43 results about "Spectral inversion" patented technology

The invention discloses a crop spectrum inversion model adaptive construction method. The method comprises the following steps: analyzing field actually-measured water nitrogen dry matter data and a crop physiological coupling rule, constructing a water nitrogen dry matter physiological constraint feasible region in a three-dimensional state space, generating a virtual sample, and fusing the virtual sample with the actually-measured water nitrogen dry matter data to construct a physical consistent training sample set; based on the combination of the moisture level and the nitrogen level, constructing a water-nitrogen cooperation state category, independently determining a spectral feature subspace, and training to generate a water-nitrogen cooperation state submodel with independent parameters; and judging the category of the target water-nitrogen coordination state, routing to the corresponding water-nitrogen coordination state sub-model, and resolving to obtain a pixel water-nitrogen instant inversion result. According to the method, the problems of model generalization and physical consistency under small samples are solved through physiological mechanism constraints, the complex influence of water-nitrogen interaction stress on the spectrum is decoupled through a state typing mechanism, and the accuracy and robustness of crop water-nitrogen inversion are improved.

The invention discloses a multi-spectral radiation temperature measurement method and system for improving a quantum particle swarm, relates to the field of radiation temperature measurement and photoelectric signal processing, and solves the problems that when an existing standard PSO algorithm is applied to high-dimensional and nonlinear multi-spectral inversion, local extreme values are likely to be trapped, and the self-adaptive capacity is poor. Setting parameters, generating an initial particle position by using Tent chaotic mapping, calculating the particle fitness of an initialized population, updating initial individual optimum and global optimum, and calculating an average optimal particle position; updating the optimal particle position through a Levy flight mechanism; and repeating the steps, calculating the multispectral radiation temperature measurement target function value of the updated position, updating the initial individual optimum and the global optimum, and if an error threshold value or the maximum number of iterations is met, outputting the global optimum solution. The method is also suitable for the application field of inverting the real temperature and the spectral emissivity of the target from the multi-channel spectral radiation signals and the like.

This invention provides a curvewave domain-based method for removing strong axes based on reflection coefficient attribute volumes, relating to the field of seismic data processing technology. The method includes: performing spectral inversion processing on raw seismic data to generate a reflection coefficient volume; based on the reflection coefficient volume, performing multi-scale, multi-directional layer-by-layer analysis in the curvewave domain, i.e., extracting reflection coefficient curves for each analysis window, determining inflection point locations by calculating the zero point of the second derivative of the curves to identify abrupt changes in the reflection coefficient; simultaneously, constructing local discrete surfaces based on the reflection coefficient volume, identifying local geometric anomaly regions of the reflection coefficient volume by fitting surface patches and calculating Gaussian curvature; and extracting strong reflection coefficient components by combining the determined inflection point locations and the identified local geometric anomaly regions. This invention can achieve precise stripping of strong reflection energy and faithful protection of effective weak signals, improving the reliability of seismic data in identifying and analyzing subsurface lithology and geological structures.

The present application belongs to the field of oil and gas and geophysical exploration, and particularly relates to a multi-channel bipolar sparse spectral inversion method based on Hessian matrix constraint. The method comprises the following steps: estimating a seismic wavelet wavelength to determine a time window length, and dividing multi-channel seismic data; extracting a seismic wavelet in the time window; constructing a multi-channel bipolar sparse spectral inversion objective function based on Hessian matrix constraint in the time window, and calculating the reflection coefficient of the multi-channel seismic data in the time window; and combining the reflection coefficient results of each time window center in time sequence to obtain the spectral inversion result of the multi-channel seismic data. The method can reflect the real contact relationship of the stratum, depict the real pinch-out position of the stratum, and provide high-resolution and more abundant geological information. While improving the resolution of the seismic data, the method can ensure the lateral continuity of the stratum in the multi-channel data, and can provide more accurate and abundant geological and reservoir information.

