge change signal S Q,1 and S Q,2 The value of the electrostatic charge change signal S in the time window considered is greater than a threshold value (e.g., a predetermined value, such as equal to about 200LSB or equal to the corresponding electrostatic charge change signal S in the time window considered). Q,1 , S Q,2 The portion of the value that is approximately 10% of the maximum value) can be considered as the peak.

[0110] Finally, the electrostatic charge change signal S Q,1 , S Q,2 The detected peak value may be verified or not based on reliability criteria so as not to take into account the electrostatic charge variation signal S Q,1 , S Q,2 , which does not indicate movement of the eyes along the first movement axis 40 and the second movement axis 42, and which may be caused, for example, by footsteps of the user or another person, sudden movement of the body on an object (such as a plastic chair), etc.

[0111] More specifically, if the electrostatic charge change signal S Q,1 , S Q,2If the detected peaks meet the conditions, they meet the reliability criteria, for example, as disclosed in patent documents such as document US2023137601 (for example, regarding the detection of unintentional blinks) and document US2022366768 of the same applicant.

[0112] These exemplary sub-steps of step S14 described so far are provided for illustrative and non-limiting purposes and may be performed consecutively to one another, or even only a subset thereof (eg without removing the baseline) may be performed.

[0113] If an event indicating that the eye 50 has moved along the first axis of movement 40 or the second axis of movement 42 has not been detected (step S16 following step S14), the iteration ends and the detection method 150 restarts from step S10.

[0114] In contrast, if an event indicating movement of the eye 50 along the first axis of movement 40 or the second axis of movement 42 has been detected (step S16 following step S14 ), the detection method 150 proceeds to step S18 following step S16 .

[0115] In step S18, the main control circuit 21 generates a signal based on the electrostatic charge change signal S Q,1 , S Q,2 The event of start detection is used to determine the movement of the eye 50.

[0116] In an embodiment, eye movement is detected by reconstructing a biaxial movement from a uniaxial displacement previously detected along at least one of the first movement axis 40 and the second movement axis 42. In other words, a biaxial (i.e., overall) movement of the eye 50 is generated starting from the correlation of uniaxial displacements along the first movement axis 40 and the second movement axis 42 (i.e., partial displacements along a single axis).

[0117] The electrostatic charge change signal S Q,1 , S Q,2 In the case where only one of the two first movement axes 40 and the second movement axis 42 presents an event, it is determined that the detected movement of the eye 50 occurs only along one of the two first movement axes 40 and the second movement axis 42, that is, corresponding to the electrostatic charge change signal S Q,1 , S Q,2 For example, if the first electrostatic charge change signal S Q,1 An event indicating upward movement along the first movement axis 40 is presented, and the second electrostatic charge change signal S Q,2 Without presenting an event, the movement of the eye 50 has occurred only along the first movement axis 40 and is of top type.

[0118] If the two electrostatic charge change signals S Q,1 , S Q,2If the events are presented simultaneously (i.e., the events are presented in respective time windows that substantially overlap and coincide with each other), it is determined that the detected movement of the eye 50 occurs along both the first movement axis 40 and the second movement axis 42. For example, if the first electrostatic charge change signal S Q,1 An event indicating upward movement along the first movement axis 40 is presented, and the second electrostatic charge change signal S Q,2 Presenting an event indicating a movement to the right along the second movement axis 42 , the movement of the eye 50 has occurred along the first movement axis 40 and the second movement axis 42 and is of the right-up type.

[0119] In addition, in step S18, the main control circuit 21 can also determine a new reference angular position of the eye 50, that is, update the reference angular position of the eye 50 after the detected movement.

[0120] This may be done based on vision grid 68 and a previous reference angular position of eye 50 .

[0121] For the purpose of illustration, assuming that the aforementioned reference angular position is the center position 75a, detecting the upper right movement of the eye 50 along the first movement axis 40 and the second movement axis 42 means that the reference angular position is updated to the upper right position 75c. Subsequent iterations will therefore use this new reference angular position as a starting point to define subsequent reference angular positions.

[0122] In addition, and in a manner not shown, the detection method 150 may also include an optional step of controlling an electronic device external to the apparatus 10 based on the detected movement or the newly detected reference angular position. In an embodiment, the electronic device may be a TV, a screen, a PC, etc., and one of its functions may be controlled based on the detected movement or the newly detected reference angular position (e.g., changing a TV channel, modifying an option on a PC or tablet, etc.).

[0123] In the embodiment, the electrostatic charge change signal S Q,1 and S Q,2 The method to identify eye movements is based on artificial intelligence and machine learning (AI / ML) technology.

[0124] Specific signal S Q,1 and S Q,2 Providing a fingerprint of specific eye movements. The signal can be filtered to remove contributions from power line noise caused by low frequency alternating electric fields and can be processed to remove offset or baseline.

[0125] In an embodiment, a data set of unique patterns is created. The data set may be formed by two vectors aligned in time associated with a particular eye movement, where the first vector corresponds to, for example, S Q,1signal with K1 and K2 peaks for the left eye associated with horizontal movement. In addition, the second vector corresponds to, for example, S Q,2 A signal having K1 and K2 peaks for the right eye associated with vertical movement. In an embodiment, the pattern is a vector of electrostatic charge variation signals, and the label corresponds to the specific eye movement that has generated the pattern itself.

[0126] When the signal S is processed Q,1 and S Q,2 When detecting eye activity, in the simplest case, by verifying the presence of a signal change that exceeds a predetermined threshold, the pre-trained system can be used to classify the resulting pattern into categories of eye movement, such as upper left, up, or upper right; left, middle, or right; lower left, down, or lower right; or a combination thereof.

