Deep learning remote sensing image registration method based on sub-image matching and application

Abstract

The invention discloses a deep learning remote sensing image registration method based on sub-image matching and application. The method comprises a sub-image matching stage and a transformation parameter estimation stage which are completed by the convolutional neural network. Comprising the following steps: 1, cutting a series of sub-images containing a plurality of features from an image; extracting sub-image features through a sub-image similarity learning network ScoreCNN with a feature vector inner product structure; estimating the similarity of the sub-images in the fusion stage; and according to the similarity, searching matched sub-images with high confidence by using a rapid screening algorithm; and 2, inputting the matched sub-images to the corresponding coordinates in the original image into a transformation parameter estimation network ETPN with a weight structure and position codes, and outputting a transformation matrix between the images to be registered. According to the invention, the problem of algorithm failure caused by insufficient correctly matched features in image registration with large feature change in a traditional registration frame is solved, and meanwhile, the precision of the deep learning registration method based on parameter regression is improved.

Description

technical field [0001] The invention relates to an image registration method and its application, in particular to a deep learning remote sensing image registration method based on sub-image matching and its application, belonging to the field of image processing. Background technique [0002] Image registration is one of the important processes of remote sensing image processing and the basis for subsequent remote sensing information applications. In recent years, remote sensing images have gradually developed towards high spatial resolution, high spectral resolution, and high temporal resolution. There are more and more application scenarios for high-resolution aerial and satellite remote sensing images, such as urban development, geographic change assessment, land analysis etc. The robustness and accuracy of remote sensing image registration have an important impact on subsequent tasks such as change detection and image fusion. Multi-temporal high-resolution optical rem...

AI Technical Summary

Problems solved by technology

[0006] In order to solve the problem that for multi-temporal high-resolution remote sensing images with large differences, the method based on local features is easy to fail and the deep learning method based on parameter regression has low precision. The present invention proposes a sub-image matching based depth Learning Remote Sensing Image Registration Methods

Images