174 results about "Left eye" patented technology

Disclosed in the present invention is a salient contour matching-based method for target measurement in a severe imaging environment. The method specifically comprises: (1) acquiring a binocular image of a target; (2) establishing a global-local joint constraint-based background light estimation model, and removing a scattering effect of a medium in an imaging environment to obtain a restored left eye image and a restored right eye image; (3) learning an original image, and on the basis of a residual between a network reconstructed image and the original image, obtaining target localization prediction maps of the left eye image and the right eye image; and (4) respectively extracting contour lines of the target in the left eye image and the right eye image, constructing feature matching descriptors of contour points, performing stereo matching on the two sets of contour lines by minimizing matching cost, and performing three-dimensional reconstruction on the contour lines in light of calibrated intrinsic and extrinsic parameters to complete the measurement of a key size. According to the present invention, the key sizes of different targets in a severe environment can be accurately measured, thereby providing an effective solution for the problem of measuring the sizes of targets in a severe environment.

This invention belongs to the field of facial expression recognition and provides a micro-expression recognition method based on convolutional neural networks and optical flow features, which is used to improve the adaptability and accuracy of micro-expression recognition. The method first constructs a face detection module to perform face detection on each image frame in a video segment, outputs facial key point information, and extracts facial regions of interest (ROIs) based on the facial key point information: nose, mouth, left eye and eyebrow, right eye and eyebrow. Then, optical flow information and optical strain information are introduced to characterize the spatiotemporal information of facial movement and the intensity information of facial deformation. The optical flow eigenvalue of each image frame is calculated, and a binary search algorithm is used to search for the image frame with the maximum optical flow eigenvalue, which is used as the vertex frame for micro-expression recognition. Finally, a micro-expression recognition model based on a convolutional neural network is constructed, which uses the horizontal and vertical components of the optical flow and optical strain of the vertex frame as input. The micro-expression recognition model outputs a micro-expression category prediction result.

The invention discloses a light-weight heat map stereo matching method and device, which are used for solving the technical problem that the precision of a final parallax result is poor due to the fact that information is easy to lose when a tiny depth difference is captured by the existing light-weight heat map stereo matching method. The method comprises the following steps: acquiring a left eye thermal image and a right eye thermal image, and inputting a preset thermal image stereo matching model (including multi-scale fusion feature extraction, edge feature extraction, an enhanced wavelet attention module, a plurality of cost aggregation residual blocks and a convolution module); a multi-scale module extracts features, generates a left eye and right eye fusion feature map, and constructs an initial cost body; the edge module outputs a left-eye edge probability feature graph, and an intermediate cost body is obtained by combining the initial cost body; the wavelet attention module outputs an attention weight according to the left eye fusion feature map; the cost aggregation residual block is multiplied by the middle cost body according to the weight, and an initial disparity map is generated through disparity regression; and the convolution module combines the left-eye edge probability feature map for refining, and finally generates a target disparity map.

A virtual image display device includes a first display device for a right eye, a second display device for a left eye, a lens barrel or the like serving as an assembly member configured to assemble the first display device and the second display device, and first and second correction units serving as post-assembly adjustment devices configured to adjust a display state of the first display device and the second display device assembled by the assembly member.

A method includes receiving scene image data, comprising left and right images for each eye. Through an eye tracking module, the method includes determining the user's gaze direction or eye vergence. Using this information, the method includes identifying an object in the scene that the user is focusing on, and determining, using a depth estimation module, a left depth from the left eye to the object and a right depth from the right eye to the object. Further, based on the computed left and right depths, the method includes generating, for the left and right eye, constant left and right depth meshes, generating a left and right output images by projecting the left and right images on the corresponding constant left and right depth meshes. Additionally, the method includes displaying the left output image for the left eye and displaying the right output image for the right eye.

A determining device has a processor configured to determine that a driver has dozed off when degree of eye opening of a left eye and degree of eye opening of a right eye of the driver are at or below a reference degree of eye opening and an absolute value of difference between the degree of eye opening of the left eye and the degree of eye opening of the right eye does not exceed a reference difference or determine that the driver has not dozed off when the degree of eye opening of the left eye and the degree of eye opening of the right eye are at or below the reference degree and the absolute value of the difference between the degree of eye opening of the left eye and the degree of eye opening of the right eye exceeds a reference difference during a determining period.

