73 results about "Polarimetric sar" patented technology

The present invention discloses a polarimetric SAR change detection method, device, equipment and medium, which relate to the field of radar image processing technology. The method acquires a time-series PolSAR image, uses JBLD divergence to calculate the similarity measure of the multi-phase covariance matrix; calculates a time-series edge intensity map based on the similarity measure; uses the time-series edge intensity map to initialize the cluster center and introduces a dynamic edge constraint mechanism to suppress superpixels from crossing the image edge during the iteration process, and outputs the superpixel segmentation result; constructs an image topology representation that integrates time-series feature similarity, spatial adjacency and cross-phase cross-feature similarity; constructs an energy function containing node cost and edge cost, solves the energy minimization problem through quadratic pseudo-Boolean optimization, and obtains a change detection map. The present invention can avoid errors caused by regional discontinuity and boundary fuzziness in superpixel segmentation, and exhibits strong robustness in both natural objects and complex urban building scenes.

The invention discloses a polarimetric SAR change detection method, device and equipment and a medium, and relates to the technical field of radar image processing. The method comprises the following steps: acquiring a time sequence PolSAR image, and calculating similarity measurement of a multi-temporal covariance matrix by adopting JBLD divergence; calculating a time sequence edge intensity graph based on similarity measurement; initializing a clustering center by using a time sequence edge intensity graph, introducing a dynamic edge constraint mechanism in an iteration process to inhibit super-pixels from crossing image edges, and outputting a super-pixel segmentation result; constructing image topological representation fusing time sequence feature similarity, spatial adjacency and cross-time phase cross feature similarity; and constructing an energy function containing node cost and edge cost, and solving an energy minimization problem through quadratic pseudo Boolean optimization to obtain a change detection graph. According to the method, errors caused by discontinuous regions and fuzzy boundaries in super-pixel segmentation can be avoided, and high robustness is shown in natural ground features and complex urban building scenes.

The invention discloses an end-to-end polarimetric SAR image superpixel segmentation method, system and device based on a full convolutional neural network, and a medium. The method comprises the following steps: inputting polarimetric features and position information; constructing a super-pixel segmentation model of the polarized SAR image based on the full convolutional neural network, and outputting a super-pixel segmentation result; training a superpixel segmentation model; inputting the processed polarization features associated with the position information into the trained super-pixel segmentation model to obtain a super-pixel segmentation result, processing the super-pixel segmentation result, and using the processed super-pixel segmentation result as the input of a polarized SAR image classification model to train the polarized SAR image classification model; classifying the polarimetric SAR images by using the trained polarimetric SAR image classification model to obtain a polarimetric SAR image classification result combined with superpixel segmentation; the system, the equipment and the medium are used for implementing the method. The method has the advantages that a high-quality superpixel segmentation result is quickly generated without a traditional clustering method, and the method is easy to combine with a subsequent polarized SAR image classification deep learning model.

A computerized method estimates crop growth in a geographic area using satellite-collected synthetic aperture radar (SAR) data. SAR data of the geographic area is obtained from a plurality of satellite passes by one or more satellites. The obtained SAR data is processed into coherence data and interferometric data. The processed data is associated with a comparison between a first SAR data subset from a first satellite pass of the plurality of satellites passes and a second SAR data subset from a second satellite pass of the plurality of satellite passes. The processed data is provided to a trained crop growth estimation model and a crop growth prediction associated with the geographic area is generated using the trained crop growth estimation model. In some examples, the obtained SAR data is processed into additional data types, such as amplitude data and / or polarimetric SAR data.

The invention relates to a forest biomass estimation method combining a polarization radar and a satellite-borne laser radar. The method comprises the following steps: preprocessing discrete footprint point data and polarimetric SAR data to obtain geographic position information and a polarimetric SAR backscattering coefficient; according to a random forest interpolation algorithm in combination with geographic position information and a polarized SAR backscattering coefficient, a nonlinear mapping relation among space coordinates, polarized SAR features and spaceborne laser radar parameters is automatically established through machine learning, and continuous spaceborne laser radar features are generated; and calculating the relative importance of all the satellite-borne laser radar features and the polarimetric SAR features with the forest biomass, sequentially selecting the features ranked in the top according to a relative importance ranking result to construct a forest biomass prediction model, and realizing forest biomass prediction by using the forest biomass prediction model. By adopting the method, high-precision forest biomass estimation can be realized.

