Patents
Literature
Patsnap Eureka AI that helps you search prior art, draft patents, and assess FTO risks, powered by patent and scientific literature data.

63 results about "Visual adaptation" patented technology

Visual adaptation is the temporary change in sensitivity or perception when exposed to a new or intense stimulus, and the lingering afterimage that may result when the stimulus is removed. These continuous small adjustments reflect the neural coding process of the visual system, and exist so the brain can attempt to "normalize" the visual experience.

Tunnel illumination control method considering visual adaptability of driver

The invention relates to a tunnel illumination control method considering visual adaptability of a driver, and belongs to the technical field of tunnel illumination control, and the method comprises the following steps: S1, employing a volume scattering point location method to obtain visual adaptability parameters of visual adaptation states of all segments in a tunnel; s2, dynamically constructing a predictive visual adaptation model of the driver group based on the visual adaptation parameters, and outputting expected visual states of the drivers according to the predictive visual adaptation model; s3, according to the expected visual state, a parameter control mechanism is adopted to control target illumination parameters of all the sections of the tunnel; s4, according to the target lighting parameters, the working state of lighting equipment in a corresponding section in the tunnel is regulated and controlled, so that the light environment in the tunnel is matched with the dynamic visual adaptability of a driver, and safe visual guidance is achieved; the method has the beneficial effects that the target illumination parameters of all the sections of the tunnel are controlled by adopting a parameter control mechanism according to the expected visual state according to the target illumination parameters.
Owner:SICHUAN HIGHWAY ENG CONSULTING & SUPERVISION CO LTD

Brightness control method and system for vehicle-mounted head-up display and display

The invention relates to a brightness control method and system for a vehicle-mounted head-up display and the display. A dynamic adaptation model based on ambient light intensity is constructed by combining human eye visual adaptation characteristics and HUD field angle characteristics, visual adaptation behaviors of human eyes under different illumination conditions can be simulated, and the brightness of the HUD is automatically adjusted according to different light intensity changes, so that information display better conforms to the visual comfort of the human eyes. According to the invention, the maximum HUD display brightness acceptable by human eyes under different illumination conditions can be calculated, the brightness adjustment values under different illumination conditions are dynamically calculated by using the De Boer coefficient, and the brightness of the HUD display is adjusted in real time according to the external light environment, so that the brightness adaptive dynamic closed-loop adjustment is realized, the HUD is effectively prevented from being too bright under low ambient light, and the HUD display quality is improved. The visual blinding phenomenon caused by instantaneous strong light reflection or bright element emerging in a dark scene is avoided, the function safety level of the vehicle-mounted HUD system is remarkably improved, and the ISO 26262ASIL-B level safety requirement is met.
Owner:WUHU HUAYANG TECHNOLOGY CO LTD

Tunnel illumination dynamic optimization method based on driver visual adaptation characteristics

The invention belongs to the field of illumination light control, and relates to a dynamic tunnel illumination optimization method based on driver visual adaptation characteristics, which comprises the following steps of: establishing a relation model between a driver pupil area and ambient illuminance in a tunnel, and calculating a pupil area change rate according to the driver pupil area; establishing a corresponding relationship among the average glancing speed, the pupil area change rate and the ambient light in the tunnel according to the historical data; constructing a calculation model of the total average illumination of the lamps on the road surface in the tunnel based on the natural illumination outside the tunnel and the average horizontal illumination of the lamps on the road surface; an energy consumption and light pollution objective function and a driver psychological load objective function are established based on parameters such as total average illumination of lamps on a road surface in a tunnel and the length from an entrance or an exit, and multi-source data such as illumination, brightness, lamp power, pupil change rate and glancing speed are deeply fused, so that human-vehicle-environment multi-dimensional collaborative optimization is realized. The driving safety and the visual comfort of a driver are improved, and meanwhile, the energy consumption is considered.
Owner:JILIN UNIVERSITY

