407 results about "Middle infrared" patented technology

The invention relates to the technical field of data image processing, in particular to a method for improving the accuracy of an infrared simulation image in an infrared imaging simulation system, and the method comprises the steps: obtaining a corresponding to-be-corrected infrared image of a target bullet in a flight process and a previous frame of historical infrared image, determining a gray level change factor and a bullet possible index corresponding to each pixel point in the to-be-corrected infrared image; target bullet points are screened out, a target bullet area formed by all the target bullet points is divided, and the target bullet points representing warhead vertexes are screened out; determining a temperature influence factor corresponding to each target bullet point; correcting the to-be-corrected infrared image according to the temperature influence factor corresponding to the target bullet point; and performing infrared simulation processing on the target image to obtain an infrared simulation image. The infrared simulation image is generated by processing the to-be-corrected infrared image and the previous frame of historical infrared image, and the accuracy of generating the infrared simulation image is improved.

The invention discloses a method for automatically detecting the combustion performance of a flooring material based on a bimodal space-time network. The method comprises the following steps: S1, synchronously acquiring and calibrating bimodal data; wherein the bimodal data comprises data acquired by a visible light camera and data acquired by a thermal infrared imager; s2, performing visible light channel flame segmentation based on the data acquired by the visible light camera in the step S1; s3, performing infrared channel temperature field calibration and carbonization analysis on the basis of data acquired by the thermal infrared imager in the step S1; s4, performing spatio-temporal feature fusion on the flame mask obtained in the step S2 and the temperature field data in the step S3; and S5, performing three-dimensional evaluation according to the dynamic prediction result generated in the step S4, and finally evaluating the combustion performance of the flooring material. According to the method, automatic detection of the combustion performance of the flooring material can be realized through the steps S1 to S5, and the problem of large manual observation error in a flooring material combustion test can be solved.

The invention discloses a converter lining thickness determination method and device, electronic equipment and a storage medium. According to the specific scheme, after smelting of a current heat is completed, smelting parameters and an infrared image of a target converter are obtained, and the infrared image is an image of a local area of the target converter; according to the infrared image, the target furnace lining temperature of the target converter is determined, and according to the target furnace lining temperature and the smelting parameters, the corresponding predicted furnace lining stripping amount of the target converter under the current heat is determined; according to the initial furnace lining thickness information and the predicted furnace lining stripping amount, the target furnace lining thickness corresponding to the target converter is determined; wherein the initial furnace lining thickness information is a furnace lining thickness parameter determined by the target converter before the current smelting. The method improves the efficiency and accuracy of determining the thickness of the converter lining.

The invention discloses a passive radiation refrigeration coating and a preparation method thereof, and relates to the technical field of industrial coatings. Comprising a fluoroacrylate emulsion, hollow glass beads, nano titanium dioxide, flaky silicon dioxide aerogel powder, polytetrafluoroethylene micro powder, hydroxyl-terminated polydimethylsiloxane, a hydroxyl acrylic acid modified silane coupling agent, a super-hydrophobic modified fluorosilicone surface additive, nano cerium oxide, aluminum fluoride doped zinc oxide infrared enhancement powder and deionized water. The paint is prepared on the basis of the formula. According to the invention, a multi-scale spectrum regulation and control and surface self-cleaning system is constructed cooperatively, so that the synergistic effect of high reflection of a sunlight region and high emission of a middle infrared region is realized. The coating can maintain continuous passive refrigeration in a day and night period, the surface of the coating has self-cleaning capability and excellent ultraviolet aging resistance, and high reflectivity and high radiation emissivity can be maintained for a long time in a complex outdoor environment, so that the thermal management efficiency of buildings and equipment is remarkably improved.

The invention relates to the technical field of infrared spectroscopic analysis, in particular to a spectroscopic analysis-based corn kernel nutrient abundance and deficiency state evaluation method, which comprises the following steps of: irradiating corn kernels by using near-infrared and mid-infrared light sources, collecting reflected spectral signals, and recording spectral signal data; and based on the spectral signal data, extracting key wavelength region data to obtain key spectral data. According to the invention, the near-infrared light source and the mid-infrared light source are combined, so that the capability of acquiring nutrient information of the corn kernels is enhanced, the reflection characteristic of spectral signals is utilized, the interference of environmental factors on data acquisition is reduced, and the stability of spectral data is improved. The screening of key wavelength regions reduces irrelevant information, so that the spectral data is more concentrated on the characteristic wave bands influencing the nutrient state. The spectral signals are processed through wavelet transform, the resolution ratio of the characteristic peak value is improved, the local change trend of the spectral signals is enhanced, and characteristic extraction is more accurate.

