# US 12,525,058 B2 · Synchronizing eye movement parameters for a delay from a monitor output to a sensor > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,525,058 B2 - Document ID: US12525058B2 - Status: Granted - Kind: B2 - Application number: 17/734,896 - Filed: 2022-05-02 - Published: 2022-11-10 - Granted: 2026-01-13 - Earliest claimed: 2021-05-03 - Assignees: NeuraLight Ltd. - Applicants: NeuraLight Ltd. - Inventors: Edmund Ben-Ami; Micha Yochanan Breakstone; Rotem Zvi Bar-Or; Vladimir Anisimov - Web page: https://patentgrep.com/patent/US12525058B2 ## CPC - G06V 40/18: Eye characteristics, e.g. of the iris - A61B 3/0025: {characterised by electronic signal processing, e.g. eye models} - A61B 3/113: for determining or recording eye movement - A61B 5/163: {by tracking eye movement, gaze, or pupil change} - G06F 3/013: {Eye tracking input arrangements (G06F3/015 takes precedence)} - G06N 3/04: Architecture, e.g. interconnection topology - G06N 3/09: Supervised learning - G06T 7/0012: {Biomedical image inspection} - G06T 7/0016: {involving temporal comparison} - G06T 7/246: using feature-based methods, e.g. the tracking of corners or segments - G06V 10/82: using neural networks - G06N 3/084: Backpropagation, e.g. using gradient descent - G06T 2207/10016: Video; Image sequence - G06T 2207/20081: Training; Learning - G06T 2207/20084: Artificial neural networks [ANN] - G06T 2207/30041: Eye; Retina; Ophthalmic - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING - A61B: DIAGNOSIS; SURGERY; IDENTIFICATION (usefulness limited to only animals A61D) - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS - G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL ## Abstract Disclosed are systems and methods for extracting high resolution oculometric parameters and eye movement parameters. A video stream having a video of a face of a user is processed to obtain a set of oculometric parameters, such as eyelid data, iris data (e.g., iris translation, iris radius and iris rotation), and pupil data (e.g., pupil center and pupil radius). The oculometric parameters are generated at a first temporal resolution. The oculometric parameters are up sampled to increase the temporal resolution to a second temporal resolution. The oculometric parameters are then processed to generate various eye movement parameters such as blink parameter, pupil response parameter, saccade parameter, anti-saccade parameter, fixation parameter, or smooth pursuit parameter. The oculometric parameters are synchronized with a video stimulus presented on a user device prior to generating the eye movement parameters. ## Claims ### Claim 1 A method comprising: obtaining a video stream from a client device associated with a user, the video stream including a video of a face of the user; processing the video stream to obtain a set of oculometric parameters, wherein the set of oculometric parameters includes (a) eye tracking data that is indicative of a rotation of an iris associated with an eye of the user, and a location of a pupil and the iris, (b) eye size data indicative of a pupil radius and iris radius, and (c) eye openness data that is indicative of an openness of the eye, wherein the set of oculometric parameters is time series data; synchronizing the set of oculometric parameters with a video stimulus presented on a display of the client device to obtain a synchronized set of oculometric parameters, wherein the synchronization is based on light modulation in the video stimulus, wherein the synchronizing comprises: obtaining video stimulus information, wherein the video stimulus information includes stimulus type information, information descriptive of graphic features of the video stimulus, or brightness and color modulation information of the video stimulus; obtaining reflected light information, wherein the reflected light information includes information regarding light reflected from a target in an environment in which the user is located, and red, green, and blue (RGB) intensity values sampled from the video stream received from the client device; and synchronizing a time component in the set of the oculometric parameters time series data based on the video stimulus information and the reflected light information to generate the synchronized set of oculometric parameters; obtaining, based on the synchronized set of oculometric parameters, a set of eye movement parameters that are indicative of a movement of the eye in response to the video stimulus; and determining one or more digital markers of the user based on the set of eye movement parameters. ### Claim 2 (depends on 1) The method of claim 1, wherein the eye openness data includes iris visible fraction information, iris coverage asymmetry information, pupil visible fraction information, and pupil coverage asymmetry information. ### Claim 3 (depends on 1) The method of claim 1, wherein obtaining the set of eye movement parameters includes: obtaining, based on the eye openness data, blink information that is indicative of blinking of the eye. ### Claim 4 (depends on 3) The method of claim 3, wherein obtaining the blink information includes: obtaining, based on a time series of the eye openness data, a time series of blink presence data that is indicative of a presence or absence of a blink at a given instant; and obtaining the blink information based on the time series of the blink presence data. ### Claim 5 (depends on 3) The method of claim 3, wherein the blink information includes (a) blink duration information that is indicative of a duration of blinking of the eye for a sequence of the video stimulus, and (b) blink frequency information that is indicative of a frequency of blink for the sequence. ### Claim 6 (depends on 1) The method of claim 1, wherein the eye size data includes iris radius and pupil radius. ### Claim 7 (depends on 1) The method of claim 1, wherein obtaining the set of