Patents
Literature
Patsnap Eureka AI that helps you search prior art, draft patents, and assess FTO risks, powered by patent and scientific literature data.

1405results about How to "Accurate classification" patented technology

Thermal power plant equipment lubricating oil on-line monitoring system and method thereof

The invention relates to the technical field of equipment monitoring, in particular to a thermal power plant equipment lubricating oil online monitoring system and method, and the system comprises a parameter real-time monitoring module, an oil condition analysis module, an abnormity early warning and transmitting module, a maintenance scheduling module, a health trend analysis module and an equipment performance strengthening module. In the invention, by implementing a timing signal capturing technology and threshold monitoring, the system improves the quick response capability to an abnormal state, and combines continuous data flow recording and oil real-time monitoring data analysis, capturing and classification of abnormal fluctuations, so that a maintenance team quickly takes preventive measures, the equipment failure risk is reduced, and the reliability of the system is improved. The real-time updated maintenance scheduling plan and the dynamic allocation of resources optimize the maintenance window time, improve the operation efficiency, deepen the understanding of the health condition of the equipment through the long-term trend prediction of the statistical method, facilitate the prevention of future problems, prolong the service life of the equipment, and improve the reliability of the equipment by finely adjusting the measurement interval and the sensitivity of the monitoring points. And the operation efficiency and safety of the thermal power plant are improved.
Owner:CHN ENERGY SHENHUA JIUJIANG POWER GENERATION CO LTD +2

Defect analysis method and system based on pipeline butt weld radiograph

The invention relates to the technical field of pipeline defect analysis, and discloses a defect analysis method and system based on a pipeline butt weld radiograph. The method comprises the following steps: carrying out digital scanning processing on a pipeline butt weld ray negative film to obtain a negative film digital image, and carrying out preprocessing and enhancement operation to obtain a target negative film image; performing feature extraction and calculation to obtain image feature data, and inputting the image feature data into a self-learning defect analysis model for defect analysis to obtain an initial defect analysis result; performing defect property evaluation and quantitative analysis on the initial defect analysis result according to preset standard information to obtain defect property data and defect equivalent, position and level information; the defect property data and the defect equivalent, position and level information are comprehensively processed, a defect correction suggestion is obtained, a repair schematic diagram and a defect analysis report are generated according to the defect correction suggestion, and the defect analysis accuracy of the pipeline butt weld radiograph is improved.
Owner:NINGBO MINGFENG INSPECTION & TESTING RES INST CO LTD

Method and system for enhancing wafer detection in semiconductor manufacturing process

The invention provides a method and system for enhancing wafer detection in a semiconductor manufacturing process, and relates to the technical field of wafer detection, and the method comprises the steps: transmitting dual-frequency laser to the surface of a wafer to form a controllable overlapping region, and collecting a beat frequency signal to obtain initial height information; carrying out adaptive filtering processing on the beat frequency signal, reconstructing a three-dimensional contour of the surface of the wafer, and generating an initial defect distribution diagram; and determining a secondary detection area according to the initial defect distribution diagram to perform orthogonal scanning, identifying and rejecting pseudo defect signals, extracting defect features, and determining defect cause types. According to the invention, the accuracy and efficiency of wafer defect detection are improved, and the semiconductor manufacturing quality can be improved.
Owner:BEIJING KEYANG TECH CO LTD

Industrial vision product surface printing quality detection method

The invention provides a product surface printing quality detection method based on industrial vision, which comprises the following steps: acquiring paper type and ink type information used by a printed matter, and extracting material spectral characteristic parameters of a paper and ink combination from a pre-established material spectral characteristic database, comprising scattering reflection characteristics of the paper surface and absorption reflection characteristics of ink; for the area with the quality defect, analyzing the spectral data of the area, extracting refined spectral characteristics, accurately classifying defect types through a deep learning model, and analyzing the influence of paper and ink material characteristics on a defect forming mechanism; according to the defect type and the position information, similar cases are retrieved from a pre-established defect knowledge base, a defect cause analysis result and an improvement suggestion are obtained, the material spectral characteristic parameters are matched with defect characteristics, and an evaluation result of the influence degree of the material characteristics on defect formation is obtained.
Owner:IFLYTEK SOUTH CHINA ARTIFICIAL INTELLIGENCE RES INST GUANGZHOU CO LTD