Tunnel portal dynamic light and signal control system based on vision algorithm

The invention discloses a tunnel entrance dynamic light and signal control system based on a visual algorithm, relates to the technical field of intelligent manufacturing control, and is used for solving the problem of poor light control when the visual field of a tunnel entrance suddenly changes. According to the method, a dynamic sensing mechanism based on visual feature understanding and multi-strategy linkage is constructed, continuous monitoring and intelligent control over the driving visual adaptation state of the tunnel portal are achieved, multi-dimensional visual features are extracted through image collection and preprocessing, visual risk scores are generated, visual field sudden change and traffic abnormity are recognized in combination with a sliding window, and the driving visual adaptation state of the tunnel portal is obtained. A risk response instruction is output, illumination adjustment and signal linkage control are driven, then vehicle behavior continuity, parking probability and blind area shielding factors are fused, speed limiting, guiding or warning signals are dynamically issued, and visual model fine adjustment and strategy updating are performed based on execution feedback. And finally, illumination and signal adaptive optimization under cross-time and multi-environment conditions is realized in combination with a control scene library, and the traffic safety and control intelligence level are improved.
Owner:JIANGXI HIGHWAY RES & DESIGN INST CO LTD

Tunnel lighting method, tunnel lighting system and tunnel

The invention provides a tunnel lighting method, a tunnel lighting system and a tunnel, the method is applied to the tunnel, and the method comprises the following steps: modeling an environment in the tunnel based on a visual simulation technology to obtain a virtual tunnel environment model; in the virtual tunnel environment model, simulating a visual adaptation process of the human eyes under the illumination condition, and obtaining visual response features of the human eyes under the illumination condition; determining illumination design parameters of the tunnel according to the visual response characteristics; and carrying out comfort optimization adjustment on the miner lamp according to the illumination design parameters so as to enable the miner lamp to provide illumination for the tunnel according to the illumination design parameters. In the embodiment of the invention, the visual adaptation process in the tunnel environment can be accurately calculated through the visual simulation technology, so that the visual response characteristics of human eyes under different illumination conditions are more accurately simulated, the illumination effect in the tunnel can meet the visual comfort requirements of drivers and passengers, and the illumination effect is improved.
Owner:SHENZHEN ZHONGFUNENG ELECTRIC EQUIPMENT CO LTD

Piezoelectric film partition dynamic focusing system and method for intelligent glasses

The invention discloses a piezoelectric film partition dynamic focusing system and method for intelligent glasses. The piezoelectric film partition dynamic focusing system comprises an optical modulation layer, a sensing layer, a control engine, a hybrid driving layer and a closed loop verification module. The optical modulation layer is integrated with an N * M piezoelectric film array, each subarea is provided with an independent electrode and a gradient thickness structure, and intervals are filled with low-modulus insulating polymers. The sensing layer is used for acquiring fixation point, diopter, temperature and head movement information of a wearer; and the control engine executes voltage mapping, temperature drift compensation and resonance suppression according to the sensing data, and drives the hybrid driving layer to complete deformation and displacement compensation. And the closed-loop verification module outputs a defocusing error in real time and feeds back a correction voltage. According to the invention, high-response, low-power-consumption and stable dynamic focusing is realized, and the visual adaptability is improved.
Owner:NINGBO JINSHENGXIN IMAGE TECH CO LTD

Illumination light control method and equipment for traffic tunnel and medium

The invention discloses an illumination light control method and equipment for a traffic tunnel and a medium, belongs to the technical field of tunnel illumination control, and aims to solve the problems that the illumination light control in the existing tunnel is relatively simple, the illumination light is difficult to adjust in time according to external light or traffic conditions in the tunnel, the visual adaptability of a driver is easy to be poor, and the illumination effect is poor. And safe driving of tunnel vehicles is not facilitated. The method comprises the following steps: collecting regional visibility data in each segmented scene; performing tunnel illumination feature analysis on the regional visibility data, and determining first control data for adjusting illumination light; performing compensation control on the illumination brightness of the illumination light to obtain second control data; performing brightness partial correlation prediction on the external brightness data and the regional traffic flow data under related human vision optimal experience, and determining optimal experience brightness data; and performing adaptive adjustment of control parameters on the first control data and the second control data to obtain optimal brightness control data.
Owner:山东大通世纪实业有限公司

