InSAR image processing method and device based on deep learning algorithm

Abstract

The invention discloses an InSAR image processing method and device based on a deep learning algorithm. The method comprises: using a low-precision digital elevation model (DEM) to simulate a synthetic aperture radar SAR image, registering the simulated SAR image with an actual SAR image, and establishing a correspondence between the low-precision DEM and the actual SAR image; performing interferogram simulation by utilizing a low-precision DEM based on the corresponding relation, and dividing the actually acquired interferogram from the simulated interferogram to obtain a differential interferogram; processing the differential interferogram, performing phase unwrapping on the differential interferogram according to the simulated interferogram, obtaining the original interferogram, and performing phase unwrapping thereon; performing baseline estimation and interference parameter calibration, reconstructing the DEM, and performing orthophoto production through the reconstructed DEM to obtain an InSAR interferogram; using the depth learning algorithm to train a noise reduction encoder DAE, and performing noise reduction processing on the InSAR interferogram to obtain a high-precisionInSAR image.

Description

technical field [0001] The present invention relates to the field of radar technology, in particular to an InSAR image processing method and device based on a deep learning algorithm. Background technique [0002] With the rapid development of radar technology in our country, Interferometric Synthetic Aperture Radar (InSAR) technology is also developing rapidly, which has outstanding advantages in rapid terrain mapping. Synthetic aperture radar interferometry technology is a high-precision earth observation technology developed rapidly with the development of information technology, photogrammetry technology, digital signal processing technology and other related technologies. It has all-time, all-weather, high-precision, high-efficiency, large-area and other outstanding advantages in topographic mapping, surface deformation monitoring, and glacier movement research. [0003] Using InSAR technology to quickly obtain high-precision digital elevation model (Digital Elevation ...

AI Technical Summary

Problems solved by technology

[0007] (1) Difficulties in interference processing and accurate elevation information inversion in alpine and urban areas

In the case of severe surface deformation, overlapping and shadowing in high mountainous areas and urban areas, undersampling of the interferometric phase and lack of interferometric information are prone to occur, resulting in difficult interferometric processing, poor solvability, and low accuracy of elevation measurement.

[0008] (2) The coherence of vegetation coverage area data is poor, and the efficiency of interference processing is low

In vegetation-covered areas, especially in dense forest areas and crop planting areas that grow vigorously in summer, the coherence of interferometric data acquired by repeated orbit mode is very low, the solvability of phase unwrapping is poor, and the accuracy of elevation measurement is low, which seriously affects the interferometric data. processing performance

[0009] (3) Large area InSAR processing requires a large number of ground control points

For areas where it is difficult to deploy control points such as mountains and valleys or overseas areas, due to the lack of ground control points, the accuracy of interferometric measurements is limited

[0010] (4) Changes in the atmosphere, ionosphere, and soil moisture will cause large changes in the interferometric phase value, which will seriously affect the interferometric accuracy measurement

Images