374 results about "Short wave infrared" patented technology

The invention discloses an artificial intelligence machine vision image acquisition system, and the system comprises a multi-mode perception layer which integrates a self-adaptive optical module, inhibits metal reflection, captures a visible light to short wave infrared image, and captures a motion edge; the dynamic adaptive layer adopts an illumination compensation and motion compensation module to dynamically adjust camera parameters and micro displacement compensation, feeds back an illumination trend, outputs a motion vector to the cognitive layer, generates a confrontation sample through a GAN, simulates virtual defects in combination with a physical engine, and expands training data; the cognitive reasoning layer is used for deploying a dynamic routing network, distributing computing resources according to image complexity and optimizing feature extraction efficiency; reducing data deviation through anti-fact analysis, and generating a thermodynamic diagram to explain a detection basis; and the collaborative decision-making layer is used for rapidly screening samples by edge nodes, training a global model by cloud aggregated data, automatically triggering manual rechecking when the confidence coefficient of the model is insufficient, synchronously optimizing a training set and a causal reasoning module by a rechecking result, and improving the labeling efficiency through AR assistance.

The invention relates to the technical field of regulating valve monitoring, in particular to a regulating valve opening degree monitoring method and system based on image recognition, and the method comprises the following steps: S1, constructing a composite optical mark: machining annular grooves and longitudinal convex ridges which are distributed in a staggered manner on the surface of a valve rod to form a composite mark belt; s2, anti-interference stereo imaging: collecting visible light and short wave infrared images to generate a fusion point cloud set; s3, dynamic shielding compensation: generating a three-dimensional point cloud model of a complete composite marking band; s4, thermal expansion decoupling calculation: visual displacement errors caused by thermal expansion are eliminated; and S5, time-space domain closed-loop calibration: reversely reckoning the opening value by using the structured light three-dimensional coordinate to carry out cross validation. According to the invention, high-precision, high-robustness and verifiability monitoring of the opening degree of the regulating valve is realized, and the measurement stability and engineering applicability under complex working conditions are effectively improved.

The invention discloses a photovoltaic module surface defect online detection method based on multi-modal image fusion, and relates to the technical field of photovoltaic module detection.The method comprises the steps that a visible light line-scan digital camera, a short-wave infrared camera, an EL line-scan digital camera and a laser speckle imaging module are installed to collect real-time data, an optical image is subjected to dynamic window median filtering, and the surface defect of the photovoltaic module is obtained; the method comprises the following steps: carrying out time moving average combined dynamic threshold segmentation on an infrared image and an EL image, carrying out image-guided outlier filtering on 3D point cloud data, judging a pixel defect type based on gray-temperature correlation and calculating a fusion weight, respectively inputting the optical image, the infrared image, the EL image and 3D point cloud into GhostNet, lightweight ViT, CNN and PointNet-Lite to extract features, and carrying out image fusion on the 3D point cloud data. And after global average pooling and splicing, inputting into a channel attention module to generate a modal weight, and after weighted fusion, obtaining a defect type through a full connection layer. According to the invention, the accuracy of defect detection is effectively improved.

The invention discloses a farmland soil moisture content real-time surveying system and method based on unmanned aerial vehicle multispectral imaging. The method comprises the steps that multispectral sensor parameters are configured, and an unmanned aerial vehicle flight scanning path is planned; a space coordinate system and time synchronization mechanism is established, and high-precision positioning and time synchronization are achieved; collecting and calibrating visible light, near-infrared and short-wave infrared original image data to form a spectral signal set; calculating an image signal-to-noise ratio, screening a low-quality image, and executing noise suppression; extracting timestamp information from the suppressed image, performing spatial positioning, and establishing a spatial corresponding relation database; calculating time synchronization precision and performing image correction; evaluating the spatial resolution according to the distortion coefficient; calculating a comprehensive quality parameter, comparing the comprehensive quality parameter with a threshold value, and obtaining a soil moisture content distribution parameter when a condition is met; a farmland moisture state map is generated, partition marking is carried out according to a multi-level standard, a monitoring result is output, and high-precision and real-time monitoring of the farmland soil moisture content is achieved.

