168 results about "Spectral reconstruction" patented technology

The invention discloses an image deblurring method based on a rotation perception multi-dimensional attention and blurring sensitivity self-adaptive distribution mechanism, aiming at the defects of the prior art in the aspects of complex blurring processing and image reality sense improvement, and belongs to the technical field of image processing, and the method comprises the following steps: preprocessing a collected picture to obtain a training set; training an image deblurring model by using the training set; and performing image deblurring by using the trained image deblurring model. According to the invention, by designing a plurality of innovative modules and combining fuzzy degree adaptive selection, kernel estimation and dynamic weight distribution driven by a physical model, a multi-dimensional rotation perception attention mechanism, spectrum reconstruction anti-noise deblurring and detail enhancement of perception loss optimization, the image deblurring effect and processing efficiency are effectively improved; the method is especially suitable for processing blurred images with high complexity and high resolution.

A pharmaceutical hyperspectral reconstruction method based on a coded aperture snapshot spectral imaging (CASSI) system includes: collecting and processing original pharmaceutical hyperspectral images to obtain augmented pharmaceutical hyperspectral images; performing simulated spatial encoding on the augmented pharmaceutical hyperspectral images to obtain encoded measurement images; performing spectral inverse shift on the encoded measurement images, then performing inverse encoding to obtain inversely encoded three-dimensional hyperspectral images, using the augmented pharmaceutical hyperspectral images as target images, and constructing a training set and a testing set according to the inversely encoded three-dimensional hyperspectral images and the target images; constructing a deep symmetric neural reconstruction network, and training and testing the deep symmetric neural reconstruction network; and deploying a tested deep symmetric neural reconstruction network onto the CASSI system, real-time collecting pharmaceutical measurement images using the snapshot coded imaging system, and performing computational reconstruction on the pharmaceutical measurement images to obtain reconstructed three-dimensional hyperspectral images.

The invention discloses an abnormity monitoring method and system for a digital pressure transmitter, and relates to the technical field of transmitter monitoring, and the method comprises the following steps: obtaining an original pressure response sequence in a high-frequency pressure pulsation environment, and synchronously recording a sampling clock pulse sequence in an acquisition process, establishing double-track mapping based on the original pressure response sequence and the sampling clock pulse sequence, and forming an input condition with a unified time baseline; and performing instantaneous phase difference extraction on the double-track mapping on the unified time base line. Through double-track mapping, phase difference extraction and nonlinear cross spectrum reconstruction, the stroboscopic aliasing risk is quantified and recognition in advance is realized, and the sensitivity and accuracy of abnormal monitoring of the digital pressure transmitter are improved; meanwhile, the multi-scale risk amplification and reversible time-frequency rearrangement technology is combined, covered high-frequency components are separated and recovered, a real pressure pulsation curve is output after dynamic correction, continuous and stable monitoring is guaranteed, and pressure measurement reliability and operation safety are improved.

A regional soil moisture monitoring method based on airborne spectral reconstruction optical satellite remote sensing, the method comprising: acquiring satellite remote sensing data of a region to be monitored, and collecting unmanned aerial vehicle remote sensing data of a local region in the region to be monitored; on the basis of the unmanned aerial vehicle remote sensing data of the local region, performing spectral reconstruction on the satellite remote sensing data of the region to be monitored, so as to obtain reconstructed satellite spectral data of the satellite remote sensing data; and inputting the reconstructed satellite spectral data into a pre-trained soil moisture inversion model, so as to obtain the soil moisture content of the region to be monitored. Therefore, soil moisture is accurately and quickly monitored.

