Integrated transfer learning classification method and system for single-view full-polarization SAR data

Abstract

The invention provides an integrated transfer learning classification method for single-view fully polarized SAR data, and the method comprises the steps of employing full-image segmentation and local windowing segmentation, and employing the context information of an image space to concentrate the labeled sample size of a source domain and expand the labeled sample size of a target domain; then, setting a source domain labeled sample selection process by combining a scattering vector similarity coefficient and a fitness function, and adjusting source domain sample distribution used by a training evaluator model according to a target domain category center; introducing reference information of the reliability of the weak classifier as a weight factor, performing category soft prediction by using the migration weak classifier in a weighting form, and giving a target domain unlabeled pixel false label with a consistent prediction result to expand the labeled sample size of the target domain and train a new weak classifier; and completing ensemble classification of all pixels in the target domain by iteratively utilizing the generated migration weak classifier set. The invention can significantly reduce the high dependence of a radar image classification task on target domain label information, and improves the classification efficiency and the automation level.

Description

technical field [0001] The invention belongs to the technical field of fully polarimetric radar remote sensing image processing, and designs a new transfer learning method and system based on fully polarimetric synthetic aperture radar (Polarimetric Synthetic Aperture Radar, POLSAR) single-view data for integrated classification of ground objects. Background technique [0002] Remote sensing technology can conduct long-distance observation without direct contact with the target, and is an ideal way to obtain regional surface information. Supervised classification of remote sensing images is the process of using pixel samples with class labels to establish a recognition model to infer the category of other pixels in the image. It has great application potential in land use management and land cover change. It provides important support for planning land use, assessing the impact of natural disasters, and organizing rescue and reconstruction in disaster areas. Among various r...

AI Technical Summary

Problems solved by technology

However, the transfer learning technology at this stage mainly focuses on conventional pattern recognition tasks, and fails to combine the spatial context information in remote sensing images and the characteristics of radar scattering vector data to design algorithms, which can easily cause negative transfer effects when directly used in SAR images; , Polarization Synthetic Aperture Radar (POLSAR) uses multi-channels to obtain the backscattering information of ground objects and targets, and the classification results are easily affected by speckle noise

A common way to reduce the impact of noise is to use multi-view processing, that is, to use the spatial set average to obtain the second-order statistics of the scattering vector as the input features of the classifier, but this processing artificially reduces the spatial resolution and loses a lot of spatial details.

Images