The invention belongs to the technical field of agricultural remote sensing monitoring, and discloses a saline-alkali soil wheat grain total phenol content remote sensing monitoring method and system. Based on multi-source remote sensing data, meteorological and vegetation characteristics are extracted through phenological matching, and a protein content estimation model containing a salt stress nonlinear inhibition item is constructed; and establishing a quantitative relationship between the protein and the total phenol content, and finally, performing inversion by using an optimization algorithm to obtain the high-precision total phenol content, thereby realizing effective monitoring on the quality of the wheat grains in the wide-range saline-alkali soil. A'protein content-total phenol content 'secondary inversion framework is created for the first time, total phenol content monitoring is indirectly achieved through a protein remote sensing inversion technology, and the technical problem that direct spectrum inversion is low in precision is effectively solved; the saline-alkali soil specificity stress response model is creatively established, the non-linear inhibition effect of salinity on the crop physiological process is considered in the inversion process, the monitoring precision and the model adaptability are remarkably improved, and the method has the advantages of being high in monitoring precision, high in practicability, wide in application range and the like.

The application provides a micro-transient temperature field detection system and method. The detection system comprises: a light source module adapted to emit laser light; a sensing module comprising a reference grating and an atomic force probe; a feedback control module connected to the atomic force probe in the sensing module, the feedback control module being adapted to obtain a surface topography scanning result of a sample to be measured after the atomic force probe scans the sample to be measured; and a data processing terminal configured to process temperature sensing information by a spectral inversion algorithm and combine the surface topography scanning result to obtain a temperature field distribution of the surface of the sample to be measured. The micro-transient temperature field detection system and method can improve the accuracy and speed of micro-transient temperature field detection, and the detection result has high spatial and temporal resolution.

The application relates to the technical field of soil monitoring, and discloses a method and system for monitoring soil pollutants in a power transmission and transformation project, wherein the method comprises the following steps: collecting hyperspectral image data in a power transmission and transformation project area; processing the hyperspectral image data by adopting a multistage spectral transformation mechanism to obtain characteristic wave bands representing pollutant contents; inputting the characteristic wave bands into a preset spectral inversion model to generate a concentration spatial distribution map of soil pollutants; constructing a soil and groundwater diffusion model according to the concentration spatial distribution map; and generating a migration path identification map of soil pollutants and an underground pollution risk area identification map based on the soil and groundwater diffusion model. The method has the beneficial effect of improving pollution identification precision and migration prediction accuracy.

This invention provides a method and system for spectral inversion calculation of chirped gratings in lithium niobate thin films. The method includes: sequentially performing time-frequency domain transformation, window truncation, and time-shifting on a preset ideal target response of the grating to obtain a physically realizable target response; using the physically realizable target response as the initial complex reflection response, performing layer-by-layer recursive calculation on the grating using a layer-by-layer peeling algorithm to obtain the complex coupling coefficients corresponding to each layer of the grating, and extracting the coupling coefficient distribution and phase distribution of the grating; obtaining the structural parameters of the chirped Bragg grating based on the coupling coefficient distribution and phase distribution; constructing a physical model of the grating based on the structural parameters, and performing simulation calculations on the physical model to obtain the spectral response. This invention, based on the traditional grating design process, introduces a layer-by-layer peeling algorithm for inversion calculation of the grating structure, inversely obtaining the coupling coefficients and phase distribution of the grating, as well as the corresponding grating structural parameters, and constructing a corresponding physical model, exhibiting strong target-oriented characteristics.

This invention discloses a combustion state inversion method, system, and apparatus based on neural networks and absorption spectra. The inversion method includes the following steps: data acquisition and preprocessing, and spectral inversion. In the data acquisition and preprocessing step, the original absorption spectrum signal of the combustion region to be tested is acquired. Background subtraction is performed on the original absorption spectrum signal to obtain a preprocessed spectral signal, and the apparent absorbance is calculated from the preprocessed spectral signal. In the spectral inversion step, the apparent absorbance is input into a pre-trained spectral inversion neural network model. The spectral inversion neural network model directly outputs the inverted combustion state parameters, which include at least temperature, pressure, and concentration. This invention utilizes an envelope correction network built based on U-Net and a temperature inversion network and a pressure and concentration inversion network built based on Inception-ResNet. These technologies can directly extract effective absorption features from the original absorption spectrum, which contains unknown and complex baselines, avoiding dependence on independent baseline measurements or estimates.

