Image-based Material Characterization for Daylight Simulation Using Illuminance-proxy and Artificial Neural Networks

N. Forouzandeh Shahraki; E. Brembilla; John Alstan Jakubiec

Image-based Material Characterization for Daylight Simulation Using Illuminance-proxy and Artificial Neural Networks

N. Forouzandeh Shahraki, E. Brembilla, John Alstan Jakubiec

Building Physics

Research output: Chapter in Book/Conference proceedings/Edited volume › Conference contribution › Scientific › peer-review

26 Downloads (Pure)

Abstract

A key aspect of daylight modeling is the definition of material optical properties. Characterization of such properties in existing indoor spaces with current methods is a labour-intensive and time-consuming task, especially in surfaces with considerable visual complexity. Faster and more accurate estimations of such properties will lead to more efficient workflows. Towards this direction, the present work studied the feasibility of using two novel approaches i.e. illuminance-proxy and probabilistic image based material characterization methods for implementation in daylight modeling. These approaches are compared with two common techniques, namely the manual selection from a measured dataset and the use of illuminance/luminance measurements. According to the results, both novel techniques are able to predict spatiallyaveraged Daylight Autonomy, continuous Daylight Autonomy, and Useful Daylight Illuminance in 300-3000 lx range with less than 5% error

Original language	English
Title of host publication	Proceedings of the 14th European Lighting Conference LUX EUROPA 2022
Place of Publication	Prague
Pages	171-178
Number of pages	8
ISBN (Electronic)	978-80-11-02269-3
Publication status	Published - 2022
Event	14th European Lighting Conference: LUX EUROPA 2022 - Hotel Olympik / Artemis, Prague, Czech Republic Duration: 20 Sep 2022 → 22 Sep 2022 https://www.luxeuropa2022.eu/

Conference

Conference	14th European Lighting Conference
Country/Territory	Czech Republic
City	Prague
Period	20/09/22 → 22/09/22
Internet address	https://www.luxeuropa2022.eu/

Bibliographical note

Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care
Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.

Keywords

on-site
measurement
visual
Digitalization
Optical

Embargoed Document

NF_LuxEuropa_published
Final published version, 1.04 MB
Embargo ends: 1/07/23

Cite this

@inproceedings{e0298d283c66442bba928235f732d0ff,

title = "Image-based Material Characterization for Daylight Simulation Using Illuminance-proxy and Artificial Neural Networks",

abstract = "A key aspect of daylight modeling is the definition of material optical properties. Characterization of such properties in existing indoor spaces with current methods is a labour-intensive and time-consuming task, especially in surfaces with considerable visual complexity. Faster and more accurate estimations of such properties will lead to more efficient workflows. Towards this direction, the present work studied the feasibility of using two novel approaches i.e. illuminance-proxy and probabilistic image based material characterization methods for implementation in daylight modeling. These approaches are compared with two common techniques, namely the manual selection from a measured dataset and the use of illuminance/luminance measurements. According to the results, both novel techniques are able to predict spatiallyaveraged Daylight Autonomy, continuous Daylight Autonomy, and Useful Daylight Illuminance in 300-3000 lx range with less than 5% error",

keywords = "on-site, measurement, visual, Digitalization, Optical",

author = "{Forouzandeh Shahraki}, N. and E. Brembilla and Jakubiec, {John Alstan}",

note = "Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.; 14th European Lighting Conference : LUX EUROPA 2022 ; Conference date: 20-09-2022 Through 22-09-2022",

year = "2022",

language = "English",

pages = "171--178",

booktitle = "Proceedings of the 14th European Lighting Conference LUX EUROPA 2022",

url = "https://www.luxeuropa2022.eu/",

}

Image-based Material Characterization for Daylight Simulation Using Illuminance-proxy and Artificial Neural Networks. / Forouzandeh Shahraki, N.; Brembilla, E.; Jakubiec, John Alstan.

Proceedings of the 14th European Lighting Conference LUX EUROPA 2022. Prague, 2022. p. 171-178.

Research output: Chapter in Book/Conference proceedings/Edited volume › Conference contribution › Scientific › peer-review

TY - GEN

T1 - Image-based Material Characterization for Daylight Simulation Using Illuminance-proxy and Artificial Neural Networks

AU - Forouzandeh Shahraki, N.

AU - Brembilla, E.

AU - Jakubiec, John Alstan

N1 - Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.

PY - 2022

Y1 - 2022

N2 - A key aspect of daylight modeling is the definition of material optical properties. Characterization of such properties in existing indoor spaces with current methods is a labour-intensive and time-consuming task, especially in surfaces with considerable visual complexity. Faster and more accurate estimations of such properties will lead to more efficient workflows. Towards this direction, the present work studied the feasibility of using two novel approaches i.e. illuminance-proxy and probabilistic image based material characterization methods for implementation in daylight modeling. These approaches are compared with two common techniques, namely the manual selection from a measured dataset and the use of illuminance/luminance measurements. According to the results, both novel techniques are able to predict spatiallyaveraged Daylight Autonomy, continuous Daylight Autonomy, and Useful Daylight Illuminance in 300-3000 lx range with less than 5% error

AB - A key aspect of daylight modeling is the definition of material optical properties. Characterization of such properties in existing indoor spaces with current methods is a labour-intensive and time-consuming task, especially in surfaces with considerable visual complexity. Faster and more accurate estimations of such properties will lead to more efficient workflows. Towards this direction, the present work studied the feasibility of using two novel approaches i.e. illuminance-proxy and probabilistic image based material characterization methods for implementation in daylight modeling. These approaches are compared with two common techniques, namely the manual selection from a measured dataset and the use of illuminance/luminance measurements. According to the results, both novel techniques are able to predict spatiallyaveraged Daylight Autonomy, continuous Daylight Autonomy, and Useful Daylight Illuminance in 300-3000 lx range with less than 5% error

KW - on-site

KW - measurement

KW - visual

KW - Digitalization

KW - Optical

M3 - Conference contribution

SP - 171

EP - 178

BT - Proceedings of the 14th European Lighting Conference LUX EUROPA 2022

CY - Prague

T2 - 14th European Lighting Conference

Y2 - 20 September 2022 through 22 September 2022

ER -

Image-based Material Characterization for Daylight Simulation Using Illuminance-proxy and Artificial Neural Networks

Abstract

Conference

Bibliographical note

Keywords

Embargoed Document

Fingerprint

Cite this