SAR satellite image and optical image automatic matching retrieval method

Abstract

The SAR satellite image and optical image automatic matching retrieval method disclosed by the invention is good in robustness, high in matching precision and high in calculation speed, and is realized through the following technical scheme: firstly, carrying out overlapping equal-interval sampling on a to-be-detected SAR image by adopting a sliding window means; respectively calculating matching results from all the optical template images to the SAR image sequences and matching results from all the SAR image sequences to the optical template images by adopting a cyclic matching mechanism, and combining SAR image block sequence results of two cyclic matching branches to a total image; sending to a screening module, screening feature point pairs of which the distance measurement matrix results of respective branches accord with a threshold, and forming an effective matching point pair set; then, calculating SAR feature point coordinates and optical feature point coordinates by utilizing the obtained correlation matrix, combining two sets of coordinate results, and screening out N sets of matching point pairs with the minimum distance; and adopting an RANSAC algorithm to screen out abnormal values to obtain an automatic matching retrieval result.

Description

technical field [0001] The invention relates to the technical field of image processing, and relates to a method for matching an optical image to a SAR satellite image. Background technique [0002] Synthetic Aperture Radar (SAR) image and optical image registration is the premise of image fusion, target change detection, natural disaster assessment and other applications, and belongs to the category of multi-modal image registration. Optical images usually use central projection area imaging or push-broom scanning to obtain data. The imaging results conform to the visual characteristics of the human eye, have high imaging resolution, and are easy to identify. However, optical sensors are easily affected by phenological phenomena and lighting conditions. It is easy to produce blurred image noise, so the work efficiency is limited to a certain extent. Synthetic Aperture Radar (SAR) technology is an active imaging system. SAR can not only image with high resolution, but also ...

AI Technical Summary

Problems solved by technology

[0004] In order to realize the matching of SAR image and optical image, the purpose of the present invention is to solve the problems existing in the prior art, and provide a kind of robustness, high matching precision, The calculation speed is fast, and the SAR satellite image and optical image automatic matching retrieval method with a cyclic verification mechanism is used to solve or at least partially solve the matching of optical image and SAR satellite image in the scene of strong illumination change and strong radiation difference existing in the method in the prior art Technical Issues That Don't Work Well

Images