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

Hyperspectral image super-resolution reconstruction method based on sparse representation and image fusion

A hyperspectral image, sparse representation technology, applied in image data processing, graphic image conversion, instruments, etc., can solve the problem of difficulty in maintaining accurate spectral information, inability to obtain prior information, and limited spatial resolution improvement in output images. , to achieve the effect of restoring fine-grained texture and coarse-grained structure, improving computing efficiency, and improving fine-grained texture and coarse-grained structure

Active Publication Date: 2020-02-28
INNOVATION ACAD FOR MICROSATELLITES OF CAS +1
View PDF9 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Commonly used image fusion methods are susceptible to spectral distortion, making it difficult to maintain accurate spectral information in the output image
The single image super-resolution method has limited improvement in spatial resolution due to the inability to obtain sufficient prior information
[0004] In recent years, some studies have proposed some deep learning-based methods for generating high-resolution hyperspectral images. These methods mainly use additional training data to learn the end-to-end relationship between low-spatial-resolution images and high-spatial-resolution images. mapping, since the mapping function is not the same for images acquired with different sensors, these methods can lead to severe spectral distortion

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
  • Hyperspectral image super-resolution reconstruction method based on sparse representation and image fusion
  • Hyperspectral image super-resolution reconstruction method based on sparse representation and image fusion
  • Hyperspectral image super-resolution reconstruction method based on sparse representation and image fusion

Examples

Experimental program
Comparison scheme
Effect test

Embodiment approach

[0055] Select the hyperspectral images in the CAVE dataset and the Harvard dataset as the implementation objects:

[0056] First, for the Harvard dataset, the image with a size of 1024×1024 in the upper left corner is taken as the image to be processed, and the CAVE dataset remains unchanged. Use these two processed datasets as high-resolution reference images, such as Figure 3a and Figure 4 As shown in the second column of images, it is used to compare the reconstruction results;

[0057] Next, the input low-resolution image is obtained through Gaussian blur and downsampling. The size of the Gaussian blur kernel is 5×5, and the downsampling factor in the row and column direction is 2. The low-resolution hyperspectral image is as follows: Figure 3b and Figure 4 as shown in the first column of images;

[0058] Next, in the approximate Heaviside sparse representation method, θ t 16 angles are selected for equidistant sampling on [0,2π], c obtains 12 values ​​from equidi...

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 hyperspectral image super-resolution reconstruction method based on sparse representation and image fusion. The method comprises the following steps: completing super-resolution reconstruction of a single picture by adopting an approximated Heaviside function sparse representation method, and then further fusing a multispectral image with a hyperspectral image obtained inthe previous step by adopting a local mixed image fusion method to enhance the resolution of the image in consideration of the fact that enough prior information cannot be obtained by only using a low-resolution image.

Description

technical field [0001] The invention relates to the technical field of hyperspectral imaging, in particular to a hyperspectral image super-resolution reconstruction method. Background technique [0002] Due to the different spectral absorption of different physical materials, the image will reflect a certain defect more significantly in a certain wavelength band, so hyperspectral images can more accurately distinguish visually similar objects. This feature helps improve the performance of many computer vision tasks, including military surveillance, object detection, and more. However, limited by factors such as imaging sensing technology and signal-to-noise ratio, it is difficult for optical systems to obtain images with both high spectral resolution and high spatial resolution. [0003] In order to enhance the spatial resolution of hyperspectral images and further improve the application range of hyperspectral imaging, image fusion methods or single image super-resolution ...

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): G06T3/40
CPCG06T3/4053Y02A40/10
Inventor 张文秀朱振才张永合王新宇卞均益
Owner INNOVATION ACAD FOR MICROSATELLITES OF CAS
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