Improved cva change detection method for complex remote sensing image background

Abstract

The invention discloses an improved CVA change detection method for complex remote sensing image backgrounds, comprising: selecting two multi-temporal remote sensing image images and performing image registration, radiation normalization preprocessing, and adopting a method based on principal component analysis and wavelet transform The image fusion method analyzes the hidden information of the multi-temporal remote sensing image, and extracts the spatial and spectral characteristics of the central pixel of the multi-temporal remote sensing image by constructing a multi-directional difference descriptor, and uses the gray level co-occurrence matrix to extract the multi-temporal remote sensing image. Texture features, and on this basis, adopt a correlation-based feature fusion strategy to obtain a unified change intensity difference image, and finally use the EM algorithm to obtain the threshold value of the change pixel, and obtain the binary detection result. This method can effectively deal with the interference of false changes in the background of complex remote sensing images, and significantly improve the accuracy and robustness of change detection.

Description

technical field [0001] The invention relates to the technical field of remote sensing image processing, in particular to an improved CVA change detection method for complex remote sensing image backgrounds. Background technique [0002] In recent years, with the rapid development of aerospace remote sensing technology, massive multi-temporal remote sensing images provide an important data source for monitoring regional changes. The change detection of remote sensing images is to use the remote sensing images of the same area in different periods to analyze and judge the changes between images, which has become one of the hotspots in the field of remote sensing image processing technology. [0003] Malila proposed a change detection method based on change vector analysis (CVA, Change Vector Analysis), which can extract the change intensity and change direction information, and can avoid the error accumulation caused by image classification; Bektas et al. Replace the original...

AI Technical Summary

Problems solved by technology

[0004] Most of the above CVA improved algorithms directly use a single pixel as the processing unit, lack of consideration of the spatial context information and texture information of the change vector, and ignore the difference and complementarity of the change information between different bands, and are susceptible to the interference of "false changes". , it is difficult to meet the requirements of high-resolution data

Images