Patents
Literature
35 results about "Multispectral image classification" patented technology
Efficacy Topic
Property
Owner
Technical Advancement
Application Domain
Technology Topic
Technology Field Word
Patent Country/Region
Patent Type
Patent Status
Application Year
Inventor
Most satellites that image the Earth provide Spectral imaging. These images may be called multispectral, hyperspectral or ultraspectral because they are acquired for the same area using different wavelengths of the electromagnetic spectrum. For example Landsat satellite, Multispectral scanner - band 1 image, band 2 image etc. Since these remote sensing images are typically multispectral responses of various features it is hard to identify directly the feature type by visual inspection. Hence the remote sensing data has to be classified first, followed by processing by various data enhancement techniques so as to help the user to understand the features that are present in the image. Such classification is a complex task which involves rigorous validation of the training samples depending on the classification algorithm used. The techniques can be grouped mainly into two types. Supervised classification techniques Unsupervised classification techniques
High spectral image classification method based on NSCT transformation and DCNN
ActiveCN107316013AImprove classification performanceEasy to classifyScene recognitionTest sampleClassification methods
The invention discloses a high spectral image classification method based on NSCT transformation and DCNN. The objective of the invention is to solve the problem that texture details and directivity information of to-be-classified high spectral images cannot be sufficiently excavated in the prior art. The method comprises steps of inputting a high spectral image; carrying out NSCT transformation; carrying out normalization and block taking operation on the transformed stereo blocks; randomly selecting training, verification and test sample sets in a sample set; constructing a depth convolution neural network and setting network super-parameters; training the network; inputting the test samples into the network to obtain actual classification tags and drawing terrain classification result graph; and comparing the classification tags and the reference tags of the test samples, calculating classification evaluation indexes, drawing loss curve graphs of the training and verification samples of increasing along with the iteration times, thereby finishing the terrain classification. According to the invention, more texture details, directivity information and space information of the high spectral image are kept; the classification is quietly precise; and the method can be applied to meteorology and environmental monitoring, land utilization, urban planning and disaster prevention and reduction.
Owner:XIDIAN UNIV
Hyperspectral image classification based on gradient lifting decision tree and semi-supervise algorithm integration
The invention discloses a hyperspectral image classification based on gradient lifting decision tree and semi-supervise algorithm integration in order to solve the technical problem that hyperspectral image classification based on active learning and semi-supervise learning is low in classification precision. Hyperspectral image classification includes the steps that firstly, hyperspectral image data is input; secondly, features of sample points are extracted; thirdly, parameters of a gradient lifting decision tree classifier are trained; fourthly, massed learning sample points are classified; fifthly, the confidence degree of the sample points are assessed; sixthly, the sample points are screened through sparse representation; seventhly, a marked training set is updated; eighthly, a classification result is output. Assessment is conducted on the confidence degree of the unmarked sample points through the prediction result of the classifier and sparse representation, according to the confidence degree of the unmarked sample points, the sample points are divided into two sets for different kinds of processing, burdens for manual marking are reduced while classification precision is improved, and hyperspectral image classification can be used in the fields of geological survey, atmospheric pollution and like.
Owner:XIDIAN UNIV
Spatial spectrum attention hyperspectral image classification method based on Octave convolution
ActiveCN110516596AResolve accuracyAddressing weak robustnessClimate change adaptationScene recognitionOctaveHyperspectral image classification
The invention discloses a spatial spectrum attention hyperspectral image classification method based on Octave convolution, and solves the problems of large class spacing, small different class spacing and low classification accuracy in the prior art. The scheme is as follows: inputting images to be classified and preprocessing data, dividing a training set and a test set, constructing an Octave convolutional neural network, determining a loss function of the Octave convolutional neural network, training and updating the Octave convolutional neural network, testing the data of the test set, and completing hyperspectral image classification. According to the method, Octave convolution operation is used to reinforce feature representation, and a spatial attention mechanism and a spectral attention mechanism are introduced, so that the network can more accurately find an area which is more beneficial to classification and contains more comprehensive and detailed information. The method ishigh in classification precision and strong in robustness, and can be applied to analysis and management of hyperspectral image data.
