Compressed learning perception based SAR (Synthetic Aperture Radar) high-resolution image reconstruction method

Abstract

The invention discloses a compressed learning perception based SAR (Synthetic Aperture Radar) image high-resolution reconstruction method which is mainly used for solving the problem that the quality of a reconstructed image is reduced because a sparse base and an observation matrix cannot meet restricted isometry property (RIP) existing in the conventional method. The method comprises the following steps of: inputting a training sample set and a test image; learning a dictionary and the observation matrix by using a Couple-KSVD (Kernel Singular Value Decomposition) method to obtain a target training dictionary psi and a coupled observation matrix phi; finally reconstructing a small block of a high-resolution image by using a fast Bayesian matching pursuit FBMP algorithm; and repeating the operation on all small blocks of the image to acquire a final SAR high-resolution reconstructed image. By adopting the method, the reconstruction quality of various SAR high-resolution images can be improved at different sampling rates; and the method can be used for recovery and recognition of targets and objects in various SAR images.

Description

technical field [0001] The invention belongs to the technical field of image processing, and relates to a synthetic aperture radar SAR image high-resolution reconstruction method, which can be used for the restoration and identification of targets and objects in various SAR images. Background technique [0002] The size of SAR image is large and the amount of data is high, which brings many problems to the real-time transmission and storage of data. The traditional SAR image compression and transmission process is: collect data under the Nyquist sampling requirement, then compress and code the SAR image, and finally store and transmit the coded value. There are two disadvantages in such a processing method: first, since the sampling rate must not be lower than twice the signal bandwidth, this will bring great pressure to the hardware system; second, in the process of compression encoding, a large number of data, resulting in a waste of data computing and memory resources. ...

AI Technical Summary

Problems solved by technology

There are two disadvantages in such a processing method: first, since the sampling rate must not be lower than twice the signal bandwidth, this will bring great pressure to the hardware system; second, in the process of compression encoding, a large number of data, resulting in a waste of data computing and memory resources

However, in the existing SAR image reconstruction algorithms, the sparse bases used are all non-adaptive, such as Fourier base, wavelet base, etc. In general, it is difficult for SAR images to obtain sufficiently sparse representations under these bases , while random matrices that obey Gaussian or Bernoulli distributions are mostly used in the selection of observation matrices, but they only have good uncorrelation with orthogonal basis, so in most cases, the accuracy of compressed sensing reconstruction is The reconstructed RIP conditions may not be satisfied, so the reconstruction effect of SAR high-resolution images will be poor

Images