Time sequence integrated multispectral remote sensing image change detection method and system

Abstract

The invention discloses a time sequence integrated multispectral remote sensing image change detection method and a time sequence integrated multispectral remote sensing image change detection systemin the technical field of image processing. Due to the fact that network output of different time sequences is integrated, the final change detection result of the double-phase multispectral remote sensing image is more reliable and stable, and the method comprises the steps of preprocessing the multispectral remote sensing image, and calculating the change vector amplitude of the multispectral remote sensing image; calculating an optimal segmentation threshold of the change vector amplitude, and determining a pseudo-mark sample set according to the optimal segmentation threshold and mean filtering; constructing a deep learning network based on time sequence integration; training the deep learning network through the pseudo-mark sample set; and inputting the multispectral images of different time phases into the trained deep learning network to obtain a final detection result.

Description

technical field [0001] The invention belongs to the technical field of image processing, and in particular relates to a time series integrated multi-spectral remote sensing image change detection method and system. Background technique [0002] The change detection of remote sensing images is to quantitatively analyze and determine the characteristics and process of surface changes from multi-temporal remote sensing data. So as to provide decision-making management departments such as land planning, natural disaster monitoring and other aspects of information. Change detection falls into three broad categories: unsupervised change detection algorithms, semi-supervised change detection algorithms, and supervised change detection algorithms. Because unsupervised change detection algorithms do not require training samples, and the modeling process does not require prior knowledge, this type of algorithm has been widely used. The unsupervised change detection algorithm general...

AI Technical Summary

Problems solved by technology

The disadvantage of this method is that the training of the network is prone to mode collapse

Images