170 results about "Polarimetric synthetic aperture radar" patented technology

The invention belongs to the technical field of image processing, relates to the POLSAR image processing technology, and discloses a polarization image sorting method based on tensor decomposition and dimension reduction. According to the method, polarization data and a polarization characteristic quantity matrix are utilized for setting three-dimensional polarization characteristic tensor, low-dimension characteristic tensor is obtained according to the dimension reduction method based on tensor decomposition, training samples are selected from the low-dimension characteristic tensor for classification of an SVM, and on the basis of not destroying the space relation between the structure of the three-dimensional polarization characteristic tensor and adjacent pixels, redundancy between the characteristic quantities is removed, dimension disasters are avoided, the classification effect is well improved, and the efficiency and robustness of the algorithm are improved. The polarization image sorting method based on tensor decomposition and dimension reduction can be applied to classification of various complex terrains.

The invention discloses a method for decomposing image four components of a polarization synthetic aperture radar and relates to analysis of the scattering characteristic of a polarization SAR image land object, in particular to a computing method of the scattering type of a building which has the non-zero orientation angle and is hard to process in an existing polarization SAR image decomposing method. As it is shown in the graph (1), the method includes the following steps that firstly, in terms of pixels corresponding to the building with the non-zero orientation angle in the image, a screening computing method is provided; secondly, in terms of the building with the non-zero orientation angle, a generalized even-time scattering model which can describe the scattering feature of the building is provided; thirdly, a non-negative feature value decomposing technology is provided for resolving the scattering components. By means of the method for decomposing the image four components of the polarization synthetic aperture radar, the defects of an original scattering model can be effectively avoided, a satisfying image decomposing result on the high-resolution full-polarized SAR image can be obtained and the method has the advantages of being novel, innovative, simple and practical.

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 sea surface oil spilling detection method of a complete polarization synthetic aperture radar (SAR). The method comprises the following steps of: carrying out adaptive threshold value segmentation on a complete polarization SAR image to obtain complete polarization SAR images getting rid of the sea surface; selecting a training sample and a testing sample from the complete polarization SAR images getting rid of the sea surface; training an SVM (Support Vector Machine) detector, and normalizing polarization characteristic vectors of the detector, which comprise a scattering entropy H, a scattering angle alpha, a negative entropy A, a co-polarization ratio gamma, a cross polarization ratio eta, a depolarization ratio delta, a co-polarization phase difference phi HH-VV and a cross polarization phase difference phi HH-VV; and finally, detecting and identifying spilled oil and suspected objects by using the SVM and outputting a detection result. The method has thecharacteristics of high detection speed and low false alarm rate and is suitable for the sea surface oil spilling detection of the SAR.

The invention relates to application of microwave remote sensing in the field of forests and discloses a polarimetric synthetic aperture radar interferometry (POLInSAR) vegetation height inversion method based on complex field adjustment theory. The complex field adjustment theory and a physical model for POLInSAR vegetation height inversion are organically combined by the method. The method comprises the following steps of: I, performing registration on obtained complete polarization data of N scenes to obtain M baseline interference pairs; II, performing polarized interference on the M baseline interference pair to obtain M*P interference fringe patterns, and estimating corresponding complex coherences of the M*P interference fringe patterns; and III, working out a vegetation height hv based on complex field adjustment computation. The POLInSAR vegetation height inversion method based on the complex field adjustment theory is visual in principle, is easy to realize programming and extension, is a steady and feasible vegetation height inversion method, and can be widely applied to the POLInSAR technology to measure the vegetation height within a large-scale area and even a global scale.

The invention provides a ground object target classification method and a device based on a full-polarization synthetic aperture radar (SAR). The method comprises the steps of receiving the feedback signal of a ground object target to form an image of the ground object target, partitioning the image of the ground object target to form image blocks, extracting polarization characteristic parameters from the image blocks and classifying the ground object target according to the polarization characteristic parameters. The device comprises an image receiving unit, a partitioning unit, a parameter extracting unit and a classifying unit, wherein the image receiving unit is used for receiving the feedback signal of the ground object target so as to form the image of the ground object target; the partitioning part is used for partitioning the image of the ground object target so as to form the image blocks; the parameter extracting unit is used for extracting the polarization characteristic parameters from the image blocks; and the classifying unit is used for classifying the ground object target according to the polarization characteristic parameters. The invention provides a solution for realizing high-precision classification of the ground object target with full-polarization SAR image.

