29 results about "Eyes vision" patented technology

The invention relates to an asymmetric scattering myopia control lens based on human eye visual behaviors, which is applied to the technical field of eye vision optics, and has the design core that an asymmetric visual behavior mode shown by human eyes in an actual visual task is deeply integrated into the optical design of the lens. Therefore, an asymmetric optical structure with scattering intensity distribution highly matched with individual visual habits is constructed. According to the lens, scattering characteristics can be accurately configured in a specific area of the lens according to a preset human eye visual behavior data model, especially in the lower half part of the lens, namely a visual field area corresponding to near-distance tasks such as near-distance reading, writing or electronic equipment use of a wearer; the scattering intensity is higher than that of the upper half part (corresponding to a far task view field area), so that the myopia control efficiency is remarkably improved, and meanwhile, the visual comfort and definition of a wearer are effectively considered.

The invention discloses a near-ground distance measurement method based on virtual large baseline four-eye vision, a medium and equipment, and the method comprises the steps: synchronously obtaining four images when a lifting appliance enters a near-ground operation range; based on the calibration relation between the cameras, the high-altitude images are respectively projected and transformed to the visual angles of the corresponding lifting appliance cameras and fused, two virtual camera images are generated, and therefore a virtual large base line far exceeding the physical distance is constructed; performing three-dimensional correction and cutting on the virtual image pair to obtain a row-aligned three-dimensional image pair; performing feature matching and triangulation on the virtual image pair to generate a sparse reference depth map; and inputting the stereo image pair and the sparse depth map into a pre-trained depth estimation neural network model together, outputting a dense depth map, and converting the dense depth map into a coordinate system taking the lifting appliance as an original point to obtain a vertical distance. According to the invention, the ultra-large baseline is virtually synthesized by using the existing camera, the remote distance measurement precision is improved, the cost is low, and the reliability is high.

The invention discloses a robot bolt assembling method and device based on multi-view vision and force sense cooperation, and belongs to the technical field of intelligent control and industrial automation. According to the method, the positions and poses of an assembled workpiece and a threaded hole are perceived cooperatively through global vision and hand-eye vision, a decision module comprehensively processes multi-source vision information, a motion control instruction is generated, and a mechanical arm is guided to complete coarse positioning and fine positioning before assembly. In the assembling process, the force sense sensing module obtains contact force and moment information in real time, the decision making module dynamically adjusts the posture of the tail end of the mechanical arm based on force sense feedback and a force control algorithm, and posture alignment of the bolt and the threaded hole is achieved. And after alignment is completed, the end effector is rotated to drive the bolt to be screwed into the threaded hole under the condition that the tail end posture is kept stable, and assembling operation is completed. The bolt assembling precision and stability are improved, and the method is suitable for multi-specification bolts and complex assembling environments.

The present application aims to provide a kind of UAV small target detection method inspired by hawk eye vision mechanism, comprising the following steps: A, construct neural network, the neural network includes Backbone network, Neck network module, Head network module;The DFB module is applied in the Backbone network module to simulate the deep foveal structure of hawk eye, and the SFB module is applied to simulate the shallow foveal structure of hawk eye;B, original image is input into Backbone network module, and the resulting processing result is input into Neck network module respectively;C, multi-scale feature fusion is carried out on input feature in Neck network module, two different resolution feature layers are obtained, and are input into Head network module for detection respectively, a series of detection frame and category data are obtained, i.e. final result.The present application method can efficiently extract the feature information of micro target, and accurately locate target in complex scene.

The invention discloses eye-protecting TFT (thin film transistor) liquid crystal panel glass, a preparation method and a liquid crystal display screen, and the preparation method comprises the following steps: cutting white glass, performing edging and chemical strengthening treatment to form TFT liquid crystal panel glass, and cleaning the TFT liquid crystal panel glass; manufacturing five liquid crystal display film layers on the inner side of the cleaned TFT liquid crystal panel glass; eight optical film layers which are stacked layer by layer and are different in thickness are designed on the outer side of cleaned TFT liquid crystal panel glass, optical film coating of the TFT liquid crystal panel glass is completed, the transmissivity of the TFT liquid crystal panel glass obtained after film coating is made to be larger than or equal to 94.5%, and the illumination perspective wavelength range is 630-750 nm. The eye-protecting TFT liquid crystal panel glass is prepared by the preparation method. The liquid crystal display screen comprises the eye-protecting TFT liquid crystal panel glass. The liquid crystal display screen of the prepared TFT liquid crystal panel glass has a good eye protection effect, so that the eyes can see display devices and the display screen more clearly and more easily, the eyes are better protected, the naked eye vision is improved, the blood circulation is accelerated, and the vision is healthier.