A system for monitoring fuel consumption in a rotary kiln includes IR sensors and computing systems. The computing systems: obtain a sequence of images; determine a map of temperature values of the infrared images in the sequence of infrared images; obtain a digital model of fuel consumption in relation to temperature values of the rotary kiln, wherein the digital model of the fuel consumption is based on a measured infrared temperature for the infrared images; determine the fuel consumption of the rotary kiln based on the measured infrared temperature with the digital model of the fuel consumption; and provide the fuel consumption in a fuel consumption report. The computing systems: analyze the fuel consumption of the kiln; obtain a correlation factor for the fuel consumption that identifies an amount of carbon dioxide emissions; and determine the emissions for the fuel consumption.

The invention provides an all-dielectric film system structure with visible near-infrared high absorption, intermediate infrared selective radiation and microwave high transmission. The all-dielectric film system structure sequentially comprises a protection and antireflection layer, a visible near-infrared absorption and infrared selective radiation layer and a substrate layer from top to bottom, the protection and antireflection layer comprises a first dielectric layer and a second dielectric layer which are arranged up and down; the visible near-infrared absorption and infrared selective radiation layer comprises a plurality of third dielectric layers and fourth dielectric layers which are alternately stacked. According to the structure, high absorption can be achieved in the wave band of 380-1100 nm, high reflection (low radiation) can be kept in the wave bands of 3-5 m and 8-14 m, high transmissivity is achieved in the microwave wave band, certain radiation can be kept in the wave bands of 5-8 m and 14-25 m, and effective heat management is achieved. The all-dielectric film system structure also considers the stability of the material in a space environment, and is provided with a protection and antireflection layer, so that the potential application reliability of the film system is improved.

The invention discloses an on-line detection method for volatile organic compounds in waste gas, and belongs to the field of waste gas emission monitoring, the detection method comprises the following specific steps: I, starting a quantum cascade laser frequency comb of a middle infrared band, calibrating various parameters of the quantum cascade laser frequency comb, and ensuring to cover a characteristic absorption area of the volatile organic compounds in the waste gas; iI, inputting the waste gas into a gas detection chamber through a sampling pipeline, monitoring the state of the waste gas in real time, and dynamically adjusting the conditions of the gas detection chamber according to various collected signals; the device can capture instantaneous fluctuation of waste gas concentration in real time, meets the high-speed dynamic emission monitoring requirement, has extremely high coherence and narrow linewidth, can analyze tiny spectral line differences which cannot be distinguished by a traditional spectrograph, remarkably improves the detection precision and the recognition capability, ensures that a measurement result still keeps consistency and high reliability under different working conditions, and is suitable for large-scale popularization and application. The signal-to-noise ratio is obviously improved, the power drift is reduced, and long-time stable operation is realized.

The invention discloses a method for predicting the aging degree of an anti-corona layer of a stator bar, and relates to the field of prediction of the aging degree of the anti-corona layer of the stator bar, and the method comprises the following steps: S1, data sampling; image data and real-time temperature information are obtained; s2, data processing; preprocessing the acquired image data to obtain a data set, and performing evaluation weight division and state division on the data set; s3, constructing a model; constructing a model by using a convolutional neural network; s4, training the model; s5, testing the model; s6, practical application; and predicting the aging degree of the anti-corona layer of the stator bar by using the anti-corona layer life prediction model. According to the method, the machine learning algorithm based on learning is adopted, the infrared thermal image, the ultraviolet sub-image and the temperature data in the aging process of the anti-corona layer of the stator bar are collected, the aging state of the stator bar is classified by applying multi-modal feature fusion, and the method has a good guiding effect on evaluation of the aging degree of the anti-corona layer of the stator bar.

The invention discloses an intelligent cabin environment sensing and control method based on a vehicle sensor, and relates to the technical field of intelligent automobiles, and the method comprises the following steps: in the operation process of an intelligent cabin, an infrared thermal sensing system collects thermal imaging data in an automobile in real time, extracts multi-dimensional feature data based on the obtained thermal imaging data, and sends the multi-dimensional feature data to the intelligent cabin; and forming an infrared thermal image characteristic data parameter set. According to the method, the key features of the infrared thermogram are extracted, and the machine learning model is combined, so that accurate identification and dynamic suppression of the thermo-optical interference state are realized. According to the method, sampling and filtering strategies can be adaptively adjusted in complex environments such as strong light reflection, a real thermal image contour is reconstructed, a non-human body heat source is effectively eliminated, the recognition accuracy and the operation stability of an infrared thermal sensing system are remarkably improved, the misjudgment rate is reduced, and the safety and the reliability of an intelligent cabin are enhanced.