The invention discloses an electronic sighting mark generating device for a synoptophore, relates to the field of optical systems, and is used for solving the problem that the types of sighting marks displayed in a traditional synoptophore are limited and are static. The device comprises a first display module and a second display module, the first display module and the second display module are arranged side by side, the left eye and the right eye of a testee face the first display module and the second display module respectively, the first display module is used for displaying a first test image and enabling light of the first test image to be emitted to the left eye, and the second display module is used for displaying a second test image. The second display module is used for displaying a second test image and enabling light of the second test image to be emitted to the right eye; and the sighting mark generation module is used for processing the image and generating image data, and respectively transmitting the image data to the first display module and the second display module, so that the first display module displays the first test image, and the second display module displays the second test image. Compared with the prior art that images are displayed through slides, more diversified test images can be displayed, and more dynamic test images can be displayed.

The invention relates to the field of image processing, and discloses a fixation point determination method, system and product. The method comprises the following steps: acquiring a first binocular image acquired by an eye camera aiming at the eyes of a user under a visible light condition; predicting a first left eye sight line of the user according to a left eye image in the first binocular image, and predicting a first right eye sight line of the user according to a right eye image in the first binocular image; predicting a first synthetic sight line of the user according to the first binocular image; the first synthetic sight line is a sight line associated with a scene camera; the scene camera is used for collecting a scene in a visual field range of the user; and determining a fixation point of the user based on two of the first left-eye sight line, the first right-eye sight line and the first synthetic sight line. By adopting the method, the near-to-eye tracking precision can be ensured under the visible light condition, and the deployment cost of eye movement tracking equipment can be reduced.

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 relates to an AR glasses binocular calculation algorithm, which is applied to AR glasses provided with left and right light machines, an eye camera and a master control module, and comprises the following steps: S1, initialization and test image projection, after system initialization and ghost image displacement correction are completed, the left and right light machines respectively project binocular calibration images to the eye camera; S2, center calibration positioning, left and right eye field images are acquired through the eye camera, and left eye center coordinates and right eye center coordinates where the binocular calibration images in the left and right eye field images are respectively extracted through an image recognition algorithm; S3, binocular alignment deviation calculation, the position alignment deviation of the left and right eyes is calculated according to the left eye center coordinates and the right eye center coordinates acquired in step S2; S4, dynamic light machine position adjustment, taking the center coordinates of the eye camera as the reference, the left and right light machines are adjusted in the horizontal direction and the vertical direction; and S5, iterative optimization, steps S2-S4 are repeated until the binocular alignment or the maximum iteration number is reached.

The embodiment of the invention provides a sub-pixel offset optimization parallax calculation method, a sub-pixel offset optimization parallax calculation device and electronic equipment. The sub-pixel offset optimization parallax calculation method comprises the following steps: acquiring a binocular image; labeling a label of a target area of the binocular image based on a preset semantic segmentation network; based on the label, extracting visual features of the target area; establishing a matching relation of the target area according to the visual features; respectively calculating a first sub-pixel offset of a left eye image in the binocular image and a second sub-pixel offset of a right eye image in the binocular image according to the matching relationship of the target areas; and calculating the parallax of the binocular image according to the first sub-pixel offset and the second sub-pixel offset. According to the method, the target area is accurately marked by introducing the semantic segmentation network, and visual feature extraction and sub-pixel offset calculation are combined, so that the precision and robustness of binocular image parallax calculation are remarkably improved.

Arrangement of artificial adaptive intraocular lenses whose operating mode is based on binocular interaction and the accommodation-convergence reflex of the eyes, i. wherein all electrically activated adaptive intraocular lenses (8)(9)(10) comprise activation mechanisms and are operated without interaction between the left and right eye, characterized in that ii. the arrangement of the novel artificial adaptive intraocular lenses, whose operating mode is based on binocular interaction (11.3)(12.3)(5) and the accommodation-convergence reflex of the eyes, is characterized by the inclusion of a microchip, wherein a microchip is used for each intraocular lens of each eye, the microchip containing magnetic nanoparticles with electromagnetic properties and made of biocompatible, non-cytotoxic material (5.1)(3.1)(4.1), wherein a conductor connected to the microchip forms a closed loop (5.2)(3.2)(4.2), and wherein the change in the distance between the microchips of the artificial intraocular lenses of the right and left eye during the convergence movements (5.3)(11.2)(12.2) and divergence movements (5.3)(11.1)(12.1) changes both the strength and the phase of the electromagnetic field (5.4) between the two microchips (5.1)(3.1)(4.1) of the two artificial intraocular lenses, which interact with each other, wherein this change in the strength and phase of the electromagnetic field (5.4) causes the generation of an electric charge or voltage at the ends of the conductor (5.5)(3.3)(4.3), which leads to an electric current flow (5.6)(3.4)(4.4) through the closed loop of the conductor (5.2)(3.2)(4.2) due to the induced voltage and according to the principle of electromagnetic induction.