The invention provides a polarized SAR (Synthetic Aperture Radar) relative similarity measurement and classification algorithm based on a graph convolutional network, which comprises the following steps: carrying out polarized superpixel segmentation (Pool-ASLIC) on a preprocessed polarized SAR image, then calculating the similarity degree between polarized covariance matrixes by using a proposed WA2 distance fusing a symmetric revised Wishart distance and an AIRM distance, and constructing an adjacent matrix; and finally, the polarization covariance matrix is used as a superpixel region feature to be input into a GCN graph convolutional network for semi-supervised classification. According to the method, the measurement effect of the polarimetric SAR data in the graph convolution network is better than that of the current popular symmetric revised Wishart distance and AIRM distance, and better polarimetric SAR classification effect and precision can be realized.

The invention provides a rock abundance inversion method and system based on an optical image and synthetic aperture radar data, a storage medium and electronic equipment. The method comprises the following steps: carrying out preprocessing operation on a polarimetric SAR image of Mini-RF; and extracting regression features among the parameters, constructing an RA-SAR inversion model by adopting a linear regression method, and endowing a higher weight for significant features in the Stokes parameters so as to enhance the fitting effect of the model. According to the invention, Mini-RF SAR data and optical remote sensing data are combined, so that the problems of inapplicability and insufficient coverage of optical data in a part of research areas due to an overlarge incident angle of the sun are solved, and higher-resolution rock abundance distribution of large-scale lunar meteorite craters can be obtained in a high-efficiency manner; the defect that the resolution ratio of the lunar surface rock abundance obtained by DiViner equipment is too low is overcome, and a brand new technical path is provided for lunar surface geological evolution research.

The invention relates to a pi / 4 compact polarimetric SAR target decomposition method, a program product and a storage medium. The method comprises the following steps: S1, obtaining complete polarimetric SAR data, and converting the complete polarimetric SAR data into a Stokes vector of a pi / 4 reduced polarimetric SAR; s2, selecting a volume scattering model according to the co-polarization ratio; s3, constructing a decomposition model according to the Stokes vector and the selected volume scattering model; s4, acquiring volume scattering energy, dihedral angle scattering energy and surface scattering energy according to the constructed decomposition model; wherein the scattering mechanism components of each pixel point of the image are obtained according to the volume scattering energy, the dihedral angle scattering energy and the surface scattering energy, and the ground object target scattering mechanism is interpreted according to different proportions of the scattering energy, so that different ground object type areas can be effectively distinguished, and the ground object scattering mechanism is obtained and accurately interpreted.

The present invention provides a method for extracting seawater raft aquaculture information from an interpretable polarimetric deep learning network, belonging to the cross - technical field of marine remote sensing and artificial intelligence. The interpretable polarimetric deep learning network includes three key components: a polarimetric scattering class activation mapping module, an interpretable segmentation consistency learning module, and a refined class activation and edge guidance network. The polarimetric scattering class activation mapping module generates a high - quality class activation mapping diagram by combining the polarimetric scattering characteristics of the fully polarimetric SAR image with the gradient weight; the interpretable segmentation consistency learning module uses the generated class activation mapping diagram to guide the model to focus on the characteristics of the aquaculture area during the training process; the refined class activation and edge guidance network adopts a dual - branch structure to perform semantic segmentation and edge supervision respectively, generating accurate segmentation results. The present invention can significantly reduce the occurrence of background misjudgment, ensure that the segmentation results are clear and detailed, and has strong applicability.

The invention discloses a space-borne polarization SMAP-R data gap filling method based on multi-polarization SAR data. The method comprises the following steps: acquiring SMAP-R, SMAP, GF-3, Sentinel-1, MODIS and SR TM 30m DEM data; preprocessing the data to obtain a total intensity reflectivity, a normalized Stokes parameter and a backscattering coefficient; unifying data spatial resolution and dividing data sets; building a data supplement method model of the multi-polarization SAR back scattering modeling SMAP-R polarization parameters based on integrated learning; verifying the parameter inversion performance by using an ANN model; and finally filling the missing grid data. According to the method, modeling is carried out on SMAP-R polarization data through SAR back scattering data, secondary inversion verification is carried out, SMAP-R spatial data missing is effectively supplemented, and the spatial resolution of inversion earth surface parameters is improved.