Two-dimensional organic / inorganic heterojunction photoelectric nerve device and preparation method thereof

The invention discloses a two-dimensional organic / inorganic heterojunction photoelectric nerve component and a preparation method thereof, and belongs to the technical field of photoelectric devices. According to the invention, a TMDC material MoS2 is transferred to a substrate through a mechanical stripping method, then a film electrode is plated on a MoS2 layer through an electron beam lithography method, and finally a single-layer Me-PTCDI crystal is epitaxially grown on the MoS2 layer through a back-off method to form the heterojunction. Due to the formation of the MoS2 / Me-PTCDI heterojunction, the photoelectric nerve device has excellent photosensitivity and light adaptability, and can simulate reactions of retinal essential photosensitive ganglion cells under different illumination; the device can make current change under the stimulation of light pulses so as to simulate the generation and action of human melatonin, and can realize visual adaptation in bright and dark environments under the regulation and control of grid voltage, and the device has a wide application prospect in the field of automatic driving due to the corresponding characteristics.
Owner:NANJING UNIV OF POSTS & TELECOMM

Advertisement push picture generation method and system based on style migration

The invention provides an advertisement push picture generation method and system based on style migration, and the method comprises the steps: firstly analyzing an advertisement style demand, and obtaining an advertisement style guide parameter used for defining the style migration direction of a generative artificial intelligence model; driving a pre-trained generative artificial intelligence model to execute style migration processing by using the parameters to obtain a style migration basic picture; adaptive advertisement core elements based on the basic picture to obtain an element integrated advertisement picture, and ensuring that the element is consistent with the picture in style; performing visual adaptation adjustment on the element integration advertisement picture in combination with the advertisement pushing scene information to obtain a pushing adaptation advertisement picture conforming to the display specification of the pushing terminal; according to the advertisement pushing method and system, the advertisement pushing pictures suitable for different scenes and audience requirements are quickly and accurately generated, and the advertisement communication effect is improved.
Owner:SICHUAN LONGZHANG FENGCAI NETWORK TECH CO LTD

Tunnel portal sunshade design method and system based on viewpoint illumination

The invention discloses a method and a system for designing a tunnel portal sunshade based on viewpoint illumination, belongs to the technical field of tunnel engineering, and aims to solve the technical problem of how to construct a sunshade with an optimal dimming effect by taking dimming uniformity and controllability as a first key for driving heart generation and smooth transition at a tunnel portal of a driver. Comprising the following steps: establishing driver viewpoint illumination feeling grading quantitative indexes; calculating the minimum length of the sunshade tunnel; setting the light transmittance of the tail section of the sun shield, and selecting a plurality of groups of sun shield light transmittance combinations based on a predefined light transmittance rule; setting a visual adaptation index for evaluating the light and dark visual perception of the driver according to the driver viewpoint illumination perception grading index; measuring points of the sunshade are divided based on the step length, whether viewpoint feeling of a driver meets the requirement of a visual adaptation index or not is evaluated by calculating the illuminance ratio of every two adjacent measuring points, the light transmittance combination is optimized according to the evaluation result, and the optimal light transmittance combination and the sunshade tunnel length are determined.
Owner:GUANGZHOU AIRPORT SECOND EXPRESSWAY CO LTD +1

