468 results about "Visual function" patented technology

In some embodiments, a method receives query content that includes first visual data and select reference content that includes second visual data. A first visual feature mapping for the query content is generated using a model that is trained to generate visual feature mappings using content pairs where alterations in one instance of the content pair are used in the training. A second visual feature mapping is determined for the reference content. The second visual feature mapping is determined using the model. The method compares the first visual feature mapping and the second visual feature mapping to generate a score that rates a similarity between the query content and the reference content. The score is based on recognizing an alteration in one instance of the query content and the reference content. The score is output.

The invention provides a VR-based dynamic visual function training method and device, a medium, a program product and a terminal. An initial training task type and configuration parameters are generated according to a visual evaluation result of a patient, a sighting mark and a stimulation signal for visual function training are constructed, and training is executed through a VR unit. In the training process, feedback data of a patient is collected in real time, a real-time evaluation result is analyzed and generated, task types, configuration parameters and sighting marks are dynamically adjusted, and new stimulation signals are generated to continue training, so that dynamic optimization of training content is achieved. Through real-time evaluation and dynamic adjustment, the problem that the training content is not matched with the requirements of the patient is solved, the defects of a traditional method in the aspects of individuation and adaptability are overcome, the training effect is remarkably improved, the requirements of the patient are better met, the training time is shortened, and the efficiency is improved. The device is especially suitable for rehabilitation training of various visual function defects, and has remarkable advantages in the aspect of dynamic visual function recovery.

According to the multi-mode visual stimulation and intelligent self-adaption combined myopia prevention and control system based on the AR glasses, all-weather, personalized and full-scene myopia suppression is realized through multi-module cooperation of sensory visual stimulation, visual function training, AI scene dynamic recognition and directional intervention, self-adaption closed-loop feedback, cloud / offline deployment and the like; through multi-dimensional visual stimulation and real-time physiological monitoring, eye axis growth is accurately regulated and controlled, myopia prevention and control precision is improved, out-of-focus and contrast setting are automatically optimized based on immediate refraction and adjustment feedback, personalized intervention is enhanced, lightweight AI and cloud pre-calculation are introduced, the endurance of equipment is effectively prolonged, an existing AR platform is compatible, the development process is simplified, and the development efficiency is improved. And the user compliance is enhanced.

Methods and apparatus for generative rendering. In some embodiments, an input visual content is operated on by a computational to perform a computer vision function and output generative display content. The generative display content may overlay the input content to be shown on a display system. In some embodiments, the generative display content replaces the video input stream for display.

A method that includes receiving user input associated with identifying a threshold point associated with a classification task, identifying, a machine learning model, in the first set of visual data, a machine placement candidate point associated with identifying the threshold point, and identifying, based on the machine placement candidate point, a set of baseline confidence values via a baseline uncertainty model. The method includes training the machine learning model based on a determined state space by identifying, subsequent sets of visual data additional threshold points, receiving user feedback indicating an accuracy, comparing the baseline confidence values with locations associated with the additional threshold points, generating reward values based on an identified amount of error, and configuring the machine learning model based on the reward values. The method includes identifying in a second set of visual data, via the trained machine learning model, a visual feature associated with the classification task.

The present invention belongs to the technical field of biomedical materials. Disclosed are a methacrylate, a succinate-diesterified starch, a preparation method therefor and the use thereof in an in-situ filler for corneal defects. The methacrylate, succinate-diesterified starch is prepared by means of performing graft carboxylation on starch and then grafting a double bond. The in-situ filler for corneal defects consists of the methacrylate succinate-diesterified starch (StacMA), gelatin methacryloyl (GelMA), a photoinitiator and a solvent. The corneal filler has a good biocompatibility, an excellent photoresponsive adhesion property and excellent mechanical properties, and can be used for promoting the regeneration of the natural structure of a damaged cornea and the reconstruction of visual function.