Owner:XIDIAN UNIV
High-spectral image classification method based on improved deep learning model
InactiveCN108388917APreserve spatial spectral informationImprove stabilityCharacter and pattern recognitionNeural architecturesClassification methodsNetwork model
The invention provides a high-spectral image classification method based on an improved learning model, and relates to the technical field of high-spectral images. The method comprises that one or more convolution layer and pooling layer form an extracted image characteristic alternatively, the obtained image characteristic is extracted for multiple times randomly to form different classificationmodels, the different classification models are used to carry out classification, and classification results are voted to obtain a final classification result in the principle that the minority submitto the majority, and the deep learning network model is constructed. The high-spectral image data to be classified is reconstructed, space spectrum information of high spectrum images is maintained,the sparsity of the data is increased, and thus, the high spectral image is easy to process by the classification model. The method includes fewer calculation parameters, is higher in classification accuracy, and can be used to classify natural objects in the high spectral image finely.
Owner:NORTHEASTERN UNIV
A multispectral image classification method based on a double-channel multi-feature fusion network
InactiveCN107463948AIntegrity guaranteedEmbody Data FusionCharacter and pattern recognitionNeural architecturesData setMultispectral image
The invention provides a multispectral image classification method based on a double-channel multi-feature fusion network. The method comprises the steps of: fusing multispectral features of different wave bands of two satellites to obtain features L and L'; performing normalization processing on the L and the L' to obtain Lnorm and L' norm; selecting pixel blocks randomly on the Lnorm and the L' norm to form a training set and a validation set and form feature matrixes Wtrain and Wval based on image blocks and obtaining a feature matrix Wtest of a testing set according to a feature matrix of sao-paulo city; building a classification model of a double-channel all-convolutional neural network; training the classification model by using the feature matrix Wtrain of the training data set and the feature matrix Wval of the validation data set; classifying the feature matrix Wtest of the test data set by using the trained classification model. According to the invention, the double-channel all-convolutional neural network is used for multispectral image classification; compared with a common all-convolutional neural network, the double-channel all-convolutional neural network can increase the classification accuracy.
Owner:XIDIAN UNIV
Spatial spectrum fusion hyperspectral image classification method based on a three-dimensional deep residual network
InactiveCN109871830AAvoid the problem of training degradationSmall scaleCharacter and pattern recognitionSlide windowClassification methods
The invention belongs to the field of hyper-spectral intelligent perception, and particularly discloses a spatial spectrum fusion hyper-spectral image classification method based on a three-dimensional deep residual network, which comprises the following steps: S1, generating candidate frames by using a sliding window method, and generating a plurality of windows; S2, randomly dividing the windowinto a training set and test set data; S3, training a three-dimensional depth residual network (3D-CNN) based on the hyperspectral data in the training set; S4, inputting a test set sample into the classification model, The hyperspectral image classification method has the advantages that the characteristics of the input data are extracted and predicted, the spectral characteristics and the spatial spectrum characteristics of the hyperspectral image are extracted at the same time, the classification precision of the hyperspectral image is further improved, a residual network structure is introduced, and the problem of learning degradation in a traditional hyperspectral classification neural network is solved. The hyperspectral image target classification method is clear in structure and easy to implement, the structural characteristics of the hyperspectral image can be fully utilized, and the hyperspectral image target classification precision is remarkably improved while the calculation time is shortened.
Owner:NAT UNIV OF DEFENSE TECH
Multi-spectral image classification method based on threshold self-adaption and convolutional neural network
ActiveCN107392130AImprove classification accuracyConform to the average characteristicScene recognitionNeural architecturesProbit modelData set
The invention discloses a multi-spectral image classification method based on threshold self-adaption and a convolutional neural network. The method comprises the following steps of inputting multispectral images of different time phases and different wave bands of satellites to be classified, and carrying out normalization on all pixels of a marked portion of a same wave band image in all cities; stacking selected 9 wave bands into one image and taking the image as a training data set; constructing a classification model based on the convolutional neural network, using the training data set to train the classification model so as to acquire a probability model based on OSM, using the model and a confidence coefficient strategy to adjust a softmax output result and acquiring a final classification model, and finally, uploading a test result to an IEEE website so as to acquire classification accuracy. By using the multi-spectral image classification method, characteristics that there are a lot of wave bands, a data volume is large and there are a lot of information redundancy in the multispectral images are fully used so that a problem that surface features of complex types are difficult to classify is solved, classification accuracy is increased, an error dividing rate is reduced and a classification speed can be increased.
Owner:XIDIAN UNIV
Hyperspectral image classification method based on spatial information enhancement and deep belief network
ActiveCN107145830AImprove performanceImprove classification accuracyCharacter and pattern recognitionNeural learning methodsMachine learningMultispectral image classification
The invention discloses a hyperspectral image classification method based on spatial information enhancement and a deep belief network and mainly solves a problem that the accuracy improvement of the hyperspectral image classification in the existing technology is not obvious. The technical scheme is as follows: the method comprises the following steps of 1) carrying out normalization and band selection on an original hyperspectral image to obtain a hyperspectral image with a reflectance value of 0 to 1; 2) carrying out spatial information enhancement on the hyperspectral image through band grouping and ground and guided filtering; 3) constructing a deep belief network model according to the features of the hyperspectral image after spatial information enhancement; and 4) carrying out model training on the hyperspectral image after spatial information enhancement and utilizing the obtained model to carry out category prediction in order to obtain a classification result. According to the method, the spatial information of the hyperspectral image is effectively enhanced without losing the original spectral information, the classification accuracy is remarkably improved, and the method can be used for environment, climate, agriculture and mineral exploration.
Owner:XIDIAN UNIV
Pest image classification method and pest image classification system based on morphological multi-feature fusion
InactiveCN104102920AImprove robustnessImprove accuracyCharacter and pattern recognitionContextual image classificationClassification methods
The invention relates to a pest image classification method based on morphological multi-feature fusion. The method comprises the following steps that: a training process is carried out: data in a training image set is subjected to image segmentation, the segmented training images are subjected to preprocessing, morphological features of the training images are extracted, and a training image feature matrix is obtained through the multi-morphological-feature fusion; a test process is carried out: test images to be recognized are input, the test images are subjected to image segmentation and preprocessing, morphological features of the test images are extracted, and a test image feature matrix is obtained through multi-morphological-feature fusion; a pest type is recognized: the similarity between the test image feature matrix and the training image feature matrix is calculated, the class with the highest similarity is found out, and the pest type and the control method are obtained according to the similarity. The invention also discloses a pest image classification system based on the morphological multi-feature fusion. The method and the system provided by the invention have the advantages that the pest recognition rate and the program robustness are improved; and the actual application value of pest recognition in agricultural production is improved.
Owner:HEFEI INSTITUTES OF PHYSICAL SCIENCE - CHINESE ACAD OF SCI
Multispectral image classification method based on adaptive feature fusion residual network
ActiveCN108830330AEasy to trainThe testing process is simpleCharacter and pattern recognitionPattern recognitionData set
The invention discloses a multispectral image classification method based on an adaptive feature fusion residual network, which mainly solves the problems of low universality and insufficient utilization of multi-level features in the prior art. The multispectral image classification method comprises the specific steps of (1) inputting a multispectral image; (2) performing normalization processingon the multispectral image; (3) selecting training samples and testing samples; (4) generating a training data set; (5) constructing a basic residual network; (6) constructing an adaptive feature fusion network; (7) generating an adaptive feature fusion residual network; (8) training the adaptive feature fusion residual network; (9) generating a testing data set; and (10) performing classification on the testing data set. The multispectral image classification method can adaptively fuse the multi-level features, extracts features with better discrimination and richer semantic information andhas the advantages of simple training and testing process and sufficient feature utilization.
