100 results about "Background spectrum" patented technology

The invention discloses an intelligent water quality monitoring and pollution source identification method based on full spectrum analysis, and relates to the technical field of environmental monitoring optical sensing, and the method comprises the following steps: carrying out dynamic background stripping on a water body pollution metadata set to obtain a dynamic background spectrum, and building a spectrum purification model to carry out characteristic purification on the dynamic background spectrum to obtain a water body pollution data set; generating a pollution characteristic spectrum; performing multi-dimensional feature aggregation and hydraulic drive topology reconstruction on the pollution feature spectrum to generate a watershed pollution dynamic propagation relationship network diagram; performing physically constrained space-time convolution and propagation inversion on the watershed pollution dynamic propagation relationship network diagram to generate a pollution source probability distribution thermodynamic diagram; and carrying out responsibility association mapping on space anchor point coordinates of the pollution characteristic spectrum and pollution source center positioning of the pollution source probability distribution thermodynamic diagram, and generating a visual traceability report. Through dynamic background stripping and feature purification, high-fidelity extraction of pollution features under a complex optical background is realized, and the detectability of trace pollutants is remarkably improved.

The invention discloses a two-stage hyperspectral image band selection and target detection method, which comprises the following steps of: based on a two-stage band selection and background reconstruction network of a transformer, realizing band selection through a first-stage training transformer and realizing background reconstruction through a second-stage training transformer; a transform position coding module and a multi-head self-attention mechanism are used for learning similar features and difference features among wave bands, a full connection layer network is used as a clustering device, a structural similarity index and an Euclidean distance are added to serve as a loss function training model, wave band clustering is achieved, and finally a local variance is used for estimating the noise level of an image of each wave band. Obtaining a band training subset; the band subset is subjected to constraint energy minimization detection and then sent to a background feature extraction network composed of a transformer and a discriminator, background pixels are arranged through position coding, network learning background features are enhanced through a multi-head self-attention mechanism, an improved loss function is used for training, and therefore reconstruction of a background image is achieved. The invention provides a two-stage wave band selection and background reconstruction network based on transformer so as to realize hyperspectral target detection. The network comprises a first-stage wave band selection work and a second-stage background spectrum learning work. And difference detection is carried out on the final background reconstruction image and the original image, so that a final task is realized, and the detection precision is improved.

The invention belongs to the technical field of image processing, and particularly relates to an intelligent agricultural product pesticide residue detection method and system based on a spectrum technology, and the method comprises the steps: obtaining the hyperspectral reflectivity according to the original hyperspectrum, dark current and whiteboard image data; calculating an illumination confidence factor by using the average spectral intensity; performing linear scaling on the obtained standard biological matrix background spectrum according to the illumination confidence factor to obtain a local background estimated value and obtain a net residual spectrum; generating a pesticide residue distribution thermodynamic diagram by combining the cosine similarity of the net residual spectrum and the target pesticide standard fingerprint spectrum and the noise suppression weight based on the illumination confidence factor; and pesticide residue detection is carried out according to the statistical characteristics of the connected region of the suspected defect mask. Through adaptive background deduction and noise suppression, the problems of uneven curved surface illumination and strong background interference are solved, and the detection accuracy is improved.

The invention discloses a background spectrum accurate acquisition method for infrared remote measurement in a complex scene, and the method comprises the steps: carrying out the division of sky and ground object backgrounds for an input background image, and selecting different radiation spectrum generation modes based on a division result; if yes, sky radiation spectrum extraction is carried out based on an MODTRAN radiation transfer model; if the background is judged to be a single ground object background, performing background spectrum extraction by adopting ELM-EMD (Extreme Learning Mode-Empirical Mode Decomposition) which is extracted in real time based on a measurement spectrum and changes slowly at low frequency; and if the background is not single, fusion of the two spectrum extraction modes is adopted. The method has the advantages that the background classification method with the visible image as the reference is adopted, the difference of infrared radiation characteristics of the sky background and the ground feature background is analyzed, different spectrum extraction modes are selected according to the difference, and therefore accurate obtaining of the target smoke plume transmittance spectrum is achieved.

