Remote sensing image change detection method based on chi-square transformation and sample selection

Abstract

The invention discloses a remote sensing image change detection method based on chi-square transformation and sample selection. Multi-scale segmentation is performed on a multi-temporal remote sensing image so as to obtain image spots; the multi-dimensional features of the image spots are extracted, and the weighted difference degree of the image spots is calculated by adopting a feature fusion method based on chi-square transformation; and training samples are self-adaptively selected, a change threshold is obtained through a Bayes threshold determination method based on an expectation maximization algorithm, and binary segmentation is performed on the weighted difference image so as to obtain a change detection result. The correct rate of change detection is ensured to be high and leak detection is also effectively reduced so that the better change detection result is obtained. The remote sensing image change detection method has great application value in monitoring of the surface coverage change.

Description

technical field [0001] The invention belongs to the field of remote sensing science and technology, and relates to a remote sensing image change detection method, in particular to an object-oriented remote sensing image change detection method based on chi-square transformation and sample selection. Background technique [0002] Due to the increasing application of high-resolution remote sensing images, object-level change detection, which can take advantage of its advantages, has gradually replaced pixel-level change detection and become the mainstream change detection technology. The object is a homogeneous collection of pixels, which can also be called an image spot. The image spot contains multi-dimensional features, and the change detection method based on the difference method or the ratio method uses a single feature for change detection, which cannot fully express the information of the image spot. Although the change detection based on the ChangeVectorAnalysis (CVA...

AI Technical Summary

Problems solved by technology

However, geographical national conditions monitoring covers a large geographical area and requires the use of large-format remote sensing images. When the time interval between the two time-phase remote sensing images is short, the ratio of the area of ​​the changed area to the unchanged area in the detection area is very small.

Directly using the Bayesian threshold determination method based on the EM algorithm cannot obtain accurate change thresholds

Images