182 results about "Terrain classification" patented technology

The invention provides an SAR image terrain classification method based on a depth RBF network. The method mainly solves the problem of the prior art that the accuracy of classification is low. The method comprises the steps of (1) extracting the texton features of an SAR image; (2) training the texton features of the SAR image through a first-layer RBF neural network of the depth RBF network to obtain the advanced features of the image; (3) training the advanced features through a second-layer sparse autocoder network SAE of the depth RBF network to obtain more advanced features of the image; (4) training the more advanced features through a third-layer RBF neural network of the depth RBF network to obtain the terrain classification features of the image; (5) comparing the terrain classification features of an image test sample with a test sample label, adjusting the parameters of each layer of the depth RBF network, and obtaining an optimal test classification accuracy. The method is high in classification accuracy and can be used for complicated image classification.

The invention discloses a sparse dynamic ensemble selection-based SAR (synthetic aperture radar) image terrain classification method, which mainly solves the problem that the speed of the conventional dynamic ensemble selection algorithm and the conventional dynamic classifier selection algorithm for terrain classification in SAR images is low. The implementation process of the sparse dynamic ensemble selection-based SAR image terrain classification method is as follows: (1) a wavelet energy feature is extracted from an SAR image to be classified; (2) training data is acquired from the SAR image to be classified; (3) the SAR image to be classified is regionalized to obtain data to be classified; (4) training samples are utilized to learn ensemble systems; (5) a dictionary is learnt for each class of training data, and a synthetic dictionary is obtained; (6) dynamic ensemble selection is carried out on each atom in the synthetic dictionary; (7) samples to be classified are sparsely coded; (8) the samples to be classified are marked according to a sparse coefficient and classifier ensembles corresponding to the atoms; (9) the marks of the samples to be classified are mapped onto pixels in the SAR image, so that a terrain classification result is obtained. The sparse dynamic ensemble selection-based SAR image terrain classification method has the advantages of high speed and good classification effect, and can be used for SAR image target identification.

The invention discloses a polarization SAR image classification method based on a deep neural network. The method mainly solves the problems that traditional polarization SAR image classification accuracy is low and boundaries are disorderly. The method includes the classification steps that a power diagram I is acquired from polarization SAR data through Pauli decomposition, the power diagram I is segmented in advance, and then a plurality of small blocks are acquired; a training data set U is selected from a polarization SAR image, input into a two-layer self-coding structure for training and then classified through a Softmax classifier; a test data set V is selected from the polarization SAR image and input into the trained two-layer self-coding structure, and then classification labels are acquired through the Softmax classifier; in the pre-segmented small blocks, the classification labels and channel information of the power diagram I are combined, and then small block labels are acquired. The polarization SAR image classification method has the advantages that the recognition rate is high, result region consistency is good, and the method can be used for polarization SAR homogeneous region terrain classification.

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.

The invention discloses a high-resolution SAR terrain classification method based on multiscale convolution and feature fusion, and mainly aims at solving the problem in the prior art that the classification precision is low and overfitting easily occurs. The high-resolution SAR terrain classification method comprises the steps of 1, extracting textural features and wavelet features of to-be-classified images; 2, fusing the to-be-classified images, the textural features and the wavelet features to constitute a fusion feature matrix; 3, according to the fusion feature matrix, constructing a training dataset and a testing dataset; 4, adding a multiscale convolution layer and a shuffle layer to an existing CNN network, changing a full-joint layer into a convolution layer, and constructing a multiscale convolution fusion network; 5, using the training dataset to train the multiscale convolution fusion network to obtain model parameters; 6, using the model parameters to initialize the multiscale fusion network to classify a test set. By means of the high-resolution SAR terrain classification method based on the multiscale convolution and the feature fusion, the parameters of the networkare reduced, the overfitting phenomenon of a small sample problem is solved, the classification precision is improved, and the high-resolution SAR terrain classification method can be applied to high-resolution SAR image terrain classification.

The invention discloses a multispectral remote sensing image terrain classification method based on spectrum and textural features. A quadtree partitioning technology is adopted in the method to carry out multistage partitioning processing on images, spectrum and textural features of land features are extracted in an image block mode, an SVM classifier is adopted to conduct land feature classification on image blocks, and classification marginal regions of the image blocks are processed through a region growing method. Compared with the prior art, the multispectral remote sensing image terrain classification method has the advantages that anti-noise performance of spectral signatures and textural features in land feature classification is improved, the problem of sizes of textural feature extraction windows is avoided, and classification result regions are high in consistency and low in noise.

