Deep Learning-Based Semantic Segmentation and 3D Reconstruction Techniques for Automatic Detection and Localization of Thermal Defects in Building Envelopes

X. Y. Yan; H. Huang; C. Zhang

doi:10.1007/978-981-99-7965-3_40

Deep Learning-Based Semantic Segmentation and 3D Reconstruction Techniques for Automatic Detection and Localization of Thermal Defects in Building Envelopes

X. Y. Yan
, H. Huang
, C. Zhang^*

^*Corresponding author for this work

Department of Civil Engineering

Xi'an Jiaotong-Liverpool University

Research output: Chapter in Book or Report/Conference proceeding › Conference Proceeding › peer-review

Abstract

Building age and extreme weather can cause thermal defects in the building envelope. Failure to inspect and fix these defects can threaten safety, increase energy consumption, and negatively impact the environment. Infrared thermal imaging (IRT) is a popular, non-destructive technique for building diagnostics due to its safety, practicality, and energy efficiency. However, manual IRT detection is time-consuming and imprecise. Therefore, this paper proposes a framework for automatically identifying and localising thermal defects in building envelopes. The outcomes of this study not only offer direction for categorising thermal defects in buildings but also provide a practical approach for automatically detecting and locating them.

Original language	English
Title of host publication	Towards a Carbon Neutral Future - The Proceedings of The 3rd International Conference on Sustainable Buildings and Structures
Editors	Konstantinos Papadikis, Cheng Zhang, Shu Tang, Engui Liu, Luigi Di Sarno
Publisher	Springer Science and Business Media Deutschland GmbH
Pages	467-478
Number of pages	12
ISBN (Print)	9789819979646
DOIs	https://doi.org/10.1007/978-981-99-7965-3_40
Publication status	Published - Aug 2023
Event	3rd International Conference on Sustainable Buildings and Structures, ICSBS 2023 - Suzhou, China Duration: 17 Aug 2023 → 20 Aug 2023

Publication series

Name	Lecture Notes in Civil Engineering
Volume	393
ISSN (Print)	2366-2557
ISSN (Electronic)	2366-2565

Conference

Conference	3rd International Conference on Sustainable Buildings and Structures, ICSBS 2023
Country/Territory	China
City	Suzhou
Period	17/08/23 → 20/08/23

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 7 Affordable and Clean Energy

Keywords

3D reconstruction techniques
Automatic detection
Building envelopes
Deep learning

Access to Document

10.1007/978-981-99-7965-3_40

Cite this

Yan, X. Y., Huang, H., & Zhang, C. (2023). Deep Learning-Based Semantic Segmentation and 3D Reconstruction Techniques for Automatic Detection and Localization of Thermal Defects in Building Envelopes. In K. Papadikis, C. Zhang, S. Tang, E. Liu, & L. Di Sarno (Eds.), Towards a Carbon Neutral Future - The Proceedings of The 3rd International Conference on Sustainable Buildings and Structures (pp. 467-478). (Lecture Notes in Civil Engineering; Vol. 393). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-981-99-7965-3_40

Yan, X. Y. ; Huang, H. ; Zhang, C. / Deep Learning-Based Semantic Segmentation and 3D Reconstruction Techniques for Automatic Detection and Localization of Thermal Defects in Building Envelopes. Towards a Carbon Neutral Future - The Proceedings of The 3rd International Conference on Sustainable Buildings and Structures. editor / Konstantinos Papadikis ; Cheng Zhang ; Shu Tang ; Engui Liu ; Luigi Di Sarno. Springer Science and Business Media Deutschland GmbH, 2023. pp. 467-478 (Lecture Notes in Civil Engineering).

@inproceedings{5c13e6b6ef1948f8a2e1f4ad305f997c,

title = "Deep Learning-Based Semantic Segmentation and 3D Reconstruction Techniques for Automatic Detection and Localization of Thermal Defects in Building Envelopes",

abstract = "Building age and extreme weather can cause thermal defects in the building envelope. Failure to inspect and fix these defects can threaten safety, increase energy consumption, and negatively impact the environment. Infrared thermal imaging (IRT) is a popular, non-destructive technique for building diagnostics due to its safety, practicality, and energy efficiency. However, manual IRT detection is time-consuming and imprecise. Therefore, this paper proposes a framework for automatically identifying and localising thermal defects in building envelopes. The outcomes of this study not only offer direction for categorising thermal defects in buildings but also provide a practical approach for automatically detecting and locating them.",

keywords = "3D reconstruction techniques, Automatic detection, Building envelopes, Deep learning",

author = "Yan, \{X. Y.\} and H. Huang and C. Zhang",

note = "Publisher Copyright: {\textcopyright} The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.; 3rd International Conference on Sustainable Buildings and Structures, ICSBS 2023 ; Conference date: 17-08-2023 Through 20-08-2023",

year = "2023",

month = aug,

doi = "10.1007/978-981-99-7965-3\_40",

language = "English",

isbn = "9789819979646",

series = "Lecture Notes in Civil Engineering",

publisher = "Springer Science and Business Media Deutschland GmbH",

pages = "467--478",

editor = "Konstantinos Papadikis and Cheng Zhang and Shu Tang and Engui Liu and \{Di Sarno\}, Luigi",

booktitle = "Towards a Carbon Neutral Future - The Proceedings of The 3rd International Conference on Sustainable Buildings and Structures",