The invention discloses an AI-based eye vision optical medical record automatic generation and correction system which comprises a core processing unit, and the output end of the core processing unit is in electric signal connection with a data acquisition module, a semantic analysis module, a dynamic correction module, a data synchronization module and a user interaction interface. And the output ends and the input ends of the data acquisition module, the semantic analysis module, the dynamic correction module, the data synchronization module and the user interaction interface are in bidirectional electric signal connection with the input end and the output end of the core processing unit. According to the AI-based visual optical medical record automatic generation and correction system, a data acquisition module is arranged, specific structured data in the visual optical field is connected through a structured data interface, and meanwhile, free text information input by a doctor is obtained through an unstructured data interface; and the real-time data flow interface is combined to realize real-time acquisition of dynamic data of the patient, so that comprehensive integration of multi-source heterogeneous data is realized, and a complete data basis is provided for subsequent medical record generation.

The application discloses a near-ground ranging method based on virtual large baseline four-eye vision, a medium and equipment, the method synchronously acquires four images when a spreader enters a near-ground operation range; based on a calibration relationship between cameras, high-position images are respectively projected and transformed to a visual angle of a corresponding spreader camera and fused to generate two virtual camera images, so that a virtual large baseline far beyond a physical distance is constructed; virtual image pairs are subjected to stereo correction and cutting to obtain row-aligned stereo image pairs; feature matching and triangulation are performed on the virtual image pairs to generate a sparse reference depth map; the stereo image pairs and the sparse depth map are jointly input into a pre-trained depth estimation neural network model to output a dense depth map, and the vertical distance is obtained in a coordinate system with the spreader as an origin. The application utilizes existing cameras to virtually synthesize an ultra-large baseline, improves long-distance ranging precision, and is low in cost and high in reliability.

The utility model relates to the technical field of vision measurement, in particular to an eye vision measurement device which comprises a base, a stand column is fixedly installed in the middle of the top end of the base, an installation base is fixedly installed at the top end of the stand column, and a lampshade is movably installed over the top end of the installation base. A measuring mechanism is arranged on the front face of the lampshade, and a lighting mechanism is arranged in the lampshade. Protection mechanisms are arranged on the two sides of the mounting base and the lampshade, and a driving mechanism matched with the protection mechanisms is arranged in the stand column. Through the color switching function of the RGBW lamp tube, dual functions of vision degree measurement and color blindness detection are realized, a user can complete comprehensive vision health assessment only by using one device, other equipment does not need to be additionally purchased or used, and the use convenience and efficiency are greatly improved.

The invention belongs to the technical field of eye vision optics, and relates to a scanning type human eye peripheral aberration measuring system and method based on wavefront sensing. The system comprises a measuring light path, an off-axis scanning structure, a full meridian scanning structure, an echo light beam restraining and folding lens group, a conjugate adjusting structure, a sighting mark module, an aligning and imaging module and a control and communication system. The off-axis scanning structure comprises a galvanometer and a linear displacement mechanism, and through the linkage of the position and the angle of the galvanometer, the incident main light enters the entrance pupil center of the detected eye at different off-axis angles; in the full meridian scanning structure, a rotating table drives a front structure to rotate around a system main shaft; echo beams enter a rear fixed light path through the center of the rotary table via the reflector. According to the system, full meridian, large off-axis angle and programmable path human eye peripheral aberration measurement can be realized under the condition that the head and eyeballs of a subject do not need to move, and the system has the advantages of compact structure, small additional aberration, high measurement precision and efficiency and the like.

