High-precision flood inundation area monitoring method based on dual-polarized SAR image

Through the multi-scale segmentation and Gaussian hybrid model based on dual-polarized SAR images, combining grayscale values ​​and texture features, the problem of noise and ground objects mixing in SAR image monitoring is solved, and the monitoring accuracy of flooded areas is significantly improved .

CN118968320AActive Publication Date: 2024-11-15OCEAN UNIV OF CHINA

Patent Information

Application Number
CN202411445434.2
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-10-16
Publication Date
2024-11-15
Estimated Expiration
2044-10-16

AI Technical Summary

Technical Problem

The prior art is susceptible to coherent spot noise and mixing of ground objects when monitoring floods using SAR images, resulting in low monitoring accuracy in flooded areas.

Method used

Using a high-precision monitoring method based on dual-polarized SAR images, multi-scale segmentation is performed by generating fake color images, combining digital elevation models for mask processing, and using Gaussian hybrid model and maximum expectation algorithm to select the best image, combining grayscale values and texture features classify uncertain areas to reduce the impact of noise and land mixing.

Benefits of technology

It significantly improves the accuracy of monitoring in flooded areas, makes full use of dual-polarized data, effectively removes coherent spot noise, reduces misjudgment and omissions of ground material mixing, and improves monitoring accuracy.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118968320A_ABST
    Figure CN118968320A_ABST
Patent Text Reader

Abstract

The invention belongs to the technical field of remote sensing image processing, and relates to a high-precision flood inundation area monitoring method based on a dual-polarized SAR (Synthetic Aperture Radar) image. Performing multi-scale segmentation on a false color image generated based on the preprocessed dual-polarization data combination; fitting SAR image histograms under different polarizations by using a Gaussian mixture model, and selecting an optimal SAR image by comparing the sizes of overlapping regions of the Gaussian mixture model; a gray value fuzzy system and a texture feature fuzzy system are combined to classify the optimal SAR images, and water body information is extracted; and comparing SAR water body extraction results before and after flood to obtain a flood inundation area. According to the method, multi-scale segmentation is carried out based on a false color image synthesized by dual polarization, so that the influence of SAR speckle noise is effectively reduced; the optimal SAR image is selected, and the uncertain area is classified by combining the gray value and the texture feature, so that the influence of ground feature mixing is effectively reduced, and the monitoring precision of the flood area is remarkably improved.
Need to check novelty before this filing date? Find Prior Art

Citation Information

Patent Citations

  • Pseudo-color synthesis method and device of images of SAR (synthetic aperture radar) under dual-polarization mode

    CN107507251A

  • Rapid extraction method for outburst flood inundation range

    CN113191292A

  • Method for carrying out pseudo-color processing on gray level image of synthetic aperture radar

    CN113436110A

  • Method for automatically extracting flood risk area based on SAR image

    CN113567981A

  • Rapid detection method for SAR image flood inundation area

    CN114519824A

Cited By

  • Drainage basin scale-oriented flood inundation range full life cycle extraction method

    CN122116188A

  • Basin flood remote sensing monitoring method and device based on high-orbit SAR (Synthetic Aperture Radar) satellite

    CN122239021A

  • Method and device for monitoring flood and waterlogging in a basin based on high-orbit SAR satellite

    CN122239021B