Remote sensing image space-time fusion method, intelligent terminal and computer readable storage medium

Abstract

The invention discloses a remote sensing image space-time fusion method, an intelligent terminal and a computer readable storage medium. The method comprises the following steps: acquiring a high-resolution image and a first low-resolution image of a first time phase and a second low-resolution image of a second time phase; calculating a pixel reliability coefficient according to the high-resolution image, the first low-resolution image and the second low-resolution image; classifying pixels in the high-resolution image by using a fuzzy C-means clustering method, and screening out various pixels according to the reliability coefficient of the pixels to participate in global unmixing so as to obtain an initial fusion image of the high-resolution image, the first low-resolution image and the second low-resolution image; correcting gross errors in the initial fusion image based on a self-adaptive local unmixing model to obtain an intermediate fusion image; and performing spatial filtering and residual distribution on the intermediate fusion image to obtain a final fusion image. The influence of different-source image differences on space-time fusion is comprehensively considered, and a better space-time fusion result is obtained.

Description

technical field [0001] The present invention relates to the field of remote sensing, in particular to a method for spatial-temporal fusion of remote sensing images, an intelligent terminal and a computer-readable storage medium. Background technique [0002] Limited by sensor technology, funds, and the impact of other factors such as clouds on surface observations, it is very difficult to achieve continuous high-spatial-resolution surface observations using a single remote sensing data, and time-space fusion technology can achieve high-spatial resolution but long return visits. Periodic satellite images are fused with fast-return but low-spatial-resolution satellite images to obtain high-spatial-spatial resolution images, which also makes spatio-temporal fusion technology widely used in phenology analysis, disaster monitoring, urbanization analysis and other fields. [0003] Although the method of spatio-temporal fusion has developed rapidly in recent years, due to the diffe...

AI Technical Summary

Problems solved by technology

[0003]Although the method of space-time fusion has developed rapidly in recent years, due to the registration of image pairs between the fused images, the performance of heterogeneous sensors, observation angles, Due to differences in heterogeneous images such as width and time, the results of spatio-temporal fusion are not accurate. In order to overcome the images caused by these differences, the existing technology uses linear regression methods or fuses the difference information of two temporal phases to weaken these images. However, it can only reduce the impact of systematic errors to a certain extent, and is ineffective for registration errors. Therefore, an effective new strategy is urgently needed to reduce the impact of various heterogeneous image differences on spatio-temporal fusion.

Images