Recognizing and Classifying Unknown Object in BIM Using 2D CNN

Jinsung Kim, Jaeyeol Song, Jin Kook Lee

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

This paper aims to propose an approach to automated classifying building element instance in BIM using deep learning-based 3D object classification algorithm. Recently, studies related to checking or validating engine of BIM object for ensuring data integrity of BIM instances are getting attention. As a part of this research, this paper train recognition models that are targeted at basic building element and interior element using 3D object recognition technique that uses images of objects as inputs. Object recognition is executed in two stages; (1) class of object (e.g. wall, window, seating furniture, toilet fixture and etc.), (2) sub-type of specific classes (e.g. Toilet or Urinal). Using the trained models, BIM plug-in prototype is developed and the performance of this AI-based approach with test BIM model is checked. We expect this recognition approach to help ensure the integrity of BIM data and contribute to the practical use of BIM.

Original languageEnglish
Title of host publicationComputer-Aided Architectural Design. “Hello, Culture” - 18th International Conference, CAAD Futures 2019, Selected Papers
EditorsJi-Hyun Lee
PublisherSpringer Verlag
Pages47-57
Number of pages11
ISBN (Print)9789811384097
DOIs
Publication statusPublished - 2019 Jan 1
Event18th International Conference on Computer-Aided Architectural Design Futures, CAAD Futures 2019 - Daejeon, Korea, Republic of
Duration: 2019 Jun 262019 Jun 28

Publication series

NameCommunications in Computer and Information Science
Volume1028
ISSN (Print)1865-0929
ISSN (Electronic)1865-0937

Conference

Conference18th International Conference on Computer-Aided Architectural Design Futures, CAAD Futures 2019
CountryKorea, Republic of
CityDaejeon
Period19/6/2619/6/28

Fingerprint

Object recognition
Unknown
3D Object Recognition
Object Classification
Data Integrity
Object Recognition
Plug-in
Classification Algorithm
Integrity
Interior
Engine
Model
Prototype
Engines
Object
Class
Learning
Deep learning

All Science Journal Classification (ASJC) codes

  • Computer Science(all)
  • Mathematics(all)

Cite this

Kim, J., Song, J., & Lee, J. K. (2019). Recognizing and Classifying Unknown Object in BIM Using 2D CNN. In J-H. Lee (Ed.), Computer-Aided Architectural Design. “Hello, Culture” - 18th International Conference, CAAD Futures 2019, Selected Papers (pp. 47-57). (Communications in Computer and Information Science; Vol. 1028). Springer Verlag. https://doi.org/10.1007/978-981-13-8410-3_4
Kim, Jinsung ; Song, Jaeyeol ; Lee, Jin Kook. / Recognizing and Classifying Unknown Object in BIM Using 2D CNN. Computer-Aided Architectural Design. “Hello, Culture” - 18th International Conference, CAAD Futures 2019, Selected Papers. editor / Ji-Hyun Lee. Springer Verlag, 2019. pp. 47-57 (Communications in Computer and Information Science).
@inproceedings{3c2fd6023d304a2f95dbaa09dbc8d095,
title = "Recognizing and Classifying Unknown Object in BIM Using 2D CNN",
abstract = "This paper aims to propose an approach to automated classifying building element instance in BIM using deep learning-based 3D object classification algorithm. Recently, studies related to checking or validating engine of BIM object for ensuring data integrity of BIM instances are getting attention. As a part of this research, this paper train recognition models that are targeted at basic building element and interior element using 3D object recognition technique that uses images of objects as inputs. Object recognition is executed in two stages; (1) class of object (e.g. wall, window, seating furniture, toilet fixture and etc.), (2) sub-type of specific classes (e.g. Toilet or Urinal). Using the trained models, BIM plug-in prototype is developed and the performance of this AI-based approach with test BIM model is checked. We expect this recognition approach to help ensure the integrity of BIM data and contribute to the practical use of BIM.",
author = "Jinsung Kim and Jaeyeol Song and Lee, {Jin Kook}",
year = "2019",
month = "1",
day = "1",
doi = "10.1007/978-981-13-8410-3_4",
language = "English",
isbn = "9789811384097",
series = "Communications in Computer and Information Science",
publisher = "Springer Verlag",
pages = "47--57",
editor = "Ji-Hyun Lee",
booktitle = "Computer-Aided Architectural Design. “Hello, Culture” - 18th International Conference, CAAD Futures 2019, Selected Papers",
address = "Germany",