The invention relates to the technical field of asthenopia monitoring and health monitoring, and discloses a remote control tower air traffic controller asthenopia monitoring method. The method comprises the following steps: synchronously collecting eye movement, electrocardio, workload and environment multi-modal data, generating a labeling label in combination with a visual function test, and constructing a high-dimensional feature data set; key features are extracted through principal component analysis dimensionality reduction, and real-time prediction of the asthenopia state is achieved through LightGBM model training; a sliding median filtering and fixation event merging strategy is adopted for the eye movement data, and baseline drift is removed and HRV features are extracted from the electrocardio data through Bior4.4 wavelet decomposition; generating an asthenopia label based on the weighted fusion visual function index; optimizing model hyper-parameters by using TPE; in real-time monitoring, the system outputs a trigger alarm according to the model. According to the invention, non-intrusive and high-precision asthenopia monitoring is realized, the system effectively adapts to the complex environment of a remote control tower, and the health management efficiency of controllers and the aviation operation safety are remarkably improved.

Aspects presented herein may enable a UE to improve (e.g., reduce) the convergence time for vision-aided positioning by enabling the UE to use images embedded with location information. In one aspect, a UE receives, from a reference device, a server, or a map, a list of visual features and a location for each visual feature in the list of visual features. The UE identifies at least one visual feature in an area via at least one camera, where the at least one visual feature is included in the list of visual features, where the area is within a threshold distance of the UE. The UE estimates a position of the UE based on the identified at least one visual feature in the area and the location corresponding to the at least one visual feature.

The invention discloses a hyperspectral data fusion analysis system, belongs to the technical field of remote sensing data processing and artificial intelligence, and provides a multi-level data fusion technology by integrating data management, preprocessing, fusion, modeling and visual function modules through a modular architecture aiming at the problems of an existing system. Machine learning algorithms such as a support vector machine and a random forest are integrated to realize dynamic parameter optimization and model evaluation, spectrum curve dynamic display, classification map rendering and customized analysis report generation functions are provided through an interactive visualization module, and system security and expansibility are enhanced based on hierarchical architecture and database standard design. And multi-source equipment access, user permission grading and data encryption storage are supported. The hyperspectral data processing efficiency, the analysis precision and the system stability are remarkably improved, and the method can be widely applied to the fields of environment monitoring, agricultural remote sensing, target recognition and the like.

The invention discloses a method for establishing an animal model for age-related retinopathy caused by lipid metabolism disorder, and the animal model is obtained by specifically knocking out Lss genes from mouse retinal pigment epithelium (RPE) cells by means of a CRISPR / Cas9 gene editing technology. The age-related retinopathy model mouse constructed by the invention shows a retinopathy phenotype with retinal lipid deposition and reduced visual function at the age of 5 months, and the retinopathy is further aggravated along with the increase of the age of the mouse and is similar to the phenotype of age-related retinopathy related to lipid metabolism disorder clinically; and an ideal and effective animal model is provided for researching age-related retinopathy.

The invention provides a neural developmental disorder prediction model construction method, system and device and a medium, and the method comprises the steps: obtaining the clinical information of a child patient, the clinical information comprises severity of developmental retardation / dyspepsia, complexity of syndromic neurodevelopmental disorder, autism spectrum disorder, epilepsy, attention deficit hyperactivity disorder, head circumference deformity, brain development deformity, hearing / visual function impairment and related ear-eye development deformity; applying logistic regression analysis to screen out predictive factors significantly related to the positive diagnosis rate of third-generation whole exon genome sequencing in the clinical information; constructing a neural developmental disorder prediction model based on binary logistic regression according to the prediction factor; and verifying the neurodevelopmental disorder prediction model by applying data of the internal verification group and the external verification group so as to evaluate the prediction efficiency of the neurodevelopmental disorder prediction model, so that the probability of obtaining positive diagnosis after the child patient receives trio-WES detection can be accurately evaluated, and the prediction efficiency is remarkably improved.

The invention belongs to the technical field of visual training, and particularly relates to a multi-dimensional visual training feedback method for improving binocular fusion visual and stereoscopic visual functions, and the method comprises the following steps: carrying out medical baseline detection, generating an initial ability portrait through visual function evaluation and cognitive ability testing, matching training difficulty parameters, and generating a personalized scheme; multi-modal game training is carried out, training types comprise gamification training, animation scene training and offline family task training, and the training difficulty is dynamically adjusted; a tutor performs remote one-to-one guidance, and dynamically adjusts a training scheme according to a change report by tracking the training progress in real time; and the system performs multi-dimensional effect evaluation and self-optimizes a difficulty prediction algorithm. According to the method, the problems of dull training and passive participation, scheme stiffness and execution deviation, single stimulation and cognitive load, scene limitation and continuous interruption are solved.

