47 results about "Visual distance" patented technology

The invention discloses a screen control integrated clearance lamp integrated industrial vehicle intelligent safety early warning system and method, and relates to the field of industrial vehicle safety early warning. The three-dimensional dynamic light field outline marker module adopts a metamaterial and a DMD (Digital Micromirror Device) to construct a dynamic light field and generate a virtual-real fusion guide line; the multi-modal perception fusion module integrates a radar and a camera, and constructs a space-time association graph model; the edge calculation decision module constructs a neuromorphic calculation unit, and adopts SNN to process time sequence data; the screen control integrated interaction module develops a light field tactile feedback display screen and generates a three-dimensional interaction interface through holographic projection; the holographic sound field positioning module deploys a metamaterial and designs a sound wave phase conjugate mirror; and the vehicle-road cooperative communication module adopts an OAM multiplexing technology to realize a 5G-V2X communication distributed edge cache network. The visual distance is optimized in rainy and foggy weather, the night detection effect is guaranteed, power consumption and response delay are controlled, operation errors are reduced, spectrum efficiency is optimized, and operation safety and economical efficiency of industrial vehicles are enhanced.

The invention provides an auxiliary driving control method and device based on visual distance detection. The method is applied to a vehicle which is provided with image acquisition equipment and supports an auxiliary driving function, and comprises the following steps: under the condition that the auxiliary driving function of the vehicle is started, acquiring a road image acquired by the image acquisition equipment for a current road, and determining the maximum visual distance of the vehicle at the current moment based on the road image; determining the minimum safety identification distance of the vehicle at the current moment according to the road information of the current road and the current driving information of the vehicle; and degrading or closing the auxiliary driving function at least under the condition that the maximum visual distance is not greater than the minimum safe identification distance.

The utility model discloses electronic equipment, and relates to the technical field of electronics, the electronic equipment comprises a case assembly, a push-pull assembly and a screen, the push-pull assembly comprises a push-pull guide rail and a moving part, the push-pull guide rail is arranged on the case assembly, the moving part is slidably arranged on the push-pull guide rail and can move along the extension direction of the push-pull guide rail, the screen is arranged on the moving part, and the push-pull guide rail is arranged on the case assembly. The electronic equipment can move along with the moving part along the extension direction of the push-pull guide rail, so that position adjustment is realized, and the screen is electrically connected with the case assembly through a cable, so that information in the electronic equipment is displayed in a visible form for a user to watch. According to the electronic equipment disclosed by the invention, the position adjustment of the screen relative to the case assembly is realized through the arrangement of the push-and-pull assembly, so that the use requirements of a user on the screen under different sight distances can be met; in the adjusting process, only the screen needs to be moved, the case assembly does not need to be moved, the visual distance between the screen and a user can be conveniently adjusted, and the flexibility of screen position adjustment is improved.

The application provides a multifunctional portable visual function detection device, which comprises a large screen, a small screen assembly, a reflection assembly, a rear support for fixing the small screen assembly and the reflection assembly, an optical module and a front support for fixing the optical module; the reflection assembly comprises two mirrors which can rotate with a mirror support; and the optical module comprises two lenses which can slide up and down along the front support. The detection device has the characteristics of high efficiency, high integration and portability, adopts a common optical path design, applies a reflection device, adjusts image elements, effectively reduces the size of the device, applies virtual imaging technology of the optical module to realize 5000mm visual function detection, and does not need any auxiliary personnel to independently complete 11 detection functions of visual acuity, color vision, stereoscopic vision, contrast sensitivity, hidden squint and flash fusion frequency under 300mm and 5000mm visual distances.

The application is suitable for the technical field of unmanned aerial vehicle cruising, and provides a nuclear power inspection method, device, equipment and medium based on deep reinforcement learning, which comprises the following steps: collecting state information containing the current position of the unmanned aerial vehicle at the current time, judging whether the distance between the current position and a target tracking point is less than a distance threshold, if yes, judging whether all target track points in a target inspection path have been tracked, if yes, completing the safety inspection of the nuclear power containment, otherwise, setting the target track point corresponding to the next time as the target tracking point, and jumping to the step of collecting the state information in real time, otherwise, according to the collected state information, obtaining the visual distance of the unmanned aerial vehicle at the current step by using a pre-trained optimal speed decision model, and tracking the target tracking point by using a preset trajectory tracking algorithm according to the visual distance and the current position, so that the average success rate and execution efficiency of the inspection task are improved.

