Building Model Object Classification for Semantic Enrichment Using Geometric Features and Pairwise Spatial Relations

Ling Ma, Rafael Sacks, Uri Kattel

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

Abstract

Semantic enrichment is a process of supplementing/correcting information in a poorly prepared BIM model. Object classifications are essential information, but are commonly missing or incorrectly represented when transferring a BIM model or creating a model using tools customized for other domains in design. Automated compilation of 'as-is' BIM models from point cloud data also requires object classification, as well as 3D reconstruction. We present a systematic approach to classifying objects in a BIM model, for use in future semantic enrichment systems. Previous work on object classification in BIM model enrichment was restricted by its limited ability to accurately interpret geometric and spatial features and by the constraints of Boolean logic rules and the rule compilation process. To address these issues, we propose a procedure for establishing a knowledge base that associates objects with their features and relationships, and a matching algorithm based on a similarity measurement between the knowledge base and facts. An implementation on a synthetic bridge model shows that whereas some objects can be classified by shape features alone, most objects require the use of spatial relations for unique classification. Spatial context is more likely to uniquely identify an object than shape features are.
Original languageEnglish
Title of host publicationProceedings of the 2017 Joint Conference on Computing in Construction (JC3)
EditorsFrédéric Bosché, Ioannis Brilakis, Rafael Sacks
Place of PublicationEdinburgh
PublisherHeriot-Watt University
Pages373-380
Number of pages8
Volume1
ISBN (Electronic)9780956595164
Publication statusPublished - 2017

Fingerprint

Semantics

Cite this

Ma, L., Sacks, R., & Kattel, U. (2017). Building Model Object Classification for Semantic Enrichment Using Geometric Features and Pairwise Spatial Relations. In F. Bosché, I. Brilakis, & R. Sacks (Eds.), Proceedings of the 2017 Joint Conference on Computing in Construction (JC3) (Vol. 1, pp. 373-380). Edinburgh: Heriot-Watt University.
Ma, Ling ; Sacks, Rafael ; Kattel, Uri. / Building Model Object Classification for Semantic Enrichment Using Geometric Features and Pairwise Spatial Relations. Proceedings of the 2017 Joint Conference on Computing in Construction (JC3). editor / Frédéric Bosché ; Ioannis Brilakis ; Rafael Sacks. Vol. 1 Edinburgh : Heriot-Watt University, 2017. pp. 373-380
@inproceedings{e791317ac41f46d791aad55efc910cd5,
title = "Building Model Object Classification for Semantic Enrichment Using Geometric Features and Pairwise Spatial Relations",
abstract = "Semantic enrichment is a process of supplementing/correcting information in a poorly prepared BIM model. Object classifications are essential information, but are commonly missing or incorrectly represented when transferring a BIM model or creating a model using tools customized for other domains in design. Automated compilation of 'as-is' BIM models from point cloud data also requires object classification, as well as 3D reconstruction. We present a systematic approach to classifying objects in a BIM model, for use in future semantic enrichment systems. Previous work on object classification in BIM model enrichment was restricted by its limited ability to accurately interpret geometric and spatial features and by the constraints of Boolean logic rules and the rule compilation process. To address these issues, we propose a procedure for establishing a knowledge base that associates objects with their features and relationships, and a matching algorithm based on a similarity measurement between the knowledge base and facts. An implementation on a synthetic bridge model shows that whereas some objects can be classified by shape features alone, most objects require the use of spatial relations for unique classification. Spatial context is more likely to uniquely identify an object than shape features are.",
keywords = "Building information modellin, Semantic enrichment, Geometric feature, Spatial relation, Object classification",
author = "Ling Ma and Rafael Sacks and Uri Kattel",
note = "No accepted Date HN 27/09/2017",
year = "2017",
language = "English",
volume = "1",
pages = "373--380",
editor = "Fr{\'e}d{\'e}ric Bosch{\'e} and Ioannis Brilakis and Rafael Sacks",
booktitle = "Proceedings of the 2017 Joint Conference on Computing in Construction (JC3)",
publisher = "Heriot-Watt University",

}

Ma, L, Sacks, R & Kattel, U 2017, Building Model Object Classification for Semantic Enrichment Using Geometric Features and Pairwise Spatial Relations. in F Bosché, I Brilakis & R Sacks (eds), Proceedings of the 2017 Joint Conference on Computing in Construction (JC3). vol. 1, Heriot-Watt University, Edinburgh, pp. 373-380.