The invention discloses an ultra-wide-spectrum endoscopic imaging device capable of being used for short-wave infrared fluorescence imaging, which is used for in-vivo minimally invasive imaging and comprises an illumination module, a wide-spectrum image transmission module, an imaging module and an image processing module. The illumination module consists of a light source and a light guide optical fiber, and is used for generating illumination light from ultraviolet to short wave infrared band and transmitting the illumination light to the wide-spectrum image transmission module; the wide-spectrum image transmission module consists of a few-interface optical imaging channel and a light guide illumination channel, and is used for illuminating an imaging target, exciting target fluorescence and collecting image signals from ultraviolet to short-wave infrared bands; the imaging module is composed of an optical filter and an imaging camera, and the imaging camera can be a wide spectral response image sensor or can be formed by combining cameras working in different wavebands and is used for converting optical images in different wavebands into image data; and the image processing module is used for registering and fusing image data of different wavebands in real time and displaying the image data.

The invention provides a short-wave infrared detector digital alloy material and a preparation process thereof. The preparation process comprises the following steps: growing a GaSb buffer layer on the surface of an n-type GaSb substrate; starting a first In furnace, and growing an InAs layer on the surface of the GaSb buffer layer in cooperation with an As beam; starting a second In furnace, and growing a quaternary solid solution layer matched with a GaSb buffer layer lattice on the surface of the InAs layer in cooperation with the Ga furnace and the AsSb beam; and alternately growing an InAs layer and a quaternary solid solution layer on the surface of the quaternary solid solution layer to generate a superlattice structure until the total thickness of the superlattice structure reaches a set target thickness, thereby obtaining the digital alloy material. According to the digital alloy material for the short-wave infrared detector and the preparation technology of the digital alloy material, the short-wave infrared detector can be expanded to the wave band ranging from 2.4 micrometers to 2.8 micrometers at the 50% cut-off wavelength.

The invention relates to the technical field of vegetation root system nondestructive testing, in particular to a multispectral vegetation root system identification system and method based on a differentiable physical engine, and the system comprises a multispectral LiDAR module which is used for transmitting near-infrared laser and short-wave infrared laser, scanning a target area, obtaining dual-wavelength reflectivity data, and determining the vegetation root system according to the dual-wavelength reflectivity data; generating a reflectivity ratio matrix by adopting a reflectivity ratio classification model; the differentiable physical engine is used for quantizing the dynamic relationship between the vegetation root growth rate and the soil resistance by adopting a coupling model according to the reflectivity ratio matrix, generating a physical model and updating the physical model at a preset time interval; and the data processing and three-dimensional modeling module is used for generating a three-dimensional root system model and a health assessment result according to the reflectivity ratio matrix and the physical model, and outputting the three-dimensional root system model and the health assessment result. According to the scheme, soil penetration and root system and foreign matter distinguishing can be carried out, the vegetation native environment is not damaged, dynamic monitoring analysis is carried out, and the accuracy of recognition analysis is improved.

The invention discloses a high and cold slope disaster body segmentation method fusing optical and SAR images, and the method comprises the following steps: 1, carrying out the snow coverage normalization processing based on the visible light green light wave band and the short wave infrared wave band of an optical image, and generating an ice and snow mask through an expectation maximization algorithm and a Gaussian mixture model; 2, preprocessing the optical image and the SAR image; step 3, constructing a high and cold slope disaster body segmentation model based on a Transform network; 4, training the segmentation model by using Dice loss and cross entropy loss in a combined manner, and freezing parameters of an image encoder in the training process; and step 5, inputting the high and cold slope remote sensing image into the trained segmentation model, and outputting a segmentation result of the slope disaster body by the segmentation model. According to the method, the problems of large ice and snow interference and poor multi-source data collaboration in high and cold slope disaster body segmentation are solved, and the segmentation precision and the engineering applicability are improved.