The application discloses a LIBS inversion method based on EMA-CNN and a weighted loss function, and relates to deep learning and spectral analysis.A LIBS spectral inversion model is constructed based on a deep convolutional neural network (CNN), an efficient multi-scale attention mechanism (EMA) is introduced, a weighted mean square error loss function is designed, and multi-component content collaborative prediction is realized.Conventional deep learning methods adopt equal attention allocation for all spectral features, the EMA module of the application can effectively guide the model to focus more reasonable attention, and the extraction and learning efficiency of key features are significantly improved.The conventional loss function is prone to the problem of unbalanced loss components caused by the order of magnitude difference of each component content, and the loss function of the application can weight the corresponding loss components of each component to collaboratively improve the prediction accuracy of all components.The method has the advantages of accuracy, stability and high efficiency, and is suitable for LIBS multi-component synchronous inversion tasks in a large data volume scene.

The present application relates to the technical field of ship emission monitoring, and particularly relates to a ship emission remote sensing method based on multi-band spectral inversion, which uses shore-based multi-band remote sensing to obtain O4 differential slant column density in the horizontal direction, calculates the effective optical path length of different bands, divides the synchronously inverted NO2 horizontal column density by the effective optical path length to obtain the average concentration on the horizontal path, separates the NO2 concentration of different horizontal layers based on multi-band inversion; constructs a ship plume model coupled with the ship sailing track and Gaussian plume model based on ship AIS data combined with wind direction and wind speed information, matches the plume track of different ships with the concentration layer passed, and quantifies the NO2 concentration of single ship emission combined with the plume width information calculated by the ship plume model. The present application evaluates the emission of ships at sea based on remote sensing means, can carry out monitoring without interfering with the normal sailing of ships, and provides strong technical means and data support for ship emission supervision.

The present application relates to the technical field of magnetic resonance inversion, and discloses a kind of magnetic resonance time domain spectrum inversion method, device and program product, the method includes: obtaining the target inversion kernel matrix of magnetic resonance experiment and magnetic resonance original sampling data set;According to the preset peak type, construct complete base matrix, and establish the initial inversion function without explicit regularization term;Using physical priori field knowledge, the initial inversion function is simplified to obtain the target inversion function, and the physical priori field knowledge includes one or more of relaxation time interval, diffusion coefficient interval, peak ridge interval and peak edge interval;Using target inversion kernel matrix and magnetic resonance original sampling data set, the target inversion function is solved, and magnetic resonance time domain inversion spectrum is generated, which not only guarantees the physical rationality and interpretability of inversion result, but also greatly reduces the operation scale.

The invention discloses a field scale soil organic matter spectrum inversion modeling-oriented sample transfer learning method and program product, and the method comprises the steps: carrying out the first-order differential processing of spectrum data in a source domain data set and a target domain data set, environment variables with Spearman correlation coefficients and variance expansion factors higher than threshold values in the source domain data set are eliminated, and target domain samples are divided into a training set and a test set; calculating environment similarity and spectrum similarity between the source domain and the training set samples, further obtaining comprehensive similarity between each source domain sample and each training set sample, and obtaining an intersection of the source domain samples with the comprehensive similarity larger than a threshold value and the source domain samples with the organic matter content within a preset range to serve as a source domain migration sample set; and obtaining a union set of the source domain migration sample set and the training set as an amplification training data set of soil organic matter spectrum inversion learning. The test precision obtained by performing field scale organic matter spectrum inversion based on the amplification training data set formed by the method is higher.

