46 results about "Spectral angle" patented technology

The invention discloses a multispectral image panchromatic sharpening method based on plug-and-play gradient feature guidance fusion, through effective extraction and integration of gradient guidance features (GRAD), excellent recovery results are obtained in the aspects of structural fidelity, detail retention and spectral consistency, and in addition, the method has the advantages of being simple in structure and convenient to use. Gradient feature guidance is fused and designed into a highly flexible plug-and-play method, and the existing architecture can be seamlessly enhanced. In particular, the present invention explicitly models a GRAD by integrating fine spatial details of a high resolution PAN with intrinsic spectral information of an MSI. Meanwhile, an attention mechanism and learnable weighting and residual connection are adopted, and selective aggregation and adaptive fusion of image information are realized, so that the MSI quality is remarkably improved. In addition, the GRAD is systematically analyzed from the aspects of structure, detail and spectrum, and the result is optimized through a multi-objective loss function. In this way, gradient information is fully mined, high-frequency details are captured, cross-modal structure guide alignment is achieved, panchromatic sharpening of the multispectral image is flexibly and efficiently achieved, and the panchromatic sharpening performance is improved.

The invention provides a textile surface defect detection method and system based on image features, and relates to the technical field of textile surface defect detection.The method comprises the steps that an RGB image of a to-be-detected textile is obtained and zoomed to 512 * 512 pixels, and then at least five semantic tags are output through a semantic segmentation model; the method comprises the following steps: adopting hyperspectral imaging with the wavelength of 400-1700 nm and the resolution of 10 nm, calculating the pixel reflectivity through a reflectivity formula, comparing the reflectivity of 5-8 characteristic wavebands, marking as a pollutant if the average deviation exceeds a threshold value, matching the type and position of a stain with a spectral angular distance, and after a standard sample and a semantic region are converted into an LAB color space, extracting a minimum rotation enclosing rectangle and dividing a grid, invalid pixels are filled with 3 * 3 neighborhood effective pixel weighted mean values, and a grid LAB mean value is calculated. A grid pollutant pixel corresponding to an image to be detected is filled with a standard sample in a mean value mode, then channels A and B are clustered through a sliding window, a pilling area is preliminarily judged according to the standard deviation of a channel L, and the pilling area is confirmed by combining the structured light three-dimensional point cloud and comparing with a threshold value.

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.

A polarization hyperspectral target classification method, system and device based on pixel-level adaptive fusion and a medium, the method comprising: performing spectral angle, spectral information divergence, root-mean-square error and red-edge spectral difference index calculation on a non-polarization hyperspectrum of each pixel and each polarization hyperspectrum to obtain m classes of similarity indexes under k polarization channels; converting the pixel-level similarity images into pixel-level similarity images, and stacking the pixel-level similarity images according to feature dimensions to form a pixel-level multi-dimensional similarity feature stack; performing standardization processing on each pixel, selecting K components with the highest characteristic values by adopting a pixel-level Top-K adaptive weighting strategy, and calculating weights according to scale coefficients to generate a single-channel weight map; performing multiplicative modulation processing on the non-polarization hyperspectral data to obtain fused polarization hyperspectral data; inputting the data into a classification recognizer for classification, and outputting a classification result; the system, the equipment and the medium are used for implementing the method. According to the invention, the classification precision and the anti-interference capability are improved.

The invention discloses a digital surface model (DSM)-guided hyperspectral and LiDAR combined unmixing method, relates to the field of multi-modal image processing, and aims to solve the problems of end member confusion and insufficient space structure maintenance caused by spectrum similarity in hyperspectral unmixing. According to the method, a hyperspectral image and LiDAR data of the same area are obtained, a LiDAR elevation map is expanded into a multiband profile through an attribute configuration file method, and a digital surface model (DSM) is generated. Constructing a spectrum and space double-branch auto-encoder, respectively extracting spectrum and space features and carrying out fusion mapping, obtaining an abundance matrix by using a normalized exponential function, and reconstructing a hyperspectral image; a double-branch adaptive mixed channel attention mechanism is designed in a spectrum branch, and a space attention mechanism is introduced in a space branch. In the training process, a self-defined loss function is formed by combining DSM-guided structure entropy regularization, spectral angular distance and root-mean-square error, and the space continuity and boundary retention of the abundance graph are improved. The method is suitable for hyperspectral unmixing and multi-modal remote sensing fine identification under complex terrains.

