5 results about "Polarimetric sar" patented technology

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.

This invention discloses a five-component power decomposition method and system for compressed polarimetric SAR data, belonging to the field of synthetic aperture radar target decomposition technology. The invention preprocesses the covariance data of each pixel in the acquired compressed polarimetric SAR image to extract two dominant scattering mechanism discriminators for each pixel; determines the dominant scattering mechanism based on the extracted discriminators; selects a scattering model for power decomposition based on the dominant scattering mechanism of each pixel; and performs power decomposition on each scattering model to obtain five-component power. This invention is used for radar target decomposition.

This invention discloses a polarimetric SAR change detection method and system based on a Siamese attention complex convolutional neural network. It addresses the issues of poor quality difference maps generated by speckle noise in PolSAR images, and the problem that current real-number networks for SAR image change detection can disrupt the integrity of the complex structure of PolSAR data. This invention utilizes a Siamese network architecture to construct a more robust multi-scale feature difference map to suppress the influence of speckle noise. Furthermore, it combines a complex network to maintain the integrity of the PolSAR data structure and reduce polarimetric information loss. A corresponding complex attention module is also designed to enhance the identification of changed regions. Finally, the change detection results are obtained by decoding the multi-scale feature difference map. By using a Siamese attention complex convolutional neural network, the invention enhances the utilization of polarimetric information while suppressing the influence of speckle noise, thereby improving the accuracy of PolSAR change detection.

The application discloses a general compact polarimetric SAR calibration method and device, and belongs to the technical field of polarization calibration. The method aims at the problems of poor universality of existing calibration methods, difficulty in adapting to different working modes of loads and inconsistency of amplitude and phase coefficients of calibrators, establishes a general system model uniformly covering three compact polarization modes of pi / 4, dual circular polarization and circular transmission and linear reception, and demonstrates that the Faraday rotation effect does not change the model structure. The application adopts a genetic algorithm to globally optimize system distortion parameters, and is supplemented by an analytical method to estimate amplitude and phase coefficients of each calibrator, so that parameter separation and high-precision estimation are realized. The application breaks through the limitation of a single mode, does not require amplitude and phase consistency of calibrators, and has the advantages of strong universality, high precision and good robustness, with each parameter estimation error being less than 1dB or 5 degrees when SNR is greater than 33dB.

This invention relates to a method for feature extraction from polarimetric SAR images, comprising the following steps: acquiring raw polarimetric SAR image data to obtain the coherence matrix of the polarimetric SAR image; performing polarization pointing angle compensation and ellipticity angle compensation on the coherence matrix; calculating the proportion of power corresponding to the asymmetric scattering component to the total power; decomposing the coherence matrix after ellipticity angle compensation into a symmetric scattering part and an asymmetric scattering part, obtaining the coherence matrix and scattering power of each part; determining an adaptive volume scattering model; decomposing the obtained symmetric scattering part into surface scattering component, even-order scattering component, and adaptive volume scattering component; and decomposing the asymmetric scattering part into helical scattering component, directional dipole scattering component, and composite asymmetric scattering component. This invention can provide a more detailed description of ground features in different states, effectively extracting scattering information from different ground features, and playing a significant role in analyzing the scattering characteristics of different ground features.