[0127] In an embodiment, the artificial intelligence or machine learning (AI / ML) system may be implemented by any well-known network, such as a convolutional neural network (CNN), a temporal convolutional network (TCN), a long short-term memory (LSTM) network, or a machine learning language model based on a learning phase of a labeled dataset.

[0128] Used to explain the electrostatic charge change signal S Q,1 and S Q,2 The method of identifying eye movements can be extended to use multiple electrodes on both the left and right eyes. Therefore, the unique pattern can be extended to the number of electrodes. In an embodiment, the AI / ML system is pre-trained using a dataset formed by the extended pattern. If we consider Fig.10 The electrodes shown in FIG. 1 and FIG. 2 can form the following four vectors: (1) S from the left eye electrodes (22a and 22b) Q,1L , (2) S from the left eye electrodes (22c and 22d) Q,2L , (3) S from the right eye electrodes (22a and 22b) Q,1R , and (4) S from the right eye electrodes (22c and 22d) Q,2R .

[0129] In general, the advantages provided by the invention can be demonstrated by examining the features of the invention made in accordance with the invention. Due to the proximity of the first and second electrodes 22a, 22b to the eye 50, the previously described device 10 and detection method 150 enable the detection of movement of the eye 50 with high accuracy.

[0130] Detecting eye movement 50 may be relevant to applications such as smart glasses that require knowledge of the direction of the user's gaze. For example, eye tracking may activate advanced features for adjusting the focus of a camera lens or quick reading features such as zoom and panorama operations. Other applications involve detecting a user's attention level, risk of falling asleep, or simply activating features in mobile and portable devices or applications like smart TVs.

[0131] Due to the inertial sensors, the possibility of performing the detection method 150 without head movements of the user avoids false detections of eye movements, which are actually due to disturbances generated by head movements.

[0132] In addition, Figure 3 and Figure 4 In the embodiment, the fact that the first electrode 22a and the second electrode 22b are carried by the frame 112 of the optical support device 100 and do not contact the user's facial skin prevents detection errors caused by the first electrode 22a and the second electrode 22b sliding on the skin (for example, when the skin is wet or sweaty).

[0133] The detection method 150 requires reduced computing resources, minimizing the required power consumption.

[0134] Furthermore, it has been verified that the closer the first electrode 22 a and the second electrode 22 b are to the corresponding eye 50 , the better the performance of detecting the change in electrostatic charge caused by the movement of the eye 50 .

[0135] Furthermore, the differential measurement performed by each of the first and second motion sensors 20a, 20b eliminates any common mode measurements of the first and second electrodes 22a, 22b, improving accuracy and robustness.

[0136] Finally, modifications and variations may be made to the invention described and illustrated herein without departing from the scope of the invention as defined in the appended claims.For example, the described embodiments may be combined to provide further solutions.

[0137] In addition, the device 10 may include a single control circuit coupled to the first electrode 22a and the second electrode 22b. For illustration purposes only, the control circuit may include the main control circuit 21 and the sensor control circuit 15, or it may be the main control circuit 21 and the sensor control circuit 15 may not be present; in these cases, the actions of the sensor control circuit 15 previously described with respect to the first motion sensor 20a and the second motion sensor 20b are performed by the main control circuit 21.

[0138] In addition, regarding Figure 2In an embodiment, the electrodes can be releasably fixed directly to the facial skin (ie, without using coupling element 52), for example, by pressure coupling technology. For example, dry electrodes can be used (more details can be found at the link https: / / wearablesensing.com / dry-electrode / ).

[0139] Furthermore, the number of electrodes of the first motion sensor 20a and the second motion sensor 20b may be greater than previously considered, such as Figures 10 to 12 shown.

[0140] In an embodiment, each of the first and second motion sensors 20a and 20b may further include a third electrode 22c and a fourth electrode 22d, which are spaced apart from each other relative to the first and second electrodes 22a and 22b of the first and second motion sensors 20a and 20b and are similar to the first and second electrodes 22a and 22b (and therefore will not be described in detail). The third and fourth electrodes 22c and 22d of each of the first and second motion sensors 20a and 20b are also coupled to the sensor control circuit 15.

[0141] The third electrode 22c and the fourth electrode 22d of the first motion sensor 20a are aligned with each other along the first parallel motion axis 80, which is transverse (specifically, orthogonal) to the first motion axis 40 and, in an embodiment, parallel to or coincident with the second motion axis 42. The third electrode 22c and the fourth electrode 22d of the first motion sensor 20a are arranged at the user's left eye 50a in a manner that is completely similar to how the first electrode 22a and the second electrode 22b of the second motion sensor 20b are arranged relative to the right eye 50b (and therefore will not be described again).

[0142] In an embodiment, the electrodes 22a-22d of the first motion sensor 20a are arranged in a cross or X shape relative to the left eye 50a. In other words, the intersection of the first motion axis 40 and the first parallel motion axis 80 occurs at the left eye 50a, for example at the corresponding pupil.

[0143] Similarly, the third electrode 22c and the fourth electrode 22d of the second motion sensor 20b are aligned with each other along a second parallel motion axis 82 that is transverse (specifically, orthogonal) to the second motion axis 42 and, in an embodiment, parallel to the first motion axis 40.

[0144] The third and fourth electrodes 22c, 22d of the second motion sensor 20b are arranged at the user's right eye 50b in a manner completely similar to how the first and second electrodes 22a, 22b of the first motion sensor 20a are arranged relative to the left eye 50a (and therefore will not be described again).

[0145] In an embodiment, the electrodes 22a-22d of the second motion sensor 20b are arranged in a cross or X shape relative to the right eye 50b. In other words, the intersection of the second motion axis 42 and the second parallel motion axis 82 occurs at the right eye 50b, for example at the corresponding pupil.

