Multi-modal remote sensing image change detection method, model generation method and terminal equipment

A change detection and remote sensing image technology, applied in the field of remote sensing images, can solve the problems of not considering the negative impact of the change detection task and the unsatisfactory change detection results, and achieve the effect of eliminating image domain differences, reliable data, and improving accuracy

Inactive Publication Date: 2021-08-24
自然资源部国土卫星遥感应用中心
View PDF4 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Therefore, this type of processing method does not consider the negative impact of the domain difference between images on the change detection task, resulting in the obtained change detection results are also not ideal.

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
  • Multi-modal remote sensing image change detection method, model generation method and terminal equipment
  • Multi-modal remote sensing image change detection method, model generation method and terminal equipment
  • Multi-modal remote sensing image change detection method, model generation method and terminal equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0054] Please refer to figure 1 , this embodiment proposes a method for generating a multimodal remote sensing image change detection model. The multimodal remote sensing image change detection model includes two domain converters and two change decision makers, which can not only effectively eliminate the It can also realize the change detection between integrated multi-modal cross-domain images.

[0055] Exemplarily, the multi-modal remote sensing image change detection model mainly includes two domain converters, two condition discriminators and two change decision makers, wherein the domain converter and change decision makers of the same image domain are set in series , different image domains are set in parallel to form an integrated structure. The generation method of the multimodal remote sensing image change detection model is described below. Such as figure 1 As shown, the generation method includes:

[0056] Step S110, constructing two domain converters and two ...

Embodiment 2

[0109] Please refer to Figure 5 , this embodiment proposes a method for detecting changes in multimodal remote sensing images, which can be used to detect changes in multimodal remote sensing images in different time phases. Exemplarily, the method includes:

[0110] Step S210, preprocessing the collected two original remote sensing images of different modalities to obtain two preprocessed images.

[0111] Considering that there are often geometric deformations between multiple remote sensing images captured at the same geographical location in different periods, in order to ensure the accuracy of change detection, geometric correction operations, also called image registration, are required before entering change detection. Exemplarily, the preprocessing may include but not limited to geometric correction, calibration and atmospheric correction. After geometrically correcting the most original remote sensing images collected, two preprocessed images that are geometrically ...

Embodiment 3

[0119] Please refer to Image 6 , based on the method of Embodiment 1 above, this embodiment proposes a multi-modal remote sensing image change detection model generation device 100, wherein the multi-modal remote sensing image change detection model includes two domain converters and two conditional discriminators and two change deciders. Exemplarily, the multimodal remote sensing image change detection model generation device 100 includes:

[0120] A domain conversion building block 110, configured to construct the two domain converters and the two conditional discriminators using a cycle consistency confrontation network; wherein the domain converter is used for cross-domain conversion between remote sensing images of different modalities , the condition discriminator is used for condition discrimination when performing the cross-domain conversion.

[0121] An objective function construction module 120, configured to construct a first objective function corresponding to t...

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 embodiment of the invention provides a multi-modal remote sensing image change detection method, a model generation method and terminal equipment. A multi-modal remote sensing image change detection model comprises two domain converters, two condition discriminators and two change decision models. The generation method comprises the following steps: constructing two domain converters and two condition discriminators by utilizing a cyclic consistency adversarial network so as to be used for cross-domain conversion among different modal remote sensing images; utilizing a twin neural network to construct respective change decision models of different image domains so as to perform change detection on two images which are subjected to cross-domain conversion to the same image domain; constructing a first target function corresponding to cross-domain conversion and a second target function corresponding to change detection; and performing model training based on the two objective functions. According to the technical scheme, the parallel multi-network integrated model is constructed by combining the cyclic consistency adversarial network and the twin neural network, so that the image domain difference between the multi-modal remote sensing images can be effectively eliminated,.

Description

technical field [0001] The present application relates to the technical field of remote sensing images, and in particular to a method for detecting changes in multimodal remote sensing images, a method for generating a model, and a terminal device. Background technique [0002] Change detection is the process of determining the change of land cover state based on multiple observations at different times. Real-time and accurate acquisition of land surface change information is of great significance for natural resource management, land spatial planning, and ecological environment protection. As an advanced and mature technical means, remote sensing earth observation has gradually formed a multi-type satellite remote sensing system such as optical, hyperspectral, radar, and laser altimetry. Advantages, it can quickly, macroscopically and dynamically acquire surface images, providing important data support for solving land cover change detection. Most change detection studies ...

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): G06K9/00G06K9/62G06N3/04
CPCG06V20/13G06N3/045G06F18/22G06F18/214
Inventor 刘力荣甘宇航唐新明尤淑撑罗征宇莫凡何芸
Owner 自然资源部国土卫星遥感应用中心
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