The invention relates to the technical field of data processing, in particular to a covariance inverse matrix recursive updating method for on-satellite hyperspectral anomaly detection, which comprises the following steps: acquiring a hyperspectral data stream; carrying out adaptive dimension reduction processing on the data stream and loading an initial background model; extracting local background statistics by adopting a sliding window mechanism, generating a background spectrum dictionary by utilizing online dictionary learning, calculating a reconstruction error between a current pixel and the dictionary and a Mahalanobis distance between the current pixel and a background model, and fusing to generate an abnormal score; performing abnormal confidence coefficient evaluation by combining the spatial context information and the spectral angle matching degree, and updating a spectral mean vector by using an exponential weighted moving average algorithm based on non-abnormal pixel data; and the updated model is injected into the next round of processing to form a recursive chain. According to the method, the high calculation complexity of direct inversion of a covariance matrix is avoided, real-time anomaly detection on a satellite is realized, the downloading amount of original data is remarkably reduced, and the congestion of a satellite-ground communication link is relieved.

The invention relates to the technical field of microbe traceability analysis, in particular to a microbe traceability analysis method based on an infrared absorption spectrum and a database, and the method comprises the following steps: acquiring absorbance spectral data: acquiring background spectral data for multiple times, performing background correction, acquiring spectral data of a sample containing a strain, and finally calculating the absorbance spectral data; preprocessing the absorbance spectrum data: smoothing the absorbance spectrum data by adopting an SG smoothing algorithm, and calculating a first-order derivative or a second-order derivative of the smoothed absorbance spectrum data to obtain an absorbance spectrum data set; spectral range selection: presetting different spectral ranges, and selecting different spectral ranges for analysis according to requirements; analyzing the similarity of the strains: analyzing the similarity of the absorbance spectral data set of the strains by adopting an improved hierarchical clustering algorithm; bacterial strain traceability analysis: determining a classification threshold by adopting a threshold determination algorithm, and judging microorganism traceability information; the traceability analysis precision is high, and the reliability, the stability and the practicability are high.

The invention discloses a household electrical appliance fault diagnosis system based on artificial intelligence, and relates to the technical field of household electrical appliance fault diagnosis and state monitoring. Working condition parameters aligned with a time window are obtained through working condition sensing, and fault features and the working condition parameters are linked in an order form to be converted into a target frequency track; fault characterization is converted into track characterization capable of being continuously tracked along with working conditions from a fixed frequency point, and disturbance to fault positioning in the speed change process is reduced; in order to solve the problem that weak fault components are covered by the same frequency band due to strong dynamic background noise jointly formed by inverter switch harmonic waves, current harmonic waves and load fluctuation, a dynamic noise reference spectrum is output under the current working condition through a condition generation model, and a current spectrum and the dynamic noise reference spectrum form a residual spectrum; the background spectrum base related to the working condition is suppressed, and the separability of the weak fault component in the residual domain is improved from the source.

The invention relates to a Mars mineral spectrum identification method and device based on deep learning. According to the Mars mineral spectrum recognition method based on deep learning, through four-dimensional constraints of standard deviation, spectral length, absorption depth and overall reflectivity, a background spectrum in an image is adaptively recognized, a ratio spectrum is calculated by taking a dynamic background spectrum as a reference, and interference of non-target factors such as atmospheric scattering and instrument noise can be effectively eliminated. The end member spectrum is directly extracted from the hyperspectral image, and the second ratio spectrum is combined with the preset standard spectrum library to construct the mixed spectrum library containing the Mars specific minerals, so that the data insufficiency of the preset standard spectrum library is made up, and the problem of poor regional adaptability caused by directly adopting the preset standard spectrum library is also avoided; that is, direct use of the earth spectrum library may not accurately reflect the Mars surface features, so that the adaptability of the model to the Mars surface is improved, and it is ensured that the model has higher recognition accuracy in a specific environment of Mars.