}

Kim, J, Song, J & Lee, JK 2019, Recognizing and Classifying Unknown Object in BIM Using 2D CNN. in J-H Lee (ed.), Computer-Aided Architectural Design. “Hello, Culture” - 18th International Conference, CAAD Futures 2019, Selected Papers. Communications in Computer and Information Science, vol. 1028, Springer Verlag, pp. 47-57, 18th International Conference on Computer-Aided Architectural Design Futures, CAAD Futures 2019, Daejeon, Korea, Republic of, 19/6/26. https://doi.org/10.1007/978-981-13-8410-3_4

Recognizing and Classifying Unknown Object in BIM Using 2D CNN. / Kim, Jinsung; Song, Jaeyeol; Lee, Jin Kook.

Computer-Aided Architectural Design. “Hello, Culture” - 18th International Conference, CAAD Futures 2019, Selected Papers. ed. / Ji-Hyun Lee. Springer Verlag, 2019. p. 47-57 (Communications in Computer and Information Science; Vol. 1028).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Recognizing and Classifying Unknown Object in BIM Using 2D CNN

AU - Kim, Jinsung

AU - Song, Jaeyeol

AU - Lee, Jin Kook

PY - 2019/1/1

Y1 - 2019/1/1

N2 - This paper aims to propose an approach to automated classifying building element instance in BIM using deep learning-based 3D object classification algorithm. Recently, studies related to checking or validating engine of BIM object for ensuring data integrity of BIM instances are getting attention. As a part of this research, this paper train recognition models that are targeted at basic building element and interior element using 3D object recognition technique that uses images of objects as inputs. Object recognition is executed in two stages; (1) class of object (e.g. wall, window, seating furniture, toilet fixture and etc.), (2) sub-type of specific classes (e.g. Toilet or Urinal). Using the trained models, BIM plug-in prototype is developed and the performance of this AI-based approach with test BIM model is checked. We expect this recognition approach to help ensure the integrity of BIM data and contribute to the practical use of BIM.

AB - This paper aims to propose an approach to automated classifying building element instance in BIM using deep learning-based 3D object classification algorithm. Recently, studies related to checking or validating engine of BIM object for ensuring data integrity of BIM instances are getting attention. As a part of this research, this paper train recognition models that are targeted at basic building element and interior element using 3D object recognition technique that uses images of objects as inputs. Object recognition is executed in two stages; (1) class of object (e.g. wall, window, seating furniture, toilet fixture and etc.), (2) sub-type of specific classes (e.g. Toilet or Urinal). Using the trained models, BIM plug-in prototype is developed and the performance of this AI-based approach with test BIM model is checked. We expect this recognition approach to help ensure the integrity of BIM data and contribute to the practical use of BIM.

UR - http://www.scopus.com/inward/record.url?scp=85068241704&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85068241704&partnerID=8YFLogxK

U2 - 10.1007/978-981-13-8410-3_4

DO - 10.1007/978-981-13-8410-3_4

M3 - Conference contribution

AN - SCOPUS:85068241704

SN - 9789811384097

T3 - Communications in Computer and Information Science

SP - 47

EP - 57

BT - Computer-Aided Architectural Design. “Hello, Culture” - 18th International Conference, CAAD Futures 2019, Selected Papers

A2 - Lee, Ji-Hyun

PB - Springer Verlag

ER -

Kim J, Song J, Lee JK. Recognizing and Classifying Unknown Object in BIM Using 2D CNN. In Lee J-H, editor, Computer-Aided Architectural Design. “Hello, Culture” - 18th International Conference, CAAD Futures 2019, Selected Papers. Springer Verlag. 2019. p. 47-57. (Communications in Computer and Information Science). https://doi.org/10.1007/978-981-13-8410-3_4