Owner:XIDIAN UNIV
Image classification method based on three-side filter and stacked sparse autocoder
ActiveCN106503734AImprove stabilityThe result is accurateScene recognitionArtificial lifeHyperspectral data classificationClassification methods
The invention provides an image classification method based on a three-side filter and a stacked sparse autocoder. The method comprises: a smooth image is obtained by using a three-side filter, and Gaussian, speckle, pulse noises of a degraded image are filtered while a spectral-spatial feature of a pixel of the image is extracted; high-order feature extraction is carried out by using an improved stacked sparse autocoder; and supervised network fine tuning and classification are carried out by using a random forest classifier. According to the method provided by the invention, the improved stacked sparse autocoder and the random forest classifier are introduced into the hyperspectral data classification to form depth learning architecture; the improved stacked sparse autocoder can extract abstract and useful underlying features of spectroscopic data layer by layer, thereby improving the classification performance of the spectroscopic data. The method is not only suitable for hyperspectral image classification but also suitable for other image classification and has high transportability; and the image classification demand can be satisfied easily.
Owner:HARBIN ENG UNIV
3DCNN (three-dimensional convolutional neural network)-based high-spectral image space spectrum combined classification method
ActiveCN106022355AImprove classification accuracySolve space problemsCharacter and pattern recognitionDimensionality reductionClassification methods
The invention relates to a 3DCNN (three-dimensional convolutional neural network)-based high-spectral image space spectrum combined classification method. According to the feature that high-spectral image data is of a three-dimensional structure, the three-dimensional convolutional network suitable for a high-spectral image is constructed and high-spectral image space spectrum combined classification is completed. First of all, data blocks within a certain neighborhood scope, taking a pixel to be classified as a center, are extracted from an original high-spectral image as initial space spectrum features, and through combination with a label of the pixel to be classified, the constructed 3DCNN is trained. Then, by use of the trained 3DCNN, the high-spectral image space spectrum combined classification is completed. The method has the following advantages: 1, the problem of need of complex processing of spectrum space dimension reduction or compression in the prior classification arts is solved; 2, the 3DCNN suitable for the high-spectral image data of the three-dimensional structure is constructed, rich information of the high-spectral image is fully utilized, and the trouble of manual set of features in advance is omitted; 3, the 3DCNN-based high-spectral image space spectrum combined classification method enlarges the application scope of depth learning and also provides a new approach for high-spectral image classification; and 4, the high-spectral image classification precision is improved.
Owner:NORTHWESTERN POLYTECHNICAL UNIV
Hyperspectral image classification method based on spatial feature iteration
ActiveCN106408034AImprove classification accuracyCharacter and pattern recognitionMultispectral image classificationClassification result
The invention discloses a hyperspectral image classification method based on spatial feature iteration. The hyperspectral image classification method comprises the steps of: calculating spectral signatures di of ground feature categories according to hyperspectral sample data; setting a category target set, a background end member set and a color constraint matrix; defining a classifier Tk capable of classifying multiple categories simultaneously by utilizing background end members U of a hyperspectral image, the constraint matrix C and an image autocorrelation inverse matrix R<-1>, extracting initial classification results of all category targets, extracting a spatial feature {Tk(iG)}of the classification result of each category target, and then feeding back and superposing the spatial features {Tk(iG)} into the hyperspectral image to be classified for carrying out fusion of the spatial features and inter-spectrum features; classifying multiple categories simultaneously by adopting an iteration mode until a set iteration stopping condition is reached; and marking classification results by using different colors. The hyperspectral image classification method effectively utilizes the method of fusing the spectral statistical features and the iteration spatial features to perform hyperspectral image category feature judgment, and gradually improves the accuracy of hyperspectral image classification.
Owner:DALIAN MARITIME UNIVERSITY
Multispectral image classification method based on deep integrated residual network
ActiveCN107832797AOvercoming the disadvantages of complex and time-consumingUniversalCharacter and pattern recognitionForeign matterData set
The present invention discloses a hyperspectral image classification method based on a deep integrated residual network. Defects are overcome that human selection of weak classifiers and design of anintegration method are complex and time-consuming, the computation process is tedious and a classification result has phenomena of the same object with different spectra characteristics and differentobjects with the same spectra characteristic caused by a semi-supervised training mode in the prior art. The implementation of the method comprises the steps of: (1) inputting multispectral images; (2) performing ground object target removal normalization processing of images of each wave band of each multispectral image; (3) obtaining a multispectral image matrix; (4) obtaining a data set; (5) establishing a deep integrated residual network; (6) training the deep integrated residual network; and (7) performing classification of the test data set. The multispectral image classification methodbased on the deep integrated residual network has complete multispectral image features for learning, is more concise and much clearer in process, allows a classification effect to be more accurate, and can be used for classification of hyperspectral images.