Liquid crystal screen defect detection method and system based on machine vision and storage medium

ActiveCN119086020AAccurate defect optimization defect point accuracyOptimize defect point accuracyImage analysisTesting optical propertiesMachine visionData set
The invention relates to the technical field of liquid crystal screen detection, in particular to a liquid crystal screen defect detection method and system based on machine vision and a storage medium. The method comprises the following steps: acquiring panel structure data of the liquid crystal screen, wherein the panel structure data comprises panel size data, pixel arrangement data, backlight module data and surface processing information data; performing optical characteristic analysis based on light wave interference on the liquid crystal screen according to the panel structure data, and mapping normal display states under different display states, display contents and visual angles according to a preset image data set so as to obtain standard display characteristic diagram data; collecting multi-area image data of the liquid crystal screen panel; according to the method, the defects of the liquid crystal screen under different refresh frequencies are dynamically tracked, particularly, the defect performance under different display states is captured, and more comprehensive defect analysis is provided.
Owner:SHENZHEN HUAHEXIN TECH DEV CO LTD

Woven tape quality detection system and method based on industrial camera detection

The invention provides a braid quality detection system and method based on industrial camera detection, and relates to the technical field of data processing. A multi-angle acquisition module; an image fusion module; an optical correction module; a preprocessing module; a preliminary defect detection module; a fine defect analysis module; a self-adaptive filtering module; the dynamic coordinate mapping module is used for mapping the physical position of the defect to obtain actual coordinate data; the data storage and analysis module is used for storing and analyzing historical actual coordinate data and related detection data and generating a quality report and a trend analysis report; the alarm and control module is used for automatically sending out an alarm signal and adjusting production parameters or pausing production when the defect number or the trend change rate in the trend analysis report reaches a preset threshold value; according to the invention, the accuracy and efficiency of braid quality detection are improved.
Owner:XIAMEN QIUTE NEW MATERIALS RES INST CO LTD

AI auxiliary decision support system for skin disease diagnosis

The invention relates to the technical field of skin disease diagnosis, and discloses an AI auxiliary decision support system for skin disease diagnosis, which integrates an image acquisition module, an image analysis module and a comprehensive analysis and diagnosis decision module. A high-definition image of the skin of a patient is obtained through high-precision skin photographing equipment, and a training data set is formed by combining basic information of the patient. A deep learning algorithm is utilized to train a skin disease recognition model and an illness state evaluation model, and accurate recognition of skin disease types and objective evaluation of severity are realized. And the comprehensive analysis module fuses output of the two models, constructs a fusion decision model and provides comprehensive diagnosis suggestions. And the diagnosis decision module is used for generating a disease type judgment and illness state evaluation report based on the trained model in combination with real-time image data so as to effectively assist doctors in making decisions. The accuracy, the efficiency and the popularization degree of skin disease diagnosis are improved, and complex and changeable diagnosis requirements in clinical practice are met.
Owner:BEIJING MINGRUN TONGKANG TECH CO LTD

Internet of Things intelligent monitoring alarm method and system for water quality detection

