Automatic segmentation of LiDAR point cloud data at different height levels for 3D building extraction

S. M. Abdullah; Mohammad Awrangjeb; Guojun Lu

doi:10.1109/ICMEW.2014.6890541

Automatic segmentation of LiDAR point cloud data at different height levels for 3D building extraction

S. M. Abdullah, Mohammad Awrangjeb, Guojun Lu

Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › Research

11 Citations (Scopus)

Abstract

This paper presents a new LiDAR segmentation technique for automatic building detection and roof plane extraction. First, it uses a height threshold, based on the digital elevation model it divides the LiDAR point cloud into 'ground' and 'non-ground' points. Then, starting from the maximum LiDAR height, and decreasing the height at each iteration, it looks for points to form planar roof segments. At each height level, it clusters the points based on the distance and finds straight lines using the points. The nearest coplanar point to the midpoint of each line is used as a seed point and the plane is grown in a region growing fashion. Finally, a rule-based procedure is followed to remove planar segments in trees. The experimental results show that the proposed technique offers a high building detection and roof plane extraction rates while compared to other recently proposed techniques.

Original language	English
Title of host publication	2014 IEEE International Conference on Multimedia and Expo Workshops (ICMEW 2014)
Subtitle of host publication	Chengdu, China, 14-18 July 2014 [Proceedings]
Publisher	IEEE, Institute of Electrical and Electronics Engineers
Pages	70-75
Number of pages	6
ISBN (Electronic)	9781479947171
ISBN (Print)	9781479947164
DOIs	https://doi.org/10.1109/ICMEW.2014.6890541
Publication status	Published - 3 Sept 2014
Event	IEEE International Workshop on Hot Topics in 3D 2014 - Chengdu, China Duration: 14 Jul 2014 → 14 Jul 2014 Conference number: 5th https://web.archive.org/web/20141107061013/http://hot3d.org:80/ http://www.ieee-icme.org/icme2014/www.icme2014.org/workshops.html (listing of all the workshops held at ICME 2014)

Workshop

Workshop	IEEE International Workshop on Hot Topics in 3D 2014
Abbreviated title	Hot3D 2014
Country/Territory	China
City	Chengdu
Period	14/07/14 → 14/07/14
Other	Held in conjunction with ICME'14 (14 workshops)
Internet address	https://web.archive.org/web/20141107061013/http://hot3d.org:80/ http://www.ieee-icme.org/icme2014/www.icme2014.org/workshops.html (listing of all the workshops held at ICME 2014)

Keywords

Building detection
height levels
LiDAR
roof plane extraction

Access to Document

10.1109/ICMEW.2014.6890541

Cite this

Abdullah, S. M., Awrangjeb, M., & Lu, G. (2014). Automatic segmentation of LiDAR point cloud data at different height levels for 3D building extraction. In 2014 IEEE International Conference on Multimedia and Expo Workshops (ICMEW 2014): Chengdu, China, 14-18 July 2014 [Proceedings] (pp. 70-75). Article 6890541 IEEE, Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/ICMEW.2014.6890541

@inproceedings{8913ac3cad0745b38eb687b6a42008f4,

title = "Automatic segmentation of LiDAR point cloud data at different height levels for 3D building extraction",

abstract = "This paper presents a new LiDAR segmentation technique for automatic building detection and roof plane extraction. First, it uses a height threshold, based on the digital elevation model it divides the LiDAR point cloud into 'ground' and 'non-ground' points. Then, starting from the maximum LiDAR height, and decreasing the height at each iteration, it looks for points to form planar roof segments. At each height level, it clusters the points based on the distance and finds straight lines using the points. The nearest coplanar point to the midpoint of each line is used as a seed point and the plane is grown in a region growing fashion. Finally, a rule-based procedure is followed to remove planar segments in trees. The experimental results show that the proposed technique offers a high building detection and roof plane extraction rates while compared to other recently proposed techniques.",

keywords = "Building detection, height levels, LiDAR, roof plane extraction",

author = "Abdullah, {S. M.} and Mohammad Awrangjeb and Guojun Lu",

year = "2014",

month = sep,

day = "3",

doi = "10.1109/ICMEW.2014.6890541",

language = "English",

isbn = "9781479947164",

pages = "70--75",

booktitle = "2014 IEEE International Conference on Multimedia and Expo Workshops (ICMEW 2014)",

publisher = "IEEE, Institute of Electrical and Electronics Engineers",

address = "United States of America",

note = "IEEE International Workshop on Hot Topics in 3D 2014, Hot3D 2014 ; Conference date: 14-07-2014 Through 14-07-2014",

url = "https://web.archive.org/web/20141107061013/http://hot3d.org:80/, http://www.ieee-icme.org/icme2014/www.icme2014.org/workshops.html",

