53 results about "Corneal reflection" patented technology

This invention discloses a 2D gaze point estimation method based on the pupil-corneal reflection vector method. It utilizes the star ray method for pupil center localization and adds a classification pupil detection mechanism for error correction. Corneal feature extraction is performed to obtain the center coordinates of the corneal reflected light spot. Step 4: Establish a gaze mapping model, and assign the detected pupil-corneal reflection vector V(V) to each frame of the image. x V y The gaze coordinates G(G) mapped onto the screen x G y This invention enables 2D gaze point estimation based on the pupil-corneal reflection vector method. Compared with existing technologies, this invention can improve the accuracy of 2D gaze point estimation.

The invention discloses a sight tracking method and system based on cascade deep learning and distance correction, and a storage medium. The method comprises the following steps: processing an eye image through a cascade deep learning model, and obtaining pupil center coordinates and cornea reflection light spot coordinates of two eyes; calculating a binocular pixel distance as a distance correction factor based on the pupil center coordinates, and calculating a relative position difference vector based on the pupil and light spot coordinates; establishing a three-dimensional nonlinear polynomial regression model taking the relative position difference vector and the distance correction factor as input; obtaining calibration data through a multi-distance sampling strategy and solving a model coefficient; and in the real-time tracking stage, calculating the coordinates of the fixation point of the screen by using the solved model. According to the method, the distance correction factor and the three-dimensional mapping model are introduced, so that geometric errors caused by forward and backward movement of the head of the user are effectively eliminated, meanwhile, the feature point positioning precision is ensured through cascaded deep learning detection, and the precision and robustness of a sight line tracking system are remarkably improved.

The present disclosure provides an electronic device, a control method of an electronic device, a program, and a medium. The electronic device includes a plurality of irradiation units configured to irradiate an eyeball of a user with infrared light, an image capturing unit configured to capture an ocular image obtained when the infrared light from the plurality of irradiation units is reflected by the eyeball, one or more memories, and one or more processors in communication with the one or more memories. The one or more processors and the one or more memories are configured to calculate a gaze position of a user viewing a display unit based on a combination of corneal reflection images included in the ocular image, and set an order with respect to each of the combinations of the corneal reflection images based on a predetermined condition during a calibration process for improving a calculation precision of the gaze position.

Abstract Apparatus and methods are presented for spectral domain optical imaging, in particular for single shot 3-D spectral domain imaging of the retina of the human eye. In certain embodiments one or more 3-D images across elongated areas of an object are acquired, with scanning perpendicular to the long axis of the elongated areas for imaging extended volumes of 5 the object. In preferred embodiments the captured light is sampled in the Fourier plane, in a dimension substantially perpendicular to the long axis, with a cylindrical lenslet array, while in other embodiments the captured light is sampled in the image plane. Apparatus and methods are also presented for hyperspectral imaging of the retina, with the illuminating beams preferably angled to suppress interference from corneal reflections. Apparatus and methods are 10 also presented for multi-wavelength wavefront sensing, with simultaneous capture of light in two or more paths with different delays. 5 1020 26 20 47 51 19 J un 2 02 6 A b s t r a c t 1 9 J u n 2 0 2 6 5 2 0 2 6 2 0 4 7 5 1 1 0

This invention discloses an eye feature detection and light source matching method based on an event camera, belonging to the field of eye-tracking detection. The method includes first placing an event camera and a ring-shaped light source assembly in front of the eye being tested, controlling the ring-shaped light source assembly to switch from off to on, and simultaneously acquiring event stream data generated by brightness changes in the eye area through the event camera; constructing a global grayscale image and a light spot grayscale image based on the event stream data, then coarsely locating the pupil contour and extracting candidate corneal reflective spots; then obtaining the precise pupil contour and pupil center position based on the candidate corneal reflective spots; finally, based on a preset light spot geometric distribution model, eliminating abnormal spots among the candidate corneal reflective spots, and identifying the correspondence between each remaining candidate corneal reflective spot and the light source in the ring-shaped light source assembly. This invention achieves pupil and corneal reflective spot detection and light source matching based on event data, providing structured feature input for subsequent eye tracking and gaze direction estimation.

