21 results about "Visual discrimination" patented technology

The invention discloses a light source color preference degree evaluation method and device, equipment and a storage medium, and relates to the technical field of light source quality testing. The method comprises the following steps: acquiring a color temperature parameter of a test light source and spectral power distribution in a preset wavelength range, acquiring an associated reference light source based on the color temperature parameter, and calculating reference spectral power distribution; a color quality index is then calculated based on the plurality of test color samples according to the color temperature parameter, the spectral power distribution, and the reference spectral power distribution. Calculating a color gamut space area formed by the test color sample under the test light source according to the spectral power distribution, calculating a color resolution index according to the color gamut space area, and finally calculating a color preference index of the test light source according to the color quality index and the color resolution index. Therefore, the color preference index is calculated according to the color temperature parameter and the reference light source, the calculation process is associated with visual feelings such as visual discrimination, and a basis is provided for accurate evaluation or comparison of the color development quality of different color temperature test light sources through quantitative calculation of the color preference.

The application relates to the field of gated dynamic protection. A non-bird touch gating dynamic protection method based on temperature difference and displacement double threshold fusion comprises the following steps: acquiring real-time monitoring data of a gating area, wherein the real-time monitoring data comprises a temperature difference characteristic parameter, a displacement characteristic parameter, an infrared shielding parameter and a visual image parameter; acquiring a temperature difference discrimination value according to the temperature difference characteristic parameter; acquiring a displacement discrimination value according to the displacement characteristic parameter; acquiring an infrared discrimination value according to the infrared shielding parameter; acquiring a visual discrimination value according to the visual image parameter; acquiring a comprehensive discrimination index according to the temperature difference discrimination value, the displacement discrimination value, the infrared discrimination value and the visual discrimination value; and judging whether the comprehensive discrimination index exceeds a preset double threshold decision interval. Through the cooperative analysis of multi-dimensional data such as temperature difference, displacement, infrared shielding and visual image, the application effectively distinguishes biological and non-biological contact and improves the detection accuracy in a complex scene.

The invention provides a method for identifying a visual area of an optical transparent protective material by adopting visual information C. The method comprises the following steps: filling a C-shaped annular character with an asymptotic complementary color of a light color system, and fusing visual resolution into measurement of the visual area of the transparent protective material. Compared with the existing method for testing the visible area of the optical transparent material, the method has the advantages that the grading of the damage condition of the transparent protective material is realized, and the scientific measurement of the residual service area after the optical transparent protective material is damaged is also realized. According to the method, the damage condition of the optical transparent protective material with the abraded surface can be graded, and compared with an existing detection method, the method does not need to use complex and expensive high-precision graph acquisition equipment, does not need to carry out graph segmentation on an acquired area, and is convenient to operate. The testing method is simple and efficient, the service capacity of the transparent protective material can be quantitatively analyzed, and a new scheme is provided for evaluating the damaged area of the transparent protective material.

The present application relates to the field of engineering detection technology, more specifically to a kind of anchor rod support quality detection method based on visual discrimination.Based on the mobile platform of multiple-view color camera and depth camera, the image and pose data of anchor rod area are collected, after image preprocessing, the instance segmentation network with multi-modal feature fusion is used to realize anchor rod segmentation and three-dimensional positioning;Relying on point cloud extraction, the surface parameters such as anchor rod shape, arrangement and tray are extracted, and the deformation of tray and surrounding rock is obtained by sub-pixel DIC technology;Through simulation and test calibration of deformation pre-tightening force model, the anchor rod pre-tightening force is inversed and the parameters are corrected;Relying on the analytic hierarchy process, a multi-dimensional evaluation model is established to complete quality classification, and finally three-dimensional modeling is used to mark defective anchor rod and output detection report.The present application is non-contact and non-destructive testing, with high degree of automation, solving the problems of traditional anchor rod detection sampling damage and large artificial determination error, and can be used for batch quality detection of roadway and tunnel anchor rod support.

The invention provides application of Alda-1 in preparation of a preparation for improving a cognitive function, and belongs to the technical field of biological medicines. According to the method, the improvement effect of Alda-1 on cognitive competence is evaluated from the perspectives of working memory, suppression control, visual discrimination and the like, and results show that Alda-1 can improve the working memory ability, the suppression control ability and the visual discrimination ability. Therefore, the invention provides a safe and effective solution for developing new application of the Alda-1 medicine, guaranteeing the visual cognition ability of special occupational people and treating early neurological and mental diseases accompanied by visual cognition impairment.