[0146] In this embodiment, each sensor control circuit 15 is also configured to process (in a manner known per se, for example by amplification and conversion to digital) the respective detection signal S acquired via the third electrode 22c and the fourth electrode 22d, similarly to what has been previously described for the first electrode 22a and the second electrode 22b. R , and generates a corresponding electrostatic charge change signal S Q,1 , S Q,2 , electrostatic charge change signal S Q,1 , S Q,2 indicates the detection signal S obtained by the third electrode 22c and the fourth electrode 22d of the first motion sensor 20a and the third electrode 22c and the fourth electrode 22d of the second motion sensor 20b, respectively. R In an embodiment, these electrostatic charge change signals S Q,1 , S Q,2 The signals are similar to those already described previously and are each indicative of a corresponding difference between electrostatic charge changes detected by the third and fourth electrodes 22c, 22d of the first and second motion sensors 20a, 20b, respectively.

[0147] For completeness of description, Figures 10 to 12 The previous references are shown respectively. Figures 2 to 4 The described embodiment shows an arrangement of the electrodes 22a-22d of the first motion sensor 20a and the second motion sensor 20b.

[0148] In general, the use of the third electrode 22c and the fourth electrode 22d of each of the first and second motion sensors 20a and 20b makes the detection of the movement of the user's eye 50 more robust and reliable.

[0149] The measurement performed by the first electrode 22a and the second electrode 22b and the measurement performed by the third electrode 22c and the fourth electrode 22d may be used alternately with each other in time, for example, in a periodic manner. For example, in the i-th iteration, the detection method 150 uses the electrostatic charge change signal S obtained by the first electrode 22a and the second electrode 22b of each of the first motion sensor 20a and the second motion sensor 20b. Q,1 , S Q,2 , and in the continuous (i+1)th iteration, the detection method 150 uses the electrostatic charge change signal S obtained through the third electrode 22c and the fourth electrode 22d of each of the first motion sensor 20a and the second motion sensor 20b Q,1 , S Q,2 .

[0150] This makes it possible to analyze the movements of the eye 50 in a completely symmetrical manner, for example, without taking into account measurements related to an asymmetric posture of the eye (e.g. an intentional blink of only one of the two eyes 50), or vice versa, so that it can be taken into account without being mistaken for a symmetrical movement (e.g. an unintentional blink).

[0151] Fig.12 A flow diagram of an embodiment method 1200 for detecting eye movement is illustrated.

[0152] At step 1202, raw data is collected from the plurality of electrodes. In an embodiment, two independent sensor channels detect eye movement along different axes. For example, a first channel may be used to detect vertical eye movement, and a second channel may be used to detect horizontal eye movement. For example, in Fig.11 In the embodiment, the first channel may correspond to the first electrode 22a and the fourth electrode 22d of the second motion sensor 20b, and the second channel may correspond to the first electrode 22a and the second electrode 22b of the first motion sensor 20a.

[0153] At step 1204, separate low pass filtering is performed on the raw data for each channel. For example, the low pass filter may have a cutoff frequency of approximately 2 Hz, which is selected to capture the typical frequency range of human eye movement while excluding faster fluctuations that may represent noise or artifacts. In an embodiment, separate low pass filtering is performed on the raw data for horizontal eye movement and vertical eye movement. Advantageously, filtering isolates the relevant eye movement signals from higher frequency noise. By applying the filters to the horizontal channel and the vertical channel separately, each eye movement dimension is processed appropriately. The filtering step helps to smooth the raw data, removing rapid fluctuations and high frequency interference, which may otherwise lead to false detections or inaccuracies in subsequent processing stages.

[0154] In step 1206, the filtered data of each channel is subjected to separate adaptive baseline removal to eliminate any offset or drift. Once the raw data from the electrodes is filtered, offsets or drifts in the signal are eliminated using the adaptive baseline removal step. Separate adaptive baseline removal helps to isolate the actual eye movement signal from any background fluctuations or slow changes in baseline voltage. Removing unwanted changes makes eye movement detection and measurement more accurate. The adaptive nature of the process enables adjustment of baseline changes over time, which helps maintain accuracy during an extended service life.

[0155] At step 1208, the filtered and baseline-removed data of each channel is amplified individually to enhance signal strength. Amplification can improve the signal-to-noise ratio of the eye movement data, making subtle eye movements easier to detect and analyze. Amplification can include applying a gain factor to the horizontal eye movement channel and the vertical eye movement channel. By increasing the amplitude of the signal, remaining background noise or small fluctuations can be better distinguished from real eye movements.

[0156] At step 1210, a modulus-to-digital (MOD) calculation is performed using the amplified, filtered, and baseline-removed data. This step combines the horizontal and vertical components to determine the overall magnitude of the eye movement. In an embodiment, the modulus-to-digital (MOD) signal (r) may be represented as Where x represents the horizontal component of the data and y represents the vertical component of the data.

[0157] At step 1212, the analog-to-digital signal is subjected to peak detection and width analysis to identify significant eye movements and their duration. In an embodiment, peak detection includes locating local maxima in the analog-to-digital signal corresponding to instances of substantial eye movement exceeding a certain threshold. Thus, peak detection includes a first step in which it is determined whether the analog-to-digital signal exceeds a threshold (r threshold ). For the period when the module signal exceeds the threshold, the peak value in this period corresponds to the peak value of the analog-to-digital signal (r peak ). Together with the peak detection, a width analysis is performed at step 1212, which includes measuring the duration or time range over which the analog-to-digital signal exceeds a threshold. threshold ) indicates eye events.