The invention relates to the technical field of image processing, and discloses a sulfur hexafluoride ring main unit gas leakage detection method and system based on thermal imaging, and the method comprises the steps: obtaining an infrared thermal imaging multispectral sequence image of a ring main unit; identifying a plurality of candidate regions of the multispectral sequence image, selecting a gas reference region, and calculating an average multispectral vector of the gas reference region as a gas reference spectrum; calculating the intra-group variance of each spectrum channel, and determining a weight vector and an angle threshold value; calculating a weighted spectral angle between the multispectral vector of the pixel point to be detected and the gas reference spectrum; judging the to-be-detected pixel point which simultaneously meets the following conditions as a gas leakage point: the weighted spectral angle is smaller than an angle threshold value, and the temperature of the to-be-detected pixel point is lower than a preset temperature threshold value; and generating a visual image of the gas leakage area according to all the judged gas leakage points. According to the invention, the anti-interference capability of detection is improved, and reliable identification of sulfur hexafluoride gas leakage can be realized under a complex background.

A metrology system may include a dual frequency comb source providing a first comb beam having a first repetition rate and a second comb beam having a second repetition rate; a beam splitter to generate one or more dual-frequency comb illumination beams from the first comb beam and the second comb beam; and a beam combiner to form a dual frequency comb illumination beam from the first comb beam and the second comb beam. The system may further include an illumination subsystem to illuminate a sample with the dual frequency comb illumination beam through an objective; a light collection subsystem to collect sample light from the sample with the objective lens; and a detector to capture a radio frequency signal based on the sample light. The system may further extract spectral measurement data associated with the sample from the radio frequency signal and generate a metrology measurement based on the spectral measurement data.

The invention discloses a precision sheet metal part visual detection system, and relates to the technical field of precision sheet metal detection. According to the system, a hardware architecture comprising a low-temperature adaptive industrial camera, a hyperspectral imaging module and a pre-stored multi-model feature fingerprint database is built; according to the method, image compensation of temperature difference value dynamic adjustment, model automatic identification of material spectrum and shape topology double-fingerprint matching, defect detection of combining spectrum angle matching with visual images, LSTM time sequence defect early warning integrated with temperature data and non-stop incremental model optimization of a frozen backbone network are matched, and a whole-process automatic detection scheme is constructed. Image blurring caused by low temperature is effectively eliminated, multiple types of sheet metal parts are quickly and accurately adapted, the defect misjudgment risk is greatly reduced, the defect development trend is warned in advance, the high recognition precision of the model is continuously maintained, the detection efficiency and precision are remarkably improved, the production loss is reduced, and the precision detection requirement of core components of cold chain equipment is fully met.

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.

This invention provides an abundance decomposition method, system, device, and storage medium applicable to remote sensing images. The abundance decomposition method includes: iteratively clustering the remote sensing image using a spatial adjustment factor and a spectral feature weight adjustment factor to obtain multiple blocks; for each block: calculating the data field strength and potential energy of each pixel; selecting the pixel with the highest potential energy as the representative pixel and obtaining the spectral angles of the remaining pixels based on its spectral response; obtaining the spectral angle judgment result based on a preset angle threshold, and processing it to obtain the component proportion of the pixel. This invention, through the energy field principle, realizes a limited correlation between the data features of the spectrum and the spatial distribution features of the spectrum, making up for the shortcomings of traditional linear spectral mixing models that cannot reasonably utilize spatial feature information; at the same time, compared with traditional methods, it utilizes the energy field principle to reduce the complexity of the algorithm in the abundance decomposition process, improve the efficiency of unmixing calculation, and also improve the decomposition accuracy.

This invention discloses a method for detecting the aging state of asphalt pavement by integrating hyperspectral imagery and deep learning, relating to the field of deep learning technology. The method includes: acquiring and preprocessing hyperspectral images of the target road section to obtain surface reflectance images; dynamically identifying and masking vehicles and their shadows in the images using a spectral angle matching method to extract effective pixel spectral datasets; performing hybrid pixel decomposition on the effective pixel spectral datasets using a non-negative matrix factorization algorithm to obtain asphalt endmember spectra and aggregate endmember abundance maps; inputting the asphalt endmember spectra into a pre-trained oxidation degree assessment model to output asphalt oxidation degree values; overlaying the aggregate endmember abundance map with near-infrared band images and inputting it into a pre-trained exposure rate segmentation network to output a binary mask of aggregate exposure areas and calculate the aggregate exposure rate. This method solves the technical problem that existing technologies cannot quickly and non-destructively detect the aging state of asphalt pavement.

