141 results about "Visual Disturbance" patented technology

The invention relates to the technical field of blind guiding robot interactive navigation, and particularly discloses a blind guiding robot interactive navigation system combining vision, inertial navigation and voice, which is characterized in that environmental vision, movement and voice data are synchronously acquired through a multi-modal perception data acquisition module, and are analyzed through a situation-user joint state feature extraction module; a user potential intention deduction module is combined to predict a user intention and generate a self-adaptive guide strategy; a self-adaptive guiding path optimization module adjusts a navigation path according to a strategy to ensure safety and high efficiency; finally, the situational multi-mode interaction instruction output module provides voice and tactile feedback, and interaction experience and navigation autonomy are enhanced. According to the method, the travel problem of the visually impaired person in a complex environment is solved, the individuation, context perception capability and safety of blind guiding are improved, and more natural and efficient navigation assistance is brought to the visually impaired person.

The invention relates to the technical field of data processing, in particular to a mountainous area road vision field obstacle image segmentation and image enhancement processing method, which specifically comprises the following steps: collecting a mountainous area road scene image, and carrying out labeling and data set division; performing multi-modal illumination correction and adaptive perspective correction based on the acquired image, and then extracting amplitude images of the frequency domain gradient and the space gradient of the corrected image for adaptive fusion to generate a fusion enhanced gradient image; a mountainous area road visual impairment detection model is constructed based on the improved U-Net, a mixed cavity convolution module and channel importance re-calibration mechanism, a space-channel double-path attention gating mechanism and an iterative enhancement strategy are adopted in the improved U-Net, sub-pixel convolution operation is adopted at each level of a decoder, and a detection result is calibrated through an example transformation weighting mechanism. Optimizing a detection result by calculating a loss function; and finally, through training, verification and testing, outputting a most important detection result. According to the method, the detection accuracy can be improved, and the sensitivity of the model to obstacle degree detection is reduced.

The invention provides a visual feature generation method for improving visual language model combinatorial reasoning, and belongs to the technical field of cross-modal semantic enhancement and image feature learning, and the method comprises the steps: constructing a data set, and obtaining a semantic offset between a positive description and a negative description to generate a difference vector; generating visual disturbance through the difference vector, guiding image feature modification, and obtaining visual features which keep semantic consistency with negative description of the text; and the generated visual negative features are applied to contrast learning of a visual-language model, and the performance of the model in a combined reasoning task is optimized. The method has the advantages that disturbance vectors for visual features can be generated through semantic offset guidance of positive and negative samples of a text, complementary information between the text and an image is fully mined, and the quality of generation of the visual negative features is improved; complex semantic information is processed more effectively in the evaluation process, and finally the ability of the model in processing the combinatorial reasoning task is improved.

A method and apparatus for generating a visual field pattern which serves as a subjective test protocol to evaluate central vision using dynamic image generation to prevent the brain from filling-in to provide better results of patient feedback and reporting of locations of visual disturbance. This enables effective central vision testing to detect the presence of visual field disruptions including scotoma, visual-neurological perceptual effects such as filling-in, and Troxler fading. The present method and apparatus can be used for vision monitoring and self-assessment, and more particularly for monitoring vision for damage or disease to the macula or retina.

To improve quality of life of users including people with disabilities.SOLUTION: An action control system disclosed herein comprises an input unit for receiving user input, a processing unit for performing specific processing using a sentence generation model for generating a sentence according to an input sentence, and an output unit configured to control an action of an electronic device to output a result of the specific processing. The processing unit determines whether a predetermined trigger condition is met or not and, when affirmative, acquires information needed for visually impaired people as a result of the specific processing using an output of the sentence generation model that uses information obtained from a camera provided on a wearable terminal worn by a user and information obtained from the user input as the input sentence, and the output unit outputs the information needed for visually impaired people by voice.SELECTED DRAWING: Figure 2