[0158] At step 1214, the method ends by detecting the eye angle. In an embodiment, the eye angle (θ) is calculated for the analog-to-digital signal peak as determined in step 1212. In an embodiment, the eye angle (θ) may be calculated based on the equation θ=arctan(y rpeak , x repeak ) to calculate, where y rpeak is the peak value of the analog-to-digital signal (r peak ), and xrpeak is the horizontal component at the peak of the analog-to-digital signal. The eye angle (θ) determines whether the user is looking.

[0159] Advantageously, by converging the horizontal eye movement channel output and the vertical eye movement channel output via analog-to-digital signals, method 1200 improves angle detection accuracy and is not limited to detecting whether the eye is facing top, bottom, right, left, upper left, upper right, lower left, or lower right - it can provide angles between 1 and 360 degrees.

[0160] Fig.13 A block diagram of an embodiment device 1300 is illustrated. The device 1300 includes a first motion sensor 20a, a second motion sensor 20b, a main control circuit 21, a memory, and a sensor 1304, which may (or may not) be arranged as shown. The device 1300 may include additional components not shown, such as various interfaces or other types of sensors. For the sake of brevity of discussion, the details of the components previously discussed are not repeated.

[0161] Device 1300 may be any device capable of utilizing the disclosed embodiments to detect eye movement and determine the eye angle of a user wearing the device. For example, device 1300 may be smart glasses (commercial or consumer-based), augmented reality (AR) headsets, virtual reality (VR) headsets, mixed reality (MR) devices, smart helmets, medical diagnostic equipment, automotive heads-up (HUD) displays, gaming headsets, etc.

[0162] The memory 1302 may be any component or collection of components suitable for storing programs, instructions, or calibration settings executed or retrieved by the main control circuit 21. In one embodiment, the memory 1302 includes a non-transitory computer-readable medium. In an embodiment, the memory 1302 is embedded within the main control circuit 21.

[0163] Sensor 1304 may be any component or collection of components for voice activity detection suitable for determining whether the user of wearable device 1300 is speaking. In an embodiment, an accelerometer is positioned to detect vibrations associated with the user's head movement and speech.

[0164] In an embodiment, the sensor 1304 is an accelerometer configured to measure acceleration forces in various directions. In an embodiment, it can measure data along the X axis, Y axis, and Z axis. The main control unit 21 can calculate the norm of the accelerometer data using equation (1): In an embodiment, sensor 1304 is a micro-electromechanical system (MEMS) type accelerometer. MEMS accelerometers are compact, have low power consumption, and have high accuracy. In an embodiment, sensor 1304 can be coupled to an analog-to-digital converter (ADC) to convert the accelerometer sensor output into a digital signal.

[0165] In an embodiment, sensor 1304 includes a microphone that can detect sound vibrations and sound patterns associated with speech. In an embodiment, sensor 1304 includes a bone conduction sensor that detects vibrations through the skull that occur during speech. In an embodiment, sensor 1304 includes an electromyography (EMG) sensor placed near the temple or jaw that can detect muscle activity associated with speech. In an embodiment, sensor 1304 includes a proximity sensor near the user's mouth that can detect changes in proximity when the jaw moves during speech. In an embodiment, sensor 1304 includes an infrared sensor aimed at the throat or jaw that detects temperature changes or movements associated with speech. In an embodiment, sensor 1304 includes an optical sensor that can detect subtle movements of the skin or changes in blood flow associated with facial muscle activity during speech. In an embodiment, sensor 1304 includes a strain gauge sensor integrated into the frame of device 1300 that can detect slight deformations caused by facial movement during speech. In an embodiment, sensor 1304 is integrated into the arm or bridge of glasses that contact the user's head.

[0166] In an embodiment, the sensor 1304 is embedded in the first mobile sensor 20a, the second mobile sensor 20b, or both. For example, the mobile sensor may include an accelerometer, which can advantageously detect the user's voice-related activity. Therefore, in a device that already includes the embedded sensor 1304, the device can determine voice activity without requiring or adding additional components.

[0167] In an embodiment, the main control circuit 21 is configured to receive data from the sensor 1304 and determine whether the user is speaking based on this. For example, if the sensor 1304 is an accelerometer, the main control circuit 21 can determine whether the user is speaking if the accelerometer norm exceeds a threshold or is within a threshold range.

[0168] If the user is not speaking, the eye detection process may follow, for example, detection method 150, such as Fig. 9 On the contrary, if the main control circuit 21 determines that the user is speaking, the eye detection process follows the following Fig.14 Detection method 1400 discussed in.

[0169] Fig.14 A flow chart of an embodiment detection method 1400 is illustrated, which can be implemented in device 1300. Detection method 1400 can address speed-related artifacts. It actively addresses the challenges posed by synchronized speech, improving the accuracy and reliability of eye movement detection in various real-world scenarios.

[0170] Note that all steps outlined in the flow chart of detection method 1400 are not required, but may be optional. In addition, changes to the arrangement of steps, removal of one or more steps and path connections, and addition of steps and path connections are similarly contemplated.

[0171] At step 1402, data is collected from an accelerometer, which may be a sensor 1304 integrated into the device 1300. The accelerometer is positioned to detect vibrations associated with the user's head movement and speech. The accelerometer data provides information about the user's physical activity, particularly sound vibrations, which may interfere with accurate eye movement detection.

[0172] During speech activity, the raw data collected from the electrodes is often affected, which in turn affects, for example, analog-to-digital signals calculated from the collected data. This interference can cause various problems in eye movement detection, such as false positives, where electrode data erroneously exceeds a threshold (r) set to identify eye movement. threshold ), because the baseline is no longer stable due to speech activity.