The invention provides an image color calibration method and device, electronic equipment and a storage medium. The image color calibration method comprises the following steps: acquiring a multispectral image, and preprocessing the multispectral image; dividing the preprocessed multispectral image into at least one spectral correlation area; performing spectrum inversion on the spectrum correlation area to obtain a reflection spectrum curve; determining a target color temperature value of the spectrum correlation area according to the reflection spectrum curve; and calibrating the color temperature of the spectrum correlation area according to the target color temperature value. According to the image color calibration method, the color temperature of the spectrum correlation area can be calibrated, global or local accurate color rendition of the multispectral image is achieved, and high-accuracy color rendition under the complex illumination condition is achieved.

The invention is suitable for the technical field of agriculture, and provides a fruit quality grading method and system based on a multi-modal model, which improves the grading precision and universality by constructing a multi-modal and multi-scale feature fusion system, directly obtains accurate physicochemical index parameters such as sweetness, pH, vitamin C concentration and the like, avoids spectrum inversion errors, and improves the quality of fruits. And an appearance and internal quality combined judgment basis is formed in combination with a double-view-angle image. Meanwhile, the cross-modal interaction relation is dynamically modeled, the modal weight is adaptively distributed, and the redundancy problem of an existing fusion means is solved. In addition, global attributes and local details are synchronously captured through a pyramid structure, fruits with large size differences are compatible, and the grading performance and compatibility of the system are remarkably improved. A hierarchical model is deployed in built-in edge computing hardware of fast detection equipment, and a full-link localization closed loop of data acquisition, feature extraction, hierarchical discrimination and result display is completed. Network dependence is eliminated, off-line real-time detection is supported, and the operation and maintenance cost is greatly reduced.

The application belongs to the technical field of agricultural remote sensing monitoring, and discloses a kind of saline-alkali soil wheat grain total phenol content remote sensing monitoring method and system, based on multi-source remote sensing data, extract weather and vegetation characteristics by phenology matching, construct protein content estimation model containing salt stress nonlinear inhibition term, and accordingly establish the quantitative relationship between protein and total phenol content, finally, high-precision total phenol content is obtained by using optimization algorithm inversion, and effective monitoring of large-scale saline-alkali soil wheat grain quality is realized.The application initiates the "protein content-total phenol content" secondary inversion architecture, indirectly realizes the total phenol content monitoring through the protein remote sensing inversion technology, effectively solves the technical problem of low direct spectral inversion precision;Innovatively establishes the specific stress response model of saline-alkali soil, the nonlinear inhibition effect of salt on crop physiological process is considered in the inversion process, which significantly improves the monitoring precision and model adaptability, and has the characteristics of high monitoring precision, strong practicability and wide application range.

The application discloses a SIF spectrum inversion method based on singular value decomposition and machine learning regression. The method comprises the following steps: step 1, acquiring sample radiance spectrum data, solar-induced chlorophyll fluorescence spectrum data corresponding to the radiance spectrum data and the like; step 2, performing singular value decomposition on a feature matrix, selecting a plurality of main singular vectors to construct a reconstruction base matrix, and calculating low-dimensional expansion coefficients of the fluorescence spectrum; step 3, performing singular value decomposition on the feature matrix; step 4, taking the low-dimensional feature coefficients of the radiance spectrum, preset key band radiance features, band ratio features and observation geometry features as input variables of a machine learning regression model; and step 5, inputting a sample to be inverted into the trained machine learning regression model. The application converts the high-dimensional solar-induced chlorophyll fluorescence spectrum inversion problem into a low-dimensional expansion coefficient prediction problem, and has the advantages of high inversion efficiency, strong model stability and suitability for popularization and application.

