23 results about "Active infrared" patented technology

The invention discloses an active infrared thermal imaging thermal diffusion parameter inversion method and system based on a physical information neural network, and belongs to the technical field of infrared thermal imaging nondestructive testing and thermophysical parameter identification. In order to solve the problems that an active infrared thermal imaging method is difficult to steadily invert spatial distribution thermal diffusion parameters under the condition of only single-side surface temperature measurement and is sensitive to measurement noise, the method comprises the following steps: collecting surface space-time temperature field data of a tested piece under thermal excitation, and calculating a relative temperature field; normalizing the space-time coordinates, and constructing a multi-output physical information neural network; the equivalent surface heat conduction equation and the boundary and initial conditions thereof serve as a loss function of a physical constraint embedded neural network, and a Huber loss function is adopted to calculate a data fitting item; a neural network is optimized through joint training, a global volume thermal diffusion coefficient, a global equivalent thermal loss coefficient, a relative thermal diffusion coefficient field and a relative thermal loss coefficient field of spatial distribution are synchronously inverted, and a high signal-to-noise ratio temperature field is reconstructed. The method is used for material surface nondestructive testing.

This application relates to the field of tunnel construction safety monitoring technology, and discloses an intelligent identification method for water seepage risk at the tunnel face in water-rich clay layers. This method controls an active infrared excitation module to project radiation in an oblique incidence manner, uses polarization imaging to acquire sequences and calculates Stokes vectors; calculates the degree of linear polarization based on the Stokes vectors and performs threshold segmentation to generate a water film distribution mask; uses the Stokes vectors to construct a polarization angle field reflecting local normal changes as texture features, solves the optical flow constraint equation to obtain the instantaneous velocity field; performs frequency domain transformation on the velocity field, extracts the proportion of low-frequency creep energy through power spectral density analysis, and determines the soil rheological softening factor; finally, combines the water film distribution, rheological softening factor, and instantaneous velocity field to construct a mudslide risk index. This invention utilizes polarization texture reconstruction to solve the problem of weak texture tracking and eliminates elastic vibration interference through frequency domain energy decoupling, effectively improving the accuracy of mudslide risk identification.

The invention discloses a methane telemetering imaging system and method based on an active infrared absorption spectrum and a fast reflector, and the system comprises a main control module, a laser driver, a laser, a detector, an off-axis parabolic reflector, a voice coil fast reflector, and a distance measurement module. The laser driver controls the laser device to emit modulated laser, the voice coil fast reflecting mirror controls the angle of emergent laser, the semiconductor photoelectric detector receives an echo optical signal, converts the echo optical signal into an electric signal and sends the electric signal to the main control module, and the main control module further completes signal analog-to-digital conversion through an analog-to-digital converter. And a digital lock-in amplifier is used to demodulate the signal to respectively obtain a first harmonic and a second harmonic. The method has the advantages of high imaging speed, high spatial resolution, high detection sensitivity and the like.

The application discloses a nondestructive testing method for cable diseases of a cable-stayed bridge based on an image sensor and particularly relates to the technical field of cable disease detection. The application realizes the technical leap from the superficial surface observation to the deep internal flaw detection by comprehensively detecting through the appearance screening and the active infrared thermal excitation technology path, firstly accurately positioning the surface cracking and the rust area, then performing the fixed-point hovering and the active heating on each defect, quantifying the temperature rise, the peak temperature and the cooling coefficient by analyzing the unique thermal response, accurately judging the internal extension degree and the damage depth of the defect, solving the problems of the missed detection and the misjudgment of the traditional method, providing the reliable data support for the disease evaluation, and realizing the technical leap from the superficial surface observation to the deep internal flaw detection.

The invention discloses a heat map sequence downsampling reconstruction method based on tensor space constraint, and relates to the field of photo-thermal science and detection and signal processing. The invention aims to solve the problem that an active infrared thermal wave imaging detection technology cannot meet the requirements of high temporal-spatial resolution, low data volume transmission and real-time monitoring in engineering application. According to the method, the core tensor of the infrared image sequence is obtained through Tucker decomposition and is updated until the convergence condition is met, and the infrared image sequence is reconstructed through the updated core tensor; the updating process comprises the following steps of: performing time mode expansion on a core tensor of an infrared image sequence, and obtaining a spatial reconstruction field under each time mode; applying thermal diffusion physical constraint on the spatial reconstruction field by adopting a lattice Boltzmann method to obtain a physical evolution field; and projecting the difference between the physical evolution field and the corresponding space reconstruction field to the corresponding position of the core tensor, and updating the core tensor slice through Adam optimization so as to update the core tensor.