Tunnel guiding system and control method

The invention relates to the technical field of traffic safety, and discloses a tunnel guidance system and a control method, in the system, a data acquisition module comprises an environmental data detection device and a vehicle information acquisition device of a tunnel area; the lighting module comprises a lighting lamp located in the tunnel and a lighting lamp located at a tunnel portal. The illumination lamp at the tunnel portal at least comprises two brightness levels; the line-shaped identification module comprises a plurality of identification devices arranged at a tunnel portal and in a tunnel; and the system control module is used for adjusting the luminance of each identification device in the line-shaped identification module and each lighting lamp in the lighting module according to the data acquired by the data acquisition module. According to the scheme, the illumination and identification modules of the tunnel are automatically adjusted according to real-time information such as ambient illumination, meteorological conditions and traffic flow conditions inside and outside the tunnel, and the black frame effect is relieved, so that the visual adaptation experience of a driver is improved, and the driving safety is enhanced.
Owner:GUANGZHOU MARITIME INST

Full-color LED screen optical adjustment and intelligent energy-saving detection method

The invention discloses a full-color LED screen optical adjustment and intelligent energy-saving detection method, and relates to the field of LED screen adjustment and energy saving. Ambient light data is collected through a bionic distributed sensor network, and features such as illumination intensity and color temperature are extracted through PCA dimension reduction; constructing a human eye visual perception model based on the CIE chromaticity diagram, and introducing a visual adaptation factor to dynamically adjust color gamut mapping; dividing a screen dimming area, and calculating an optimal brightness value by adopting a local contrast enhancement algorithm; the RGB ratio is optimized through a genetic algorithm, and the color difference between the mixed spectrum and the target color gamut is minimized; power consumption is monitored in real time, an energy consumption prediction model is established, and an optimization strategy is triggered when a predicted value exceeds a threshold value. The color gamut coverage rate is high, the local contrast ratio is excellent, and the comprehensive energy-saving rate is greatly improved; blue light harm is reduced, screen flicker is eliminated, the visual comfort is improved, the functions of peep prevention and block chain energy consumption evidence storage are achieved, and the display quality, the energy efficiency performance and the use safety of the LED screen are comprehensively improved.
Owner:SHANGHAI FANGWEI ENVIRONMENTAL ENG CO LTD

Visual identification method and system based on artificial intelligence

The invention relates to the technical field of visual identification, in particular to a visual identification method and system based on artificial intelligence. Comprising the following steps: S1, acquiring image data acquired by a camera, preprocessing the image data, extracting a defect area in the image data by using a panoramic segmentation technology, and acquiring environment data during image shooting according to the image defect area; and S2, constructing a visual adaptation model according to the environmental data, constructing a prediction model to supplement the visual adaptation model, performing visual simulation on a defect area in the image data based on the visual adaptation model, and determining a shooting adjustment angle of the camera according to a simulation result. According to the invention, through image acquisition and preprocessing, panoramic segmentation, environmental data acquisition and visual adaptation model construction, a defect area is accurately identified; combining the prediction model and closed-loop control, dynamically adjusting camera parameters, and optimizing a defect detection effect; the accuracy and stability of the system are ensured through real-time feedback and evaluation, and the automation level and adaptability are improved.
Owner:BEIJING ZHONGKE INST OF OPTICAL ANALYSIS SCI & TECH SHANDONG BRANCH +3

Tunnel photovoltaic sunshade design method capable of meeting visual safety requirement of driver

InactiveCN119577907ARealize integrated photovoltaic designPrecisely match visual adaptation needsGeometric CADSingle network parallel feeding arrangementsDriver/operatorModel selection
The invention discloses a tunnel photovoltaic sunshade design method capable of meeting the visual safety requirement of a driver, and the method comprises the steps: collecting the section parameters of an entrance road section of a target tunnel, the viewpoint illumination change condition of the driver, and other information through data collection and real vehicle testing; designing a visual perception test, and establishing a visual adaptability curve meeting a safety response time threshold value; a sunshade preselection scheme is provided from the angles of the total length, the light transmittance combination scheme, the photovoltaic material laying range and the like; the method comprises the following steps: respectively acquiring data such as a viewpoint illumination change curve and annual total solar radiation quantity through simulation software Ecotect Analysis and meteorological software Meteonorm; comparing and analyzing the simulation curve, and searching a recommendation scheme meeting the visual adaptability curve; and finally, the photovoltaic generating capacity, the economic benefit and the environmental benefit corresponding to the recommendation scheme are obtained through formula calculation, and more reference bases are provided for model selection of the photovoltaic sunshade. The invention constructs a novel photovoltaic sunshade design guidance method which is widely applicable and rich in theoretical basis.
Owner:HEBEI UNIV OF TECH