The application provides an eyeball parameter positioning and eyeball optical axis estimation method based on iris reconstruction, and relates to the technical field of visual line tracking. The method comprises the following steps: based on the characteristics of the iris on the camera imaging, a space iris circle is reconstructed, the iris imaging elliptical cone is standardized through coordinate system transformation, and the iris imaging elliptical cone in the new coordinate system is obtained; based on the iris imaging elliptical cone, two circular sections are determined; based on the normal vectors of the two circular sections, the normal vector of the OCI plane is determined; based on the normal vector of the OCI plane, the vector of the three-dimensional cornea center and the camera optical center is determined, and the positions of the three-dimensional iris center, the three-dimensional cornea center and the cornea reflection point are further determined; taking the eyeball structure and the imaging relationship as constraints, based on the iris radius and the distance from the three-dimensional cornea center to the three-dimensional iris center, the three-dimensional cornea center and the three-dimensional iris center are obtained, and the optical axis of the eyeball is estimated through the three-dimensional cornea center and the three-dimensional iris center. The application can reduce the complexity of the eyeball parameter calculation.

The present disclosure allows for accurate and computationally efficient gaze tracking without requiring a corneal reflection. Eye tracking systems and methods are provided. They include obtaining images of the user's face, detecting a head pose, and locating the centre eye rotation, the pupil centre, the optical axis, the cornea centre and finally the visual axis corresponding to the gaze direction using user-specific parameters. Calibration systems and methods are also provided for acquiring the user-specific parameters. They include at least twice displaying a target point for the user to glaze at, directing light to obtain a corneal reflection, obtaining an image of the user's face, detecting the head pose, inferring a transformation to convert coordinates between the world coordinate system and a head coordinate system, and locating the corneal reflection, the cornea centre, the pupil centres and the optical axes. The data acquired thereby is used to compute the parameters.

The invention relates to the technical field of vision detection, in particular to an eye position image analysis system for measuring a strabismus angle of a child. The strabismus measurement reliability is determined based on the difference of position changes of different types of pupil center areas in eye position images of two steering eye positions in a symmetrical eye position pair and the difference of the position relations between the pupil center areas and cornea light reflecting spots in the eye position images; the strabismus measurement reliability is adjusted through the included angle between the steering eye position and the orthogonal direction in all symmetrical eye position centering, the strabismus deviation angle is determined, and then the overall measurement reliability is determined; determining a strabismus measurement value according to the difference of position changes of different types of pupil center areas in the eye position images of the steering eye position and the positive eye position; and adjusting the strabismus measurement value by using the overall measurement reliability of all the steering eye positions, and determining the final strabismus angle under the positive eye position. According to the method, the final strabismus angle is determined by integrating the information of all the steering eye positions, and the dynamic characteristics of intermittent strabismus are effectively captured.

The invention discloses a myopia prevention and control method based on a wearable device, the wearable device and a storage medium, and relates to the technical field of wearable device.The method comprises the steps that a first image representing user eye information is collected, and a second image representing a user cornea area in the first image is extracted; performing spherical distortion removal processing on the second image to obtain a target cornea reflection image; multi-dimensional dynamic analysis is carried out on the target cornea reflection image to obtain multi-dimensional evaluation information, and the multi-dimensional dynamic analysis comprises target object recognition, distance speculation and illumination detection; in response to the situation that the multi-dimensional evaluation information does not meet preset myopia prevention and control conditions, it is determined that the myopia risk exists, preset prompt information for prompting the user that the myopia risk exists is output, and the preset myopia prevention and control conditions comprise at least one of the fixation time condition, the fixation distance condition and the illumination intensity condition. According to the method, the hardware cost of the wearable equipment is not increased, and meanwhile, accurate myopia prevention and control are realized.

The application relates to the technical field of knowledge graph, and particularly provides a strabismus three-dimensional mapping method and system based on a knowledge graph, which comprises the following steps: taking a starting point space coordinate, a patient corneal reflection point offset and an eyeball rotation center coordinate as attribute values of an entity node, establishing a directed connection edge between nodes according to a fixed attachment relationship between muscles and eyeballs and between muscles and bone walls in anatomy, and constructing an initial heterogeneous graph by all entity nodes and the directed connection edge; weighting and aggregating attribute values of neighborhood nodes connected by the directed connection edge of each node in the obtained initial heterogeneous graph to obtain an aggregated feature vector of the node; and mapping all node coordinates in each obtained sub-graph to a unified three-dimensional coordinate system, and adjusting the relative positions between the sub-graphs so that all positioning base points are located on a plane. The application realizes systematic mapping and pathological posture analysis of three-dimensional space configurations of eye external muscles of a strabismus patient.

