80 results about "Spectral angle" patented technology

The invention discloses a metal ore body identification method based on remote sensing interpretation, relates to the technical field of mineral resource exploration, and aims to solve the problems of low identification precision, neglect of geological laws and poor generalization caused by dependence on single remote sensing data in the prior art. After standardization processing, spectrum and texture features are fused to generate a composite vector; extracting a multi-scale mineralization signal by using a convolutional neural network, and interpreting and constructing an ore control area in combination with a terrain gradient and a curvature; alteration zoning is identified through spectrum angle matching, and a favorable mineralization area is determined by combining lithology combination analysis; and dynamically weighting geological elements by adopting a deep learning fusion network, outputting an ore body position according to a comprehensive score, and finally optimizing a boundary through spatial clustering and morphological filtering. The method significantly improves the automation degree and reliability of ore body identification in a complex environment, and is suitable for metal mineral exploration target area delineation.

The invention provides a self-encoding hyperspectral anomaly detection method based on local and global dual-branch cooperation, and mainly solves the problem that the detection effect is poor due to the fact that an existing method is interfered by abnormal pixels. Comprising the following steps: 1) acquiring an original hyperspectral image; 2) constructing a self-encoding hyperspectral anomaly detection model comprising an encoder, a multi-direction mask convolution MDMC module which destroys anomaly spatial correlation along each direction, an attention-driven multi-scale grouping convolution AMGC module, a cascade type spatial spectrum attention CSSA module and a reconstruction module, wherein the self-encoding hyperspectral anomaly detection model comprises the encoder, the multi-direction mask convolution MDMC module, the attention-driven multi-scale grouping convolution AMGC module, the cascade type spatial spectrum attention CSSA module and the reconstruction module; 3) using an L1 norm and a spectral angular distance LSAD as a joint loss function, and guiding the model training to converge; and 4) inputting the original hyperspectral image into the trained final detection model to obtain a reconstructed hyperspectral image, and calculating to obtain an anomaly detection result. According to the method, the background reconstruction capability of the model can be improved, the reconstruction of the model on the anomaly is remarkably weakened, and the hyperspectral anomaly detection performance is effectively improved.

The invention discloses a three-dimensional fluorescence dynamic monitoring and automatic processing system for water quality. The system comprises a water sample collection module, a three-dimensional fluorescence spectrum detection module, a pollution fingerprint database, a spectral analysis unit, a diffusion path simulation module based on a distributed sensor network and an automatic control execution module. The diffusion path simulation module is used for acquiring spatio-temporal data through a water quality spectrum sensor, a hydrological sensor and a meteorological sensor, and dynamically predicting a pollutant migration track by combining a water body flow field model constructed by a finite volume method and a first-order dynamic fluorescence attenuation model; the automatic control execution module is based on the pollution recognition result and track prediction, emergency operations such as gate opening and closing and medicament adding are linked through a fuzzy logic algorithm, and full-process automation from monitoring to disposal is achieved. The system completes pollution identification within 10 minutes through a spectral angle mapping algorithm, and the defects that a traditional method lags in response and lacks dynamic prediction and automatic disposal are overcome.

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.

The invention belongs to the technical field of image analysis, and particularly relates to an egg oiling quality detection method based on machine vision, so as to solve the technical problems of low contrast, high light interference and single information dimension of the traditional machine vision in the prior art, and the method comprises the following steps: S1, obtaining a multispectral polarization image of an egg to be detected; s2, obtaining a contour mask and a highlight area mask of the egg; s3, obtaining an effective analysis area; s4, generating a linear polarization degree characteristic pattern representing the uniformity of the oil film; s5, generating a spectral angle characteristic pattern representing the oiling thickness; s6, constructing a region graph which takes each superpixel as a node and the adjacency relation as an edge; s7, fusing the initial feature vectors of the superpixel nodes; s8, identifying and outputting the super-pixel nodes which are judged as oiling defects; and S9, comprehensively evaluating the oiling quality grade of the egg. And automatic and high-precision comprehensive grading of egg oiling quality is realized.