Building Model Object Classification for Semantic Enrichment Using Geometric Features and Pairwise Spatial Relations. / Ma, Ling; Sacks, Rafael; Kattel, Uri.

Proceedings of the 2017 Joint Conference on Computing in Construction (JC3). ed. / Frédéric Bosché; Ioannis Brilakis; Rafael Sacks. Vol. 1 Edinburgh : Heriot-Watt University, 2017. p. 373-380.

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

TY - GEN

T1 - Building Model Object Classification for Semantic Enrichment Using Geometric Features and Pairwise Spatial Relations

AU - Ma, Ling

AU - Sacks, Rafael

AU - Kattel, Uri

N1 - No accepted Date HN 27/09/2017

PY - 2017

Y1 - 2017

N2 - Semantic enrichment is a process of supplementing/correcting information in a poorly prepared BIM model. Object classifications are essential information, but are commonly missing or incorrectly represented when transferring a BIM model or creating a model using tools customized for other domains in design. Automated compilation of 'as-is' BIM models from point cloud data also requires object classification, as well as 3D reconstruction. We present a systematic approach to classifying objects in a BIM model, for use in future semantic enrichment systems. Previous work on object classification in BIM model enrichment was restricted by its limited ability to accurately interpret geometric and spatial features and by the constraints of Boolean logic rules and the rule compilation process. To address these issues, we propose a procedure for establishing a knowledge base that associates objects with their features and relationships, and a matching algorithm based on a similarity measurement between the knowledge base and facts. An implementation on a synthetic bridge model shows that whereas some objects can be classified by shape features alone, most objects require the use of spatial relations for unique classification. Spatial context is more likely to uniquely identify an object than shape features are.

AB - Semantic enrichment is a process of supplementing/correcting information in a poorly prepared BIM model. Object classifications are essential information, but are commonly missing or incorrectly represented when transferring a BIM model or creating a model using tools customized for other domains in design. Automated compilation of 'as-is' BIM models from point cloud data also requires object classification, as well as 3D reconstruction. We present a systematic approach to classifying objects in a BIM model, for use in future semantic enrichment systems. Previous work on object classification in BIM model enrichment was restricted by its limited ability to accurately interpret geometric and spatial features and by the constraints of Boolean logic rules and the rule compilation process. To address these issues, we propose a procedure for establishing a knowledge base that associates objects with their features and relationships, and a matching algorithm based on a similarity measurement between the knowledge base and facts. An implementation on a synthetic bridge model shows that whereas some objects can be classified by shape features alone, most objects require the use of spatial relations for unique classification. Spatial context is more likely to uniquely identify an object than shape features are.

KW - Building information modellin

KW - Semantic enrichment

KW - Geometric feature

KW - Spatial relation

KW - Object classification

UR - http://www.lc3-2017.com/

M3 - Conference contribution

VL - 1

SP - 373

EP - 380

BT - Proceedings of the 2017 Joint Conference on Computing in Construction (JC3)

A2 - Bosché, Frédéric

A2 - Brilakis, Ioannis

A2 - Sacks, Rafael

PB - Heriot-Watt University

CY - Edinburgh

ER -

Ma L, Sacks R, Kattel U. Building Model Object Classification for Semantic Enrichment Using Geometric Features and Pairwise Spatial Relations. In Bosché F, Brilakis I, Sacks R, editors, Proceedings of the 2017 Joint Conference on Computing in Construction (JC3). Vol. 1. Edinburgh: Heriot-Watt University. 2017. p. 373-380