Techniques are provided for variable sensitivity in infrared imaging. In one example, an infrared imaging system includes an infrared imager and a logic device. The infrared imager is configured to capture a first infrared image of a scene using a sensitivity setting. The logic device is configured to determine a temperature associated with the scene based on a second infrared image of the scene. The logic device is further configured to determine the sensitivity setting based on an ambient temperature associated with the infrared imager and the temperature associated with the scene. Related devices and methods are also provided.

The invention relates to the technical field of energy-saving materials, and discloses a preparation method of a self-assembled multilayer radiation refrigeration film, the self-assembled multilayer radiation refrigeration film comprises: a surface coating composed of a super-hydrophobic coating and used for providing anti-fouling and self-cleaning functions; the top layer is composed of titanium dioxide nanoparticles and has high sunlight reflectivity; the middle layer is a polytetrafluoroethylene layer with a hierarchical porous structure and provides thermal insulation and efficient mid-infrared emission; the bottom layer is composed of graphene oxide, has high heat conduction performance and promotes heat transfer; and the substrate is a flexible polyester film PET and is used as a supporting structure. Through the titanium dioxide nano-particle design of the top layer and the graded porous structure of the middle layer, the film achieves the reflectivity exceeding 90% in the sunlight band (400-2500nm), meanwhile, the film has the radiance exceeding 85% in the middle infrared band (8-13mu m), and due to the optical performance, surface heat absorption can be remarkably reduced under the intense sunlight condition.

The present invention relates to a tapered stack absorber capable of perfect light absorption in the spectral range of 0.5 [mu] m to 10 [mu] m. The structure is formed by periodically arranging conical unit structures in the horizontal direction, the bottommost layer of each unit structure is a square titanium (Ti) plate with the thickness of d and the width of p, and the square titanium (Ti) plate is used for preventing transmission of electromagnetic waves. On the basis of a Ti plate, 18 TiN / VO2 disc composite layers are stacked from bottom to top, the radius size is decreased by delta t every time, the radius of the bottom composite layer is D1, and the radius of the top composite layer is D2. The upper layer of the composite layer is a TiN layer with the height of h, and the lower layer of the composite layer is a VO2 layer with the height of h. The structure can realize perfect absorption from visible light to a middle infrared band (0.5-10 [mu] m).

The embodiment of the invention provides an eye movement tracking method and near-to-eye display equipment. The near-to-eye display device comprises a light source assembly, an optical waveguide, an image acquisition unit and a processing unit. The light source assembly comprises a visible light source and a plurality of infrared light sources arranged at intervals. The image acquisition unit is used for acquiring images of eyes. The eye movement tracking method comprises the following steps: determining the position of a preset eye region according to an eye image; determining a target infrared light source in the plurality of infrared light sources according to the position of the eye preset area; controlling the target infrared light source to emit infrared light to the pupil area of the eyes; and determining the gazing direction of the eye according to the light spot formed by the infrared light in the image of the eye. According to the technical scheme, when the pupil areas of the eyes are located at different positions, the infrared light can be accurately transmitted to the pupil areas, and high-precision eye movement tracking is achieved.

The utility model provides infrared thermal imaging equipment. The infrared thermal imaging equipment comprises a main processing unit and a data acquisition unit electrically connected with the main processing unit, the data acquisition unit comprises an infrared module used for acquiring infrared image data and a temperature data set corresponding to the infrared image data; the depth sensor is used for collecting a corresponding depth data set; and the main processing unit corrects the temperature data set through the depth data set, and applies the corrected temperature data set to image data for display. Wherein the infrared thermal imaging equipment adopts a multi-sensor data acquisition unit consisting of an infrared module and a depth sensor, so that data support is provided for correcting a temperature data set by using a depth data set, the data accuracy of a temperature field can be improved, and the application requirement of a temperature measurement scene with a higher temperature measurement precision requirement can be conveniently met.

