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

Fusion method of panchromatic image and multispectral image based on deep neural network

A deep neural network, multi-spectral image technology, applied in image enhancement, graphic image conversion, image data processing and other directions, can solve the problem of non-linear description of remote sensing image structure information, achieve high spatial resolution, increase expression ability, The effect of preserving spectral information

Active Publication Date: 2018-05-01
NANJING UNIV OF SCI & TECH
View PDF4 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although these methods can reconstruct high-resolution multispectral images well, they only share a shallow linear structure and cannot describe the complex structural information of remote sensing images nonlinearly.

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
  • Fusion method of panchromatic image and multispectral image based on deep neural network
  • Fusion method of panchromatic image and multispectral image based on deep neural network
  • Fusion method of panchromatic image and multispectral image based on deep neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0057] to combine figure 1 , a method for fusion of panchromatic images and multispectral images based on deep neural networks, the specific steps are as follows:

[0058] Step 1. Construct a training set paired with high-resolution and low-resolution image patches The specific process is:

[0059] Step 1.1, multispectral images of known low spatial resolution Perform a band-by-band interpolation operation, zoom in 4 times to get an initially enlarged multispectral image in Contains 4 bands, the pixel size of each band image is 150×150, It also contains 4 bands, and the pixel size of each band image is 600×600;

[0060] Step 1.2, for known high-resolution panchromatic images with a size of 600×600 and the initial upscaled multispectral image The maximum and minimum normalization method is performed on each band pixel, so that their pixel value range is between [0,1]. Among them, the high-resolution panchromatic image Such as Figure 4 As shown in (a), the imag...

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 method for fusing a full-color image and a multispectral image based on a deep neural network. Specific steps are as follows: step 1. constructing a training set of high resolution and low resolution image block pairs; step 2. using an improved sparse denoising self-encoder to learn to train initialization parameters of a first layer in a neural network model; step 3. using the improved sparse denoising self-encoder to perform pretraining of the neural network layer by layer; step 4. performing fine adjustment of parameters of the pretrained deep neural network; and step 5. using the deep neural network to reconstruct a multispectral image of high resolution according to a known multispectral image of low spatial resolution. The method provided by the invention adopts a method of deep learning, and can make full use of a nonlinear neural network to depict complex structural information of a multispectral image, thereby enabling the fused multispectral image to have high spatial resolution, and well keeping spectral information of the multispectral image.

Description

technical field [0001] The invention belongs to the technical field of remote sensing image processing, and in particular relates to a high-resolution panchromatic image and multispectral image fusion method based on a deep neural network. Background technique [0002] Earth observation satellites typically provide two different types of imagery, panchromatic images with high spatial and low spectral resolution and multispectral images with low spatial and high spectral resolution. Currently, it is generally difficult to directly acquire highly spatially and hyperspectral-resolved multispectral images due to the technical limitations of current satellite sensors. Therefore, it is undoubtedly a better choice to obtain high-spatial and hyperspectral-resolved multispectral images through a technology that fuses information from these two different types of images. [0003] The method of multispectral image fusion is to fuse the panchromatic image with high spatial resolution a...

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): G06T5/50G06T3/40G06K9/66
Inventor 黄伟肖亮韦志辉
Owner NANJING UNIV OF SCI & TECH
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