The invention relates to the technical field of robot vision and advanced man-machine interaction, in particular to an imaging and human eye mapping method and system based on a multi-degree-of-freedom bionic eye platform, which can realize high-precision and real-time matching of a bionic eye vision system and a human eye vision system. Based on the multi-degree-of-freedom bionic eye platform, compared with a binocular camera commonly used in the prior art, the multi-degree-of-freedom bionic eye platform has more degrees of freedom and is more flexible, and the bionic eye joint angle and the human eye motion parameters are directly associated through the trigonometric function relation for the first time. And meanwhile, the eyeball rotation angle is calculated by using the optical axis direction vector of the rotation matrix, so that the accuracy of biokinematics is ensured.

The invention discloses eye-protecting TFT (thin film transistor) liquid crystal panel glass, a preparation method and a liquid crystal display screen, and the preparation method comprises the following steps: cutting white glass, performing edging and chemical strengthening treatment to form TFT liquid crystal panel glass, and cleaning the TFT liquid crystal panel glass; manufacturing five liquid crystal display film layers on the inner side of the cleaned TFT liquid crystal panel glass; six optical film layers which are stacked layer by layer and are different in thickness are designed on the outer side of cleaned TFT liquid crystal panel glass, optical film coating of the TFT liquid crystal panel glass is completed, the transmissivity of the TFT liquid crystal panel glass obtained after film coating is made to be larger than or equal to 94.5%, and the illumination perspective wavelength range is 630-750 nm. The eye-protecting TFT liquid crystal panel glass is prepared by the preparation method. The liquid crystal display screen comprises the eye-protecting TFT liquid crystal panel glass. The liquid crystal display screen of the prepared TFT liquid crystal panel glass has a good eye protection effect, so that the eyes can see display devices and the display screen more clearly and more easily, the eyes are better protected, the naked eye vision is improved, the blood circulation is accelerated, and the vision is healthier.

1. The name of the design product: naked eye 3D system vision training instrument (SK-JS03). 2. The use of the design product: for naked eye 3D system to guide eye vision training, vision care. 3. The design points of the design product: in shape. 4. The picture or photo that best indicates the design points: perspective view 1.

The invention relates to a reverse visual training device based on multispectral dynamic stimulation and a training method thereof. The training device comprises a display device and a hyperopia lens device, the display device comprises a main control board and a display screen which are connected with each other; the hyperopia lens device is of a replaceable lens structure design and is provided with a plurality of hyperopia lenses with different hyperopia degrees; the main control board is used for controlling the display screen to play dynamic sighting mark sequences of four colors of red, blue, green and white, and adjusting the display screen to display the dynamic sighting mark sequences according to a feedback result of a trainer; during visual training, the display screen is placed at a position which is a set distance away from a trainee, the trainee wears the hyperopia lens device and is provided with hyperopia lenses for setting hyperopia degrees, the main control board controls the display screen to play dynamic sighting mark sequences of four colors of red, blue, green and white, and the trainee carries out visual training by observing the dynamic sighting marks and carrying out feedback. According to the technical scheme, the naked eye visual training effect can be improved.

The invention relates to the field of intelligent medicine, and discloses an eye vision light prediction method and device based on multi-scale perception, a medium and a program product. Comprising the steps of obtaining eye vision light data; inputting the eye vision light data into a multi-scale perception feature extraction network to extract features to obtain multi-scale features; and multiplying the multi-scale features by a weight matrix to simulate local and global receptive fields to obtain detail features, finally performing multi-task loss constraint on feature depth interaction, derivative feature construction and unified feature fusion, and predicting the myopia condition of the patient. According to the method, the defect that the internal relation of an eyeball optical system is neglected in the prior art can be overcome, and the accuracy, robustness and clinical interpretability of a prediction model are remarkably improved by introducing multi-task constraints.

The invention discloses a three-dimensional perception method based on four-eye vision of an orthogonal double-baseline unmanned aerial vehicle. The method comprises the following steps: constructing an unmanned aerial vehicle four-eye vision imaging system; obtaining preprocessed left, right, upper and lower images; obtaining a three-dimensional background point cloud; obtaining a three-dimensional point cloud of a cable target; and generating a fused three-dimensional point cloud and the like. According to the invention, wide-area perception and high-precision measurement are both considered, and the unmanned aerial vehicle can see a wide range, and can see clearly and accurately by carrying two sets of stereoscopic vision systems of a short base line wide angle and a long base line long focus. The detection success rate and the three-dimensional measurement precision of key targets such as power lines, pipelines and building edges are greatly improved. In the long-focus image processing process, through ROI extraction, complex stereo matching operation is limited to the extremely small part of the image, the huge calculation amount caused by full-image dense matching is avoided, the whole system can efficiently operate on an unmanned aerial vehicle embedded platform, and the real-time requirement is met.