The invention provides a method for checking light leakage of a sun shield, which is used for effectively adjusting and optimally avoiding the conditions of upper light leakage or left light leakage of the sun shield, the sun shield, a ceiling boundary, an A column boundary and a front windshield black edge in the driving process of a driver and passengers. By taking the left limit point or the upper limit point of the left eye ellipse as a projection center, projecting a point on the sun shield onto the curved surface of the front windshield, projecting a point on the left A column onto the curved surface of the front windshield, and projecting a point on the ceiling onto the curved surface of the front windshield; and then processing the data. According to the method, the optimized result can be quantitatively presented, a model or an organizing person is not needed for review, and high efficiency and low cost are achieved.

A personal eyewear device comprises: a frame for supporting one or more lenses in front of a left eye and a right eye of a wearer when the personal eyewear device is worn by the wearer and an electronics module. The electronics module includes: a processor, a memory, a power source for powering the electronics module, and an eye tracking subsystem, wherein the processor and the memory are communicatively coupled with the eye tracking subsystem and wherein the eye tracking subsystem comprises: a first pair of imaging sensors forming a first stereo imaging sensor configured to capture images of a left eye of the wearer; and a second pair of imaging sensors forming a second stereo imaging sensor configured to capture images of a right eye of the wearer. The device further includes at least one additional sensor subsystem and a scheduling module.

Various implementations disclosed herein include devices, systems, and methods that uses a horizontal shift of left eye and right eye image content to control a stereo effect of the image content. For example, a process may include obtaining image data including images to be presented with a stereo effect at a virtual screen position within a three-dimensional (3D) viewing environment. The process may further obtain depth data corresponding to distances of elements of a scene depicted in the images. The process may further determine a horizontal positioning characteristic for presenting the images at the virtual screen with the stereo effect based on the depth data and a view of the images are presented with the stereo effect based on the horizontal positioning characteristic at the virtual screen within the 3D environment. The images may additionally be presented with a blur, a lighting, a fading, and / or a vignetting effect.

This application provides a method, apparatus, and device for left and right eye recognition. The method involves emitting a first signal at a first angle and a second signal at a second angle; receiving reflected signals, including a first reflected signal and a second reflected signal, where the first reflected signal is the signal reflected back from the first signal and the second reflected signal is the signal reflected back from the second signal; and determining whether the currently measured eye is the left or right eye based on the first and second reflected signals. Both the first and second signals are optical signals, or both are coded signals, where the coded signal is an optical signal carrying a code. Embodiments of this application can automatically identify the left and right eyes.

To provide a wearable terminal device capable of OCT-imaging one of the right eye and the left eye while SLO-imaging the other.SOLUTION: An ophthalmologic apparatus comprises: an ejection part including light sources having at least one of a first light source and a second light source for emitting light for an examination with respect to eyes to be examined so as to eject the light from the light sources; an optical system 507 for guiding the light ejected from the ejection part to a right eye retinal and / or a left eye retinal; and a control part 570 for controlling the ejection part and the optical system so as to irradiate the right eye retinal and / or the left eye retinal with the light.SELECTED DRAWING: Figure 14

The application provides a multi-task driver line-of-sight estimation method and system for assisting safe driving. A plurality of driver images are obtained from a video sequence, face key feature points and a face region image of each driver image are extracted by a Dlib CNN method, eye region cropping and head posture extraction are performed on the face key feature points of each driver image, left eye region images, right eye region images and head postures of each driver image are obtained, a driver line-of-sight estimation network is constructed, the left eye region images, the right eye region images, the face region images and the head postures of each driver image are taken as inputs of the driver line-of-sight estimation network, estimated line-of-sight directions and estimated gaze region types of each driver image are obtained, real-time driver images are obtained and input into the driver line-of-sight estimation network, and estimated line-of-sight directions and estimated gaze region types of the real-time driver are obtained.

