Remote sensing image change detection method based on fractal attribute and decision fusion

Abstract

The invention discloses a remote sensing image change detection method based on fractal attribute and decision fusion. The method comprises the following steps: acquiring a multi-temporal high-resolution remote sensing image; establishing a target function based on a minimum correlation value between average scales, adaptively determining a scale parameter set of each attribute through iterative computation, and extracting a morphological attribute profile with adaptive scale parameters; constructing a multi-feature decision fusion framework, calculating a change intensity index and an evidence confidence index to describe change information and a corresponding trust degree respectively, and fusing the morphological attribute profile from the adaptive scale parameter and the change information of the original spectrum by using the multi-feature decision fusion framework to obtain a final change detection graph. According to the method, a target function is established based on the correlation between the minimum average scales, a group of scale parameters are adaptively obtained, a multi-feature decision fusion framework is constructed on the basis, and the decision reliability isimproved by reducing the uncertainty of change information of different sources.

Description

technical field [0001] The invention belongs to the field of image processing, and in particular relates to a remote sensing image change detection method. Background technique [0002] With the continuous development of remote sensing systems, Change Detection (CD), as one of the most important applications in the field of remote sensing, has attracted widespread attention. Accurate understanding of land cover change is an important issue in human activities such as dynamic land use, vegetation health, and environmental detection. The widespread use of a new generation of high-resolution sensors such as IKONOS, Quickbird and GF2 further expands the range of applications for CD technology. Compared with medium and low-resolution remote sensing images, high-resolution remote sensing images (High-Resolution Remote Sensing, HRRS) contain more land cover spatial information and thematic information, making it feasible to identify different types of complex structures in the sce...

AI Technical Summary

Problems solved by technology

Even so, most CD methods based on MAPs still have some problems: (1) In order to highlight representative spatial structure information while reducing redundant information in a limited number of attribute profiles (Attribute Profiles, APs), an adaptive Determining a reasonable set of scale parameters

However, the MAPs theory does not give a clear standard, and most of the current scale parameters are manually determined based on experience.

(2) Given the complexity of land cover change in the scenario, when combining the change information and other features of multiple APs, the uncertainties contained in the change information from different sources are rarely considered in existing studies

Images