The invention discloses a coal composition and gangue rapid identification method in an intelligent coal dressing process, and relates to the technical field of photoelectric detection. The method comprises the following steps: acquiring an original spectral signal and a belt background spectrum, and preprocessing and calibrating the original spectral signal to obtain a current material spectrum; whether belt background interference exists in the current material spectrum or not is judged through spectrum similarity calculation, if the belt background interference exists, a belt signal proportion coefficient alpha is obtained through quantification based on a preset linear spectrum mixing method, and a belt background existence mark is set to be true; the alpha is compared with a preset interference threshold value, when the alpha is higher than the interference threshold value, spectrum background correction is carried out on the current material spectrum, and a corrected material spectrum is obtained; interference of belt reflection on material spectrums can be effectively eliminated, real spectral characteristics of the thin coal seam are completely recovered, and coal resources are prevented from being mistakenly eliminated as gangue.

The invention provides a numerical control machining tool wear multispectral imaging detection method and system. The method comprises the steps that a three-dimensional data cube is constructed through a multispectral image sequence of a tool machining area; defining a spectrum detection window of each pixel point in the three-dimensional data cube, dividing the spectrum detection window into a main detection sub-block and auxiliary detection sub-blocks, and generating a spectrum difference feature map based on a difference relationship between a spectrum curve of each pixel in the main detection sub-block and an average spectrum curve of all the auxiliary detection sub-blocks; determining a projection vector according to a target spectral feature in the center detection sub-block and a background spectral feature in the local detection window; and determining a spectral feature map according to the projection vector and the three-dimensional data cube, and recognizing an abnormal wear area in the tool machining area according to a multidirectional gradient feature map constructed by a spatial gradient operator corresponding to each pixel in the spectral feature map and a spectral difference feature map. According to the technical scheme provided by the invention, the subtle difference between the wear region and the background region can be distinguished in a multi-dimensional interference state.

The invention discloses a satellite hyperspectral hydrocarbon pollution monitoring and tracing method and system, and the method comprises the steps: obtaining and preprocessing hyperspectral satellite data, defining a potential pollution region ROI and a pure background spectrum library, extracting hydrocarbon pollution spectral features through a direct and indirect method, and achieving the extraction of pollution information through combining with an intelligent model. And finally, dynamic monitoring, tracing and early warning are carried out. The system correspondingly comprises a data acquisition and preprocessing module, an ROI and background spectrum library construction module, a spectrum feature enhancement and extraction module, a hydrocarbon pollution intelligent extraction module, and a dynamic monitoring traceability and early warning and result output module. According to the method, pollution can be directly identified according to spectral characteristics of hydrocarbon molecular bonds, the monitoring range is wide, the cost is low, the efficiency is high, hydrocarbon pollution monitoring and tracing can be achieved, and powerful support is provided for environment supervision and enterprise self-inspection.

The present application relates to water quality detection and analysis technical field, specifically to a kind of water total phosphorus multi-parameter synchronous detection method based on water, comprising: after the original water sample is pretreated, the standard test solution obtained is simultaneously introduced into parallel digestion tank and optical cell, and the digestion and conversion of phosphorus compound and the collection of water sample background spectrum are completed synchronously.Digestion liquid is distributed to multiple independent color developing channels, each channel uses characteristic color developing agent configured for different concentration interval or interference condition, concurrent color developing reaction is carried out under the same environment, and the reaction kinetics time sequence spectrum of each channel is collected.The background spectrum and all kinetic spectrum sequences are input into integrated calibration model for data fusion and cross analysis, and total phosphorus content detection result is directly output.The method realizes wide concentration range, high anti-interference capability of water total phosphorus rapid and accurate detection by parallel acquisition of homologous background information and multi-reaction channel kinetic data.

The present invention relates to a method and device for identifying Martian mineral spectra based on deep learning. The Martian mineral spectra identification method based on deep learning uses four-dimensional constraints, namely, standard deviation, spectrum length, absorption depth, and overall reflectivity, to adaptively identify background spectra in images, and calculate ratio spectra based on dynamic background spectra, effectively eliminating interference from non-target factors such as atmospheric scattering and instrument noise. By directly extracting endmember spectra from hyperspectral images and combining the second ratio spectrum with a preset standard spectrum library, a mixed spectrum library containing Martian-specific minerals is constructed, thereby making up for the lack of data in the preset standard spectrum library and avoiding the problem of poor regional adaptability of directly using the preset standard spectrum library, that is, directly using the Earth spectrum library may not accurately reflect the surface characteristics of Mars, thereby improving the adaptability of the model to the Martian surface and ensuring that the model has higher recognition accuracy in the specific environment of Mars.

