A Change Detection Method in Remote Sensing Image Based on Kernel Propagation

Abstract

The invention discloses a remote sensing image change detection method based on nuclear transmission and the method is mainly used for overcoming the defects in the prior art of low detection accuracy caused by a fact that a relation between data cannot be accurately reflected. The remote sensing image change detection method is realized by the following steps of: inputting two remote sensing images with different time phases and making the difference between the two remote sensing images to obtain a difference value image; dividing the difference value image to obtain a super-pixel set; utilizing a k mean value method to divide the super-pixel set into a certain change type, a certain non-change type and an uncertain type; selecting a seed construction constraint set in super-pixels which belong to the certain change type and the certain non-change type; utilizing the constraint set to calculate a seed nuclear matrix and utilizing a nuclear transmission formula to calculate a full-nuclear matrix and opposite angle normalization; and clustering a normalized full-nuclear matrix to obtain a change detection result. The remote sensing image change detection method disclosed by the invention has stronger noise immunity and can be used for effectively removing miscellaneous points; and meanwhile, edge information can be better kept and the accuracy of the detection result is high. The remote sensing image change detection method can be used in fields of urban area extending monitoring, forest and vegetation change monitoring and the like.

Description

Technical field [0001] The invention belongs to the field of digital image processing, and mainly relates to remote sensing image change detection, in particular to a remote sensing image change detection method based on nuclear propagation, which can be used for remote sensing image analysis and processing. Background technique [0002] Remote sensing image change detection is the process of identifying the state change or phenomenon change of the object by analyzing and extracting the difference in electromagnetic spectrum characteristics or spatial structure characteristics between remote sensing images of different time phases in the same area. It has been widely used in many fields of national economy and national defense construction, such as agricultural survey, forest and vegetation change monitoring, urban expansion monitoring, military target monitoring, etc. [0003] A common detection method in remote sensing image change detection is the method of first comparison and ...

AI Technical Summary

Problems solved by technology

This method reduces the false detection of change detection results by incorporating neighborhood information and improving the clustering method, but the method also performs poorly on low-contrast difference maps

[0006] The above-mentioned change detection methods all use unsupervised learning methods, which cannot accurately reflect the relationship between data, which makes the change detection results unsatisfactory.

Images