Method and system for detecting interannual change of land cover

Abstract

An embodiment of the present invention provides a method and system for detecting interannual changes in land cover, which can determine whether the target area is in the first target year and the second target year through time-series remote sensing data of the target area in the first target year and the second target year NDVI time-series data; on the basis of the preset remote sensing time-series model to reconstruct the NDVI time-series data of two different years, use the DTW algorithm to compare the similarity of the time-series curves of two different years, and obtain the interannual change detection of land cover result. In the embodiments of the present invention, the available value of time-series remote sensing data is fully exploited, and has great application prospects in the aspect of using remote sensing time-series image change detection. Moreover, the DTW algorithm can overcome the displacement problem on the time axis to a certain extent, reduce the influence of outliers such as noise and clouds, achieve better matching results, and improve the detection accuracy of interannual changes in land cover.

Description

technical field [0001] Embodiments of the present invention relate to the technical field of remote sensing image change detection, and more specifically, to a method and system for detecting interannual changes in land cover. Background technique [0002] Land cover change is a comprehensive response of many elements on the surface, which has a direct impact on surface energy balance, climate change, water cycle, etc., and is the focus of many disciplines. Remote sensing data is an important data source for land cover change identification because of its macroscopicity, periodicity and continuity. Time-series remote sensing images can provide a long-term record of the land surface state, reflect the dynamic changes of the land surface in a long-term range, and provide a reliable data source for the spatio-temporal identification of land cover changes. It is one of the research hotspots in the field of remote sensing technology to fully exploit the temporal dimension inform...

AI Technical Summary

Problems solved by technology

The time series similarity calculation method generally adopts the Euclidean distance method. The Euclidean distance calculates the real distance between two points at the same time. In different years, the time-series curve of ground objects will expand and shift on the time axis, so the Euclidean distance method cannot overcome the displacement problem of the time-series curve on the time axis

Images