Remote sensing image change detection method based on twin convolutional neural network

Abstract

The invention discloses a remote sensing image change detection method based on a twin convolutional neural network, relates to the field of remote sensing, and mainly solves the problem of poor generalization of a conventional change detection method at present. The method comprises the following steps: acquiring multi-temporal remote sensing image data; obtaining mask images, establishing a remote sensing image change detection data set; constructing a twin convolutional neural network model; training a twin convolutional neural network by using the data set; obtaining a training model, carrying out change detection on a front time phase image and a rear time phase image to be detected by utilizing the training model; and obtaining a preliminary change prediction result, and comparing the prediction value of the pixel of the preliminary change prediction result with a preset pixel threshold, thereby dividing the preliminary change prediction result into a change region category and anon-change region category, and obtaining a change detection result. The method is better in generalization performance, meanwhile, end-to-end processing is met, and engineering application is facilitated.

Description

technical field [0001] The invention relates to the field of ultrafast laser processing, in particular to a remote sensing image change detection method based on a twin convolutional neural network. Background technique [0002] Remote sensing image change detection is a method to obtain the change information of the area by analyzing the same area of ​​the multi-temporal remote sensing image. With the development of science and technology and the progress of society, the ability of human beings to develop and transform nature has been continuously strengthened, and the surface landscape has changed more and more frequently, which makes the research on land use and land cover change become the frontier and hot spot in the global change research. As the main technical means of change detection, the rapid development of remote sensing technology makes the number of acquired remote sensing images more and more, and the spatial and temporal resolutions are getting higher and hig...

AI Technical Summary

Problems solved by technology

[0003] The technical problem solved by the present invention is to provide a remote sensing image change detection method based on a twin convolutional neural network, which solves the problem that the traditional remote sensing image change detection method cannot meet the requirements of the increase in the number and resolution of remote sensing images due to the inability to accurately extract the features in the image. The problem of generalization accuracy requirements

Images