VBuilt : Volume-based automatic building extraction for as-built point clouds

M. K. Masood; A. Pushkar; O. Seppänen; V. Singh; A. Aikala

doi:10.22260/ISARC2019/0161

VBuilt : Volume-based automatic building extraction for as-built point clouds

M. K. Masood, A. Pushkar, O. Seppänen, V. Singh, A. Aikala

Carnegie Mellon University

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceedings › Scientific › peer-review

207 Downloads (Pure)

Abstract

Monitoring the progress of a large construction site manually is a challenging task for managers. By collecting visual data of the site, many monitoring tasks can be automated using machine vision techniques. In this work, we study a new method of collecting site data, which is through crane camera images used to create 3D point clouds. The technology is cost-effective and enables automatic capturing and transmission of on-site data. To automatically extract buildings from the as-built point clouds, we present VBUILT, which uses 3D convex hull volumes to identify building clusters. Experimental results on 40 point clouds collected over four months on a large construction site show that the proposed algorithm can identify building clusters with 100% accuracy.

Original language	English
Title of host publication	Automation and robotics in construction. International symposium
Editors	M. Al-Hussein
Publisher	International Association on Automation and Robotics in Construction (IAARC)
Pages	1202-1209
Number of pages	8
ISBN (Electronic)	978-952-69524-0-6
DOIs	https://doi.org/10.22260/ISARC2019/0161
Publication status	Published - 1 Jan 2019
MoE publication type	A4 Conference publication
Event	International Symposium on Automation and Robotics in Construction - Banff, Canada Duration: 21 May 2019 → 24 May 2019 Conference number: 36

Conference

Conference	International Symposium on Automation and Robotics in Construction
Abbreviated title	ISARC
Country/Territory	Canada
City	Banff
Period	21/05/2019 → 24/05/2019

Keywords

Building extraction
Convex hull
Crane cameras
Progress monitoring

Access to Document

10.22260/ISARC2019/0161

VBUILT_CameraReadyManuscript_ISARC2019Accepted author manuscript, 625 KB
ISARC_2019_Paper_235Final published version, 890 KB

https://www.iaarc.org/publications/2019_proceedings_of_the_36th_isarc/vbuilt-volume_based_automatic_building_extraction_for_as_built_point_clouds.html

Cite this

Masood, M. K., Pushkar, A., Seppänen, O., Singh, V., & Aikala, A. (2019). VBuilt : Volume-based automatic building extraction for as-built point clouds. In M. Al-Hussein (Ed.), Automation and robotics in construction. International symposium (pp. 1202-1209). International Association on Automation and Robotics in Construction (IAARC). https://doi.org/10.22260/ISARC2019/0161

@inproceedings{22387dddb13e414faa5a21d22f4497a2,

title = "VBuilt : Volume-based automatic building extraction for as-built point clouds",

abstract = "Monitoring the progress of a large construction site manually is a challenging task for managers. By collecting visual data of the site, many monitoring tasks can be automated using machine vision techniques. In this work, we study a new method of collecting site data, which is through crane camera images used to create 3D point clouds. The technology is cost-effective and enables automatic capturing and transmission of on-site data. To automatically extract buildings from the as-built point clouds, we present VBUILT, which uses 3D convex hull volumes to identify building clusters. Experimental results on 40 point clouds collected over four months on a large construction site show that the proposed algorithm can identify building clusters with 100% accuracy.",

keywords = "Building extraction, Convex hull, Crane cameras, Progress monitoring",

author = "Masood, {M. K.} and A. Pushkar and O. Sepp{\"a}nen and V. Singh and A. Aikala",

year = "2019",

month = jan,

day = "1",

doi = "10.22260/ISARC2019/0161",

language = "English",

pages = "1202--1209",

editor = "M. Al-Hussein",

booktitle = "Automation and robotics in construction. International symposium",

publisher = "International Association on Automation and Robotics in Construction (IAARC)",

address = "Finland",

note = "International Symposium on Automation and Robotics in Construction, ISARC ; Conference date: 21-05-2019 Through 24-05-2019",

}

Masood, MK, Pushkar, A, Seppänen, O, Singh, V & Aikala, A 2019, VBuilt : Volume-based automatic building extraction for as-built point clouds. in M Al-Hussein (ed.), Automation and robotics in construction. International symposium. International Association on Automation and Robotics in Construction (IAARC), pp. 1202-1209, International Symposium on Automation and Robotics in Construction, Banff, Alberta, Canada, 21/05/2019. https://doi.org/10.22260/ISARC2019/0161

VBuilt : Volume-based automatic building extraction for as-built point clouds. / Masood, M. K.; Pushkar, A.; Seppänen, O. et al.
Automation and robotics in construction. International symposium. ed. / M. Al-Hussein. International Association on Automation and Robotics in Construction (IAARC), 2019. p. 1202-1209.

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceedings › Scientific › peer-review

TY - GEN

T1 - VBuilt : Volume-based automatic building extraction for as-built point clouds

AU - Masood, M. K.

AU - Pushkar, A.

AU - Seppänen, O.

AU - Singh, V.

AU - Aikala, A.

N1 - Conference code: 36

PY - 2019/1/1

Y1 - 2019/1/1

N2 - Monitoring the progress of a large construction site manually is a challenging task for managers. By collecting visual data of the site, many monitoring tasks can be automated using machine vision techniques. In this work, we study a new method of collecting site data, which is through crane camera images used to create 3D point clouds. The technology is cost-effective and enables automatic capturing and transmission of on-site data. To automatically extract buildings from the as-built point clouds, we present VBUILT, which uses 3D convex hull volumes to identify building clusters. Experimental results on 40 point clouds collected over four months on a large construction site show that the proposed algorithm can identify building clusters with 100% accuracy.

AB - Monitoring the progress of a large construction site manually is a challenging task for managers. By collecting visual data of the site, many monitoring tasks can be automated using machine vision techniques. In this work, we study a new method of collecting site data, which is through crane camera images used to create 3D point clouds. The technology is cost-effective and enables automatic capturing and transmission of on-site data. To automatically extract buildings from the as-built point clouds, we present VBUILT, which uses 3D convex hull volumes to identify building clusters. Experimental results on 40 point clouds collected over four months on a large construction site show that the proposed algorithm can identify building clusters with 100% accuracy.

KW - Building extraction

KW - Convex hull

KW - Crane cameras

KW - Progress monitoring

UR - http://www.scopus.com/inward/record.url?scp=85071427752&partnerID=8YFLogxK

UR - https://doi.org/10.22260/ISARC2019/0010

U2 - 10.22260/ISARC2019/0161

DO - 10.22260/ISARC2019/0161

M3 - Conference article in proceedings

SP - 1202

EP - 1209

BT - Automation and robotics in construction. International symposium

A2 - Al-Hussein, M.

PB - International Association on Automation and Robotics in Construction (IAARC)

T2 - International Symposium on Automation and Robotics in Construction

Y2 - 21 May 2019 through 24 May 2019

ER -

VBuilt : Volume-based automatic building extraction for as-built point clouds

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Reality Capture for Construction Management

Cite this

VBuilt : Volume-based automatic building extraction for as-built point clouds

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Projects

Reality Capture for Construction Management

Cite this