Method for estimating spatio-temporal change of remote sensing image, device and storage medium

Abstract

The invention discloses a method for estimating temporal and spatial change of remote sensing image, a device and a storage medium. The method includes: a target area is divided into a plurality of grids with a set grid size as a unit; the multi-temporal remote sensing image data are clipped by the grid, and the spatio-temporal image data set is obtained; CNN model is used to classify and train the spatio-temporal image dataset to generate feature model of surface features; the grid is used to cut the source remote sensing image data and the target remote sensing image data so as to obtain aplurality of grid source images and a plurality of grid target images; the features of the grid source image and the grid target image are extracted by the feature model of the features, and the differences are compared and analyzed to obtain the spatio-temporal change results of the target region. Through this method, the CNN and GIS technology can be highly integrated, and the automatic processing of urban spatial and temporal change estimation based on the massive urban remote sensing image data is realized, which has high efficiency.

Description

technical field [0001] The invention relates to the technical field of remote sensing image applications, in particular to a method, device and storage medium for estimating temporal and spatial changes of remote sensing images. Background technique [0002] Change estimation of remote sensing images is an important part of remote sensing image data processing and application. Change estimation is to qualitatively or quantitatively analyze and determine the characteristics and processes of surface changes from remote sensing images of different periods and ages. Estimation of urban temporal and spatial changes based on remote sensing images will play an important role in many fields, such as land use status investigation, land use planning compilation, urban overall planning compilation, urban change and management planning, natural resource investigation, and urban basic surveying and mapping. Updating of basic geographic databases, monitoring of ocean and inland water bodi...

AI Technical Summary

Problems solved by technology

[0003] With the increasing accuracy, faster update frequency and better timeliness of urban remote sensing images, it has become an important data source for urban spatiotemporal change estimation; however, the traditional urban spatiotemporal change estimation methods mainly Including the method of manual comparison, the method of manual comparison is based on remote sensing image data of different ages or time periods through manual interpretation of images or even on-site detection. The image data of the phase is relatively low, and the degree of automation of manual interpretation is low, which is time-consuming and inefficient

Images