Polarization SAR image classification method based on deep neural network

Abstract

The invention discloses a polarization SAR image classification method based on a deep neural network. The method mainly solves the problems that traditional polarization SAR image classification accuracy is low and boundaries are disorderly. The method includes the classification steps that a power diagram I is acquired from polarization SAR data through Pauli decomposition, the power diagram I is segmented in advance, and then a plurality of small blocks are acquired; a training data set U is selected from a polarization SAR image, input into a two-layer self-coding structure for training and then classified through a Softmax classifier; a test data set V is selected from the polarization SAR image and input into the trained two-layer self-coding structure, and then classification labels are acquired through the Softmax classifier; in the pre-segmented small blocks, the classification labels and channel information of the power diagram I are combined, and then small block labels are acquired. The polarization SAR image classification method has the advantages that the recognition rate is high, result region consistency is good, and the method can be used for polarization SAR homogeneous region terrain classification.

Description

technical field [0001] The invention belongs to the field of polarimetric synthetic aperture radar, in particular to a method related to polarimetric SAR image segmentation, which can be applied to ground object recognition. Background technique [0002] Synthetic Aperture Radar (SAR) is an active sensor, which has the great advantages of all-time, all-weather, and high resolution, so it is very popular. Due to the wide application of synthetic aperture radar in many fields such as military reconnaissance, resource survey, and disaster monitoring, countries have gradually increased their attention and investment in research and development of synthetic aperture radar. Polarimetric SAR is a synthetic aperture radar capable of measuring and imaging targets with full polarization. [0003] From the way of polarization, according to the way of sending and receiving electromagnetic waves, radar can be divided into four kinds of polarization, namely HH, HV, VH, VV. Wherein, H in...

AI Technical Summary

Problems solved by technology

However, the above three classification methods usually only consider the independent information of each pixel. In fact, the pixel information in its neighborhood will also affect its classification results.

Secondly, the scattering characteristics of an independent pixel in polarimetric SAR data are easily affected by coherent speckle noise, and it is difficult to achieve satisfactory classification results.

Images