}

Abdullah, SM, Awrangjeb, M & Lu, G 2014, Automatic segmentation of LiDAR point cloud data at different height levels for 3D building extraction. in 2014 IEEE International Conference on Multimedia and Expo Workshops (ICMEW 2014): Chengdu, China, 14-18 July 2014 [Proceedings]., 6890541, IEEE, Institute of Electrical and Electronics Engineers, pp. 70-75, IEEE International Workshop on Hot Topics in 3D 2014, Chengdu, China, 14/07/14. https://doi.org/10.1109/ICMEW.2014.6890541

Automatic segmentation of LiDAR point cloud data at different height levels for 3D building extraction. / Abdullah, S. M.; Awrangjeb, Mohammad; Lu, Guojun.
2014 IEEE International Conference on Multimedia and Expo Workshops (ICMEW 2014): Chengdu, China, 14-18 July 2014 [Proceedings]. IEEE, Institute of Electrical and Electronics Engineers, 2014. p. 70-75 6890541.

Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › Research

TY - GEN

T1 - Automatic segmentation of LiDAR point cloud data at different height levels for 3D building extraction

AU - Abdullah, S. M.

AU - Awrangjeb, Mohammad

AU - Lu, Guojun

N1 - Conference code: 5th

PY - 2014/9/3

Y1 - 2014/9/3

N2 - This paper presents a new LiDAR segmentation technique for automatic building detection and roof plane extraction. First, it uses a height threshold, based on the digital elevation model it divides the LiDAR point cloud into 'ground' and 'non-ground' points. Then, starting from the maximum LiDAR height, and decreasing the height at each iteration, it looks for points to form planar roof segments. At each height level, it clusters the points based on the distance and finds straight lines using the points. The nearest coplanar point to the midpoint of each line is used as a seed point and the plane is grown in a region growing fashion. Finally, a rule-based procedure is followed to remove planar segments in trees. The experimental results show that the proposed technique offers a high building detection and roof plane extraction rates while compared to other recently proposed techniques.

AB - This paper presents a new LiDAR segmentation technique for automatic building detection and roof plane extraction. First, it uses a height threshold, based on the digital elevation model it divides the LiDAR point cloud into 'ground' and 'non-ground' points. Then, starting from the maximum LiDAR height, and decreasing the height at each iteration, it looks for points to form planar roof segments. At each height level, it clusters the points based on the distance and finds straight lines using the points. The nearest coplanar point to the midpoint of each line is used as a seed point and the plane is grown in a region growing fashion. Finally, a rule-based procedure is followed to remove planar segments in trees. The experimental results show that the proposed technique offers a high building detection and roof plane extraction rates while compared to other recently proposed techniques.

KW - Building detection

KW - height levels

KW - LiDAR

KW - roof plane extraction

UR - http://www.scopus.com/inward/record.url?scp=84937144342&partnerID=8YFLogxK

U2 - 10.1109/ICMEW.2014.6890541

DO - 10.1109/ICMEW.2014.6890541

M3 - Conference Paper

AN - SCOPUS:84937144342

SN - 9781479947164

SP - 70

EP - 75

BT - 2014 IEEE International Conference on Multimedia and Expo Workshops (ICMEW 2014)

PB - IEEE, Institute of Electrical and Electronics Engineers

T2 - IEEE International Workshop on Hot Topics in 3D 2014

Y2 - 14 July 2014 through 14 July 2014

ER -

Abdullah SM, Awrangjeb M, Lu G. Automatic segmentation of LiDAR point cloud data at different height levels for 3D building extraction. In 2014 IEEE International Conference on Multimedia and Expo Workshops (ICMEW 2014): Chengdu, China, 14-18 July 2014 [Proceedings]. IEEE, Institute of Electrical and Electronics Engineers. 2014. p. 70-75. 6890541 doi: 10.1109/ICMEW.2014.6890541

Automatic segmentation of LiDAR point cloud data at different height levels for 3D building extraction

Abstract

Workshop

Keywords

Access to Document

Other files and links

Building change detection and map update using multispectral imagery and height data

Cite this

Automatic segmentation of LiDAR point cloud data at different height levels for 3D building extraction

Abstract

Workshop

Keywords

Access to Document

Other files and links

Projects

Building change detection and map update using multispectral imagery and height data

Cite this