The invention discloses an Internet of Things intelligent monitoring alarm method and system for water quality detection, and relates to the technical field of environmental protection monitoring, and the method comprises the steps: respectively sampling water quality electrochemical data for corresponding monitoring water area blocks based on each Internet of Things node; extracting electrochemical time sequence sensing characteristics respectively corresponding to each piece of water quality electrochemical data; extracting mode time sequence dependence features corresponding to the electrochemical time sequence sensing features based on a water quality anomaly identification model to predict water quality anomaly risks; identifying a corresponding water quality abnormity risk event type based on an abnormal event identification model; and according to the block identifier of each risk monitoring water area block and the corresponding water quality abnormity risk event type, executing water area water quality pollution alarm operation. Therefore, based on distributed water quality monitoring, intelligent risk identification and water quality pollution early warning operation of the Internet of Things nodes, water quality monitoring real-time performance, comprehensive coverage and intelligent management capability are remarkably improved.
Owner:GUANGDONG JUNXIN TECH CO LTD +1

Cognitive state interpretable method based on brain-language-vision large model

The invention belongs to the technical field of learner cognitive state interpretation, and particularly discloses a brain-language-vision large model-based cognitive state interpretable method, which comprises the following steps of performing multi-modal data collection for the cognitive state of a learner; performing learner cognitive state characterization based on a multi-scale map convolutional network; brain-vision-language mixed multi-modal time sequence feature fusion based on hierarchical mutual information maximization is carried out; embedding knowledge graph nodes for enhancing the complex task understanding ability of the multi-modal large model; training a brain-vision-language multi-modal large model guided by knowledge; recognizing a learner cognitive state based on a multi-modal large model; the cognitive state of the learner can be explained and analyzed under the support of multi-mode owned reasoning. According to the cognitive state interpretable method based on the brain-language-vision large model, the input multi-modal fusion features are converted into high-quality prompts so as to guide the large language model to extract implicit knowledge, and important support is provided for reasoning generation.
Owner:ZHEJIANG NORMAL UNIV

Virtualized network fault rapid positioning method fusing multi-source information

The invention provides a multi-source information fused virtualized network fault rapid positioning method, and relates to the technical field of electric digital data processing, and the method comprises the steps: classifying and sorting historical fault events, constructing a historical dynamic evaluation model, correcting a calibration index, capturing equipment performance changes and abnormities, and enhancing the fault recognition capability. Similar faults are accurately classified and preferentially processed according to severity; in the real-time monitoring stage, real-time multi-source and abnormal data are combined, a real-time dynamic evaluation model and a correction calibration index are calculated, a ratio is applied to calculate a fine adjustment strategy, the real-time performance and accuracy of fault positioning are remarkably improved, and network dynamic changes are quickly responded. And carrying out difference analysis on the adjusted real-time model and the historical model, calibrating a preliminary fault positioning result, and improving the positioning precision and reliability.
Owner:BEIJING DONGFANG RONGCHUANG INFORMATION TECH CO LTD

Method for identifying impurities and bubbles in wine bottle based on multi-feature comprehensive judgment

The invention discloses a method for identifying impurities and bubbles in a wine bottle based on multi-feature comprehensive judgment, and belongs to the technical field of image processing and computer vision, and the method comprises the steps: employing a high-resolution industrial camera to be combined with an LED light source, and continuously shooting multiple frames of images of the wine bottle under the consistent shooting angle and illumination condition; carrying out the preprocessing of the collected image through employing a self-adaptive histogram equalization and Gaussian blur method; extracting the edges of impurities and bubbles in the wine bottle on the image by adopting a Canny edge detection algorithm to obtain an edge image; segmenting the edge image into a plurality of target areas by using a contour detection technology, and extracting possible bubble and impurity areas from the edge image; extracting target area features including circularity, gray average, gray uniformity, texture features and color space; and according to the extracted features, bubbles and impurities are distinguished by applying a comprehensive judgment rule. According to the method, the bubbles and the impurities are comprehensively judged by adopting multi-feature combination, so that the accuracy and the robustness of detection are greatly improved.
Owner:DONGFANG ELECTRIC AUTOMATIC CONTROL ENG CO LTD

Epilepsy electroencephalogram signal recognition method, system and equipment and storage medium