The invention provides an eye movement tracking method, electronic equipment, a storage medium and a chip system, and in the method, at least two cameras are arranged for each eye of a user in the electronic equipment. When a user uses the electronic equipment, each camera can collect the eye image of the corresponding eye of the user, and the electronic equipment can determine the cornea center and the pupil center of the eye according to the position of the pupil center and the eye parameters in the at least two eye images corresponding to the same eye, so that the gazing direction of the user is determined. An electronic device may interact with a user using a gaze direction of the user. In the method, the process of acquiring the gazing direction of the user by the electronic equipment does not depend on light spots formed by cornea reflection, the application range is wider, the accuracy is higher, and the interaction experience of the user is improved.

The invention provides an infrared eye movement tracking device and eye movement tracking equipment, and relates to the technical field of eye movement tracking. The device comprises a single infrared light emitting diode, a collimating element, a metasurface device, an image sensor and a control processing unit. The metasurface device is arranged on the light emitting path of the collimating element and located between the infrared light emitting diode and the human eye observation area; the metasurface device is a device designed based on a two-dimensional metasurface grating structure and is configured to diffract and modulate an incident light beam into a plurality of illumination light beams separated in space so as to form a plurality of light spots distributed in a concentric ring shape on the cornea surface of a target eyeball; the image sensor is used for collecting a cornea reflection image containing a plurality of light spots; and the control processing unit is in communication connection with the image sensor and is used for outputting sight line direction data based on the relative position relationship between a plurality of light spots in the cornea reflection image and the pupil center, so that the eye movement tracking performance with higher precision and higher reliability is realized while hardware is simplified.

The invention relates to the technical field of eye movement tracking, in particular to an eye movement tracking method and device based on an optical waveguide near-infrared luminous point, and the method comprises the steps: controlling a near-infrared light machine to generate illumination light in a near-infrared band, and guiding the illumination light to an in-coupling region of a near-infrared light waveguide lens; the illumination light is coupled into the near-infrared light waveguide lens through an in-coupling diffractive optical element arranged in the in-coupling area, so that the illumination light is transmitted in the near-infrared light waveguide lens along a predetermined propagation path and reaches the out-coupling area; in the out-coupling area, an out-coupling diffractive optical element is used for emitting the illumination light from the near-infrared light waveguide lens to form a plurality of near-infrared light-emitting points distributed on the near-infrared light waveguide lens, and the emitting direction of the near-infrared light-emitting points is made to point to the pupil area of the user, so that corresponding cornea reflection light spots are formed on the cornea surface of the user; an infrared eye movement camera is used for collecting an eye image containing a pupil area and a cornea reflection light spot; and performing feature extraction on the eye image to obtain an image coordinate of the pupil center and an image coordinate of the cornea reflection facula, establishing an eyeball geometric model based on a cornea reflection method, and performing calculation to obtain the sight line direction of the user. According to the invention, the problems that the frame is too wide, the view shielding is too large and the wearing comfort is insufficient when the eye movement glasses adopt a cornea reflex method can be solved.

The invention belongs to the technical field of automobile active safety and intelligent cabins, and particularly relates to a self-adaptive dynamic anti-dazzling shading control method based on sight tracking prediction. According to the method, vehicle motion, ambient light and driver state information is collected through a multi-source sensor, a dazzling light source is identified by using a convolutional neural network, and a future position is predicted by combining a long-short-term memory network and a vehicle motion model. Eye images of a driver are captured through an in-vehicle infrared camera, the sight line direction is calculated in real time through a pupil-cornea reflection model, and the future sight line is predicted according to the head posture. A sight line-light source included angle matrix and a dazzling score are calculated according to the predicted light source position, sight line direction and ambient light intensity, and a dazzling area is accurately positioned. The matrix type electric control glass on the front windshield is driven, the light transmittance of the corresponding area is adjusted in real time, and the shading patches are pre-updated. According to the invention, active prediction and accurate shielding of various complex light sources are realized, and the driving safety and the driving comfort are improved.