The invention puts forward a polarized SAR (Synthetic Aperture Radar) image classification method based on an SLIC (Software Licensing Internal Code) and an improved CNN (Convolutional Neural Network), and is used for solving the technical problem of low classification speed and low classification accuracy in an existing supervised polarized SAR image classification method. The method comprises the following steps that: firstly, taking the Wishart distance and the polarization feature of a polarized SAR image as new data, carrying out Lee filtering on the new data, and inputting the new data into an improved CNN to be classified so as to obtain a preliminary classification result; then, carrying out SLIC superpixel segmentation on the pseudo-color image of the polarized SAR image to obtain a superpixel segmentation result; and finally, utilizing the superpixel segmentation result to carry out constraint post-processing on the preliminary classification result to obtain a final classification result. The method is high in classification speed and accuracy, and can be used for fields including polarized SAR terrain classification and the like.

The invention discloses a polarization SAR image classification method based on RBM and SVM, mainly solving the problem of the existing polarization SAR image classification method that the classification precision is low. The method comprises the steps as follows: (1) inputting the polarization SAR image to be classified, having delicate polarization Lee filtering operation; (2) resolving and extracting original feature of each pixel point and integrating based on the polarization coherence matrix, polarization covariance matrix and Cloude; (3) initializing and training RBM to obtain the related parameter; (4) classifying by using SVM according to the feature learned by the RBM to obtain the classification result. Compared with the existing method, the space dependency of the image is totally considered and the feature in favour of classifying polarization SAR image can be extracted, the polarization SAR image classification precision is obviously raised, the method can be used for terrain classification and object identification for polarization SAR image.

The invention belongs to the technical field of remote sensing image processing and in particular relates to a manifold dimension reduction method of hyperspectral images based on image block distance. According to the method, a novel distance measure, namely an image block distance measure is provided and is applied to neighborhood selection and lower dimension coordinate embedding in manifold learning, and a nonlinear dimension reduction method of novel hyperspectral remote sensing images is obtained. The physical properties of the hyperspectral images are utilized, the spectral information and space information of the images are combined, the local characteristics between data points can be better kept, and the characteristics of an original data set are well kept on the basis of reducing the image information redundancy to the greatest degree. The method has high applicability on various different hyperspectral data, and has important application values in detection and identification aspects of high-precision terrain classification and ground targets based on the hyperspectral remote sensing images.

The invention discloses a remote sensing image terrain classification method based on a lightweight semantic segmentation network, and mainly solves the problems of low remote sensing image terrain classification precision and low training speed caused by insufficient utilization of image space and channel feature information and a huge model in an existing method. According to the scheme, the method includes obtaining a training sample and a test sample in a remote sensing image terrain classification data set; constructing and introducing a lightweight remote sensing image terrain classification model capable of broadening channel decomposition hole convolution, and designing an overall loss function of a concerned terrain edge; inputting a training sample into the constructed terrain classification model for training to obtain a trained model; and inputting the test sample into the trained model, and predicting and outputting a terrain classification result in the remote sensing image. According to the method of the invention, the feature expression capability is improved, the network parameters are reduced, the average precision and the training speed of remote sensing image terrain classification are improved, and the method can be used for obtaining the terrain distribution condition of a remote sensing image.

The invention discloses a method for classifying polarimetric SAR (synthetic aperture radar) images on the basis of Cloude decomposition and K-wishart distribution and mainly solves the problem that the prior art is poor in classification effect and high in computation complexity. The method includes the steps of firstly, reading a polarimetric SAR image to be classified, subjecting each pixel of the image to Cloude decomposition to obtain an entropy H and a scattering angle alpha; secondly, initially partitioning the polarimetric SAR image according to the values of the entropy H and the scattering angle into eight classes; thirdly, subjecting results of eight classes of the whole polarimetric SAR image to iteration to obtain more accurate classification results. Compared with classic classification methods, the method is stricter in partitioning the polarimetric SAR image, better in classification effect, lower in computation complexity and applicable to terrain classification and target recognition of the polarimetric SAR images.