The invention belongs to the technical field of eye vision optics, and relates to a remote optometry method and device, computer equipment and a storage medium, and the method comprises the steps: sending a remote communication request to a fitting end, and building a shared view with the fitting end based on the remote communication request; in a camera shooting range corresponding to the shared view, light rays are projected to eyes of a user, and multiple groups of refraction signals of the eyes of the user under the light rays are collected; determining multiple groups of initial optometry data according to the multiple groups of refraction signals; fitting the multiple groups of initial optometry data to obtain target optometry data; and converting the target optometry data into optometry parameters, and transmitting the optometry parameters to a fitting end. According to the method, professional judgment and glasses matching requirements are met, the regional limitation is broken, the service accessibility is improved, and the user can conveniently obtain accurate optometry service by guaranteeing the optometry quality and efficiency.

The embodiment relates to an eye vision correction demonstration teaching aid which comprises a parallel light source, a lens for correcting vision and a first convex lens used as a crystalline lens, and is characterized by further comprising a cylinder and a fixing plate, a smoke generating assembly capable of generating smoke is arranged in the cylinder, the top end of the cylinder is provided with an upper end opening, and the upper end opening is provided with a lower end opening. A mark serving as a retina is arranged on the outer wall of the cylinder; the fixing plate is arranged in the barrel and located below the upper end opening, a through hole allowing parallel light to penetrate through is formed in the middle of the fixing plate, the first convex lens is arranged on the fixing plate, and the lens is detachably arranged above the first convex lens and located below the parallel light source. The vision problem demonstration instrument has the advantages that the cause of formation of vision problems and the correction result can be displayed, the whole experiment process is convenient to operate, less time is consumed, the change of a light path can be displayed due to the fact that the cylinder body is filled with smoke, and the experiment phenomenon is more obvious and clearer.

Vision testing system (10, 42) for checking the eyes of a test subject, comprising a display device (11, 12, 13, 45, 46) with which vision test symbols can be visualized for at least one eye of the test subject (44), comprising a control unit (14) for controlling the display device, wherein the display device comprises a backlit screen (19, 30, 35), wherein the screen has an adjustment device for adapting a screen luminance to an ambient luminance, wherein the adjustment device has a measuring device for measuring the screen luminance, characterized in that the vision testing system (10, 42) comprises as a display device a stationary distance test display device (11, 12, 45) whose display area size is designed for vision tests with a viewing distance of 3 m to 10 m, and as a display device a portable near test display device (13, 46),the display area of ​​which is designed for vision tests with a viewing distance of 10 cm to 3 m, wherein the remote test display device has a camera device (25) by means of which the eyes of the test subject (44) can be recorded.

The invention provides a trinocular vision and 4D radar cooperative line external damage prevention early warning method, which belongs to the technical field of external damage early warning, and specifically comprises the following steps: according to mobile monitoring position data and in combination with the distance interval condition between different mobile monitoring positions and other mobile monitoring positions, determining the distance between the mobile monitoring positions and other mobile monitoring positions; the method comprises the following steps: determining a movement control strategy in a comparison processing process of a multi-view vision camera device and a 4D radar which are used for movably monitoring a position, and when it is determined that an early warning strategy needs to be updated based on comparison processing data, combining different camera devices in pairs to form a movement monitoring combination; according to comparison data of different mobile monitoring combinations in different angle intervals in the object moving process, a line external damage prevention early warning method with trinocular vision and 4D radar cooperation in different positions is determined, and the reliability of early warning processing is improved.