The invention discloses a vehicle blind area dynamic enhancement and warning system for a low-light environment, and relates to the technical field of automobile active safety, and the system comprises a short wave infrared imaging module which is used for capturing a passive thermal feature image of a scene behind the side of a vehicle; the multi-source signal acquisition module is used for acquiring a vehicle bus signal representing a vehicle motion state and an operation intention of a driver in real time; the data processing and risk assessment module is connected with the short wave infrared imaging module and the multi-source signal acquisition module, and is used for performing fusion processing on the thermal feature image and the vehicle bus signal, identifying a blind area target and calculating a dynamic risk level of the blind area target; the grading warning and intervention module is connected with the data processing and risk assessment module; the short-wave infrared imaging technology which is sensitive to night light and high in anti-interference capacity is adopted, the imaging problem under extremely low illumination is fundamentally solved, and stable detection of vehicles and pedestrians in a long distance in a completely light-source-free environment is achieved.

The invention provides a spectral imaging type defect detection method and system for a coating of an isolating switch, and relates to the technical field of electrical equipment maintenance, and the method comprises the following steps: S1, collecting a multiband reflection image of the coating on the surface of the isolating switch through a multispectral imaging device, the multiband at least comprising a visible light band, a near-infrared band and a short-wave infrared band; and S2, carrying out registration and fusion processing on the multi-band reflection image. According to the method and system, visible light, near-infrared and short-wave infrared bands are fused through multispectral imaging, high-precision defect recognition and thickness inversion are achieved, physical damage of traditional contact type detection to a plating layer is avoided, reflection interference is restrained through polarization filtering, the illumination fluctuation influence is eliminated through an ambient light dynamic compensation algorithm, and the detection accuracy is improved. And finally, in combination with structured light three-dimensional reconstruction and a multispectral inversion model, a coating thickness distribution diagram and a service life prediction curve are generated, data support is provided for preventive maintenance, and the service life of equipment is prolonged.

The invention provides a precise and small broadband hyperspectral imager, which is used for solving the technical problem that the existing broadband spectral imager from visible near-infrared to short-wave infrared for sceneries cannot meet the increasingly harsh imaging requirements. According to the small broadband hyperspectral imager, the front optical assembly of an off-axis two-reflection structure and the spectrometer assembly in a free-form surface reflector, optical path multiplexing and axis folding mode are adopted, the number of used lenses is greatly reduced, meanwhile, the length of a spectrometer is effectively reduced, and the imaging precision is improved. The volume and the weight of the spectral imager are greatly reduced; besides, front surfaces and rear surfaces of a first lens and a second lens in the spectrometer assembly are plated with broadband antireflection films from visible near-infrared to short-wave infrared according to light angles, and broadband detection from visible near-infrared to short-wave infrared can be realized in combination with a broadband refrigeration type detector. And the complexity and the installation and adjustment difficulty of the detector assembly and the circuit assembly are greatly reduced.

The invention discloses an intelligent optical sensing system based on multispectral fusion, and relates to the technical field of optical sensing, and the system comprises a multispectral image collection module which is used for synchronously collecting original image data of a target scene under three spectral channels of visible light, near-infrared and short-wave infrared; the space-time registration and preprocessing module is used for carrying out high-precision space-time registration and radiation correction on the images of different spectrum channels; the self-adaptive feature extraction and fusion module is used for extracting multi-scale spectral features from the registered multi-spectral image and dynamically selecting and weighting a fusion strategy according to scene content; and the lightweight decision network module outputs a final target identification and state discrimination result. According to the technical scheme, the time-space consistency of multispectral data acquisition can be realized, the cross-band registration precision is improved, the robustness under the conditions of low contrast, shielding and severe weather is enhanced, meanwhile, the calculation complexity and memory occupation are greatly reduced, and the method is suitable for edge calculation equipment with limited resources.

The utility model relates to the technical field of heating devices, in particular to a short-wave infrared ray heating curing lamp box which comprises a heat insulation box body, a short-wave infrared ray lamp, an air blowing device, a lampshade fixing plate and a reflection lampshade, and the reflection lampshade comprises an outer shell, an arc-shaped reflection plate, a profiling pressing plate, a locking piece, an insulation base and at least two conductive chucks. The profiling pressing plate and the arc-shaped reflecting plate are arranged in the outer shell from top to bottom in an overlapped mode, and a heating curing groove and an exhaust groove are formed in the bottom face of the heat insulation box body. Short-wave infrared light emitted by the short-wave infrared lamp can be focused on a workpiece to the maximum extent through the arc-shaped reflecting plate, so that the utilization rate of heat energy and the heating efficiency are improved, modular assembly of the reflecting lampshade is achieved, disassembly, assembly and maintenance are convenient, and the practicability is high. The arc-shaped reflecting plates with different reflectivity can be replaced according to the heating requirements of different workpieces, the airflow generated by the blowing device dissipates heat of the short-wave infrared lamp, the heated airflow is blown to the workpieces, and the workpieces can also be heated.