The purpose of the present disclosure is to reduce erroneous detection of a false image caused by sidelobes and also minimize the deterioration of angular resolution by appropriately using a window function when detecting a target using a radar.　A target angle detection device 2 comprises: an angle spectrum calculation unit 21 that performs digital beamforming on the same reception signal of a radar array antenna by using first and second window functions having different sidelobe suppression levels, and calculates first and second angle spectra, respectively; a differential spectrum calculation unit 22 that calculates a differential-intensity spectrum on the basis of the first and second angle spectra; and a target angle detection unit 23 that detects a target at a spectral angle where the spectral intensity lies within a predetermined range on the basis of the differential-intensity spectrum, and determines that what is detected is a false image rather than the target at spectral angles where the spectral intensity lies outside the predetermined range.

The application discloses a kind of precision sheet metal parts visual inspection systems, it is related to precision sheet metal detection technical field;The system is built by including low-temperature adaptation industrial camera, hyperspectral imaging module and pre-stored multi-model feature fingerprint library Hardware architecture, cooperate with temperature difference dynamic adjustment Image compensation, material spectrum and shape topology double-fingerprint matching Model automatic identification, spectrum angle matching combined with visual image Defect detection, integrate temperature data LSTM time series defect early warning, and frozen backbone network Non-stop incremental model optimization, build full-process automated detection scheme. Effectively eliminate the image blur caused by low temperature, quickly and accurately adapt to multiple models of sheet metal parts, significantly reduce the risk of defect misjudgment, early warning of defect development trend, continuously maintain high recognition accuracy of model, significantly improve detection efficiency and accuracy, reduce production loss, fully meet the precision detection needs of cold chain equipment core components.

The invention relates to the technical field of image processing, in particular to a liquid crystal filtering multispectral image generation method based on quantum inspiration. According to the invention, a quantum inspiration optimization structure is combined with liquid crystal filtering hardware, the filtering parameter optimization speed and precision are improved by referring to quantum superposition and parallelism characteristics, and the spectral band dynamic switching is realized by using the electrically-controlled adjustable characteristic of liquid crystal filtering; the problems that a traditional mechanical filtering structure is poor in adjustability and low in integration level and a traditional algorithm is low in high-dimensional data processing efficiency are solved, and high-quality original signals and efficient calculation support are provided for multispectral image generation. According to the method, an image quality analysis and feedback mechanism is constructed, the image quality is evaluated based on parameters such as spectral angular distance and residual noise energy, bad images are fed back to an optimization link to be reprocessed, an optimization frequency threshold value is set to avoid invalid circulation, the quality stability of output images is effectively guaranteed, and the method is suitable for large-scale popularization and application. And the problems of spectrum distortion, noise and difficulty in balancing details are solved.

The invention discloses a non-photosynthetic vegetation automatic extraction method based on spectral angle mapping driving, and relates to the field of vegetation and soil hyperspectral data application and monitoring, and the method comprises the steps: carrying out field vegetation soil spectral data sampling and region division; the hyperspectral data are convolved into wavebands under different sensors, and hyperspectral and multispectral information fusion is realized; integrating band information reference sampling region division into a spectral angle to serve as a reference band reference spectrum of the spectral angle; a spectrum angle and a spectrum mixed analysis model are fused and established, an optimal spectrum end member value is automatically obtained through the spectrum angle according to input remote sensor waveband data, then the spectrum mixed analysis model is input to separate bare soil, photosynthetic vegetation and non-photosynthetic vegetation, and identification information of all pixels is specifically obtained. According to the method disclosed by the invention, the naked soil, the photosynthetic vegetation and the non-photosynthetic vegetation in different ecological environments are identified and separated based on the fusion of the spectrum angle and spectrum mixed analysis model through the difference of hyperspectrums of different ground features.

This invention proposes an intelligent landslide identification method based on changes in remote sensing semantic embedding. The method includes collecting annual remote sensing semantic embedding data, optical remote sensing imagery, digital elevation models, and land cover data for the study area; constructing physically feasible landslide identification areas constrained by both slope and land cover; calculating and standardizing the intensity of land cover semantic changes in adjacent years; generating annual vegetation index results based on growing season optical remote sensing imagery to produce landslide anomaly intensity results; extracting strong landslide candidate areas using adaptive thresholding; automatically generating potential and non-landslide samples, and optimizing the samples based on time-series normalized vegetation index and spectral angle measurements; and finally, using supervised classification methods such as random forest to achieve landslide identification and obtain the final landslide classification map. This invention realizes a complete intelligent landslide identification process, from anomaly identification of changes in remote sensing semantic embedding, automatic extraction of strong landslide candidate areas, automatic sample optimization, to supervised classification mapping.