The invention relates to a noninvasive blood glucose detection technology, in particular to a blood glucose detection method for a noninvasive blood glucose meter and a blood glucose detector. The invention discloses a blood glucose detection method for a noninvasive blood glucose meter. The blood glucose detection method comprises the following steps: acquiring near-infrared light data and mid-infrared light data and calculating corresponding weight coefficients; acquiring a predicted blood glucose value by using the blood glucose detection model, calculating credibility, comparing the credibility with a preset credibility threshold, and executing corresponding operation; and acquiring a blood glucose health assessment result by using the blood glucose health assessment model. The near-infrared spectrum technology and the mid-infrared spectrum technology are combined, the influence of environmental factors is considered in real time, the weight coefficients of the near-infrared light data and the mid-infrared light data are calculated respectively, analysis of the spectrum data is adjusted and optimized, a more accurate blood glucose detection result is provided, and the accuracy of blood glucose detection is improved. And reliable blood glucose measurement values can be obtained under different environmental conditions.

The invention relates to a bionic mist catching net material and a construction method and application thereof, and belongs to the field of air water collecting materials. The bionic mist catching net is a thermoplastic polymer fiber net, and radiation refrigeration particles are blended in fibers of the fiber net; and the part coated with the hydrophobic micro-nano coating and the part not coated with the hydrophobic micro-nano coating on the surface of the fiber net are alternately distributed. The radiation refrigeration particles are introduced into the bionic mist catching net material, and the hydrophobic coating is distributed on the surface of the bionic mist catching net material, so that the light reflectivity and the intermediate infrared emissivity are improved, and the radiation refrigeration efficiency is improved. Besides, the surface hydrophobic coating part forms a super-hydrophobic area, fog drops are promoted to be quickly coalesced into beads after collision, energy dissipation caused by spreading of a liquid film is reduced, the fiber substrate without the coating is kept hydrophilic, a heterogeneous wetting surface is formed, Laplace pressure difference is generated by surface energy difference at a hydrophilic-super-hydrophobic interface, and the super-hydrophobic surface is formed. The spontaneous migration of liquid drops from a super-hydrophobic region to a hydrophilic region is accelerated, and the water collection efficiency is remarkably improved.

Techniques for facilitating temperature compensation are provided. In one example, an infrared imaging system includes a focal plane array configured to capture radiation from a scene and generate image data based on the radiation. The focal plane array further captures radiation from an element associated with the infrared imaging system during capture of the radiation from the scene. The infrared imaging system further includes a temperature sensor configured to determine a temperature of the focal plane array. The infrared imaging system further includes a processing circuit configured to determine a temperature associated with the element based on the temperature of the focal plane array. The processing circuit is further configured to determine a temperature associated with an object in the scene based on the infrared image data, the temperature associated with the element, and the temperature of the focal plane array. Related devices and methods are also provided.

The invention discloses a flatness detection device for air conditioner metal pipeline spraying, and relates to the technical field of pipeline anti-corrosion spraying. The flatness detection device for spraying of the air conditioner metal pipeline comprises a spraying bin, an input pipeline is assembled at the top of the spraying bin, and an air draft pipeline is assembled at the bottom of the spraying bin; and the recycling bin filter plate is assembled between the spraying bin and the recycling bin. According to the flatness detection device for spraying of the air conditioner metal pipeline, the air conditioner metal pipeline is put into the spraying bin, a high-pressure liquid pump and a servo motor are started, and a reciprocating lead screw, a square pipeline, a pipeline connector, a gear, a first toothed bar, a second toothed bar, a connecting rod and a limiting rod are matched, so that anti-corrosion liquid can be rotationally sprayed out in different rotating directions; and in the reciprocating motion process of the spray head, the infrared distance meter can perform corresponding flatness detection operation on the air conditioner metal pipeline which is just sprayed, so that the detection efficiency of the device is improved.

The invention provides a cooling capacity-increasing overhead conductor, a dynamic current-carrying capacity determination method, a medium and equipment, and relates to the technical field of power transmission lines, the method is characterized in that the overhead conductor adopts a three-layer composite structure, the outer layer is a passive cooling coating, the thickness is 50-200 [mu] m, the surface is provided with a micro-nano structure for enhancing mid-infrared radiation, the emissivity is greater than or equal to 0.92, and the dynamic current-carrying capacity is greater than or equal to 0.92; the contact angle is greater than 120 degrees through hydrophobic modification treatment; the middle layer is a high-conductivity aluminum alloy conductor layer, and the inner layer is a high-strength galvanized steel core; a directional heat conduction path is formed between the coating and the conductor layer through a gradient heat conduction material, and the heat conductivity coefficient of the gradient material is gradually increased from the coating to the conductor layer; the coating mode of the coating is axial segmented coating or net-shaped coating. According to the overhead conductor, the current-carrying capacity of the line can be effectively improved, the power transmission design of the line is optimized, and the quantitative index of the capacity increasing effect can be obtained through the dynamic current-carrying capacity determination method.