The invention discloses an epilepsy electroencephalogram signal recognition method, system and device and a storage medium, and the method comprises the steps: obtaining an electroencephalogram signal, and calculating phase synchronization information between different channels according to the electroencephalogram signal as an edge feature; filtering the electroencephalogram signals, respectively calculating and extracting time domain features, dynamic features and phase amplitude coupling features corresponding to different wavebands of each channel, and fusing the features into node features; and integrating the obtained edge features and node features into a graph, performing classification by using a graph attention network model, and performing judgment and recognition on the electroencephalogram signals according to a classification result. The invention provides a classification method which is high in performance, has priori interpretability and is used for epilepsy signal identification and prediction, not only considers an interaction relationship among different channels, but also pays attention to and extracts deep features of time domain, dynamics, cross-frequency coupling and the like of nodes, and is more accurate in classification of electroencephalogram signals in different periods.
Owner:XI AN JIAOTONG UNIV

Road disease detection system and method based on multi-source data fusion

The invention discloses a road disease detection system and method based on multi-source data fusion. The system comprises a data acquisition module, a data preprocessing module, a disease detection module, a three-dimensional modeling module, a data analysis module and a maintenance module. The data acquisition module is used for acquiring road surface data and sending the acquired data to the data preprocessing module; the road surface data comprises road data, road disease data, road vehicle data, non-motor vehicle data and pedestrian data, compared with the prior art, more comprehensive and more accurate detection of road diseases is realized by fusing multi-source data; by means of multi-dimensional data acquisition of radar data, video data, three-dimensional point cloud data, geographical location information and the like, the limitation of a single data source is overcome; the data preprocessing module can effectively remove noise and abnormal values, accurately classify and mark diseases, and fuse data collected by different sensors, so that the quality and integrity of the data are improved.
Owner:CHINA DESIGN GROUP CO LTD

Wind power plant equipment fault intelligent diagnosis method and system

The invention discloses a wind power plant equipment fault intelligent diagnosis method and system. The method comprises the following steps: acquiring multi-dimensional sensor data of wind power plant equipment; carrying out preliminary screening on the data by utilizing an edge analysis algorithm, and determining data needing to be further diagnosed; the screened data are input into a pre-constructed fault diagnosis model, the data are fused through a multi-modal deep learning model in the pre-constructed fault diagnosis model, and then a fault occurrence area is determined through transfer learning, domain adaptation and a multi-agent reinforcement learning framework; meanwhile, the causal inference engine and the knowledge graph enhanced neural symbol inference module are responsible for deep processing and fault diagnosis. And finally, inputting the determined fault area and the diagnosis result into a dynamic system health index calculation module to generate a final fault diagnosis result. According to the method, the diagnosis efficiency and accuracy of the equipment fault of the wind power plant are remarkably improved, and a powerful guarantee is provided for stable operation of the wind power plant.
Owner:HUANENG HEZHANG WIND POWER CO LTD +1

Target monitoring method, medium and system for high-resolution satellite remote sensing image

ActiveCN119131614AAccurately estimate occlusion distributionMake up the detailsScene recognitionNeural learning methodsCategory recognitionDistribution matrix
The invention provides a target monitoring method, medium and system for a high-resolution satellite remote sensing image, and belongs to the technical field of remote sensing data processing, and the method comprises the steps: firstly, carrying out the preprocessing of an image, and dividing the image into a plurality of sub-regions through a region segmentation algorithm; and then carrying out iterative enhancement on the sub-regions by adopting a global-region enhancement network, and establishing a game optimization model to balance local features and global features so as to generate candidate refined images. Thirdly, preliminarily scanning the preprocessed image by using a deep target detection network to obtain a target candidate area; and then, target features are extracted by adopting a multi-layer attention mechanism, a shielding distribution matrix is solved based on a shielding perception equation set, and adaptive compensation is carried out on a target area with shielding. And finally, inputting the extracted target features into a pre-trained recognition model to realize category recognition and position positioning of the target. The problem that enhancement processing of remote sensing images in the prior art is difficult to deal with different types of targets in complex scenes is solved.
Owner:QINGDAO GUOCEN HAIYAO INFORMATION TECH CO LTD