A method and system for detecting computer network data leaks over optical channels, for example using a mobile phone or other handheld device to rapidly scan a room with many light sources to identify the hidden transmission of data via optical steganography. The method of identification leverages spectral divergence created by the entropy produced by steganographically embedding data in the optical channel. The method and system proceed through multiple steps that can be computed in near real-time to eliminate background spectrum effects and isolate likely sources of information. The user or automated detection system captures a short video, and the video frames are then subdivided into smaller blocks effectively producing many adjacent videos of smaller pixel area.

The invention relates to the technical field of rock core spectral analysis, in particular to a method, a device and equipment for detecting the original oil content of a rock core drilled by oil-based drilling fluid, and the method comprises the following steps: firstly, based on local waveform similarity of a rock core and a drilling fluid spectrum, accurately quantifying a wavelength-level oil-based interference degree and determining a fusion weight; constructing a drilling fluid fusion spectrum sequence reflecting the current rock core pollution characteristic, then finely correcting the rock core spectrum, and detecting the original oil content of the rock core according to an obtained corrected spectrum curve and a pre-constructed spectrum peak area-crude oil component volume percentage content relation equation; according to the method, the heterogeneity of the drilling fluid and the wavelength interference difference are fully considered, accurate denoising is implemented by constructing the self-adaptive background spectrum, the problem of excessive signal removal or residual caused by a traditional global difference method is effectively avoided, the corrected spectrum curve after correction can restore the original characteristics of the rock core more truly, and the accuracy of the rock core is improved. The accuracy of detecting the original oil content of the polluted rock core is obviously improved.

The present application relates to the technical field of electronic module detection, and discloses a method, system and storage medium for analyzing the state of smart furniture based on the Internet of Things. The method regularly collects the first sound data of the electronic module within a set time period, and performs spectrum conversion on it to obtain first spectrum data. At the same time, a background sound library of the environment in which the electronic module is located is obtained, which contains background sound data and corresponding background spectrum data. The first spectrum data is then filtered based on the background spectrum data to obtain second spectrum data. Thereafter, the incremental frequency, incremental energy, average value and discrete value of the incremental frequency, and cumulative value and fluctuation value of the incremental energy of multiple second spectrum data are calculated. The frequency confidence value and energy confidence value are then calculated using these values, and then a comprehensive confidence value is obtained. If the comprehensive confidence value is greater than the preset reference confidence value, a status abnormality prompt is issued, thereby achieving effective monitoring and early warning of the operating status of the electronic module of the smart furniture.

The present application relates to the technical field of gas detection, in particular to a real-time mass spectrum analysis system for detecting volatile gas components of grain, which comprises a sample spectrum acquisition unit for obtaining original sample spectra at different depths, then weighting each depth original spectrum according to preset weight, and outputting characteristic fingerprint spectrum; a differential background suppression unit for acquiring real-time background spectrum, and using a closed-loop adaptive multi-scale background suppression method to remove background ion signals of the original sample spectrum based on the real-time background spectrum and the characteristic fingerprint spectrum, and generating a net characteristic spectrum without background; and a target VOC determination unit for determining target VOC in the grain pile based on the net characteristic spectrum through a triple verification mechanism. The system improves the recognition sensitivity and quantitative accuracy of the system for low-concentration target volatile compounds, enhances the adaptability and robustness of the system in a complex grain storage environment, and effectively avoids the misjudgment and missed detection problems existing in traditional methods.