The utility model belongs to the technical field of display screens, and particularly relates to a display screen module with an active infrared induction device, which comprises an outer shell, and a rear cover is arranged on the rear side of the outer shell. The structure is more compact, the appearance is more concise, meanwhile, the assembling difficulty and the production cost are reduced, the outer shell and the rear cover are rapidly disassembled and assembled through cooperation of the clamping pins and the clamping grooves, high-strength connection can still be guaranteed under the condition that screws are not needed through cooperation of the linkage structure of the reinforcing assembly, falling impact is effectively resisted, and the service life is prolonged. And through the environment light sensor and the distance sensor, the surrounding light intensity and the user distance can be monitored in real time, the brightness and the touch sensitivity of the display screen can be dynamically adjusted, the use experience is improved, and the equipment endurance is prolonged.

The invention discloses an active infrared binocular depth estimation method based on Gaussian splashing. The method comprises the following steps: firstly, for the same scene, respectively acquiring three-dimensional images under different infrared emission intensities at different visual angles, and constructing a real scene binocular infrared image data set; training a Gaussian splashing model by using a real scene binocular infrared image data set, rendering a simulated binocular infrared image at any angle in each scene and a corresponding depth value, and generating a parallax proxy label through a depth-parallax conversion formula; and carrying out active infrared projection based on the simulated binocular infrared image to obtain an image sequence with different infrared emission intensities under a new view angle, and carrying out data enhancement on a real scene binocular infrared image data set. Designing self-supervision loss and parallax supervision loss based on a projection pattern, and constructing a loss function of mixed supervision through weighted summation; and training the active stereo matching network by using the enhanced data set and the mixed supervision loss function, and outputting a high-precision depth estimation result.

The invention relates to a nondestructive testing technology of electrical equipment, and discloses an infrared detection device for cracks of an electrical tube, which comprises a support plate, a closed detection camera obscura, a rotary moving mechanism, an infrared imaging unit and an active infrared lighting unit, and is also provided with an infrared light source intensity real-time adjusting system, the system integrates an environment state evaluation module, a system state evaluation module, an adaptation evaluation module and a motion state evaluation module, and can sense multi-dimensional parameters such as environment light intensity, air suspended matter concentration, light source working temperature, optical window transmissivity, production line operation speed and pipeline rotation angular velocity in real time; and the infrared illumination intensity is dynamically adjusted by integrating the average gray scale of the image and the target feature contrast ratio. According to the invention, intelligent self-adaptive control of the infrared light source in a complex and changeable production environment is realized, the image quality stability and the accuracy and reliability of crack detection are effectively improved, and the method is suitable for full-automatic online nondestructive detection in large-scale production of power tubes.

The invention discloses a low-wind-resistance flexible passive infrared plane target, and belongs to the technical field of infrared optics. A traditional active infrared plane target or a traditional passive infrared plane target has the problems of complex composition, large size, poor wind resistance, easiness in damage when being used in a field environment and the like. The invention discloses a passive infrared plane target which is small in size, light in weight, foldable, small in wind resistance and good in environment adaptability. According to the method, the infrared reflection element array is arranged on the flexible basic network, the required infrared target pattern is obtained through a method of carrying out spatial modulation on natural infrared radiation of the field environment, no energy is consumed, infrared characteristics are stable for a long time, and the method is particularly suitable for being used in the environment with poor guarantee conditions in remote areas.

The invention discloses an unmanned ship autonomous berthing navigation system and method based on infrared vision tight coupling. The system comprises an infrared visual perception module, a visual processing module and a multi-sensor fusion pose estimation module, an active infrared light source array is installed at a berth, and an improved deep learning target detection network is adopted at an unmanned ship end to carry out light source array detection; secondly, information fusion of heterogeneous and asynchronous multiple sensors is realized in a sliding window through a constructed tight coupling integrated navigation system based on factor graph optimization; according to the method, infrared light source array detection can be carried out, robust visual feature extraction and fusion of heterogeneous and asynchronous multi-sensor information under complex illumination changes are ensured, distance and attitude estimation of the unmanned ship relative to a berth light source array is realized, vulnerability of a single sensor is overcome, and the method is suitable for large-scale popularization and application. Accurate self state and relative berth attitude information are provided for autonomous berthing of the unmanned ship, and long-term navigation consistency is improved.

The embodiment of the invention discloses a multi-mode peep-proof detection method and device, electronic equipment and a storage medium, and relates to the technical field of information security and anti-theft, and the method comprises the steps: obtaining multi-mode environment data in an omnibearing manner through radio frequency signal scanning, magnetic induction, active infrared detection and sound wave detection; and through a multi-source data fusion algorithm and decision tree model analysis, a sleep device activation mechanism is combined, and a detection result is accurately obtained. On the basis, an AR visual guiding and self-adaptive shielding technology is used for generating a peep-proof scheme, and positioning guiding and interference elimination of dangerous equipment are achieved. If the threat is not eliminated, continuously monitoring the environment, and dynamically adjusting the strategy; and if the threat is eliminated, optimizing the decision tree model and the wake-up signal parameter according to the detection data. The problem of missing detection caused by diversification and miniaturization of hidden equipment in the prior art and the problem that detection is difficult in the quiet period of dormant equipment are effectively solved.

