Study on image diagnosis of timber houses damaged by earthquake using deep learning

Hiroyuki Chida; Noriyuki Takahashi

doi:10.3130/AIJS.85.529

Study on image diagnosis of timber houses damaged by earthquake using deep learning

Hiroyuki Chida, Noriyuki Takahashi

ENG - Architecture and Building Science

Research output: Contribution to journal › Article › peer-review

1 Citation (Scopus)

Abstract

The image processing (with deep learning, semantic segmentation, hough transformation, edge extraction) for the image diagnosis of wooden houses damaged by earthquake was studied and verified. As a result, the following 3 aspects were revealed. 1. The usefulness of chroma keying for creating image database for deep learning instead of real damaged images 2. The potential of the image diagnosis for not only qualitative damage assessment of timber houses, but also quantitative one 3. The possibility of installation of drift ratio estimation into the image diagnosis.

Original language	English
Pages (from-to)	529-538
Number of pages	10
Journal	Journal of Structural and Construction Engineering
Volume	85
Issue number	770
DOIs	https://doi.org/10.3130/AIJS.85.529
Publication status	Published - 2020 Apr

Keywords

Damage assessment
Deep learning
Image diagnosis
Image processing
Timber house

ASJC Scopus subject areas

Architecture
Building and Construction

Access to Document

10.3130/AIJS.85.529

Fingerprint Dive into the research topics of 'Study on image diagnosis of timber houses damaged by earthquake using deep learning'. Together they form a unique fingerprint.

Cite this

@article{9525e2689f65469cae3eb1cdbf747a93,

title = "Study on image diagnosis of timber houses damaged by earthquake using deep learning",

abstract = "The image processing (with deep learning, semantic segmentation, hough transformation, edge extraction) for the image diagnosis of wooden houses damaged by earthquake was studied and verified. As a result, the following 3 aspects were revealed. 1. The usefulness of chroma keying for creating image database for deep learning instead of real damaged images 2. The potential of the image diagnosis for not only qualitative damage assessment of timber houses, but also quantitative one 3. The possibility of installation of drift ratio estimation into the image diagnosis.",

keywords = "Damage assessment, Deep learning, Image diagnosis, Image processing, Timber house",

author = "Hiroyuki Chida and Noriyuki Takahashi",

year = "2020",

month = apr,

doi = "10.3130/AIJS.85.529",

language = "English",

volume = "85",

pages = "529--538",

journal = "Journal of Structural and Construction Engineering",

issn = "1340-4202",

publisher = "Architectural Institute of Japan",

number = "770",

}

TY - JOUR

T1 - Study on image diagnosis of timber houses damaged by earthquake using deep learning

AU - Chida, Hiroyuki

AU - Takahashi, Noriyuki

PY - 2020/4

Y1 - 2020/4

N2 - The image processing (with deep learning, semantic segmentation, hough transformation, edge extraction) for the image diagnosis of wooden houses damaged by earthquake was studied and verified. As a result, the following 3 aspects were revealed. 1. The usefulness of chroma keying for creating image database for deep learning instead of real damaged images 2. The potential of the image diagnosis for not only qualitative damage assessment of timber houses, but also quantitative one 3. The possibility of installation of drift ratio estimation into the image diagnosis.

AB - The image processing (with deep learning, semantic segmentation, hough transformation, edge extraction) for the image diagnosis of wooden houses damaged by earthquake was studied and verified. As a result, the following 3 aspects were revealed. 1. The usefulness of chroma keying for creating image database for deep learning instead of real damaged images 2. The potential of the image diagnosis for not only qualitative damage assessment of timber houses, but also quantitative one 3. The possibility of installation of drift ratio estimation into the image diagnosis.

KW - Damage assessment

KW - Deep learning

KW - Image diagnosis

KW - Image processing

KW - Timber house

UR - http://www.scopus.com/inward/record.url?scp=85085639156&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85085639156&partnerID=8YFLogxK

U2 - 10.3130/AIJS.85.529

DO - 10.3130/AIJS.85.529

M3 - Article

AN - SCOPUS:85085639156

VL - 85

SP - 529

EP - 538

JO - Journal of Structural and Construction Engineering

JF - Journal of Structural and Construction Engineering

SN - 1340-4202

IS - 770

ER -

Study on image diagnosis of timber houses damaged by earthquake using deep learning

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Cite this