High-resolution SAR image change detection method based on space-time graph kernel function

Abstract

The invention discloses a high-resolution SAR (Synthetic Aperture Radar) image change detection method based on a space-time graph kernel function, and mainly solves the problem of low detection precision caused by the fact that an existing ratio kernel method cannot fully mine and utilize the spatial structure characteristics of an image. The method comprises the following implementation steps: (1) constructing a two-moment local sparse graph model according to two-moment SAR images; (2) constructing a two-moment global graph model by using the two-moment local sparse graph model; (3) constructing a two-moment space kernel function based on the two-moment global graph model; (4) constructing a space-time graph kernel function by utilizing the two-moment space kernel function; and (5) inputting the space-time graph kernel function into the support vector product to obtain a change detection result. Compared with a ratio kernel method, the SAR image change detection method has the advantages of being high in detection precision and good in change area detail keeping, and can be used for SAR image change detection.

Description

technical field [0001] The invention belongs to the technical field of image processing, relates to image change detection, and can be used for monitoring and evaluating ground object state changes on SAR images. Background technique [0002] SAR image change detection aims to identify the change information between SAR images of the same scene captured at different times, and is an important branch of remote sensing interpretation. SAR image change detection has been widely used in disaster management, urban planning, land cover monitoring, man-made target detection and other fields. With the improvement of resolution, complex spatial structure information appears in high-resolution SAR images, and the effective utilization of complex local and global spatial structure information brings challenges to the development of change detection technology. [0003] SAR image change detection technology is generally implemented through supervised and unsupervised methods. Unsuperv...

AI Technical Summary

Problems solved by technology

[0004] The object of the present invention is to address the shortcomings of the above-mentioned existing problems, and propose a high-resolution SAR image change detection method of a spatio-temporal image kernel function, to solve the problem that the existing ratio kernel method cannot fully tap and utilize the image spatial structure features to cause detection The problem of low precision

Images