Permafrost thawing prevention may involve deploying a cooling geotextile onto a permafrost soil. The geotextile may include a biomass scaffold comprising natural plant-based fibers. The geotextile may further include a cellulose layer comprising cellulose fibers laminated onto the biomass scaffold such that the cellulose fibers are physically entangled with the plant-based fibers. The geotextile may further include a hydrophobic and biodegradable coating which defines at least one surface of the geotextile. The geotextile may be optically opaque, exhibits high solar reflectivity, and maintains high mid-infrared emissivity to enable passive radiative cooling.

The invention discloses a magnetic infrared radiation heat dissipation material MnSe2, and a preparation method of the magnetic infrared radiation heat dissipation material MnSe2 comprises the following steps: 1) uniformly mixing manganese powder and selenium powder in proportion, and tabletting the obtained mixed powder to obtain a primary block 2) melting and quenching the obtained primary block under a vacuum condition; 3) grinding the quenched casting body, and tabletting to obtain a secondary block body; and 4) carrying out step-by-step melting annealing on the obtained secondary block under a vacuum condition, and then grinding to obtain the magnetic infrared radiation heat dissipation material MnSe2. Manganese powder and selenium powder are used as main raw materials, the melting quenching process and the step-by-step melting annealing process are combined, the infrared emissivity of the obtained MnSe2 material is promoted to be improved, and particularly, the high emissivity can be shown in the middle infrared band and the far infrared band; when the material is applied to preparation of a MnSe2 composite film, a good radiation refrigeration effect can be achieved, and the material has a good application prospect in the fields of thermal management of microelectronic devices and the like.

The invention discloses a fuel gas leakage detection system based on mid-infrared laser, relates to the technical field of fuel gas detection, and aims to solve the problems that a large-area region is difficult to cover quickly and only close-range detection can be carried out in an existing laser fuel gas leakage detection method. The gas leakage detection system comprises a laser emission module, an infrared imaging detector module and a data processing module, the laser emission module is used for emitting an intermediate infrared laser beam to a to-be-detected area; the infrared imaging detector module is used for collecting an infrared spectrum signal of the to-be-detected area in real time; the infrared spectrum transmitting module is used for transmitting the infrared spectrum signal to the data processing module; and the data processing module is used for processing the received infrared spectrum signal to obtain a gas leakage detection result of the to-be-detected area. The method is suitable for detecting gas leakage in a natural gas pipeline and a liquefied petroleum gas storage tank area.

To estimate a deterioration level of a machine auxiliary agent to be supplied to machines by a simple structure or a simple method.SOLUTION: A measurement device 10 comprises: a spectrometer 13; and a processing device 14. The spectrometer 13 spectroscopically measures a machine auxiliary agent, using a visible light ray, near infrared-ray, middle infrared-ray or ultraviolet ray to acquire spectral data. The processing device 14 outputs a deterioration level of the machine auxiliary agent on the basis of the spectral data. A model is configured by machine-learning using additive consumption rate as second learning data, or a deterioration level converting the additive consumption rate by use of the spectral data as first learning data. The processing device 14 is configured to output the deterioration level of the machine auxiliary agent estimated based on the additive consumption rate the model outputs, or the deterioration level of the machine auxiliary agent the model outputs.SELECTED DRAWING: Figure 1

The invention discloses a near-zero dispersion 3-5m middle-infrared band composite hollow-core optical fiber. The composite hollow-core optical fiber comprises a photonic crystal band gap region, an anti-resonance region and an air fiber core region which are sequentially arranged from outside to inside, the photonic crystal band gap region is composed of a series of air holes at equal intervals; the anti-resonance area is composed of a plurality of anti-resonance units; the anti-resonance unit is of a nested cladding tube structure and comprises a first-class elliptical dielectric tube, and a second-class elliptical dielectric tube and a round dielectric tube which are arranged in the first-class elliptical dielectric tube; the internally tangent points of the first-class elliptical medium tube and the second-class elliptical medium tube are in contact and coincide with the inner wall surface of the band gap region of the photonic crystal; and the second-class elliptical medium pipe and the circular medium pipe are externally tangent and welded. The mid-infrared band of 3-5m is the working band of the optical fiber, and the optical fiber has the characteristics of relatively low limiting loss, relatively large mode field area and low dispersion (the dispersion is close to zero) in the working band range, so that high-power and high-quality transmission of light in the band can be realized.

