170 results about "Eye position" patented technology

The invention discloses a data processing and interaction control system based on dynamic eye position tracking, and particularly relates to the technical field of man-machine interaction and eye movement tracking, which comprises an image acquisition module, a data processing module, an interaction control module and an equipment interface module. The image acquisition module controls a near-infrared camera to capture an eye video; the data processing module executes dynamic calibration, triggers calibration points based on a historical gaze point distribution sparse region, updates a sight line mapping model online by adopting a recursive least square method, and recognizes an interaction intention through a state machine in combination with a gaze point sequence and an eye movement event mode; the interaction control module carries out logic binding on the eye movement intention and signals such as head postures, gestures and voice, and a composite control instruction is generated through complementary fusion, concurrent binding and conflict arbitration; and the device interface module standardizes the instruction and then outputs the instruction to the controlled device. The system realizes non-intrusive dynamic calibration, effectively improves tracking precision and interaction robustness, and is suitable for a multi-modal fusion control scene.

The invention discloses a pseudo 3D display method and system based on eye movement tracking and affine transformation, particularly relates to the technical field of display and man-machine interaction, and comprises the steps of 3D model preprocessing, real-time eye movement tracking, view angle parameter calculation, dynamic projection generation, affine transformation correction, display image adjustment and dynamic pseudo 3D display effect realization. The pseudo 3D effect that the visual angle is dynamically adjusted along with the eye position of the user can be achieved through a common 2D screen, special 3D display equipment is not needed, pixel-level perspective correction is achieved, the depth perception of a pseudo 3D image observed by the user is closer to a real three-dimensional space, the visual immersion and interaction naturalness are effectively improved, and the user experience is improved. The core problems that traditional pseudo 3D depth perception is fuzzy and distortion is easily generated due to view angle deviation are solved, the user immersion and interaction naturalness are remarkably improved, and the method can be widely applied to scenes such as virtual social contact, vehicle-mounted HMI, telemedicine and education simulation.

The invention provides a display screen adjusting method and a vehicle, and relates to the technical field of display, and the display screen adjusting method comprises the steps: obtaining the eye position of a user, and the illumination intensity and incident direction vector of incident light of a display screen; determining a reflection direction vector of reflected light corresponding to the incident light based on the incident direction vector of the incident light; and determining an included angle between a reflection direction vector and human eyes based on the reflection direction vector of the reflected light and the position of the human eyes of the user, judging whether a dazzling risk exists or not according to the illumination intensity and the included angle, and adjusting a display screen under the condition that the dazzling risk exists. According to the method, the illumination intensity and the direction vector of the incident light and the human eye position of the passenger are analyzed at the same time, the dazzling risk is actively recognized and responded, and therefore the screen brightness and the contrast ratio can be correspondingly adjusted under the condition that the illumination condition changes or strong light is reflected, and it is ensured that the display content is always clear and visible.

This invention discloses an interactive method and system for automotive taillights with anti-glare and active warning functions. Addressing the problem that single-dimensional dimming based solely on ambient illuminance is insufficient to simultaneously address glare from following vehicles and glare caused by sudden brightness spikes from brake lights, this invention detects the relative distance, relative azimuth angle, and visibility of the following vehicle to determine the driver's eye position area. Based on the inverse square ratio, cosine incidence, and propagation transmission triple attenuation, the current luminous intensity of the taillight is converted into an estimated eye position illuminance. When the estimated eye position illuminance is not less than a first preset threshold, the luminous intensity is reduced without falling below a second preset threshold. During brake light spikes, the rate of increase in estimated eye position illuminance is limited to a third preset threshold to suppress transient glare. Based on the calculated collision time, a rear-end collision warning is output when it is not greater than a fourth preset threshold. This unified illuminance measurement supports both anti-glare and warning functions, achieving a balance between anti-glare and driving safety without the need for a neural network.

The utility model relates to the technical field of clothes, and provides a hat connecting structure and clothes, the hat connecting structure and the clothes are integrally connected, the hat connecting structure comprises a left hat piece, a right hat piece, a middle piece and a front piece, and the left hat piece is provided with a first opening at the eye position; a second opening is formed in the eye position of the right cap piece; the middle piece is connected between the left cap piece and the right cap piece, and one end of the middle piece is connected with a neck or a collar of the garment; the front piece is connected between the left cap piece and the right cap piece, and the front piece, the middle piece, the first opening and the second opening are connected and enclosed to form an eye opening; the front piece is arranged at the neck position of the garment. A full-wrapping cap connecting structure is formed by sewing a plurality of pieces, so that the protection performance and all-around wrapping on the head and the neck are achieved, the good windproof and sun-proof effects are achieved, meanwhile, the breathability is enhanced, the oppressed feeling is reduced, and the wearing comfort is improved.

