Laplacian Operators for Direct Processing of Range Data

SA Coleman, S Suganthan, BW Scotney

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

2 Citations (Scopus)

Abstract

The use of range data has become prominent in the field of computer vision. Due to the irregular nature of range data that occurs with a number of sensors, feature extraction is a complex and challenging problem. Feature extraction techniques for range images are often based on scan line data approximations and hence do not employ exact data locations. We present a finite element based approach to the development of Laplacian operators that can be applied to both regularly or irregularly distributed range data. We demonstrate that the feature maps generated using our approach on range data are much less susceptible to noise than the traditional use of Laplacian operators on intensity images.
LanguageEnglish
Title of host publicationUnknown Host Publication
PagesV-261-V-264
Number of pages4
DOIs
Publication statusPublished - Sep 2007
EventIEEE International Conference on Image Processing (ICIP 2007) - San Antonio, Texas
Duration: 1 Sep 2007 → …

Conference

ConferenceIEEE International Conference on Image Processing (ICIP 2007)
Period1/09/07 → …

Fingerprint

Feature extraction
Processing
Computer vision
Sensors

Keywords

  • Edge detection
  • Laplacian operators
  • Range Images

Cite this

Coleman, SA ; Suganthan, S ; Scotney, BW. / Laplacian Operators for Direct Processing of Range Data. Unknown Host Publication. 2007. pp. V-261-V-264
@inproceedings{db036737236e4528a3d5289199b09e05,
title = "Laplacian Operators for Direct Processing of Range Data",
abstract = "The use of range data has become prominent in the field of computer vision. Due to the irregular nature of range data that occurs with a number of sensors, feature extraction is a complex and challenging problem. Feature extraction techniques for range images are often based on scan line data approximations and hence do not employ exact data locations. We present a finite element based approach to the development of Laplacian operators that can be applied to both regularly or irregularly distributed range data. We demonstrate that the feature maps generated using our approach on range data are much less susceptible to noise than the traditional use of Laplacian operators on intensity images.",
keywords = "Edge detection, Laplacian operators, Range Images",
author = "SA Coleman and S Suganthan and BW Scotney",
year = "2007",
month = "9",
doi = "10.1109/ICIP.2007.4379815",
language = "English",
pages = "V--261--V--264",
booktitle = "Unknown Host Publication",

}

Coleman, SA, Suganthan, S & Scotney, BW 2007, Laplacian Operators for Direct Processing of Range Data. in Unknown Host Publication. pp. V-261-V-264, IEEE International Conference on Image Processing (ICIP 2007), 1/09/07. https://doi.org/10.1109/ICIP.2007.4379815

Laplacian Operators for Direct Processing of Range Data. / Coleman, SA; Suganthan, S; Scotney, BW.

Unknown Host Publication. 2007. p. V-261-V-264.

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

TY - GEN

T1 - Laplacian Operators for Direct Processing of Range Data

AU - Coleman, SA

AU - Suganthan, S

AU - Scotney, BW

PY - 2007/9

Y1 - 2007/9

N2 - The use of range data has become prominent in the field of computer vision. Due to the irregular nature of range data that occurs with a number of sensors, feature extraction is a complex and challenging problem. Feature extraction techniques for range images are often based on scan line data approximations and hence do not employ exact data locations. We present a finite element based approach to the development of Laplacian operators that can be applied to both regularly or irregularly distributed range data. We demonstrate that the feature maps generated using our approach on range data are much less susceptible to noise than the traditional use of Laplacian operators on intensity images.

AB - The use of range data has become prominent in the field of computer vision. Due to the irregular nature of range data that occurs with a number of sensors, feature extraction is a complex and challenging problem. Feature extraction techniques for range images are often based on scan line data approximations and hence do not employ exact data locations. We present a finite element based approach to the development of Laplacian operators that can be applied to both regularly or irregularly distributed range data. We demonstrate that the feature maps generated using our approach on range data are much less susceptible to noise than the traditional use of Laplacian operators on intensity images.

KW - Edge detection

KW - Laplacian operators

KW - Range Images

U2 - 10.1109/ICIP.2007.4379815

DO - 10.1109/ICIP.2007.4379815

M3 - Conference contribution

SP - V-261-V-264

BT - Unknown Host Publication

ER -