The application discloses a kind of network configuration line three-dimensional scene modeling equipment and method comprising storage medium.Belong to robot, digital twin, power engineering and fire protection engineering technical field;Including point cloud acquisition module, data receiving and filtering module, point cloud storage module, three-dimensional modeling module, three-dimensional model storage library module and visualization terminal;Its modeling steps are: point cloud acquisition, volume filtering, denoising processing, region segmentation processing, feature attribute extraction, model library feature attribute matching, OpenGL library 3D modeling, model assembly, end.The application is based on laser radar to environment information acquisition, without theodolite, GPS, Beidou positioning and other auxiliary measuring tools, low in cost;Without human participation measurement, reduce human uncertain influencing factor;Since laser radar uses active infrared light to measure, not susceptible to environmental illumination influence.Point cloud feature in the application carries out three-dimensional modeling, method is simple, modeling speed is fast, high in accuracy.

A medium-voltage switch cabinet structure is applied to the technical field of switch cabinets. The structure comprises a switch cabinet body, the side end of the switch cabinet body is rotatably connected with a breaker chamber cabinet door, and a lighting lamp is arranged in a breaker chamber. An adjusting assembly and a connecting pipe made of a stainless steel corrugated pipe or a strength plastic pipe are arranged in the switch cabinet body, a threaded lamp holder is arranged at the side end of the connecting pipe, a lighting lamp is in threaded connection in the lamp holder, an electric wire in the lamp holder is electrically connected with a switch circuit in the switch cabinet body, and the position and orientation of the lighting lamp can be adjusted according to the layout of a circuit breaker chamber and lighting requirements. An opening and closing assembly is arranged between the switch cabinet body and the circuit breaker chamber cabinet door and comprises a slot, an active infrared correlation sensor and an opening and closing insertion block. By detecting opening and closing of the cabinet door and utilizing an infrared light reflection principle to control on-off of the switching circuit, automatic on-off of the lighting lamp is realized, and the lighting lamp is kept on to prompt when the cabinet door is not completely closed.

The utility model discloses a kind of hand waving response area lamp hat, including safety helmet;The safety helmet front end is provided with controller, microprocessor is installed in the controller, voice prompter is installed in the controller one side upper end, active infrared sensor is installed in the controller one side lower end, universal ball seat is installed in the safety helmet both sides, clamping groove is installed in the universal ball seat one side, lamp is detachably installed in the clamping groove interior, control switch is installed in the lamp upper side, power supply mechanism is installed in the lamp rear end, the universal ball seat and controller are installed on the safety helmet upper side by plug-in mechanism.

This invention discloses a method for preparing a thermal insulation coating for curtain wall glass, specifically relating to the field of building materials technology. The thermal insulation coating is prepared from a fluorocarbon-fluorosilicone copolymer resin solution, modified composite filler, silica-modified microspheres, fluorocarbon particle dispersion slurry, 1,6-hexanediol diacrylate, trimethylolpropane triacrylate, photoinitiator, 1-hydroxycyclohexylphenyl ketone, leveling agent, defoamer, and stabilizer. This invention achieves a synergistic effect of solar spectrum reflection blocking and phase transition temperature-triggered active infrared radiation heat dissipation by constructing a ternary composite system of reflective glass microspheres with titanium dioxide core-shell filler, barrier-type modified tin oxide antimony nanoparticles, and radiation-cooling tungsten-doped vanadium dioxide microparticles, thereby improving weather resistance.

The invention discloses an active infrared three-dimensional reconstruction method based on a depth camera, which relates to the technical field of computer vision and three-dimensional reconstruction, improves the quality of basic data through accurate alignment of multi-modal data, and solves the problem of low-texture scene registration in combination with temperature-geometry joint constraint. The TSDF model is improved to realize thermal-geometric information collaborative storage, and finally, in infrared target reconstruction, the F1 score is improved by 16.05%-16.88% compared with the traditional ICP, and the PSNR and SSIM are respectively improved by 15% and 20% compared with KinectFusion, so that an efficient solution is provided for active infrared three-dimensional reconstruction.