The invention discloses a crop height inversion method and device based on compact polarimetric SAR data, and relates to the technical field of polarimetric radar remote sensing quantitative inversion, and the crop height inversion method based on compact polarimetric SAR data mainly comprises the steps: carrying out the data preprocessing of an original polarimetric SAR image, and obtaining compact polarimetric data; a multi-dimensional feature set is obtained according to polarization parameters, a machine learning algorithm model is trained and verified by combining a field actually-measured crop height data set to obtain a height prediction model, and crop height estimation data is obtained accordingly; and feature subset optimization is carried out by using a forward feature selection method, the machine learning algorithm model is trained and verified again based on the optimized feature subset to obtain a height prediction model, and the optimized feature subset is predicted to obtain a higher-precision crop height inversion result. According to the crop height inversion method and device based on the compact polarimetric SAR data, the inversion efficiency and precision can be effectively improved.

The application provides a polarization SAR image simulation method for forests under complex terrain conditions, comprising the following steps: (1) setting parameters of a polarization SAR imaging process, including radar imaging parameters, forest parameters and terrain parameters; (2) generating a corresponding terrain model according to the terrain parameters; (3) constructing a forest model according to the forest parameters; (4) calculating a polarization SAR image according to the forest parameter model, and finally simulating the polarization SAR image of the forest under the complex terrain conditions. The method can improve the simulation of the polarization SAR image of the forest under the complex terrain conditions, can be used for understanding the remote sensing mechanism, testing new applications and designing the inversion algorithm of the forest structure, and can further explore the influence of the terrain on the polarization SAR image imaging process.

The invention discloses a polarized SAR image classification method and system, a medium and a program product, and relates to the field of polarized SAR image classification, and the method comprises the steps: obtaining a polarized data set; constructing an anchoring sample training set and a positive sample pair data set according to the polarization data set; constructing a residual neural network model; performing first-stage training on the residual neural network model by using the positive sample pair data set to obtain a middle residual neural network model which passes through the first-stage training; performing second-stage training on the intermediate residual neural network model by using the polarization data set and the anchoring sample training set to obtain a residual neural network model through the second-stage training; and clustering the to-be-classified polarized SAR images by using the residual neural network model trained in the second stage and generating a classification result graph. According to the method, the polarimetric SAR image can be effectively and accurately classified and identified under the condition that any marking cost is not needed.

The application relates to a fast maximum likelihood estimation method of a polarized SAR image equivalent view number graph and relates to the technical field of imaging radar image processing. The method comprises the following steps: obtaining a logarithmic determinant graph of polarized SAR image data by adopting logarithmic operation; calculating a local mean value graph of the polarized SAR logarithmic determinant graph; calculating a local mean value graph of each channel data of the polarized SAR; calculating the determinant value of all pixel data of the polarized SAR image after local averaging, forming a corresponding determinant graph, and obtaining a logarithmic determinant graph by adopting logarithmic operation; obtaining a local sample statistic graph of the polarized SAR data equivalent view number estimation by adopting matrix subtraction; and quickly estimating the equivalent view number graph of the polarized SAR image by using an analytical approximation solving formula of the ML estimation and based on matrix operation. The method avoids the iterative numerical operation and initial interval setting problem of a traditional method, and the fast calculation method based on matrix operation and convolution has obvious efficiency advantages when the equivalent view number graph of the polarized SAR image is estimated.

The present invention discloses a method for detecting landslides in full-polarization SAR images, which relates to the technical field of landslide detection and includes the following steps: collecting a single full-polarization SAR image of a landslide target area and performing data preprocessing; based on the data preprocessing results, using the depolarization degree as a constraint and combining double-sided angle scattering and surface scattering to construct a landslide identification detector; using the generalized gamma distribution model to characterize the statistical information of the landslide identification detector; using a morphological operator to denoise the binary image obtained from the characterized landslide identification detector to obtain the landslide detection result, thereby completing the landslide detection in full-polarization SAR images. The present invention solves the technical bottleneck in the prior art that it is difficult to quickly and accurately obtain the location distribution of landslides based on a single full-polarization SAR image.