The invention discloses a personalized myopia prevention and control visual function training and fatigue evaluation method and system, and belongs to the technical field of visual health. In order to solve the problems of single training mode, inaccurate fatigue evaluation, lack of personalized intervention and the like in the existing myopia prevention and control scheme, the method comprises the following steps of: acquiring facial image data of a user through a built-in camera of equipment, and synchronously acquiring interaction data of finishing a visual function training task by the user; and calculating an eye fatigue degree evaluation value in real time by utilizing a preset evaluation model, and generating a personalized visual rest scheme or a training parameter adjustment strategy in combination with personal historical data of the user. According to the method, multi-modal data fusion analysis is innovatively realized, a closed-loop prevention and control system integrating training, evaluation and intervention is established, and the pertinence, accuracy and user experience of myopia prevention and control are effectively improved.

The invention provides an application of a human retina organ in preparation of a medicament for treating traumatic optic neuropathy. According to the invention, the induced and differentiated human retina-like organ is applied to the optic nerve injury area, and the eye and brain nerve connection can be functionally reconstructed, so that the damaged visual function is recovered.

The invention discloses an unmanned aerial vehicle bird nest cleaning device with a visual function, and relates to the technical field of unmanned aerial vehicle application, the unmanned aerial vehicle bird nest cleaning device comprises an unmanned aerial vehicle body, the unmanned aerial vehicle body cooperates with a camera to observe the position of a high-altitude bird nest on power transmission tower equipment, and then the relative position of a clamping plate and the bird nest is adjusted through the unmanned aerial vehicle body; the height of the clamping plates is adjusted through the lifting mechanism, the orientation of the clamping plates is adjusted through the steering mechanism, and the effect of driving the two clamping plates to get close to each other to clamp a bird nest is achieved through cooperation of the stepping motor, the bidirectional lead screw and the sliding block. Then the unmanned aerial vehicle body is controlled to take down the bird nest, then the bird nest removing and cleaning operation on the power transmission tower equipment can be completed, finally, under the action of the unmanned aerial vehicle body, the bird nest is brought to the ground, then the stepping motor is started to control the two clamping plates to be loosened, and the whole device is small, small, low in energy loss and safe and reliable in use.

The invention belongs to the related technical field of neuromorphic visual sensors, and discloses an eagle-eye bionic dynamic visual sensor and a preparation method and application thereof, the visual sensor comprises a dielectric layer substrate, a functional layer and a cross array structure composed of a bottom electrode, an insulating layer and a top electrode which are arranged from bottom to top; wherein the functional layer is of a core-shell heterojunction structure formed by noble metal nanoparticles and a two-dimensional metal chalcogenide. According to the obtained core-shell heterojunction structure, an electron capture and slow release phenomenon caused by local surface plasmon resonance effect excitation and interface defects of precious metal nanoparticles is constructed on a device, and the sensor can realize an eagle-eye-imitating dynamic visual function; and the visual sensor can perform eagle-eye-imitating dynamic visual processing on image information due to a unique electronic synapse function while realizing an image optical sensing function, so that integration of sensing and preprocessing functions is realized.

The invention provides a dual-light fusion night vision device, which comprises a right display lens group, a left display lens group and a bridge frame assembly, the right low-light objective lens group is arranged on the right lens barrel along the right low-light optical axis; the infrared lens group is arranged on the right lens barrel along the infrared light axis; the left display lens group comprises a left lens; the left low-light objective lens group is arranged on the left lens barrel along the left low-light optical axis; the bridge assembly is connected with the right bridge interface piece and the left bridge interface piece in the mode that the right low-light optical axis is parallel to the left low-light optical axis. According to the invention, the right display lens group uses low-light and infrared fusion and has the advantage of dual-spectrum fusion imaging, and the right display lens group and the left display lens group are connected through the bridge assembly, so that the right display lens group has the advantage of stereo imaging and realizes a binocular stereo discrimination visual function.

