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

A feature extraction method of watershed underlying surface based on computer vision technology

A computer vision and feature extraction technology, applied in computer parts, computing, instruments, etc., can solve problems such as loss of spatial information, and achieve the effect of avoiding the loss of spatial information and fully and quickly characterizing

Active Publication Date: 2022-07-12
CHINA INST OF WATER RESOURCES & HYDROPOWER RES
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Both of these two types of feature expression methods will bring about the problem of loss of spatial information.

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
  • A feature extraction method of watershed underlying surface based on computer vision technology
  • A feature extraction method of watershed underlying surface based on computer vision technology
  • A feature extraction method of watershed underlying surface based on computer vision technology

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0067] 1) Collection and preprocessing of the underlying surface data of the watershed.

[0068] 1-1 Collect the underlying surface data of the study area, including but not limited to digital elevation data, land use data, soil data, and normalized vegetation index data. The data is in the form of raster data. In theory, the higher the spatial resolution of the raster data, the better. The size of the visible watershed area should be adjusted appropriately. If the spatial resolution is too low, the feature extraction effect will be poor.

[0069] 1-2 Preprocess the digital elevation data. The preprocessing of the digital elevation data is mainly the analysis of the flow direction and slope of the watershed. The D8 algorithm is used for the calculation of the flow direction, and the slope value is expressed by the percentage method;

[0070] 1-3 Preprocess the land use data. The preprocessing of the land use data is mainly to map the land use type to the SCS-CN value to expres...

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 method for extracting underlying surface features of a watershed based on computer vision technology, comprising the following steps: 1) collecting and preprocessing data of the underlying surface of the watershed; 2) converting the underlying surface data into a grayscale image; 3) Color feature extraction based on color aggregation vector; 4) Shape feature extraction based on image moments; 5) Texture feature extraction based on local binary pattern; Different from the previous expression methods of the underlying surface of the watershed using statistical values ​​or characteristic indices and coefficients, the present invention proposes a method for extracting the characteristics of the underlying surface of the watershed by using computer vision technology, which can perform the characteristics of the underlying surface of the watershed in the form of feature vectors. Therefore, it contains more feature information, especially avoids the loss of spatial information in the process of feature extraction, and is a more accurate and fast underlying surface feature extraction and expression method.

Description

technical field [0001] The invention belongs to the technical field of water conservancy engineering, in particular to the technical field of hydrology and geography, in particular to a method for extracting features of underlying surfaces of watersheds based on computer vision technology. Background technique [0002] The condition of the underlying surface of a watershed is one of the decisive factors of its hydrological process. Therefore, the accurate description of the characteristics of the underlying surface of the watershed is an important basis for the study of the drainage and runoff mechanism, the simulation of the hydrological process and the flood forecasting. [0003] At present, there are usually two ways to express the characteristics of the underlying surface of the watershed: one is the statistical value, such as the average elevation of the watershed, the average slope, the average soil depth, the forest coverage rate, etc.; Such as steepness index, terrai...

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 Patents(China)
IPC IPC(8): G06V20/10G06V10/56G06V10/54G06V10/44G06V10/50
CPCY02A10/40
Inventor 王帆张大伟向立云白钰张丹杜晓鹤
Owner CHINA INST OF WATER RESOURCES & HYDROPOWER RES