Automatic ore fine sorting method and system based on XRT and hyperspectrum

The invention discloses an automatic fine ore sorting method and system based on XRT (X ray tomography) and hyperspectrum, which are used for realizing comprehensive fusion of ore surface and internal information by combining X-ray tomography and hyperspectral imaging technologies so as to improve the recognition precision and the sorting efficiency. XRT is used for extracting the internal structure and density characteristics of the ore, hyperspectral imaging is used for identifying the mineral composition characteristics of the ore surface, and information complementation is achieved. The system adopts a multi-modal convolutional neural network to perform independent feature extraction on XRT and hyperspectral data, and the extracted features are fused through a deep residual network. And the fused features are processed by a cross-modal attention mechanism to ensure that key features of different modals are fully integrated and optimized, and finally high-precision ore classification and sorting are realized. According to the method, the limitation of a single data source on feature extraction is overcome, the ore recognition and sorting precision is greatly improved, and the refined and intelligent development of ore sorting is promoted.
Owner:SHANGHAI UNIV

Method for creating structured document based on deep learning model

The invention provides a method for creating a structured document based on a deep learning model, and relates to the technical field of data processing, and the method comprises the steps: obtaining basic text information collected by a user, obtaining text data, fragmenting the text data, obtaining text fragmented data, and creating a structured document according to the text fragmented data. Analyzing the structures of the sentences in the paragraphs, determining keywords in the sentences, analyzing the logical relationship between the sentences in the paragraphs, associating the sentence keywords in the paragraphs, analyzing the association degree between the paragraphs in the chapters, identifying core keywords of the chapters, obtaining a chapter keyword data set, and analyzing the field involved in the text. The method comprises the steps of extracting field information of a text to obtain a text keyword data set, constructing a structured document model based on a graph neural network model, and inputting the text keyword data set and text data into the structured document model to obtain a structured document. According to the method, the structured document can be constructed through the deep learning model.
Owner:FUJIAN WHALE AIR NETWORK TECH CO LTD

Negative emotion characterization analysis system for social contact in colleges and universities

The invention, which relates to the technical field of social emotion analysis, discloses a university social negative emotion characterization analysis system comprising a data acquisition and preprocessing module, a feature extraction and anomaly detection module, an intelligent perception and negative emotion characterization module, and an anomaly risk assessment and response module. Emotional feature information is acquired in real time based on a multi-dimensional data source, and the acquired emotional feature information is cleaned and preprocessed. According to the method, by calculating the data consistency offset coefficient and the strong correlation coefficient, the multi-collinearity problem among multi-dimensional data features is solved, and instability of the model regression coefficient is avoided. And the system identifies abnormal correlation in real time and combines risk threshold classification processing to ensure robust model output. An analysis set is established by continuously collecting data, long-term emotion trend analysis is supported, personalized responses such as reminding, intervention or emergency measures are provided according to risk levels, and accurate management and timely adjustment of student emotional states are achieved.
Owner:JILIN CENTURY TENGFEI TECHNOLOGY CO LTD

Archive system and method based on artificial intelligence

The invention discloses an archive system and method based on artificial intelligence, and relates to the technical field of artificial intelligence, and the archive system comprises an intelligent retrieval module, an information sharing optimization module, a deep learning engine and an adaptive classification module. The semantic meaning of a retrieval request input by a user can be deeply understood, the deep neural network further strengthens the analysis capability of a complex semantic relationship, the retrieval request and an archive text are converted into high-dimensional vectors in combination with a word vector model, and the retrieval request and the archive text are analyzed through accurate cosine similarity calculation and introduction of a correlation calculation formula of a time decay factor. According to the method, the archives which most meet the requirements are quickly and accurately screened out from massive archives, and even in a huge-scale archive room, a deep learning engine can continuously optimize feature extraction and mode recognition capabilities through training of a large amount of archive data, so that a large amount of time is saved, and the possibility of error occurrence is reduced.
Owner:SHANDONG QIANHE ARCHIVES MANAGEMENT CO LTD