The invention discloses a modular intelligent analysis method for the suspension state of a contact network, and relates to the technical field of intelligent operation and maintenance of rail transit. The method comprises the following steps: firstly, carrying out quality preliminary screening on an original image sequence through an image pre-screening module based on illuminance, ambiguity and coverage indexes; and then, the key component accurate positioning module performs high-precision analysis on the effective image by using a customized two-stage cascade deep learning network, and outputs structural data such as component types, bounding boxes, center lines and scale factors. And the multi-modal state discrimination module fuses a visual discrimination result based on a support vector machine and non-visual sensing data corrected by a physical model, and carries out comprehensive determination according to line section type dynamic weighting. According to the method, the problems of poor reliability and insufficient adaptability caused by out-of-control data quality, coarseness of feature extraction and lack of physical modeling in fusion in the prior art are solved, and intelligent analysis of the contact network state with high robustness and high accuracy is realized.

The invention discloses a method for ratio type colorimetric detection of perchlorate. The method comprises the following steps: performing specific surface modification on gold nanoparticles, constructing a methylene blue functionalized gold nanoparticle (MB (at) AuNPs) colorimetric probe, inducing a particle aggregation effect by utilizing specific interaction between perchlorate and MB (at) AuNPs, triggering red shift of a localized surface plasma resonance absorption peak of the probe, and detecting the concentration of the MB (at) AuNPs. And a 523 nm (dispersed state characteristic peak) and 660 nm (aggregation state characteristic peak) dual-wavelength absorption signal is formed. Ratio-type quantitative analysis is realized by calculating the ratio (A660 / A523) of the absorbance of the two wavelengths, and the defect that single-signal detection is easily influenced by environmental fluctuation and system condition change is effectively avoided. Based on the response characteristics, a dual quantitative relation between the ratio of the concentration of the perchlorate to the absorbance and the ratio of the color intensity of an image collected by the smart phone is further established, and an ultraviolet-visible spectrophotometry-smart phone image analysis dual-mode detection system is constructed. Wherein the detection limit of the spectrum detection mode is 2.77 [mu] M, and the detection limit of the smart phone auxiliary detection mode is 5.63 [mu] M. The method is simple and convenient to operate, does not need a large-scale analytical instrument or complex sample pretreatment, has the advantages of good sensitivity, stability and visual discrimination, can quickly realize on-site screening and accurate quantification of perchlorate in water and food samples, and is high in practicability and wide in popularization prospect.

The invention discloses a respirator oscillogram recognition auxiliary tool and a use method thereof, and relates to the technical field of respirator man-machine asynchronous recognition, and the tool comprises a box body, a shear fork telescopic frame assembly, a push plate and a recognition marker post; one side of the box body is provided with two windows, and one side of the width direction of the box body is provided with a slideway corresponding to each window; each shear fork telescopic frame group is mounted in the corresponding slide way; a spacing mark post is hinged to each intersection point on each scissor-fork telescopic frame assembly, each spacing mark post is parallel to the width direction of the corresponding slide way, the two ends of each spacing mark post are slidably connected with the corresponding slide way, and the spacing mark posts on the two scissor-fork telescopic frame assemblies are in one-to-one correspondence up and down; the two shear fork telescopic frame assemblies are connected with the push plate; the identification marker post stretches across the box body and slides along the box body. The method does not depend on computer program analysis, and can assist critical medical staff in quickly recognizing the abnormal type of the human-machine asynchronism of the respirator in a visual discrimination mode.

The invention discloses an X-Ray detection image data management system and method for a ceramic wine bottle, and relates to the technical field of image processing, and the management method comprises the following steps: collecting initial image data of the ceramic wine bottle, and carrying out the preprocessing of the initial image data to generate a standardized image; summarizing the standardized images to generate a detection log; performing defect area acquisition on each standardized image in any detection log, and determining a defect type in any defect area; extracting a shooting angle corresponding to X-Ray of any standardized image, generating a matching parameter showing a defect condition, and obtaining an optimal shooting angle of any defect type in different defect areas; when defect detection is carried out on the ceramic wine bottle in real time, an X-Ray shooting path is obtained; setting an optimal shooting angle for X-Ray, analyzing an actual defect condition presented by the optimal shooting angle, and performing abnormality judgment on a defect identification condition; manual visual judgment links are reduced, and subjective errors are avoided.