The invention discloses a tracing identification method for industrial wastewater in a municipal pipe network based on a three-dimensional fluorescence spectrum angle algorithm. The tracing identification method is characterized by comprising the following steps: collecting industrial area municipal pipe network confluence well water outside a factory, industrial wastewater raw water in the factory, treated industrial wastewater and a water sample of an enterprise inspection well; mixing the municipal pipe network confluence well water with the industrial wastewater raw water, the treated industrial wastewater and enterprise inspection well water in the factory according to a series of different proportions to obtain three-dimensional fluorescence spectrum data of water samples with different mixing proportions; reading the three-dimensional fluorescence spectrum data obtained after correction in the step 1 in a python environment, flattening the three-dimensional fluorescence spectrum data into a one-dimensional vector, and performing normalization processing on the one-dimensional vector to obtain one-dimensional vectors of each group of mixed water samples; the spectral difference and similarity between samples are compared and analyzed through a spectral angle algorithm, the characteristics of the industrial wastewater are quantitatively evaluated, qualitative recognition of the industrial wastewater in the municipal pipe network is achieved, and the method has the advantages of being efficient, accurate and convenient.

A metrology system may include a dual frequency comb source providing a first comb beam with a first repetition rate and a second comb beam with a second repetition rate, a beamsplitter to generate one or more dual frequency comb illumination beams from the first comb beam and the second comb beam, and a beam combiner to form a dual frequency comb illumination beam from the first comb beam and the second comb beam. The system may further include an illumination sub-system to illuminate a sample with the dual frequency comb illumination beam through an objective lens, a collection sub-system to collect sample light from the sample with the objective lens, and a detector to capture a radio-frequency signal based on the sample light. The system may further extract spectral measurement data associated with the sample from the radio-frequency signal and generate metrology measurements based on the spectral measurement data.

The invention provides a sun-cured tobacco producing area identification method based on a hyperspectral characteristic wave band and a machine learning algorithm, relates to the technical field of analysis and detection, and particularly relates to the following steps: obtaining sun-cured tobacco samples from different producing areas, and carrying out nondestructive pretreatment on the sun-cured tobacco samples to obtain pre-treated sun-cured tobacco samples; a hyperspectral imaging system is used for collecting hyperspectral images of the preprocessed air-cured tobacco samples, an original spectral data set is obtained, and the spectral data set is processed through multivariate scatter correction, standard normal variable transformation, a first-order derivative and a second-order derivative to obtain a spectral data set of the processed air-cured tobacco samples; extracting a characteristic spectral band data set for reflecting the difference of the sun-cured tobacco producing areas, wherein a characteristic spectral band is screened out from the hyperspectral data set based on a spectral angle algorithm; and constructing a machine learning classification model by using the extracted characteristic spectral wave band data set, and inputting the hyperspectral data set of a to-be-detected air-cured tobacco sample into the trained machine learning model to obtain a production place identification result.

The invention discloses a remote sensing geological prospecting method based on information entropy-partial differential equation combined modeling, and belongs to the technical field of mineral exploration, and the method comprises the steps: extracting a plurality of layers from a remote sensing image, the plurality of layers including a spectral angle map layer, an iron stain alteration grading layer, a hydroxyl alteration grading layer and an indication mineral distribution layer; superposing the multiple layers to generate a comprehensive graph; establishing a target region extraction model, and outputting a target region by taking the comprehensive graph as input; and vectorizing the boundary of the target region, and delineating the position of the target region. According to the information entropy-partial differential equation combined modeling-based remote sensing geological prospecting method disclosed by the invention, visual innovation of mineral space distribution is realized, four mineral identification technologies are cooperatively applied, the mineral strength is quantified into a transparency parameter, the problem of information overload due to multi-layer superposition is solved, automatic and rapid mining area identification is realized, and the mining efficiency is improved. And the identification accuracy is extremely high.