The invention belongs to the field of visual training, and particularly relates to a multispectral dynamic visual function training system and method. The multispectral dynamic visual function training system comprises an image acquisition module, an intelligent analysis module, a control module, a training execution module and a multispectral light source module, the image acquisition module is arranged at a position corresponding to an eye and is used for acquiring image information near eyeballs of a user, personal information of the user and a vision diagnosis result in real time, and the image information comprises eyeball movement tracks, pupil sizes and forms, cornea edge contours and eye white elastic states; and the intelligent analysis module combines the image information and the acquisition time of the image information. According to the scheme, through collection, analysis, regulation and control of a closed loop, the problems that in the prior art, a real-time analysis mechanism based on eyeball images is lacked, the adaptability of a training scheme and eye dynamic characteristics is weak, and precise regulation and control of functions such as light nutrition supplement and choroid stimulation cannot be achieved are solved; and precise training is also realized, and the effects of prevention and protection, cooperative improvement, compliance improvement and the like are achieved.

The invention relates to the technical field of smart home, and provides an intelligent door opening method and device, electronic equipment and a readable storage medium, and the method comprises the steps: receiving an access request sent by visitor equipment through a visitor browser; verifying the access request, and generating a visiting notification; sending the visiting notification to a smart home application of the householder device, so that the smart home application establishes a two-way communication connection with a smart home platform according to the visiting notification, and turns on a camera and a microphone of the householder device; establishing a bidirectional video transmission channel with a visitor browser, and requesting visitor equipment to start a camera and a microphone; based on the two-way communication connection and the two-way video transmission channel, managing a video call between the householder device and the visitor device, so that the householder confirms the identity of the visitor; and opening the intelligent door lock in response to a door opening instruction sent by the householder through the intelligent home application. According to the technical scheme provided by one or more implementation modes, the visual function of the intelligent door lock can be achieved in a low-cost mode.

Systems and techniques are provided for vision perception processing. An example method can include determining an attention demand score or characteristic per region of a frame from a sequence of frames; generating attention votes per region of the frame based on the attention demand score or characteristic per region, the attention votes per region providing attention demands and / or attention requests; determining an attention score or characteristic per region of the frame based on a number of attention votes from one or more computer vision functions; based on the attention score or characteristic per region of the frame, selecting one or more regions of the frame for processing using a neural network; and detecting or tracking one or more objects in the one or more regions of the frame based on processing of the one or more regions using the neural network.

The invention relates to the technical field of visual function diagnosis, and provides a visual function examination device based on eye movement tracking, a medium and computer equipment, the device comprises a data acquisition unit, an eye movement evaluation unit, a visual field evaluation unit and a comprehensive analysis unit, the data acquisition unit is used for acquiring visual function data of an examinee, and the comprehensive analysis unit is used for analyzing the visual function data of the examinee; the eye movement evaluation unit evaluates an eye movement function based on eye movement parameters in the visual function data; the visual field evaluation unit evaluates a visual field function based on visual field parameters in the visual function data; according to the application, objective sight drop points are used for replacing subjective keys, false negative and false positive are reduced, before typical defects do not appear in the visual field, early visual function changes can be prompted through eye movement parameter abnormity, auxiliary screening of early glaucoma and other diseases is achieved, and the visual function detection accuracy is improved. Meanwhile, the diagnosis accuracy is improved through double evidences of eye movement and visual field in the middle and late stages, and the sensitivity and specificity of visual function examination are remarkably improved on the whole.

The invention discloses a visual indoor decoration engineering online design system and method, and relates to the technical field of building and indoor design, a scheme display module displays a to-be-optimized design scheme by using a visual function of decoration effect picture design software, and a user can perform interactive viewing and editing after logging in; the satisfaction investigation module judges whether a design effect difference evaluation instruction is sent or not according to the user evaluation satisfaction Dmy, and collects user feedback data to construct opinion feedback information; the data acquisition module is used for acquiring furniture layout, material use and color data of the design scheme to be optimized by utilizing a modeling parameter retrieval function based on the difference evaluation instruction; the effect difference evaluation module is used for comparing the user feedback data information with related layout information data, related material information data and related color information data, and fitting to obtain a design effect difference evaluation index Zcy; the optimization design module compares the data with a preset threshold value Y and judges whether redesign is needed or not.

The utility model discloses a turnover mirror for visual function training. The visual training bat comprises a supporting rod, a first connecting block, a second connecting block and a plurality of mirror plates, wherein the first connecting block and the second connecting block are detachably mounted on the supporting rod; the mirror plates are detachably mounted on the first connecting block and the second connecting block respectively; and the plurality of groups of elastic positioning assemblies are respectively arranged on the first connecting block and the second connecting block and are used for elastically clamping the mirror disks. The plurality of mirror discs are detachably mounted on the first connecting block and the second connecting block respectively, so that the mirror discs can be detached and replaced conveniently, the corresponding mirror discs can be directly replaced when the lenses need to be replaced, the process of replacing the lenses is greatly simplified, and even a user without professional knowledge can replace the lenses more quickly; through the arrangement of the elastic positioning assembly, each mirror disc can be elastically clamped on the first connecting block and the second connecting block, the operation is rapid and convenient, and the assembly efficiency is improved.

