Unlock instant, AI-driven research and patent intelligence for your innovation.

Vector guidance-based method for rapidly extracting a disaster situation of a disaster damaged road on a remote sensing platform

An extraction method and road technology, applied in the field of information science, can solve the problems of backwardness, multi-manual labor, and the lack of timely update of ground feature information, and achieve the effect of reducing time.

Pending Publication Date: 2021-12-17
应急管理部国家减灾中心 +1
View PDF2 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Geographic Information System (GIS) data, topographic map data and other vector geographic data that have been collected and edited manually have the characteristics of high precision and strong reliability, but due to the need for more human labor, they often lag behind remote sensing data in terms of temporal Image, some changed features information has not been updated in time

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
  • Vector guidance-based method for rapidly extracting a disaster situation of a disaster damaged road on a remote sensing platform
  • Vector guidance-based method for rapidly extracting a disaster situation of a disaster damaged road on a remote sensing platform
  • Vector guidance-based method for rapidly extracting a disaster situation of a disaster damaged road on a remote sensing platform

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0066] Embodiment 1 remote sensing image preprocessing

[0067] The method comprises the steps of:

[0068] 1) Use Mean-shift filtering to smooth the image;

[0069] 2) Use KMeans++ clustering and naive Bayesian classification to grayscale the image

[0070] The cluster center of radiation information of two or three road points is obtained by KMeans++ clustering; then, a sufficient number of negative sample points are collected equidistantly and screened out (negative sample points are sample points that have not been classified after equidistant collection) for simple shelling Yessian classification, to obtain binarized classification results;

[0071] 3) Image cropping

[0072] Register vector data (vector database) and high-resolution remote sensing image (classified image), and use the buffer generated by vector data to crop the road from the image.

[0073] The registration of vector data and high-resolution remote sensing images adopts a rough matching method. The p...

Embodiment 2

[0074] Example 2 Extraction of Disaster Damaged Road Vector Information

[0075] The extraction method includes the following steps:

[0076] 1) Utilize the method described in embodiment 1 to carry out preprocessing to remote sensing image;

[0077] 2) the image processed in step 1) is carried out to extract the road centerline;

[0078] Use the Hough transform algorithm to extract the road centerline; the edge extraction method of the Hough transform algorithm uses the Sobel operator, the Prewitt operator, and the Canny operator to conduct experiments respectively;

[0079] 3) Post-processing the segmented image

[0080] The method based on vector geometric analysis connects interrupted roads by calculating the extension direction of each road end point, and removes redundant road segments such as burrs and short branches through buffer analysis (references: Zhu Xiaoling, Wu Qunyong, based on high-resolution remote sensing Research on urban road extraction method from ima...

Embodiment 3

[0083] Embodiment 3 Vector-guided remote sensing platform disaster damaged road rapid extraction method

[0084] The evaluation method includes the following steps:

[0085] 1) utilize the extraction method described in embodiment 2 to obtain the vector data of road;

[0086] 2) Use the SURF algorithm to accurately match the road information and the vector guidance template; the SURF algorithm includes three parts: feature extraction, feature description, and feature matching, including:

[0087] i) the vector data extracted in step 1) is generated as a seed point;

[0088] ii) Face filling with seed points;

[0089] iii) Matching the result obtained in step ii) with the vector guidance template (vector database) to identify the damaged area.

[0090] The generation of seed points should conform to the following basic principles:

[0091] I) There is at least 1 seed point in each undamaged surface;

[0092] II) The number of seed points in a single undamaged surface shoul...

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 discloses a vector guidance-based method for rapidly extracting a disaster situation of a disaster damaged road on a remote sensing platform. Under the guidance of road vector basic data, a Hough transform algorithm is utilized to extract a center line of a road, edge extraction is carried out on preprocessed 0-level or 1-level remote sensing data based on a Canny operator, then road information and a vector template are accurately matched based on an SURF algorithm, road disaster damage information is rapidly identified, and the road disaster damage information is rapidly identified, and the position and scale of the disaster point are accurately extracted. Besides, a core algorithm is supported to be integrated on a remote sensing platform, disaster information extracted from the remote sensing platform is directly downloaded to a decision-making user, the transmission efficiency of effective information is greatly improved due to the small data size, and the high-timeliness requirement from imaging to disaster information extraction to transmission to the user is met; and faster decision support is provided for disaster reduction and relief services.

Description

technical field [0001] The invention belongs to the technical field of information science, and relates to a method for quickly extracting disaster situations of disaster-damaged roads on a remote sensing platform based on vector guidance. Background technique [0002] Disaster assessment is the dynamic and quantitative evaluation and estimation of the position, scope, area, type and other change information of surface natural and human elements after a disaster. It is the basic work for comprehensively understanding the disaster situation, grasping the situation, and formulating strategies. Surface information refers to the current natural or human-induced geographic element information on the earth's surface, such as roads, cultivated land, gardens, woodlands, grasslands, waters, etc. As an important content of disaster information, land surface information is a true reflection of the types and natural attributes of surface objects, and its extraction after disasters is an...

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): G06K9/00G06K9/34G06K9/36G06K9/46G06K9/52G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06N3/045G06F18/22G06F18/23213G06F18/24155
Inventor 王志强柳锦宝麻楠楠张晓冉祝明梁芳
Owner 应急管理部国家减灾中心
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com