Scalable Operators for Feature Extraction on 3-D Data

S Suganthan, SA Coleman, BW Scotney

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

3 Citations (Scopus)

Abstract

Real-time extraction of features from range images can play an important role in robotic vision tasks such as localisation and navigation. Feature driven segmentation of range images has been primarily used for 3D object recognition, and hence the accuracy of the detected features is a prominent issue. Feature extraction on range data has proven to be a more complex problem than on intensity images due to both the irregular distribution of range images. This paper presents a general approach to the development of scalable derivative operators using a finite element framework that can be applied directly to processing regularly or irregularly distributed range image data. The gradient operators of varying scales are evaluated with respect to their performance on regular and irregular grids.
LanguageEnglish
Title of host publicationUnknown Host Publication
Place of PublicationBerlin / Heidelberg
Pages263-272
Number of pages10
DOIs
Publication statusPublished - Mar 2008
EventEuropean Robotics Symposium 2008 (Euros 2008) - Prague
Duration: 1 Mar 2008 → …

Conference

ConferenceEuropean Robotics Symposium 2008 (Euros 2008)
Period1/03/08 → …

Fingerprint

Object recognition
Feature extraction
Navigation
Robotics
Derivatives
Processing

Cite this

Suganthan, S., Coleman, SA., & Scotney, BW. (2008). Scalable Operators for Feature Extraction on 3-D Data. In Unknown Host Publication (pp. 263-272). Berlin / Heidelberg. https://doi.org/10.1007/978-3-540-78317-6_27
Suganthan, S ; Coleman, SA ; Scotney, BW. / Scalable Operators for Feature Extraction on 3-D Data. Unknown Host Publication. Berlin / Heidelberg, 2008. pp. 263-272
@inproceedings{8ff14640661b4195bad9d15e3bc03bf2,
title = "Scalable Operators for Feature Extraction on 3-D Data",
abstract = "Real-time extraction of features from range images can play an important role in robotic vision tasks such as localisation and navigation. Feature driven segmentation of range images has been primarily used for 3D object recognition, and hence the accuracy of the detected features is a prominent issue. Feature extraction on range data has proven to be a more complex problem than on intensity images due to both the irregular distribution of range images. This paper presents a general approach to the development of scalable derivative operators using a finite element framework that can be applied directly to processing regularly or irregularly distributed range image data. The gradient operators of varying scales are evaluated with respect to their performance on regular and irregular grids.",
author = "S Suganthan and SA Coleman and BW Scotney",
year = "2008",
month = "3",
doi = "10.1007/978-3-540-78317-6_27",
language = "English",
pages = "263--272",
booktitle = "Unknown Host Publication",

}

Suganthan, S, Coleman, SA & Scotney, BW 2008, Scalable Operators for Feature Extraction on 3-D Data. in Unknown Host Publication. Berlin / Heidelberg, pp. 263-272, European Robotics Symposium 2008 (Euros 2008), 1/03/08. https://doi.org/10.1007/978-3-540-78317-6_27

Scalable Operators for Feature Extraction on 3-D Data. / Suganthan, S; Coleman, SA; Scotney, BW.

Unknown Host Publication. Berlin / Heidelberg, 2008. p. 263-272.

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

TY - GEN

T1 - Scalable Operators for Feature Extraction on 3-D Data

AU - Suganthan, S

AU - Coleman, SA

AU - Scotney, BW

PY - 2008/3

Y1 - 2008/3

N2 - Real-time extraction of features from range images can play an important role in robotic vision tasks such as localisation and navigation. Feature driven segmentation of range images has been primarily used for 3D object recognition, and hence the accuracy of the detected features is a prominent issue. Feature extraction on range data has proven to be a more complex problem than on intensity images due to both the irregular distribution of range images. This paper presents a general approach to the development of scalable derivative operators using a finite element framework that can be applied directly to processing regularly or irregularly distributed range image data. The gradient operators of varying scales are evaluated with respect to their performance on regular and irregular grids.

AB - Real-time extraction of features from range images can play an important role in robotic vision tasks such as localisation and navigation. Feature driven segmentation of range images has been primarily used for 3D object recognition, and hence the accuracy of the detected features is a prominent issue. Feature extraction on range data has proven to be a more complex problem than on intensity images due to both the irregular distribution of range images. This paper presents a general approach to the development of scalable derivative operators using a finite element framework that can be applied directly to processing regularly or irregularly distributed range image data. The gradient operators of varying scales are evaluated with respect to their performance on regular and irregular grids.

UR - http://dx.doi.org/10.1007/978-3-540-78317-6

UR - http://dx.doi.org/10.1007/978-3-540-78317-6

U2 - 10.1007/978-3-540-78317-6_27

DO - 10.1007/978-3-540-78317-6_27

M3 - Conference contribution

SP - 263

EP - 272

BT - Unknown Host Publication

CY - Berlin / Heidelberg

ER -

Suganthan S, Coleman SA, Scotney BW. Scalable Operators for Feature Extraction on 3-D Data. In Unknown Host Publication. Berlin / Heidelberg. 2008. p. 263-272 https://doi.org/10.1007/978-3-540-78317-6_27