[0173] Furthermore, other aspects of the eye detection method may be affected due to these speech-related artifacts. Therefore, it is beneficial to implement measures to address and mitigate the effects of speech-related artifacts in the raw data obtained from the electrodes. Such measures can significantly improve the accuracy and reliability of eye movement detection during periods of vocal activity.

[0174] At step 1404, data is collected from the electrodes. In an embodiment, the electrodes are configured to detect electrostatic charge changes (Qvar) associated with eye movement. In an embodiment, at least two sets of electrodes are used - one set for detecting vertical eye movement and another set for detecting horizontal eye movement. The data collected from the electrodes forms an input to the eye movement analysis.

[0175] In response to determining that the user is speaking by analyzing the accelerometer data, one or more processes may be used to process the raw data collected by the electrodes to determine the eye angle at step 1406. In an embodiment, the accelerometer data may detect vibrations associated with speech. The analysis may include processing the accelerometer signal to identify patterns characteristic of speech-related vibrations. Detection of speech is advantageous because vocal activity can introduce artifacts into the eye movement data, potentially causing erroneous readings.

[0176] It should be noted that the use of an accelerometer to determine that the user is speaking is non-limiting, and other methods for making the determination are contemplated in embodiments. For example, the device 1300 may include a microphone, a bone conduction sensor, an electromyography (EMG) sensor, a proximity sensor, an infrared sensor, a piezoelectric sensor, an optical sensor, or a strain gauge sensor to determine whether the user is speaking.

[0177] In an embodiment, determining that the user is speaking can lead to various options to resolve speech-related activity. Detection method 1400 includes three possible options that can be used alone or in combination to determine eye angle. These options are described in detail in steps 1408a to 1408c. Two or more potential processes can be combined to provide greater accuracy in determining eye angle.

[0178] In step 1408a, the threshold for eye movement detection (r threshold ) to address the challenge of speech artifacts - providing a new baseline for eye detection when the user is speaking. In an embodiment, by setting the offset threshold threshold ) is added to the original threshold for the non-speech condition (r threshold ) to calculate the new threshold (r threshold In an embodiment, the offset threshold (offset threshold ) is computed as the average of the modulus signal over a time window, providing dynamic adjustment to account for signal variability during speech.

[0179] For example, immediately after the detection of speech-related activity, the average analog-to-digital signal is calculated in the subsequent 4-second time window. The offset threshold (offset) of the average analog-to-digital signal over the time window is set. threshold ) is added to the original threshold for the non-speech condition (r threshold ) to reach an updated threshold. In step 1410, the updated threshold is then used for peak detection and width analysis.

[0180] Adaptive thresholding helps maintain detection sensitivity while reducing false positives due to movement caused by speech. threshold ) is calculated and stored in memory 1302.

[0181] At step 1408b, speech effect denoising by filtering is applied to mitigate speech-related artifacts in the eye movement data. In an embodiment, denoising includes signal processing techniques designed to isolate and remove artifacts introduced by speech. The denoising algorithm may use information from the voice activity detection sensor and the electrode data to identify and filter out speech-related interference while retaining the true eye movement signal. In an embodiment, the filter filters out noise data from the raw data collected by the electrodes. In an embodiment, the threshold (r threshold ) remains unchanged.

[0182] At step 1408c, AI-based eye pattern detection is used, for example, using a machine learning algorithm to distinguish between real eye movements and speech-induced artifacts. In an embodiment, AI-based eye pattern detection includes training a model on a large dataset of eye movements with and without concurrent speech, such that the system can recognize and classify eye movement patterns with high accuracy even in the presence of speech-related interference. In an embodiment, AI-based eye pattern detection includes training a model on a large dataset of eye movements without concurrent speech, such that the system can recognize and classify eye movement patterns with high accuracy.

[0183] In an embodiment, AI-based eye pattern detection employs various machine learning model configurations to determine eye angles during voice activity. In one embodiment, the machine learning model employs a single input, e.g., an analog-to-digital signal calculated from a horizontal movement channel and a vertical movement channel. In an embodiment, the model may have two separate inputs corresponding directly to the horizontal movement channel and the vertical movement channel. The weights of the machine learning model may be determined during a training phase using data collected from electrodes during periods of, for example, voice activity. This enables the model to learn patterns that distinguish real eye movements from voice-related artifacts.

[0184] The output of the machine learning model can be configured in a variety of ways depending on the desired granularity of eye angle detection. In some embodiments, the model outputs discrete angle values ​​at intervals of 45 degrees: 0 degrees, 45 degrees, 90 degrees, 135 degrees, 180 degrees, 225 degrees, 270 degrees, and 315 degrees. A simpler configuration may output only four basic directions: up, down, left, and right. As another example, the model may output eight directions: up, down, left, right, upper left, upper right, lower left, and lower right. The choice of output configuration can be customized according to the specific needs of the application. Given the flexibility in AI-based detection systems to balance accuracy, computational efficiency, and application requirements, other combinations of inputs and outputs are also contemplated.

[0185] At step 1410, peak detection and width analysis are performed on the processed data. This step includes identifying significant peaks in the eye movement signal corresponding to different eye movements. In an embodiment, peak detection is based on modulus values ​​that exceed an updated threshold for the data from step 1408a. In an embodiment, peak detection is based on modulus values ​​that exceed the original threshold after the data is updated to remove speed-related artifacts at step 1408b. Width analysis examines the duration that the modulus signal exceeds the updated threshold or the original threshold, providing information about the type of eye movement (e.g., quick glances versus longer gazes). This analysis can help characterize the nature and intent of the user's eye movements.

[0186] In step 1412, the eye angle is determined based on the results of the previous steps. This determination may include combining the processed electrode data, the results of the peak and width analysis, and any corrections or classifications performed by the AI-based detection system. The eye angle calculation provides the final output of the eye tracking system, indicating the direction and range of the user's gaze.

[0187] It should be noted that in embodiments where horizontal eye movement and vertical eye movement are not aggregated into an analog-to-digital signal, each channel (i.e., horizontal and vertical channels) is analyzed separately (i.e., updating thresholds, denoising, or AI-based) to detect whether the user is looking up or down from the vertical channel data, or looking left or right from the horizontal channel data.

[0188] Fig.15 A flow chart of an embodiment detection method 1500 that can be implemented in device 1300 is illustrated. Note that all steps outlined in the flow chart of detection method 1500 are not required, but may be optional. In addition, changes to the arrangement of steps, removal of one or more steps and path connections, and addition of steps and path connections are similarly contemplated.

[0189] In step 1502, data is collected from an accelerometer, which may be a sensor 1304 integrated into the device 1300. The accelerometer is positioned to detect vibrations associated with the user's head movement and speaking. The accelerometer data provides information about the user's physical activity, particularly sound vibrations, which may interfere with accurate eye movement detection.

[0190] At step 1504, data is collected from the electrodes. In an embodiment, the electrodes are configured to detect electrostatic charge changes (Qvar) associated with eye movement. In an embodiment, at least two sets of electrodes are used - one set for detecting vertical eye movement and another set for detecting horizontal eye movement. The data collected from the electrodes forms an input to the eye movement analysis.

[0191] At step 1506, the main control circuit 21 determines whether the user is speaking by analyzing the accelerometer data. The accelerometer data can detect vibrations associated with speech. The analysis can include processing the accelerometer signal to identify pattern features of speech-related vibrations.

[0192] In response to detecting speech, the threshold is updated to account for speech-related artifacts, the data is processed to remove speech-related artifacts, and AI / ML techniques or a combination thereof are used to determine eye angles. In an embodiment, a weighting factor is provided for each potential process to determine eye angles.

[0193] In response to not detecting speech, the thresholds, AI / ML techniques, or a combination thereof detailed in detection method 150 are used to determine eye angle at step 1510. In an embodiment, a weighting factor is provided to each process to determine eye angle.

[0194] Although the specification has been described in detail, it should be understood that various changes, substitutions and modifications may be made without departing from the spirit and scope of the present disclosure as defined by the appended claims. In various figures, the same elements are represented by the same reference numerals. In addition, the scope of the present disclosure is not intended to be limited to the specific embodiments described herein, because it will be readily understood by those of ordinary skill in the art from the present disclosure that existing or later developed processes, machines, manufactures, material compositions, equipment, methods or steps can perform substantially the same functions as the corresponding embodiments described herein or achieve substantially the same results. Therefore, the appended claims are intended to include these processes, machines, manufactures, material compositions, equipment, methods or steps within their scope.

[0195] Accordingly, the specification and drawings are to be regarded as illustrative only of the present disclosure as defined by the appended claims, and are intended to cover any and all modifications, variations, combinations or equivalents falling within the scope of the present disclosure.

Claims

1. A circuit for detecting movement of a first eye and a second eye of a user, the circuit comprising: a first movement sensor comprising a first electrode and a second electrode, the first electrode being aligned with the second electrode along a first movement axis, being separated by a first distance, being positionable proximate to the first eye, and being configured to detect a first electrostatic charge change and a second electrostatic charge change, respectively, the first electrostatic charge change and the second electrostatic charge change being generated by movement of the first eye along the first movement axis; a second movement sensor comprising a third electrode and a fourth electrode, the third electrode aligned with the fourth electrode along a second movement axis, spaced apart by a second distance, positionable proximate to the second eye, and configured to detect a third electrostatic charge change and a fourth electrostatic charge change, respectively, the third electrostatic charge change and the fourth electrostatic charge change generated by movement of the second eye along the second movement axis, the second movement axis being transverse to the first movement axis; as well as a control circuit coupled to the first motion sensor and the second motion sensor, the control circuit being configured to: acquiring a first electrostatic charge change signal, wherein the first electrostatic charge change signal indicates a difference between the first electrostatic charge change and the second electrostatic charge change, acquiring a second electrostatic charge change signal, wherein the second electrostatic charge change signal indicates a difference between the third electrostatic charge change and the fourth electrostatic charge change, Starting from the first electrostatic charge change signal and the second electrostatic charge change signal, detecting an event, the event indicating an eye displacement along the first movement axis or the second movement axis, and Movement of the first eye and movement of the second eye are determined based on the event.

2. The circuit of claim 1 , further comprising a sensor configured to detect a voice-related activity of the user, wherein the control circuit is configured to: Calculating an analog-to-digital signal according to the first electrostatic charge change signal and the second electrostatic charge change signal, and taking into account the voice-related activity, wherein taking into account the voice-related activity comprises: before calculating the analog-to-digital signal, removing speech-related artifacts from the first electrostatic charge variation signal and the second electrostatic charge variation signal, In response to detecting the voice-related activity, updating the threshold by adding an offset value to the threshold, the threshold being used to detect the event; as well as An angle is determined based on the analog-to-digital signal at which the first eye and the second eye are oriented.

3. The circuit according to claim 1, wherein the first movement axis and the second movement axis are orthogonal to each other, or wherein the first movement axis is parallel to a longitudinal axis of the user's face, wherein the second movement axis is parallel to a transverse axis of the user's face, or coincides with the transverse axis of the user's face, wherein the longitudinal axis is equidistant from the first eye and the second eye, and Wherein the transverse axis passes through the first eye and the second eye.

4. The circuit according to claim 1, wherein the first electrode and the second electrode extend from opposite sides of the first eye along the first movement axis, and Wherein the third electrode and the fourth electrode extend from opposite sides of the second eye along the second movement axis.