The invention relates to the technical field of optics, and discloses a display method, electronic equipment and a medium. In the display method provided by the invention, when the processor determines that the user interpupillary distance information is not in the standard interpupillary distance range, the DDIC is indicated to perform translation processing on the to-be-displayed image, and the corresponding display is controlled to display the corresponding image. For example, when the user interpupillary distance is larger than the standard interpupillary distance range, the DDIC is indicated to translate the to-be-displayed image corresponding to the left eye to the left, the display corresponding to the left eye is controlled to display the translated image corresponding to the left eye, and the to-be-displayed image corresponding to the right eye is translated to the right; and controlling the display corresponding to the right eye to display the translated to-be-displayed image corresponding to the right eye. Therefore, the watching requirements of users with different interpupillary distances can be met, the watching experience of the users is improved, in addition, the occupation of processor resources can be reduced by performing translation and other processing on the to-be-displayed image based on DDIC, and thus the power consumption of the processor is saved.

The invention provides an ophthalmic apparatus which can easily detect eye position deviation when brightness difference of a visual target presented to a left eye and a right eye is enlarged from a double-eye visual state. An ophthalmic apparatus (1) is provided with a visual target presentation means (visual target projection system (44)) for presenting a left-eye visual target (OtL) to a left subject eye (EL) and presenting a right-eye visual target (OtR) to a right subject eye (ER), and the left-eye visual target (OtL) and the right-eye visual target (OtR) are in the same form. A sighting target presentation means (sighting target projection system (44)) presents a left-eye sighting target (OtL) to a left subject eye (EL) and presents a right-eye sighting target (OtR) to a right subject eye (ER), thereby enlarging the brightness difference between a common portion of the left-eye sighting target (OtL) and the right-eye sighting target (OtR) and maintaining the brightness difference between the remaining portions of the left-eye sighting target (OtL) and the right-eye sighting target (OtR).

The present disclosure provides a near-eye display for augmented reality having a polygon-curved optical waveguide holographic coupler and a method of operating the same. In the present disclosure, the near-eye display for augmented reality comprises at least one source and a curved optical waveguide disposed in front of at least one of a user's right eye and left eye, which replicates light from the source by internally reflecting it through at least one of two ends and outputs the replicated light for at least one of the right eye and left eye, and the curved optical waveguide may be a polygon-curved optical waveguide having a plurality of planes disposed at points where the light is totally reflected.

The present invention comprises: first and second image display units respectively displaying first and second images to the right eye and the left eye of a user; and first and second display optical elements respectively corresponding to the first and second image display units. The present invention further comprises an actuator for changing the relative position of at least one of the display optical elements and the corresponding image display units. The actuator is driven in accordance with depth information supplied by an image displayed in a region which is a portion of the first and second image display units and crosses the optical axis of the display optical elements in the first and second image display units. In addition, the relative positions of the display optical elements and the corresponding image display units are changed by driving the actuator.

The invention belongs to the technical field of fan gear box defect detection, and relates to a fan gear box defect real-time detection and three-dimensional measurement method and a related device. Comprising the following steps: acquiring a left eye image frame and a right eye image frame in the fan gearbox in real time to form an image sequence; performing defect detection on the image sequence, identifying a defect region in the image sequence and determining a defect category to obtain a defect detection result including the defect region and category information; based on the left eye image frame and the right eye image frame, reconstructing a three-dimensional surface point cloud of the gearbox by adopting a binocular stereoscopic vision algorithm; extracting three-dimensional point cloud data corresponding to the defect area from the three-dimensional surface point cloud according to a defect detection result; and based on the three-dimensional point cloud data corresponding to the defect area, carrying out quantitative measurement on defect size parameters. According to the invention, automatic and intelligent identification and high-precision three-dimensional quantitative analysis of internal defects of the fan gearbox are realized.

The invention discloses a preparation method of a display module and the display module prepared by the method, and the method comprises the following steps: obtaining a substrate, and arranging a plurality of groups of supporting Chip type LED elements on a first surface of the substrate in a matrix manner; a staggered channel jointly formed by the multiple sets of LED elements is filled with colloid, the colloid is solidified to form a shading part flush with the top light-emitting face of any LED element, and the side light-emitting face of any LED element is completely shielded; a polaroid is formed on any top light-emitting surface; the light shielding part is formed by injecting the colloid, so that the influence of interference light formed by the side light emitting part of the LED element on the later imaging quality can be effectively prevented, and the polaroid enables a user to respectively receive corresponding images from the left eye and the right eye so as to form a corresponding three-dimensional effect in the brain; under the action of the process, the limitation of the LED element structure is effectively broken through, and the applicability is higher.