A planter suitable for block seeds that relates to agricultural seeding machinery includes a frame, a fertilizing tank, a fertilizing box, a seeding mechanism, a control mechanism, a seed box, a ridging mechanism, land wheels, a seeding furrower, a fertilizing furrower, a seed-clearing mechanism, and a replanting mechanism. The fertilizing furrower, the fertilizing tank, the fertilizing box, the seeding furrower, the land wheels, the seeding mechanism, the control mechanism, the seed box, and the ridging mechanism are mounted in turn from one end to an opposite end of the frame. A photoelectric sensor of an active infrared intrusion detector is adopted to dynamically monitor the presence of seed potatoes on a seed-discharge spoon in a conveying process. Seeds are replanted with the control mechanism when the seeds are sowed with an empty spoon.

The invention belongs to the technical field of active infrared thermal imaging nondestructive testing, and particularly relates to a modulation thermal imaging data and flash thermal imaging data conversion method, a signal reconstruction method and a computer device. The conversion method of the modulation thermal imaging data and the flash thermal imaging data comprises the following steps: S1, obtaining a temperature time sequence T omega (t) of the average temperature of a sample along with time change under modulation thermal excitation; s2, performing nonlinear fitting on the temperature time sequence T omega (t) to obtain an initial phase shift of modulation thermal excitation; s3, calculating a parameter sum by using the initial phase displacement of the modulation thermal excitation; and S4, for the temperature time sequence, obtaining temperature time data under similar flash thermal excitation. According to the method, a conversion model between modulation thermal imaging data and flash thermal imaging data is established, and a theoretical basis is provided for combination of the two technologies.

This invention discloses an automatic adjustment device and method for a machine vision target light source, comprising a structure under test and a machine vision camera component. An active infrared target light is installed on the structure under test. A visibility meter is installed between the active infrared target light and the machine vision camera component. The visibility meter and the active infrared target light are communicatively connected through a system controller. The visibility meter is used to collect on-site visibility data and transmits it to the system controller via an RS485 bus. The output visibility data range is 5-10000m. This invention can solve the problem of attenuation of active target light intensity in machine vision displacement monitoring systems under low visibility conditions such as rain, fog, and haze. By automatically adjusting parameters such as light source emission power, focusing emission angle, binarization threshold, and exposure time, it ensures image quality.

The invention relates to an active infrared vision fusion VR positioning method in an under-illumination environment, and the method comprises the steps: configuring an active infrared illumination unit on a head-mounted device, controlling the active infrared illumination unit to emit infrared light to the environment in a preset illumination mode, and collecting an infrared image; synchronously acquiring measurement data of the inertial measurement unit; performing preprocessing and feature extraction and tracking on the infrared image to obtain visual features; carrying out pre-integration on the measurement data to obtain IMU pre-integration data; visual features and IMU pre-integration data are fused, and state estimation and map construction are carried out through a multi-sensor tight coupling optimization algorithm; outputting a six-degree-of-freedom pose; and based on a state estimation result or visual feature extraction quality, dynamically adjusting illumination parameters, and repeating the steps. The fundamental problem that a traditional visual scheme fails in the dark is thoroughly solved, stable and continuous six-degree-of-freedom pose output is achieved, meanwhile, the optimal balance of power consumption and performance is achieved, mutual interference among multiple devices is effectively restrained, and the precision and robustness of the system are greatly improved.

The present application relates to a kind of infrared nondestructive testing methods and systems for detecting the defect condition of ancient building wall wood column.The infrared detection device of wall wood column is built, and clear infrared image is obtained at regular intervals;The infrared thermal image set obtained is perspective transformed, and corrected as the infrared image set under orthographic projection, and the infrared image noise is removed based on median filtering;Edge detection is carried out on its gray image using Canny operator, and the best threshold is obtained using adaptive iteration method, and further threshold highlight edge map is obtained, to determine the defect position and defect degree.The system detects the defect of wall wood column by active infrared nondestructive testing technology, overcomes the technical difficulties of effectively detecting the defect of wall wood column by current nondestructive testing means, and has the advantages of strong portability, simple operation, no need to contact and the like.Provides a new method and system for nondestructive testing of the defect condition of wall wood column, and has very important practical significance for nondestructive testing research of ancient building.

The invention discloses a nondestructive detection method for cable-stayed bridge cable damage based on an image sensor, and particularly relates to the technical field of cable damage detection. According to the method, through appearance screening and active infrared thermal excitation technology path comprehensive detection, firstly, surface cracking and corrosion areas are accurately positioned, then, spot hovering and active heating are carried out on each defect, and the internal extension degree and damage depth of the defects are accurately judged by analyzing unique thermal response, quantifying temperature rise, peak temperature and cooling coefficients of the defects, so that the defect detection accuracy is improved. The problems of missing detection and false detection of a traditional method are solved, reliable data support is provided for disease assessment, and technical span from rhus and shallow surface observation to deep internal flaw detection is achieved.