The application relates to the field of image processing, and discloses a remote eye optometry and treatment intelligent service method and system and a storage medium. The method comprises the following steps: acquiring an eye fundus image to be processed, and performing standardization processing on the image, wherein the standardization processing comprises normalizing a gray value of the image and performing geometric correction; performing edge detection processing on the image after the standardization, extracting a structural feature region contained in the image, and dividing an image subregion based on the structural feature region; the system comprises the following modules: an image acquisition and processing module, an encoding and transmission module, a decoding and recovery module, and an evaluation and diagnosis module. By introducing a region weight map and a multi-scale decomposition technology, the image reconstruction precision is significantly improved, the detail retention capability is optimized, higher-quality image restoration is realized, and the system performs excellently in complex images and scenes with rich details.

The application discloses a charged power transmission line conductor spacer installation and locking control method of visual alignment, which establishes an impedance model containing target mass, target damping and target stiffness, inputs the external contact force into the model to calculate the compliant displacement, and adjusts the mechanical arm motion trajectory in real time. The system identifies the conductor material and the dancing amplitude through a hand-eye vision sensing unit, and dynamically adjusts the target stiffness value. In the locking stage, the system obtains the real-time torque value and monitors the rotation angle in real time, controls the work carrier and the spacer to separate when the preset threshold is reached and lasts for a preset time, and immediately stops the action and controls the mechanical arm to retreat by a preset distance and then retries if the real-time torque value reaches the torque safety upper limit when the rotation angle does not meet the standard. The application realizes flexible contact and intelligent locking, and improves the safety and reliability of live working.

The invention discloses a medical eye vision rehabilitation exercise device for old people, and relates to the field of rehabilitation exercise devices.The medical eye vision rehabilitation exercise device comprises a bottom plate and supporting frames, a lifting body is arranged between the two supporting frames, the supporting frames are provided with connecting bodies, the two connecting bodies are provided with a training plate, the training plate is provided with a training hole for training eyepieces and a shading plate training hole, and the training hole is provided with an attaching colloid; a massage part is arranged on the fitting rubber body; an adjusting frame is arranged on the bottom plate, an adjusting shaft body is arranged on the adjusting frame, a testing frame is installed at one end of the adjusting shaft body, the other end of the adjusting shaft body is connected with a rotating part, a plurality of inserting frames are arranged in the testing frame, a plurality of light-transmitting plates are arranged in the inserting frames, light source bodies are arranged on the back faces of the inserting frames, and light-transmitting films are arranged on the front faces of the inserting frames. The light source body irradiates on the light-transmitting plate to emit light of different colors, so that a trainee can be in contact with different light, training of the pupil sphincter is facilitated, and through double-eye interchange training, accurate training is facilitated, and fatigue of muscles around the eyes is reduced.

The invention discloses a bionic compound eye net-shaped membrane lens and a film coating method of a compound eye net-shaped membrane layer, the bionic compound eye net-shaped membrane lens is manufactured under the condition of not influencing lens main body imaging, and the bionic compound eye net-shaped membrane lens comprises a lens base layer, a lens hardening layer and a compound eye net-shaped membrane layer. The compound eye net-shaped film layer is plated on the surface layer of the lens substrate to form a plurality of micro convex lens regular hexagonal grids similar to insect compound eye structures, an independent optical element is formed, and the lens surface with the micro lens array structure is complete compared with the surface without the array structure, so that light entering human eyes is remodeled and managed. The definition of human eyes and the management of optical noise such as strong light, glare, stray light and the like are greatly enhanced; according to the lens, light passing through the lens can be effectively remodeled and managed, after optical noise in an eye using environment is eliminated, the definition of vision of eyes of a wearer is enhanced, and stimulation of harmful light such as hard light and glare to the eyes is reduced.

The invention provides a free-form surface astigmatism lens design method based on differentiable ray tracing, is used for astigmatism correction of specific axial positions of human eyes, and belongs to the field of eye vision optical design. Design of the free-form surface lens is realized through a differentiable ray tracing technology, the method fuses multi-lens-eye distance simulation to comprehensively evaluate aberration, constraints of edge thickness and surface curvature inflection points are synchronously introduced in an optimization process, and optimization iteration of a free-form surface system is driven by gradient calculation of lens parameters by means of an evaluation function. And finally, focal power matching in different view fields is realized through the high degree of freedom of the curved surface, so that personalized astigmatism correction requirements of specific axial positions of human eyes are met, the method is suitable for design and manufacturing of astigmatism correction lenses, and the astigmatism correction effect can be improved compared with design of traditional spherical cylinders and the like.