eye movement parameters includes: obtaining pupil response information based on the eye size data, blink presence data and a stimulus type of the video stimulus, wherein the pupil response information is indicative of a response of the pupil or the eye to the video stimulus. ### Claim 8 (depends on 7) The method of claim 7, wherein the pupil response information includes (a) pupil response amplitude that is indicative of a maximal variance of pupil diameter for an event, and (b) pupil response rate that is indicative of mean temporal rate of variance in the pupil diameter for the event. ### Claim 9 (depends on 7) The method of claim 7, wherein the pupil response information includes (a) pupil response latency that is indicative of a time interval between an event in the video stimulus and an initial change in pupil diameter, and (b) pupil response duration that is indicative of a time interval between the initial change in the pupil diameter following the event and a stabilization of change in the size of the pupil diameter. ### Claim 10 (depends on 1) The method of claim 1, wherein the eye tracking data includes iris translation and pupil location. ### Claim 11 (depends on 1) The method of claim 1, wherein obtaining the set of eye movement parameters includes: obtaining saccade information based on the eye tracking data, blink presence data and a stimulus type of the video stimulus, wherein the saccade information is indicative of a rapid movement of the eye in response to the video stimulus. ### Claim 12 (depends on 11) The method of claim 11, wherein the saccade information includes at least one of (a) saccade latency, (b) saccade amplitude, (c) saccade peak velocity, (d) saccade overshoot amplitude, or (e) saccade correction time. ### Claim 13 (depends on 1) The method of claim 1, wherein obtaining the set of eye movement parameters includes: obtaining anti-saccade information based on the eye tracking data, blink presence data and a stimulus type of the video stimulus, wherein the anti-saccade information is indicative of a movement of the eye in a direction opposite to a side where a target is presented in the video stimulus. ### Claim 14 (depends on 13) The method of claim 13, wherein the anti-saccade information includes at least one of anti-saccade latency, anti-saccade amplitude, anti-saccade peak velocity, anti-saccade overshoot amplitude, anti-saccade correction time, anti-saccade direction confusion rate, or anticipated anti-saccadic information. ### Claim 15 (depends on 1) The method of claim 1, wherein obtaining the set of eye movement parameters includes: obtaining fixation information based on the eye tracking data, blink presence data and a stimulus type of the video stimulus, wherein the fixation information is indicative of an ability of the eye to maintain a gaze on a single location in the video stimulus. ### Claim 16 (depends on 15) The method of claim 15, wherein the fixation information includes micro-saccade amplitude distribution that is indicative of a distribution of both angular and amplitude around a target in the video stimulus. ### Claim 17 (depends on 15) The method of claim 15, wherein obtaining the fixation information includes obtaining square wave jerk information. ### Claim 18 (depends on 17) The method of claim 17, wherein the square wave jerk information includes at least one of square wave jerk amplitude, square wave jerk frequency, or square wave jerk offset duration. ### Claim 19 (depends on 1) The method of claim 1, wherein obtaining the set of eye movement parameters includes: obtaining smooth pursuit information based on the eye tracking data, blink presence data and a stimulus type of the video stimulus, wherein the smooth pursuit information is indicative of a type of eye movement in which the eyes remain fixated on a moving object in the video stimulus. ### Claim 20 (depends on 19) The method of claim 19, wherein obtaining smooth pursuit information includes: determining a movement of the eye as one of saccade, fixation, or smooth pursuit. ### Claim 21 (depends on 19) The method of claim 19, wherein obtaining the smooth pursuit information includes: obtaining at least one of saccadic movement amplitude percentage, or smooth movement amplitude percentage. ### Claim 22 (depends on 19) The method of claim 19, wherein obtaining the smooth pursuit information includes: obtaining saccadic movement temporal percentage that is indicative of a time fraction of saccadic movements for an act in the video stimulus. ### Claim 23 (depends on 19) The method of claim 19, wherein obtaining the smooth pursuit information includes: obtaining fixation temporal percentage that is indicative of a time fraction of fixation for an act in the video stimulus. ### Claim 24 (depends on 19) The method of claim 19, wherein obtaining the smooth pursuit information includes: obtaining smooth movement temporal percentage that is indicative of a time fraction of smooth movements for an act in the video stimulus. ### Claim 25 (depends on 1) The method of claim 1, wherein the set of eye movement parameters is measured for at least one of an event, a brick, a sequence, or an act. ### Claim 26 (depends on 25) The method of claim 25, wherein the event corresponds to an event of a specified duration in the video stimulus, wherein the brick corresponds to a collection of consecutive events in the video stimulus, wherein the sequence corresponds to a collection of consecutive bricks of the same type of brick, and wherein the act corresponds to a collection of consecutive sequences recorded for the user. ### Claim 27 (depends on 1) The method of claim 1, wherein processing the video stream includes: obtaining the set of oculometric parameters at a first temporal resolution; and up sampling the set of oculometric parameters to obtain the set of oculometric parameters at a second temporal resolution greater than the