The present application belongs to the field of remote sensing image processing, and particularly relates to a ship detection method based on remote sensing images. The present application aims at the problem of low recognition accuracy in the existing ship model detection task of remote sensing images, and proposes a ship detection method based on remote sensing images. The present application constructs a ship detection model based on remote sensing images for the fine-grained target recognition task of marine ships; inputs the ship remote sensing image of the to-be-recognized area into the trained ship detection model based on remote sensing images to obtain the ship model of the ship in the to-be-recognized area; decouples the fine-grained target detection task into a positioning subtask and a classification subtask, and simultaneously, in view of the problem of short supply of marine ship training samples, designs a data expansion strategy based on CycleGAN and a contrast learning module to improve the recognition accuracy. The present application solves the problem of poor recognition accuracy in the existing fine-grained target recognition technology of remote sensing images due to high visual distance, small targets and insufficient training data.

This application relates to the field of display technology, and more particularly to display control methods, apparatus, devices, and readable storage media. The method includes: displaying a target interface on a display screen, wherein a target display area in the target interface is displayed on the display screen according to first display parameters, and the target display area includes an area of ​​interest to a browsing object on the display screen; and, when a display parameter update condition is met, controlling the target display area to be displayed on the display screen according to second display parameters; wherein the first display parameters and the second display parameters respectively correspond to different visual distance simulation states. Using embodiments of this application, visual fatigue caused by prolonged viewing at a fixed distance can be reduced while maintaining visibility of the main content.

The invention discloses a screen shooting image moire quantification method and device and a storage medium, which are used for improving the compensation precision of a display screen. Acquiring a sub-pixel unit image of the display screen to be tested; performing brightness compensation processing on the sub-pixel unit image to generate an expected brightness compensation image; generating a compensation graph frequency spectrum amplitude image according to the brightness compensation image; generating a stripe frequency band sensing image according to the visual distance and the pixel pitch corresponding to the target color channel; carrying out region division on the frequency spectrum amplitude image of the compensation graph; standard deviations of the elliptical region and the plurality of elliptical ring regions are calculated, and a region standard deviation set is generated; filling a blank image with the standard deviation in the regional standard deviation set to generate a first elliptical ring standard deviation image; performing frequency domain filtering on the first elliptical ring standard deviation image by using the stripe frequency band sensing image to generate a first frequency domain filtering image; and generating a first moire quantization value corresponding to the brightness compensation image according to the compensation image frequency spectrum amplitude image and the first frequency domain filtering image.

The present application relates to the technical field of holographic imaging, and particularly relates to a holographic imaging information display structure. The technical scheme comprises a protective shell, an imaging mechanism and a locking mechanism, the locking mechanism comprises an explosion-proof protection plate, the bottom of the explosion-proof protection plate is clamped with the protective shell, the top of the explosion-proof protection plate is provided with an upper clamping groove, and the inside of the protective shell is slidably connected with a snake bone hose. The present application prolongs the overall length through the symmetrically arranged protective frame, presents an infinite extension tunnel vision, forms a visual distance difference between the image and the tunnel space behind the image, presents a visual effect of floating image display, and the transparent OLED display screen used by the protective shell is a transparent screen, so that the real space behind the screen can be seen through the image on the screen, the effect of floating image display can be further strengthened, the shadow part of the protective frame shields the display screen, and sunlight is prevented from being irradiated on the display screen.

The present invention discloses a method for controlling lighting in a tunnel diversion area, comprising: obtaining a relationship model for changes in visual distance and brightness value relative to brightness ratio generated based on multiple visual recognition samples, where each visual recognition sample includes at least two of the following: a minimum visual distance for an observer observing a target in a low-brightness lighting section from a high-brightness lighting section, a first brightness value for the low-brightness lighting section, a second brightness value for the high-brightness lighting section, and a brightness ratio of the second brightness value relative to the first brightness value; obtaining a safe visual distance for the tunnel, a first brightness value for the low-brightness lighting section, or a second brightness value for the high-brightness lighting section; determining, based on the safe visual distance and the first or second brightness value of the tunnel, a maximum brightness ratio that satisfies the safe visual distance at the first or second brightness value using the relationship model; and selectively setting a transition lighting section between the high-brightness lighting section and the low-brightness lighting section of the tunnel based on the maximum brightness ratio. The method of the present invention can improve the safety of tunnel diversion areas.