The invention discloses a hyperspectral camouflage fiber fabric based on a flocking technology. The hyperspectral camouflage fiber fabric comprises an ultra-black fluff layer, an adhesive layer, a near-infrared absorption layer and an ultra-black base cloth layer which are sequentially arranged from top to bottom. Through a multi-layer synergistic structure, the fitting degree of the material and an ocean background spectrum at the wave band of 400-2500nm reaches 0.91 or above, the characteristics of weak reflection of visible light and strong absorption of near infrared light are reproduced, the problem of poor matching precision is solved, hyperspectral reconnaissance is avoided, and the concealment of ocean equipment is improved. The invention has the advantages of strong environmental adaptability, easy mass production, humidity and heat resistance of grade 1, no abnormity at-20 DEG C to 50 DEG C, and color fastness to sunlight of grade 5, and adapts to complex marine environment; based on a mature flocking technology, complex equipment is not needed, large-scale production can be achieved, and stability and economical efficiency are both considered.

The application discloses a hyperspectral remote sensing image target detection method based on target-background reconstruction deviation, comprising the following steps: acquiring a to-be-detected hyperspectral remote sensing image, inputting the pre-trained asymmetric auto-encoding network, and obtaining the first output and the second output of each pixel in the image; the pre-trained asymmetric auto-encoding network comprises a feature extraction subnetwork, a feature fusion subnetwork and a feature reconstruction subnetwork; the first output is the output of the feature extraction subnetwork, and the second output is the output of the feature reconstruction subnetwork; the pre-trained asymmetric auto-encoding network is obtained by training a mixed target spectrum and a mixed background spectrum; the mixed target spectrum and the mixed background spectrum are generated based on a first hyperspectral remote sensing sample image, a prior spectrum of a preset target and a bilinear spectrum mixing model; according to the first output and the second output, the spectral angle distance of the pixel is determined; and the spectral angle distance is smoothed to obtain the detection result of the to-be-detected hyperspectral remote sensing image.

The invention discloses an LCoS box thickness measuring method and equipment. The device comprises a light source, a fiber optic spectrometer, a communication module and a calculation module. The measuring method comprises the following steps: 1, acquiring an environment dark spectrum and a spectrum of a light source by a fiber optic spectrometer; 2, light of each wavelength enters each pixel point of the LCoS device, forms two beams of coherent reflected light on the surfaces of the upper substrate and the lower substrate respectively, and enters the optical fiber spectrometer; 3, the communication module automatically obtains the model and serial port information corresponding to the spectrograph; 4, the communication module transmits the spectral data back to the data calculation module, filters the input data and compares the filtered data with a background spectrum to obtain an interference spectrum; and 5, automatically identifying the interference spectrum waveform by a calculation module, and calculating to obtain the box thickness and the box thickness uniformity of the LCoS device. The LCoS box thickness measuring equipment is simple in composition and convenient to use, the measuring method is high in automation degree, the LCoS box thickness measuring efficiency and precision can be remarkably improved, and the practical engineering significance is achieved.

This invention discloses a class of novel small-molecule fluorescent compounds based on thiazolyl-2-pyridone rings and their applications in analytical detection and diagnostics. The small-molecule fluorescent compounds of this invention have novel structures, readily available starting materials, mild synthesis conditions, and high yields. Some of the obtained compounds are responsive to amines, hydrazine, hypochlorite, and bisulfite, and are expected to serve as detection probes for these compounds. Other compounds exhibit long fluorescence emission and large Stokes shifts, effectively avoiding background spectral interference, generating Type I reactive oxygen species, and possessing near-infrared emission characteristics, showing potential as Type I photodynamic therapy photosensitizers.

The invention discloses a hyperspectral video target tracking method based on depth spectrum target perception features, and the method comprises the steps: determining a target region Tt of a tth frame of hyperspectral image after normalization; determining a selected local area # imgabs0 # in the first frame of hyperspectral image Tt, determining a maximum spectrum curve # imgabs1 # and a minimum spectrum curve # imgabs1 # through the spectrum curve of each pixel, and comparing the pixel spectrum curve of the search area with # imgabs3 # of # imgabs2 #; segmenting the image into a target area and a background area, obtaining a target spectrum curve Co and a background spectrum curve Ck, obtaining a spectrum curve of each pixel point in a search area, carrying out dimension reduction processing on the spectrum curve to obtain a band graph after dimension reduction, extracting depth features and edge features of the image, covering the depth features and the edge features with a spectrum mask in dimension reduction, and obtaining a band graph after dimension reduction; obtaining a target sensing feature P, obtaining a weight of each spectrum channel according to an information entropy curve of the P, multiplying the weight with the P of the corresponding channel to obtain a spectrum target sensing feature # imgabs4 #, performing pixel-by-pixel convolution on the spectrum target sensing feature # imgabs4 # and the depth feature E to obtain a depth spectrum target sensing feature Uz, sending the Uz of a first frame image into a CACF filter to train a template, and obtaining a target sensing feature P; uz of the (t + 1) th frame of hyperspectral image is sent to a filter template to obtain a response graph, confidence determination and scale estimation are carried out on the response graph, a tracking target of the current frame of hyperspectral image is obtained, and whether the (t + 1) th frame of hyperspectral image is updated or not is judged according to confidence determination.

