Infrared and visible light fusion imaging method based on deep learning

A deep learning and imaging method technology, applied in the field of infrared and visible light fusion imaging, can solve the problems of visible light images being easily affected by bad weather, poor infrared imaging quality, noise interference, etc.

Active Publication Date: 2021-10-08
GUANGDONG UNIV OF TECH
View PDF4 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of this application is to provide a deep learning-based infrared and visible light fusion imaging method to solve the problems of poor infrared imaging quality, serious noise interference and visible light images being easily affected by bad weather in infrared and visible light imaging systems

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
  • Infrared and visible light fusion imaging method based on deep learning
  • Infrared and visible light fusion imaging method based on deep learning
  • Infrared and visible light fusion imaging method based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0042] This application provides a fusion imaging method of infrared and visible light based on deep learning. This method improves the imaging quality and effectively removes noise interference in the image, so that the target in the image is prominent and the texture is clear, which is convenient for more accurate target identification and is more conducive to 24 / 7 operation of the imaging system.

[0043] like figure 1 As shown, this application uses the deep learning image fusion method to process the target image pair, and uses the infrared and visible light imaging system to capture the measured target image to generate the infrared and visible light image pair, and processes the target image pair. The fusion process is divided into the following steps :

[0044] S1. Simultaneously collect infrared images and visible light images of the same size for the target to form a target image pair, and perform down-sampling processing on the target image pair to be divided into ...

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 an infrared and visible light fusion imaging method based on deep learning. The method comprises the steps: collecting an infrared image and a visible light image of the same size for a target at the same time to form a target object image pair, carrying out the sub-image pair segmentation and preprocessing of sub-images in the target object image pair, and adding a noise image, inputting the sub-image pair added with the noise map into a trained image fusion model as an input image pair to obtain a fused image, wherein the image fusion model comprises a shallow feature extraction unit, an encoder, a fusion module and a decoder. The general fact that the source image contains noise is considered, the source image is used as the premise of actual imaging application, image denoising is performed in the image fusion process, and noise points in the source image pair are effectively prevented from being introduced into the fusion image; the method is very beneficial to application research of infrared and visible light fusion and a deep learning technology, and is expected to be widely applied to the fields of medical imaging, night monitoring and the like.

Description

technical field [0001] This application relates to the field of image fusion, in particular to a fusion imaging method of infrared and visible light based on deep learning. Background technique [0002] Infrared thermal imaging takes the thermal radiation information of the target as input, and can also detect the target when the light is insufficient and distinguish the target from the background according to the difference in radiation. Visible light sensors use object reflectivity to image targets and can provide images with high resolution and sharp texture details. Infrared and visible light imaging systems can reflect different attributes of the same target at the same time, provide scene information from different aspects, and have a wide range of applications in military, video surveillance, car assisted driving, forest fire prevention and other fields. [0003] In recent years, with the widespread application of infrared and visible light imaging technology, the in...

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): G06T5/50G06T5/00G06K9/62G06N3/04G06N3/08
CPCG06T5/50G06T5/002G06N3/08G06T2207/10048G06T2207/20081G06T2207/20221G06N3/045G06F18/253
Inventor 程良伦李卓吴衡
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