Owner:XIDIAN UNIV
Space spectrum combined feature extracting method for hyperspectral images
ActiveCN106682675AImprove utilizationImprove classification accuracyCharacter and pattern recognitionPrincipal component analysisHyperspectral image classification
The invention discloses a space spectrum combined feature extracting technology for hyperspectral image classification and belongs to a field of remote sensing image processing. The method includes steps of 1, utilizing pixel coordinates to generate an abscissa image and an ordinate image; 2, calculating the statistic features of the hiyperspectral images; 3, performing range stretching on the abscissa image and the ordinate image by utilizing the statistic features; 4, inserting the coordinate images into an initial hyperspectral images; 5, performing fusion and extraction on the feature by utilizing principal component analysis. According to the invention, hyerspectral image space features are converted to spectrum features and fusion of the space features and the spectrum features is realized by utilizing the principal component analysis method, so that a problem of insufficient use of hyperspectral image classification space features is solved. The method is good in adaptability and simple in calculation, and can improve hyperspectral image classification precision effectively.
Owner:NO 54 INST OF CHINA ELECTRONICS SCI & TECH GRP
High-spectral image classification method based on discrimination and robust multi-feature extraction
ActiveCN108830320AFully excavatedFully mine complementary informationCharacter and pattern recognitionAcquired characteristicClassification methods
The invention provides a high-spectral image classification method based on discrimination and robust multi-feature extraction. Different spatial spectral features in high-spectral images are projected into a common low-rank discrimination subspace, and significance of the different features is remained. The method comprises that the features are assigned with different weights according to the significance; a low-dimensional subspace with robust and discrimination features is learned; the different features are projected to the low-dimension subspace; and a support vector machine is used to classify the new features. The dimensions of the features are reduced, noise robustness is realized, noise interference in the high-spectral image can be defended, the significance of different features can be maintained, the obtained features has discrimination characteristic via exiting labels, and the classification effect is improved effectively.
Owner:上海蓝长自动化科技有限公司
Hyperspectral image classification-oriented data adaptive activation function learning method
ActiveCN110443296AImprove classification accuracyImprove classification resultsCharacter and pattern recognitionNeural architecturesData setActivation function
The invention discloses a hyperspectral image classification-oriented data adaptive activation function learning method, which is used for solving the technical problem of poor accuracy of an existinghyperspectral image classification method. According to the technical scheme, spectral information and spatial information of hyperspectral data are utilized, and hyperspectral image classification is carried out by learning an activation function based on specific data. By analyzing a common activation function, it is found that the activation function can be represented in the mode that activation mapping is multiplied by input features. Therefore, activation mapping is learned by constructing a two-layer neural network. The neural network learns from two aspects of channels and spectrums,and activation functions conforming to the characteristics of the channels and the spectrums are constructed respectively, so that the image classification accuracy is improved. Tests show that on anIndian Pines data set, the classification accuracy of the activation function based on the channel and the spectrum is averagely improved by 2.17% and 4.03% respectively.
