Building seismic damage information extraction method and device

A technology of information extraction and building, which is applied in the direction of instruments, character and pattern recognition, computer parts, etc., and can solve the problems of poor accuracy of earthquake damage information extraction

Inactive Publication Date: 2017-12-29
SEISMOLOGICAL BUREAU OF GANSU PROVINCE CHINA EARTHQUAKE ADMINISTRATION
View PDF2 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] In view of this, the object of the present invention is to provide a method and device for extracting building earthquake damage information to solve the problem of poor extraction accuracy of building earthquake damage information in the prior art, and to improve the accuracy of building earthquake damage information. Extraction accuracy

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Building seismic damage information extraction method and device
  • Building seismic damage information extraction method and device
  • Building seismic damage information extraction method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0050] figure 1 A flow chart showing a method for extracting building earthquake damage information provided by an embodiment of the present invention can be applied to earthquake damage assessment in earthquake-stricken areas and can improve the accuracy of building earthquake damage information extraction. The method includes the following steps:

[0051] S101: Acquiring image information in the full-polarization SAR data of the earthquake-damaged area, where the image information includes polarization information and texture information.

[0052] Wherein, the above-mentioned full-polarization synthetic aperture radar data is a single-temporal PolSAR image after an earthquake, which can be acquired by an airborne SAR sensor or a spaceborne SAR sensor, which is not specifically limited in this embodiment of the present invention.

[0053] Considering the method of multi-temporal PolSAR image recognition of earthquake damage information of buildings, it will not only be diffic...

Embodiment 2

[0085] Figure 4 It shows a flow chart of the second method for extracting building earthquake damage information provided by the embodiment of the present invention. Based on the first embodiment, the method includes:

[0086] S401: Acquiring image information in the full-polarization SAR data of the earthquake-damaged area, where the image information includes polarization information and texture information.

[0087] Considering that image information in full-polarization SAR data usually has the defect of speckle noise, based on this, the method for extracting building earthquake damage information provided in this embodiment further includes a preprocessing step S101.

[0088] S402: Preprocessing the image information.

[0089] This step mainly uses the polarimetric SAR image filtering algorithm (such as the refined Lee filtering algorithm) to perform speckle denoising on the above image information, so as to reduce the impact of speckle noise on subsequent results, impr...

Embodiment 3

[0111] Such as Figure 5 As shown, the embodiment of the present invention provides a building earthquake damage information extraction device, including an image acquisition module 10 , a compensation module 20 , a polarization decomposition module 30 , a texture feature extraction module 40 , and a classification extraction module 50 .

[0112] The image acquisition module 10 is used to acquire image information in the full polarization SAR data of the earthquake damaged area, the image information includes polarization information and texture information.

[0113] The compensation module 20 is configured to perform polarization azimuth offset estimation and compensation on the above polarization information to obtain polarization azimuth compensation data.

[0114] The polarization decomposition module 30 is used to perform Yamaguchi polarization decomposition on the above-mentioned polarization azimuth angle compensation data to obtain dihedral scattering dominant features...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention provides a building seismic damage information extraction method and device, which relate to the technical field of information processing and can improve the accuracy of building seismic damage information extracted using SAR data. The building seismic damage information extraction method includes the following steps: acquiring image information in polarimetric SAR data of a seismic damage area, including polarization information and texture information; carrying out polarization azimuth offset estimation and compensation on the polarization information to get polarization azimuth compensation data; carrying out Yamaguchi polarization decomposition on the polarization azimuth compensation data to get a dihedral angle scattering dominant feature and a volume scattering dominant feature, wherein the volume scattering dominant feature is a mixed feature of a collapsed building and an inclined building; extracting texture feature information which can effectively distinguish between a collapsed building and an inclined building from the texture information; and fusing the texture feature information through a multi-feature fusion method based on accuracy weighting, and classifying the volume scattering dominant feature to get a collapsed building and an inclined building.

Description

technical field [0001] The invention relates to the technical field of information acquisition and processing, in particular to a method and device for extracting building earthquake damage information. Background technique [0002] Earthquake is one of the most destructive and harmful natural disasters. After a destructive earthquake, it often causes heavy casualties and huge economic losses. my country is located between the circum-Pacific seismic belt and the Himalaya-Mediterranean seismic belt, which makes my country one of the countries most seriously affected by earthquakes in the world. [0003] The automatic interpretation of remote sensing images can give the most comprehensive and accurate earthquake damage distribution in the shortest time after the earthquake, and provide relevant government departments with reliable decision-making basis in time, which is an incomparable advantage of on-site investigation. In the field of remote sensing research, optical remote...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/00G06K9/62
CPCG06V20/176G06F18/253G06F18/24
Inventor 翟玮
Owner SEISMOLOGICAL BUREAU OF GANSU PROVINCE CHINA EARTHQUAKE ADMINISTRATION
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap