Polarized SAR image classification method based deep multi-example learning

Abstract

The invention discloses a polarized SAR image classification method based deep multi-example learning, and solves the technical problem of low classification precision due to insufficient feature extraction in a conventional polarized SAR image classification method. The method includes the steps of filtering polarized SAR images, selecting a training sample set, extracting sample characteristics, initializing a convolutional neural network (CNN) and a deep belief network (DBN), normalizing sample characteristics, training the CNN and the BDN, extracting combined characteristics, inputting the combined characteristics to an SVM classifier for training, classifying polarized SAR images through the trained SVM classifier, outputting the classification result and calculating classification precision. The method effectively combines image spatial neighborhood characteristics and polarized characteristics, thereby improving the classification precision for polarized SAR images. The method is applicable to terrain classification and target identification for polarized SAR images.

Description

technical field [0001] The invention belongs to the technical field of image processing, and relates to a polarization SAR image classification method, in particular to a polarization SAR image classification method based on deep multi-instance learning, which can be used for ground object classification and target recognition of polarization SAR images. Background technique [0002] SAR is a synthetic aperture radar, which has the advantages of all-weather, all-time, high resolution, and side-view imaging. Polarization SAR is a high-resolution active coherent multi-channel synthetic aperture radar, which is an important part of SAR. It has the characteristics of acquiring data through multi-polarization channels, and can express more abundant information than SAR. It can be widely used in military, navigation, agriculture, geographical surveillance and many other fields. It is extremely important in the field of international remote sensing, so polarimetric SAR image class...

AI Technical Summary

Problems solved by technology

[0006] The purpose of the present invention is to overcome the above-mentioned defects in the prior art, and propose a polarimetric SAR image classification method based on deep multi-instance learning, which is used to solve the problems in the existing polarimetric SAR image classification because there is no spatial neighborhood information of the image. Combining with polarization information leads to technical problems of low image classification accuracy

Images