An electronic device and a control method thereof are provided. The electronic device includes a detection unit configured to perform gaze detection based on an eye image in which an eye looking at a display unit is photographed, and a control unit configured to perform control to give a predetermined notification about a method of adjusting a viewing state in which the display unit is visually perceived based on at least one of a position of a pupil image in the eye image and a number of corneal reflection images in the eye image.

An arrangement for tracking a position of an individual's eye comprises: (a) a frame mountable on a head of an individual; (b) at least one visually transparent element mounted within the frame in a the field of view of an eye of the individual; (c) at least one infrared light source configured for emitting an infrared light beam; (d) an image sensor configured for capturing images of the eye; (e) a processing unit configured for controlling the infrared light source and the image sensor and detecting a pupil position and a corneal reflection within images captured the at least image sensor. The transparent element comprises a spectrally-selective layer configured for reflecting the infrared beam. The visually transparent element is configured for selectively directing the infrared beam onto the eye and directing an infrared radiation reflected from a pupil and cornea of the eye to the image sensor.

The invention relates to a method for the extrinsic calibration of an interior camera in a vehicle, wherein the interior camera is first calibrated with respect to a reference coordinate system and the position of an interior light in the vehicle relative to the reference coordinate system is known. According to the invention, it is provided that: - a three-dimensional environmental model is created with respect to the vehicle based on signals acquired from an environmental sensor; - the interior light in a section is activated corresponding to a position of a three-dimensional object acquired in the environmental model; - a projection vector between a light point of the activated section of the interior light and the position of the acquired object is determined; - a corneal reflection image is determined based on acquired image data from the interior camera to be calibrated.- the determined projection vector is projected onto the corneal reflection image and a reference vector is determined, - a reflected light point of the ambient light activated relative to the object is detected in the corneal reflection image, - a deviation between the reflected light point and the reference vector is determined, - the deviation is evaluated with respect to a threshold value, and - if it is determined that the deviation exceeds the threshold value, extrinsic calibration parameters of the indoor camera are recalibrated.

This invention discloses an eye-tracking device and method. The eye-tracking device includes a dense display device with a first display area configured to emit infrared vector structured light toward a first eye; a first detection component including at least two first probes configured to receive light reflected or scattered by the first eye to acquire first detection image information, the first detection image information including a first pupil center point and at least one first flicker point; and a control component electrically connected to the dense display device and the first detection component, configured to drive the dense display device to emit light and calculate the gaze direction of the first eye based on the first detection image information; wherein the control component is configured to calculate the gaze direction of the first eye using a corneal curvature algorithm model and / or a pupil center corneal reflection algorithm model. This invention can simultaneously meet the requirements of simple structure and high tracking accuracy in eye-tracking devices.

The invention relates to a method for detecting astigmatism based on a visual detection of the eyes (1) of a person. The invention is characterized in that a vehicle-internal computing unit determines a degree of astigmatism by comparing a reflection (3) of the environment extracted from a corneal reflection image (CRI) of a vehicle occupant (2) with an environment camera image (4), wherein the corneal reflection image (CRI) and the environment camera image (4) show at least partially the same section of the environment.

This invention relates to a UV laser-based system, specifically a UV laser-based system (100) for correcting impaired vision in a patient's eye (10), a UVL-LVC system (100). The UVL-LVC system (100) comprises: a UV laser source (102) designed to emit laser radiation to treat the patient's eye (10); and an imaging optics (124) for focusing the laser radiation onto the cornea (12) of the patient's eye (10), wherein the imaging optics (124) is designed such that it detects the reflection (126) of radiation at a receiving angle χMαχ of at least 2.5°, the radiation being incident on the cornea (12) of the patient's eye (10) through the imaging optics (124) and at least partially reflected from the cornea (12) of the patient's eye (10). The invention also relates to a method for centering the UVL-LVC system (100).