}

Yan, XY, Huang, H & Zhang, C 2023, Deep Learning-Based Semantic Segmentation and 3D Reconstruction Techniques for Automatic Detection and Localization of Thermal Defects in Building Envelopes. in K Papadikis, C Zhang, S Tang, E Liu & L Di Sarno (eds), Towards a Carbon Neutral Future - The Proceedings of The 3rd International Conference on Sustainable Buildings and Structures. Lecture Notes in Civil Engineering, vol. 393, Springer Science and Business Media Deutschland GmbH, pp. 467-478, 3rd International Conference on Sustainable Buildings and Structures, ICSBS 2023, Suzhou, China, 17/08/23. https://doi.org/10.1007/978-981-99-7965-3_40

Deep Learning-Based Semantic Segmentation and 3D Reconstruction Techniques for Automatic Detection and Localization of Thermal Defects in Building Envelopes. / Yan, X. Y.; Huang, H.; Zhang, C.
Towards a Carbon Neutral Future - The Proceedings of The 3rd International Conference on Sustainable Buildings and Structures. ed. / Konstantinos Papadikis; Cheng Zhang; Shu Tang; Engui Liu; Luigi Di Sarno. Springer Science and Business Media Deutschland GmbH, 2023. p. 467-478 (Lecture Notes in Civil Engineering; Vol. 393).

Research output: Chapter in Book or Report/Conference proceeding › Conference Proceeding › peer-review

TY - GEN

T1 - Deep Learning-Based Semantic Segmentation and 3D Reconstruction Techniques for Automatic Detection and Localization of Thermal Defects in Building Envelopes

AU - Yan, X. Y.

AU - Huang, H.

AU - Zhang, C.

N1 - Publisher Copyright: © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

PY - 2023/8

Y1 - 2023/8

N2 - Building age and extreme weather can cause thermal defects in the building envelope. Failure to inspect and fix these defects can threaten safety, increase energy consumption, and negatively impact the environment. Infrared thermal imaging (IRT) is a popular, non-destructive technique for building diagnostics due to its safety, practicality, and energy efficiency. However, manual IRT detection is time-consuming and imprecise. Therefore, this paper proposes a framework for automatically identifying and localising thermal defects in building envelopes. The outcomes of this study not only offer direction for categorising thermal defects in buildings but also provide a practical approach for automatically detecting and locating them.

AB - Building age and extreme weather can cause thermal defects in the building envelope. Failure to inspect and fix these defects can threaten safety, increase energy consumption, and negatively impact the environment. Infrared thermal imaging (IRT) is a popular, non-destructive technique for building diagnostics due to its safety, practicality, and energy efficiency. However, manual IRT detection is time-consuming and imprecise. Therefore, this paper proposes a framework for automatically identifying and localising thermal defects in building envelopes. The outcomes of this study not only offer direction for categorising thermal defects in buildings but also provide a practical approach for automatically detecting and locating them.

KW - 3D reconstruction techniques

KW - Automatic detection

KW - Building envelopes

KW - Deep learning

UR - https://www.scopus.com/pages/publications/85189563582

U2 - 10.1007/978-981-99-7965-3_40

DO - 10.1007/978-981-99-7965-3_40

M3 - Conference Proceeding

AN - SCOPUS:85189563582

SN - 9789819979646

T3 - Lecture Notes in Civil Engineering

SP - 467

EP - 478

BT - Towards a Carbon Neutral Future - The Proceedings of The 3rd International Conference on Sustainable Buildings and Structures

A2 - Papadikis, Konstantinos

A2 - Zhang, Cheng

A2 - Tang, Shu

A2 - Liu, Engui

A2 - Di Sarno, Luigi

PB - Springer Science and Business Media Deutschland GmbH

T2 - 3rd International Conference on Sustainable Buildings and Structures, ICSBS 2023

Y2 - 17 August 2023 through 20 August 2023

ER -

Yan XY, Huang H, Zhang C. Deep Learning-Based Semantic Segmentation and 3D Reconstruction Techniques for Automatic Detection and Localization of Thermal Defects in Building Envelopes. In Papadikis K, Zhang C, Tang S, Liu E, Di Sarno L, editors, Towards a Carbon Neutral Future - The Proceedings of The 3rd International Conference on Sustainable Buildings and Structures. Springer Science and Business Media Deutschland GmbH. 2023. p. 467-478. (Lecture Notes in Civil Engineering). doi: 10.1007/978-981-99-7965-3_40

Deep Learning-Based Semantic Segmentation and 3D Reconstruction Techniques for Automatic Detection and Localization of Thermal Defects in Building Envelopes

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this