Cargando…

Midwave FTIR-Based Remote Surface Temperature Estimation Using a Deep Convolutional Neural Network in a Dynamic Weather Environment

Remote measurements of thermal radiation are very important for analyzing the solar effect in various environments. This paper presents a novel real-time remote temperature estimation method by applying a deep learning-based regression method to midwave infrared hyperspectral images. A conventional...

Descripción completa

Detalles Bibliográficos
Autores principales: Kim, Sungho, Kim, Jungho, Lee, Jinyong, Ahn, Junmo
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2018
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6215119/
https://www.ncbi.nlm.nih.gov/pubmed/30424428
http://dx.doi.org/10.3390/mi9100495
_version_ 1783368079871311872
author Kim, Sungho
Kim, Jungho
Lee, Jinyong
Ahn, Junmo
author_facet Kim, Sungho
Kim, Jungho
Lee, Jinyong
Ahn, Junmo
author_sort Kim, Sungho
collection PubMed
description Remote measurements of thermal radiation are very important for analyzing the solar effect in various environments. This paper presents a novel real-time remote temperature estimation method by applying a deep learning-based regression method to midwave infrared hyperspectral images. A conventional remote temperature estimation using only one channel or multiple channels cannot provide a reliable temperature in dynamic weather environments because of the unknown atmospheric transmissivities. This paper solves the issue (real-time remote temperature measurement with high accuracy) with the proposed surface temperature-deep convolutional neural network (ST-DCNN) and a hyperspectral thermal camera (TELOPS HYPER-CAM MWE). The 27-layer ST-DCNN regressor can learn and predict the underlying temperatures from 75 spectral channels. Midwave infrared hyperspectral image data of a remote object were acquired three times a day (10:00, 13:00, 15:00) for 7 months to consider the dynamic weather variations. The experimental results validate the feasibility of the novel remote temperature estimation method in real-world dynamic environments. In addition, the thermal stealth properties of two types of paint were demonstrated by the proposed ST-DCNN as a real-world application.
format Online
Article
Text
id pubmed-6215119
institution National Center for Biotechnology Information
language English
publishDate 2018
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-62151192018-11-06 Midwave FTIR-Based Remote Surface Temperature Estimation Using a Deep Convolutional Neural Network in a Dynamic Weather Environment Kim, Sungho Kim, Jungho Lee, Jinyong Ahn, Junmo Micromachines (Basel) Article Remote measurements of thermal radiation are very important for analyzing the solar effect in various environments. This paper presents a novel real-time remote temperature estimation method by applying a deep learning-based regression method to midwave infrared hyperspectral images. A conventional remote temperature estimation using only one channel or multiple channels cannot provide a reliable temperature in dynamic weather environments because of the unknown atmospheric transmissivities. This paper solves the issue (real-time remote temperature measurement with high accuracy) with the proposed surface temperature-deep convolutional neural network (ST-DCNN) and a hyperspectral thermal camera (TELOPS HYPER-CAM MWE). The 27-layer ST-DCNN regressor can learn and predict the underlying temperatures from 75 spectral channels. Midwave infrared hyperspectral image data of a remote object were acquired three times a day (10:00, 13:00, 15:00) for 7 months to consider the dynamic weather variations. The experimental results validate the feasibility of the novel remote temperature estimation method in real-world dynamic environments. In addition, the thermal stealth properties of two types of paint were demonstrated by the proposed ST-DCNN as a real-world application. MDPI 2018-09-27 /pmc/articles/PMC6215119/ /pubmed/30424428 http://dx.doi.org/10.3390/mi9100495 Text en © 2018 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Kim, Sungho
Kim, Jungho
Lee, Jinyong
Ahn, Junmo
Midwave FTIR-Based Remote Surface Temperature Estimation Using a Deep Convolutional Neural Network in a Dynamic Weather Environment
title Midwave FTIR-Based Remote Surface Temperature Estimation Using a Deep Convolutional Neural Network in a Dynamic Weather Environment
title_full Midwave FTIR-Based Remote Surface Temperature Estimation Using a Deep Convolutional Neural Network in a Dynamic Weather Environment
title_fullStr Midwave FTIR-Based Remote Surface Temperature Estimation Using a Deep Convolutional Neural Network in a Dynamic Weather Environment
title_full_unstemmed Midwave FTIR-Based Remote Surface Temperature Estimation Using a Deep Convolutional Neural Network in a Dynamic Weather Environment
title_short Midwave FTIR-Based Remote Surface Temperature Estimation Using a Deep Convolutional Neural Network in a Dynamic Weather Environment
title_sort midwave ftir-based remote surface temperature estimation using a deep convolutional neural network in a dynamic weather environment
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6215119/
https://www.ncbi.nlm.nih.gov/pubmed/30424428
http://dx.doi.org/10.3390/mi9100495
work_keys_str_mv AT kimsungho midwaveftirbasedremotesurfacetemperatureestimationusingadeepconvolutionalneuralnetworkinadynamicweatherenvironment
AT kimjungho midwaveftirbasedremotesurfacetemperatureestimationusingadeepconvolutionalneuralnetworkinadynamicweatherenvironment
AT leejinyong midwaveftirbasedremotesurfacetemperatureestimationusingadeepconvolutionalneuralnetworkinadynamicweatherenvironment
AT ahnjunmo midwaveftirbasedremotesurfacetemperatureestimationusingadeepconvolutionalneuralnetworkinadynamicweatherenvironment