Systematic infrared image quality improvement using deep learning based techniques

Huaizhong Zhang, Pablo Casaseca-de-la-Higueraa, Chunbo Luob, Qi Wanga, Matthew Kitchinic, Andrew Parmleyc, Jesus Monge-Alvareza

Research output: Chapter in Book/Report/Conference proceedingConference proceeding (ISBN)

2 Citations (Scopus)
13 Downloads (Pure)

Abstract

Infrared thermography (IRT, or thermal video) uses thermographic cameras to detect and record radiation in the longwavelength infrared range of the electromagnetic spectrum. It allows sensing environments beyond the visual perception limitations, and thus has been widely used in many civilian and military applications. Even though current thermal cameras are able to provide high resolution and bitdepth images, there are significant challenges to be addressed in specific applications such as poor contrast, low target signature resolution, etc. This paper addresses quality improvement in IRT images for object recognition. A systematic approach based on image bias correction and deep learning is proposed to increase target signature resolution and optimise the baseline quality of inputs for object recognition. Our main objective is to maximise the useful information on the object to be detected even when the number of pixels on target is adversely small. The experimental results show that our approach can significantly improve target resolution and thus helps making object recognition more efficient in automatic target detection/recognition systems (ATD/R).
Original languageEnglish
Title of host publicationNot Known
Pages1-8
Volume10008
DOIs
Publication statusE-pub ahead of print - 26 Oct 2016
EventRemote Sensing Technologies and Applications - Edinburgh, United Kingdom
Duration: 26 Oct 2016 → …

Conference

ConferenceRemote Sensing Technologies and Applications
CountryUnited Kingdom
CityEdinburgh
Period26/10/16 → …

Fingerprint

Cameras
Infrared radiation
Military applications
Object recognition
Pixels
Radiation
Deep learning
Hot Temperature

Cite this

Zhang, H., Casaseca-de-la-Higueraa, P., Luob, C., Wanga, Q., Kitchinic, M., Parmleyc, A., & Monge-Alvareza, J. (2016). Systematic infrared image quality improvement using deep learning based techniques. In Not Known (Vol. 10008, pp. 1-8) https://doi.org/10.1117/12.2242036
Zhang, Huaizhong ; Casaseca-de-la-Higueraa, Pablo ; Luob, Chunbo ; Wanga, Qi ; Kitchinic, Matthew ; Parmleyc, Andrew ; Monge-Alvareza, Jesus. / Systematic infrared image quality improvement using deep learning based techniques. Not Known. Vol. 10008 2016. pp. 1-8
@inproceedings{a34c13f24c5f4ab581f60c032ea52243,
title = "Systematic infrared image quality improvement using deep learning based techniques",
abstract = "Infrared thermography (IRT, or thermal video) uses thermographic cameras to detect and record radiation in the longwavelength infrared range of the electromagnetic spectrum. It allows sensing environments beyond the visual perception limitations, and thus has been widely used in many civilian and military applications. Even though current thermal cameras are able to provide high resolution and bitdepth images, there are significant challenges to be addressed in specific applications such as poor contrast, low target signature resolution, etc. This paper addresses quality improvement in IRT images for object recognition. A systematic approach based on image bias correction and deep learning is proposed to increase target signature resolution and optimise the baseline quality of inputs for object recognition. Our main objective is to maximise the useful information on the object to be detected even when the number of pixels on target is adversely small. The experimental results show that our approach can significantly improve target resolution and thus helps making object recognition more efficient in automatic target detection/recognition systems (ATD/R).",
author = "Huaizhong Zhang and Pablo Casaseca-de-la-Higueraa and Chunbo Luob and Qi Wanga and Matthew Kitchinic and Andrew Parmleyc and Jesus Monge-Alvareza",
note = "Proc. SPIE 10008, Remote Sensing Technologies and Applications in Urban Environments, 100080P",
year = "2016",
month = "10",
day = "26",
doi = "10.1117/12.2242036",
language = "English",
volume = "10008",
pages = "1--8",
booktitle = "Not Known",

}

Zhang, H, Casaseca-de-la-Higueraa, P, Luob, C, Wanga, Q, Kitchinic, M, Parmleyc, A & Monge-Alvareza, J 2016, Systematic infrared image quality improvement using deep learning based techniques. in Not Known. vol. 10008, pp. 1-8, Remote Sensing Technologies and Applications, Edinburgh, United Kingdom, 26/10/16. https://doi.org/10.1117/12.2242036

Systematic infrared image quality improvement using deep learning based techniques. / Zhang, Huaizhong; Casaseca-de-la-Higueraa, Pablo; Luob, Chunbo; Wanga, Qi; Kitchinic, Matthew; Parmleyc, Andrew; Monge-Alvareza, Jesus.

Not Known. Vol. 10008 2016. p. 1-8.

Research output: Chapter in Book/Report/Conference proceedingConference proceeding (ISBN)

TY - GEN

T1 - Systematic infrared image quality improvement using deep learning based techniques

AU - Zhang, Huaizhong

AU - Casaseca-de-la-Higueraa, Pablo

AU - Luob, Chunbo

AU - Wanga, Qi

AU - Kitchinic, Matthew

AU - Parmleyc, Andrew

AU - Monge-Alvareza, Jesus

N1 - Proc. SPIE 10008, Remote Sensing Technologies and Applications in Urban Environments, 100080P

PY - 2016/10/26

Y1 - 2016/10/26

N2 - Infrared thermography (IRT, or thermal video) uses thermographic cameras to detect and record radiation in the longwavelength infrared range of the electromagnetic spectrum. It allows sensing environments beyond the visual perception limitations, and thus has been widely used in many civilian and military applications. Even though current thermal cameras are able to provide high resolution and bitdepth images, there are significant challenges to be addressed in specific applications such as poor contrast, low target signature resolution, etc. This paper addresses quality improvement in IRT images for object recognition. A systematic approach based on image bias correction and deep learning is proposed to increase target signature resolution and optimise the baseline quality of inputs for object recognition. Our main objective is to maximise the useful information on the object to be detected even when the number of pixels on target is adversely small. The experimental results show that our approach can significantly improve target resolution and thus helps making object recognition more efficient in automatic target detection/recognition systems (ATD/R).

AB - Infrared thermography (IRT, or thermal video) uses thermographic cameras to detect and record radiation in the longwavelength infrared range of the electromagnetic spectrum. It allows sensing environments beyond the visual perception limitations, and thus has been widely used in many civilian and military applications. Even though current thermal cameras are able to provide high resolution and bitdepth images, there are significant challenges to be addressed in specific applications such as poor contrast, low target signature resolution, etc. This paper addresses quality improvement in IRT images for object recognition. A systematic approach based on image bias correction and deep learning is proposed to increase target signature resolution and optimise the baseline quality of inputs for object recognition. Our main objective is to maximise the useful information on the object to be detected even when the number of pixels on target is adversely small. The experimental results show that our approach can significantly improve target resolution and thus helps making object recognition more efficient in automatic target detection/recognition systems (ATD/R).

U2 - 10.1117/12.2242036

DO - 10.1117/12.2242036

M3 - Conference proceeding (ISBN)

VL - 10008

SP - 1

EP - 8

BT - Not Known

ER -

Zhang H, Casaseca-de-la-Higueraa P, Luob C, Wanga Q, Kitchinic M, Parmleyc A et al. Systematic infrared image quality improvement using deep learning based techniques. In Not Known. Vol. 10008. 2016. p. 1-8 https://doi.org/10.1117/12.2242036