A high-quality reconstruction method of a spectral imaging system based on a convolutional neural network

A convolutional neural network and spectral imaging technology, which is applied in the field of high-quality reconstruction of hyperspectral images and rapid acquisition of high-quality hyperspectral images, can solve the problems of low quality of reconstructed images, and the imaging process is not considered, so as to improve efficiency, The effect of extending the scope of application

Inactive Publication Date: 2019-05-10
BEIJING INSTITUTE OF TECHNOLOGYGY
View PDF7 Cites 12 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] For existing algorithms, the imaging process is not considered, and the quality of the reconstructed image is low.

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
  • A high-quality reconstruction method of a spectral imaging system based on a convolutional neural network
  • A high-quality reconstruction method of a spectral imaging system based on a convolutional neural network
  • A high-quality reconstruction method of a spectral imaging system based on a convolutional neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0065] A high-quality reconstruction method for a spectral imaging system based on a convolutional neural network disclosed in this embodiment is applied to a coded aperture snapshot spectral imaging system, namely the CASSI system, which was first proposed by Ashwin Wagadarikar et al. (see Wagadarikar A, John R, Willett R, Brady D.Single disperser design for codedaperture snapshot spectral imaging[J].Applied optics.2008,47(10):B44-B51.). The CASSI system modulates the 3D hyperspectral image by using a binarized coded aperture and a dispersive medium, and uses a detector to obtain a 2D compressed image of the 3D hyperspectral data. An optimization algorithm is then used to reconstruct the underlying 3D hyperspectral image from the 2D image.

[0066] Such as figure 1 As shown, a high-quality reconstruction method for a spectral imaging system based on a convolutional neural network disclosed in this embodiment includes the following steps:

[0067] The spectral imager describ...

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 high-quality reconstruction method of a spectral imaging system based on a convolutional neural network, and belongs to the field of computational photography. The method isapplied to a snapshot spectral imaging system based on a coded aperture, spatial correlation and spectral correlation between images are considered in the reconstruction process of a hyperspectral image, residual error learning is used for accelerating the training speed and the convergence rate of a network, and a GPU is used for completing optimization solving of the whole network. Network parameters are updated by using a random gradient descent method; and block-by-block processing is performed to complete reconstruction of the hyperspectral image. According to the method, hyperspectral image reconstruction of the CASSI spectral imaging system can be completed in a high-quality mode, it is guaranteed that a reconstruction result has high spatial resolution and high spectral fidelity, meanwhile, the efficiency of hyperspectral image reconstruction is greatly improved, and the application range of hyperspectral images is expanded. The method can be applied to the fields of geologicalexploration, agricultural production, biomedicine and the like.

Description

technical field [0001] The patent of the present invention relates to a high-quality hyperspectral image reconstruction method for spectral imaging, in particular to a method capable of quickly acquiring high-quality hyperspectral images, which belongs to the field of computational photography. Background technique [0002] Hyperspectral imaging technology is a combination of spatial imaging technology and spectral imaging technology, which can intensively collect the spectral signal of each point in the scene. The data cube collected by this technology is a hyperspectral image, which contains two-dimensional spatial information and one-dimensional spectral information of the target scene. This technology has been applied in many fields such as geological exploration, agricultural production and biomedicine. Due to the limitations of existing two-dimensional imaging sensors, it is not possible to obtain a three-dimensional hyperspectral image simply by one exposure. The tr...

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): G06T9/00
Inventor 王立志张涛付莹黄华
Owner BEIJING INSTITUTE OF TECHNOLOGYGY
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