Owner:NORTHWESTERN POLYTECHNICAL UNIV
A Method for Preparing Typical Object Reference Map Using Multispectral Image Classification
ActiveCN103090868BSolve problems that cannot be directly identifiedExcellent matching recognition performanceNavigational calculation instrumentsCharacter and pattern recognitionReference mapContextual image classification
The invention discloses a method for preparing a typical ground object reference picture by using multispectral image classification. An interesting type is extracted from a multispectral image and is taken as a landmark, and the reference picture comprising the landmark can be prepared and is used for indirectly positioning and identifying a target. The method specifically comprises the following steps of: selecting the interesting type from the multispectral image, extracting a spectral-spatial texture characteristic of the interesting type, and classifying the multispectral image according to the extracted spectral-spatial texture characteristic; on the basis of classification, extracting the complete interesting type, and taking the interesting type as the interesting type of the landmark according to a landmark selection rule; calculating an infrared radiation amount of the landmark under an atmospheric parameter condition by using an infrared radiation formula according to a landmark material type; and mapping the infrared radiation amount to obtain a gray scale value, and preparing the reference picture comprising a landmark shape, the gray scale of the landmark shape and a background gray scale. According to the method, accuracy and automation are relatively high, and the performance of a matching and identification algorithm based on the reference picture can be improved.
Owner:HUAZHONG UNIV OF SCI & TECH
3dcnn-based spatial-spectral joint classification method for hyperspectral images
ActiveCN106022355BImprove classification accuracyCharacter and pattern recognitionDimensionality reductionClassification methods
The invention relates to a hyperspectral image space-spectrum joint classification method based on 3DCNN. Aiming at the characteristic that hyperspectral image data is a three-dimensional structure, a three-dimensional convolutional network suitable for hyperspectral images is constructed to complete hyperspectral image space-spectrum joint classification. First, from the original hyperspectral image, a data block in a certain neighborhood centered on the pixel to be classified is extracted as the initial spatial spectral feature, and the 3DCNN network constructed is trained in combination with the label of the pixel to be classified. Then, the hyperspectral image space-spectrum joint classification is accomplished using the trained 3DCNN. Beneficial effects are: 1) solve the complex processing problem of spectrum space dimensionality reduction or compression in the existing classification technology; Rich information and saves the trouble of artificially pre-setting features; 3) 3DCNN-based hyperspectral image space-spectrum joint classification method. 4) The hyperspectral image classification accuracy is improved.
Owner:NORTHWESTERN POLYTECHNICAL UNIV
A non-local weighted joint sparse representation method for hyperspectral image classification
ActiveCN109145945AReduce distractionsOvercome a series of problems caused by too high dimensionalityCharacter and pattern recognitionSensing dataData information
The embodiment of the invention discloses a non-local weighted joint sparse representation hyperspectral image classification method. Firstly, an adaptive threshold value is obtained according to a training sample; then, the threshold and cross-window similarity methods are used to exclude the points with large class differences and calculate the weights of the remaining points; then the joint signal matrix is obtained by weighting the points in the search window with the obtained weights; finally, the joint sparse signal matrix is used for joint sparse representation classification, and the classification of the center points to be measured is obtained. As the spectral angle between pixel is used to replace the Euclidean distance to measure the similarity between pixel, the data information of the hyperspectral remote sensing data is fully utilized, a series of problems caused by the hyperspectral remote sensing data are overcome, the classification effect of the sparse representationis ideal, and the interference of the heterogeneous points to the center point to be measured is well reduced.
Owner:SHANTOU UNIV
Multispectral image classification method based on adaptive feature fusion residual network
PendingCN121962772AEasy extractionovercome limitationsNeural learning methodsNetwork modelMachine learning
The invention provides a multispectral image classification method based on an adaptive feature fusion residual network, and belongs to the technical field of computer vision and remote sensing image processing. The method comprises the following steps: firstly, preprocessing an original multispectral image; then, a novel adaptive feature fusion residual network model is constructed, the core of the model comprises a dual-path feature extraction backbone network, and spectral features and spatial context features are extracted respectively; a self-adaptive feature fusion module is introduced, multi-level features from double paths are dynamically learned and fused through a channel attention mechanism, and optimal integration of spectral information and spatial information is achieved; and finally, completing pixel-level or image-level classification by using the fused advanced features. According to the method, the problems of insufficient utilization of spectrum-space joint features of multispectral data and weak model generalization ability of a traditional method are effectively solved, and the precision and robustness of multispectral image classification are remarkably improved.
