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

Deep learning image denoising method and device for infrared thermal imaging

A technology of infrared thermal imaging and deep learning, applied in the field of deep learning image denoising of infrared thermal imaging system, can solve problems such as noise interference and poor imaging quality, and achieve the effect of increasing speed, reducing complexity, and good denoising effect

Active Publication Date: 2021-06-25
GUANGDONG UNIV OF TECH
View PDF8 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to provide a deep learning image denoising method and device for an infrared thermal imaging system to solve the problems of poor imaging quality and serious noise interference existing in the existing infrared imaging system

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
  • Deep learning image denoising method and device for infrared thermal imaging
  • Deep learning image denoising method and device for infrared thermal imaging
  • Deep learning image denoising method and device for infrared thermal imaging

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0048] see figure 1 , the first aspect of the present application provides an infrared thermal imaging system deep learning image denoising method, comprising the following steps:

[0049] S1. Obtain the image of the target object collected by the infrared thermal imaging system, perform down-sampling processing, and divide it into sub-images.

[0050] In one embodiment of the present application, the image I of the measured object is taken by an infrared thermal imaging system, and its size is n ch ×h×w, the target image I is down-sampled and divided into 4n ch ×h / 2×w / 2 sub-images. where n ch is the channel, h is the height, and w is the width.

[0051] S2. Perform image block extraction and pixel reorganization on each sub-image to obtain a preprocessed sub-image.

[0052] In this embodiment, 2×2 image blocks are extracted for each image, and its pixels are reorganized in different channels of the output image to obtain the preprocessed sub-image A 0 , its mathematica...

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 deep learning image denoising method and device for an infrared thermal imaging system. The method comprises the steps: obtaining a target object image collected by the infrared thermal imaging system, carrying out down-sampling processing, and segmenting the target object image into sub-images; performing image block extraction and pixel recombination on each sub-image to obtain a pre-processed sub-image; constructing a noise map, and adding the noise map as an additional channel to the preprocessed sub-image as an input image; taking the input image as a trained deep learning model, and outputting an estimated value of noise; and removing the estimated value of the noise from the target object image to obtain a denoised image. According to the method, rich structural features and similarity of the image can be fully utilized, context information in image block features can be better utilized, image features are fully extracted, a better effect is achieved under the condition that feature values of the infrared image are few, and application research of infrared thermal imaging and the deep learning technology is facilitated.

Description

technical field [0001] The invention relates to the field of thermal infrared imaging, in particular to an infrared thermal imaging system deep learning image denoising method and device. Background technique [0002] Due to the existence of black body radiation, any object radiates electromagnetic waves according to the temperature. The part with a wavelength of 2.0 to 1000 microns is called thermal infrared. Thermal infrared imaging can image objects by being sensitive to thermal infrared, and can reflect the temperature field on the surface of the object. Thermal infrared is widely used in military, industrial, automotive assisted driving, and medical fields. [0003] In recent years, with the widespread application of infrared thermal imaging technology, the visual range of human vision has been further broadened, but some problems have also been exposed, such as poor imaging quality of infrared images and serious noise interference, especially for environments with av...

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): G06T5/00G06T7/10G06N3/04
CPCG06T7/10G06T2207/20021G06T2207/20081G06N3/045G06T5/70
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 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