The invention discloses an environment perception method based on a binocular camera and an all-round fisheye camera, and the method comprises the steps: collecting the three-dimensional information of an image, carrying out the stereo vision obstacle detection, generating a disparity map, obtaining the three-dimensional information through the position deviation of a corresponding point after the comparison with a reference condition, carrying out the target detection based on deep learning, and carrying out the semantic segmentation. The method comprises the following steps: detecting a drivable area, inputting a sensing result into a decision planning module for track planning, judging whether each path point on a track is occupied at a time point or not, adjusting a plan to avoid risks, and inputting the adjusted track into a vehicle control module. And the control instruction is input into a vehicle platform drive-by-wire module to drive an original vehicle execution mechanism to complete execution of an acceleration / steering angle instruction. According to the method, the binocular camera is used for collecting images to calculate the depth information of the target pixel points, the distance information of the obstacle is obtained, in other words, depth information measurement and calculation are completed on the premise that obstacle target recognition is not completed, and the intelligent driving function of driving and parking is achieved.

The invention relates to a system for activating nerve cells in the human eye and brain for enhancing the residual vision in existing visual-field defects, for reducing or correcting other visual disturbances or cognitive deficits by means of neurostimulation, in particular non-invasive application of microcurrent to the head, more particularly non-invasive transcranial alternating current stimulation (tACS), the system consisting of: a non-invasive applicator for guiding a flow of energy to the eye and brain and for stimulating the blood flow and activation of nerve cells, in particular retinal ganglion cells and brain cells; an impulse generator for generating electrical or magnetic stimulation signals; and a data-processing and control unit for providing patient-specific stimulation signal sequences; wherein the applicator comprises for example at least two electrodes, which can be brought into contact with the head of the test subject and in this respect stimulation electrodes, in particular replaceable stimulation electrodes, are fixed on the applicator such that they rest or make contact on the right and left of the eye in the region of the temple of the patient's head; wherein the stimulation signal sequences are provided repeatedly for application until a demonstrable reduction in an existing vascular dysregulation in the eyes and in the brain is determined.

The invention relates to the field of coal mine danger early warning, and particularly discloses a coal mine conveying belt tearing detection method and system based on AI vision, which does not depend on judgment of a single-frame image any more, and firstly, all candidate targets suspected to be torn are captured by using a high-sensitivity space detector; then, a space-time cube is constructed for each candidate target for cross-frame tracking, and a key time sequence consistency evaluation mechanism is introduced; according to the mechanism, by quantitatively evaluating the stability of the candidate target in appearance, movement and existence persistence, real tearing with stable physical characteristics can be accurately identified from a large amount of instantaneous and random visual interference. According to the strategy of turning spatial feature analysis to spatio-temporal behavior mode verification, the robustness and accuracy of detection are fundamentally improved, and the technical problem of high false alarm rate in a traditional scheme is effectively solved.

The invention relates to an electronic watch with a sense of direction for visually impaired individuals which minimizes the transportation problem for visually impaired individuals and enables them to move as they wish without the need for anyone and which comprises the parts of watch case (1), battery (8), vibration motor (3), motherboard (7), processor, microphone (6) and solenoid coils (4).

A mobile device and a method for testing an individual's vision are provided, the mobile device including a screen for displaying at least one test pattern, such as a smartphone or a tablet computer. A test of the individual's vision is performed using the test pattern displayed on the screen of the mobile device, in particular for testing visual acuity, contrast sensitivity and / or visual disturbances. Further, a parameter influencing the test result is evaluated before and / or during performing the test. The parameter includes at least one of the distance between the eye of the individual and the screen; the brightness at which the test pattern is displayed; and the ambient luminosity.

1. The name of the design product: smart glasses. 2. The use of the design product: for the wearer to perceive multimedia information, and can be used for navigation by visually impaired people. 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 application provides a kind of space perception teaching auxiliary method, device, equipment and storage medium, wherein, the method comprises: determining target value for training, and recording the first starting point of first user action;When triggering end instruction, determine the critical point of first user action;The difference between first starting point and critical point is used as measurement value;According to the comparison result between target value and measurement value, determine the guidance information, feedback guidance information in the form that visual impaired person can perceive.The space perception teaching auxiliary method, device, equipment and storage medium provided by the embodiment of the application, the user makes first user action with the help of mobile terminal, realizes the perception of specified length or angle, and does not need teaching aid throughout;And, each time triggering end instruction, mobile terminal will compare the result of measurement value and target value to user in real time, and does not need the feedback of naked eye person.Provide the efficiency of teaching, also reduce economic cost.