The invention discloses a saturated spectrum processing method for wide-range detection of an absorption spectrum of a tunable diode, and relates to the technical field of spectrum gas detection. According to the saturated spectrum processing method for wide-range detection of the absorption spectrum of the tunable diode, an effective spectrum signal is obtained by performing denoising and baseline correction on an original absorption spectrum signal, a plurality of spectrum characteristic parameters are extracted to calculate a saturated quantized value, and a complete absorption spectrum line contour is reconstructed by adopting a spectrum reconstruction algorithm according to the quantized value, so that the wide-range detection of the absorption spectrum of the tunable diode is realized. The method comprises the following steps of: constructing a saturation quantitative evaluation system, a layered self-adaptive spectrum reconstruction strategy, a dual-mode detection fusion mechanism and a working condition compensation model, calculating weights of an absorption spectrum and a wavelength modulation spectrum through an S-type function, correcting a preliminary concentration value by combining environment temperature, pressure and a compensation model, and outputting an accurate final gas concentration. Without additional hardware, wide-range high-precision gas detection is realized, and environmental interference and saturation influence are eliminated.

The invention discloses an inland water area remote sensing reflectivity weak supervision spectrum super-resolution reconstruction method and equipment, and relates to the technical field of remote sensing data processing and remote sensing image spectrum enhancement, and the inland water area remote sensing reflectivity weak supervision spectrum super-resolution reconstruction method mainly comprises the steps: constructing a spectrum super-resolution data set; pre-training a spectrum degradation network and a space degradation network by using a degradation loss function, constructing a spectrum super-resolution network, training the spectrum super-resolution network by using an SA loss function according to the spectrum super-resolution data set, and obtaining a trained spectrum super-resolution network; and carrying out image super-division on the remote sensing image to be subjected to spectral super-division to obtain a super-division high-spectral-resolution image. By implementing the inland water area remote sensing reflectivity weak supervision spectrum super-resolution reconstruction method and equipment provided by the invention, the precision and robustness of spectrum reconstruction in a water body scene can be improved.

The invention provides a spectrograph, a spectrum reconstruction method and device and electronic equipment, and relates to the field of spectrum analysis. The spectrograph comprises a chip and a peripheral circuit, the chip comprises a photoelectric response layer, a gate layer and an electrode lead-out layer, and a target semiconductor is arranged in the photoelectric response layer; the photoelectric response layer is used for converting an incident spectrum into a photocurrent signal; the gate layer is used for changing the photoelectric response characteristic of the target semiconductor and covers the upper and lower surfaces of the photoelectric response layer; the electrode lead-out layer is used for outputting the photocurrent signal to external equipment, and the external equipment is used for reconstructing an incident spectrum according to the photocurrent signal and the photoelectric response characteristic of the target semiconductor; the peripheral circuit is used for maintaining the chip to work. According to the invention, the semiconductor with adjustable photoelectric response characteristics is used as the core of the photoelectric response layer, so that the spectrometer has the spectral analysis capability from infrared to terahertz wave bands, does not need to depend on a huge optical assembly and a precise mechanical displacement assembly, and can effectively solve the problems in the prior art.

The invention relates to an aircraft spectral data dynamic acquisition method, which comprises the following steps of: designing working modes of a voltage modulation reconstruction type spectrograph, including a full-wave band spectral acquisition mode, a specific wave band spectral acquisition mode and a standby mode; determining use conditions; when the spectrograph works in a full-band spectrum acquisition mode, setting the voltage of the full-band spectrum as m1 groups of voltages, detecting an incident spectrum to obtain m1 groups of light intensity signals, and performing spectrum reconstruction calculation to obtain all spectrum information; when working in a specific wave band spectrum acquisition mode, setting the voltage of a specific wave band spectrum as m2 groups of voltages, m2 < = m1, detecting an incident spectrum to obtain m2 groups of light intensity signals, and performing spectrum reconstruction and calculation to obtain specific spectrum information; in a standby mode, a single voltage is set, an incident spectrum is detected to obtain a group of light intensity signals, and spectrum reconstruction is not carried out. According to the method, the problems of bandwidth occupation, storage pressure, energy consumption increase and the like caused by whole-process full-amount transmission are solved, and meanwhile, the differentiated requirements of different task stages for specific data are met.

