Burned area fine extraction method based on remote sensing cloud platform and decision tree
A technology of burning slashes and extraction methods, which is applied in the fields of forest resources, ecological environment, and fire prevention and disaster reduction. It can solve the problems of no decision tree algorithm and insufficient precision, and achieve the effects of saving manpower and material resources, accurate boundaries, and improving work efficiency.
Active Publication Date: 2020-11-06
BEIJING FORESTRY UNIVERSITY
View PDF6 Cites 2 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Although related studies have used methods such as GEE and deep learning to extract burned areas, there is no decision tree algorithm involved in the work of information extraction, and the degree of refinement is still insufficient.
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0040] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.
[0041] It should be pointed out that the following detailed description is exemplary and intended to provide further explanation to the present application. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.
[0042] It should be noted that the terminology used here is only for describing specific implementations, and is not intended to limit the exemplary implementations according to the present application. As used herein, unless the context clearly dictates otherwise, the singular is intended to include the plural, and it should also be understood that when the terms "comprising" and / or "comprising" are used in this specification, they mean There are features, steps, operations, means, components and / or combinatio...
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
Login to View More Abstract
The invention relates to a burned area fine extraction method based on a remote sensing cloud platform and a decision tree. The method includes screening a Landsat5-8 series remote sensing image dataset which covers a research area and accords with a fire time range; acquiring remote sensing images before and after burning; extracting sensitive features, including near-infrared band NIR'reflectance and differential normalized fire index dNBR, of the fire passing area by combining spectral features of the fire passing area and change difference of the NBR of the image before and after fire; calculating a threshold value by utilizing an OTSU algorithm, constructing a decision tree classification model to extract a burned area, exporting the burned area to a local place to count the fire area, verifying the recognition precision and drawing a product. The embodiment is based on a remote sensing cloud platform GEE. The large-scale and long-time-sequence burned area is rapidly extracted through the constructed decision tree classification model, the comprehensive macroscopic characteristics of the satellite remote sensing technology are highlighted, the advantages of high efficiency and rapidness of the cloud platform are brought into play, the defects that time and labor are consumed in the traditional remote sensing technology are overcome, and a new way is provided for extraction, analysis and research work of the forest burned area.
Description
technical field [0001] The invention relates to the fields of ecological environment, forest resources, fire prevention and disaster reduction, and in particular, a method for extracting fire traces based on remote sensing big data and decision trees. Background technique [0002] Forests are the vital material basis for human survival and development, and an indispensable natural resource for economic and social progress and sustainable development. For a long time, forest fires have attracted the attention of countries all over the world because of their characteristics of uncertainty, great harm and difficulty in control. Affected by global climate change and human activities in recent years, although the financial expenditures for fire prevention in various countries in the world have been increasing, the frequency of forest fires and the area burned are still showing an upward trend year by year, and the situation of forest fire prevention is becoming more and more seve...
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
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/62G06K9/00
CPCG06V20/13G06F18/24323Y02A90/10
Inventor 刘炀炀
Owner BEIJING FORESTRY UNIVERSITY