An Unsupervised Change Detection Method for Multispectral Remote Sensing Images Based on Information Expansion

Abstract

The present invention relates to a method for non-supervised change detection of multi-spectral remote sensing images based on information expansion, comprising the following steps: 1) band spectrum information expansion based on nonlinear wave band generation: respectively performing multi-spectral images of the previous time phase and the next time phase Extend the band spectral information of any two original bands to obtain the newly expanded nonlinear artificial spectral band; 2) Expand the band space information based on multi-scale morphological reconstruction: the original band and the nonlinear artificial spectral band are respectively reconstructed through space After obtaining the feature set of spatially extended bands by operation, the differential operation is performed to obtain the difference band set; 3) Unsupervised multi-class change detection. Compared with the prior art, the invention has the advantages of realizing limited original band expansion and spatial information reconstruction, realizing automation of multi-type changes, non-supervised detection and the like.

Description

Technical field [0001] The present invention relates to a multi-spectral remote sensing image processing, in particular, to a multi-spectral remote sensing method based on information expansion. Background technique [0002] The dynamic changes of the surface reveals the environmental evolution of the environment from the time dimension. Connect-to-place observations of Earth Observatory, detect human activities and natural factors on environmental and surface coverage, which has extremely important significance for global changes. Variation detection technology is one of the most important technologies in terms of land observation, automatically or semi-automatically identifies the actual land coverage / land of two or more images between different satellite observations, two or more images in the same geographic area. Use changes. In many sensors mounted on satellites, multi-spectral scanners can acquire a remote sensing image of higher spatial resolution over a large geographi...

AI Technical Summary

Problems solved by technology

[0003] Conventionally, when using multi-temporal and multi-spectral images for change detection applications, due to the limitations of the data source itself, such as the poor quality of image bands (including uncalibrated water vapor bands, image bad sectors, band noise, etc.), the space between bands Location inconsistency, inconsistency between multi-temporal data (such as cloud, shadow and other interference), and the limitation of the spectral range of the band (such as only covering the visible light band, no near-infrared, mid-wave infrared), etc., and then using very few bands When performing multi-type change detection, the original spectral band cannot fully reflect the real ground change information, which increases the difficulty of change detection

Although methods based on kernel functions or deep neural networks can provide a way to solve such problems to a certain extent, they all require a long-term tuning process and a huge amount of computation, and the large number of training samples required by these methods is changing in practice. detection applications are difficult to obtain

Images