Intelligent extraction method of water body in global scale remote sensing images based on multi-index
A technology of remote sensing image and extraction method, which is applied in image analysis, image enhancement, image data processing, etc., and can solve problems such as inaccuracy and misclassification of results
Inactive Publication Date: 2021-09-14
INST OF REMOTE SENSING & DIGITAL EARTH CHINESE ACADEMY OF SCI
View PDF3 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
However, for global-scale land surface water mapping, the current sample library can only refer to existing land surface water products
However, water bodies are greatly affected by seasons, that is to say, compared with water bodies in different time phases, the samples are inaccurate to a certain extent, which easily leads to misclassification of results
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
[0013] The present invention is described in further detail below in conjunction with accompanying drawing:
[0014] The present invention is based on the multi-index Landsat remote sensing image land surface water body rapid extraction method, comprising the following steps:
[0015] (1) Data processing
[0016] The present invention needs to carry out radiometric calibration on the adopted satellite remote sensing image data to obtain the reflectance on the satellite. The DEM data adopts SRTM 30m Dem data, which is longitude-latitude projection and WGS84 coordinate system. In order to adapt to the extraction of global land surface water body information, the global 30m Dem data can be mosaiced into the result of vrt format first, and then transprojected and cropped corresponding to the range of each satellite remote sensing data. Using the existing 2000 Landsat water product (GLCF-GIW) as a sample library, training and learning are carried out, so as to realize the adaptiv...
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 discloses a multi-index-based global scale remote sensing image water body intelligent extraction method. The technical field of the invention is the direction of remote sensing image information mining, and particularly relates to the rapid extraction of water bodies from Landsat remote sensing images. The invention comprehensively adopts the terrain index and the normalized index of water body, vegetation, buildings, etc., and solves the problem of confusion between water body and mountain shadow, urban area, cloud shadow, ice and snow and other ground objects encountered in the process of extracting water body information from satellite remote sensing images. And the use of the exponential method greatly simplifies the complexity of the calculation and can effectively improve the calculation speed of the algorithm. At the same time, using prior knowledge, the decision tree method is used to establish a rule model, and the threshold is determined adaptively. It has strong universality and can be well applied to the extraction of water body information in global regions. The invention can quickly, accurately and intelligently produce global land surface water products, and can be used for research on water resources monitoring, global changes and the like.
Description
technical field [0001] The technical field of the present invention is the mining of remote sensing image information, and specifically relates to the rapid and intelligent extraction of remote sensing image water bodies on a global scale. Background technique [0002] Water resources are an irreplaceable strategic resource for human survival and social development, and an indispensable and important basic information for global resource security and management, climate change research, and dynamic monitoring of the ecological environment. How to establish an effective method to scientifically, accurately and quickly extract the information of global land surface water bodies, and timely grasp the change information of land surface water bodies has become a key issue in the research of global changes such as water cycle. Because remote sensing technology has the characteristics of large-area synchronous observation, timeliness, comprehensiveness and comparability of data, 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
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06K9/62G06T7/11
CPCG06T7/11G06T2207/20132G06F18/24G06F18/214
Inventor 彭燕何国金江威刘慧婵
Owner INST OF REMOTE SENSING & DIGITAL EARTH CHINESE ACADEMY OF SCI