To provide an elevator car capable of making it easier for visually impaired people to recognize the number of car doors.SOLUTION: An elevator car comprises car doors 12 and 13 that open and close, and a car handrail 20 arranged inside. The car handrail 20 comprises a handrail part 22 extending in a first lateral direction, and a door display part 24 formed in an uneven shape on a surface of the handrail part 22 to indicate the number of the car doors 12 and 13.SELECTED DRAWING: Figure 4

A method for compensating for a visual impairment in a virtual reality environment, by multiple computer systems associated with a head mounted display, including, rendering an initial image for display in a virtual reality environment, determining a first visual adjustment to the HMD based on an input received by the HMD, the input being associated with a visual impairment of a user of the HMD, determining that the first visual adjustment does not satisfy a threshold measure of compensation for the visual impairment of the user, determining a second visual adjustment to the HMD, and rendering an adjusted image for display in the virtual reality environment based on the first visual adjustment and the second visual adjustment.

The present application relates to the technical field of data processing, in particular to a mountainous area highway visual field obstacle image segmentation and image enhancement processing method, specifically as follows: collecting mountainous area highway scene image, marking and data set division; based on the collected image, multi-modal light correction and adaptive perspective correction are carried out, then the amplitude graph of the frequency domain gradient and the spatial gradient of the corrected image is extracted for adaptive fusion, and a fusion enhanced gradient graph is generated; based on the improved U-Net, a mountainous area highway visual obstacle detection model is constructed, the mixed hollow convolution module and the channel importance re-labeling mechanism, the space-channel dual-channel attention gate mechanism, the iterative enhancement strategy, the sub-pixel convolution operation in the decoder level and the example transformation weighting mechanism calibration detection result in the improved U-Net, and the detection result is optimized by calculating the loss function; finally, after training, verification and testing, the most heavy detection result is output. The present application can improve the accuracy of detection and reduce the sensitivity of the model to obstacle detection.

A method for producing an educational book includes creating a draft layout with tactile materials and subsequently working up and assembling same. Illustrations, scoring, perforation channels and embossing are applied to the layout. A picture has audio regions applied thereto which, when touched with a portable device, playback an audio track (audio description). All audio files are combined into a single file for recording on a portable audio playback device. The prepared material is sent for comprehensive preparation and printing to produce a finished page spread. This is followed by a decorative work-up and final manual assembly, which includes attaching the tactile materials to the working portions of the spread and folding the spread along the marked score lines. The technical result consists in the creation of a multi-sensory product that allows children with vision impairment to receive information via several sensory channels simultaneously.

According to one embodiment of the present invention, provided is an information processing system. This information processing system is provided with a processor that can execute a program so that the following steps are performed. In an acquisition step, specific user information is acquired which is information pertaining to a specific user. The specific user is a person corresponding to a subject among users engaged in the information processing system. The specific user information includes information indicating that the specific user has a visual impairment or an auditory impairment. In a presentation step, instruction information including an instruction for urging the specific user to perform prescribed speech is variably presented to the specific user in accordance with the specific user information. In a reception step, speech data pertaining to the speech from the specific user is received. In an evaluation step, the presence / absence or the degree of cognitive function deterioration of the specific user is evaluated on the basis of the speech data and a preset trained model.

The embodiments of the present invention provide a barrier-free customer service method, apparatus, device and computer program product. The customer service method includes: in response to a configuration request for a customer service interface from a visually impaired user, activating voice guidance information for configuring the customer service interface; using the voice guidance information to guide the visually impaired user to perform preference configuration operations and obtain barrier-free preferences for the customer service interface; based on the barrier-free preferences and the customer service interface, generating a preference service interface adapted to the visually impaired user; and using the preference service interface to assist the visually impaired user in performing customer service operations. In this embodiment, since the preference service interface is configured based on the preferences of the visually impaired user, when the preference service interface is used to assist the visually impaired user in performing customer service operations, it can not only meet the personalized needs of the visually impaired user, but also effectively ensure the service quality and effect of the visually impaired user.