The invention discloses a polarimetric SAR ship target detection method and device based on a multi-channel network in the technical field of computer neural networks and signal processing. The polarimetric SAR ship target detection method based on the multi-channel network comprises the following steps: constructing a polarimetric SAR ship target detection system based on the multi-channel network; constructing a data set for training a polarized SAR ship target detection system; carrying out weight optimization on the polarimetric SAR ship target detection system by adopting the training set, and storing weight parameters after training; pre-stored weight parameters are loaded, and a final detection system is obtained; and finally, the detection system is used for detecting the input polarimetric SAR ship target and outputting a result. According to the polarimetric SAR ship target detection method and device based on the multi-channel network, the multi-channel deep learning network is constructed, and the problem of missing detection caused by small target and clutter interference is effectively solved.

The invention discloses a passive microwave constrained time sequence complete polarization soil humidity inversion method, which belongs to the technical field of remote sensing image processing, and comprises the following steps of: calculating time and space change ranges of earth surface dielectric constants of a soil humidity mapping area by using time sequence passive microwave observation data as constraint conditions for solving unknown parameters; filtering vegetation body scattering and dihedral angle scattering information by using a dual-stage iterative polarization target decomposition algorithm, and adaptively and optimally extracting back scattering coefficients of surface scattering HH and VV polarization; based on an alpha approximation model and a scattering coefficient ratio algorithm, a time sequence soil humidity inversion algorithm model combining HH and VV polarization observation data is constructed, a passive microwave soil dielectric constant constraint condition is introduced, a soil dielectric constant is solved, and the soil dielectric constant is converted into soil humidity by utilizing a dielectric constant and soil humidity empirical relation model. According to the method, high-resolution soil humidity drawing can be ensured, and the soil humidity inversion and drawing precision of the vegetation coverage area can be improved.

The present invention discloses a polarimetric SAR image classification method that combines polarization rotation angle and spatial self-attention. The method comprises the following steps: obtaining a polarimetric coherence matrix sequence of a polarimetric SAR image and extracting four-dimensional neighborhood window data of pixels to be classified; extracting low-level feature representations of the polarimetric SAR image using two 3D convolution blocks; establishing a polarimetric angle and spatial local feature extraction network architecture to extract local features of the polarimetric angle and space respectively; establishing a polarimetric angle and spatial global feature extraction and fusion network architecture based on a transformer coding layer to learn global features of the polarimetric angle and space respectively and perform global feature fusion; downsampling and high-level feature extraction of the global feature fusion map using a combination of a 3D pooling layer and a 3D convolution block to obtain a feature vector; and mapping the feature vector to a classifier to classify the polarimetric SAR image and output the classification result of the pixel to be classified. The present invention effectively improves the classification accuracy of polarimetric SAR images.

The present invention discloses a method for retrieving soil moisture in vegetated areas considering polarimetric scattering information, including extracting soil moisture retrieval characteristic parameters in vegetated areas based on polarimetric target decomposition; analyzing and obtaining an optimized combination of characteristic parameters; constructing and solving a soil moisture retrieval model integrating polarimetric information and radar backscattering information. In the method provided by the present invention, the construction of the model starts from the target scattering mechanism. Through the decomposition and correction of polarimetric characteristic parameters, the influence of vegetation coverage is effectively removed. By combining independent component analysis to obtain an optimized combination of retrieval characteristic parameters, the effective observation information of fully polarimetric SAR data is fully utilized, and reliable retrieval of soil moisture in vegetated areas is realized without the need for other auxiliary data.

The invention belongs to the technical field of image processing, and discloses a full-polarization SAR image sea surface oil spill extraction method based on an active contour. The method comprises the following steps: S1, obtaining four-channel data of a complete polarization SAR image, wherein the four-channel data covers polarization characteristic difference of oil spill; s2, selecting a closed curve surrounding a suspected oil spill area through visual interpretation based on fusion features of the complete polarization image, and optimizing a contour line through smooth and uniform sampling; s3, maintaining the continuity and expansion characteristics of the contour line by constructing an internal energy function; s4, iteratively adjusting the positions of the contour points according to the minimum energy principle, and judging the termination opportunity by combining the contour stability; s5, filling holes in the area through morphological operation, removing edge small bulges, and optimizing the area form; and S6, verifying the extraction precision through field observation, and judging whether a result meets an application standard or not. According to the invention, accurate segmentation of the oil spill area is realized through the multi-energy item active contour, and the method can be applied to marine environment monitoring and marine oil spill emergency response scenes.

