Dynamic chain graph model-based earthquake damage remote sensing image segmentation method and system

Abstract

The invention discloses a dynamic chain graph model-based earthquake damage remote sensing image segmentation method and system. The method includes the following steps that: a multi-spectral earthquake damage remote sensing image is segmented initially, so that the initial segmentation regions of the multi-spectral earthquake damage remote sensing image can be obtained; heterogeneities of all the initial segmentation regions are calculated; a chain graph model is constructed according to the heterogeneities of the segmentation regions and the adjacency relations among the segmentation regions, wherein the chain graph model includes a region adjoining graph and a nearest neighbor graph which are linked to each other; and red-black tree-based priority queues are constructed with edge lengths in the nearest neighbor graph adopted as primary keys, the red-black tree-based priority queues are dynamically merged according to rule that priority queues with lowest heterogeneity are merged first, and multi-spectral earthquake damage remote sensing image segmentation results matched with earthquake damage surface features can be obtained. With the method and system adopted, wrong segmentation in complex earthquake damage remote sensing image segmentation can be avoided, the correctness of segmentation can be improved, and the segmentation results can be better matched with the earthquake damage surface features.

Description

technical field [0001] The invention belongs to the technical field of remote sensing image processing, and in particular relates to a method for segmenting earthquake damage remote sensing images based on a dynamic chain graph model and a system thereof. Background technique [0002] Earthquake disasters occur frequently and bring great losses to human beings. In the face of severe earthquake disasters, how to quickly and accurately extract the disaster information is of great significance to provide reliable information support for disaster assessment, earthquake relief, post-disaster reconstruction, etc. [0003] The development of high-resolution earth observation technology provides data guarantee for earthquake disaster monitoring. At present, disaster interpretation based on high-score data is mainly based on visual judgment and manual interpretation, and the degree of automation is not high, resulting in low efficiency and strong subjectivity. Image segmentation is...

AI Technical Summary

Problems solved by technology

[0004] Although the image segmentation method based on region merging has significant advantages over other methods, there are still some shortcomings in the face of remote sensing earthquake damage images with large data volume and high complexity: (1) the algorithm is inefficient; (2) The merging criterion lacks robustness; (3) the order of regional merging is disordered, prone to wrong segmentation, and it is difficult to ensure the minimum overall segmentation error; (4) the boundary positioning error is large, resulting in a mismatch between the segmentation result and the earthquake damage

Images