The invention discloses an application operation method and device, electronic equipment and a storage medium. The method comprises the steps of determining first operation information according to a first application; determining a first operation instruction, and determining a first operation path according to the first operation instruction and the first operation information; determining a first image; and operating the first application according to the first image, the first operation information and the first operation path. According to the method, the trigger path of the first application is determined according to the first operation information, and the first application is triggered according to the obtained trigger path, so that an object with visual impairment can be assisted to complete the operation on the application; the problem that the hearing of an object with visual impairment is occupied by existing operation software is avoided, the safety of privacy information can be guaranteed, and the safety of the object with visual impairment can also be guaranteed.

A device, system and method for generating a full hemispheric view with no blind spots are described. A plurality of image are positioned in an interleaved configuration. A first type of image sensor view is generated by a first type of the plurality of image sensors. A second type of image sensor view is generated by a second type of the plurality of image sensors. The first type of image sensor view and the second type of image sensor view are stitched together into a full hemispheric image sensor view. A visual obstruction from the full hemispheric image sensor view is removed based on the stitching into the full hemispheric image sensor view.

The present application belongs to the field of navigation technology, and relates to a navigation method, a navigation device and a computer readable storage medium. The navigation method comprises the following steps: obtaining user information, the user information comprising biological species information, position information and movement information; matching corresponding navigation prompt information according to the user information; and outputting the navigation prompt information. Therefore, the present application can generate navigation information and output the navigation information correspondingly according to the differences between the visually impaired and the guide dogs, so that the visually impaired and the guide dogs can both receive the navigation information, the visually impaired can be guided not only by the navigation method itself but also by the guide dogs when going out, and the visually impaired can go out more safely and conveniently, the risk and danger of accidents are reduced, the independence of the visually impaired when going out is increased, and the personal safety and health of the visually impaired are ensured.

The invention discloses a virtual simulation training system and method for post-stroke visual disorder rehabilitation. The virtual simulation training system comprises VR glasses, an image generation module, an eye movement detection module, a user interaction module, a feedback evaluation module and a power module. The VR glasses are used for being worn by a patient, so that visual impairment repair is carried out on the patient; the image generation module is used for generating different images so as to provide various different visual restoration schemes; the eye movement detection module is used for synchronizing sight and imaging and acquiring eyeball parameters; the user interaction module is used for enabling a patient to interact with the system and selecting to-be-used options; the feedback evaluation module is used for monitoring and analyzing the reaction time, the accuracy rate and the behavior pattern of the patient in real time; the power module is used for supplying power to other modules. According to the application, the VR technology in the VR equipment is utilized to locally process the image, so that the targeted stimulation on the diseased part is enhanced, and a better rehabilitation effect is provided for the user.

The application discloses a four-fingered tetra intelligent net cage breeding system and method based on behavior recognition and low stress control, which comprises a flexible anti-collision light-blocking net cage module, an underwater AI behavior early warning module, a micro-bubble and sound-light soothing intervention module and a dry-free flexible transfer module. The flexible anti-collision light-blocking net cage eliminates net collision and scale shedding and visual disturbance from the physical structure, the underwater AI behavior early warning module extracts three-dimensional features of sudden change rate of swimming speed, spatial dispersion and gill cover vibration frequency to calculate a comprehensive stress index, realizes four-level grading early warning, the micro-bubble and sound-light soothing intervention module realizes targeted soothing through mute oxygenation, blue-green light and low-frequency sound waves, and the dry-free flexible transfer module realizes underwater zero-fishing transfer of fish bodies. The application improves the survival rate of four-fingered tetra by 22.6% and reduces the scale infection rate by 93.5%, solves the stress bottleneck of large-scale breeding of the four-fingered tetra and is suitable for large-scale near-shore net cage breeding of the four-fingered tetra.