5. The circuit according to claim 1, The first movement sensor further comprises a fifth electrode and a sixth electrode, the fifth electrode and the sixth electrode are aligned along a first parallel movement axis, are separated by a third distance, can be positioned close to the first eye, and are configured to detect a fifth electrostatic charge change and a sixth electrostatic charge change, respectively, the first parallel movement axis is transverse or orthogonal to the first movement axis, the fifth electrostatic charge change and the sixth electrostatic charge change are generated by movement of the first eye along the first parallel movement axis, The second movement sensor further includes a seventh electrode and an eighth electrode, the seventh electrode is aligned with the eighth electrode along a second parallel movement axis, is separated by a fourth distance, can be positioned close to the second eye, and is configured to detect a seventh electrostatic charge change and an eighth electrostatic charge change, respectively, the second parallel movement axis is transverse or orthogonal to the second movement axis, the seventh electrostatic charge change and the eighth electrostatic charge change are generated by movement of the second eye along the second parallel movement axis, the second parallel movement axis is transverse or orthogonal to the first parallel movement axis, The control circuit is configured as follows: acquiring a third electrostatic charge change signal, the third electrostatic charge change signal indicating a difference between the fifth electrostatic charge change and the sixth electrostatic charge change, acquiring a fourth electrostatic charge change signal, the fourth electrostatic charge change signal indicating a difference between the seventh electrostatic charge change and the eighth electrostatic charge change, Starting from the third electrostatic charge change signal and the fourth electrostatic charge change signal, detecting a second event, the second event indicating eye displacement along the first parallel movement axis or the second parallel movement axis, and Movement of the first eye and movement of the second eye are determined based on the second event. 6 . The circuit of claim 1 , wherein the first electrode, the second electrode, the third electrode, and the fourth electrode are detachably fixed to the user's skin.

7. The circuit of claim 1, wherein the circuit is hosted by a wearable device, the wearable device being a goggle device, a wearable eyewear device, a smart wearable eyewear device, a headset, or an augmented reality headset.

8. A wearable device comprising: frame; as well as A circuit for detecting movement of a first eye and a second eye of a user, the circuit being arranged on the frame and comprising: a first movement sensor, the first movement sensor comprising a first electrode and a second electrode, the first electrode and the second electrode being aligned along a first movement axis, spaced apart by a first distance, positionable proximate to the first eye, and configured to detect a first electrostatic charge change and a second electrostatic charge change, respectively, the first electrostatic charge change and the second electrostatic charge change being generated by movement of the first eye along the first movement axis, a second movement sensor comprising a third electrode and a fourth electrode, the third electrode being aligned with the fourth electrode along a second movement axis, being spaced apart by a second distance, being positionable proximate to the second eye, and being configured to detect a third electrostatic charge change and a fourth electrostatic charge change, respectively, the third electrostatic charge change and the fourth electrostatic charge change being generated by movement of the second eye along the second movement axis, the second movement axis being transverse to the first movement axis, and a control circuit coupled to the first motion sensor and the second motion sensor, the control circuit being configured to: Acquire a first electrostatic charge change signal, wherein the first electrostatic charge change signal indicates a difference between the first electrostatic charge change and the second electrostatic charge change; acquiring a second electrostatic charge change signal, wherein the second electrostatic charge change signal indicates a difference between the third electrostatic charge change and the fourth electrostatic charge change; Starting from the first electrostatic charge change signal and the second electrostatic charge change signal, detecting an event, the event indicating eye displacement along the first movement axis or the second movement axis; and Movement of the first eye and movement of the second eye are determined based on the event.

9. The wearable device according to claim 8, wherein the frame comprises a first supporting portion and a second supporting portion, the first supporting portion and the second supporting portion are coupled to each other and are configured to face the first eye and the second eye, respectively, wherein the first electrode and the second electrode are fixed to the first support portion and are arranged opposite to each other relative to the first support portion along the first movement axis, The third electrode and the fourth electrode are fixed to the second supporting portion and are arranged opposite to each other relative to the second supporting portion along the second movement axis.

10. The wearable device according to claim 8, further comprising a first lens and a second lens, the first lens facing the first eye, and the second lens facing the second eye, wherein the frame comprises a first supporting portion and a second supporting portion, the first supporting portion and the second supporting portion are coupled to each other and are configured to face the first eye and the second eye, respectively, wherein the first lens is fixed to the first supporting portion and is carried by the first supporting portion, wherein the second lens is fixed to and carried by the second supporting portion, wherein the first electrode and the second electrode are fixed to the first lens and carried by the first lens, and The third electrode and the fourth electrode are fixed to the second lens and carried by the second lens.

11. The wearable device according to claim 8, wherein the wearable device is a goggle device, a wearable glasses device, a smart wearable glasses device, a headset, or an augmented reality headset.

12. The wearable device according to claim 8, wherein the first movement axis and the second movement axis are orthogonal to each other, or Wherein the first movement axis is parallel to the longitudinal axis of the user's face, wherein the second movement axis is parallel to the transverse axis of the user's face, or coincides with the transverse axis of the user's face, wherein the longitudinal axis is equidistant from the first eye and the second eye, and wherein the transverse axis passes through the first eye and the second eye.

13. The wearable device according to claim 8, wherein the first electrode and the second electrode extend from opposite sides of the first eye along the first movement axis, and Wherein the third electrode and the fourth electrode extend from opposite sides of the second eye along the second movement axis.