The invention relates to the technical field of robots, and discloses an automatic pipeline inclination measuring robot which comprises an upper shell and a lower shell which are fixed to the two sides of a mounting plate correspondingly, a first motor is fixedly mounted on the lower surface of the mounting plate, and a driving wheel is fixed to the output end of the first motor; a first driven wheel and a second driven wheel are sequentially meshed with the side face of the driving wheel, a driving chain wheel is fixed to the lower surface of the second driven wheel through a connecting rod and arranged on the upper surface of a mounting plate, a chain is arranged on the upper surface of the mounting plate, and the driving chain wheel is matched with the chain. According to the invention, the full-automatic and high-precision positioning and movement of the inclinometer robot in the pipeline are realized, and the traditional operation mode of depending on manual traction of a signal line and visual distance marking is replaced, so that operators are liberated from tedious and repeated labor; and random errors such as uneven tension, inaccurate pause position and inconsistent reading intervals caused by human factors can be eliminated.

The application discloses a multi-source sensing-based anti-collision early warning system for power distribution network construction machinery, and relates to the technical field of image analysis, which comprises the following steps: obtaining laser radar point cloud data and camera image data, obtaining laser radar distance and visual distance respectively, and performing consistency determination; when there is inconsistency, determining the reference sensor and the sensor to be adjusted by analyzing the visual recognition influence value and the radar response influence value, performing dynamic parameter adjustment on the sensor to be adjusted, obtaining the target distance based on the re-measured distance value and the reference measured distance fusion, thereby constructing a dynamic envelope volume, calculating the net safety distance, and outputting an anti-collision early warning signal, which effectively solves the problem that multi-source sensing data deviates and is inconsistent under complex environmental interference in the prior art, resulting in a decrease in distance detection reliability and affecting anti-collision early warning precision.

A method and system for locating defects in cable-stayed bridges based on image recognition is disclosed, relating to general image data processing or generation. In this method, the spiral features of the cable-stayed bridge in consecutive video frames are extracted, and a sequence of equally spaced virtual nodes is generated by combining these features with a reference pixel spacing. The cumulative pixel displacement of the current frame is obtained by matching the translation differences between virtual nodes in adjacent frames. When a defect is identified, the intra-frame pixel offset of the defect relative to the first virtual node is calculated. Finally, the cumulative displacement and the intra-frame offset are added to obtain the total pixel coordinates of the defect, and calibration parameters are used to convert them into absolute positioning coordinates in physical space. This application aims to suppress missed and false detections during image feature extraction, reduce accumulated errors in visual distance calculation, and thus improve the accuracy of locating cable-stayed bridge defects in physical space.

The invention discloses a visualization method, device and equipment for monitoring data in a machining process and a medium, and relates to the technical field of precision manufacturing, and the method comprises the following steps: obtaining coordinate data of a cutter and machining monitoring data in a workpiece cutting process; performing data fusion of the coordinate data and the processing monitoring data based on real-time stream processing and real-time linear interpolation of historical data to obtain fused data; constructing a three-dimensional scene of the workpiece cutting process based on a finite element network, and putting the fusion data into the three-dimensional scene; and according to the three-dimensional scene, the fusion data in the view cone is rendered, and the rendering depth is determined according to the fusion data and the visual distance of the user. According to the method, the physical state of the cutter in the cutting process can be reproduced in real time, omnibearing visualization of the machining process in the three-dimensional angle and the stress aspect is achieved, then the real-time visualization monitoring effect of the numerical control machine tool machining process is achieved, and networking and informatization development of the numerical control technology is promoted.

The invention discloses a dispersive attention body assembly and a use method thereof, and relates to the field of optical devices, the dispersive attention body assembly comprises a dispersive body made of a transparent material, the dispersive body is provided with a first light inlet and a first light outlet, the first light inlet is used for incident light to enter the dispersive body, and the first light outlet is used for incident light to enter the dispersive body; the outer surface of the dispersion body is coated with reflective coating layers except the first light inlet and the first light outlet; the attention body is made of a transparent material, and a second light inlet and a second light outlet are formed in the attention body; according to the invention, the dispersion body and the attention body are arranged, so that dispersion, spectrum temporary storage, multi-path modulation and directional emission of incident light can be efficiently realized, the visual attraction and color richness of the emergent light are remarkably enhanced, and an observer can obtain a stable and clear center positioning reference and visual and accurate visual distance feedback; the problem that in the prior art, vision guiding, positioning and distance measuring functions are difficult to consider in a limited space is effectively solved.

