Classification Method of Polarized SAR Objects Based on Self-paced Learning Convolutional Neural Network

Abstract

The invention discloses a polarization SAR ground object classification method based on a self-step learning convolutional neural network, which mainly solves the problems of low classification accuracy and large noise influence on complex ground object scenes in the prior art. The implementation scheme is as follows: 1. Obtain the polarization scattering matrix S and the pseudo-color RGB image under the Pauli basis from the original fully polarimetric SAR data; 2. Construct a three-dimensional matrix for each pixel to form a sample set, and construct training samples and test samples Sample set; 3. Construct a convolutional neural network and train the convolutional neural network based on self-paced learning to accelerate network convergence and improve the generalization ability of the network; 4. Use the trained convolutional neural network to classify test samples, The final classification result of fully polarized SAR ground objects is obtained. The invention improves the correct rate of classification of target objects in complex object scenes in polarimetric SAR images, and can be used for object classification and target recognition.

Description

technical field [0001] The invention belongs to the technical field of image processing, and further relates to a polarimetric SAR object classification method, which is applicable to object classification and target recognition. Background technique [0002] With the development of microwave remote sensing technology, high-resolution polarization synthetic aperture radar has become an inevitable trend in the development of SAR field, and polarization SAR image classification, as one of the important methods of polarization SAR image interpretation, has been widely used in national defense and civilian applications. and many other fields. Although high-resolution polarization SAR contains rich backscatter information, the current classification algorithms only use shallow polarization features, which cannot fully represent the complex scene information contained in the image. [0003] The classification of polarimetric SAR images involves many disciplines such as statistica...

AI Technical Summary

Problems solved by technology

However, the disadvantage of this method is that there is still a lack of better selection criteria for the polarization characteristic parameters, and only using the polarization characteristic parameters of the SAR image cannot fully express the image, which will directly affect the final result of the classification

Images