The invention provides an onboard P-waveband polarization synthetic aperture radar (SAR) calibration method under a non-ideal calibrator condition, and relates to radar techniques. The method is used for calibrating polarization discrimination, polarization channel imbalance and other system errors of the SAR. The non-ideal condition indicates non-ideal performance of scattering matrixes led in by posture changes of a calibrator and an aerial carrier. The method corrects the scattering matrixes of the ideal calibrator, carries out correction on antenna direction pictures, accordingly overcomes the occasion that calibration parameters change with visual angles (distance direction) of an antenna, takes consideration of the fact that polarizing angle changes caused by the postures of the aerial carrier change the scattering matrixes of the calibrator, corrects a polarizing calibration model based on the preceding steps, carries out calibration treatment to obtain an emission distortion matrix and a receiving distortion matrix of a system, and accordingly carries out polarizing correction for the polarization SAR pictures.

The invention discloses a polarization four-component decomposition method for a city area. The method comprises the following steps of: performing preprocessing on the polarimetric synthetic aperture radar image data of the city area so as to obtain a coherent matrix T theta; S12: eliminating the orientation angle theta in the coherent matrix T theta so as to obtain coherent matrix T; and S13: performing polarization four-component decomposition on the coherent matrix T by using a volume scattering model Tv. Through the orientation angle compensation performed on a coherent matrix and using a new volume scattering model to describe the volume scatting in polarization decomposition, the negative power problems of surface scattering and dihedral angle scattering, which are caused by overestimated volume scattering power, can be released to a certain extent.

The invention discloses a method for detecting oil spill at sea based on a full-polarized synthetic aperture radar (SAR) image. The method includes the following steps: pre-treating polarized SAR data which require analyzing to obtain a full-polarized SAR covariance matrix; conducting refining polarized Lee filtering on the covariance matrix; based on the filtered covariance matrix or through a Stokes vector calculated by the covariance matrix, extracting 6 polarized features to constitute a feature combination; inputting training sample features with ground verification label information to a maximum likelihood (ML) classifier, training the classifier and optimizing parameters of the classifier; taking polarized features as input, utilizing the ML classifier to conduct detection and classification on an oil membrane; processing a classification result based on morphology, utilizing verification information of actual measurement to evaluate classification precision. According to the invention, the method can increase performances of oil spill at sea detection and classification methods and promote the application of the full-polarized SAR in actual engineering problems such as monitoring of oil spill at sea.

The present invention relates to a polarimetric calibration technique based on natural distribution scenes and a rare calibrator, which is used for the calibration and correction of distorted polarimetric synthetic aperture radar (SAR) data. The present invention breaks the calibration bottleneck of domestic machine-borne polarimetric SAR data, and develops a technique which utilizes widely distributed natural ground objects for the crosstalk calibration of polarimetric data without the help of an artificial corner reflector and needs only one or a small amount of triple-sided corner reflectors for the calibration of the imbalance of polarimetric receiving channels. In addition, the technique uses the strength change of natural ground object scenes with wide similar radar backward scattering properties in the distance direction to fit out an antenna directional pattern, and fully utilizes polarimetric ground object information to correct all the polarimetric SAR channel data with the same antenna directional pattern, thereby retaining the polarimetric scattering characteristics of ground object targets before and after correction.

A method for classifying radar images of polarization synthetic apertures based on sub-aperture analysis belongs to the technical field of radar imagery, which relates to a polarization synthetic aperture radar (PolSAR) imagery processing technology. The classifying method is characterized in that the initial classification of SAR images polarized in the entire resolution ratio is primarily performed by adopting an H/Alpha plane; then the sub-aperture decomposition of SAR images polarized in the entire resolution ratio is performed; then a center of an initial category Vm is calculated through the coherent matrix of sub-aperture images; the distance measure of all pixels and each class center in all the sub-aperture images is calculated, and the pixels are categorized to the class with the minimum distance measure; finally, whether the iteration terminal conditions are not met or not, if the terminal conditions are met, the iteration is terminated; if the terminal conditions are not met, the iteration is continuously performed by returning to step 2. The invention can synthesize scattering properties of the target and the change of the scattering properties at different visual angles, and the classification precision is improved, so as to bring better classifying effect.

A system for determining the location of a man-made object based upon symmetry of the object comprising a receiver configured to receive radar signals comprising cross-polarized and co-polarized responses; at least one processor configured to combine the horizontal-horizontal polarimetric responses and vertical-vertical polarimetric responses to form co-polarimetric images and operate on one or both of the vertical-horizontal polarimetric responses and horizontal-vertical polarimetric responses to form cross-polarized images; the at least one processor configured to process the co-polarized and cross-polarized images to locate areas of interest containing a maximum in the co-pol image and a null state in the co-pol image indicating the potential detection of a man-made object; the at least one processor being configured to filter data using buffer regions and/or skipping of pixels in the vicinity of an area of interest. A method for detection of man-made objects is also disclosed.