A semi-supervised polarization SAR terrain classification method based on full convolution GAN is implemented by the following steps: performing refined Lee filtering; inputting polarization SAR data;constructing a generation network G; constructing a discrimination network D; training and testing the networks and calculating classification accuracy rate. Compared with the semi-supervised Co-training classification method in the prior art, the invention improves the classification accuracy of polarization SAR data of the polarized synthetic aperture radar, solves the problem of insufficient utilization of polarization information, enhances the robustness of the model to the input data, and has the effect of end-to-end classification. The invention can be applied to the terrain classification of polarized synthetic aperture radar polarized SAR data.

The invention discloses a semi-supervised deep learning method based on semi-supervised sparse filtering. The method solves a technical problem that a conventional deep learning method is complex in parameter regulation and low in classification precision when having low label data, and comprises steps of: inputting polarized SAR image data to be classified; extracting a training sample and a testing sample; solving the Wishart neighbor sample of the training sample; initializing the parameter of a deep sparse filtering network; pre-training the deep sparse filtering network; fine regulating the deep sparse filtering network; predicting the classification of the testing sample; and outputting the classification image and the classification precision of the polarized SAR image to be classified. The method, by constructing the novel deep sparse filtering network and adding a semi-supervised regular term to a pre-training process, reduces parameter regulation complexity of the deep learning network, increases polarized SAR image terrain classification, and can be used in the technical fields of environment monitoring, earth resource exploration, military systems and the like.

The invention belongs to the technical field of remote sensing image processing and particularly relates to a dimension reducing and sorting method of a hyperspectral imagery based on blocking low rank tensor analysis. According to the dimension reducing and sorting method of the hyperspectral imagery based on the blocking low rank tensor analysis, a blocking idea is introduced into a dimension reducing method of the hyperspectral imagery based on the low rank tensor analysis according to three-dimensional data structures, spectral characteristics and correlated characteristics of local spaces of the hyperspectral imagery, the problems that integral spatial correlation of the imagery is weaker and negative effects of configuration of dimension-reduced subspace dimension on a dimension reducing effect are overcome, finally a novel dimension reducing method capable of greatly improving total sorting precision of the imagery is realized, and the novel dimension reducing method is a blocking low rank tensor analysis method. An algorithm presents well applicability on various different hyperspectral data (including simulation data and actual data sets). The dimension reducing and sorting method of the hyperspectral imagery based on the blocking low rank tensor analysis has important application values in high-precision terrain classification aspects based on the hyperspectral imagery.

The invention discloses a polarized SAR (Synthetic Aperture Radar) image classification method on the basis of an SAE (Stake Auto-Encoder) and IDL (Inbalanced Data Learning). The polarized SAR image classification method comprises the following implementing steps: (1) preprocessing; (2) training parameters of the SAE; (3) extracting characteristics; (4) training parameters of a Softmax classifier; (5) acquiring a classification result I; (6) establishing an IDL model; (7) training the IDL model; (8) acquiring a classification result II; (9) outputting a final classification result. The polarized SAR image classification method adopts the SAE to extract the characteristics capable of more substantially describing an original input; moreover, the polarized SAR image classification method solves the problem of large classification accuracy difference between classes, which is caused by class unbalance of a training sample set, and has the advantage of improving classification accuracy and region consistency; and the polarized SAR image classification method can be applied to the fields of terrain classification, target detection, identification and the like of a remote sensing image.

The invention provides a hyperspectral image demixing method and system based on abundance significance analysis. The method comprises the steps of establishing an end member spectrum bank of a hyperspectral remote sensing image to be processed; conducting preliminary mixed pixel decomposition on each pixel with the sparse regression-based mixed pixel decomposition method, ranking abundance values in a descending order, conducting significance analysis on the abundance sequence obtained through ranking to obtain the critical value of significance abundance, and then judging a sparse representation end member subset constituting the pixel according to a preset significance abundance threshold value; finally, conducting mixed pixel decomposition again with the abundance restraint type least square method, and taking the result as the final mixed pixel decomposition result. By the adoption of the method and system, a more sparse and accurate pixel representation end member subset can be obtained, hyperspectral remote sensing image mixed pixel decomposition precision can be improved, and the method and system have significant application value in high-precision terrain classification and ground target detection and recognition based on hyperspectral remote sensing images.

