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

Remote sensing image space spectrum fusion method of deep recursive residual network, and electronic equipment

A technology of remote sensing image and fusion method, which is applied in the field of remote sensing image fusion, can solve problems such as difficulty in learning to deep layers, and achieve the effect of solving the problem of gradient disappearance and gradient explosion, good image fusion effect, and improved accuracy

Active Publication Date: 2020-06-30
INST OF REMOTE SENSING & DIGITAL EARTH CHINESE ACADEMY OF SCI
View PDF6 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The present invention aims to provide a remote sensing image space-spectrum fusion method and electronic equipment with a deep recursive residual network to solve the problem of improving the spectral distortion in the traditional image fusion method. The network of the existing deep learning fusion method is relatively simple and difficult to learn deep layers. The technical problem of the characteristics, the above-mentioned method provided by the present invention is applicable to the space-spectrum fusion of panchromatic images and multispectral images, and has better fusion effect

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
  • Remote sensing image space spectrum fusion method of deep recursive residual network, and electronic equipment
  • Remote sensing image space spectrum fusion method of deep recursive residual network, and electronic equipment
  • Remote sensing image space spectrum fusion method of deep recursive residual network, and electronic equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0055] This embodiment provides a space-spectrum fusion method for remote sensing images with a deep recursive residual network, such as figure 1 shown, including the following steps:

[0056] (a) Generating a data set: acquiring multiple original remote sensing images and processing the multiple original remote sensing images to obtain a plurality of corresponding low-resolution image blocks and original multispectral image blocks, wherein each remote sensing image includes Multispectral images and panchromatic images;

[0057] (b) Construct a deep recursive residual network model, including:

[0058] (b1) The identity branch in the residual network learning model uses global residual learning; a recursive block including a plurality of local residual units is constructed in the residual branch of the residual network model to obtain a recursive residual learning branch.

[0059] (b2) The global residuals used by the identity branch and the local residuals contained in the ...

Embodiment 2

[0119] This embodiment provides a computer-readable storage medium, in which a computer program is stored, and the computer program is executed by a computer to realize the remote sensing image of the deep recursive residual network described in any one of the technical solutions in Embodiment 1 Spatial Spectral Fusion Method.

Embodiment 3

[0121] This embodiment provides an electronic device, such as Figure 9 As shown, at least one processor 901 and at least one memory 902 are included, at least one memory 902 stores instruction information, and at least one processor 901 can execute any solution in Embodiment 1 after reading the program instructions The space-spectrum fusion method of remote sensing images with the described deep recursive residual network.

[0122] The foregoing device may further include: an input device 903 and an output device 904 . The processor 901, the memory 902, the input device 903 and the output device 904 may be connected via a bus or in other ways. The above-mentioned products can execute the method provided by the embodiment of the present application, and have corresponding functional modules and beneficial effects for executing the method. For technical details not described in detail in this embodiment, refer to the method provided in Embodiment 1 of the present application....

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 provides a remote sensing image space spectrum fusion method of a deep recursive residual network, and electronic equipment. The method comprises the following steps: (a) processing a plurality of original remote sensing images to generate a data set; (b) constructing a deep recursive residual network model; (c) training the deep recursive residual network model obtained in the step(b) by utilizing the data set obtained in the step (a) to obtain a trained deep recursive residual network model; (d) fusing remote sensing images to be fused by using the trained deep recursive residual network model to obtain a fused image. According to the method, the advantages of the residual network and the recursive network can be utilized, rich image features of the deep-level network arelearned through end-to-end network design, the spectral information of the original low-resolution multispectral image is reserved as much as possible while the spatial resolution is improved, and thespectral distortion phenomenon existing in a traditional method is well improved.

Description

technical field [0001] The invention relates to the field of remote sensing image fusion, in particular to a remote sensing image space-spectrum fusion method and electronic equipment of a deep recursive residual network. Background technique [0002] In the field of remote sensing, with the development of imaging system and satellite technology, more and more satellites are launched, and more and more satellite image data are obtained. In order to more comprehensively analyze the images collected by satellites, it is necessary to apply remote sensing image fusion technology. Currently common optical satellites usually provide two types of remote sensing images: multispectral image (Multispectral Image, MS) with rich spectral information but low spatial resolution, and panchromatic image (Panchromatic Image, MS) with rich spatial details but only grayscale information. PAN). [0003] At present, traditional image fusion methods have obtained rich research results, mainly i...

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
IPC IPC(8): G06K9/00G06K9/62G06N3/08G06N3/04
CPCG06N3/084G06V20/13G06N3/045G06F18/25G06F18/214Y02A40/10
Inventor 郭擎王芬葛小青李安张洪群韦宏卫
Owner INST OF REMOTE SENSING & DIGITAL EARTH CHINESE ACADEMY OF SCI
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