The present invention provides a method of optimizing interference coefficients of coherence on the basis of polarimetric synthetic aperture radar (SAR) data, relating to the SAR technology. The method comprises steps of firstly calculating the flattening phase of each polarized state by utilizing a fast fourier transformation (FFT) method; eliminating an influence of the flattening phase of eachpolarized state on polarimetric data; performing smooth filtering to the polarimetric data; extracting the optimal projection vector pair by using an eigen-decomposition method; calculating the optimal interference coefficient of coherence and the optimal interference phase and verifying the validity of the optimal estimation; compensating the optimal interference phase by the flattening phase, and arranging the optimal interferences coefficient of coherence and the optimal interference phases in a value sequence of the interference coefficients of coherence. The method of the present invention is not limited by a condition that a polarimetric data matrix is invertible, dispenses with the compensation of absolute offset between the optimal projection vectors and can verify the validity ofthe optimal result. The method of the invention has characteristics of a simple principle and convenience in calculation and can be applied in processing of data of polarimetric classification, parameter inversion and the like.

The invention discloses a neighborhood information and SVGDL (support vector guide dictionary learning)-based polarimetric SAR image classification method. The objective of the invention is to solve the problems of long operation time and low computation efficiency caused by low dictionary learning convergence rate in a polarimetric synthetic aperture radar (SAR) image classification process in the prior art. The method includes the following specific steps of: (1) inputting a polarimetric SAR images; (2) performing filtering; (3) extracting polarimetric neighborhood features; (4) performing dimensionality reduction; (5) selecting a training sample and a test sample; (6) training a dictionary and a classifier; (7) testing the dictionary and the classifier; (8) performing coloring; and (9) outputting a classification result diagram. Compared with the prior art, the neighborhood information and SVGDL (support vector guide dictionary learning)-based polarimetric SAR image classification method of the invention can effectively improve the correction rate and computation efficiency of polarimetric SAR image classification.

The invention discloses a ground feature classifying method based on simplified polarization synthetic aperture radar data, which relates to the synthetic aperture radar remote sensing information processing technology. The ground feature classifying method includes steps: a) obtaining Stokes parameters after filtering; b) extracting characteristic parameters including polarizability m, relative phase difference delta among orthogonal channels and total polarization power span for showing scattering mechanisms; c) calculating power ingredients corresponding to the basic scattering mechanisms, and determining main scattering mechanisms of pixels and dividing data into three types of pixels with identical scattering characteristics; d) further dividing each type of pixels with identical scattering characteristics into a plurality of types of pixels with equal sample numbers by the aid of the span; and e) realizing iterative Wishart classification. The ground feature classifying method is simple in principle and convenient in calculation, and can be used for analyzing and classifying ground feature scattering characteristics.

The invention relates to a topographic surveying method, the method comprises: full polarizing synthetic aperture radar compound image by a single path and calculating to obtain a polarization position angle offset value of each earth's surface unit in the irradiation area adopting circular polarization algorithm; calculating an incidence angle and the resolution of each earth's surface unit by system parameters; calculating the grade guess value of each earth's surface unit by compensation Lambert algorithm; calculating the absolute elevation value of each earth's surface unit by the complete multiple gridding algorithm. A moderate accuracy grade and digital height model can be rapidly obtained by the single path full polarization synthetic aperture radar slant distance compound image data. The method of the invention is characterized in that, the limitation for acquiring radar data is less, the dependence on the exterior data is less, the automatization degree is high and the computational efficiency of the integral process flow is high, thereby the terrain is visible and the application field has larger application value.

The invention discloses an active and passive remote sensing data-based rural residential land extraction method. The method comprises the following steps: (1) acquiring data and preprocessing; (2) calculating a normalized differential vegetation index; (3) calculating a normalized difference build-up index; (4) calculating a POLSAR (Polarimetric Synthetic Aperture Radar) dihedral angle scattering component; (5) performing maximum likelihood classification. According to the method, the optical remote sensing and microwave remote sensing information are comprehensively applied, the difference between ground and an object can be more fully embodied through supplementation of advantages and disadvantages of the two kinds of remote sensing information, and the accuracy for rural residential land extraction is greatly improved.

This invention relates to a method for inversing ground digit altitude of single flying complete polarization synthetic aperture radar image using fully polarized scattering Mueller matrix solution to derive orientation angle psi migration, with the help of transformation of euler angle to set up relations among psi migration and tilted surface picture element range angle beta and horizontal azimuth gamma determine by three stokes arameters. Under the condition of only single flying SAR data, adaptive threshold value binary and image morphology refinement are used to determine gamma and beta and ground range azimuth slope and horizontal azimuth slope, therefore, using complete multiple mesh alogirhtm value to resolve Poisson equation of DEM to get inversion of DEM.