This application relates to the field of smart glasses technology, and discloses a light source detection method, device, equipment, and storage medium. The method is applied to smart glasses equipped with an image acquisition component, and includes: acquiring images of the user's left and right eyes using the image acquisition component; determining the brightness parameters of the user's left eye based on the left eye image, and determining the brightness parameters of the user's right eye based on the right eye image; and performing uniform illumination detection on the current light source based on the left and right eye brightness parameters to obtain a light source detection result. Because this application can acquire images of the user's eyes using the image acquisition component, it allows for direct detection of whether the light source provides uniform illumination based on the left and right eye brightness parameters determined from the eye images. This enables accurate identification of high-contrast lighting environments with significant differences in brightness between the left and right eyes, thereby improving the user's eye health.

A personal eyewear device 100 and method are provided for obtaining eye tracking data of a wearer of the personal eyewear device 100. The personal eyewear device 100 comprises a frame 104, an electronics module 106 including a processor 110, a memory, a power source 112 for powering the electronics module 106, and an eye tracking subsystem comprising a first pair of imaging sensors forming a first stereo imaging sensor configured to capture images of a left eye of the wearer, and a second pair of imaging sensors forming a second stereo imaging sensor configured to capture images of a right eye of the wearer. An accelerometer and gyroscope may provide positional data.

The present disclosure relates to a data processing method, an apparatus, and an electronic device, which relates to the technical field of data processing. The method comprises: a VR device decodes received image data to obtain a planar image to be processed; first acquiring field of view information of a user; then generating, according to the field of view information and the planar image, a left eye image and a right eye image at a same timestamp; and displaying a virtual reality image according to the left eye image and the right eye image at the same timestamp. The present disclosure can reduce the amount of transmitted data by half, reduce the pressure on network bandwidth by half, reduce the situation of network congestion, and correspondingly reduce the transmission delay. The simplified processing procedures result in no problem of asynchronous transmission between the left eye and the right eye.

The invention relates to a method of processing data representative of a person's binocular motricity, the method comprising the following steps: —stimulating the binocular motricity of a person by means of a binocular motricity stimulation device (21) configured to specifically stimulate saccades, vergences or a combination of both or of a reading test (22); physical stimuli in 3D real space seen with both eyes naturally (without artifices); acquiring the movement of the right eye (RE) and left eye (LE) of a person (P) during said stimulation and, if applicable, a stimulation signal from the binocular motor stimulation device; the method comprising the following steps implemented in a processing unit (3); determination from the movement of the left eye (LE) and the right eye (RE), of an effective trajectory (Tr1) of the eyes in response to each stimulation, an effective trajectory corresponding to a saccade and / or a vergence movement of the eyes.

The application discloses a line-of-sight evaluation method and system for calibrating assistance, comprising the following steps: acquiring line-of-sight evaluation video frame data collected by a collection device; wherein the line-of-sight evaluation video frame data comprises dynamic data and static data; performing data segmentation on the line-of-sight evaluation video frame data to obtain left eye line-of-sight data, right eye line-of-sight data and face line-of-sight data; performing convolution operation on the left eye line-of-sight data, the right eye line-of-sight data and the face line-of-sight data respectively to extract features and calculate line-of-sight landing point coordinates; performing data cleaning on the line-of-sight landing point coordinates according to a preset multi-rule joint data cleaning method, calibrating the cleaned data through a convolutional neural network and a full connection layer to output a line-of-sight evaluation result. The application can obtain an accurate line-of-sight evaluation result.

An image synthesizing apparatus stores a first stereo image having a first image for the right eye and a first image for the left eye, arranges a three-dimensional object in a three-dimensional virtual space, generates a second stereo image containing a second image for the right eye, which is an image from the point of sight for the right eye in a state in which the first image for the right eye is displayed, and a second image for the left eye, which is an image from the point of sight for the left eye in a state in which the first image for the left eye is displayed, in the three-dimensional virtual space in which the three-dimensional object is arranged, and outputs the second stereo image.