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

Method and system for extracting water bodies from remote sensing images based on collaborative training and semi-supervised learning

A semi-supervised learning and remote sensing image technology, applied in the direction of instruments, calculations, character and pattern recognition, etc., can solve the problems of poor water body extraction accuracy and insufficient number of samples, and achieve the effect of reducing workload and complexity and ensuring accuracy

Active Publication Date: 2018-09-21
SICHUAN AEROSPACE SYST ENG INST
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0008] The purpose of the present invention is to provide a remote sensing image water body extraction method based on collaborative training and semi-supervised learning to solve the problem of poor water body extraction accuracy due to insufficient number of manually selected samples when using supervised classification methods to extract water bodies from remote sensing images

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
  • Method and system for extracting water bodies from remote sensing images based on collaborative training and semi-supervised learning
  • Method and system for extracting water bodies from remote sensing images based on collaborative training and semi-supervised learning
  • Method and system for extracting water bodies from remote sensing images based on collaborative training and semi-supervised learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0053] figure 1 A structural block diagram of a remote sensing image water body extraction system based on collaborative training semi-supervised learning provided in Embodiment 1 of the present invention. Such as figure 1 As shown, the system includes a remote sensing image feature extraction module, a dual-view building module, a classifier training module, and a classification module. The classifier training module includes an initialization module, a sample labeling module, a sample set updating module, and an iterative control module.

[0054] The remote sensing image feature extraction module is configured to extract the spectral features and texture features of the remote sensing image, the spectral features include each band data X of the remote sensing image, the water body index NDWI and the vegetation index NDVI, and the texture features include at least the angle 2 of the gray level co-occurrence matrix of the remote sensing image The order moment ASM, the homogen...

Embodiment 2

[0067] figure 2 It is a flow chart of the method for extracting water bodies from remote sensing images based on collaborative training and semi-supervised learning provided by Embodiment 2 of the present invention. Such as figure 2 As shown, the method includes step S1 to step S7, and the above steps will be described in detail below.

[0068] Step S1: Remote sensing image feature extraction.

[0069] In step S1, the spectral features and texture features of the remote sensing image are extracted. The spectral features include the data X of each band of the remote sensing image, the water body index NDWI and the vegetation index NDVI. The uniformity HOM of the gray level co-occurrence matrix, the entropy ENT of the gray level co-occurrence matrix and the fractal dimension FD of the fractal texture model of the remote sensing image, where X=[B 1 ,B 2 ,...,B n ] T , n is the number of bands, B i is the gray value of the band i image, 1≤i≤n. water body index Among th...

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 present invention relates to the technical field of water body remote sensing, and provides a remote sensing image water body extraction method and system based on collaborative training and semi-supervised learning to solve the problem of water body extraction due to insufficient number of manually selected samples when using supervised classification methods for remote sensing image water body extraction. For the problem of poor accuracy, the system includes a remote sensing image feature extraction module, a dual-view building module, a classifier training module and a classification module. The classifier training module includes an initialization module, a sample labeling module, a sample set update module and an iterative control module. The technical solution proposed by the present invention can still ensure the accuracy of water body extraction from high-resolution remote sensing images even in the case of small samples, thereby reducing the workload and complexity of manually labeling training samples.

Description

technical field [0001] The invention relates to the technical field of water body remote sensing, in particular to a remote sensing image water body extraction method and system based on collaborative training and semi-supervised learning. Background technique [0002] Traditional remote sensing image water extraction methods include water index method, spectral relationship method, and image classification method is often used when the spatial resolution of the image is high and the number of bands is small. At present, supervised classification methods are mostly used in the research on water body extraction from remote sensing images, such as maximum likelihood method, support vector machine, neural network method, etc. The basic steps for water body extraction using these methods are: [0003] (1) Extract the features of each pixel of the image (mainly spectral features and texture features) to form a feature vector; [0004] (2) Select some training samples (marked as ...

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): G06K9/62
CPCG06F18/24
Inventor 韩宇韬吕琪菲周保琢谷永艳张至怡杨宇彬宋勇
Owner SICHUAN AEROSPACE SYST ENG INST