A high-resolution SAR image classification method based on sparse features and conditional random fields

Abstract

The invention provides a high-resolution SAR image classification method based on sparse features and conditional random fields. The method mainly solves the problems of low classification precision and non-accurate boundary retention in complicated scenes in the prior art. The method comprises the steps of: firstly, inputting high-resolution SAR images, selecting images to build a training data block set, and training system parameters of a sparse feature extraction algorithm; secondly, extracting SAR image block sparse features and training a logistics classifier to obtain the classificationposterior probability of the images and build a univariate potential energy function; thirdly, building a bivariate potential energy function by using a boundary constraint map obtained after fusionof a binary edge partition map and an edge strength map; forming a complete full connection conditional random field model by using the univariate potential energy function and the bivariate potentialenergy function and performing reasoning on the model to obtain a classification result. The method increases the classification precision of complicated scenes and edge details of high-resolution SAR images and can be used for SAR image terrain classification.

Description

technical field [0001] The invention belongs to the technical field of image processing, and further relates to a high-resolution SAR image classification method, which can be used for ground object classification and target recognition on the high-resolution SAR image. Background technique [0002] Synthetic aperture radar (SAR) is an all-weather and all-weather active microwave earth observation imaging system. Nowadays, high-resolution SAR images can be obtained through airborne platforms, TerraSAR-X, F-SAR satellites, etc., and high-resolution SAR images are classified as An important part of SAR image interpretation and analysis, realizing pixel-level image classification is an important task. [0003] Existing SAR image classification methods mainly focus on feature-based classification methods and graphical model-based classification methods. Based on traditional feature extraction methods such as statistical features including mean, variance, heterogeneity coefficie...

AI Technical Summary

Problems solved by technology

Many deep learning models, such as autoencoders, restricted Boltzmann machines, and sparse filtering have been applied to SAR image classification. These algorithms can learn abstract representations of data autonomously and obtain more discriminative feature expressions. However, these algorithms are due to There are a large number of parameters that need to be adjusted, and the correlation between the local features of the image is not fully considered, making the classification results of the real edge positions blurred and inaccurate, and it is impossible to obtain fine segmentation results

Images