The invention provides a non-linear constrained time domain high-resolution spectrum inversion method, which relates to the field of seismic data broadband processing, and comprises the following steps: constructing a wedge-shaped model library composed of odd-even reflection coefficient pairs; in a time domain, carrying out convolution on the wedge-shaped model library and the wavelets to obtain a wedge-shaped model library responded by a simple layer; forming expected inversion seismic data through the combination of different layer responses; subtraction is carried out on the seismic data and an expected result, and an objective function is designed by applying L2-Cauchy constraint; solving a non-linear problem of regularization constraint by using a fast iterative shrinkage threshold algorithm to obtain a high-resolution reflection coefficient profile; and carrying out profile convolution shaping on the high-resolution reflection coefficient to obtain high-resolution wide-spectrum inversion seismic data. The method has the beneficial effects that the high-resolution reflection coefficient profile convolution shaping broadband wavelet is performed to obtain the high-resolution wide-spectrum inversion seismic data, the low frequency and the high frequency of the seismic data are compensated, and thin-layer information is effectively identified.

The invention discloses an all-sky background radiometer full-channel calibration method based on spectral inversion, and the method comprises the steps: obtaining a discrete response value of a non-absorption wave band of an all-sky background radiometer based on solar direct radiation and a Langley calibration method in combination with the solar irradiance of an atmospheric boundary layer, the atmospheric relative quality and a sun-ground distance correction factor; a solar direct radiation and gas absorption calibration method is utilized, a gas absorption effect is considered, and a discrete response value of an absorption wave band is calculated through inversion of the total amount of water vapor; determining a full-band discrete irradiance calibration coefficient based on the discrete response values of the non-absorption band and the absorption band; fitting by using the full-band discrete irradiance calibration coefficient and adopting an interpolation algorithm to obtain a full-band instrument irradiance calibration function; and transmitting an instrument irradiance calibration function to the direct incidence channel and the scattering channel, and obtaining radiance calibration coefficients of the direct incidence channel and the scattering channel in combination with the field angle and the attenuation coefficient of the optical filter, thereby completing full-channel calibration.

This invention discloses a three-dimensional shape reconstruction system and sensor fabrication method combining grating inversion technology, belonging to the field of fiber optic sensing technology. The system includes a shape sensor, a grating demodulation device, and a shape reconstruction device; a fiber bundle or multi-core fiber composed of several fiber grating strings is bonded to the outside of a substrate, but not completely bonded, only point-constrained, forming the shape sensor; the demodulation device acquires spectral information in real time; and the reconstruction device combines spectral inversion technology to accurately reconstruct and display the three-dimensional shape. This invention also includes a method for fabricating the shape sensor: first, fabricating the fiber bundle or multi-core fiber; second, placing the fiber bundle in a hollow flexible tube bonded to the side of the substrate, fixing only one end. This invention solves the problem of low spatial resolution in fiber grating shape sensing technology, and the shape sensor structure can eliminate strain on the outside of the substrate when the substrate is bent, protecting the optical fiber.

The invention provides a spectrum inversion high-resolution processing method based on strong axis stripping, and relates to the field of seismic exploration, and the technical scheme is that the spectrum inversion high-resolution processing method based on strong axis stripping is characterized by comprising the following steps: inputting original seismic data, and extracting strong reflection wave event seismic data; subtracting the extracted strong reflection wave event seismic data from the original seismic data to obtain seismic data after strong reflection suppression; replacing the original seismic data with the seismic data subjected to strong reflection suppression, and establishing a spectrum inversion objective function; and solving the spectral inversion objective function to obtain a high-resolution seismic section which suppresses strong reflected waves and highlights weak signals. The method has the advantages that a spectral inversion high-resolution processing mechanism based on strong axis stripping is clear, and time domain iteration deconvolution stripping of the strong reflection wave event, spectral inversion high-resolution processing stripping of the strong reflection wave event, strong reflection suppression and spectral inversion high-resolution thin layer recognition are involved.