The invention relates to an agricultural greenhouse remote sensing monitoring method and device based on PIE-Engine, and electronic equipment. The method comprises the steps of classification sample point selection, remote sensing image preprocessing, optimal index set construction, classification feature selection, SNIC-based image segmentation and classification algorithm, agricultural greenhouse automatic extraction, agricultural greenhouse recognition precision judgment and extraction result output. According to the invention, long-time, large-range and high-precision agricultural greenhouse information automatic identification and extraction based on cloud computing are realized, so that agricultural greenhouse remote sensing monitoring is more efficient and real-time, and the classification effect is judged through precision evaluation. In the process, an optimal feature set of spectral features, vegetation indexes and texture features is constructed, and meanwhile time sequence NDVI data is combined. An object-oriented combined random forest (RF) algorithm is adopted to construct a classification model for agricultural greenhouse classification and identification in a research area. A classification result of the model is evaluated through a precision evaluation and visual discrimination method.

The invention relates to the field of gating dynamic protection. A non-bird false touch gating dynamic protection method based on temperature difference and displacement double threshold fusion comprises the steps that real-time monitoring data of a gating area are acquired, and the real-time monitoring data comprise temperature difference characteristic parameters, displacement characteristic parameters, infrared shielding parameters and visual image parameters; obtaining a temperature difference discriminant value according to the temperature difference characteristic parameters; acquiring a displacement discriminant value according to the displacement characteristic parameter; obtaining an infrared discrimination value according to the infrared shielding parameter; obtaining a visual discrimination value according to the visual image parameter; obtaining a comprehensive discrimination index according to the temperature difference discrimination value, the displacement discrimination value, the infrared discrimination value and the visual discrimination value; and judging whether the comprehensive judgment index exceeds a preset dual-threshold decision interval or not. According to the method, through collaborative analysis of multi-dimensional data such as temperature difference, displacement, infrared shielding and visual images, biological contact and non-biological contact are effectively distinguished, and the detection accuracy in a complex scene is improved.

The invention provides an indicator light control method and system for self-service consignment equipment, a medium and a product. According to the method, a control processing unit firstly obtains the current service operation state of the self-service consignment equipment, collects a static image frame of the environment where the equipment is located, obtains a foreground shielding area through area recognition, and determines other areas as environment reference areas. Then, the control processing unit calculates a gray statistical value of the environment reference area, calculates a minimum visual identification brightness value meeting the human eye visual identification requirement based on the gray statistical value, and converts the minimum visual identification brightness value into a target duty ratio; and finally, the control processing unit generates a first pulse width modulation driving signal or a second pulse width modulation driving signal according to different service operation states, so that the indicating lamp emits light according to the corresponding driving signal. The method relieves the technical problem that the indicating lamp is difficult to adapt to a complex and changeable illumination environment, and realizes adaptive adjustment of the brightness of the indicating lamp along with the environment illumination intensity.

A method for rapidly assessing cerebral visual function based on electroencephalogram (EEG) and fast periodic visual stimulation oddball paradigm includes: presenting several sets of visual stimuli images to a target individual and collecting EEG signals of the target individual while presenting the visual stimuli images, detecting a first and a second signal amplitude of the EEG signals, comparing the first signal amplitude with a third signal amplitude of a healthy individual in a database to determine a visual processing ability score of the target individual, and comparing the second signal amplitude with a fourth signal amplitude of the healthy individual in the database to determine a visual discrimination ability score of the target individual.

The present application belongs to the field of geotechnical engineering earthquake liquefaction discrimination, and relates to a three-dimensional site liquefaction discrimination method based on SPT, comprising: obtaining site seismic parameters; obtaining geological soil layer conditions; establishing a three-dimensional site grid model; conducting field standard penetration tests on typical soil types; generating a three-dimensional site measured average standard penetration field; generating a three-dimensional site critical standard penetration field; generating a three-dimensional site anti-liquefaction safety factor field; and discriminating the three-dimensional site liquefaction possibility. The present application ensures data reliability and reduces detection cost through twice correction of overlying effective stress; realizes dynamic coupling analysis of stress state and standard penetration value through stress coupling correction technology, and improves discrimination accuracy; represents spatial distribution characteristics and physical properties of soil layers through establishment of a three-dimensional site grid model; and can overall and intuitively evaluate site liquefaction through a three-dimensional visual discrimination system.

The utility model provides CVD (Chemical Vapor Deposition) equipment and semiconductor equipment. According to the heating device in the CVD equipment, a temperature sensing structure is arranged on the outer surface of a heating belt, and the temperature sensing structure comprises thermosensitive pigment. As the temperature-sensitive pigment changes in color along with the change of temperature, the temperature sensing structure can present different colors and has an obvious visual distinguishing effect when the heating tape is at different temperatures, so that the temperature of the heating tape can be visually monitored, the temperature loss condition of the heating tape can be found in time, and the heating tape is convenient to use. The normal process effect of the CVD equipment or other semiconductor equipment is effectively prevented from being affected due to the fact that the temperature loss of the heating tape is not found in time. Therefore, the temperature sensing structure not only can improve the monitoring efficiency of the temperature of the heating tape, but also is low in preparation cost of the thermosensitive pigment and high in feasibility.