The application discloses a remote sensing geological prospecting method based on information entropy-partial differential equation joint modeling, and belongs to the technical field of mineral exploration, and comprises the following steps: extracting multiple layers from remote sensing images, wherein the multiple layers comprise a spectral angle mapping layer, an iron staining alteration grading layer, a hydroxyl alteration grading layer and an indicator mineral distribution layer; superimposing the multiple layers to generate a comprehensive map; establishing a target area extraction model, taking the comprehensive map as input and outputting a target area; and vectorizing the target area boundary to delineate the target area position. The remote sensing geological prospecting method based on information entropy-partial differential equation joint modeling realizes mineral spatial distribution visualization innovation, cooperatively applies four mineral identification technologies, quantifies mineral intensity into a transparency parameter, solves the problem of information overload caused by multiple layer superimposition, realizes automatic and rapid identification of a mining area, and has extremely high identification accuracy.

This invention relates to a high-resolution remote sensing image enhancement method for forest ecological monitoring, belonging to the field of forest ecological remote sensing monitoring. It includes the following steps: unified grid registration and effective forest pixel selection are performed on Sentinel-2 multi-band surface reflectance data; a continuous canopy shadow intensity map integrating topographic incidence relationships and local canopy darkness is constructed; slow-release reflectance correction is performed by band grouping; a spectral-spatial collaborative residual enhancement network is constructed, extracting texture and band combination features through parallel spatial enhancement and spectral enhancement branches, respectively, and introducing a band group attention mechanism based on ecological function; the network is jointly trained using weighted reconstruction loss and spectral angle loss; finally, a panoramic enhanced image is generated through sliding window inference and weighted stitching of overlapping areas. This invention can effectively suppress deep shadow overcompensation and spectral distortion problems, and improve the detail representation of ecologically sensitive bands such as red edge and near-infrared.

The invention provides a hyperspectral image super-resolution method and device based on iterative reconstruction and spectral refinement, and relates to the technical field of hyperspectral imagines.The method comprises the steps that firstly, a three-adjacent-window cube is intercepted in a sliding mode along the spectral dimension, and the three-adjacent-window cube is mapped into pseudo RGB three-channel features through a lightweight head adapter; then domain adaptation is carried out on the frozen pre-training network through LoRA low-rank decomposition, and corresponding three-band high-resolution prediction is output; for multiple predictions generated by different central windows in the same target wave band, obtaining a coarse super-resolution result by normalized fusion of'spectral position window weight * confidence coefficient '; and finally, the spectrum reconstruction decoder performs end-to-end refinement under the joint SAM spectrum angle constraint to obtain a final high-resolution hyperspectral image. The method aims to transfer a natural image pre-training model to a hundred-wave-band hyperspectral scene in a lossless mode with extremely low parameter increment, and synchronous jumping of space details and spectral fidelity is achieved.

The invention relates to an altered mineral sample library construction method and device and a storage medium, and the method comprises the steps: obtaining multi-source heterogeneous data which at least comprises remote sensing image data, historical altered mineral mapping and standard spectrum data; generating a pure pixel sample based on the remote sensing image data; based on the remote sensing image data and the standard spectral data, for each pixel, calculating a spectral angle between a pixel spectrum in the remote sensing image data and various altered mineral spectrums in the standard spectral data, and generating spectral angle index data; generating a matching sample based on the spectral angle index data; and carrying out spatial position superposition on the pure pixel sample and the matching sample to generate an altered mineral sample library. Through the method and the device, the problem of lack of altered mineral sample libraries is solved, and high-quality training data is provided for deep learning.

This invention discloses a comprehensive visual super-resolution method based on neural networks. Through a two-stage optimization process of offline training and online deployment, it achieves real-time super-resolution reconstruction of remote sensing images on an edge computing platform. In the offline stage, a physics-data hybrid-driven training dataset is constructed, including optical MTF analysis, atmospheric turbulence simulation, and sinc artifact enhancement. A dynamic network, RAG-SRNet, is designed to adaptively switch the RRDB computation path based on the screen projection size, and training is performed using remote sensing-specific perception loss, RaGAN adversarial loss, and spectral angle loss. In the online stage, TensorRT INT8 quantization and mixed-precision optimization are employed. CUDA-OpenGL zero-copy memory mapping enables the reuse of memory addresses for the inference output buffer and texture objects. Asynchronous inference thread pools and hardware semaphore synchronization are used to achieve pipelined parallelism for tile requests, super-resolution computation, and texture rendering. Compared to existing methods, this invention significantly improves PSNR, increases frame rate by over 25%, and reduces CPU usage by 77%, providing an industrial-grade visual enhancement solution for aerospace simulation and autonomous driving.