Attitude motion and visual training combined motion visual evaluation system and method

The invention discloses a motion visual evaluation system and method combining attitude motion and visual training, and relates to the technical field of digital medical treatment and visual health, and the system comprises a biomechanics-attitude acquisition module which integrates a three-dimensional force sensor, a high-precision joint angle sensor, an inertial measurement unit sensor group and a depth camera; synchronously collecting joint torque, ground reaction force, muscle power output, joint angle and posture offset; through a mechanics-vision correlation model of the data processing module, how the biomechanical characteristics influence the visual response and the feedback effect of the visual task on the biomechanical state can be deeply excavated, the improvement of the posture and the visual ability is concerned, the training strategy can be optimized from the biomechanical level, and the training efficiency is improved. And a key basis is provided for the evaluation feedback module to output a multi-dimensional report containing collaborative rating, biomechanical optimization direction and visual adaptation suggestions.
Owner:TSINGHUA UNIVERSITY

Tunnel light environment dynamic dark adaptation experiment method based on driver view

The invention discloses a tunnel light environment dynamic dark adaptation experiment method based on driver view, and relates to the technical field of tunnel illumination, and the method comprises the steps: collecting the view data and behavior data of a driver, obtaining the perception data of the driver in real time, and obtaining a driver view behavior data set; through a light source configuration strategy, tunnel illumination changes are simulated in combination with the virtual reality environment, experiment simulation is conducted, the visual adaptation process of a driver is evaluated, and virtual reality experiment evaluation data are obtained; and based on virtual reality experiment evaluation data, analyzing a visual adaptation condition of a driver and feeding back and adjusting a light source configuration strategy, obtaining a light adaptation strategy, and combining real-time driver feedback data and light environment changes to generate a light adaptation adjustment scheme. The visual comfort, alertness and safety of the driver are improved, the fatigue feeling caused by uncomfortable illumination is reduced, and the safety and comfort of tunnel driving are effectively improved.
Owner:CHINA OVERSEAS CONSTR LTD +1

LED power supply safety control system and method with over-temperature protection function

The invention discloses an LED power supply safety control system and method with an over-temperature protection function, particularly relates to the technical field of LED driving power supply thermal management, and aims to solve the problem of visual stroboflash induced when a traditional over-temperature protection mechanism is implemented. The temperature of a key part of a power supply is monitored in real time, and luminous flux response delay characteristics and human eye vision sensitive frequency parameters of a light source are obtained during overtemperature; calculating a light fluctuation frequency component caused by the power derating operation based on the delay parameter; analyzing dynamic visual adaptation characteristics in combination with environment illumination changes; amending to obtain a perception sensitivity equivalent frequency; when the frequency is lower than a human eye sensitive threshold value, optimizing the derating rate through closed-loop iteration to enable the derating rate to reach the standard; and finally executing power derating according to the optimization rate. Decoupling of a thermal protection process and human eye visual perception is realized, and a light source stroboflash phenomenon is eliminated while thermal safety of a power supply is ensured.
Owner:SHENZHEN UWET ELECTRIC TECH CO LTD