The present invention discloses a phishing website detection method, system, device, and medium, relating to the field of computer network security. The method comprises: based on a pre-stored whitelist of websites, measuring and weighting the character positions and similarities of the target website's uniform resource locator string, obtaining a position similarity weight and a visual similarity weight for each character; based on a pre-stored whitelist of websites, classifying and weighting the string operations of the target website's uniform resource locator, obtaining an operation similarity weight; converting the uniform resource locators of the whitelist and target websites into binary images, obtaining a whitelist binary image and a target binary image, and converting the binary images into one-dimensional vectors; calculating the visual distance between the two vectors; and determining whether the target website is a phishing website based on the weight and the visual distance. The present invention can detect phishing websites in real time, accurately, and stably.

The application relates to the technical field of substation operation, and discloses a substation visual distance measurement method, system, device and medium, the method constructs a real-time dense point cloud model of each sampling point through a multi-view image sequence of a target monitoring area at continuous sampling points, so that the real-time and authenticity of the dense point cloud model are ensured, dynamic target segmentation is carried out on scene point clouds of the real-time dense point cloud model, point cloud clusters of dynamic targets can be accurately extracted from a complex substation background, the continuous three-dimensional motion trajectory of the dynamic target is obtained through cross-frame association and state estimation of the dynamic target, the robustness of target identification and tracking is significantly improved, distance measurement target tracking loss or drift is avoided, and the spatial distance between the dynamic target and a preset distance measurement observation point is solved in real time by using the three-dimensional motion trajectory of the dynamic target, so that the distance measurement precision is improved, and the false detection rate and the safety distance misjudgment rate are reduced.

The invention discloses a target detection tracking method based on vision and intelligent identification, and the method specifically comprises the following steps: S1, installing a high-definition near-infrared camera on a sailing ship, and carrying out the real-time collection of surrounding video images, and obtaining the video image data; s2, preprocessing the acquired video image data, and processing the video image data frame by frame; s3, performing target detection and recognition on the preprocessed video image data based on a deep learning algorithm to obtain a target recognition result; and S4, according to a target identification result, carrying out courtship calculation on the detection target according to the confidence coefficient, marking the detection tracking target according to a calculation result, and pushing and displaying a detection tracking result. The high-definition near-infrared camera is adopted for video image acquisition, information acquisition in daytime and night environments is supported, the visual distance is far beyond the visual range of human eyes, the input information amount is greatly increased, and sailing personnel can conveniently take relevant measures in time according to emergencies.

The invention relates to test equipment for testing the display degree of a test sample with an adjustable visual field distance. The test equipment comprises a darkroom experiment cavity defined by a box body and a cover body, a light source, a sample mounting module and an illuminometer are arranged in the box body; an observation assembly for observing the display degree of the to-be-detected sample is rotationally arranged on the box body; a short-distance test mode and a long-distance test mode are arranged in the box body; an adjusting module for adjusting the visual field distance between the sample mounting module and the observation assembly is also arranged in the box body; the test equipment is ingenious in design, provides a short-distance test mode and a long-distance test mode, can meet the requirements of different test standards and test distances, and improves the flexibility and the application range of the test equipment. The visual field distance between the sample installation module and the observation assembly is adjusted through the adjusting module, and the observation conditions of people for the emergency lighting lamp at different distances in actual use can be simulated more truly.

The invention relates to an infrared image parallel defogging method based on a GPU, and the method comprises the steps: S1, constructing a dark channel fog light image with an infrared image as an input, estimating the transmittance of a scene, and obtaining a GPU transmittance image; s2, taking the infrared image as a guide image, performing guide filtering optimization on the GPU transmissivity image, and outputting a GPU refined transmissivity image; s3, the GPU refinement transmissivity image passes through an atmospheric scattering model to obtain a preliminary defogging image; s4, adjusting a contrast limit parameter according to the estimated scene transmissivity, and enhancing the preliminary defogged image by using a contrast limit adaptive histogram equalization method to obtain an infrared enhanced image; and S5, designing a kernel function by using a GPU parallel language, and executing the processing processes of the steps S1 to S4. According to the method, the real-time requirement of infrared video processing can be met, and meanwhile, the resolution and the visual distance of an infrared image can be improved.