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.

A water body suspended sediment concentration monitoring method based on FUI water body classification comprises the steps that firstly, a target watershed Sentinel-2 L1C image from a certain year to a certain year is obtained from GEE, and after resampling is conducted till the resolution is 10 m, preprocessing such as 6S model atmospheric correction, proximity effect correction and quality control is conducted; 5 wave bands are used for calculating spectral angles to obtain FUI, and 14 is used as a threshold value to divide the water body into clear water and muddy water. And then selecting an optimal wave band combination according to the FUI classification to construct a semi-empirical inversion model, and finally calculating the suspended sediment concentration distribution by using the model and verifying the suspended sediment concentration distribution. The method solves the problem that the model generalization ability is low in the monitoring of the suspended sediment concentration of the target drainage basin, and the inversion precision is high.

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 hyperspectral anomaly detection method based on local spectral contrast and multi-branch convolution, and the method comprises the steps: segmenting a multi-scale window region A in an original hyperspectral image into 3 * 3 region blocks, setting a middle block B0 as a target region, and setting the other region blocks as a background region Bi; determining an average spectral curve Bavg of the Bi, and solving a spectral angular distance matrix D according to the spectral curve Ap of each pixel in the multi-scale window region and the average spectral curve Bavg of the background region; then determining the maximum value Tmax of the spectral angular distance in the target area; determining a spectral angular distance average value Mi in the background area, determining a local spectral contrast Ci, taking a minimum value in the Ci as a change coefficient c, and determining a contrast score u according to the c and the test pixel dtest; window areas with different scales are selected to traverse the whole image, and a feature map U is obtained; and putting the feature map U into multi-branch convolution, extracting feature maps of different scales through convolution operation of three different branches, and fusing the feature maps to obtain a hyperspectral anomaly detection result map.

The present invention discloses a method and system for detecting the transparency of tortoise shell glue based on multispectrum, including: S1: obtaining a multispectral image sequence of a tortoise shell glue sample and performing band correction, constructing a multispectral image data cube and performing spatial registration; S2: generating a spectral angle mapping diagram according to the registered multispectral image data cube; S3: extracting the tortoise shell glue region through spectral angle mapping and regional growing algorithm and constructing a spectral feature matrix; S4: obtaining an optimal tortoise shell glue transparency qualified product identification model based on the spectral feature matrix and cross-validation method, and performing qualified judgment on the transparency of the tortoise shell glue sample to be tested; S5: constructing a transparency quality evaluation model, and classifying the transparency of tortoise shell glue into quality grades. Classifying the transparency of tortoise shell glue into quality grades. The present invention can achieve an objective and comprehensive evaluation of the transparency quality of tortoise shell glue by obtaining image information of tortoise shell glue samples in multiple spectral bands and combining intelligent analysis algorithms.

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 discloses a hyperspectral target height inversion method and device based on a radiation transfer model, and belongs to the field of remote sensing data analysis. The method comprises the following steps: acquiring a corresponding relation between atmospheric height and atmospheric temperature in the weather based on atmospheric data, and establishing a relation equation between target surface temperature and atmospheric temperature to determine the corresponding relation between atmospheric height and target surface temperature in the weather; sequentially simulating and calculating target spectrum entrance pupil radiation brightness and target center brightness temperature so as to transmit and determine a target center spectrum brightness temperature curve corresponding to each atmospheric height under the weather; and after wave band selection is carried out based on channel correlation of the target center spectrum brightness temperature curve corresponding to each atmospheric height, spectral angles of the real single-star image brightness temperature curve and the target center spectrum brightness temperature curve under each atmospheric height are respectively calculated, so that the atmospheric height with the highest spectral similarity is determined as the target height obtained by inversion. Therefore, the height inversion of the single-satellite imaging aerial target is realized.