According to an embodiment of the disclosure, a media content rendering method may be provided. The method may include determining a plurality of eye attributes of a user, based on eye position for each of a left eye and a right eye. The method may include identifying eye movement for each of the left eye and right eye, based on the plurality of eye attributes. The method may include determining a constraint for a movement of each of the left eye and right eye, based on the eye movement. The method may include determining a binocular field-of-view (FOV) of the user, based on the constraint for each of the left eye and right eye. The method may include determining transformation values, based on the binocular FOV of the user. The method may include providing a transformed media content based on the transformation values to render the transformed media content.

The application belongs to the technical field of attention monitoring, and discloses an attention monitoring method, device, equipment and storage medium. The method comprises the following steps: when the use time length of a user is greater than a preset time length, collecting a face video of the user in a preset time period through a head-mounted device, and obtaining a face image in the face video; determining an eye position in the face image, and extracting eye information in the face image according to the eye position; determining eye opening and closing information of the user in the preset time period according to the eye information, and determining gaze information of the user in the preset time period; determining an attention monitoring result of the user based on the eye opening and closing information and the gaze information, and taking an intervention measure according to the attention monitoring result. In the above manner, an intervention measure can be taken in time when it is monitored that the user has attention dispersion.

The application discloses an eye movement detection method and system and a storage medium, which are applied to eye movement measurement requiring a subject to gaze at a visual target, and relate to the biomedical field, in particular to the technical field of eye movement detection. The eye movement detection method comprises the following steps: acquiring head posture data of the subject; determining a compensation amount of the visual target according to the head posture data, wherein the compensation amount comprises a compensation displacement amount and / or a compensation rotation amount; updating a display position and / or an orientation of the visual target according to the compensation amount of the visual target, so that a direction in which a center of an eyeball of the subject points to the visual target is consistent with a direction in which the center of the eyeball of the subject points to the visual target in a preset reference state; collecting eye image data of the subject during presentation of the visual target; determining at least one eye movement parameter based on the eye image data; and outputting an eye movement measurement result of the subject based on the head posture data and the eye movement parameter. According to the scheme, the influence of non-target eye position adjustment of the subject on the eye movement measurement result caused by the subject for maintaining the gaze is reduced, and the accuracy of the eye movement measurement is improved.

The invention relates to an exception handling circuit and exception handling method for clock data recovery. According to the method and the device, the data sender can be supported to implement data scrambling with direct current balance as a target on the target data to be transmitted, so that the data receiver can receive scrambled data with a direct current balance characteristic through a physical channel. On the basis, periodic samples of sampled data obtained by sampling the scrambled data by a data receiver can be obtained, and when it is judged that a sampling clock phase of the scrambled data is locked at a false eye position in an eye pattern of the scrambled data according to periodic direct-current unbalance deviation of a plurality of continuous periodic samples, the scrambled data is locked at the false eye position in the eye pattern of the scrambled data. According to the method, the phase of the sampling clock can be separated from the false eye position by implementing unlocking phase adjustment on the phase of the sampling clock, so that the dynamic calibration of the phase of the sampling clock can be recovered in time, and the failure risk of clock data recovery can be reduced.

A head-mounted display may include a display system and an optical system in a housing. The display system may have displays that produce images. Positioners may be used to move the displays relative to the eye positions of a user's eyes. An adjustable optical system may include tunable lenses such as tunable cylindrical liquid crystal lenses. The displays may be viewed through the lenses when the user's eyes are at the eye positions. A sensor may be incorporated into the head-mounted display to measure refractive errors in the user's eyes. The sensor may include waveguides and volume holograms, and a camera for gathering light that has reflected from the retinas of the user's eyes. Viewing comfort may be enhanced by adjusting display positions relative to the eye positions and / or by adjusting lens settings based on the content being presented on the display and / or measured refractive errors.

The invention discloses a three-section zoom head-up display light path system. The light path system comprises an image generation unit, a free-form surface reflector and a zoom path optimization module, the image generation unit is used for generating an image light beam, and the image light beam is reflected by the free-form surface reflector and then is reflected to the eye position of a driver through a windshield to form a virtual image; the free-form surface reflector supports imaging of different virtual image distances according to preset multi-section surface type parameters; the zoom path optimization module controls the distance change between the image generation unit and the free-form surface reflector according to the vehicle speed information, adjusts the virtual image distance, and achieves three-section zoom display. The invention further discloses a vehicle-mounted head-up display device and / or a motor vehicle comprising the light path system. The invention further discloses a three-section type zooming head-up display light path regulation and control method which has wide application value.