The application discloses a hyperspectral imaging chip, device and system based on an adjustable reconfigurable metasurface, and the chip comprises a metasurface unit array, a metasurface reconfiguration module, a metasurface adjustment module, a CMOS image sensor and a spectrum reconstruction and identification module, the metasurface unit array comprises a plurality of metasurface units arranged on a silicon layer; the metasurface reconfiguration module is used for adjusting the number of metasurface units included in the reconfigurable metasurface unit array; the metasurface adjustment module is used for connecting the silicon layer of the metasurface unit array through wires, and is used for changing the spectral response of the metasurface unit by adjusting the voltage of the wires; the CMOS image sensor is used for detecting light signals from the reconfigurable metasurface unit array after modulation; and the spectrum reconstruction and identification module is used for performing hyperspectral reconstruction and imaging according to the light signals detected by the CMOS image sensor. The application has adjustable spectral response, ultrahigh spectral resolution, real-time dynamic monitoring capability and self-adaptive imaging capability.

The invention discloses a computing spectrum reconstruction method based on CS-Unet and a spectral imaging system. The calculation spectrum reconstruction method comprises two parts, namely TwIST pre-reconstruction and Unet coupling reconstruction, wherein the TwIST pre-reconstruction is used for preprocessing an initial coding spectrum image to generate a pre-reconstructed spectrum image; and the Unet part couples the pre-reconstructed image and the initial coding spectral image in the spectral dimension and inputs the coupled image and the initial coding spectral image into a network for fine reconstruction, and finally a target space-spectral image is recovered. The imaging system is composed of a spectral image coding module and a CS-Unet reconstruction module, a metasurface spectral modulator applied to the spectral image coding module is composed of 36 silicon-based all-dielectric structures, and rich spectral response is achieved by adjusting the period, the size and the direction angle of three basic C4 symmetric units, namely a round unit, a cross unit and a square unit. According to the method, high-robustness and high-imaging-quality spectrum reconstruction is realized in a visible light wave band (400-700 nm), and the method has relatively high engineering applicability.

A spectral sensing device and associated methods for enhanced diagnostic capabilities across medical fields are disclosed. The device incorporates multispectral, hyperspectral, and photoplethysmography technologies to analyze biological features including tongue, oral cavity, saliva, teeth, and other tissues. The system transforms any standard RGB camera into a multispectral imaging device by training machine learning models to associate RGB values with spectral values inside and outside the visible spectrum using measurements from a single pixel detector spectroradiometer. A multimodal neural network with separate processing branches analyzes spectral images, non-spectral images, and tabular data to predict microbiome composition. The system generates health risk assessments by comparing predicted microbial abundances to thresholds associated with various medical conditions. Near-infrared sensing enables blood flow monitoring, subcutaneous imaging, and assessment of physiological parameters. Convolutional neural networks enable spectral reconstruction without requiring the physical device, while supporting continuous monitoring in various form factors.

The invention discloses a near infrared spectrum reconstruction method based on stage perception mixed prior and a two-channel optical imaging system, and the method comprises the steps: constructing a deep expansion network model of stage perception mixed prior based on RGB guidance, and the network model comprises k cascade reconstruction stages, each reconstruction stage comprises a degradation perception residual gradient descent module and a near-end mapping module. According to the method, a degradation sensing residual error gradient descent module is introduced, the difference between a sensing matrix and an actual degradation process is effectively reduced through degradation learning, and the iteration process of a deep expansion network is divided into two stages of spectral space preliminary feature extraction and space detail deep extraction by applying a segmented optimization strategy; the network reconstruction precision is guaranteed, the optimization of the calculation efficiency is improved by adjusting the network complexity in stages, and the completeness and quality of the reconstructed image are guaranteed while the calculation overhead is reduced.