The invention provides a high-resolution SAR image classification method based on sparse features and conditional random fields. The method mainly solves the problems of low classification precision and non-accurate boundary retention in complicated scenes in the prior art. The method comprises the steps of: firstly, inputting high-resolution SAR images, selecting images to build a training data block set, and training system parameters of a sparse feature extraction algorithm; secondly, extracting SAR image block sparse features and training a logistics classifier to obtain the classificationposterior probability of the images and build a univariate potential energy function; thirdly, building a bivariate potential energy function by using a boundary constraint map obtained after fusionof a binary edge partition map and an edge strength map; forming a complete full connection conditional random field model by using the univariate potential energy function and the bivariate potentialenergy function and performing reasoning on the model to obtain a classification result. The method increases the classification precision of complicated scenes and edge details of high-resolution SAR images and can be used for SAR image terrain classification.

The present invention discloses a multispectral image and full-color image fusion method based on dual sparse non-negative matrix factorization and mainly solves the problems that space information is fuzzy and a spectrum is distorted in the prior art. The multispectral image and full-color image fusion method comprises the steps of: (1) respectively inputting a multispectral image with a low spatial resolution ratio, a full-color image with a high spatial resolution ratio, a spectrum degenerate matrix and a spatial degenerate matrix; (2) respectively carrying out partitioned column vectorization on the multispectral image with the low spatial resolution ratio and the full-color image with the high spatial resolution ratio; (3) carrying out dual sparse non-negative matrix factorization on the images subjected to column vectorization so as to obtain a dictionary with a high spatial resolution ratio and a coefficient matrix with spectral information; and (4) multiplying the dictionary with the high spatial resolution ratio by the coefficient matrix with the spectral information so as to obtain the multispectral image with the high spatial resolution ratio, which is subjected to column vectorization, and restoring the multispectral image with the high spatial resolution ratio, which is subjected to column vectorization, into the multispectral image with the high spatial resolution ratio. According to the multispectral image and full-color image fusion method disclosed by the present invention, the accurate space information and the accurate spectral information can be obtained; and the multispectral image and full-color image fusion method can be used for the fields of remote sensing of object identification, terrain classification, environmental monitoring and the like.

The invention discloses a polarimetric SAR (synthetic aperture radar) terrain classification method based on semantic information and polarimetric decomposition. The polarimetric SAR terrain classification method includes performing mean shift on a span image, extracting a sketch map of the span image, extracting a line segment gathering region in the sketch map by an region extracting technology based on the semantic information, merging span image mean shift over-segmentation regions based on the line segment gathering region as well as by the aid of a critical region majority vote merging strategy and based on a polarimetric feature merging strategy, acquiring an image segmentation result, and fusing the image segmentation result based on the semantic information and an H / alpha-Wishart classification result based on an MRF (markov random field) to acquire a final classification result. The semantic information, an image processing technique and a polarimetric scattering property are combined by the polarimetric SAR terrain classification method, the problem of bad region consistency of existing classification techniques based on the polarimetric decomposition to classification results with gathering-featured surface features (like forest, building groups and the like) is mainly solved, and region consistency and boundary retainability of the classification results with the gathering-featured surface features are improved.

A method for hyperspectral remote sensing image sparse mix-decomposition based on homogenous indexes comprises the steps that homogeneity analysis is conducted on each image element of a hyperspectral remote sensing image so that the homogeneity indexes can be extracted; according to a value domain of the homogeneity indexes of the image elements in the whole hyperspectral remote sensing image, linear enhancement is conducted on the homogenous indexes of the image elements, the enhanced homogeneity indexes serve as variable separations based on whole variation to separate a weight of a space regular term in the augmentation Lagrange sparse mix-decomposition algorithm, and a difference quotient operator approaching inter-image-element abundance in the algorithm is redefined. According to the method, the accuracy of sparse mix-decomposition is improved, the space smooth texture of the mix-decomposition abundance approaches the real space smooth texture distribution of the image, and influence on a mix-decomposition result by noise is effectively restrained. According to the method, important application value is brought for the aspects of high-accuracy terrain classification and ground target detection and identification based on the hyperspectral remote sensing image.