The invention discloses a visual bamboo mildew detection method and system based on hyperspectral characteristic wavelengths, and the method comprises the steps: obtaining hyperspectral image data of bamboos with different mildew degrees; preprocessing the acquired hyperspectral image data; marking a region of interest for the preprocessed hyperspectral image data, and obtaining average spectral data of the region of interest; screening the average spectrum data, and dividing the average spectrum data corresponding to the screened characteristic wavelength into a verification set and a training set according to a preset proportion; training a support vector machine by using the training set, and constructing an SVM discrimination model; verifying the SVM discrimination model by using the verification set to obtain a final SVM discrimination model; and discriminating the bamboo hyperspectral image by using the final SVM discriminating model to obtain a visual discriminating result for representing different mildew degrees by using different colors. The method can effectively solve the problems that the bamboo is not easy to detect in the early stage of mildew, and the detection result is not visual to display.

This invention provides a multi-source data respiratory state discrimination device and electronic device. The device includes: a sample feature extraction module for determining audio sample features and visual sample features of a target user under different respiratory states; a first comparison module for comparing the currently acquired first audio signal and audio sample features of the target user to obtain an audio confidence score; a second comparison module for comparing the currently acquired first visual signal and visual sample features of the target user to obtain a visual discrimination result; a determination module for obtaining a preliminary recognition result based on the visual discrimination result; and using the audio confidence score to assist in verifying the preliminary recognition result to obtain a target recognition result. This device and electronic device can improve the accuracy of respiratory state discrimination in respiratory training application scenarios.

The application provides a visual encoder training method and a face forgery detection and explanation method. The training method comprises the following steps: obtaining a face image, a corresponding authenticity label and an explanation text, and sequentially obtaining an image feature sequence by dividing the face image into blocks; initializing a learnable prompt vector for classification, general forgery and explanation perception, and splicing the image feature sequence into a composite input sequence; inputting the composite input sequence into a visual encoder to extract classification features, general pattern features and explanation features; using a frozen text encoder to extract semantic embeddings corresponding to the authenticity label and the explanation text; constructing a comprehensive loss function, updating the learnable prompt vector based on the comprehensive loss function, and obtaining a trained visual encoder. The application breaks the modal gap between the bottom-level visual discrimination features and the high-level language reasoning, and realizes the pre-alignment of the explanation semantics in the early stage of visual feature extraction.

The disclosure relates to methods and systems related to spatial encoding / decoding of features. The provided orthogonal cleavage ligation sequencing (OCLS) system encodes two or more orthogonal recognition sites for a restriction enzyme, such as an IIS-type enzyme, to decode a visual barcode. The decoding employs specific orthogonal ligation of differentially tagged probes, which enables visual discrimination of barcodes at each feature. The process can be cyclically repeated and carried out in parallel.

The invention relates to the technical field of image feature extraction and matching, in particular to an elevator fault accident recognition method and system based on image recognition, and the method comprises the following steps: collecting an elevator image positioning slide rail structure area, extracting an edge line to generate a closed graph, analyzing a door body texture extension mode, calibrating a chain driving area, and tracking a texture moving direction. Door body boundary structure changes are compared, and finally an elevator fault feature matching image recognition result is output. According to the invention, by establishing a linkage mechanism of image boundary extraction, texture direction analysis and trajectory tracking, spatial correlation analysis among a slide rail, a door body and a chain structure is realized, the image recognition precision of door body tiny deformation and chain motion abnormity is enhanced, and potential fault features are extracted based on difference comparison and density comparison. The structure change tracking capability and the time sequence integrity of image expression are improved, the visual judgment capability of complex structure abnormity is enhanced, and the application of image recognition in elevator operation monitoring is expanded.

Visual effects presented in at least an ultra-far peripheral horizontal static field of the eyes of a user improve or enhance brain function, homeostasis and performance. The visual effects are non-contextual with respect to content appearing in a central field of vision, and do not constitute a cursor, a user input field or other user interface element. The ultra-far peripheral horizontal static field extends rearwardly from a fovea centralis of the eye in a straight ahead static gaze direction to 100 degrees or more rearwardly from the fovea centralis. Such can be used to treat or improve: traumatic brain injury; acuity, focus, visual convergence, visual sustainability, visual processing, visual field, retinal health, brain field health, visual discrimination, visual spatial memory, ocular motility, pursuits and saccades, hold fixation, convergence / divergence, eye alignment, depth perception, Phorias, occipital cortex, blink rate, pain, migraine headaches, and / or balance of the user or human subject.