The invention discloses a weighted synthetic kernel and TMF based polarimetric SAR image classification method and relates to polarimetric SAR image classification. The method comprises the steps of step 1, selecting polarimetric SAR image polarization characteristics and training samples, and building characteristic space; step 2, establishing the weighted synthetic kernel; step 3, achieving initial classification by the combination of the weighted synthetic kernel and a support vector machine to be used as an initial value of a marking field X; step 4, estimating a novel marking field X and a novel auxiliary field U; step 5, using the marking field X as the final polarimetric SAR image classification result till the marking field X converges. According to the method, the problems that the initial classification accuracy is not high, and the Markove field cannot process polarimetric SAR image unsteady characteristics of the prior method are mainly solved. Homogeneous region classification results are smooth, marginal information can be kept well, the classification accuracy is improved apparently, and the method can be used for target detection and recognition of polarimetric SAR images.

The invention discloses a multicore fusion and spatial Wishart LapSVM-based semi-supervised polarimetric SAR image classification method, and mainly aims at solving the problem that the classification precision is low as labelled samples of synthetic aperture radar full-polarimetric SAR images are relatively few in existing classification method. The method comprises the following steps of: obtaining a polarization related matrix T; extracting polarization feature vectors of the matrix T and carrying out normalization processing; establishing a training sample set; constructing a Spatial-Wishart manifold regular term; and calculating classification correctness and outputting a polarimetric SAR image classification result. According to the method, the problem that the traditional non-supervision polarimetric SAR image classification is low in correctness is solved, the malpractices of difficulty artificial labelling and high cost caused by requirement of massive label data are avoided; and by jointly utilizing less labelled data and massive un-labelled cheap data, a better classification effect is obtained, so that the method can be used for target classification, detection and recognition of polarimetric SAR images.

The invention belongs to the technical field of full polarimetric synthetic aperture radar imaging remote sensing and relates to a rotation domain polarimetric zero angle characteristic-based polarimetric SAR terrain classification method. The method mainly comprises eight specific steps. In a first step, polarimetric SAR images to be classified are chosen; in a second step, coherent speckle filtering operation is conducted; in a third step, polarimetric characteristic parameters are extracted, and polarimetric characteristic parameters corresponding to all pixel points are extracted based on filtered polarimetric SAR images; in a fourth step, polarimetric characteristic parameters are normalized; in a fifth step, training samples and testing samples are chosen; in a sixth step, an SVM classifier is trained; in a seventh step, classifying operation is conducted, and a classifying result is output; in an eighth step, classification precision is calculated. The method is simple to implement and has good robustness for polarimetric SAR image data of different time phases, and the method can be directly used for conducting terrain classification operation on polarimetric SAR image data of different time phases obtained from all kinds of polarimetric SAR systems.

The invention provides a full-polarization aperture radar image super-resolution reconstruction method based on a multi-scale attention mechanism, constructs a residual convolutional neural network with embedded feature layer up-sampling, spatial attention, channel attention, multi-scale attention, adaptive loss function and other modules, and combines supervised and zero-projection training mechanisms. A training convergence network is obtained. Through the trained network, super-resolution reconstruction is carried out on the to-be-processed low-resolution synthetic aperture radar image to obtain a high-resolution full-polarization synthetic aperture radar image, and spatial information of the image is effectively reconstructed while polarization information of the image is maintained.

The invention discloses a polarimetric SAR image classification method based on a tensor MPCA, and the method can be applied to SAR image classification. The method includes 1, inputting data of three polarimetric SAR image channels; 2, converting original data into the tensor mode; 3, extracting image features; 4, training a classifier; 5, classifying the data to be classified, and acquiring the classification results. Since the data of the three polarimetric SAR image channels are converted into the tensor mode, the spatial structure information of the original data is utilized, and the classification accuracy is improved.

The invention discloses a precise extracting method for a sea surface oil spilling area through remote sensing of a polarized synthetic aperture radar. The method comprises the steps that an SAR imageis subjected to polarization filtering, and the influence of noises of information of the sea surface is reduced; multiple methods are adopted for extracting effective polarization characteristics; astack auto-encoder (SAE) is utilized for classifying sea surface mineral oil and a non-oil slick area; the classifying result is subjected to morphological processing to obtain a reticle mask of a mineral oil area; a backscattering cross-section intensity image is subjected to space density threshold value segmentation, and an oil slick border of high precision is acquired; the reticle mask is fused with the oil slick border to obtain the precise extracting result of the sea surface oil spilling area. The method solves the problems of distinguishing of substances similar to biologic oil slickand mineral oil and precise extracting of the oil slick border in the prior art.