Detection method for changes of high-resolution remote sensing images

Abstract

The invention relates to a detection method for changes of high-resolution remote sensing images. The method comprises the steps of: S1: extracting multi-scale change characteristics of an image; S2: calculating change detection results of a minimum scale by virtue of partial characteristics of the image and a progressive direct-push support vector machine; and S3: making hierarchical refinement for the change detection results of the minimum scale by adopting the strategy of 'Hierarchical refinement from coarse to fine'. In the method, the changeable scale dependence is reflected by comprehensively utilizing the divisibility of the change characteristic under different scales, the scale propagation characteristic of the changes is reflected by adopting the multiscale change detection strategy of 'Hierarchical refinement from coarse to fine', the hierarchy of human eyes in observation of the changes is simulated , and the calculating efficiency and robustness are greatly improved. The method can be widely applied to more application systems for disaster detecting, target monitoring, e-map updating and the like.

Description

Technical field [0001] The invention relates to the technical fields of remote sensing image processing, multi-scale analysis, pattern recognition and machine learning, in particular to a high-resolution remote sensing image change detection method based on scale propagation and progressive direct push support vector machine. Background technique [0002] Remote sensing image change detection automatically detects the changed area by analyzing the registered high-resolution remote sensing images of the same scene in different phases. It can be widely used in military and civilian fields such as target monitoring and disaster monitoring. Remote sensing image change detection is not only driven by strong application requirements, but also has important strategic significance. Due to the importance of change detection technology, remote sensing image change detection technology has been highly valued by countries all over the world. The successful launch of a new generation of high...

AI Technical Summary

Problems solved by technology

[0003] However, due to the complexity of high-resolution remote sensing images, traditional change detection methods cannot be directly applied to change detection in high-resolution remote sensing images.

At present, the research on the change detection method of high-resolution remote sensing images is still very immature, and it is far from meeting the actual needs. The main performance is that the current change detection mostly relies on manual calibration, which is time-consuming and labor-intensive, and has poor versatility and automation.

In fact, only 5-10% of the data has been effectively utilized, and the accuracy of change detection in high-resolution remote sensing images is mostly around 85%. Change detection technology greatly limits the wide application of high-resolution remote sensing images

Images