The invention relates to the technical field of moisture prediction, in particular to a 3D reconstruction and illumination adaptive coal surface moisture prediction method, which comprises the following steps of: planning an unmanned aerial vehicle route to collect an image, reconstructing coal pile surface space structure information, forming a local triangular grid, dividing an illumination continuous area, establishing a space corresponding relation between the illumination area and a hyperspectral pixel, and predicting the moisture content of a coal pile. And geometric registration and reflection transition correction are executed, depression points and shoulder positions of a reflection curve are detected in the identification interval, moisture absorption characteristics are constructed, a moisture migration link is established in the slope direction, and a coal surface moisture prediction result is obtained. According to the method, a spatial structure and illumination distribution are coupled, a dynamic correction relation is established to unify reflection information, image registration and spectrum reconstruction are combined to strengthen geometric consistency, a moisture migration trend is extracted by utilizing depression point and slope correlation, link and accumulation distribution is formed, and a corrected reflection characteristic represents a spectrum attenuation rule. The spatial continuity and numerical stability of moisture identification are ensured, and the water content grade division is coherent and comparable.

The invention provides a spectrum reconstruction method based on double-branch heterogeneous feature fusion, and relates to the technical field of computational imaging and artificial intelligence, and the method comprises the steps: obtaining a two-dimensional compression measurement image vector, constructing a local-global feature fusion deep neural network model, and constructing a local-global feature fusion deep neural network model; the method comprises a local feature extraction module, a global context extraction module, a feature fusion module and a decoder, a composite loss function is designed, the composite loss function comprises reconstruction loss, physical prior loss and feature regularization loss, end-to-end training is performed on a local-global feature fusion deep neural network model, and the trained model is deployed. And rapid spectrum reconstruction is realized. According to the method, the rapid reasoning capability of the deep neural network is combined with a novel parallel feature extraction and fusion architecture, and local and global information is effectively integrated and constrained in a feature space through a well-designed network model and a composite loss function, so that rapid and high-precision reconstruction of a hyperspectral image is realized.

The invention provides a method and system for identifying sorghum varieties based on spectrum reconstruction and a storage medium, and belongs to the technical field of sorghum variety identification. The method comprises the following steps: acquiring hyperspectral data of a sorghum grain sample and a corresponding pseudo RGB image through a hyperspectral image acquisition system; a mapping relation between pseudo RGB and hyperspectral data is established by using an ASTEM-MST + + model, a spectrum reconstruction model is established, and the ASTEM-MST + + model integrates an adaptive feature enhancement module into a multi-stage spectrum converter network, so that the sorghum spectrum reconstruction quality is improved. A real RGB image of a sample collected by an industrial camera replaces a pseudo RGB image to be input into a reconstruction model, corresponding hyperspectral data is reconstructed, then a region of interest is obtained, spectral data is extracted, variety labels are calibrated and then input into an SSA-RF model for training, a variety identification model is constructed, and the sorghum variety is identified.

The invention discloses a frequency data analysis method and device based on self-supervised learning, and a storage medium. The method comprises the following steps: S1, constructing a standard spectrum tensor; s2, executing frequency change feature extraction operation to generate a frequency change feature map; s3, determining a frequency section of which the hopping intensity is greater than a preset hopping threshold value, constructing a hopping section mask, and generating a structure covering spectrum tensor; s4, inputting to an improved ConvTransform model, and generating a frequency spectrum reconstruction tensor and a residual feature tensor; s5, constructing a frequency spectrum reconstruction loss function and a residual error fitting loss function, executing a self-supervised training process, and constructing a frequency guidance feedback graph; and S6, applying to frequency data analysis, and generating a frequency spectrum reconstruction result, a residual error response result and a hopping section positioning result. According to the invention, the abnormal change identification capability and the frequency spectrum reconstruction precision in the frequency data analysis process are improved.

The invention provides a hyperspectral spectrum data fusion method and a hyperspectral spectrum data fusion system capable of widening a spectral band, and the method comprises the steps: carrying out the wavelength domain matching of Vis-NIR hyperspectral data obtained by a ground object spectrometer based on the visible light band of a hyperspectral image, and storing the resampled Vis-NIR hyperspectral data in a spectrum library. Performing similarity measurement on the spectral vector of each pixel in the hyperspectral image and all standard spectrums in the spectrum library to generate a spectral feature fingerprint map and a spectral response coefficient map; and performing spectrum reconstruction on each pixel in the hyperspectral image data in combination with the spectral feature fingerprint map and the spectral response coefficient map. And finally, obtaining a hyperspectral image cube after broadened spectrum fusion. According to the scheme, on the basis of wavelength domain matching, the spectral feature fingerprint map, the spectral response coefficient map and the like, the hyperspectral image cube obtained through final fusion covers a wider spectral range, and the original high spatial resolution is reserved.