The present invention relates to a diagnostic method and a diagnostic apparatus for differentiating a dry eye type. The method comprises: (a) a step of examining a tear film break-up time point and position, photographing a cornea of an eye of a subject to be examined and examining at least one tear film break-up time point in time series as time elapses, at which a break-up appearance is determined from an image of the photographed cornea reflection; (b) a step of examining a corneal surface temperature, measuring the corneal surface temperature of the subject to be examined using a thermal imaging camera, and examining a change in the surface temperature of the cornea over time in time series, which is performed simultaneously with photographing a tear film of the eye; (c) a step of mapping the at least one tear film break-up time point and the change in the surface temperature of the cornea based on time and comparing a position of the at least one tear film break-up time point with a position of the surface temperature of the cornea; and (d) a step of diagnosing a type of dry eye, in a mapping result of step (c), based on any one position of the at least one tear film break-up time point and a position of a change time point of the surface temperature of the cornea corresponding thereto, a type of dry eye is diagnosed.

The invention relates to a computer-implemented method (200) for determining an eye orientation of an eye (24) of a patient (22), performed by a mobile device (10) having a display unit (12) and a camera (14) arranged on the same side of the mobile device (10) as the display unit (12). The method (200) includes outputting (202) instructions (18) to the patient (22) for assisting the patient (22) when orienting the mobile device (10) relative to the eye (24) of the patient (22) such that the display unit (12) and the camera (14) are positioned in a predetermined area relative to the eye (24) of the patient (22) and face the eye (24). The method further comprises determining (204) a position of the eye (24) relative to the mobile device (10); displaying (206) the light visualization (16) on the display unit (12); and capturing (208) at least one image of the eyes (24) by means of the camera (14), such that a corneal reflection (26) of the light visualization (16) displayed on the display unit (12) in each eye (24) of the patient (22) can be determined in the captured image. Furthermore, the method comprises determining (210) a position of a respective corneal reflection (26) in the eye (24) based on the captured at least one image, and determining an eye orientation of the two eyes (24) using the position of the respective corneal reflection (26) in the eye (24).

The present invention relates to the technical field of eye imaging and measurement, and in particular, to a corneal curvature measurement system and a corneal curvature measurement apparatus. The present invention can lower the difficulty of adjusting a light source configured for corneal curvature measurement, without limiting the imaging field of view of other optical paths in the same system or apparatus. The corneal curvature measurement system comprises an eyepiece assembly (100), a light source module (300), a camera module (400), and a diaphragm (500), wherein the light source module (300), the camera module (400), and the diaphragm (500) are located inside the eyepiece assembly (100). The light source module (300) comprises a point light source array (310). The point light source array (310) emits light or forms an image on a focal plane inside the eyepiece assembly (100), and the light passes through the eyepiece assembly (100) as a plurality of collimated light beams incident on the measured eyeball. The plurality of collimated light beams fall on a circumference at the same latitude of the cornea, and form virtual images of corneal reflection points after being reflected by the cornea. Then, real images are formed on a detection surface of a camera (410) through the eyepiece assembly (100) and the camera module (400). The corneal curvature is calculated according to the position information of the corneal reflection points in the real images.

The embodiment of the application provides a method and device for unlocking a vehicle door, the method comprising: controlling a camera to collect pupil data and a corneal reflection image of a target driver in a target vehicle, the pupil data comprising a pupil diameter of the target driver; obtaining a tension level value of the target driver according to the pupil data; obtaining a distance risk value corresponding to each object image in the corneal reflection image and the target vehicle according to the corneal reflection image; and unlocking a door of the target vehicle if the tension level value is greater than or equal to a preset tension level threshold value and the distance risk value of at least one object image is greater than or equal to a preset distance risk threshold value corresponding to the object image. The method can accurately predict whether a vehicle will collide by collecting pupil data and corneal reflection imaging of a driver, and the door of the vehicle can be unlocked in advance before the vehicle collides, thereby improving the safety of the vehicle.

The invention discloses a slit lamp microscopic imaging device integrated with a fundus observation function, and belongs to the technical field of ophthalmology detection, and the device comprises a moving base, a jaw bracket, a light source supporting arm, a microscope supporting arm, a slit illumination assembly, a fundus illumination assembly and a microscopic observation assembly; a central shading diaphragm is arranged on a newly added fundus lighting light path, a front collecting lens capable of movably moving in or out of the light path is arranged between the plane mirror and the microscopic observation assembly, and light combination of the crack lighting light path and the fundus lighting light path is achieved through a beam splitter prism. According to the invention, the central energy of the light beam irradiated to the cornea can be reduced, the fundus examination safety is improved, the interference of cornea reflection stray light is effectively avoided, the fundus imaging quality is improved, the integrated detection of the anterior segment and the fundus tissue is realized, and the efficiency and stability of ophthalmic clinical detection are improved.

