Parallel processing method for airborne laser scanning data using a PC cluster and a virtual grid

Soo Hee Han, Joon Heo, Hong Gyoo Sohn, Kiyun Yu

Research output: Contribution to journalArticle

26 Citations (Scopus)

Abstract

In this study, a parallel processing method using a PC cluster and a virtual grid is proposed for the fast processing of enormous amounts of airborne laser scanning (ALS) data. The method creates a raster digital surface model (DSM) by interpolating point data with inverse distance weighting (IDW), and produces a digital terrain model (DTM) by local minimum filtering of the DSM. To make a consistent comparison of performance between sequential and parallel processing approaches, the means of dealing with boundary data and of selecting interpolation centers were controlled for each processing node in parallel approach. To test the speedup, efficiency and linearity of the proposed algorithm, actual ALS data up to 134 million points were processed with a PC cluster consisting of one master node and eight slave nodes. The results showed that parallel processing provides better performance when the computational overhead, the number of processors, and the data size become large. It was verified that the proposed algorithm is a linear time operation and that the products obtained by parallel processing are identical to those produced by sequential processing.

Original languageEnglish
Pages (from-to)2555-2573
Number of pages19
JournalSensors (Switzerland)
Volume9
Issue number4
DOIs
Publication statusPublished - 2009 Apr 1

Fingerprint

airborne lasers
Lasers
grids
Scanning
scanning
Processing
linearity
interpolation
central processing units
products
Interpolation

All Science Journal Classification (ASJC) codes

  • Analytical Chemistry
  • Atomic and Molecular Physics, and Optics
  • Biochemistry
  • Instrumentation
  • Electrical and Electronic Engineering

Cite this

@article{2237467a0b464e2fa92019d1a6b0cb9f,
title = "Parallel processing method for airborne laser scanning data using a PC cluster and a virtual grid",
abstract = "In this study, a parallel processing method using a PC cluster and a virtual grid is proposed for the fast processing of enormous amounts of airborne laser scanning (ALS) data. The method creates a raster digital surface model (DSM) by interpolating point data with inverse distance weighting (IDW), and produces a digital terrain model (DTM) by local minimum filtering of the DSM. To make a consistent comparison of performance between sequential and parallel processing approaches, the means of dealing with boundary data and of selecting interpolation centers were controlled for each processing node in parallel approach. To test the speedup, efficiency and linearity of the proposed algorithm, actual ALS data up to 134 million points were processed with a PC cluster consisting of one master node and eight slave nodes. The results showed that parallel processing provides better performance when the computational overhead, the number of processors, and the data size become large. It was verified that the proposed algorithm is a linear time operation and that the products obtained by parallel processing are identical to those produced by sequential processing.",
author = "Han, {Soo Hee} and Joon Heo and Sohn, {Hong Gyoo} and Kiyun Yu",
year = "2009",
month = "4",
day = "1",
doi = "10.3390/s90402555",
language = "English",
volume = "9",
pages = "2555--2573",
journal = "Sensors",
issn = "1424-3210",
publisher = "Multidisciplinary Digital Publishing Institute (MDPI)",
number = "4",

}

Parallel processing method for airborne laser scanning data using a PC cluster and a virtual grid. / Han, Soo Hee; Heo, Joon; Sohn, Hong Gyoo; Yu, Kiyun.

In: Sensors (Switzerland), Vol. 9, No. 4, 01.04.2009, p. 2555-2573.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Parallel processing method for airborne laser scanning data using a PC cluster and a virtual grid

AU - Han, Soo Hee

AU - Heo, Joon

AU - Sohn, Hong Gyoo

AU - Yu, Kiyun

PY - 2009/4/1

Y1 - 2009/4/1

N2 - In this study, a parallel processing method using a PC cluster and a virtual grid is proposed for the fast processing of enormous amounts of airborne laser scanning (ALS) data. The method creates a raster digital surface model (DSM) by interpolating point data with inverse distance weighting (IDW), and produces a digital terrain model (DTM) by local minimum filtering of the DSM. To make a consistent comparison of performance between sequential and parallel processing approaches, the means of dealing with boundary data and of selecting interpolation centers were controlled for each processing node in parallel approach. To test the speedup, efficiency and linearity of the proposed algorithm, actual ALS data up to 134 million points were processed with a PC cluster consisting of one master node and eight slave nodes. The results showed that parallel processing provides better performance when the computational overhead, the number of processors, and the data size become large. It was verified that the proposed algorithm is a linear time operation and that the products obtained by parallel processing are identical to those produced by sequential processing.

AB - In this study, a parallel processing method using a PC cluster and a virtual grid is proposed for the fast processing of enormous amounts of airborne laser scanning (ALS) data. The method creates a raster digital surface model (DSM) by interpolating point data with inverse distance weighting (IDW), and produces a digital terrain model (DTM) by local minimum filtering of the DSM. To make a consistent comparison of performance between sequential and parallel processing approaches, the means of dealing with boundary data and of selecting interpolation centers were controlled for each processing node in parallel approach. To test the speedup, efficiency and linearity of the proposed algorithm, actual ALS data up to 134 million points were processed with a PC cluster consisting of one master node and eight slave nodes. The results showed that parallel processing provides better performance when the computational overhead, the number of processors, and the data size become large. It was verified that the proposed algorithm is a linear time operation and that the products obtained by parallel processing are identical to those produced by sequential processing.

UR - http://www.scopus.com/inward/record.url?scp=78650871314&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=78650871314&partnerID=8YFLogxK

U2 - 10.3390/s90402555

DO - 10.3390/s90402555

M3 - Article

C2 - 22574032

AN - SCOPUS:78650871314

VL - 9

SP - 2555

EP - 2573

JO - Sensors

JF - Sensors

SN - 1424-3210

IS - 4

ER -