The application discloses a kind of light field regulation detection method and device based on computing spectral reconstruction, belong to spectral analysis technical field.The method is by introducing medium-metal composite nanostructure, integrates metal nanoisland array and silicon nitride nanocolumn array on quartz substrate, realizes electric field enhancement using the local surface plasmon resonance effect excited by metal nanoisland array, simultaneously realizes wide spectral range phase coding by medium nanocolumn array;Super surface chip is integrated with single point detector, combines pre-calibrated super surface sensing matrix A and enhancement factor matrix E, and reconstructs spectrum using compressed sensing or Tikhonov regularization algorithm.The application keeps the advantages of miniaturization and no moving parts, realizes directional high sensitivity detection to weak signal, and signal-to-noise ratio is improved.

The invention discloses a spectrum super-resolution method and system based on an FP cavity and deep learning, and the method comprises the steps: S1, carrying out the initialization of spectrum collection, and selecting light with a specific wavelength after the light is acted with a target detection object; s2, performing photoelectric conversion and digitization to generate low-resolution original discrete spectrum data of corresponding wavelengths; s3, continuous spectrum scanning is carried out, and original discrete spectrum data collection of the whole target wave band is completed; and S4, performing super-resolution spectrum reconstruction, and judging whether cyclic reconstruction is performed or not based on a reconstruction data quality evaluation result until the quality is qualified. According to the method, an accurate mapping model from a low-resolution spectrum to a high-resolution spectrum is established through a pre-trained deep neural network, and an original spectrum which is collected by an FP cavity and is limited by the theoretical limit optical resolution of the FP cavity can be reconstructed into a super-resolution spectrum of which the resolution remarkably exceeds the theoretical limit. The problem that the resolution of an FP cavity in a long-wave region is sharply reduced is effectively solved, and the full-wave-band uniform high resolution is realized.

The invention relates to the technical field of remote sensing image processing, in particular to a dahurian larch pest occurrence degree identification method based on spectrum reconstruction, and the method comprises the steps: obtaining a real multispectral image of a forest region invaded by defoliated pine caterpillars, and the ground hyperspectral data of a local region of the forest region; performing consistency processing on the real multispectral image and the ground hyperspectral data obtained in the step to obtain a simulated multispectral curve of a local area; performing interpolation reconstruction on the real multispectral image based on the simulated multispectral curve to obtain simulated hyperspectral images of all the forest regions; extracting a sensitive wave band sensitive to the invasion of the deciduous pine caterpillars and sensitive spectral characteristics from the simulated hyperspectral image; and an integrated learning strategy is adopted, and sensitive wave bands and sensitive spectrum characteristics are utilized to analyze the pest occurrence degrees of all the areas of the forest region. According to the method, spectrum reconstruction and an integrated learning strategy are combined to identify the occurrence degree of larch hairy pests, so that the spectrum reconstruction quality and the pest identification precision are improved.

This invention discloses an end-to-end spectral reconstruction method, comprising the following steps: S1, reconstructing a hyperspectral image; S2, using the obtained hyperspectral image as input to an optimized neural network, training the neural network parameters according to the end-to-end spectral reconstruction model, and calculating the loss function; S3, backpropagating errors to the coding template to be designed, changing the design parameters of the coding template, and continuing to train the model until a high-quality hyperspectral image is reconstructed. By employing the above technical solution, the design of the optical system is combined with the reconstruction method. Based on the coded aperture snapshot system, an adaptive coding template is added according to the end-to-end spectral reconstruction method, replacing the traditional random coding template, thereby improving the quality of spectral reconstruction.