GFE-Mama neural network-based interpretable Alzheimer's progress classification method

The invention discloses an interpretable Alzheimer's progress classification method based on a GFE-Manba neural network, and the method comprises the following steps: 1, constructing a GFE-Manba neural network model, 2, building an MRI and PET image data set, dividing the MRI and PET image data set into a training set and a test set, and pre-training a 3D GAN-Vit module through the MRI and PET image training set and the test set; 3, establishing a multi-mode Alzheimer's progress classification data set combining MRI and scale data, and dividing the multi-mode Alzheimer's progress classification data set into a training set and a test set; 4, training the pre-trained GFE-Mama neural network model by using the training set, and carrying out parameter tuning on the pre-trained GFE-Mama neural network model; and step 5, testing the pre-trained GFE-Mama neural network model obtained through evaluation by using a test set, and finally explaining the multi-modal Alzheimer's progress classification. The method not only can provide an important reference standard for clinical doctors to diagnose and treat major dangerous diseases, but also further enhances the diagnosis capability of the clinical doctors on AD and other major brain diseases, and is of great significance to clinical diagnosis and AD disease prevention.
Owner:HANGZHOU DIANZI UNIV

Wind power plant fan blade detection method and system based on three-dimensional point cloud

The invention relates to the technical field of fan blade detection, and provides a wind power plant fan blade detection method and system based on three-dimensional point clouds, and the method comprises the following steps: carrying out the multi-angle scanning of a fan blade through a laser scanner, and obtaining the three-dimensional point cloud data of the fan blade; performing registration processing on the three-dimensional point cloud data, and unifying the three-dimensional point cloud data into the same coordinate system to obtain registered point cloud data; performing block acceleration processing on the registered point cloud data by adopting an octree partitioning algorithm to obtain block acceleration point cloud data; performing feature extraction and feature segmentation on the block acceleration point cloud data to obtain a key feature region of the fan blade; performing defect identification analysis on the key feature region based on a point cloud network enhancement model to obtain a defect detection result, the defect detection result comprising a defect position and a defect type; and generating a detection report containing the defect position and the defect type, and visually displaying the detection report. According to the invention, the integrity of data acquisition and the precision of defect identification are improved, and the efficiency of fan blade detection is improved.
Owner:POWERCHINA EQUIP RES INST CO LTD

Automatic exploration method and system based on aerial photography of roof by unmanned aerial vehicle

The invention relates to the technical field of unmanned aerial vehicle exploration, in particular to an automatic exploration method and system based on unmanned aerial vehicle aerial photography of a roof. The method comprises the following steps: firstly, acquiring high-precision three-dimensional point cloud data and a multi-angle two-dimensional image by using a three-dimensional vision sensor carried by an unmanned aerial vehicle; then constructing an accurate roof three-dimensional model based on the three-dimensional point cloud data and the multi-angle two-dimensional image; a roof plane area and a shelter are identified through model analysis; calculating an optimal layout scheme in combination with the parameters of the photovoltaic panel; and finally, generating a three-dimensional rendering image for a user to confirm and adjust. By considering the plane area and the shielding object information and combining the input photovoltaic panel parameters, a more accurate layout scheme is calculated, the exploration precision is improved, the environmental adaptability is high, and layout optimization is more comprehensive.
Owner:GUANGDONG WEIYANG TECH CO LTD

Spectrum analysis device and method for radio monitoring system, and storage medium