The embodiment of the invention provides a quality control method for an eye fundus image, and the method comprises the steps: firstly, recognizing a region of interest in a target eye fundus image; secondly, extracting eye features and image features from the region of interest; and finally, based on a preset scoring rule and a preset weight, performing weighting processing on a scoring result corresponding to the eye feature and a scoring result corresponding to the image feature, and generating an image quality score. According to the embodiment of the invention, the eye position judgment result, the eye type judgment result, the average definition, the average exposure and the image resolution judgment result of the region of interest are combined for evaluating the quality of the eye fundus image; therefore, the quality of the eye fundus image can be evaluated more comprehensively and accurately; in addition, according to the embodiment, the image feature scoring result and the eye feature scoring result are weighted, so that the eye fundus image can be evaluated in a targeted manner in combination with the characteristics of the eye fundus, the fineness of quality evaluation of the eye fundus image is improved, and later detection of eye fundus diseases is facilitated.

The invention discloses a highway cutting slope photovoltaic panel anti-dazzle belt setting method and device. The method comprises the steps that a plane where a slope toe of a road slope is located serves as a reference plane, eye positions of a driver during driving serve as original points, and the geometrical relationship among the driver, the road, an anti-dazzle zone and the slope is constructed; constructing an equivalent visual field cone formed by the original point and the anti-dazzle visual angle threshold value of the vehicle; the vision field range of a driver during driving is within the equivalent vision field cone; the highway cutting slope is equivalent to a triangular prism; based on the geometrical relationship, solving a section curve at the intersection of the visual field cone and the triangular prism inclined plane, and respectively obtaining a first intersection point of the section curve and the slope top and a second intersection point of the section curve and the slope bottom; based on the original point, the first intersection point, the second intersection point and the geometrical relationship, the effective anti-dazzle interval of the anti-dazzle belt in the vertical direction and the effective length of the anti-dazzle belt in the driving direction are determined. According to the method, the determined anti-dazzle belt can relieve the visual impact of the photovoltaic panel on a driver, and the driving safety is ensured.

The utility model provides a cap-connected neck protection pillow which comprises a neck pillow body and a cap body, and the cap body is connected with the neck pillow body. Wherein the cap body is provided with an eyeshade corresponding to the eyes of a user, the two ends of the eyeshade are connected with the cap body, and the lower edge of the eyeshade is provided with a structure conforming to the outline of the nose of the user. According to the neck protection pillow connected with the cap, the cap body can cover the head, the back face of the neck and the side face of the neck of a user, the neck can be prevented from being sunburnt by dazzling sunlight, the eyeshade can better conform to the face of the user, the eyes can be effectively shielded, the eyes are prevented from being stimulated by the sunlight, and through cooperation of the neck pillow, the cap body and the eyeshade, the user can feel more comfortable. When a user wears the hat, sun shading and sun blocking can be effectively achieved, the better shading effect is provided, the comfort requirement of the user in the journey is met, and the sleep quality is improved.

The invention relates to the technical field of intelligent automobile driving, and discloses a method, device, equipment and medium for preventing a marker from being shielded, and the method comprises the steps: obtaining an environment image of a vehicle in a real environment, and determining the marker coordinates of the marker in the environment image; eye position coordinates of a driver are obtained, and the relative coordinate position of the marker in the sight line plane of the driver is determined based on the marker coordinates; and based on the relative coordinate position, judging the shielding condition of the marker and the head-up display image, and adjusting the head-up display image according to the shielding condition, so that the marker and the head-up display image are not shielded. According to the technical scheme provided by the invention, the sight overlapping can be avoided while the driver can quickly and accurately obtain the key information.

A stereoscopic image display device includes a display panel configured to display an image and an optical member that refracts image display light emitted in the display area of the display panel, outputting it as stereoscopic image display light. A plurality of image sensors arranged in the display area capture front-side image data. A main driver circuit analyzes the front-side image data to track a user's location and / or the user's right and left eye positions and controls pixels in the display area to display right-eye and left-eye image data. The main driver circuit further adjusts the viewing points of the right-eye and left-eye image data based on the tracked user's location and / or eye positions and drives the pixels to display a stereoscopic image aligned with the adjusted viewing points.

