Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Building change detection method based on remote sensing image and twin neural network

A neural network and remote sensing image technology, applied in biological neural network models, neural learning methods, neural architectures, etc., can solve the problems of automation, intelligence and rapidity, and achieve reliable results, strong robustness, efficient and accurate positioning Effect

Pending Publication Date: 2022-03-01
YUNNAN POWER GRID CO LTD ELECTRIC POWER RES INST
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] This application provides a building change detection method based on remote sensing images and twin neural networks to solve the problems of low automation, intelligence and rapidity in the traditional way of detecting changes in ground features

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
  • Building change detection method based on remote sensing image and twin neural network
  • Building change detection method based on remote sensing image and twin neural network
  • Building change detection method based on remote sensing image and twin neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0031] In order to facilitate the description and understanding of the technical solution of the application, the technical solution of the application will be further described below in conjunction with the drawings and embodiments.

[0032] The building change detection method based on remote sensing images and twin neural networks provided in the embodiment of the present application includes the following steps:

[0033] First, the input data preprocessing stage. see figure 1 , is the twin neural network structure diagram provided in the embodiment of this application. The data source is a series of domestic satellites with independent property rights. The data set input into the network contains 5000 pairs of non-urban areas including farmland, forest and desert, which have undergone radiation correction and atmospheric correction. L2 level remote sensing images, the format is png, including three bands of R, G, and B, the size is 1024*1024 pixels, and the resolution is ...

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 relates to the technical field of artificial intelligence image segmentation, target detection and classification, in particular to a building change detection method based on remote sensing images and a twin neural network, and the method comprises the steps: obtaining a data set containing a plurality of pairs of remote sensing images; dividing the data set into a training set, a verification set and a test set, and cutting remote sensing images in the training set, the verification set and the test set; training the clipping training set remote sensing image to obtain a network model weight file; and testing the clipping test set remote sensing image according to the network model weight file to obtain a building change result. The method has the advantages of automation, intellectualization and rapidness, and for two input remote sensing images subjected to radiation correction of front and back time phases, the remote sensing images only need to be input into an algorithm interface for preprocessing and then are transmitted to a network. According to the method, efficient and accurate positioning and end-to-end detection of changing buildings in front and back time phase remote sensing images are realized, operation is simple after deployment, and a building change detection result is reliable.

Description

technical field [0001] This application relates to the technical fields of artificial intelligence image segmentation, target detection and classification, and in particular to a building change detection method based on remote sensing images and twin neural networks. Background technique [0002] Requirements for the construction of the ground object change and classification detection test site: acquisition of multi-temporal image data; reproducible physical surface object changes; change detection and change analysis; standardized output of ground object change true value results. [0003] The ground object change scene analysis unit mainly realizes the function of satellite remote sensing image change detection, which is divided into two parts: change detection and change analysis. The change detection part mainly realizes the detection of the changed area for the input multi-temporal satellite remote sensing image. According to the technical process, it includes necess...

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 Applications(China)
IPC IPC(8): G06T7/00G06T7/11G06K9/62G06V10/774G06V10/764G06V20/13G06V10/40G06V10/80G06V10/82G06N3/04G06N3/08
CPCG06T7/0002G06T7/11G06N3/08G06T2207/10032G06T2207/20081G06T2207/20084G06T2207/20132G06T2207/20221G06N3/045G06F18/241G06F18/253G06F18/214
Inventor 马御棠马仪周仿荣黑颖顿代维菊洪志湖王山刘兴涛曹俊胡锦
Owner YUNNAN POWER GRID CO LTD ELECTRIC POWER RES INST
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com