The application relates to a highway suitability evaluation method for an automatic driving vehicle team, and belongs to the field of road traffic control. The method obtains basic information of an evaluation highway section, traffic flow information, automatic driving vehicle team information and automatic driving and traditional manual driving interactive vehicle information as input information, adopts a virtual test method, calculates the available visual distance of the automatic driving vehicle team and the interactive vehicle under the obtained traffic flow and the automatic driving vehicle team formation scheme, constructs a visual distance safety failure function function of the automatic driving vehicle team and the interactive vehicle according to a demand visual distance model and a structure reliability theory, calculates a visual distance safety failure probability, and finally determines the highway section suitability evaluation result for the automatic driving vehicle team according to the visual distance safety allowable failure probability of different levels. The application can efficiently and safely quantitatively evaluate the suitability of the automatic driving vehicle team on the evaluation highway section, and identify dangerous sections with insufficient visual distance of the automatic driving vehicle team.

Disclosed are an apparatus and method for learning temporal distance-aware representations and method, and the apparatus includes: an initialization unit configured to initialize a buffer where a goal-conditioned policy, an exploration policy, visual distance-aware representation, and experience data for learning are stored; a learning execution unit configured to set a goal based on a Temporal Distance-aware Representations (TLDR) reward in a current episode, and determine a new state and action data through execution of the goal-conditioned policy and the exploration policy to reach the goal; a policy learning unit configured to learn the goal-conditioned policy based on experience of reaching the goal, and learn the exploration policy based on a visual distance to the goal; and a visual distance-aware representations learning unit configured to learn the visual distance-aware representations by encoding a visual distance between the states based on constraints.

The invention discloses a detection device. A reference sighting mark chart and a reference vision value conversion ruler are made by setting a reference sighting mark with a fixed size. A plurality of reference vision values and visual distance values can be measured at the same time by using the reference sighting mark chart and the reference vision value conversion ruler. The reference vision value is a universal five-minute vision value; the visual distant vision value is a direct recorded value of the length value of the distant vision. By applying the detection device, two types of visual values with sufficient quantity can be provided at the same time, the precision and intuition of the visual distance ability detection value are improved, and the higher requirements of visual examination of children and adolescents on the visual measurement range and the recognition of tiny visual change are fully met.

The application particularly relates to a kind of near distance multi-target fast deformation monitoring methods based on small aperture MIMO radar, high azimuth resolution two-dimensional imaging of multiple azimuth adjacent targets is realized by discrete fourier transform combined with MUSIC algorithm, and accurate positioning of multi-target is completed;Secondly, the mutual interference between target side lobe is suppressed using APES filter, and based on the target distance and azimuth information obtained in the previous step, the accurate recovery of target phase is realized;Finally, the time difference interference method is used to accurately estimate the small deformation of target visual distance.The space smoothing (FBSS) idea is introduced into the two-dimensional imaging algorithm, which effectively suppresses the coherent signal interference and realizes high azimuth resolution two-dimensional imaging in complex deformation monitoring scene.

The invention relates to the technical field of navigation mark guidance of ship navigation, and particularly discloses an intelligent navigation mark guidance system based on marine ship navigation, which comprises a navigation mark attenuation analysis module, a ship risk calculation module, a collision risk extraction module and a ship navigation early warning module, by fusing data of a navigation mark body state sensor and an environment sensor, a photoelectric output attenuation model of a battery under a low-temperature working condition is established, and an effective visual distance attenuation factor of light intensity is accurately calculated, so that dynamic quantitative evaluation of actual luminous efficiency of the navigation mark is realized, the reliability and timeliness of navigation mark information are fundamentally improved, and the application prospect is wide. And the effective guiding range of the navigation mark under the current weather and sea condition can be truly reflected. By analyzing the trajectory deviation degree of a ship in a risk area, abnormal navigation behaviors are identified, and collision risk prefactors are extracted, so that early identification and quantitative evaluation of risks are realized.

