Content-based remote sensing image change detection information retrieval method

Abstract

The invention discloses a content-based remote sensing image change detection information retrieval method. The method comprises the following retrieval steps of performing image super-resolution on a to-be-detected original remote sensing image by using a super-resolution variable rate generative adversarial network to obtain a high-resolution remote sensing image; extracting an LSH feature of each pixel in the high-resolution remote sensing image by using a position sensitive histogram algorithm, and extracting an illumination invariance feature of the high-resolution remote sensing image to obtain a chromatogram of the high-resolution remote sensing image; assigning an initial weight value of each pixel in the chromatogram to be 1 by using an iterative weighted multivariate change detection algorithm, and then determining a weight value in the chromatogram until the number of iterations is equal to a preset number threshold; and respectively comparing the current weight of each pixel in the chromatogram with a preset weight threshold, and determining a change area in the original remote sensing image according to the target pixel point belonging to a change element to obtain a change detection result map of the original remote sensing image.

Description

technical field [0001] The invention relates to the technical field of remote control image processing, in particular to a content-based remote sensing image change detection information retrieval method. Background technique [0002] Remote sensing image processing is a series of operations such as radiation correction and geometric correction, image finishing, projection transformation, mosaic, feature extraction, classification and various thematic processing on the image in order to achieve the expected purpose. Remote sensing image processing can be divided into two categories: one is to use optical, photographic and electronic methods to process remote sensing analog images, referred to as optical processing; the other is to use computers to perform a series of operations on remote sensing digital images to obtain certain expected results. The resulting technique is called remote sensing digital image processing. [0003] Traditional remote sensing image change detect...

AI Technical Summary

Problems solved by technology

For content differences, traditional algorithms may misjudge the same object as a change element, resulting in a significant decrease in the accuracy of change detection

Images