The invention relates to the technical field of glasses fitting, and discloses an intelligent AI full-automatic glasses fitting debugging system, which comprises the following steps: a face data acquisition and pupil positioning module, a dynamic optical adjustment module, an AI intelligent decision and adaptive optimization algorithm module, a visual function evaluation and dynamic adjustment module, and a data interaction and user feedback module. An intelligent AI full-automatic glasses fitting and debugging method comprises the following steps: acquiring facial geometric data and pupil positions of a user, and calculating pupil distance and pupil height parameters; the diopter and pupil height are adjusted based on facial data, and a liquid crystal adjustable lens and a mechanical translation prism are adopted for dynamic optical adjustment. The AI full-automatic glasses fitting technical scheme based on multi-modal data fusion is adopted, the real-time high-precision glasses fitting adjustment effect is achieved, the problems of precision deviation and tedious operation caused by manual intervention are solved, and the rapid and automatic whole-process fitting process is achieved.

A method for performing an eye test includes the steps of: receiving a request from a user to perform the eye test; acquiring predetermined user identification data from the user; presenting or providing at least one test image to the user, the at least one test image including at least one test target contained therein; instructing the user to identify at least one of the at least one test target(s) contained within the at least one test image; acquiring response data associated with the user's attempt(s) to identify the at least one test target(s) contained within the at least one test image; aggregating and / or analysing the acquired user identification data and / or the response data utilising a test algorithm which determines result data; and, presenting or providing the result data to the user.

The invention provides aqueous ophthalmic solutions of phentolamine or pharmaceutically acceptable salts thereof, medical kits, and methods for using such ophthalmic solutions to improve visual performance in a patient. Exemplary aqueous ophthalmic solutions include those containing phentolamine mesylate, mannitol, sodium acetate, and water.

A method for automatically determining multifocal lens parameters associated with a contact lens and a contact lens for correcting ametropia of a patient's eye wherein a personalized multifocal contact lens for treating presbyopia takes into account various related clinical patient measurements including patient clinical data and lifestyle data, to determine which lens is likely to provide personalized lens parameters for new patients. Historical patient clinical data and lifestyle data are used to train the system to predict which multi-focal lenses (i.e., lenses including lens designs and having lens geometries and powers) would result in optimal lens-to-eye fit and optimal visual function for each eye of presbyopia patients.

The invention provides a full-color-gamut digital curing illumination method and system, and relates to the technical field of medical illumination, and the method comprises the steps: forming a medical curing light password according to the influence of different illumination parameters on visual and non-visual functions (such as rhythm, emotion, sleep and the like); based on the medical treatment healing light password, developing a digital treatment healing illumination module meeting preset illumination intensity, color temperature range, spectral energy distribution, color rendering and anti-dazzle requirements; performing intelligent regulation and control on a digital healing illumination module according to the scene parameters so as to perform healing illumination on the target user; monitoring the illumination quality of healing illumination, user behaviors and biological indexes in real time, and forming a dynamic healing illumination database according to a monitoring result; and analyzing the healing illumination database, generating a standardized illumination strategy library, and performing scene multiplexing. The illumination quality and the physical and psychological health of the user can be improved, a personalized and standardized illumination strategy can be realized through real-time monitoring and data analysis, and better healing experience is provided for the user.

The invention provides sgRNA for knocking out zebra fish pde6a and application of the sgRNA in visual diseases. According to the sgRNA provided by the invention aiming at a specific position, pde6a of the zebra fish can be knocked out or knocked down in a targeted manner by utilizing a CRISPR / Cas9 system. After pde6a is successfully knocked out or knocked down, a zebra fish model with impaired visual functions and normal retina development is obtained, and the model also has morphological changes such as shorter body length, smaller eyes and shorter inter-ocular distance and also shows a trend of increasing the length of an ocular axis. The zebrafish model provides an experimental tool and a model basis for the research of visual function related diseases.