This application discloses a vehicle A-pillar blind spot display system and method. It acquires a real-time image of the driver's front view from inside the vehicle using an in-vehicle binocular camera, and a data processing module performs eye recognition and positioning on the driver's front view to achieve real-time eye position acquisition. It also acquires real-time images of the outside environment using an external camera, and the data processing module, combined with wide-angle perspective transformation technology, adaptively crops and adjusts the images based on eye positioning. This allows for the acquisition of the A-pillar blind spot image inside the vehicle, where the external image is obscured by the A-pillar. The A-pillar display screen then displays this blind spot image in real-time, achieving complete integration of the blind spot image inside the vehicle with the external scenery.

The invention provides a three-dimensional display device and a display method. The three-dimensional display device comprises an eyeball tracking device, a processor and a display. The eyeball tracking device tracks a left eye position and a right eye position. The processor calculates a plurality of left-eye viewpoints and a plurality of right-eye viewpoints according to the left-eye position and the right-eye position, and generates a plurality of views. The display comprises a plurality of light emitting units and a plurality of light splitting units. The plurality of light emitting units emit a plurality of light beams. The plurality of light splitting units distribute a plurality of beams of light emitted by the plurality of light emitting units. The processor calculates the field angles and the optical paths of the plurality of light beams emitted by the plurality of light emitting units penetrating through the plurality of light splitting units so as to generate viewpoints through which the plurality of light beams pass. The processor performs light intensity comparison post-processing on views corresponding to at least one of the plurality of left eye viewpoints and at least one of the plurality of right eye viewpoints. The three-dimensional display device and the display method disclosed by the invention can provide a good three-dimensional image display method.

The invention discloses an absolute calibration method for an interferometer with spherical output wavefront. An interferometer, a spherical standard lens, a computer-generated hologram and a plane mirror are included. Firstly, the computer-generated holography works in a spherical mode a, the computer-generated holography is placed in and out of focus positions of an interferometer for measurement, and then the computer-generated holography is rotated by 180 degrees for measurement; after the four steps of measurement are completed, the computer-generated holography works in a spherical mode b, the computer-generated holography is placed in and out of focus positions of the interferometer for measurement, and then the computer-generated holography is rotated by 180 degrees for measurement; then the plane mirror is placed at the cat eye position for measurement; according to computer-generated hologram manufacturing error characteristics, through the nine times of measurement, all errors in measurement results are decoupled, computer-generated hologram manufacturing errors including substrate errors, pattern distortion errors and etching depth errors are removed, interferometer system errors are obtained, and absolute calibration of the interferometer system errors is completed; the method is ingenious in design, high in precision and high in engineering application value.

A method for operating a display device (102) for a vehicle comprises perspective-adjusting first image content to be displayed on a first display surface (106) using a first distance between an occupant's eye position (104) and the first display surface (106) to obtain perspective-adjusted first image content with a smooth transition to second image content to be displayed on a second display surface (108), and of second image content to be displayed on the second display surface (108) using a second distance between the eye position and the second display surface (108) to obtain perspective-adjusted second image content with a smooth transition to the first image content to be displayed on the first display surface.The perspective-adjusted first image content is displayed on the first display area (106) and the perspective-adjusted second image content is displayed on the second display area (108).

The invention relates to a method for displaying visual display contents to a vehicle occupant by means of at least one vehicle-mounted display device for which an associated maximum eyebox window is specified from which the entire display region of the display is visible to said occupant; the method comprising the steps of: - dynamically capturing a current seat and / or eye position of the occupant; - based on this, dynamically detecting whether and how their eyes move in a predetermined eyebox transition region which lies within the eyebox window of a display device currently used by them or adjoins same in such a way that a part of its specified display region is still visible to them; and - changing the display of the display device, in a manner synchronised with the dynamically detected eye movement of the occupant in the eyebox transition region of the respective display device, such that the occupant's leaving the eyebox window, and the movement direction that led to this, is intuitively indicated and / or explicitly displayed to the occupant.

A system and a method set the cockpit in a motor vehicle automatically. The method includes detecting an eye position of a driver in the motor vehicle using a driver observation camera; determining an optimized cockpit setting on the basis of the detected eye position, with the optimized cockpit setting comprising at least one position setting of a positionally adjustable display screen predetermined on the basis of the eye position; and implementing the optimized cockpit setting, with at least the positionally adjustable display screen being set to the predetermined position setting.