This invention provides a spectral reconstruction method based on dual-branch heterogeneous feature fusion, relating to the fields of computational imaging and artificial intelligence. The method includes acquiring two-dimensional compressed measurement image vectors, constructing a local-global feature fusion deep neural network model, which includes a local feature extraction module, a global context extraction module, a feature fusion module, and a decoder; designing a composite loss function, including reconstruction loss, physical prior loss, and feature regularization loss; performing end-to-end training on the local-global feature fusion deep neural network model; and deploying the trained model to achieve rapid spectral reconstruction. This invention combines the fast inference capability of deep neural networks with a novel parallel feature extraction and fusion architecture. Through a carefully designed network model and a composite loss function, it effectively integrates and constrains local and global information in the feature space, achieving rapid and high-precision reconstruction of hyperspectral images.

The invention provides a spectral data cube reconstruction method, device and equipment based on compressed physical prior, a storage medium and a program product, and relates to the technical field of spectral reconstruction, and the method comprises the steps: obtaining a two-dimensional measurement image formed after a to-be-observed target is coded and modulated by a spectral imaging chip; obtaining an original transmission spectrum matrix corresponding to each pixel in the spectral imaging chip; performing principal component analysis on the original transmission spectrum matrix in a spectrum dimension, and extracting a principal component feature vector through a singular value decomposition method; projecting the original transmission spectrum matrix into an orthogonal subspace formed by the principal component feature vectors to obtain a compressed physical prior vector; and inputting the two-dimensional measurement image and the compressed physical prior vector into a deep expansion neural network, and outputting a high-dimensional spectral data cube of the to-be-observed target. The reconstruction efficiency of the spectral data cube can be remarkably improved.

The invention discloses a high-luminous-efficiency LED lighting device and a manufacturing method thereof, and relates to the technical field of lighting, the high-luminous-efficiency LED lighting device comprises a shell, a heat dissipation module used for avoiding light attenuation acceleration is arranged in the shell, the heat dissipation module comprises a ceramic heat dissipation plate and an aluminum substrate which are arranged in the shell, and concave-convex textures are arranged on the heat dissipation surface of the ceramic heat dissipation plate; the aluminum substrate is provided with a multi-channel assembly used for preventing the overall lighting effect from being reduced, and the opening of the shell is provided with an anti-glare assembly used for restraining glare under low light loss. Convection heat transfer is enhanced through concave-convex textures on the surface of the ceramic heat dissipation plate so as to delay light attenuation, the multi-channel assembly independently adjusts driving current through a power management system so as to achieve spectrum refined reconstruction, and the anti-dazzle assembly achieves dazzle suppression under low light loss through microstructure textures on the light-emitting face of a lens and light diffusion particles filled in the center area.

The application discloses a kind of based on human eye visual system screening optical filter's spectral reconstruction method and application, steps are as follows: using LMS cone response function to the original filter is weighted, using weighted area screening method, select and the LMS cone response function of human eye visual system most matched three filter as initial filter;Determine initial filter, and the remaining filter is sequentially exhaustively combined with three initial filters;The filter group generated is substituted into spectral reconstruction model, and the spectral recovery and chroma error of each filter group are obtained;According to self-defined recovery error set sorting, select the optimal filter group under L weighting, M weighting and S weighting, select the optimal group through self-defined error score ranking.When the number of channels increases, the respective optimal filter group under L weighting, M weighting and S weighting is exhaustively combined with the remaining filter, and the above steps are repeated according to the number of channels until the number of filters in the selected filter group meets the number of channels.

This invention relates to the field of computational optical imaging and provides a hyperspectral computational imaging method, system, and related equipment for multispectral acquisition. The method includes: acquiring filter parameters; constructing a spectral simulation reconstruction network; setting a minimum reconstruction error and using the filter parameters to set variables for the annealing algorithm, constructing a simulated transmittance curve to train the spectral simulation reconstruction network, calculating the error until the annealing algorithm calculates the optimal solution and obtains the optimal parameters; training the spectral reconstruction network based on the optimal parameters, simultaneously selecting corresponding filters to form spectral sampling units, and sampling the target spectrum to obtain a mixed spectral image; registering the mixed spectral image to obtain a registered spectral image; and inputting the registered spectral image into the spectral reconstruction network to obtain a reconstructed spectral image. This invention improves the spectral acquisition speed, solves the registration problem of snapshot-type spectral acquisition, and further improves the accuracy of hyperspectral computational imaging.