The application relates to an AI binocular vision femtosecond laser positioning healing promoting device against eyeball movement interference, and belongs to the technical field of medical instruments. A positioning system comprises a binocular vision acquisition module, a MEMS attitude sensing module, an AI vision tracking module, a signal linkage module and a double-path data synchronous calibration unit. A healing promoting device comprises a PRP storage module, a precise smearing module, a moisturizing and supplementing module and an intelligent control unit, so as to solve the technical problems that the binocular vision and the MEMS linkage are out of synchronization, the corneal reflection interferes with the precision, the PRP activity maintenance time is short, the smearing is prone to loss, the moisturizing and healing synergy is poor, and the positioning and healing are not intelligently linked in the existing femtosecond laser positioning system and the PRP healing promoting device, and the integrated management of preoperative judgment, intraoperative precise positioning and postoperative intelligent healing of refractive surgery is realized.

The invention provides a sitting posture monitoring method and device and glasses, the method is applied to the sitting posture monitoring device arranged on the glasses, the sitting posture monitoring device comprises an inertial measurement unit and a camera, and the method comprises the following steps: controlling the inertial measurement unit to obtain first inertial data of the head of a user according to a first frequency; controlling the camera to obtain a cornea reflection image of the user according to a second frequency; determining whether the user is in a wrong sitting posture reading state or not according to the first inertial data and the corneal reflection image; and when the user is in the wrong sitting posture reading state, sending out a reminding of correcting the sitting posture.

The invention relates to a method for visualizing a vehicle environment using a surround-view system, wherein parts of the vehicle (1) are displayed as semi-transparent in order to avoid obscuring objects in the vehicle environment from a driver's perspective. The invention is characterized in that a corneal reflection image (CRI) is detected by means of a driver observation camera (7) based on two-dimensional images, wherein in an image of the corneal reflection image (CRI) a vehicle interior is segmented as the foreground and the part of the vehicle environment recognizable from the driver's perspective is segmented as the background, wherein a surround-view visualization of the surround-view system is generated depending on a predetermined driver viewing direction, wherein the foreground segmented from the image of the corneal reflection image (CRI) is projected semi-transparently into the surround-view visualization and displayed together with it.

The application relates to the technical field of line-of-sight tracking and discloses a classroom teacher behavior space-time feature fusion tracking method, which comprises the following steps: acquiring a pupil corneal reflection difference signal of teacher eye movement, locking an alias frequency according to aliasing relationship between a classroom lighting modulation frequency and an eye movement sampling rate; calculating a whiteboard glare coefficient of the signal at the frequency, quantifying phase distortion generated by whiteboard mirror reflection, lighting stroboscopic and rolling shutter coupling; analyzing the coefficient into an effective time dislocation between axes, implementing fractional delay phase equalization on an image line scanning axis component of the signal, generating a deskewing vector, and finally calculating a gaze point on a whiteboard plane based on the vector. The application can accurately remove classroom-specific optical-sampling composite noise, effectively suppress abnormal jitter of the line-of-sight signal, and significantly improve the positioning accuracy and stability of teacher board writing behavior monitoring.

The present application relates to the technical field of pupil recognition, in particular to a pupil rotation angle and direction recognition method based on multi-feature fusion, comprising: collecting eye images of a user and positioning eye regions of interest, segmenting to obtain iris annular texture features, pupil edge key point features and double corneal reflection point reference features, and registering as multi-modal features; predicting the pupil rotation angle and the pupil direction based on the multi-modal features; and merging the recognition results of multiple detection frames and outputting. In view of the problem of low robustness of single mode detection in the prior art, the iris annular texture features, the pupil edge key point features and the double corneal reflection point reference features are introduced to form multi-modal features to realize better representation of the actual angle of the pupil and then prediction. Considering the problem of prediction accuracy, the collection time is also prolonged, and the historical multi-frame prediction results are corrected, so as to realize accurate recognition of the pupil rotation angle and direction.