Virtual Sensors Determined Through Machine Learning

Yumi Iwashita, Adrian Stoica, Kazuto Nakashima, Ryo Kurazume, Jim Torresen

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

We propose a method that increases the capability of a conventional sensor, transforming it into an enhanced virtual sensor. This paper focuses on a virtual thermal Infrared Radiation (IR) sensor based on a conventional visual (RGB) sensor. The estimation of thermal IR images can enhance the ability of terrain classification, which is crucial for autonomous navigation of rovers. The estimate in IR from visual band has inherent limitations, as these are different bands, yet correlations between visual RGB and thermal IR images exist, as different terrains, which visually may appear different, also have different thermal inertia. This paper describes the developed deep learning-based algorithm that estimates thermal IR images from RGB images of terrains, providing the feasibility of the idea with average 1.21 error [degree Celsius].

Original languageEnglish
Title of host publication2018 World Automation Congress, WAC 2018
PublisherIEEE Computer Society
Pages318-321
Number of pages4
Volume2018-June
ISBN (Print)9781532377914
DOIs
Publication statusPublished - Aug 8 2018
Event2018 World Automation Congress, WAC 2018 - Stevenson, United States
Duration: Jun 3 2018Jun 6 2018

Publication series

NameWorld Automation Congress Proceedings
Volume2018-June
ISSN (Print)2154-4824
ISSN (Electronic)2154-4832

Conference

Conference2018 World Automation Congress, WAC 2018
CountryUnited States
CityStevenson
Period6/3/186/6/18

Fingerprint

Learning systems
Heat radiation
Infrared radiation
Sensors
Navigation

All Science Journal Classification (ASJC) codes

  • Control and Systems Engineering

Cite this

Iwashita, Y., Stoica, A., Nakashima, K., Kurazume, R., & Torresen, J. (2018). Virtual Sensors Determined Through Machine Learning. In 2018 World Automation Congress, WAC 2018 (Vol. 2018-June, pp. 318-321). [8430480] (World Automation Congress Proceedings; Vol. 2018-June). IEEE Computer Society. https://doi.org/10.23919/WAC.2018.8430480

Virtual Sensors Determined Through Machine Learning. / Iwashita, Yumi; Stoica, Adrian; Nakashima, Kazuto; Kurazume, Ryo; Torresen, Jim.

2018 World Automation Congress, WAC 2018. Vol. 2018-June IEEE Computer Society, 2018. p. 318-321 8430480 (World Automation Congress Proceedings; Vol. 2018-June).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Iwashita, Y, Stoica, A, Nakashima, K, Kurazume, R & Torresen, J 2018, Virtual Sensors Determined Through Machine Learning. in 2018 World Automation Congress, WAC 2018. vol. 2018-June, 8430480, World Automation Congress Proceedings, vol. 2018-June, IEEE Computer Society, pp. 318-321, 2018 World Automation Congress, WAC 2018, Stevenson, United States, 6/3/18. https://doi.org/10.23919/WAC.2018.8430480
Iwashita Y, Stoica A, Nakashima K, Kurazume R, Torresen J. Virtual Sensors Determined Through Machine Learning. In 2018 World Automation Congress, WAC 2018. Vol. 2018-June. IEEE Computer Society. 2018. p. 318-321. 8430480. (World Automation Congress Proceedings). https://doi.org/10.23919/WAC.2018.8430480
Iwashita, Yumi ; Stoica, Adrian ; Nakashima, Kazuto ; Kurazume, Ryo ; Torresen, Jim. / Virtual Sensors Determined Through Machine Learning. 2018 World Automation Congress, WAC 2018. Vol. 2018-June IEEE Computer Society, 2018. pp. 318-321 (World Automation Congress Proceedings).
@inproceedings{dda9aa97b2844cf89dca92096f84e2ad,
title = "Virtual Sensors Determined Through Machine Learning",
abstract = "We propose a method that increases the capability of a conventional sensor, transforming it into an enhanced virtual sensor. This paper focuses on a virtual thermal Infrared Radiation (IR) sensor based on a conventional visual (RGB) sensor. The estimation of thermal IR images can enhance the ability of terrain classification, which is crucial for autonomous navigation of rovers. The estimate in IR from visual band has inherent limitations, as these are different bands, yet correlations between visual RGB and thermal IR images exist, as different terrains, which visually may appear different, also have different thermal inertia. This paper describes the developed deep learning-based algorithm that estimates thermal IR images from RGB images of terrains, providing the feasibility of the idea with average 1.21 error [degree Celsius].",
author = "Yumi Iwashita and Adrian Stoica and Kazuto Nakashima and Ryo Kurazume and Jim Torresen",
year = "2018",
month = "8",
day = "8",
doi = "10.23919/WAC.2018.8430480",
language = "English",
isbn = "9781532377914",
volume = "2018-June",
series = "World Automation Congress Proceedings",
publisher = "IEEE Computer Society",
pages = "318--321",
booktitle = "2018 World Automation Congress, WAC 2018",
address = "United States",

}

TY - GEN

T1 - Virtual Sensors Determined Through Machine Learning

AU - Iwashita, Yumi

AU - Stoica, Adrian

AU - Nakashima, Kazuto

AU - Kurazume, Ryo

AU - Torresen, Jim

PY - 2018/8/8

Y1 - 2018/8/8

N2 - We propose a method that increases the capability of a conventional sensor, transforming it into an enhanced virtual sensor. This paper focuses on a virtual thermal Infrared Radiation (IR) sensor based on a conventional visual (RGB) sensor. The estimation of thermal IR images can enhance the ability of terrain classification, which is crucial for autonomous navigation of rovers. The estimate in IR from visual band has inherent limitations, as these are different bands, yet correlations between visual RGB and thermal IR images exist, as different terrains, which visually may appear different, also have different thermal inertia. This paper describes the developed deep learning-based algorithm that estimates thermal IR images from RGB images of terrains, providing the feasibility of the idea with average 1.21 error [degree Celsius].

AB - We propose a method that increases the capability of a conventional sensor, transforming it into an enhanced virtual sensor. This paper focuses on a virtual thermal Infrared Radiation (IR) sensor based on a conventional visual (RGB) sensor. The estimation of thermal IR images can enhance the ability of terrain classification, which is crucial for autonomous navigation of rovers. The estimate in IR from visual band has inherent limitations, as these are different bands, yet correlations between visual RGB and thermal IR images exist, as different terrains, which visually may appear different, also have different thermal inertia. This paper describes the developed deep learning-based algorithm that estimates thermal IR images from RGB images of terrains, providing the feasibility of the idea with average 1.21 error [degree Celsius].

UR - http://www.scopus.com/inward/record.url?scp=85052064772&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85052064772&partnerID=8YFLogxK

U2 - 10.23919/WAC.2018.8430480

DO - 10.23919/WAC.2018.8430480

M3 - Conference contribution

AN - SCOPUS:85052064772

SN - 9781532377914

VL - 2018-June

T3 - World Automation Congress Proceedings

SP - 318

EP - 321

BT - 2018 World Automation Congress, WAC 2018

PB - IEEE Computer Society

ER -