The invention relates to the technical field of radio monitoring, in particular to a spectrum analysis device and method for a radio monitoring system and a storage medium, and the method comprises the steps: obtaining a corresponding environment noise level in a monitoring process, adjusting a sensitivity threshold value corresponding to signal detection based on the environment noise level, receiving a corresponding to-be-analyzed radio frequency signal, and preprocessing the received to-be-analyzed radio frequency signal based on an adaptive filter; calling a pre-trained spectrum analysis model, inputting the preprocessed to-be-analyzed radio frequency signal into the spectrum analysis model, and obtaining a corresponding spectrum classification result; and calling frequency information and time sequence data corresponding to a radio frequency signal to be analyzed, obtaining corresponding spectrum analysis data based on the spectrum classification result, the frequency information and the time sequence data, and displaying key parameters in the spectrum analysis data through a graphical interface. According to the invention, the effectiveness of signal detection and identification can be improved.
Owner:SHENZHEN RUIXUNTONG INFORMATION TECH CO LTD

Edge-based open vocabulary segmentation model target identification method

The invention discloses an edge-based open vocabulary segmentation model target identification method. The method comprises the steps of obtaining a target image; initializing Gaussian white noise as a noise contour mask pattern of a target; inputting the target image and the noise contour mask image into an open vocabulary segmentation model to execute the following operations: extracting multi-scale features of the target from the target image and the noise contour mask image; encoding the noise contour mask pattern to obtain encoding features; the multi-scale features are used as condition features to be fused with the coding features, and fusion features are obtained; predicting a de-noised contour mask graph of the target according to the fusion features; and according to the de-noised contour mask graph and the multi-scale features, a single full connection layer is used to predict classification and positioning of the target. According to the method, target identification based on the open vocabulary segmentation model can be effectively and quickly completed.
Owner:XIDIAN UNIV

X-band weather radar insect and bird identification method based on multi-scale information fusion

The invention discloses an X-band weather radar insect and bird identification method based on multi-scale information fusion. According to the method, identification is carried out from point and local scales based on a pixel-level classifier, identification is carried out from global scales based on an image classification model, and then point and local scale information is corrected based on global scale information; through combination of point, local and global multi-scale information, insect and bird scattering features and spatial distribution features are fully utilized, and the accuracy of X-band weather radar insect and bird identification is greatly improved. Compared with a model before improvement, the method has the advantages that the recognition accuracy of the X-band weather radar is improved by 9.33%, and an effective means is provided for accurately realizing insect and bird migration monitoring of the X-band weather radar in China.
Owner:BEIJING INST OF TECH

Transform remote sensing semantic segmentation method based on adaptive dynamic attention mechanism

The invention discloses a Transform remote sensing semantic segmentation method based on an adaptive dynamic attention mechanism, and relates to the technical field of the adaptive dynamic attention mechanism, and the method comprises the following steps: obtaining a remote sensing image data set, and carrying out the data marking and data enhancement; adjusting the remote sensing image into a model input size and a pixel value unified specification, and generating a standardized data set; feature embedding is generated based on a preset embedding module, and position coding is added to enhance position information for decoding; correcting the decoding process by using a self-attention and cross attention module; combining different scale features with continuously iterated updated adaptive weights to obtain a fusion feature value; constructing a multi-task joint loss function based on the to-be-solved problem; refining the fusion feature value through a segmentation module, and generating predicted values of different sub-tasks; according to the method, the problems of information loss and inconsistency possibly occurring during feature fusion in a multi-scale task in a traditional method are solved.
Owner:ECONOMIC TECH RES INST OF STATE GRID ANHUI ELECTRIC POWER +2

Spatial-spectral combined hyperspectral image classification method based on multi-scale adaptive attention mechanism