The invention discloses a brain-eye collaborative cognitive enhanced AR (Augmented Reality) intelligent glasses system without language interaction, and belongs to the technical field of intelligent wearable equipment, augmented reality technology and non-invasive brain-computer interface. The system aims at the industry pain points that existing AR equipment is high in visual damage risk, tedious in interaction mode, large in single-mode intention recognition error, heavy in product form and free of cognitive enhancement core ability. Full-link closed-loop coupling of full-spectrum ambient light modulation zero-eye-injury display, eye vision frequency regulation and control enhancement, brain wave synergistic nerve regulation and control, eye movement-electroencephalogram double-locking language-free interaction and cognitive evolution closed-loop training is realized. According to the system, through double verification of eye movement space locking and electroencephalogram intention qualification, the intention recognition accuracy rate is improved to 95% or above, the false touch rate is reduced to 0.1% or below, contactless and language-free consciousness-level interaction can be achieved, meanwhile, the human eye vision boundary can be expanded, the cognitive ability can be enhanced, the whole machine adopts a miniaturized integrated design and a human body self-energy-supply scheme, and the system is suitable for popularization and application. The wearing experience is consistent with that of common glasses. The system can be widely applied to the fields of consumer electronics, medical rehabilitation, industrial assistance, cognitive training and the like.

The invention discloses a visual guidance self-adaptive bottle opening and closing control method and system. The method comprises the steps that a three-section type self-adaptive clamping platform is controlled to execute self-adaptive clamping operation, bottles of known models are rapidly clamped through preset parameters, and bottles of unknown models are gradually clamped in a self-adaptive mode based on real-time torque feedback. The sizes of bottles are accurately recognized and classified in real time through the hand-eye vision system integrated at the tail end of the robot, and therefore the system can actively pre-judge and plan the optimal clamping section and force control parameters before clamping. The three-section type integral moving clamp is combined with a torque feedback self-adaptive clamping algorithm, so that unstable clamping or bottle body damage is avoided; an elastic buffer device and real-time torque monitoring are integrated through the top cover opening unit, so that rigid collision and motor stalling can be effectively prevented through cover opening and closing operation; through a distributed real-time control architecture based on the industrial Ethernet, the cooperation of vision, a robot, a clamp and an uncovering unit is realized.

The utility model discloses a four-eye vision positioning device, which comprises a protective shell and four camera modules, two sides of the protective shell are respectively provided with two mounting grooves, the camera modules are arranged in the corresponding mounting grooves, the outer side of the protective shell is provided with four U-shaped side frames, and each U-shaped side frame is provided with a U-shaped groove. The side walls of the four camera modules are all provided with spherical connecting mechanisms, the outer sides of the spherical connecting mechanisms are sleeved with supporting rings, and the bottom ends of the supporting rings are fixedly connected with supporting rods. The front binocular camera and the rear binocular camera are formed through the four camera modules, by means of the layout, the device can cover the view fields of the front view angle and the rear view angle at the same time, the observation area is remarkably increased, depth information can be obtained through the stereoscopic vision technology, data of the four camera modules are processed through a fusion algorithm, and the image quality is improved. The device is particularly suitable for visual SLAM (Simultaneous Localization and Mapping) application in a complex environment, and can realize stable positioning in dynamic and static scenes.

The present application relates to a kind of bionic human eye vision system, belong to the cross-disciplinary technical field of biomedical and optics.The whole system is placed on unified optical platform, including white light source, linear motorized translation stage, observed target, band-pass filter, achromatic lens, polaroid, electrically controlled diaphragm, artificial lens, scanning lens, two-dimensional galvanometer, beam splitter, beam quality analyzer, full mirror, lens, high-sensitivity photodetector and computer.The advantage is novel structure, through high-sensitivity detector and feedback control circuit can realize automatic adjustment system light quantity size, prevent overexposure, through adjusting artificial lens and two-dimensional galvanometer can realize detecting different distance, different angle object, so as to simulate the basic function of human eye, can gather and process image in complex environment.