Terahertz image information interpretation method, network and storage medium

An image information and terahertz technology, applied in the field of image processing, can solve the problems of loss of detail information, high recognition rate, coherent speckle noise interference, etc., achieve efficient information interpretation, overcome low resolution, and reduce computing costs

Active Publication Date: 2019-05-10
GUANGDONG UNIV OF TECH
View PDF7 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

For a long time, low-resolution terahertz images have poor imaging clarity and contrast, unclear edge outlines, and coherent speckle noise interference, which has become one of the main factors hindering the application of terahertz images.
[0003] Combining image p

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
  • Terahertz image information interpretation method, network and storage medium
  • Terahertz image information interpretation method, network and storage medium
  • Terahertz image information interpretation method, network and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0069] Embodiment 1 provides a method for interpreting terahertz image information, please refer to figure 1 , which includes the following steps:

[0070] S1. Perform super-resolution reconstruction on the acquired low-resolution terahertz image to obtain a super-resolution terahertz image;

[0071] S2. Use at least one convolutional layer to extract features from low-resolution terahertz images to obtain low-resolution feature maps; use at least one convolutional layer to perform feature extraction on super-resolution terahertz images to obtain super-resolution features picture;

[0072] S3. Perform feature-level image fusion of the low-resolution feature map and the super-resolution feature map to obtain a feature fusion map;

[0073] S4. Perform region proposal on the feature fusion map to obtain candidate regions; perform region pooling on candidate regions to obtain region pooling results;

[0074] S5. Perform target detection and / or semantic segmentation on the regio...

Embodiment 2

[0119] This embodiment provides a terahertz image information interpretation network for implementing the terahertz image information interpretation method in Embodiment 1, specifically including:

[0120] The super-resolution reconstruction sub-network 11 is used to perform super-resolution reconstruction on the acquired low-resolution terahertz images;

[0121] The feature extraction sub-network 12 is used to extract features from low-resolution terahertz images by using at least one convolutional layer to obtain low-resolution feature maps, and to extract features from super-resolution terahertz images by using at least one convolutional layer , to obtain the super-resolution feature map;

[0122] The feature fusion sub-network 13 is used to perform feature-level image fusion of the low-resolution feature map and the super-resolution feature map to obtain a feature fusion map;

[0123] The region proposal sub-network 14 is used to perform region proposals on the feature fu...

Embodiment 3

[0168] An embodiment of the present invention provides a storage medium containing computer-executable instructions, and the computer-executable instructions are used to execute the method for interpreting terahertz image information according to Embodiment 1 of the present invention when executed by a computer processor.

[0169] The computer storage medium in the embodiments of the present invention may use any combination of one or more computer-readable media. The computer readable medium may be a computer readable signal medium or a computer readable storage medium. A computer readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples (non-exhaustive list) of computer readable storage media include: electrical connections with one or more leads, portable computer disks, hard disks, random access memory (RAM), ...

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 terahertz image information interpretation method, a network and a storage medium. The method comprises the following steps: obtaining a low-resolution terahertz image; carrying out super-resolution reconstruction on the obtained low-resolution terahertz image to obtain a super-resolution terahertz image; performing feature extraction on the low-resolution terahertz imageby using at least one convolution layer to obtain a low-resolution feature map; performing feature extraction on the super-resolution terahertz image by using at least one convolution layer to obtaina super-resolution feature map; carrying out feature level image fusion on the low-resolution feature map and the super-resolution feature map to obtain a feature fusion map; carrying out region proposal on the feature fusion image to obtain a candidate region; carrying out region pooling on the candidate region to obtain a region pooling result; and carrying out target detection and/or semanticsegmentation on the regional pooling result to complete information interpretation of the terahertz image. According to the invention, the information interpretation of the terahertz image can be completed with high efficiency and high quality.

Description

technical field [0001] The invention relates to the field of image processing, in particular to a method for interpreting terahertz image information, a network and a storage medium. Background technique [0002] Terahertz technology can carry out non-contact automatic identification of hidden dangerous objects, and can solve the technical problems of safety detection in public environments. For a long time, the poor imaging clarity and contrast of low-resolution terahertz images, unclear edge contours, and coherent speckle noise interference have become one of the main factors hindering the application of terahertz images. [0003] Combining image processing technology with terahertz imaging principles, terahertz images can be recognized, but using low-resolution images for semantic segmentation, although the recognition rate is high, many small but important details are lost compared to high-resolution images . [0004] In order to obtain the information that the image 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): G06K9/62G06T3/40G06N3/04
Inventor 程良伦梁广宇何伟健
Owner GUANGDONG UNIV OF TECH
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