The invention relates to an underwater binocular vision distance estimation method based on key point matching and a multi-layer perceptron, which comprises the following steps: acquiring video data of a target by using a binocular camera, acquiring key point matching pairs in a target area in left and right images, and forming input features and label pairs by using parallax features of the key point matching pairs and corresponding actual distances; performing feature extraction and fusion by using a multi-layer perceptron model, and outputting a prediction distance; performing training optimization on the multi-layer perceptron model by taking the parallax feature as input and taking the actual distance as a label; and carrying out actual distance test by utilizing the optimized model. According to the embodiment, the multi-layer perceptron model is used for distance measurement, errors in feature point extraction and matching can be processed, and higher robustness is achieved; dependence on high-precision camera calibration and an imaging model is avoided, and the system deployment cost is reduced; the method is simple in model training, high in reasoning speed and suitable for a low-power-consumption underwater platform.

The application designs a highway video monitoring visual distance determination method under scene prior constraint, and belongs to the field of image processing.The method realizes automatic learning of highway structured scene information, and calibrates a camera depth scale based on road prior and vehicle model prior, constructs a visual distance calculation model based on three criteria of imaging area historical background information and current visible edge contrast, farthest target recognition vehicle position and historical background information correction transmissivity graph, and calculates real-time visual distance of the camera on the current erected road.The visual distance estimation method based on ordinary monocular monitoring camera can be widely applied to the monitoring cameras erected on various road sections of the highway, and can roughly determine the visual distance of the current road section without professional equipment and without knowing other detailed data of the camera, thereby helping to realize intelligent transportation.

The application discloses a live-line state sensing and early warning system applied to a power transmission line of an unmanned plane, comprising a multistage live-line state identification module, a single-chip microcomputer control system, a DC-DC module, a visual distance-exceeding prompting module and an unmanned plane operation platform; the multistage live-line state identification module, the single-chip microcomputer control system, the DC-DC module and the visual distance-exceeding prompting module are all integrally packaged on the unmanned plane operation platform.The application has the beneficial effects that: through the cooperative work of the multistage live-line state identification module and the single-chip microcomputer control system and the setting of multistage voltage thresholds, three states of no electricity, induced live line and power frequency live line can be clearly distinguished, thus accurate decision basis is provided for operation and maintenance personnel, safety accidents or unnecessary power cut caused by misjudgment are avoided, and the reliability and safety of detection are remarkably improved.

The present application relates to the field of ophthalmology, biomedical engineering and health information technology, and particularly relates to a myopia dynamic prediction and intervention evaluation method and system fusing physiological parameters and behavior visual distance, an electronic device and a storage medium, comprising collecting age, refractive state and eye use time distribution of a target individual at multiple preset visual distance levels; calling a preset age-myopia progression group benchmark model to obtain an annual progress reference value corresponding to the age; calling a preset visual distance-adjustment lag relative risk coefficient model to calculate an individual comprehensive adjustment lag load coefficient K based on the eye use time distribution; predicting the natural development trajectory of the individual based on the annual progress reference value and the comprehensive adjustment lag load coefficient K; simulating at least two intervention scenarios to generate comparative development trajectories; and outputting a comparison report containing the natural development trajectory and at least one post-intervention trajectory. The present application realizes accurate quantitative prediction of myopia risk.

The present application relates to model management, in particular to a three-dimensional model management method and system based on unmanned aerial vehicle and grid technology, model modeling: the latitude and longitude range is calculated by extracting the Exif information of the photo, and grouping is carried out according to the grid code, the oblique photography modeling is completed, the model is cut according to the grid boundary line, and the model and model auxiliary information are stored; model updating: the grid of the area needing to be updated is selected, the corresponding route is generated, the unmanned aerial vehicle multi-angle aerial photo is taken, the model is modeled, and the model and model auxiliary information of the grid of the area needing to be updated are stored and updated; model rendering: the underlying nodes are constructed and the adjacent grids are merged to form the bounding volume, the grid boundary line is converted into the node content, the model data is taken as the sub-node and the visual distance precision is configured, the rendering load is optimized through hierarchical merging and LOD simplification; the present application can overcome the defects that it is difficult to divide the unmanned aerial vehicle aerial survey model into spatial structure, automatically update and maintain and efficiently render and display.