The invention discloses an inversion method for obtaining an N2O gas volume mixing ratio profile based on a short-wave infrared laser occultation detection technology. The inversion method comprises the following steps: calculating a short-wave infrared atmospheric refractive index profile at the center position of an N2O gas absorption spectral line; calculating a collision parameter profile according to the short-wave infrared atmospheric refractive index profile, respectively calculating atmospheric transmittance profiles of an N2O gas absorption spectral line and a reference spectral line based on normalized energy data of infrared laser occultation detection, and executing Abel integral inverse transformation on a difference value between the atmospheric transmittance profiles to obtain an N2O gas absorption coefficient profile; converting the N2O gas absorption coefficient profile into an N2O gas initial volume mixing ratio profile; and by taking the N2O gas initial volume mixing ratio profile as an initial value, carrying out analog calculation on an atmospheric transmittance profile after N2O gas absorption, constructing a cost function, carrying out iterative optimization, outputting an N2O gas volume mixing ratio profile, and obtaining a final inversion result. According to the method, the inversion precision is improved.

The embodiment of the invention discloses an all-day and all-world time measurement method and device. A specific embodiment of the method comprises the following steps: constructing a short-wave infrared astronomical survey star catalogue; constructing a short-wave infrared astronomical geodetic survey star database according to the short-wave infrared astronomical survey star catalogue; optimizing the short-wave infrared astronomical geodetic survey star library to obtain an optimized short-wave infrared astronomical geodetic survey star library, and correcting atmospheric refraction errors in the optimized short-wave infrared astronomical geodetic survey star library; carrying out all-day fixed star point coordinate extraction on the shot multi-frame daytime star map to obtain fixed star point coordinates; and according to the star point coordinates of the fixed star, carrying out all-day astronomical observation world time calculation on the observation fixed star to obtain all-day world time. According to the embodiment, unified comparison of multi-period monitoring data is realized, and the engineering practicability of a monitoring result is improved.

The invention discloses an intelligent monitoring, prevention and control system for tobacco brown spot, and relates to the technical field of agricultural disease monitoring and intelligent prevention and control. A lower canopy monitoring array, elevation thermal infrared and red edge near infrared imaging and spore sampling (fluorescent quantitative PCR / loop-mediated isothermal amplification) are used as inputs; fog drop deposition D, leaf surface water film W and spore concentration S are predicted through multi-modal alignment and a physical field generator; carrying out long sequence risk assessment by inputting a correlation state space model and superposing a liquid state self-correlation kernel, and carrying out long sequence risk assessment by using concentric wheel patterns and narrow yellow halo (rlt; 0.15) + near-infrared / short-wave infrared black mould layer triple discrimination and checking, and a prescription is formed by combining double-pulse triggering that leaf surface wetting is larger than or equal to 8 h or a spore index reaches a threshold. The prescription comprises night microclimate intervention, variable spraying and leaf thinning control; resistance rotation compliance is realized through prescription uplink pre-check and electronic control unit unlocking; based on row belt / Thiessen polygon scheduling, 36 h coverage is larger than or equal to 95%, the dosage and residues are reduced, and the hit rate and timeliness are improved.

The invention belongs to the technical field of infrared detection, and particularly relates to a low-noise high-frame-frequency short-wave infrared imaging system. The system comprises an optical element, a detector, an analog acquisition circuit, a digital driving circuit and an upper computer, the digital driving circuit sends time sequence signals to the detector and the analog acquisition circuit respectively to enable the detector and the analog acquisition circuit to keep time sequence synchronization, and the optical element collects infrared light of a detected target and sends the infrared light to the upper computer. The infrared light of a detected target is refracted to a focal plane of the detector, the detector converts the infrared light into an analog electric signal based on a time sequence signal, and the analog acquisition circuit processes the analog electric signal based on the time sequence signal and outputs an obtained digital signal to the digital driving circuit. And the digital driving circuit performs format conversion on the digital signal and sends the signal obtained by format conversion to an upper computer for image display. According to the invention, a high-frame-frequency imaging function under the condition of low readout noise is realized.

