Method for carrying out change detection on multi-level segmented remote sensing image

Abstract

The invention discloses a method for carrying out change detection on a multi-level segmented remote sensing image, and is characterized in that the method comprises nine steps, and in the method, after carrying out denoising and smoothing and the like on the image, through merging patch objects, a change detection result of the remote sensing image is obtained finally. In the method, the patch objects subjected to segmentation are compared by using a direct comparison method firstly, if the patch objects are changed, the patch objects are subjected to secondary segmentation by using an algorithm, then characteristic values are extracted and compared. By using the method disclosed by the invention, the pseudo change information can be removed effectively, and the change detection accuracy can be improved; and compared with the existing methods, by using the method disclosed by the invention, a more detailed and complex change result can be obtained, thereby realizing the change detection on sub-patch objects.

Description

technical field [0001] The invention relates to a method for detecting changes in remote sensing images, in particular to a method for detecting changes in remote sensing images with multi-level segmentation, and belongs to the technical field of image processing. Background technique [0002] Remote sensing image change detection refers to the analysis of remote sensing images in the same area in different periods, from which the information of changes in ground features over time can be detected, which can be used for geographic system information update, resource and environment monitoring, target dynamic monitoring, and military strike effect evaluation wait. [0003] The current detection techniques are divided into: [0004] 1. Pixel-based change detection method [0005] Based on pixel change detection, its realization mainly depends on the change of the spectral reflectance value in the remote sensing image caused by the change of the ground object, and these chang...

AI Technical Summary

Problems solved by technology

[0015] (1) Change detection based on pixels has a lot of pseudo-change information, the accuracy of change detection is not high, and it is not suitable for high-resolution remote sensing images

[0016] (2) The object-oriented change detection method adopts the direct comparison method, that is, after the image is segmented, the feature value is directly extracted for the change detection of the patch object, and it is difficult to detect the change of the sub-map object (inside the segmented area)

This method is limited by the accuracy of classification results, and there is a phenomenon of classification error accumulation

Images