Owner:JIANGSU UNIV OF SCI & TECH
A discriminant Gabor filtering method for hyperspectral image classification
InactiveCN109002775AImprove discrimination abilityConform to data characteristicsScene recognitionPattern recognitionSupport vector machine classifier
The invention discloses a discriminant Gabor filtering method for hyperspectral image classification, which comprises the following steps: reading hyperspectral image data and preprocessing; decomposing the standard three-dimensional Gabor filter into eight sub-filters; taking the CCS component (spatial low-pass, spectral dimension band-pass) of one of that sub-filters to construct a discriminantGabor filter; using different frequency amplitudes, different frequencies empty-spectral space direction, and discriminant Gabor filters at different scales to filter hyperspectral images respectively; taking the amplitude as the features, and obtaining the feature blocks under different parameters; connecting and merging feature blocks with different frequency parameters (frequency amplitude anddirection) at the same scale; selecting the scale parameters by a cross-validation method, and obtaining the optimal scale parameters, and using the features under the optimal scale parameters as thefinal discriminant Gabor features; finally, using a support vector machine classifier or least square classifier to classify the discriminant Gabor features of hyperspectral images. The method effectively improves the classification accuracy of the hyperspectral image.
Owner:SOUTH CHINA UNIV OF TECH
Multispectral Image Classification Method Based on Adaptive Threshold and Convolutional Neural Network
ActiveCN107392130BConform to the average characteristicReduce distractionsScene recognitionNeural architecturesData setClassification methods
The invention discloses a multi-spectral image classification method based on threshold self-adaptation and convolutional neural network, which inputs multi-spectral images of satellites to be classified in different time phases and different bands, and converts the marked parts of the same band images of all cities All pixels are normalized; the selected 9 bands are stacked into an image as a training data set; a classification model based on convolutional neural network is constructed, and the training data set is used to train the classification model to obtain a probability model based on OSM. The model and the confidence strategy adjust the softmax output results to obtain the final classification model, and finally upload the test results to the IEEE website to obtain the classification accuracy. The multi-spectral image classification method provided by the present invention makes full use of the characteristics of multi-spectral image with multiple bands, large data volume, and large information redundancy, and solves the problem that it is difficult to classify complex types of ground objects, and can not only improve the classification accuracy , Reduce the misclassification rate, and can also improve the classification speed.
Owner:XIDIAN UNIV
Multispectral multi-label classification method based on low confusion and spatial spectral self-balancing
ActiveCN121033559BCharacter and pattern recognitionNeural learning methodsFeature learningClassification methods
The application discloses a multispectral multi-label classification method based on low confusion and spatial spectrum self-balancing, belongs to the technical field of meteorological remote sensing image classification, and relates to a spectral convolution network used for efficiently extracting spectral features, a query generation module used for effectively improving the expression capability of label query, a multilayer perceptron used for mapping label embedding into a query vector, and cross-correlation constraints used for reducing the similarity between label queries; in order to sufficiently mine spatial and spectral features, a three-branch network is designed, including a spatial branch, a spectral branch and a comprehensive branch; each branch independently carries out feature learning, and the prediction results of each branch are fused through a branch balance voting mechanism; the training effect of a weak branch is enhanced through the interaction between branches; and finally, more accurate classification results are obtained. In the meteorological multispectral image classification task, especially in the identification of complex meteorological system categories, the application can accurately classify weather systems, ground coverings and clouds.
Owner:ZHEJIANG UNIV OF TECH
Hyperspectral Image Classification Method Based on Ridgelet and Deep Convolutional Networks
ActiveCN105069468BOvercome the neglect of effective use of spatial informationImprove classification accuracyCharacter and pattern recognitionComputation complexityClassification methods
The invention discloses a hyperspectral image classification method based on ridgelet and deep convolution network, which mainly solves the problems of low classification accuracy and high computational complexity of hyperspectral image classification in the prior art. The implementation steps are: 1. Select training samples in the hyperspectral image; 2. Extract the spectral information and spatial information of the training samples; 3. Combine the spectral information and spatial information to form a training sample set; 4. Construct a five-layer deep convolutional network , and design a ridgelet filter to initialize the network; 5. Use the training sample set to train the constructed neural network; 6. Classify the remaining samples with the trained neural network to complete the image classification. The invention has the advantages of high classification accuracy and fast classification speed, and can be used in meteorological monitoring, environmental monitoring, urban planning and disaster prevention and reduction.