14. The wearable device according to claim 8, The first movement sensor further comprises a fifth electrode and a sixth electrode, the fifth electrode and the sixth electrode are aligned along a first parallel movement axis, are separated by a third distance, can be positioned close to the first eye, and are configured to detect a fifth electrostatic charge change and a sixth electrostatic charge change, respectively, the first parallel movement axis is transverse or orthogonal to the first movement axis, the fifth electrostatic charge change and the sixth electrostatic charge change are generated by movement of the first eye along the first parallel movement axis, The second movement sensor further includes a seventh electrode and an eighth electrode, the seventh electrode is aligned with the eighth electrode along a second parallel movement axis, is separated by a fourth distance, can be positioned close to the second eye, and is configured to detect a seventh electrostatic charge change and an eighth electrostatic charge change, respectively, the second parallel movement axis is transverse or orthogonal to the second movement axis, the seventh electrostatic charge change and the eighth electrostatic charge change are generated by movement of the second eye along the second parallel movement axis, the second parallel movement axis is transverse or orthogonal to the first parallel movement axis, The control circuit is configured as follows: acquiring a third electrostatic charge change signal, the third electrostatic charge change signal indicating a difference between the fifth electrostatic charge change and the sixth electrostatic charge change, acquiring a fourth electrostatic charge change signal, the fourth electrostatic charge change signal indicating a difference between the seventh electrostatic charge change and the eighth electrostatic charge change, Starting from the third electrostatic charge change signal and the fourth electrostatic charge change signal, detecting a second event, the second event indicating eye displacement along the first parallel movement axis or the second parallel movement axis, and Movement of the first eye and movement of the second eye are determined based on the second event.

15. A method for detecting eyes of a user using a wearable device, the method comprising: detecting, by a first electrode of a first motion sensor, a first electrostatic charge change generated by movement of the first eye along a first axis of movement; detecting a second electrostatic charge change by a second electrode of the first motion sensor, the second electrostatic charge change being generated by movement of the first eye along the first motion axis, the first electrode and the second electrode being aligned along the first motion axis, spaced a first distance apart, and positionable proximate to the first eye; detecting, by a third electrode of the second movement sensor, a third electrostatic charge change generated by movement of the second eye along the second movement axis; detecting a fourth electrostatic charge change by a fourth electrode of the second motion sensor, the fourth electrostatic charge change generated by movement of the second eye along the second motion axis, the third electrode being aligned with the fourth electrode along the second motion axis, being spaced apart a second distance, and being positionable proximate to the second eye, the second motion axis being transverse to the first motion axis; acquiring a first electrostatic charge change signal by a control circuit, the control circuit being coupled to the first motion sensor and the second motion sensor, the first electrostatic charge change signal indicating a difference between the first electrostatic charge change and the second electrostatic charge change; The control circuit acquires a second electrostatic charge change signal, wherein the second electrostatic charge change signal indicates a difference between the third electrostatic charge change and the fourth electrostatic charge change; detecting, by the control circuit, an event from the first electrostatic charge change signal and the second electrostatic charge change signal, the event indicating eye displacement along the first movement axis or the second movement axis; as well as Movement of the first eye and movement of the second eye are determined by the control circuit based on the event.

16. The method of claim 15, wherein detecting the event comprises: Verify whether the first electrostatic charge variation signal and the second electrostatic charge variation signal include corresponding peaks, the corresponding peaks indicating eye displacement along the first movement axis and eye displacement along the second movement axis.

17. The method of claim 15, wherein determining, by the control circuit, the movement of the first eye and the movement of the second eye based on the event comprises: The movement is determined using a machine learning model.

18. The method of claim 15, wherein determining the movement of the first eye and the movement of the second eye comprises: correlating detection of the eye displacement along the first axis of movement with detection of the eye displacement along the second axis of movement; or The reference angular position of the first eye and the reference angular position of the second eye are updated according to a previous reference angular position of the first eye and a previous reference angular position of the second eye, wherein the previous reference angular position of the first eye and the previous reference angular position of the second eye are detected based on the event, and the reference angular position is one of a plurality of predetermined reference angular positions.

19. The method according to claim 15, further comprising: verifying a feasibility condition, the feasibility condition being used to determine the movement of the first eye and the movement of the second eye, the feasibility condition being related to the presence or absence of a head movement of the user, The acquiring of the first electrostatic charge change signal and the second electrostatic charge change signal is performed according to the verification of the feasibility condition.

20. A non-transitory computer readable medium storing computer instructions, which when executed by a processor, cause the processor to: detecting, by a first electrode of a first motion sensor, a first electrostatic charge change generated by movement of the first eye along a first axis of movement; detecting a second electrostatic charge change by a second electrode of the first motion sensor, the second electrostatic charge change being generated by movement of the first eye along the first motion axis, the first electrode and the second electrode being aligned along the first motion axis, spaced a first distance apart, and positionable proximate to the first eye; detecting, by a third electrode of the second movement sensor, a third electrostatic charge change generated by movement of the second eye along the second movement axis; detecting a fourth electrostatic charge change by a fourth electrode of the second motion sensor, the fourth electrostatic charge change generated by movement of the second eye along the second motion axis, the third electrode being aligned with the fourth electrode along the second motion axis, being spaced apart a second distance, and being positionable proximate to the second eye, the second motion axis being transverse to the first motion axis; acquiring a first electrostatic charge change signal by a control circuit, the control circuit being coupled to the first motion sensor and the second motion sensor, the first electrostatic charge change signal indicating a difference between the first electrostatic charge change and the second electrostatic charge change; The control circuit acquires a second electrostatic charge change signal, wherein the second electrostatic charge change signal indicates a difference between the third electrostatic charge change and the fourth electrostatic charge change; detecting, by the control circuit, an event from the first electrostatic charge change signal and the second electrostatic charge change signal, the event indicating eye displacement along the first movement axis or the second movement axis; as well as Movement of the first eye and movement of the second eye are determined by the control circuit based on the event.

Images