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 present invention relates to the field of data processing technology, and in particular to a rice variety classification method based on hyperspectral pixel-level information, comprising the following steps: acquiring pixel data from a hyperspectral image; determining a first temporary grid based on pixel values; determining a second temporary grid based on reflectivity; determining a sample grid based on spectral angle; acquiring pixel-level labels and spectral reflectivity and performing variety classification; and adjusting pixel thresholds and determining the variety based on the classification results. The present invention effectively distinguishes different rice varieties through multi-level image processing and feature extraction steps. By extracting features such as real-time average pixel values, reflectivity, and spectral angles, it accurately captures subtle differences in rice. The dynamic adjustment of pixel thresholds, combined with variety deviation and fluctuation analysis, automatically optimizes classification accuracy under different sampling environments and conditions, effectively addressing the issues of insufficient classification accuracy and poor adaptability caused by reliance on static remote sensing data and lower-resolution imagery.

The invention relates to a multi-spectral remote sensing image depth spectrum super-division method considering land types, which comprises the following steps: constructing a one-dimensional convolution-up-sampling fusion spectrum super-division network model, and adopting a one-dimensional up-sampling convolution network architecture which comprises a spectrum convolution layer, a linear spectrum space full-connection layer and a spectrum feature up-sampling layer; establishing a multispectral-hyperspectral non-monocular network set by land classes, and for multispectral-hyperspectral pixel pairs of different land classes, inputting a network model for training to obtain multispectral-hyperspectral non-monocular weights of different land classes; weighted adversarial pixel spectrum prediction and image reconstruction are carried out, spectrum prediction is carried out pixel by pixel by using a spectrum non-single-shot network set to obtain spectrum prediction results of different land classes, and according to a spectrum coefficient weighted average method and spectrum angle minimum adversarial comparison, an optimal pixel spectrum prediction result is selected, and prediction is carried out pixel by pixel to obtain a reconstructed hyperspectral image. According to the invention, a reconstruction scheme of the multispectral image is designed, and the spectral resolution of the multispectral remote sensing image is enhanced.

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 present application belongs to the technical field of image analysis, and particularly relates to a kind of egg oiling quality detection method based on machine vision, to solve the technical problems of low contrast, high light interference and single information dimension faced by traditional machine vision in prior art, comprising the following steps: S1, obtaining the multispectral polarized image of the egg to be detected;S2, obtaining the contour mask and highlight area mask of the egg;S3, obtaining the effective analysis area;S4, generating a linear polarization degree feature map representing oil film uniformity;S5, generating a spectral angle feature map representing oiling thickness;S6, constructing a region graph with each superpixel as a node and an adjacency relationship as an edge;S7, fusing the initial feature vector of the superpixel node;S8, identifying and outputting the superpixel node determined as an oiling defect;S9, comprehensively evaluating the oiling quality grade of the egg. The automatic, high-precision comprehensive grading of egg oiling quality is realized.

The present application discloses a drone pegmatite spectral acquisition device, a lithium-bearing pegmatite identification method and system, which relate to the field of data acquisition and processing. Through reasonable design, a hyperspectral sensor is carried on the drone, which can collect hyperspectral data of pegmatite in real time through the drone, providing a data basis for the identification of lithium-bearing pegmatite. By processing the obtained drone hyperspectral data, reflectance spectral data, etc., a drone hyperspectral spatial vector cloud, a lithium-bearing pegmatite spectral vector cloud and a non-lithium-bearing pegmatite spectral vector cloud are obtained. Using these spectral vector clouds as the input of the constructed network model to obtain the identification result can improve the real-time performance of pegmatite identification. By adopting the spectral angle comparison method based on the identification result and retaining the image containing the information of lithium-bearing pegmatite, the accuracy of lithium-bearing pegmatite identification can be further improved, thereby solving the problem that the prior art cannot carry out the identification of lithium-bearing pegmatite for drone hyperspectral data.

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.