High resolution optical remote sensing image post-disaster water body information extracting method and system

Abstract

The invention relates to a high resolution optical remote sensing image post-disaster water body information extracting method and system. The method comprises the steps that a post-disaster water body region is selected as a target post-disaster water body research region; the high-resolution optical remote sensing image is acquired; radiation calibration, atmospheric correction, geometric correction and noise removing are carried out on the acquired remote sensing image to acquire a preprocessed image; the preprocessed image is enhanced based on a generalized fuzzy operator method to acquire the enhanced image of the target post-disaster water body research region; an object-oriented method is used to segment the enhanced image; a method based on spectral information is used to carry out coarse extracting on water body information in the segmented image to acquire coarse-extracted post-disaster water body information; according to a water body information extraction feature knowledge judgment method, refined extracting is carried out on the coarse-extracted post-disaster water body information to acquire refined-extracted post-disaster water body information; and a regional mark method is used to carry out hole filling on the water body region to acquire final post-disaster water body information.

Description

technical field [0001] The invention relates to the field of remote sensing image processing, in particular to a method and system for extracting post-disaster water body information from high-resolution optical remote sensing images. Background technique [0002] Water is an important resource for the survival of the earth's organisms. In the natural environment, water, as an independent factor, has attracted people's attention. Water body information extraction is of great significance for investigating global water resources, predicting flood disasters, and evaluating environmental impacts, as well as reference information for moving or non-moving targets such as bridges, docks, and ships. Remote sensing technology has become an important means of obtaining information on the earth's surface due to its wide detection range, large amount of information, and fast update time, especially the launch of high-resolution remote sensing satellites, and resource investigation and ...

AI Technical Summary

Problems solved by technology

[0004] The single-band threshold method has the characteristics of simple model and high calculation efficiency, but it is easily affected by factors such as shadows, water quality changes, waves, and depths; the multi-band spectral relationship method can effectively remove the influence of shadows, and is especially suitable for the extraction of water bodies in mountainous areas , but there is no formula for the spectral feature model constructed by this method. The spectral feature model is related to the study area and the time phase of remote sensing images; the water body index method has outstanding advantages in suppressing vegetation, shadows, soil and other information, but its key is to always maintain Once this relationship is weakened, the recognition result of this method will be poor or even invalid; the decision tree method uses other knowledge except the brightness value, and the recognition result is more accurate, but the decision-making process The formulation of abstract or decision rules is more complicated

[0005] Considering the rich spatial structure of high-resolution optical images, which leads to the poor effect of conventional post-disaster water body information extraction methods, exploring a post-disaster water body information extraction method that can improve the accuracy of water body information extraction from optical remote sensing images has become another in the field of remote sensing image processing. challenge

Images