first temporal resolution. ### Claim 28 (depends on 27) The method of claim 27, wherein up sampling the set of oculometric parameters includes: up sampling the set of oculometric parameters prior to synchronizing the set of oculometric parameters. ### Claim 29 (depends on 27) The method of claim 27, wherein up sampling the set of oculometric parameters includes: obtaining a first plurality of sets of oculometric parameters at the first temporal resolution; obtaining, using an eye tracking device configured to generate oculometric parameters at the second temporal resolution, the first plurality of sets of oculometric parameters at the second temporal resolution; and training a machine learning model with the first plurality of sets of oculometric parameters to generate a predicted set of oculometric parameters at the second temporal resolution. ### Claim 30 (depends on 1) The method of claim 1 further comprising: generating a set of digital biomarkers based on the set of eye movement parameters. ### Claim 31 A non-transitory computer-readable medium having instructions that, when executed by a computer, cause the computer to execute a method, the method comprising: obtaining a video stream from a client device associated with a user, the video stream including a video of a face of the user; obtaining a time series of a set of oculometric parameters from the video stream, wherein the set of oculometric parameters includes (a) eye tracking data that is indicative of a rotation of an iris associated with an eye of the user, and a location of a pupil and the iris, (b) eye size data indicative of a pupil radius and iris radius, and (c) eye openness data that is indicative of an openness of the eye, wherein the set of oculometric parameters is obtained at a first temporal resolution; up sampling the set of oculometric parameters to a second temporal resolution to generate an up sampled set of oculometric parameters, wherein the second temporal resolution is greater than the first temporal resolution; synchronizing the up sampled set of oculometric parameters with a video stimulus presented on a display of the client device to obtain a synchronized set of oculometric parameters, wherein the synchronizing is based on light modulation in the video stimulus, wherein the synchronizing comprises: obtaining video stimulus information, wherein the video stimulus information includes stimulus type information, information descriptive of graphic features of the video stimulus, or brightness and color modulation information of the video stimulus; obtaining reflected light information, wherein the reflected light information includes information regarding light reflected from a target in an environment in which the user is located, and red, green, and blue (RGB) intensity values sampled from the video stream received from the client device; and synchronizing a time component in the set of the up sampled set of oculometric parameters based on the video stimulus information and the reflected light information to generate the synchronized set of oculometric parameters; and obtaining, based on the synchronized set of oculometric parameters, a set of eye movement parameters that are indicative of a movement of the eye in response to the video stimulus. ### Claim 32 (depends on 31) The computer-readable medium of claim 31, wherein obtaining the set of eye movement parameters includes: obtaining, based on the eye openness data, blink information that is indicative of blinking of the eye; obtaining pupillary response information based on the eye size data, the blink information, and a stimulus type of the video stimulus, wherein the pupillary response information is indicative of a response of the pupil to the video stimulus; and obtaining at least one of saccade information, anti-saccade information, fixation information, or smooth pursuit information based on the eye tracking data, the blink information, and the stimulus type. ### Claim 33 A system, comprising: a memory storing a set of instructions; and a processor configured to execute the set of instructions to cause the system to perform a method of: obtaining a video stream from a client device associated with a user, the video stream including a video of a face of the user; processing the video stream to obtain a set of oculometric parameters, wherein the set of oculometric parameters includes (a) eye tracking data that is indicative of a rotation of an iris associated with an eye of the user, and a location of a pupil and the iris, (b) eye size data indicative of a pupil radius and iris radius, and (c) eye openness data that is indicative of an openness of the eye; synchronizing the set of oculometric parameters with a video stimulus presented on a display of the client device to obtain a synchronized set of oculometric parameters, wherein the synchronizing is based on light modulation in the video stimulus, wherein the synchronizing comprises: obtaining video stimulus information, wherein the video stimulus information includes stimulus type information, information descriptive of graphic features of the video stimulus, or brightness and color modulation information of the video stimulus; obtaining reflected light information, wherein the reflected light information includes information regarding light reflected from a target in an environment in which the user is located, and red, green, and blue (RGB) intensity values sampled from the video stream received from the client device; and synchronizing a time component in the set of the up sampled set of oculometric parameters based on the video stimulus information and the reflected light information to generate the synchronized set of oculometric parameters; and obtaining, based on the synchronized set of oculometric parameters, a set of eye movement parameters that are indicative of a movement of the eye in response to the video stimulus.