Automatic building roof segmentation based on PFICA algorithm and morphological filtering from LiDAR point clouds

Saman  Ghaffarian; Salar Ghaffarian; Youssef El merabet; Zineb Samir; Yassine Ruicheck

Automatic building roof segmentation based on PFICA algorithm and morphological filtering from LiDAR point clouds

Saman Ghaffarian
, Salar Ghaffarian
, Youssef El merabet
, Zineb Samir
, Yassine Ruicheck

Faculty of Geo-Information Science and Earth Observation

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

338 Downloads (Pure)

Abstract

In this study, we propose a new approach for segmenting building roofs from Light Detection And Ranging (LiDAR) point clouds. The algorithm takes advantage of height gradients to automatically seed Purposive FastICA (PFICA) algorithm. The PFICA algorithm with a novel seeding method is implemented to detect ridge points from point clouds of building roofs. Then, 2D coordinates are used to rasterize the detected points. Eventually, morphological filtering and thinning algorithms are used to extract inner and external boundaries of the building roofs. In addition, the potential of PFICA algorithm in clustering 3D point clouds are discussed. The results obtained on a set of LiDAR point clouds demonstrate

Original language	English
Title of host publication	37th Asian Conference on Remote Sensing (ACRS 2016)
Subtitle of host publication	Promoting spatial data infrastructure for sustainable economic development, 17-21 October 2016, Colombo, Sri Lanka
Number of pages	8
Publication status	Published - 2016
Event	37th Asian Conference on Remote Sensing, ACRS 2016: Spatial Data Infrastructure for Sustainable Development - Colombo, Sri Lanka Duration: 17 Oct 2016 → 21 Oct 2016 Conference number: 37 http://www.acrs2016.org/

Conference

Conference	37th Asian Conference on Remote Sensing, ACRS 2016
Abbreviated title	ACRS
Country/Territory	Sri Lanka
City	Colombo
Period	17/10/16 → 21/10/16
Internet address	http://www.acrs2016.org/

Access to Document

Ghaffarian2016automaticFinal published version, 349 KB

Cite this

@inproceedings{a60789e09ebc470c9bc0e90f247070b3,

title = "Automatic building roof segmentation based on PFICA algorithm and morphological filtering from LiDAR point clouds",

abstract = "In this study, we propose a new approach for segmenting building roofs from Light Detection And Ranging (LiDAR) point clouds. The algorithm takes advantage of height gradients to automatically seed Purposive FastICA (PFICA) algorithm. The PFICA algorithm with a novel seeding method is implemented to detect ridge points from point clouds of building roofs. Then, 2D coordinates are used to rasterize the detected points. Eventually, morphological filtering and thinning algorithms are used to extract inner and external boundaries of the building roofs. In addition, the potential of PFICA algorithm in clustering 3D point clouds are discussed. The results obtained on a set of LiDAR point clouds demonstrate",

author = "Saman Ghaffarian and Salar Ghaffarian and \{El merabet\}, Youssef and Zineb Samir and Yassine Ruicheck",

year = "2016",

language = "English",

isbn = "978-1-5108-3461-3",

booktitle = "37th Asian Conference on Remote Sensing (ACRS 2016)",

note = "37th Asian Conference on Remote Sensing, ACRS 2016 : Spatial Data Infrastructure for Sustainable Development, ACRS ; Conference date: 17-10-2016 Through 21-10-2016",

url = "http://www.acrs2016.org/",

}

Ghaffarian, S, Ghaffarian, S, El merabet, Y, Samir, Z & Ruicheck, Y 2016, Automatic building roof segmentation based on PFICA algorithm and morphological filtering from LiDAR point clouds. in 37th Asian Conference on Remote Sensing (ACRS 2016): Promoting spatial data infrastructure for sustainable economic development, 17-21 October 2016, Colombo, Sri Lanka. 37th Asian Conference on Remote Sensing, ACRS 2016, Colombo, Sri Lanka, 17/10/16.

Automatic building roof segmentation based on PFICA algorithm and morphological filtering from LiDAR point clouds. / Ghaffarian, Saman ; Ghaffarian, Salar; El merabet, Youssef et al.
37th Asian Conference on Remote Sensing (ACRS 2016): Promoting spatial data infrastructure for sustainable economic development, 17-21 October 2016, Colombo, Sri Lanka. 2016.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

TY - GEN

T1 - Automatic building roof segmentation based on PFICA algorithm and morphological filtering from LiDAR point clouds

AU - Ghaffarian, Saman

AU - Ghaffarian, Salar

AU - El merabet, Youssef

AU - Samir, Zineb

AU - Ruicheck, Yassine

N1 - Conference code: 37

PY - 2016

Y1 - 2016

N2 - In this study, we propose a new approach for segmenting building roofs from Light Detection And Ranging (LiDAR) point clouds. The algorithm takes advantage of height gradients to automatically seed Purposive FastICA (PFICA) algorithm. The PFICA algorithm with a novel seeding method is implemented to detect ridge points from point clouds of building roofs. Then, 2D coordinates are used to rasterize the detected points. Eventually, morphological filtering and thinning algorithms are used to extract inner and external boundaries of the building roofs. In addition, the potential of PFICA algorithm in clustering 3D point clouds are discussed. The results obtained on a set of LiDAR point clouds demonstrate

AB - In this study, we propose a new approach for segmenting building roofs from Light Detection And Ranging (LiDAR) point clouds. The algorithm takes advantage of height gradients to automatically seed Purposive FastICA (PFICA) algorithm. The PFICA algorithm with a novel seeding method is implemented to detect ridge points from point clouds of building roofs. Then, 2D coordinates are used to rasterize the detected points. Eventually, morphological filtering and thinning algorithms are used to extract inner and external boundaries of the building roofs. In addition, the potential of PFICA algorithm in clustering 3D point clouds are discussed. The results obtained on a set of LiDAR point clouds demonstrate

M3 - Conference contribution

SN - 978-1-5108-3461-3

BT - 37th Asian Conference on Remote Sensing (ACRS 2016)

T2 - 37th Asian Conference on Remote Sensing, ACRS 2016

Y2 - 17 October 2016 through 21 October 2016

ER -

Automatic building roof segmentation based on PFICA algorithm and morphological filtering from LiDAR point clouds

Abstract

Conference

Access to Document

Fingerprint

Cite this