This invention provides a method, apparatus, device, medium, program product, and computational spectral imaging and spectral analysis system for screening spectral modulation microstructures based on a broadband measurement basis, relating to the field of optical technology. The method includes: acquiring the transmission spectra of multiple candidate spectral modulation microstructures; determining a sparse matrix based on the spectral application scenario; and performing inverse design based on the sparse matrix and the transmission spectra of multiple candidate spectral modulation microstructures, iteratively screening at least one target spectral modulation microstructure as the optimal combination of spectral modulation microstructures. The inverse design process aims to minimize the objective function, which is determined based on the maximum column coherence of the sensing matrix, which is determined based on the sparse matrix. Through this method, the optimal combination of spectral modulation microstructures can possess task adaptability for specific spectral application scenarios, which is beneficial for ensuring the system's spectral reconstruction performance and spectral feature extraction performance in spectral application scenarios.

The application discloses a spectral imaging method based on an RGB camera and a broadband filter coding. According to a camera spectral response function, an optimized parameter of a broadband filter and a spectral reconstruction network construction design stage, an end-to-end optimization framework is constructed. Then, the end-to-end optimization framework is trained according to a hyperspectral dataset to obtain a trained end-to-end optimization framework of the design stage and obtain a theoretical design parameter of the broadband filter. Then, an actual spectral transmittance function of the combined broadband filter and a final spectral reconstruction network are obtained. Finally, an RGB imaging system is built and a scene image is obtained, which is input into the final spectral reconstruction network to obtain a hyperspectral image. The application is based on the wavelength coding spectral imaging principle, a specially designed broadband filter is added in the imaging light path, and the input image of the reconstruction algorithm is increased from 3 channels to multiple channels through multiple imaging, so that the spectral accuracy of the reconstruction result can be effectively improved.

The invention discloses a disaster scene-oriented double-stage diffusion remote sensing hyperspectral reconstruction method. The method comprises the following steps of: acquiring a data set of a multispectral image and a hyperspectral image; generating a prior noise image; constructing conditional prior; generating an intermediate hyperspectral image through reverse diffusion iteration; and a more refined hyperspectral image is obtained through further optimization of the spectrum correction network. According to the method, a prior-guided diffusion method is adopted, accurate hyperspectral construction under a single sample is realized by utilizing spectral prior information, and hyperspectral data can be effectively generated in a scene lacking hyperspectral data; in the spectrum correction process, a progressive design is adopted to divide an input image into a plurality of hierarchies, the noise problem introduced in the diffusion process is gradually eliminated in the hierarchies with different resolutions, and high-quality generation of a hyperspectral image is completed. According to the method, a spectrum super-resolution generation task can be completed based on a single sample, on the other hand, the structural precision of a hyperspectral image generated by an algorithm can be improved, and the hyperspectral data generation effect is remarkably improved.

The application relates to the technical field of spectral imaging, and discloses a spectral imaging method and system based on hyperspectral low rank and binocular stereo matching, which comprises the following steps: representing a hyperspectral image as based on an SVD algorithm, updating orthogonal spectral bases and coefficients, synthesizing a color image under a CASSI branch perspective by using an initial hyperspectral image, obtaining a disparity between the color image under the CASSI branch perspective and the color image under the RGB camera perspective by using a GwcNet neural network, aligning the color image of the RGB camera to the CASSI branch according to the disparity, forming a new color image, and quickly reconstructing the hyperspectral image by using a low rank algorithm again on the new color image and the original encoded image; the method fully excavates the low rank characteristics of the spectral image, greatly improves the imaging speed, uses the color image to guide the reconstruction of the spectral image, eliminates the image difference possibly caused by the first prism dispersion through twice dispersion, and improves the spectral reconstruction accuracy to a certain extent.