Remote sensing image change detection method based on neighbourhood similarity and threshold segmentation

Abstract

The invention discloses a remote sensing image change detection method based on neighbourhood similarity and threshold segmentation and aims to overcome the defect that the traditional method has poor noise immunity and low detection accuracy in terms of the change detection of the target with high noise. The realization process comprises the following steps: (1) using the strength normalization formula to carry out gray level matching on two remote sensing images; (2) using neighbourhood similarity distance measure to construct a similar matrix of the two remote sensing images; (3) combing the similar matrix to construct a difference image of the two remote sensing images; (4) constructing a two-dimension gray level column diagram for the difference image, using the 2D-OTSU method to determine the segmentation threshold value and separating the target area from the background area; and (5) using the fuzzy entropy method to continue classifying the unprocessed edges and noise points. The invention has the advantages of good noise immunity and high detection accuracy for the changing target and can be used for detecting targets with changes of multitemporal remote sensing images.

Description

technical field [0001] The invention belongs to the technical field of image processing, relates to an image change detection method, and is suitable for detecting ground object change information contained in two remote sensing images of the same area with different time phases. Background technique [0002] Change detection aims to obtain the ground object change information of the image through the difference between images in different periods in the same area. The key technology in observation application has urgent need and broad application prospect. [0003] Change detection is a key and hot issue in the field of remote sensing. Many scholars have classified and analyzed the existing change detection methods from different perspectives. The change detection method mainly considers image-to-image detection, and is a detection method developed at the pixel level. Existing change detection methods can be summarized into two categories: one is supervised detection meth...

AI Technical Summary

Problems solved by technology

However, on the whole, there are still many difficulties and problems in change detection that need to be studied and solved in depth.

For example, in the construction of difference images, in the case of strong noise, the traditional filtering method is easy to cause blur effect and lose the target information; in the classification process of the image, the anti-noise of the above method is not strong enough to keep the target edge intact At the same time, it can effectively remove noise interference, or it may easily cause the loss of target boundary information, resulting in poor detection results and insufficient detection accuracy.

Images