The application provides a kind of optical fiber pressure sensor demodulation method and device for sensing ship-bridge impact force, and relates to the field of optical fiber sensing technology.The method comprises: constructing an optical fiber pressure sensor demodulation system, an initial multi-modal model based on a double-branch radial basis function neural network, and using a hybrid optimization algorithm including an improved adaptive particle swarm global exploration and an enhanced sparrow search local optimization.In the global stage, a nonlinear adaptive PSO is used to obtain the global optimal solution, and in the local stage, the solution is fine-tuned by SSA and dynamic refocusing is achieved using multi-modal monitoring to obtain the optimal solution of the model.The characteristic vector is input into the model, the analytic signal is obtained by Hilbert transform, the envelope is extracted by extracting the modulus, and the real-time pressure prediction value is output by the weighted fusion layer.The application can significantly improve the convergence speed and accuracy of nonlinear spectral inversion, and meet the demand for real-time and high robustness monitoring of local high pressure in ship-bridge impact scenarios.

The application relates to the technical field of optical communication, in particular to a method for suppressing low-frequency noise, which comprises the following steps: at a sending end, converting an input original service signal into a digital signal to obtain a digital signal sequence; performing a shaping filter operation on the up-sampled digital signal sequence by using a root-raised cosine filter, then performing a frequency spectrum inversion operation on the filtered digital signal sequence to obtain an inverted digital signal sequence; in a channel, transmitting the inverted digital signal sequence, and simultaneously introducing a low-frequency noise signal; at a receiving end, performing a frequency spectrum inversion operation on the digital signal sequence with the introduced low-frequency noise signal, then performing a root-raised cosine matching filter operation and a down-sampling operation to obtain and output a final digital signal. The application does not need to introduce additional devices, thereby reducing the cost of a communication system; the algorithm has low complexity, and the flexibility of suppressing the low-frequency noise is high; even if the low-frequency noise is randomly changed, the application still has a good suppression effect.

The invention provides an optical fiber pressure sensor demodulation method and device for sensing impact force of ship colliding with a bridge, and relates to the technical field of optical fiber sensing. The method comprises the following steps: constructing an optical fiber pressure sensor demodulation system, initializing a multi-modal model based on a double-branch radial basis function neural network, and adopting a hybrid optimization algorithm including improved adaptive particle swarm global exploration and enhanced sparrow search local optimization. In the global stage, nonlinear adaptive PSO is adopted to obtain a global optimal solution, and in the local stage, dynamic refocusing is achieved through SSA fine tuning and multi-modal monitoring, and a model optimal solution is obtained. And inputting the feature vector into a model, performing Hilbert transform to obtain an analysis signal, extracting a module value to obtain an envelope, and outputting a real-time pressure prediction value through a weighted fusion layer. According to the method, the convergence speed and precision of nonlinear spectral inversion can be remarkably improved, and the requirements for real-time and high-robustness monitoring of local high pressure in a ship and bridge collision scene are met.

The present invention relates to the field of garbage classification technology, specifically to an intelligent food waste classification system based on the Internet of Things. The system includes a node access module, an image preprocessing module, an edge structure judgment module, an oil-water ratio perception module, and a garbage type classification module. In the present invention, by combining node geographic identification and timestamps to achieve effective node status binding, the spatial traceability accuracy of garbage disposal behavior is improved, and the physical recognition accuracy of garbage components in the image is enhanced by linking image grayscale difference extraction with spectral reflectance calculation. Directional features are constructed by edge region gradient amplitude, and a texture consistency screening mechanism for continuous regions is combined to strengthen the target stability of edge features in the image. The spectral inversion processing of oil and water distribution in the image is completed by matching oil feature peaks and extracting moisture index thresholds, thereby improving the imaging recognition capability of typical food waste components, enhancing the reliability of food waste image recognition, and enhancing the automation level of the classification process.