The invention discloses a polarized synthetic aperture radar (SAR) image classification method based on Freeman decomposition and data distribution characteristics and mainly solves the problems of high computation complexity and poor classification effect in the prior art. The polarized SAR image classification method includes step: (1) performing Freeman decomposition for polarized SAR images to be classified to obtain plane scattering power, dihedral angle scattering power and volume scattering power; (2) initially dividing the polarized SAR images into three classes according to the three scattering powers; (3) calculating the distribution characteristic parameter xL of each pixel point in each class; (4) subdividing each of the three initially divided classes into three classes according to the distribution characteristic parameters xL to divide the whole polarized SAR images into nine classes; and (5) performing complex Wishart iteration for the obtained nine-class dividing results to obtain the final classification result. Compared with the typical classification method, the polarized SAR image classification method is rigorous in polarized SAR image dividing, good in classification effect and small in computation complexity and can be applied to terrain classification and object identification of the polarized SAR images.

Two-dimensional aerial images and other geo-spatial information are processed to produce land classification data, vector data and attribute data for buildings found within the images. This data is stored upon a server computer within shape files, and also stored are source code scripts describing how to reconstruct a type of building along with compiled versions of the scripts. A software game or simulator executes upon a client computer in which an avatar moves within a landscape. A classifier classifies a type of building in the shape file to execute the appropriate script. Depending upon its location, a scene composer downloads a shape file and a compiled script is executed in order to reconstruct any number of buildings in the vicinity of the avatar. The script produces a three-dimensional texture mesh which is then rendered upon a screen of the client computer to display a two-dimensional representation of the building.

The invention provides a polarimetric SAR multi-component target decomposition method. According to the method, an additional diffuse scattering mechanism which may come from a terrain or rough surface is added as a fifth decomposition component on the basis of a previous four-component decomposition algorithm, namely, the linear weighted sum of five scattering components (odd scattering, even scattering, volume scattering, helicoid scattering and diffuse scattering) decomposed from a fully-polarimetric SAR coherence matrix T or covariance matrix C. The power of volume scattering is solved by an improved NNED method, and the contribution values of odd scattering, even scattering and diffuse scattering are directly solved by adopting corresponding odd scattering, even scattering and diffuse scattering models of a Pauli matrix directly and using a generalized similarity parameter GSP and eigenvalue decomposition. The novel method provided by the invention is conductive to improving the terrain classification accuracy of polarimetric SAR data.

The invention provides a SAR image terrain classification method based on domain adaption. By use of domain adaption algorithm, by means of prior SAR image data of a source domain, a classification model is established for adaptive application in classification of another similar yet different target domain SAR image, so that the cost of obtaining a target domain SAR image label is reduced. According to the invention, the mechanism of only reserving support vectors as the training set every time when a training set is optimized and updated can substantially reduce the redundant sample quantity of the training set and can effectively alleviate the problem that an SVM classifier is restricted by computational complexity and a storage capacity; through introduction of a recovery utilization mechanism of target domain samples unable to serve as the support vectors, the target area samples can be repeatedly and efficiently utilized so that a classification face can be continuously adjusted and corrected; and at the same time, through deletion of source domain samples unable to serve as the support vectors, the quantity of source domain training samples which do not match target domain distribution can be reduced, more accurate classification results can be obtained, and the convergence is better.

The invention relates to independent component analysis global search method of realizing the high spectrum fine classification under no prior knowledge situation, the method including: reading in the high spectral data, the establishment of independent component analysis model based on the kurtosis, the center of the data, the ball of data, the iterative solution based on quantum genetic algorithm, independent component compositor, two value of the image, the feature classification. The invention method can established on the circumstance of no data background model, using the self high statistical data to achieve the feature fine unsupervised classification of the high spectral data; at the same time, avoided to plunge in the local best solution problem in the independent component analysis solution process, and compared with the traditional genetic algorithm, the invention used quantum genetic algorithm has less number of iterations, fast convergence, high search efficiency and the strong overall search capability and so on features.