The present invention discloses a camouflaged target detection method and device based on spectral variation augmentation. The method first obtains a background spectral variation dictionary and a target spectral variation dictionary based on a hyperspectral image. The background spectral variation dictionary and the target spectral variation dictionary are then merged to form a joint spectral variation dictionary. The joint spectral variation dictionary is then used to expand the background dictionary and the target dictionary, respectively, to form an extended background dictionary and an extended target dictionary. Based on collaborative representation, the extended background dictionary and the extended target dictionary are used to reconstruct a test sample, respectively. The reconstruction errors of the extended background dictionary and the extended target dictionary are calculated. The reconstruction errors of the extended background dictionary and the extended target dictionary are then used to determine whether the test sample is a camouflaged target. This method increases the diversity of spectral variations in the dictionary, addressing the limited diversity of spectral variations in the dictionary caused by a small number of samples and spectral variations, thereby improving the detection accuracy of the method.

The invention belongs to the technical field of gas detection, and discloses a TDLAS-based mine confined space gas concentration adaptive detection method. Comprising the following steps: S1, acquiring environmental parameters and approximate background spectral signals of a mine confined space, performing composite analysis, and determining current control parameters of a laser based on output wavelength drift compensation amount; s2, driving a laser to output wavelength by applying the current control parameter, scanning a characteristic absorption spectral line area of the target gas, obtaining an initial absorption signal, and analyzing and determining a gain absorption signal of the target gas; s3, performing secondary harmonic detection and phase-locked amplification treatment on the gain absorption signal to generate a pure absorption spectral line of the target gas, determining an initial concentration value of the target gas based on characteristic parameters of the pure absorption spectral line, and performing further analysis to obtain a real-time concentration value of the target gas; and S4, generating a parameter instruction or a standard exceeding early warning signal based on the real-time concentration value of the target gas, and providing stable signal guarantee for concentration inversion.

The embodiment of the application provides a kind of miniature infrared spectrometer and electronic equipment, for environmental monitoring, biological medical treatment, food safety etc..The spectrometer additionally increases narrow-band light source, for emitting second light beam, by micro stepping motor control plane grating, the first background spectrum and second background spectrum are generated in linear array detector by the second light beam spectrophotometry;In addition, the first light beam is emitted to the surface of the object to be measured by wide spectrum light source and occurs diffuse reflection, by micro stepping motor control plane grating, the first mixed spectrum and second mixed spectrum are generated in linear array detector by the mixed light beam spectrophotometry of first light beam and second light beam.Finally, the spectrum of the object to be measured is determined by the spectrum of narrow-band light source, first mixed spectrum and second mixed spectrum, and first background spectrum and second background spectrum by linear array detector.The technical scheme of the application can further compress the volume of spectrometer, reduce cost, and also can realize wide spectral range detection.

The invention relates to the technical field of new material related services, and discloses a spectral analysis-based paint noxious substance rapid detection method and a spectral analysis-based paint noxious substance rapid detection system, the method comprises the following steps: spreading a liquid paint into a test liquid film with a standard thickness, and collecting a full-wave band static background spectrum; applying non-contact pulse heat shock disturbance to the test liquid film, and establishing a heat diffusion non-equilibrium field; capturing a dynamic time-varying spectrum set of the test liquid film, and extracting an absorbance transient change rate of the dynamic time-varying spectrum set; based on the absorbance transient change rate and the energy attenuation gradient of the thermal diffusion non-equilibrium field, constructing a thermal spectrum dynamic separation map; analyzing a high-frequency response region of the thermodynamic separation spectrum, and locking a specific decoupling spectrum of the paint noxious substances; and inverting the mass fraction of the coating harmful substances based on the integral intensity of the specific decoupling spectrum to obtain a detection result report. According to the method, the field rapid screening efficiency of the coating harmful substances can be improved.