The invention discloses a method for synchronously realizing medium-wave infrared spectral imaging metasurface design and spectral image reconstruction. The method comprises the following steps: firstly, establishing a'structure parameter-spectral response 'database of a metasurface unit through simulation software; a forward prediction network is then constructed to predict its spectral response curve from the structural parameters. On the basis, a plurality of metasurface units with differentiated spectral characteristics are arranged on a two-dimensional plane in a spatial-spectral coding mode, and an input hyperspectral image is coded through convolution operation to generate a measurement image. And the target hyperspectral data is recovered from the measurement map in cooperation with a spatial-spectral decoding network. According to the method, metasurface structure design and reconstruction network training are integrated, structure parameters and decoding network weights are updated at the same time through back propagation, collaborative optimization of hardware and software is achieved, the spectrum reconstruction precision can be remarkably improved, the design period can be shortened, and the method is suitable for large-scale popularization and application. The method has a wide application prospect in the fields of spectral imaging, spectral detection, identification and the like of a middle-infrared band.

The invention provides an aerial infrared dim small moving target detection method. The method comprises the following steps: acquiring a to-be-detected image group; based on a grouping convolution kernel, a Transform module and a multi-frame signal adaptive accumulation module of the convolution kernel, performing adaptive signal accumulation on the to-be-detected image group to obtain an image feature matrix with enhanced representation; performing multi-scale detection on the representation enhanced image feature matrix through a preset convolutional neural network YOLOX-Tiny to obtain a multi-scale detection result of the image feature matrix; and performing exclusion processing on the multi-scale detection result of the image feature matrix based on a multi-scale detection result unification mechanism, and determining a target detection result of the to-be-detected image group. The multi-frame infrared target detection method can solve the problem that the existing multi-frame infrared target detection method is slow in detection speed and cannot meet the requirements of real-time performance or higher-frequency detection of an infrared detection system, and effectively improves the detection precision of the infrared small target under low contrast.

The invention relates to an infrared image temperature calibration method and system. Error amount generated by distance measurement between an infrared radiation source and an infrared imager is determined through atmospheric transmittance. And calling object surface emissivity preliminary information to reduce the surface emissivity error amount of the infrared radiation source in the actual measurement process. Based on the atmospheric transmittance, a temperature and hyper-parameter joint estimation model can be formed by establishing an infrared radiation model and constructing a forward model. A Bayesian inference method is utilized to deduce the surface emissivity of an object, meanwhile, prior information of different measurement materials is considered, and model parameters and temperature distribution are reconstructed by combining an improved model with a maximum posteriori estimation method. The improved infrared thermal radiation model is suitable for scenes with different measurement distances, humidity factors and emissivity. Through verification of multiple experiments of the black body and the high-speed direct-driven fan, the method can significantly reduce the measurement error and improve the accuracy of temperature measurement.

The invention belongs to the field of quality control of traditional Chinese medicinal materials, and particularly relates to a genuine medicinal material producing area distinguishing method based on multi-mode molecular spectrum characteristic recombination. Accurate identification of the producing area of the traditional Chinese medicine decoction pieces / powder is achieved by collecting the near infrared spectrum, the middle infrared spectrum and the terahertz spectrum of the sample, meanwhile, the recombination characteristic spectrum of the traditional Chinese medicine decoction pieces / powder in the near infrared spectrum, the middle infrared spectrum and the terahertz wave band can be visually displayed, and the method has the advantages of being higher in identification pertinence, higher in accuracy and wider in application range.

The invention relates to a cross-modal pedestrian re-identification method based on multi-scale multi-branch feature utilization, and belongs to the field of cross-modal pedestrian re-identification. The method comprises the following steps: acquiring an original data set, and learning a relationship between each channel of a visible light modal image in the original data set and a single-channel infrared light modal image through a random channel; the processed image is input into a cross-modal feature extraction module, different attributes of different modals are processed through a double-flow network, and then multi-scale features are extracted through a shared network; inputting the multi-scale features into a multi-scale information mining module for feature fusion; and the fusion features are subjected to discriminant feature extraction by a multi-branch joint module, and pedestrian re-identification is carried out through cooperation of the discriminant features extracted by each branch. According to the method, multi-level spatial feature information is combined for feature extraction, the correlation between an infrared mode and a visible light mode in visual representation is increased by using global features and local features, and the retrieval accuracy of cross-modal pedestrian re-identification is improved.