Automatic registration method of optical and sar images under multi-level and multi-feature constraints

Abstract

The invention provides an optical image and SAR image automatic registration method within multilevel multi-feature constraint. The optical image and SAR image automatic registration method within the multilevel multi-feature constraint comprises the following steps that optical images and SAR images are preprocessed, multi-scale level set segmentation is conducted, and a plane segmentation result is obtained; when similar plane targets exist, a coordinate set of centroid points of areas seemingly provided with the same name is calculated; when similar plane targets do not exist, multi-scale analysis is conducted on the images by means of wavelet transformation, extraction of lower-layer linear characteristics and point set matching are conducted on the thickest image, and lower-layer registration transformation parameters are extracted; high-layer linear characteristics is extracted, a control-point matching degree function is defined according to the lower-layer transformation parameters, and high-layer point set matching is conduced; finally, a matched point pair is precisely judged out through the KNN image from the structure, a wrong matched point pair is eliminated, transformation parameters of the matched point pair are obtained according to a polynomial transformational model, and a final registration result is obtained.

Description

technical field [0001] The invention relates to the technical field of remote sensing image processing, in particular to a method for feature registration of optical images and SAR images. Background technique [0002] With the development of imaging technology, a large number of synthetic aperture radar (SAR) and optical sensor systems have emerged, providing a variety of image data for earth observation in the same area. SAR images reflect structural information better, and have the advantages of all-weather, all-weather, penetrability, etc. Compared with optical images, they have a larger reconnaissance range, and can find targets that are not easy to be found by optical sensors, but the images do not contain spectral information, and The microwave reflection characteristics of the target may cause the SAR images of the same object to appear in different forms. Optical images image the target intuitively and contain rich spectral information, but are greatly affected by ...

AI Technical Summary

Problems solved by technology

[0016] To sum up, the feature-based registration method is more suitable for the registration of heterogeneous images. However, most of the existing feature registration algorithms use the similarity measure to judge whether each target feature is similar, and only consider the target itself. For optical and SAR images, due to the above-mentioned radiation and geometric differences, and the inaccurate feature extraction of SAR images, it is not enough to judge only by the characteristics of the target itself

Images