Owner:XIDIAN UNIV
Multi-spectral image acquisition and processing method of contact image sensor
ActiveCN103632433BReduce noiseFilter out noiseCharacter and pattern recognitionField-programmable gate arrayMultispectral image classification
The invention belongs to the field of financial tools and discloses a multispectral image acquisition and processing method for a contact image sensor, aiming at solving the defects in the prior art that noise points exist in an acquired image, overall brightness difference between segments of the acquired image is great, and images of the same paper money under different light sources cannot synchronously acquired. The method comprises the following steps: an upper multiple-light-source CIS image sensor and a lower multiple-light-source CIS image sensor which are symmetrical to each other are arranged to acquire original images; acquired analog signals are subjected to filtering and then are sent to two independent A / D sampling modules to be quantized so as to obtain digital signals; the A / D sampling modules send the digital signals to a FPGA (Field Programmable Gate Array) for compensating, splicing, compressing and storing; the FPGA sends the signals to a main control chip; the main control chip puts the two-path information into two independent address areas of an external RAM (Random Access Memory) for caching; after whole images are acquired, a DSP (Digital Signal Processor) takes out the images from the external RAM to process. The multispectral image acquisition and processing method has the advantages that the acquired images have less noise; the images of the paper money under different light sources can be synchronously acquired; the acquired images are relatively smooth and the quality of the images is relatively high.
Owner:尤新革
Classification method and device for fusing panchromatic images and multispectral images
InactiveCN104794481BEfficient use ofReduce dependenceCharacter and pattern recognitionClassification methodsMultispectral image
The present invention provides a classification method and device for fusing panchromatic images and multispectral images, wherein the classification method for fusing panchromatic images and multispectral images includes: collecting panchromatic images and multispectral images of the area to be measured; Segment the panchromatic image to obtain an over-segmented volume of the panchromatic image; merge the over-segmented volumes of the panchromatic image to determine a segmented volume unit; perform segmentation on the multispectral image according to the segmented volume unit classification, obtaining classification labels of the multi-spectral image; wherein, the segmented volume unit includes at least one over-segmented volume. Through the classification method and device for fusing panchromatic images and multispectral images provided by the present invention, the spatial information of panchromatic images can flow to the multispectral image classification process, and the spatial information and multispectral images in panchromatic images can be fully and effectively utilized. The spatial information in the image reduces the dependence of image classification on spectral information, improves the accuracy of classification, and makes the classification labels clear.
Owner:BEIJING NORMAL UNIVERSITY
Multispectral Image Classification Method Based on Recoding and Deep Fusion Convolutional Networks
ActiveCN107358204BImprove generalization abilityImprove classification accuracyScene recognitionNeural architecturesPattern recognitionData set
The invention discloses a multi-spectral image classification method based on data recoding and deep fusion convolutional network, which stacks data of different bands in multi-spectral images to be classified to obtain three-dimensional image features FA; input the multi-spectral image to be classified Classify auxiliary data; then encode to obtain the three-dimensional image feature FB; combine the three-dimensional feature matrix FA and FB obtained after processing the two data sources as the input feature F; normalize F, and normalize the normalized feature Each element in the matrix F1 takes a block to form a feature matrix F2 based on the image block; according to F2, the feature matrix W1 of the training data set and the feature matrix W2 of the test data set are obtained; a classification model based on a multi-scale depth filter is constructed; The feature matrix W1 of the training data set is used to train the classification model; the feature matrix W2 of the test data set is used to classify the trained classification model. The invention improves the classification accuracy of the multi-spectral remote sensing images and can be used for classification of ground objects.
Owner:XIDIAN UNIV
Hyperspectral Image Classification Method Based on Local Cooperative Representation and Neighborhood Information Constraint
ActiveCN103065160BReduce the numberGuaranteed structural performanceCharacter and pattern recognitionComputation complexityTest sample
Owner:XIDIAN UNIV