The present invention discloses a red soil organic matter spectral inversion method and device that eliminates the influence of free iron. The method comprises: obtaining soil sample data, storing organic matter data into a set P, storing free iron content data of a typical red soil sample into a set F, storing spectral reflectance data of a red soil survey sample into a set H, and storing spectral reflectance data of a typical red soil sample into a set D; decomposing sets H and D using the MODWT algorithm to obtain stratified discrete detail coefficient sets CH and CD for the red soil survey sample and the typical red soil sample; removing the noise layer based on CD to obtain a valid layer discrete detail coefficient set C; calculating the correlation coefficient of each element in C with sets F and P, respectively, to screen out a characteristic band set CDG; selecting detail coefficients CHG located in the characteristic band from the stratified discrete detail coefficient set CH; constructing a prediction model and training it using CHG; and using the trained prediction model to predict organic matter content. The present invention can eliminate the influence of free iron oxide and is low-cost and highly efficient.

The application discloses a kind of infrared interference signal equal optical path difference interval reconstruction methods based on optical path difference model, belong to Fourier infrared spectrometer signal processing technical field.Method includes: to reference signal is filtered and transformed, and the extraction index of quarter wavelength interval is obtained by peak searching;Linear region and nonlinear region are determined using the Taylor expansion of optical path difference mathematical model;Infrared interference signal is directly sampled or interpolation correction in linear region at equal interval, and high times interpolation reconstruction is carried out in nonlinear region.The present application makes full use of the optical path difference mathematical model of rotating mirror spectrometer, overcomes the defects that the existing method only relies on reference signal, resulting in less sampling points, low precision, improves the sampling density and spectral inversion accuracy of equal optical path difference interval reconstruction.

The invention discloses a multi-axis differential gas analyzer data real-time transmission system and method, belongs to the technical field of multi-axis differential gas analyzer data real-time processing and transmission systems, and is used for multi-axis differential gas analyzer data real-time processing and transmission. The system comprises a spectrograph, an acquisition card, a storage module, a computer end, a wireless communication module, a core processing unit and a display terminal module, the method comprises the following steps: obtaining initial spectral information by adopting a filtering processing method, obtaining gas concentration data by adopting spectral inversion and a differential absorption algorithm, transmitting the data through the wireless communication plate, and visualizing the data on the display terminal. According to the invention, through a specific transmission mode, the collected original data is transmitted to the core processing unit, the core processing unit processes the original spectral data with a relatively large data volume to obtain the gas concentration data, and the gas concentration data processing speed is improved by a method of performing integration and de-noising processing by using a computer end; and the efficiency of the whole gas analysis data transmission process is improved.

The application discloses a kind of fusion multispectral inversion's semi-autonomous remote sensing water area generalization segmentation method, it is related to remote sensing image processing technical field, specific implementation scheme is as follows: acquisition remote sensing multispectral data;Remote sensing multispectral data and coordinate point prompt information are used as the input of end-to-end model, after being processed through multispectral inversion branch, generalization segmentation branch, cross-modal feature fusion, generate optimal water area segmentation mask;After morphological filtering and vector conversion, the optimal water area segmentation mask is converted into high-precision remote sensing water area segmentation vector result.The application embeds multispectral inversion and generalization segmentation depth into the same model structure, realizes the cooperation of spectral physical priori and semantic feature by three-stage progressive fusion, and utilizes GPU parallel computing optimization framework, significantly improves the labeling accuracy and calculation efficiency.

The application discloses a spectral inversion frequency expansion processing method based on stratum structure dimension reduction, obtains post-stack seismic data after preprocessing such as denoising and zero-phase; designs different simple thin-layer stratum structure forward models, establishes the relationship between the seismic response characteristics of different models and the corresponding waveform phase information; obtains odd and even component data reflecting different simple stratum structure thin-layer information and obtains seismic data after phase decomposition; based on the phase decomposition method, the dimension of the complex stratum structure is reduced by decomposing the seismic data, and the optimal solution is searched in the data space after dimension reduction, and accurate high-resolution seismic data is obtained. Compared with the prior art, the data space size of spectral inversion optimization is reduced, the reliability and stability of the spectral inversion frequency expansion result are improved, and the fine seismic reservoir characterization ability of the spectral inversion result, such as thin-layer identification, is enhanced.