Artificial Intelligence for Detecting Indoor Visual Discomfort from Facial Analysis of Building Occupants

Hicham Johra; Rikke Gade; Mathias Østergaard Poulsen; Albert Daugbjerg Christensen; Mandana Sarey Khanie; Thomas B. Moeslund; Rasmus Lund Jensen

doi:10.1088/1742-6596/2042/1/012008

Artificial Intelligence for Detecting Indoor Visual Discomfort from Facial Analysis of Building Occupants

Hicham Johra, Rikke Gade, Mathias Østergaard Poulsen, Albert Daugbjerg Christensen, Mandana Sarey Khanie, Thomas B. Moeslund, Rasmus Lund Jensen

Research output: Contribution to journal › Conference article in Journal › Research › peer-review

1 Citation (Scopus)

45 Downloads (Pure)

Abstract

Glare is a common local visual discomfort that is difficult to identify with conventional light sensors. This article presents an artificial intelligence algorithm that detects subjective local glare discomfort from the image analysis of the video footage of an office occupant’s face. The occupant’s face is directly used as a visual comfort sensor. Results show that it can recognize glare discomfort with around 90% accuracy. This algorithm can thus be at the basis of an efficient feedback control system to regulate shading devices in an office building.

Original language	English
Article number	012008
Book series	Journal of Physics: Conference Series (Online)
Volume	2042
Issue number	1
ISSN	1742-6596
DOIs	https://doi.org/10.1088/1742-6596/2042/1/012008
Publication status	Published - 2021
Event	CISBAT 2021 - Lausanne, Virtual, Switzerland Duration: 8 Sept 2021 → 10 Sept 2021 https://cisbat.epfl.ch/call.html

Conference

Conference	CISBAT 2021
Country/Territory	Switzerland
City	Lausanne, Virtual
Period	08/09/2021 → 10/09/2021
Internet address	https://cisbat.epfl.ch/call.html

Keywords

AI
Visual Comfort
Glare
Machine Learning

Access to Document

10.1088/1742-6596/2042/1/012008Licence: CC BY 3.0

Artificial Intelligence for Detecting Indoor Visual Discomfort from Facial Analysis of Building OccupantsFinal published version, 1.07 MBLicence: CC BY 3.0

https://iopscience.iop.org/article/10.1088/1742-6596/2042/1/012008/pdfLicence: CC BY 3.0

AUB Link

Search for the material in Aalborg University Library's search engine

Cite this

@inproceedings{6124247ace324587808bd5490e38c356,

title = "Artificial Intelligence for Detecting Indoor Visual Discomfort from Facial Analysis of Building Occupants",

abstract = "Glare is a common local visual discomfort that is difficult to identify with conventional light sensors. This article presents an artificial intelligence algorithm that detects subjective local glare discomfort from the image analysis of the video footage of an office occupant{\textquoteright}s face. The occupant{\textquoteright}s face is directly used as a visual comfort sensor. Results show that it can recognize glare discomfort with around 90% accuracy. This algorithm can thus be at the basis of an efficient feedback control system to regulate shading devices in an office building.",

keywords = "AI, Visual Comfort, Glare, Machine Learning, AI, Visual Comfort, Glare, Machine Learning",

author = "Hicham Johra and Rikke Gade and Poulsen, {Mathias {\O}stergaard} and Christensen, {Albert Daugbjerg} and {Sarey Khanie}, Mandana and Moeslund, {Thomas B.} and Jensen, {Rasmus Lund}",

year = "2021",

doi = "10.1088/1742-6596/2042/1/012008",

language = "English",

volume = "2042",

journal = "Journal of Physics: Conference Series (Online)",

issn = "1742-6596",

publisher = "IOP Publishing",

number = "1",

note = "CISBAT 2021 ; Conference date: 08-09-2021 Through 10-09-2021",

url = "https://cisbat.epfl.ch/call.html",

}

TY - GEN

T1 - Artificial Intelligence for Detecting Indoor Visual Discomfort from Facial Analysis of Building Occupants

AU - Johra, Hicham

AU - Gade, Rikke

AU - Poulsen, Mathias Østergaard

AU - Christensen, Albert Daugbjerg

AU - Sarey Khanie, Mandana

AU - Moeslund, Thomas B.

AU - Jensen, Rasmus Lund

PY - 2021

Y1 - 2021

N2 - Glare is a common local visual discomfort that is difficult to identify with conventional light sensors. This article presents an artificial intelligence algorithm that detects subjective local glare discomfort from the image analysis of the video footage of an office occupant’s face. The occupant’s face is directly used as a visual comfort sensor. Results show that it can recognize glare discomfort with around 90% accuracy. This algorithm can thus be at the basis of an efficient feedback control system to regulate shading devices in an office building.

AB - Glare is a common local visual discomfort that is difficult to identify with conventional light sensors. This article presents an artificial intelligence algorithm that detects subjective local glare discomfort from the image analysis of the video footage of an office occupant’s face. The occupant’s face is directly used as a visual comfort sensor. Results show that it can recognize glare discomfort with around 90% accuracy. This algorithm can thus be at the basis of an efficient feedback control system to regulate shading devices in an office building.

KW - AI

KW - Visual Comfort

KW - Glare

KW - Machine Learning

KW - AI

KW - Visual Comfort

KW - Glare

KW - Machine Learning

U2 - 10.1088/1742-6596/2042/1/012008

DO - 10.1088/1742-6596/2042/1/012008

M3 - Conference article in Journal

SN - 1742-6596

VL - 2042

JO - Journal of Physics: Conference Series (Online)

JF - Journal of Physics: Conference Series (Online)

IS - 1

M1 - 012008

T2 - CISBAT 2021

Y2 - 8 September 2021 through 10 September 2021

ER -

Artificial Intelligence for Detecting Indoor Visual Discomfort from Facial Analysis of Building Occupants

Abstract

Conference

Keywords

Access to Document

AUB Link

Other files and links

Fingerprint

AI for optimizing indoor visual comfort from facial analysis

AAU AI for the People Center - Talk

Best Paper Award at Conference CISBAT 2021

BEST PAPER AWARD TO THE BRIDGING PROJECT

Training and testing labelled image and video datasets of human faces for different indoor visual comfort and glare visual discomfort situations

Cite this

Artificial Intelligence for Detecting Indoor Visual Discomfort from Facial Analysis of Building Occupants

Abstract

Conference

Keywords

Access to Document

AUB Link

Other files and links

Fingerprint

Projects

AI for optimizing indoor visual comfort from facial analysis

Activities

AAU AI for the People Center - Talk

Prizes

Best Paper Award at Conference CISBAT 2021

Press/Media

BEST PAPER AWARD TO THE BRIDGING PROJECT

Research output

Training and testing labelled image and video datasets of human faces for different indoor visual comfort and glare visual discomfort situations

Cite this