The application discloses a hyperspectral image target detection method based on spectral mask driving background learning, and belongs to the field of remote sensing image processing. The scheme is as follows: background sample screening is performed on an original hyperspectral image, and high-confidence background samples obtained are used as training samples of a network; a band mask is constructed for the obtained background spectrum as a mask training sample; two parallel automatic encoder networks are constructed, and the original background spectrum sample and the background spectrum sample subjected to the mask are used for training the two automatic encoder networks respectively; a constraint loss is constructed between the encoder outputs of the two automatic encoders during training; and the reconstruction error of a reconstructed hyperspectral image of the automatic encoder trained by using the original background spectrum is calculated and used as a detection result. The application can fully utilize background spectrum information, improve the target detection precision of the hyperspectral image, and can be used for target reconnaissance, mineral exploration and field search and rescue.

The invention relates to the technical field of electronic module detection, and discloses an intelligent furniture state analysis method and system based on the Internet of Things, and a storage medium, and the method comprises the steps: collecting first sound data of an electronic module in a set time period, and carrying out the frequency spectrum conversion of the first sound data to obtain first frequency spectrum data; meanwhile, a background sound library of the environment where the electronic module is located is obtained, and background sound data and corresponding background spectrum data exist in the library; filtering the first spectrum data according to the background spectrum data to obtain second spectrum data; calculating incremental frequencies, incremental energy, an average value and a discrete value of the incremental frequencies, and an accumulated value and a fluctuation value of the incremental energy of the plurality of second frequency spectrum data; and a frequency confidence value and an energy confidence value are calculated through the numerical values, so that a comprehensive confidence value is obtained. And if the comprehensive confidence value is greater than a preset reference confidence value, state abnormity prompting is carried out, so that effective monitoring and early warning of the operation state of the intelligent furniture electronic module can be realized.

The application discloses a target and background spatio-temporal spectrum similarity analysis system and method, which comprises a spectrum pretreatment module, a spectrum feature extraction module, a spatio-temporal variation rule analysis module and a similarity analysis module; target and background spectra are transmitted to the spectrum feature extraction module after being processed by the spectrum pretreatment module; the spectrum feature extraction module extracts features of the spectra and quantifies differences, and then transmits the features to the spatio-temporal variation rule analysis module; the spatio-temporal variation rule analysis module analyzes the spectrum feature differences with the spatio-temporal variation rule, and transmits the variation rule to the similarity analysis module; the similarity analysis module combines the spectrum feature differences with the spatio-temporal variation rule, assigns weights to each feature, and comprehensively obtains a similarity value to grade the spectrum similarity. The application considers the influence of the time dimension and the space dimension on the spectrum features, combines the spectrum features with the variation rule to assign weights, and realizes the expansion of traditional static spectrum features to the analysis system and method of a dynamic scene.

The invention provides an adhesive component quantitative detection method and system based on spectral analysis, and relates to the technical field of analysis and detection.According to the method, near infrared spectral data of an adhesive sample are obtained, and environmental background spectral data are synchronously collected for background correction, so that interference is eliminated. And performing signal enhancement processing on the corrected data, extracting spectral features under different scales, and separating overlapped absorption peaks. In the decomposition process, for the possible layering or interfacial effect of the adhesive, an interfacial feature enhancement treatment is introduced to focus on the absorption features of the internal layered structure. A compensation factor of flow-induced spectral distortion is introduced based on the transmission speed of the production line, and characteristics related to the internal structure are corrected. And combining the corrected characteristics into a set, inputting the set into a quantitative prediction model established through supervised learning in advance, and outputting the concentration value of the adhesive component, so that high-precision quantitative detection of the adhesive component can be realized.