Automatic vision adaptation system and method

A system and method for adjusting brightness levels within a vehicle includes providing destination brightness data, external brightness data, and internal brightness data to a processing system. Processing, in a processing system, at least the destination data, the external brightness data, and the internal brightness data to: calculate an estimated time of arrival (ETA) for the vehicle to reach a predetermined task destination location; comparing the calculated ETA with a maximum visual adaptation time; and selectively implementing a first brightness level adjustment process for adjusting an interior brightness level within the vehicle or a second brightness level adjustment process for adjusting an interior brightness level within the vehicle based on a comparison of the calculated ETA to a maximum visual adaptation time.
Owner:HONEYWELL INTERNATIONAL INC

Cascaded artificial vision substitution compensation mechanism and vision auxiliary enhancement equipment

The invention provides a cascade artificial vision substitution compensation mechanism and vision auxiliary enhancement equipment, and relates to the technical field of artificial vision enhancement, and the mechanism comprises an equivalent convex lens imaging system and a photoelectric imaging system. The equivalent convex lens imaging system is an ultra-short-focus high-convergence equivalent convex lens imaging system formed by one or a series of optical lenses; the photoelectric imaging system captures external image information in real time through the image acquisition equipment, removes depth-of-field information, generates a focus real image for compensating visual adaptation after focal length optimization, and outputs the focus real image to the display equipment to be displayed in front of the visual field of a user; the equivalent convex lens imaging system serves as a substitution mechanism and is located at the near end of a visual axis, the photoelectric imaging system serves as a compensation imaging mechanism and is located at the far end, and the substitution mechanism and the compensation imaging mechanism are sequentially arranged on a light path in a cascading mode from the near end to the far end to form a cascading structure for compensating visual defects. Visual replacement and compensation are achieved at the near end and the far end respectively, and the visual ability of an amblyopia patient is improved.
Owner:温慎洁

A display screen brightness self-adaptive adjusting method and system

This invention relates to the field of intelligent control technology and discloses a method and system for adaptive brightness adjustment of a display screen. The method includes: acquiring ambient light intensity data and analyzing its changing trends to determine the directional characteristics of light intensity as the basis for adaptive speed adjustment; inputting the adaptive speed adjustment basis into a visual adaptation model to generate smooth curve parameters adapted to human eye characteristics, generating a brightness transition sequence through discretization sampling, and converting the brightness transition sequence into an adjustment instruction set; obtaining a target reference value from the adjustment instruction set, calculating the deviation between the actual brightness and the target reference value through a feedback mechanism to obtain a corrected brightness value; fusing real-time light intensity and historical data to construct a time series set and predicting the expected light sequence to generate a primary and backup adjustment path, adaptively switching based on the light intensity deviation; extracting the current adjustment instruction and transmitting it to the display driver module to achieve gradual brightness adjustment and a visually comfortable state. This method can achieve precise adaptation between human eye characteristics and display device hardware.
Owner:SHENZHEN RUIFENG OPTOELECTRONICS CO LTD

Intelligent visual adaptation for image and / or video applications to enhance user experience

A computer-implemented method including receiving an input image; adapting, based on one or more visual adaptation criteria, one or more visual properties of the input image to generate a synthesized image, wherein the adapting includes generating one or more masked image patches, each comprising a respective masked portion of the input image; processing the one or more masked image patches using one or more computer vision models to generate respective ones of one or more output image patches; and generating the synthesized image based on the input image and the one or more output image patches, the synthesized image comprising at least a first portion extending a view of the input image and a second portion modifying content within the input image; and rendering, on a display device, the synthesized image.
Owner:FUTUREWEI TECHNOLOGIES INC

A lightweight conversion method and device for IFC format data

The present invention discloses a lightweight conversion method, device, electronic device and computer-readable storage medium for IFC format data, the method comprising: after obtaining BIM model data in IFC format, performing lightweight processing on the BIM model data to obtain lightweight data; converting the lightweight data into conversion data in a simplified format for three-dimensional visualization on a cloud platform. After obtaining BIM model data in IFC format, the present invention can sequentially perform lightweight processing and format conversion processing on the BIM model data, and finally use the processed data for visualization, thereby realizing visualization adaptation of the IFC model on the cloud platform, while reducing the effect of the amount of data transmitted and analyzed, thereby improving transmission efficiency and processing efficiency.
Owner:GUANGZHOU YUEJIAN SANHE SOFTWARE