The invention discloses a spatial-spectral combined hyperspectral image classification method based on a multi-scale adaptive attention mechanism, and the method comprises the steps: firstly carrying out the extraction and fusion of features of different scales through a multi-scale feature fusion module, and comprehensively capturing the detailed spectral information of a hyperspectral image; secondly, dynamically adjusting a feature extraction process by using an efficient self-adaptive spectrum-space feature extraction module, and optimizing fusion and representation of spectrum-space features; and finally, enhancing the ability of the model to understand the context relationship in the image by using the context-aware fusion network. The three modules provided by the method are based on a deep learning framework, a convolutional neural network in deep learning can utilize multiband rich spectral information, and the method is suitable for hyperspectral remote sensing image data sets with different spatial resolutions, including a foreign hyperspectral data set and a domestic hyperspectral data set. The method has high adaptability and transportability, and can meet the requirement of image classification more easily.
Owner:HENGYANG NORMAL UNIV

Coal quality evaluation method and system based on spectrum and image feature fusion

PendingCN119000670ARealize fusion analysis and evaluationEnsure evaluation accuracyColor/spectral properties measurementsManufacturing computing systemsEvaluation resultFeature evaluation
The invention discloses a coal quality evaluation method and system based on spectrum and image feature fusion, and solves the problem that the existing method cannot perform fusion analysis evaluation based on coal type physical features and image features, thereby affecting accurate feature evaluation representation of pulverized coal data. Dividing the pulverized coal sample data into a training set and a test set, pre-constructing a coal quality evaluation model based on spectrum and image feature fusion, and training the coal quality evaluation model by adopting the training set; the coal quality evaluation model performs feature fusion analysis on the preprocessing set and outputs a coal quality evaluation result; according to the method, the coal quality evaluation model based on spectrum and image feature fusion is pre-constructed, the training set is adopted to train the coal quality evaluation model, and the precision of the coal quality evaluation model is tested through the test set, so that fusion analysis and evaluation of the coal type physical features and the image features are realized, the coal powder evaluation precision is ensured, and the coal powder evaluation efficiency is improved. And classification support is provided for pulverized coal utilization.
Owner:国能南京煤炭质量监督检验有限公司 +1

Combined zero sample image classification method based on hierarchical feature fusion

The invention belongs to the technical field of computer vision and artificial intelligence, and discloses a combined zero sample image classification method based on hierarchical feature fusion. According to the method, a solution based on hierarchical feature fusion is innovatively provided for the technical difficulty of combined zero sample image classification. According to the method, features of different depths in a CLIP model visual encoder are selected and subjected to hierarchical fusion, multi-level and multi-scale visual information is effectively extracted, the fused features are further used for visual and semantic cross-modal interaction, and the understanding ability of the model for complex combinations is remarkably improved. In addition, by introducing a specific loss item, attributes and object features are effectively separated, and the feature aliasing problem is avoided. In a combined zero sample image classification task, the method shows excellent generalization ability and recognition effect, and can significantly improve the classification performance of the model for unknown complex combined images.
Owner:NANJING UNIV OF AERONAUTICS & ASTRONAUTICS

Generative AI service website identification method based on multi-modal fusion learning

The invention provides a generative AI service website identification method based on multi-modal fusion learning. The method comprises the following steps: inputting original multi-dimensional and multi-modal information of an artificial intelligence generation service website, converting the multi-dimensional information into three feature vectors of a text, a picture and a code of the artificial intelligence service website through a multi-modal feature extraction model, and inputting the three feature vectors into a multi-modal feature fusion recognition model, and outputting a judgment result of whether the artificial intelligence generation service website provides the artificial intelligence service or not. According to the method, more accurate artificial intelligence generation service website recognition is realized through feature fusion of texts, images and code modes of websites, so that the generalization performance of a model on emerging and diversified website data is improved, the generalization ability and adaptability of a website recognition and classification model are enhanced, the limitation of classification of a single data type is broken through, and the classification efficiency is improved. And the generalization ability of the classification system is improved, so that the classification system can adapt to continuously changing and diversified artificial intelligence generation type website contents.
Owner:NAT COMP NETWORK & INFORMATION SECURITY MANAGEMENT CENT