The present disclosure relates to a method for a camera system, in particular a surround-view camera system, for a vehicle, which has a control device, multiple surround-view cameras, and a display apparatus. The method includes: generating an original image (step I), generating a simulated image of the original image, the simulated image simulating a coloration of the original image resulting from an ascertainable visual impairment, generating a differential image between the original image and the simulated image, determining edges in the differential image, generating a superimposed image by superimposing the original image and the edges of the differential image, and displaying the superimposed image using the display apparatus.

The utility model provides a satellite point diffusion re-check multi-point fog-sand multi-effect lens and glasses, and relates to the technical field of lenses, the lens comprises a lens body, at least partial area of the lens body is provided with a point diffusion area, the point diffusion area comprises a transition point diffusion area, a main nucleus point diffusion area and a satellite point diffusion area, the transition point diffusion area is arranged at the inner side, and the main nucleus point diffusion area is arranged at the outer side. The main nuclear point diffusion area and the transition point diffusion area are arranged on the outer side, and the main nuclear point diffusion area and the satellite point diffusion area coincide; the main nuclear point diffusion area comprises a plurality of main nuclear diffusion points, the satellite point diffusion area comprises a plurality of satellite diffusion points, the diameter of the satellite diffusion points is smaller than that of the main nuclear diffusion points, and the satellite diffusion points and the main nuclear diffusion points are arranged in a staggered mode; on one hand, on the basis of ensuring the light transmission of the lens, vision deepening is inhibited in a contrast weakening mode, the effect is remarkable, on the other hand, contrast change transition is gentle and gentle, visual impairment caused by overlarge contrast difference change can be effectively reduced, and the lens is more comfortable to wear.

The invention relates to the technical field of energy storage, and particularly discloses a power bank for users with visual impairment and an electric quantity prompting method thereof.The power bank comprises a power bank body, and a first braille display module is arranged on the power bank body; the first braille display module comprises a plurality of salient point units which can be independently controlled to protrude and retract, and the first braille display module is used for representing the electric quantity interval through the protruding combination of the plurality of salient point units. The first braille display module is not influenced by light and environmental noise, and no matter in a dark environment, a noisy scene or a quiet place, a user with visual impairment can quickly perceive the number of bumps through fingertip touch so as to judge the electric quantity interval, so that barrier-free use experience of touching at any time and knowing immediately is realized.

1. The name of the design product: head-mounted smart visual auxiliary glasses. 2. The use of the design product: for providing environmental perception and travel navigation for the severely visually impaired, realizing obstacle avoidance, text reading and other functions. 3. The design points of the design product: in shape. 4. The picture or photo that best indicates the design points: perspective view.

The utility model relates to the technical field of household control equipment, and discloses an intelligent control panel for electric doors and windows, which comprises a control panel shell, a control panel display screen fixedly mounted in the control panel shell, and a control host fixedly mounted in the control panel shell. The control panel comprises a control panel shell, a control panel display screen, a control host, a sound controller and a main microphone, the control host is provided with a plurality of recognizable buttons, the recognizable buttons are all provided with recognition convex blocks with different characters, the control host is provided with an emergency stop button, and the control panel shell, the control panel display screen, the control host, the recognizable buttons, the sound controller and the main microphone are arranged. In actual use, the problems that the existing electric door and window control panel does not fully consider the special requirements of visual impaired people, so that the users face certain challenges in use, the standard control panel design often depends on visual elements, and the users with limited vision are difficult to identify or understand can be effectively solved.

The application relates to the technical field of blind guiding robot interactive navigation, and particularly discloses a blind guiding robot interactive navigation system combining vision, inertial navigation and voice, wherein the blind guiding robot interactive navigation system synchronously acquires environment vision, motion and sound data through a multi-modal perception data acquisition module, analyzes the data through a context-user joint state feature extraction module, combines a user potential intention deduction module, predicts the user intention, generates an adaptive guiding strategy, adjusts a navigation path according to the strategy through an adaptive guiding path optimization module, ensures safety and efficiency, and finally provides voice and tactile feedback through a situational multi-modal interactive instruction output module, thereby enhancing the interactive experience and navigation autonomy. The application solves the travel problem of the visually impaired in a complex environment, improves the individualization, situational perception ability and safety of blind guiding, and brings more natural and efficient navigation assistance to the visually impaired.