The invention provides a method for detecting the content of liquiritin and glycyrrhizic acid in liquorice decoction pieces based on hyperspectrum, and relates to a method for rapidly and nondestructively predicting the content of index components of the liquorice decoction pieces by using a hyperspectrum technology. The method comprises the following implementation steps: acquiring a hyperspectral image of the liquorice decoction piece, determining the liquid phase content of the liquorice decoction piece, preprocessing the hyperspectral image, establishing a content prediction model, and quickly and nondestructively detecting the liquorice decoction piece. The method comprises the following steps: collecting licorice decoction pieces in a short-wave infrared band by using a hyperspectral imaging technology, determining the contents of liquiritin and glycyrrhizic acid in a collected sample through liquid chromatography, extracting characteristic wavelengths according to the content measurement data, comparing the advantages and disadvantages of different characteristic variable extraction methods and content prediction models, and determining the content of glycyrrhizic acid in the licorice decoction pieces. Therefore, rapid nondestructive detection of the liquiritin and glycyrrhizic acid content in the licorice decoction pieces is realized, an analysis method is provided for rapid grading and screening of the traditional Chinese medicine decoction pieces, digitization, intelligence and greenization of the traditional Chinese medicine industry are promoted, and improvement of the equipment manufacturing level of the pharmaceutical industry is promoted.

The invention discloses a fire monitoring-oriented SAR-to-optical image generation method and device, and aims to solve the problems that an SAR image is difficult to interpret and optical remote sensing is shielded in fire monitoring, and an existing generation method is unstable in training, high in calculation overhead, discontinuous in structure and the like. According to the method, an SAR image is acquired and preprocessed, and a pseudo RGB image is constructed; extracting near-infrared and short-wave infrared bands of the multispectral image, calculating an NBR index to generate a fire mask, and constructing a spectrum guide loss function; taking DDPM as a generation trunk, embedding a cross-domain translator and combining a hierarchical structure guide mechanism to perform weighted fusion on global and local reconstruction results; and outputting the optical style image. The method can generate optical images with clear details, consistent spectrums and coherent structures under the shielding of smoke and clouds, balances the generation quality and efficiency, improves the accuracy of fire monitoring and post-disaster evaluation, and is suitable for multi-scene fire monitoring.

The invention discloses a forest weak disturbance area identification method and device, equipment, a medium and a product, and relates to the technical field of forest detection, and the method comprises the steps: employing a change detection algorithm of a long-time sequence image to construct a prediction model according to a normalized red wave and short wave infrared distance index and a tasseled cap transformation humidity index; constructing a training set according to the two prediction models; each sample in the training set comprises input data and label data, the input data comprises waveform coefficients and environment data of the two prediction models, and the label data comprises a forest type and a non-forest type; the forest type comprises existence of forest weak disturbance and absence of forest weak disturbance; the detection threshold value for distinguishing the existence of the forest weak disturbance and the absence of the forest weak disturbance is obtained by performing adaptive calculation on a prediction model change probability threshold value by utilizing a gradient lifting decision tree algorithm; and training the classification model by adopting the training set to obtain a forest weak disturbance recognition model. The forest weak disturbance detection accuracy is improved.

The invention discloses a low-distortion athermalization correctable short-wave infrared optical system and a lens, and belongs to the technical field of optics. According to the system, an optical lens is additionally arranged at the rear end to serve as a correction lens to achieve image correction in an external field environment; passive athermalization under wide-temperature and vacuum conditions is realized through focal power distribution and material matching of each optical lens; all the lenses are set to be spherical surfaces, so that the influence of aspheric surface processing errors on system index precision, processing cost and system installation and adjustment is avoided; the system adopts a positive-negative-positive-negative-negative five-lens focal power configuration. The positive-negative-positive-negative lenses are located at the front end, and the last negative lens is located at the rear end. The five lens materials are zinc sulfide, a chalcogenide material, single crystal barium fluoride, single crystal calcium fluoride and a chalcogenide material in sequence; the correction lens is located at the rear end of the last negative lens. The short-wave infrared optical system can solve the problems that an existing short-wave infrared optical system is large in imaging distortion, or athermalization is not achieved, or image correction under the external field application condition cannot be achieved.