The application discloses a full polarization SAR image ship detection method, comprising the following steps: S1, pre-processing a full polarization SAR image to obtain different types of scattering power and polarization wave anisotropy parameters of each pixel; S2, using the decomposed different scattering power and combining the polarization wave anisotropy parameters to construct a full polarization SAR image detector; S3, using a generalized gamma distribution to describe the statistical characteristics of the full polarization SAR image detector to realize constant false alarm rate adaptive detection of the full polarization SAR image detector. The scattering characteristics and anisotropy of the scattering wave of the ship target are used to fully represent the ship target, so that the ship is strengthened and the background is weakened, and the ship can be detected from the complex marine background.

The invention provides a satellite-borne SAR image denoising method and device, a storage medium and equipment, and the method comprises the steps: obtaining an original polarimetric SAR image which is polarimetric SAR data which is not subjected to the past noise processing and is provided with speckle noise; inputting the original polarimetric SAR image into an SIRV model, and solving the SIRV model based on a fixed point estimation algorithm to obtain a first normalized polarimetric coherence matrix and a first texture grayscale image; and obtaining a polarization coherence matrix of the original polarization SAR image based on the first normalized polarization coherence matrix and the first texture grayscale image. According to the method and the device, polarization denoising can be carried out on the polarization coherence matrix of the satellite-borne SAR image based on the SIRV model, and the problems of large calculation amount, great denoising effect and the like of a mode of carrying out polarization denoising on the polarization coherence matrix of the satellite-borne SAR image by utilizing a Wishart priori distribution SAR speckle filtering algorithm in the prior art are solved.

The invention discloses a multi-band polarized SAR (Synthetic Aperture Radar) image ground object classification method based on wavelet enhancement Swin Transform, and belongs to the technical field of radar remote sensing image processing. Comprising the steps of polarized SAR image preprocessing, image block division, Swin Transform branch feature extraction, wavelet transform branch feature extraction, feature dimension alignment, cross-band attention feature fusion, classification prediction, loss function optimization and end-to-end training optimization. Through a cross-band attention fusion module, a multi-directional cross attention mechanism and learnable weighted residual connection are adopted to realize adaptive deep fusion of spatial domain and multi-band polarization features, and the method solves the contradiction between global context modeling and local detail keeping in a traditional method. The precision and robustness of multi-band polarized SAR image ground feature classification are significantly improved, and a new technical approach is provided for accurate ground feature recognition in a complex ground surface environment.

This invention discloses a polarimetric SAR target enhancement extraction method for complex ground scenes. This method, belonging to the field of radar technology, comprises the following steps: S1: full-scene self-correction of polarimetric distortion; S2: generation of equivalent subview images; S3: construction of a polarimetric statistical enhancement test model; S4: enhanced likelihood test based on subview data characteristics; and S5: CFAR enhanced detection based on the composite chi-squared distribution. This method effectively and quantitatively describes the differences between the target and background, significantly enhancing the target signal-to-clutter ratio and detection robustness, meeting the requirements for automatic target enhancement extraction and batch application in large-scale SAR imagery.

The application provides a polarimetric SAR bridge detection method fusing section probability modeling and graph topology analysis, first, water and land segmentation is performed on the polarimetric SAR image, and independent water area branches are extracted; for the end of each water area branch, a particle filtering algorithm is used for probability modeling, and a rectangular section representing a potential bridge connection point is robustly extracted; a water area network graph is constructed with the water area branches as nodes and matched section pairs as edges, the sections are accurately connected through a two-stage matching strategy combining bidirectional propagation verification and geometric constraint, and non-river water bodies are filtered out based on geometric features; edges in the network graph are traversed, and the bridge region is accurately positioned according to the geometric relationship between the matched sections. The application utilizes the stable topological characteristics that bridges cause water area rupture and form symmetrical sections, overcomes the problems that traditional methods are unstable, easy to miss detection and misjudgment under complex water area networks, narrow tributaries and strong noise interference, and realizes high-precision and high-robustness detection of multi-scale bridges.

