SAR (synthetic aperture radar) image change detection method based on support vector machine and discriminative random field

Abstract

The invention belongs to the technical field of SAR (synthetic aperture radar) image change detection, and discloses an SAR image change detection method based on a support vector machine and a discriminative random field. The SAR image change detection method based on the support vector machine and the discriminative random field includes the steps: normalizing gray values of two original time phase images, and extracting corresponding gray characteristic differences and textural characteristic differences in the processed images; forming difference characteristic vectors; extracting boundary strength of each pixel in a difference image by the aid of weighted average ratio operators; selecting training samples in the difference image, and expressing the training samples by the aid of the corresponding difference characteristic vectors to obtain initial category labels of testing samples and posterior probabilities of the category labels of the testing samples by the aid of the training support vector machine; obtaining initial support vector machine-discriminative random field models; updating the support vector machine-discriminative random field models to obtain final category labels and change detection results of the corresponding testing samples.

Description

technical field [0001] The invention belongs to the technical field of SAR image change detection, in particular to a SAR image change detection method based on a support vector machine and a discriminant random field. Background technique [0002] With the gradual maturity of synthetic aperture radar (SAR) technology and the continuous improvement of SAR image resolution, the use of SAR images has gradually attracted people's attention. Compared with optical remote sensing images, SAR images are not affected by factors such as weather and clouds, and can obtain remote sensing data all-weather and all-weather, which is a better source of change detection information. [0003] SAR image change detection (change detection) through the comparison and analysis of SAR images in different periods, according to the difference analysis between images to obtain the required ground object change information. Change detection technology can be applied in many aspects, such as the posi...

AI Technical Summary

Problems solved by technology

Recently, there are many researches on SAR image change detection: change detection methods based on statistical models, such as L. Bruzzone performs generalized Gaussian modeling (GGD, Generalized Gaussian Distributions) on the SAR image logarithmic ratio difference map and then applies it under GGD The improved KI (Kittler–Illingworth) threshold selection algorithm is used to classify to obtain the final change image. This method has achieved good detection results but does not consider spatial information, and the selection of model parameters is also a difficulty; change detection based on multi-scale analysis Methods, such as Kai-Kuang Ma proposed a multi-scale change detection method based on dual-tree-complex wavelet transform (DT-CWT, Dual-Tree Complex Wavelet Transform), which uses DT-CWT to perform multi-scale decomposition of the logarithmic ratio map , but does not take into account the texture information of the image, and the selection of the threshold is also a thorny issue; in recent years, a new SAR image change detection algorithm based on the kernel method has been developed. Gustavo Camps-Valls first proposed the application of the kernel method in 2008. For SAR image change detection, this method first extracts the intensity information and texture information of the image, and then constructs an intensity-texture ratio difference synthesis kernel (RDC_kernel) to realize SAR image change detection. This method can effectively realize SAR image change detection, but it does not consider Spatial information, and sensitive to noise

Images