The invention discloses an outdoor box video monitoring method, device and system based on multi-dimensional fusion. The system has the advantages that the visible light camera adopted by the main lens collects the physical state of the surface of the box body and the peripheral visible dynamic state, and the short-wave infrared equipment is adopted by the auxiliary lens to collect invisible characteristics and temperature distribution; feature points are extracted to calculate similarity, pixel-level matching is realized through a constructed perspective transformation matrix, and a correlation database is constructed; based on the multispectral data, three types of interaction events of biological interference, natural action and environmental transaction are identified in combination with deep learning, a fault and event association data set is constructed, a weight is assigned, a baseline threshold is set, and early warning is triggered when the threshold is exceeded; after early warning, the starting time and position of an event are positioned, a risk network is constructed to calculate the contribution degree of the event to determine a core risk source, three levels of risks are divided, a traceability map is generated, a differentiated operation and maintenance scheme is generated, monitoring is optimized, and the accuracy and operation and maintenance efficiency of outdoor box monitoring are improved.

The invention relates to the technical field of remote sensing prospecting, and discloses a uranium-copper multi-metal remote sensing prospecting method which comprises the following steps: S1, data acquisition and preprocessing; s2, alteration information is extracted; s3, multi-source information comprehensive analysis and prospecting prediction; s4, alteration abnormity verification is carried out; and S5, delineating the prospecting target area. According to the method, vegetation spectrum interference is stripped by carrying out principal component analysis on visible light-short wave infrared of a remote sensing image, weak iron staining and hydroxyl alteration signals are extracted, a geological and remote sensing coupling technology is carried out, alteration anomaly is superposed with a geological map, geochemical data and a construction interpretation result, a comprehensive remote sensing anomaly map is obtained, and the comprehensive remote sensing anomaly map is obtained. According to the method, the multi-parameter grading model GGS is established, and the target region is graded based on the multi-parameter grading model GGS, so that the probability of missed judgment of the target region is reduced.

The invention provides a carbon monoxide plume identification and quantification method based on a domestic hyperspectral satellite, and the method comprises the steps: carrying out the radiometric calibration and atmospheric correction of the data of a visible short-wave infrared hyperspectral camera AHS I carried by the domestic hyperspectral observation satellite (GF-5B, Gaofen-5 B satellite); generating a carbon monoxide unit absorption spectrum by using a medium-resolution atmospheric transmission model MODTRAN; inverting a carbon monoxide enhancement value by adopting a matched filtering method; generating a binary plume mask through threshold segmentation; and constructing a deep learning model based on a residual neural network ResNet network, and realizing plume pixel-level identification and carbon monoxide column concentration enhancement value prediction. The method can identify the carbon monoxide plume with high precision and high efficiency, and is suitable for atmospheric pollution monitoring and pollution source quantification.

The invention discloses a short wave infrared small sample three-dimensional Gaussian three-dimensional reconstruction method based on knowledge assistance. The method comprises the following steps: firstly, converting a three-dimensional structure model into a point cloud, carrying out structure perception point cloud fusion on the point cloud and an original target point cloud, and then carrying out initial training to realize geometric construction based on structure prior; then generating a short-wave infrared simulation image based on the three-dimensional model, and performing target instance driven cross-domain adaptation training on a pre-trained diffusion model to obtain a cross-domain diffusion model; and finally, in combination with a cross-domain diffusion model and a structure prior driven geometric construction result, triple constraints are added to reconstruct a three-dimensional image. Through staged modeling under structure guidance, the fuzzy or artifact risk caused by directly introducing misaligned or error accumulated geometric information into the texture stage is avoided, and a stable structure guidance image with clear components is provided for the texture modeling stage; and the generation stability and the structural fidelity of the diffusion model under complex observation conditions are effectively enhanced.