The application discloses an AI animation digital human device and method for face-to-face communication with people, which successfully solves the problem of lack of naturalness and immersion in virtual digital human interaction with users by combining sound positioning, infrared laser ranging and face recognition technology. Through the microphone unit and the infrared laser ranging sensor, the device can accurately locate the sound source position and measure the distance between the object and the display screen, avoiding the limitations of traditional speech recognition technology affected by environmental noise. Combined with YOLO algorithm and FaceNet deep learning model, the device can identify the user's facial features in real time and accurately locate the eye position, realizing the synchronous gaze of the digital human eyes and the user's eyes. When the user moves, the device calculates the accurate physical position of the user and adjusts the digital human eye direction to ensure that the digital human always faces the user.

An information processing device according to one aspect of the present invention comprises an acquisition unit and an estimation unit. The acquisition unit acquires a first image including the face of a user at first intervals, and acquires a second image, which is a part of the first image and includes the eyes of the user, at second intervals shorter than the first intervals. The estimation unit estimates real space eye positions, which are the positions of the eyes of the user in the real space, on the basis of the first image and the second image. In the information processing device, the first image including the face of the user is acquired, and the second image including the eyes of the user is acquired at shorter intervals than the first image. Furthermore, the positions of the eyes of the user are estimated on the basis of the first image and the second image. Therefore, it is possible to efficiently detect the positions of the eyes of the user.

An image generation method, including: sending an acquired eye position of a user at a current moment t1 to a server; receiving an initial gaze area, second-resolution image data, and initial first-resolution image data of an image to be displayed from the server, where the second-resolution image data has a resolution lower than the initial first-resolution image data; in response to the fact that the acquired actual eye position at a moment t2 is within the initial gaze area, taking the initial gaze area of the image to be displayed as the actual gaze area of the image to be displayed, and taking the initial first-resolution image data of the image to be displayed as the actual first-resolution image data; and generating the image to be displayed based on at least the second-resolution image data of the image to be displayed and the actual first-resolution image data.

A system for generating a floating image for a passenger within a vehicle includes a passenger monitoring system adapted to monitor the position of the passenger's head and eyes, a compute engine in communication with the passenger monitoring system and adapted to calculate a holographic image and encode the holographic image onto a spatial light modulator (SLM) of a picture generating unit (PGU) hologram generator, a beam steering device, wherein the beam steering device is adapted to receive, via the compute engine, information related to a position of the passenger's head and eyes from the passenger monitoring system, and the SLM is adapted to project the holographic image to the beam steering device and the beam steering device is adapted to re-direct the projected holographic image to the eyes of the passenger, based on the information received from the passenger monitoring system.

Method (Z) for controlling a medical imaging device (1) and / or an information display device (7) that displays data (BD) generated by the medical imaging device (1) to a user (13) by means of a user input (EI, AI), wherein the user input (EI, AI) is performed at least on the basis of an eye position and / or movement detection (Y) in combination with a further non-contact user input recognition logic (X), - wherein the user input (EI, AI) includes a selection input, wherein the user (13) views an object and / or region to be selected with the eye (15) and initiates a selection of the viewed object by means of an expression of intent signal, and the selection input is continued by the user (13) moving the selected object to a location he views after initiating the selection by means of a displacement signal, and / or - the user input (EI, AI) based on eye position and / or movement detection (Y) in combination with further non-contact user input recognition logic (X) includes a graphical input of an object.

The invention discloses a fixation point evaluation method and device integrating head movement and eye movement data and a guide method and device. The method comprises the following steps: collecting eyeball initial position data and head initial position data; and combining the eye movement data and the head movement data, and calculating a fixation drop point position of the eyes. And performing rotation conversion of head movement and eye movement to calculate a gaze direction vector. Calculating a drop point position of the fixation drop point position in a picture displayed by the VR equipment by using an equidistant columnar transformation projection method; and based on the eye drop point position, analyzing eye movement behaviors in different scenes. The head movement and eye movement data of the subject are collected through the VR equipment, the eye movement and head movement rotation matrix and the gazing direction vector are calculated, the drop point and track of the gazing direction on the picture are obtained through projection transformation, the coverage area and time of the gazing point are analyzed, and the gazing behavior of the person is effectively evaluated.

The present invention relates to a method for diagnosing an ocular disease from a fundus image. The method for diagnosing an ocular disease from a fundus image, according to an embodiment of the present invention, comprises: a step A of extracting a grayscale map from a static field of view report by using template matching; a step B of generating a pair of images by mapping a patient's fundus image and the grayscale map, the patient's fundus image having the same examination date and the same eye position; and a step C of training a visual field prediction model by using the generated pair of images.