Dynamic Optimization Method for Tunnel Lighting Based on Driver's Visual Adaptation Characteristics

The present invention belongs to the field of control of lighting, and relates to a dynamic optimization method for tunnel lighting based on the visual adaptation characteristics of drivers. The method establishes a relationship model between the pupil area of a driver and the ambient illuminance in a tunnel, calculates the change rate of the pupil area according to the pupil area of the driver; establishes the corresponding relationship between the average saccade speed, the change rate of the pupil area and the ambient light in the tunnel based on historical data; constructs a calculation model for the total average illuminance of the lamps on the tunnel road surface based on the natural light outside the tunnel and the average horizontal illuminance of the lamps on the road surface; establishes an objective function for energy consumption and light pollution and an objective function for the psychological load of the driver based on parameters such as the total average illuminance of the lamps on the tunnel road surface, the length from the entrance or exit, etc. By deeply integrating multi-source data such as illuminance, brightness, lamp power, pupil change rate, and saccade speed, multi-dimensional collaborative optimization of "human-vehicle-environment" is realized, taking into account energy consumption while improving driving safety and driver visual comfort.
Owner:JILIN UNIVERSITY

Generalized zero sample learning method based on instance-level vision and semantic self-adaption

The invention discloses a generalization zero sample learning method based on instance-level vision and semantic self-adaption, which can effectively adapt to pre-trained image features of a GZSL task and realize consistent alignment of attributes and images. This contributes to effective transfer of features between visible classes and invisible classes, prompting the performance representation of zero samples. In terms of semantic adaptation, the method proposes to select attributes specific to instances for dynamic semantic prompt tuning. In terms of visual adaptation, the method constructs an instance visual prototype to generate channel attention, thereby adaptively enhancing key visual features of each sample. A large number of experiments on three GZSL reference data sets show that the method achieves advanced performance.
Owner:BEIJING UNIV OF TECH

Method and system for generating candidate sets of video action segments based on common sense enhancement

The present invention belongs to the technical field of video behavior segment retrieval. A method and system for generating a candidate set of video behavior segments based on common sense enhancement is provided, which obtains the semantic feature representation of the query statement and the video to be retrieved; interacts with the semantic representation of the visual feature and the semantic representation of the text feature through a cross-modal interaction module to fuse multimodal information; predicts the probability of each video unit being retained, and retains the video units with high information validity based on the probability; maps the features of the retained video frames to the input space of the large image-text pre-training model through the visual adaptation layer; fine-tunes the large image-text pre-training model by inserting the adaptation layer, and constructs an instruction to instruct the model to complete the task of generating a candidate set of video behavior segments. The present invention introduces a large image-text pre-training model to utilize the rich external knowledge therein to improve the understanding of the visual content, while taking into account the generation speed and accuracy of the candidate set of video behavior segments.
Owner:SHANDONG UNIV +3

Bio-inspired imaging device with in-sensor visual adaptation

A bio-inspired imaging device mimicking visual adaptation of human vision provides a large dynamic range in imaging an image. The device employs a neuromorphic vision sensor realized with phototransistors each being a field-effect transistor, a channel layer of which is an atomically-thin layer of two-dimensional semiconductor material. The channel layer is intentionally formed with defects trap states for trapping a portion of charge carriers generated by a light beam incident on the phototransistor such that intensity information of the light beam is memorized. A gate-source voltage directs the defects trap states to de-trap the trapped portion of charge carriers or to further trap an additional portion of charge carriers, allowing the phototransistor to exhibit a time-dependent excitation or inhibition effect on drain current to thereby enable the imaging sensor to mimic scotopic or photopic adaptation in imaging the image.
Owner:THE HONG KONG POLYTECHNIC UNIV