The invention relates to a terrain geometric parameter extraction method based on a hierarchical elevation cloud atlas, which comprises terrain classification and recognition, terrain simplification and terrain geometric parameter extraction processes. For a 401*401 DEM grid terrain specified in the digital map of the GeoTIFF format of the ASTER GDEM type, the relative height is first calculated to divide the terrain into five types: the plain, the hill, the low mountain, the middle mountain, and the high mountain through programming; the hierarchical elevation cloud atlas of the specified terrain is obtained through elevation layering and color mapping; the eight neighborhood boundary tracking algorithm is used in image processing to obtain the terrain bottom surface boundary, the bottomsurface area and the center of the bottom surface, and the color representing the maximum elevation interval is identified to obtain the average elevation of the highest area of the terrain; finally,the geometric parameters of the plain, spherical crown, cone and wedge shape of the terrain simplified geometric model are obtained by combining the terrain classification, the calculation of the bottom shape factor and the slope calculation. The invention has the advantages of simple method, small calculation amount, real-time performance and practicality.

The invention discloses a polarimetric SAR speckle noise suppression method based on non-local bilateral filtering. The method mainly solves the problem of loss of edge texture details in the prior art. The method comprises the steps of 1, searching for similar pixel points of a polarimetric SAR image to form a similar pixel point set and obtain the similarity weight; 2, obtaining neighborhood windows with similar pixel points as the centers and carrying out bilateral filtering on the neighborhood windows to obtain filtering results; 3, carrying out non-local weight averaging on all the filtering results of the similar pixel points to obtain a covariance matrix generated after primary filtering; 4, filtering the covariance matrix generated after primary filtering to obtain a covariance matrix generated after final filtering; 5, synthesizing the covariance matrix generated after final filtering into a pseudocolor image and converting the pseudocolor image into a grayscale image. According to the method, information of the edge texture details can be kept on the premise that speckles are suppressed, and therefore the effect of suppressing the speckles of the polarimetric SAR image is improved. The method can be used for terrain classification and target identification of the polarimetric SAR image.

The invention provides a vehicle laser radar three-dimensional scanning method, and a terrain classification method and system. A laser emission unit, a signal detection unit, a POS unit and a core processing unit are arranged on a vehicle, wherein the laser emission unit comprises a colorful laser source, an acquisition result of the signal detection unit is inputted to the core processing unit, point cloud acquired through scanning is acquired, the colorful spectrum information of the point cloud is acquired, and the relative geometric position of the point cloud is determined; the attitude position information is further recorded by the POS unit and is inputted to the core processing unit, according to the relative attitude of the laser emission unit and the POS unit, the absolute geometric position of the point cloud is acquired based on the relative geometric position of the point cloud, and the space position information of the point cloud is acquired. The vehicle laser radar three dimensional scanning method is advantaged in that the colorful laser spectrum information of a target terrain and the laser point cloud space information are directly and simultaneously acquired, so colorful laser imaging of the target terrain is acquired through three-dimensional reconstruction, and the method can be widely applied to the digital city and smart city fields.

The invention relates to a terrain classification and recognition method based on learned vibration information, which aims to solve a problem of low accuracy of the existing classification and recognition method. The terrain classification and recognition method comprises the steps of first, collecting original data of vibration information of a sensor in the x-axis, y-axis and z-axis directionsin a coordinate system; second, performing segmentation processing on the original data to form n vectors with the time length being 1s; third, performing terrain type marking on the n vectors; fourth, converting the segmented n vectors into a frequency domain; fifth, performing off-line learning training on the n vectors converted into the frequency domain by using a multilayer feedforward neuralnetwork to obtain a trained multilayer feedforward neural network; and sixth, obtaining vibration data online in real time, executing the step two to the step four, and performing online classification and recognition by using the trained multilayer feedforward neural network in the step five to obtain the terrain type. The terrain classification and recognition method is applied to the technicalfield of recognition and classification.

The invention discloses a polarized SAR (synthetic aperture radar) image classification method based on improved affinity propagation clustering. The problem of low classification accuracy in the existing unsupervised polarized SAR classification method is mainly solved. The method comprises the implementation steps of: carrying out four component decompositions on each pixel point, extracting four scattering powers of each pixel point; dividing an image according to the obtained scattering powers to obtain four classes; equally dividing each obtained class into 20 small classes; clustering the 20 small classes in each class by the improved affinity propagation clustering to obtain the pre-classification result of the image; and finally, carrying out iterative classification on a pre-classified image by a Wishart classifier to obtain the final classification result. Compared with the classical classification method, for the method disclosed by the invention, the division on a polarized SAR image is stricter; the classification effect is better; the computation complexity is small; and the polarized SAR image classification method can be used for carrying out terrain classification and target identification on the polarized SAR image.