The invention discloses a wheat grain moisture content lossless prediction method based on hyperspectral imaging and Wasserstein generative adversarial network data enhancement, which realizes accurate moisture prediction by fusing spectral feature data enhancement and deep learning modeling. Collecting spectral image data of the wheat grains by using a visible light-near infrared and short wave infrared hyperspectral imaging system; a Wasserstein generative adversarial network is adopted to generate synthetic spectrum and moisture data in a differentiated mode, data distribution consistency is verified through t-SNE, and a triple training set is expanded; noise is eliminated in combination with first-order derivative preprocessing, key characteristic wavelengths are screened by using SPA and ReliefF algorithms, and a convolutional neural network regression model is constructed; experiments show that the method achieves # imgabs0 # imgabs1 # RMSEP = 0.5717 in the visible light-near infrared band and # imgabs2 # RMSEP = 1.0009 in the short wave infrared band, and the precision is remarkably improved compared with a traditional extreme learning machine and a back propagation neural network.

The invention relates to the technical field of industrial machine vision detection, in particular to an intelligent detection system and method based on multi-modal vision. Comprising a multi-mode imaging unit which comprises a visible light camera, a short wave infrared camera and a laser displacement sensor, and the optical axes of the three devices intersect at the center point of a detection surface; a nitrogen cooling channel and a thermoelectric refrigerating unit are arranged in the active temperature control module, and the imaging unit is kept in a constant-temperature environment of 40 + / -2 DEG C; the tail end of the six-axis robot carrying platform is provided with a multi-mode imaging unit; the high-temperature metering module is installed on the rear side of the tail end of the six-axis robot carrying platform through a rear support, the multi-mode imaging unit is installed under the tail end of the six-axis robot carrying platform through a front support, and the working distance between the high-temperature metering module and the multi-mode imaging unit is larger than or equal to 200 mm. Through cooperative work of the multi-mode imaging unit, high-temperature radiation interference is effectively overcome, and clear imaging and accurate positioning of bubble group defects are achieved.

In general, the disclosure describes a sensor comprising a photo-sensitive silicon substrate configured to detect ultraviolet (UV), visible, and near-infrared (NIR) light and an upconversion layer comprising a plurality of crystals configured to convert short wave infrared light to UV, visible, or NIR light. An example sensor includes an upconversion layer comprising a plurality of crystals configured to convert electromagnetic radiation comprising a first range of wavelengths greater than 1100 nm to electromagnetic radiation comprising a second range of wavelengths less than or equal to 1100 nm and a photo-sensitive silicon substrate configured to detect the electromagnetic radiation comprising the second range of wavelengths.

An image sensor pixel is provided that includes a semiconductor substrate having a front surface and a back surface opposing the front surface, a photosensitive element such as a photodiode formed in the front surface of the semiconductor substrate and configured to sense light in a first range of wavelengths, an interconnect stack formed on the front surface of the semiconductor substrate, and a thin-film diode formed in the interconnect stack and configured to sense light in a second range of wavelengths different than the first range of wavelengths. The thin-film diode may be a Schottky diode. The thin-film diode may include one or more rows of protruding or finger-like metal structures and semiconducting oxide material disposed directly on the protruding metal structures.

The invention provides a tunnel surrounding rock identification method and system, and relates to the technical field of tunnel construction, and the method comprises the steps: obtaining a mixed frequency sound wave reflection signal collected by a sensor array disposed on a tunnel face, synchronously acquiring the hyperspectral image data of the tunnel face rock mass from the visible light to the short wave infrared band through a portable spectrometer; topological mode construction is carried out according to the mixed frequency sound wave reflection signals, and topological invariant features are obtained; performing cross-modal fusion according to the topology invariant features and the hyperspectral image data to obtain a fused topology-spectrum association graph; hidden manifold structure learning is carried out according to the fusion topology-spectrum correlation graph, and a low-dimensional feature vector is obtained; performing dynamic surrounding rock category division according to the low-dimensional feature vector to obtain a surrounding rock dynamic classification label; and performing identification result decision according to the surrounding rock dynamic classification label to obtain a tunnel surrounding rock identification result. According to the invention, high-precision and high-robustness dynamic identification of the tunnel surrounding rock state is realized.