Remote sensing image thin cloud removal method and system based on full-wave band feature fusion

A feature fusion and remote sensing image technology, applied in neural learning methods, image enhancement, image analysis, etc., can solve the problems of not being able to make full use of the spectral information of multispectral images, the destruction of image texture information, and the strong subjectivity of resampling functions , to achieve the effect of improving thin cloud removal ability, small error, and high precision of thin cloud removal

Active Publication Date: 2022-02-18
NANJING UNIV OF AERONAUTICS & ASTRONAUTICS
View PDF12 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The first method cannot make full use of the spectral information of multispectral images; the artificially designed resampling

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 thin cloud removal method and system based on full-wave band feature fusion
  • Remote sensing image thin cloud removal method and system based on full-wave band feature fusion
  • Remote sensing image thin cloud removal method and system based on full-wave band feature fusion

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0060] Such as figure 1 As shown, the embodiment of the present invention provides a remote sensing image thin cloud removal method based on full-band feature fusion, including:

[0061] Obtain multispectral remote sensing images to be processed;

[0062] Use the trained thin cloud removal network to perform multispectral influence thin cloud removal on the multispectral remote sensing image to be processed, and output the multispectral remote sensing image with thin cloud removed;

[0063] Wherein, the thin cloud removal network completed by the training is obtained through the following steps:

[0064] Obtain multispectral remote sensing images in the same area with and without clouds, preprocess the acquired images, and obtain training sets and test sets;

[0065] Use the pre-built convolutional neural network to sample the acquired image to obtain the spatial and spectral features of the spectral bands of different resolutions of the image;

[0066] Using the pre-built ...

Embodiment 2

[0097] Such as Figure 5 As shown, the embodiment of the present invention provides a remote sensing image thin cloud removal system based on full-band feature fusion, including:

[0098] Acquisition module: used to acquire multispectral remote sensing images to be processed;

[0099] Output module: used to use the trained thin cloud removal network to perform multi-spectral influence thin cloud removal on the multi-spectral remote sensing image to be processed, and output the multi-spectral remote sensing image with thin cloud removed.

[0100] The output module includes a network processing module for training thin clouds to remove the network, and the network processing module includes:

[0101] Preprocessing module: used to obtain multispectral remote sensing images in the same area with and without clouds, and preprocess the obtained images to obtain training sets and test sets;

[0102] Sampling module: used to sample the acquired image by using the pre-built convoluti...

Embodiment 3

[0107] An embodiment of the present invention provides a remote sensing image thin cloud removal device based on full-band feature fusion, including a processor and a storage medium;

[0108] The storage medium is used to store instructions;

[0109] The processor is configured to operate according to the instructions to execute the steps of the method in the first embodiment.

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 remote sensing image thin cloud removal method and system based on full-band feature fusion. The method comprises the following steps: carrying out multispectral influence thin cloud removal on a multispectral remote sensing image to be processed by using a trained thin cloud removal network; wherein the trained thin cloud removal network is obtained through the following steps: obtaining multispectral remote sensing images in the same region under the condition of clouds and no clouds, and obtaining a training set and a test set; sampling to obtain spatial features and spectral features of spectral bands with different resolutions of the image; carrying out feature fusion to respectively obtain feature maps of the images under the cloud condition and the cloud-free condition; calculating multi-path supervision loss, and optimizing network parameters of a preset thin cloud removal network; and training and testing the optimized thin cloud removal network by using the training set and the test set to obtain a trained thin cloud removal network. The method is high in thin cloud removal precision and small in error, compared with the prior art, the removal training is greatly improved, and the method has a wide application space in multispectral remote sensing images.

Description

technical field [0001] The invention relates to a thin cloud removal method and system for remote sensing images based on full-band feature fusion, and belongs to the technical field of thin cloud removal for remote sensing images. Background technique [0002] As more and more remote sensing satellites are launched into space, the massive data acquired by remote sensing satellites provide rich information for vegetation health monitoring, disaster monitoring, and land cover classification. However, thin clouds have always been an important factor affecting the quality of remote sensing images, so thin cloud removal is an essential step in remote sensing image preprocessing. At present, satellite sensors detect more and more spectral bands, and generally have high spatial resolution in the visible near-infrared band, and lower resolution in the short-wave infrared band. [0003] Although the detection accuracy of the current deep learning method is much higher than that of ...

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): G06T5/00G06V10/80G06V10/82G06N3/04G06N3/08
CPCG06T5/003G06N3/08G06T2207/10036G06T2207/20021G06T2207/20081G06T2207/20084G06N3/045G06F18/253
Inventor 李俊盛庆红王博徐炜岚
Owner NANJING UNIV OF AERONAUTICS & ASTRONAUTICS
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