The application discloses a water area extraction method fusing radar backscattering and interference coherence coefficients, and belongs to the technical field of remote sensing water area extraction, and comprises the following steps: S1, acquiring a polarimetric SAR image, and pre-processing the polarimetric SAR image to obtain a backscattering coefficient image and an interference coherence coefficient image; S2, calculating an SDWI water body index according to the backscattering coefficient image; S3, determining a water body preliminary extraction result according to the SDWI water body index; S4, performing fusion processing on the water body preliminary extraction result based on the interference coherence coefficient image to generate a fused water body extraction result; and S5, performing refinement processing on the fused water body extraction result to obtain a final water body range. The application can not only accurately calculate a segmentation threshold, but also can avoid the influence of submerged plants and silt on the extraction result, and improves the accuracy of water area extraction.

The present application relates to a method, device and equipment for polarization SAR image classification based on complex and real numbers, which preprocesses the full polarization SAR sample data, extracts multiple polarization features by using the reflection symmetry decomposition method and performs normalization processing, and divides them into real polarization features and complex polarization features, and constructs corresponding training data, and inputs the training data into an image classification composite network for training, wherein the image classification composite network includes a real branch network and a complex branch network that process real polarization features and complex polarization features respectively, and a fusion classification network that fuses the output features of the real branch network and the complex branch network and classifies according to the fused features, and inputs the real polarization features and the complex polarization features corresponding to the full polarization data into the trained image classification composite network to realize image classification. The present method can effectively improve the classification accuracy of polarization images.

The invention relates to a simplified polarimetric SAR ship refined interpretation method and system based on joint feature space construction. The method comprises the following steps: receiving compact polarization data in a compact polarimetric SAR system through a linear polarization mode and carrying out protocol processing to obtain uniformly represented compact polarization data; extracting polarization characteristic parameters, and constructing a classification joint characteristic space; sVR is introduced to carry out dynamic self-adaptive adjustment on a boundary threshold value of surface scattering and volume scattering, and a combined feature space classification plane after self-adaptive adjustment is used to carry out initial classification on ship targets; and performing iterative clustering on the scattering mechanism by using a GHPSS-Wishart classifier to obtain a refined interpretation result of the ship target. The main work of the simplified polarimetric SAR data is to interpret the structure scattering mechanism of a ship target, fine interpretation can be carried out on different types of ship targets, the type of a ship to which the ship targets belong can be judged through an interpreted image, and the interpretation degree of the ship structure is improved.

The present invention discloses a polarization SAR coherent speckle filtering method based on mean shift, the purpose of which is to solve the problem that current methods are mostly based on statistical correlation between polarization channels, and thus easily filter only the diagonal elements of the polarization covariance matrix / polarization coherence matrix, thereby realizing the processing of non-diagonal elements and improving the filtering effect, and can realize the preservation of boundary features and polarization scattering characteristics, belonging to the field of radar electronic warfare. The technical solution is to estimate the probability density function according to the kernel function; calculate the mean shift vector according to the gradient of the probability density estimate of the kernel function; perform peak iterative search according to the obtained mean shift vector; and obtain the filtering result after the iterative search ends. The present invention is simple to operate, has a strong engineering foundation and application prospects, and can be extended to actual scenarios such as battlefield reconnaissance and detection of local targets in complex electromagnetic environments.

The application discloses a polarimetric SAR image classification method and system, a medium and a program product, relates to the field of polarimetric SAR image classification, and comprises the following steps: acquiring a polarimetric data set; constructing an anchor sample training set and a positive sample pair data set according to the polarimetric data set; constructing a residual neural network model; performing first stage training on the residual neural network model by using the positive sample pair data set, obtaining an intermediate residual neural network model trained through the first stage; performing second stage training on the intermediate residual neural network model by using the polarimetric data set and the anchor sample training set, obtaining a residual neural network model trained through the second stage; and performing clustering on a polarimetric SAR image to be classified by using the residual neural network model trained through the second stage and generating a classification result map. The application can effectively and accurately classify and identify the polarimetric SAR image without any labeling cost.