Change detection method and device based on time sequence SAR intensity image variable coefficient

Abstract

The invention discloses a change detection method and device based on a time sequence SAR intensity image variable coefficient, and the method comprises the steps: acquiring SAR intensity images of a to-be-detected region at a plurality of time nodes within a preset time length, and obtaining a time sequence SAR intensity image sequence; calculating a variation coefficient of each space pixel point according to an intensity time sequence sample of each space pixel point in the time sequence SAR intensity image sequence, and then generating a variation coefficient graph according to the variation coefficient of each space pixel point; according to the time sequence SAR intensity image sequence, extracting a statistical identically distributed pixel sample corresponding to each space pixel point; performing spatial filtering on the variable coefficient image according to the statistical same-distribution pixel sample of each spatial pixel point to obtain a filtered variable coefficient image; and carrying out threshold segmentation on the filtered variable coefficient image to obtain a change detection result of the to-be-detected region. By implementing the method, the accuracy of change detection can be improved.

Description

technical field [0001] The invention relates to the technical field of remote sensing image processing, in particular to a method and device for detecting variation coefficients of time-series SAR intensity images. Background technique [0002] Remote sensing change detection techniques have proven to be a powerful tool for obtaining spatial information at multiple scales using satellites with high spatiotemporal coverage and sufficiently high image resolution. Compared with optical systems, the all-weather observation capability and high temporal and spatial resolution ensure the availability of SAR (Synthetic Aperture Radar, synthetic aperture radar) data during the occurrence of important events at different spatial scales, and SAR targets surface roughness and surface structure The high sensitivity of the attribute can flexibly resolve the spectral ambiguity brought about by the surface transformation. [0003] The traditional dual-temporal SAR change detection is based...

AI Technical Summary

Problems solved by technology

[0003] The traditional dual-temporal SAR change detection is based on the first and last two SAR images to generate the difference map, and then realize the change detection, but the traditional dual-temporal SAR change detection, on the one hand, the local adaptive statistics driven by the spatial neighborhood destroy the image On the other hand, only the first and last two SAR images are used for detection, the amount of information is too small, and some areas that are not sensitive to changes will be easily overlooked, and the probability of false warnings for irrelevant events such as vehicles passing by will be increased.

The above two aspects lead to traditional dual-temporal SAR change detection with low accuracy

Images