The invention discloses a hyperspectral scene generation method based on dynamic target embedding, and the method comprises the steps: inputting an RGB base map of a scene object and correlation parameters of the scene object, generating a hyperspectral image of the scene object through a spatial-spectral combined generative adversarial network, and updating network parameters, the associated parameters of the scene object at least comprise latitude and longitude coordinates, a wave band range, spectral resolution, spatial resolution and environmental factors; obtaining dynamic target embedded data based on the spectral information and the motion track of a target object, and obtaining a hyperspectral image containing the target object based on the hyperspectral image of the scene object and the dynamic target embedded data; and obtaining evaluation data of the scene object through performance evaluation based on the hyperspectral image containing the target object and the truth value of the hyperspectral image containing the target object, wherein the evaluation data at least comprises data of an Euclidean distance, a relative quadratic error, a spectral angle and a peak signal-to-noise ratio.

The invention discloses a micro-nano plastic analysis method based on nano hyperspectral fingerprint characteristics, and belongs to the technical field of environmental pollutant detection. The method comprises the following steps: establishing an initial spectrum library [SL1.0] containing a plurality of plastic polymers; optimizing the spectrum library through principal component analysis, extracting characteristic peaks, determining 600-840nm as a plastic fingerprint region, and constructing an optimized spectrum library [SL2.0]; preparing an atmospheric sedimentation sample or a biological tissue paraffin section; and collecting a hyperspectral image of the sample, and matching the hyperspectral image with the optimized spectrum library in the fingerprint region by using a spectrum angle matching algorithm to realize component identification and spatial positioning of the micro-nano plastic. According to the method, spectral redundancy and noise interference are effectively eliminated through PCA optimization, the multi-component identification accuracy is remarkably improved by focusing the fingerprint area, the form, component and distribution information of the micro-nano plastic can be obtained at the same time, and a reliable technical means is provided for environmental monitoring and toxicological research.

This invention discloses a large-scene hyperspectral zero-shot classification method and system based on a visual language model. The method includes the following steps: generating an initial pseudo-label map for the hyperspectral image based on a visual language model; calculating the spectral angle between each pixel in the initial pseudo-label map and the spectral fingerprint vector; filtering the initial pseudo-label map based on the spectral angle to obtain an optimized pseudo-label map; training a hyperspectral segmentation network based on the hyperspectral image and its optimized pseudo-label map to establish a mapping relationship between the hyperspectral image and its land cover categories for land cover category classification. The hyperspectral segmentation network consists of an encoder, a decoder, and a classifier, wherein the encoder is composed of N-level cascaded multi-kernel convolutional residual modules. This invention aims to accurately identify and segment different land cover categories in complex hyperspectral images without manual annotation.

The invention provides a forest lightning uplink pilot multispectral high-speed shooting and positioning system, and relates to the technical field of lightning monitoring and forest lightning fire prevention and control. The forest lightning uplink pilot multispectral high-speed shooting and positioning system comprises an imaging module, a positioning module, a tracking snapshot module, an intelligent cooperation module and an auxiliary function module. Through the multispectral imaging module, forest lightning can be imaged from multiple spectral angles such as visible light, infrared light, ultraviolet light and the like, rich lightning information is obtained, and the physical characteristics and the development mechanism of lightning can be deeply researched; according to the invention, the system provides comprehensive and detailed image data for research through high-resolution visible light imaging, specific-band infrared imaging, high-sensitivity ultraviolet imaging and high-frame-rate high-speed camera imaging, and the high-frame-rate shooting function of the high-speed camera module can clearly record the rapid change process of lightning uplink pilot.

This invention relates to the field of image recognition technology and proposes a method and system for grading vegetable waste and adapting it to insect feed based on image recognition. The method includes: radiometric calibration of hyperspectral image data to obtain a spectral image cube; extracting chromatic space deviation feature values ​​and short-wave infrared absorption peak curvature feature values ​​from the cube; performing pixel-level matching to obtain the overall spoilage level; when the overall spoilage level is "fresh and tender," performing spectral angle matching between the reflectance of the soluble sugar feature band and the palatability benchmark spectral library of yellow mealworms to obtain a first set of feed processing parameters; when it is "semi-rotten," comparing the spectral characteristics of the lignin-to-cellulose ratio with the feeding preference spectral range of white-spotted flower beetle larvae to obtain a second set of feed processing parameters; when it is "deeply rotten," generating a third set of feed processing parameters; and outputting the corresponding parameter sets to a feed formulation terminal to obtain the final feed adaptation scheme. This invention can improve the efficiency of grading vegetable waste and adapting it to insect feed.