Intelligent visual adaptation for image and / or video applications to enhance user experience

A computer-implemented method including receiving an input image; adapting, based on one or more visual adaptation criteria, one or more visual properties of the input image to generate a synthesized image, wherein the adapting includes generating one or more masked image patches, each comprising a respective masked portion of the input image; processing the one or more masked image patches using one or more computer vision models to generate respective ones of one or more output image patches; and generating the synthesized image based on the input image and the one or more output image patches, the synthesized image comprising at least a first portion extending a view of the input image and a second portion modifying content within the input image; and rendering, on a display device, the synthesized image.
Owner:FUTUREWEI TECHNOLOGIES INC

A multi-viewing image fusion processing method and system for holographic projection

The present invention relates to the field of picture fusion processing technology, specifically a multi-view picture fusion processing method and system for holographic projection, comprising the following steps: adjusting the focal length and projection angle of multiple projectors based on distance sensor and angle sensor data, automatically calculating and adjusting the picture ratio according to the audience's perspective and distance, matching the actual viewing conditions, and generating a picture adaptation result. In the present invention, the focal length and projection angle of the projector are automatically adjusted by integrating distance and angle sensing data to improve the visual adaptability and consistency of the holographic projection. The dynamic optimization mechanism adjusts the picture according to the specific position and perspective of the audience to ensure that the optimized visual experience adapts to the needs of each audience, reduce visual errors, adjust the color output of each projector, optimize the color dynamic range under the light distribution, enhance the performance of color balance and details, and accurately correct real-time three-dimensional modeling and geometric distortion to improve the overall accuracy and quality of the holographic image.
Owner:SHENZHEN YOULI HOLOGRAPHIC TECH CO LTD +1

Tunnel portal dynamic light and signal control system based on visual algorithm

This invention discloses a dynamic lighting and signal control system for tunnel entrances based on visual algorithms, belonging to the field of intelligent manufacturing control technology, to solve the problem of poor lighting control when the field of vision changes abruptly at tunnel entrances. This invention achieves continuous monitoring and intelligent control of the driver's visual adaptation state at tunnel entrances by constructing a dynamic perception mechanism based on visual feature understanding and multi-strategy linkage. First, multi-dimensional visual features are extracted through image acquisition and preprocessing to generate a visual risk score. Combined with a sliding window to identify abrupt changes in the field of vision and traffic anomalies, risk response commands are output to drive illumination adjustment and signal linkage control. Then, by integrating vehicle behavior continuity, parking probability, and blind spot occlusion factors, speed limit, guidance, or warning signals are dynamically issued. Based on execution feedback, the visual model is fine-tuned and the strategy is updated. Finally, combined with a control scenario library, adaptive optimization of lighting and signals across time periods and multiple environments is achieved, improving traffic safety and control intelligence.
Owner:JIANGXI HIGHWAY RES & DESIGN INST CO LTD

Intelligent watermark replacement method and system based on multi-modal feature matching

PendingCN122289416AEngineeringBackground image
This invention provides an intelligent watermark replacement method and system based on multimodal feature matching. The method includes: reading the image to be processed; extracting the text, visual, and positional features of the watermark using a multimodal feature parsing module, and outputting a multimodal feature vector; dynamically calculating the OCR confidence threshold and the number of generator iterations based on image complexity and processing feedback to achieve adaptive parameter adjustment; performing watermark generation and background restoration tasks in an integrated manner using an improved attention-gated U-Net generator; transferring the visual style of the original image to the new watermark area using a dynamic style transfer module to achieve automatic visual adaptation; and calculating a visual consistency score through a quantitative evaluation module and feeding it back to the dynamic parameter decision module to form a closed-loop optimization. This invention achieves accurate identification and adaptive replacement of watermarks from complex background images, while ensuring a high degree of consistency between the replacement area and the visual style of the original image.
Owner:XIAMEN CHUANGSHI THREAD TECHNOLOGY CO LTD