A water body extraction method based on multi-scale optimization for high-resolution remote sensing images

A remote sensing image, high-resolution technology, applied in neural learning methods, image enhancement, image analysis, etc., can solve problems such as inaccuracy, inability to identify small water bodies and edge areas, and difficulty in capturing image details. The network structure is simple, the extraction effect of small water bodies is good, and the generalization ability is good.

Active Publication Date: 2020-12-01
CHONGQING GEOMATICS & REMOTE SENSING CENT +1
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Due to the limitation of resolution, this method is usually difficult to capture the detailed information of the image, resulting in the inability to identify some small water bodies and inaccurate identification of edge areas.

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 water body extraction method based on multi-scale optimization for high-resolution remote sensing images
  • A water body extraction method based on multi-scale optimization for high-resolution remote sensing images
  • A water body extraction method based on multi-scale optimization for high-resolution remote sensing images

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0042] The specific implementation manner and working principle of the present invention will be further described in detail below in conjunction with the accompanying drawings.

[0043] Such as figure 1 As shown, a water body extraction method based on multi-scale optimization of high-resolution remote sensing images, the specific steps are as follows:

[0044] Step 1: Build the convolutional neural network to be trained based on the existing pre-trained convolutional neural network, such as figure 2 As shown, and use the pre-trained convolutional neural network to extract multi-scale feature maps from the input remote sensing images, and then use the first classifier in the convolutional neural network to be trained to extract the feature map with the lowest resolution from the multi-scale feature map Obtain the initial rough water body segmentation results, including the following sub-steps:

[0045] The specific steps of the multi-scale feature map extraction are:

[0...

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 water bodies from high-resolution remote sensing images based on multi-scale optimization. Obtain the initial rough water body segmentation results in the feature; through the erasure attention method, combine the multi-scale features and the initial segmentation results, output the water body extraction results at full resolution; build a multi-scale loss function to obtain a trained convolutional neural network; Input the high-resolution remote sensing image to be extracted into the trained network to obtain the water body extraction result. The method learns and trains the remote sensing image training data set with real water body annotations, and combines the multi-scale optimization strategy through the guidance of the erasing attention mechanism. Identification and extraction of water bodies.

Description

technical field [0001] The invention relates to the technical field of automatic extraction of remote sensing image information, in particular to a method for extracting water bodies from high-resolution remote sensing images based on multi-scale optimization. Background technique [0002] Water body extraction is a classic problem in the field of automatic extraction of remote sensing image information. Its main goal is to identify and extract water body regions in remote sensing images. The results of water body extraction are widely used in many fields, such as military reconnaissance, environmental protection, cartography and geographic analysis. Therefore, water extraction has important research value. [0003] Most of the traditional water body extraction methods are based on the water body index for water body extraction, which mainly uses the reflectance difference of the water body in different bands to identify the water body. However, these methods often misclas...

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): G06K9/00G06N3/04G06N3/08G06T7/136G06T7/143
CPCG06N3/08G06T7/143G06T7/136G06T2207/10032G06T2207/20016G06T2207/30184G06T2207/20081G06T2207/20084G06V20/13G06N3/045
Inventor 曾安明李朋龙丁忆胡翔云张泽烈胡艳段伦豪张觅李晓龙段松江罗鼎吴凤敏刘金龙刘建黄印陈雪洋钱进魏文杰张黎黄潇莹
Owner CHONGQING GEOMATICS & REMOTE SENSING CENT
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap