Gradient Operators for Feature Extraction and Characterisation in Range Images

SA Coleman, Shanmugalingam Suganthan, BW Scotney

Research output: Contribution to journalArticle

16 Citations (Scopus)

Abstract

In recent years range images have become prominent in computer vision applications as they provide an almost 3-D description of an otherwise 2-D scene and are suitable for computer vision tasks such as localisation and navigation. Feature extraction from range images has proven to be a complex problem; developing operators that can characterise features in a range image, such as step, crease, or smooth edges, is challenging, due to both the irregular spatial distribution of range image data and the nature of the features themselves. We present an adaptive design procedure for first order gradient operators that can automatically change shape to accommodate irregular data distribution; through appropriate analysis of the output responses, we show that the operators can also be specialised to characterise particular types of range image features. Hence the method is appropriate for direct use on range image data without re-sampling
LanguageEnglish
Pages1028-1040
JournalPattern Recognition Letters
Volume31
Issue number9
DOIs
Publication statusPublished - 23 Apr 2010

Fingerprint

Computer vision
Feature extraction
Spatial distribution
Navigation
Sampling

Cite this

@article{fa1d56613623410bb2571f335320907d,
title = "Gradient Operators for Feature Extraction and Characterisation in Range Images",
abstract = "In recent years range images have become prominent in computer vision applications as they provide an almost 3-D description of an otherwise 2-D scene and are suitable for computer vision tasks such as localisation and navigation. Feature extraction from range images has proven to be a complex problem; developing operators that can characterise features in a range image, such as step, crease, or smooth edges, is challenging, due to both the irregular spatial distribution of range image data and the nature of the features themselves. We present an adaptive design procedure for first order gradient operators that can automatically change shape to accommodate irregular data distribution; through appropriate analysis of the output responses, we show that the operators can also be specialised to characterise particular types of range image features. Hence the method is appropriate for direct use on range image data without re-sampling",
author = "SA Coleman and Shanmugalingam Suganthan and BW Scotney",
year = "2010",
month = "4",
day = "23",
doi = "10.1016/j.patrec.2009.12.022",
language = "English",
volume = "31",
pages = "1028--1040",
journal = "Pattern Recognition Letters",
issn = "0167-8655",
publisher = "Elsevier",
number = "9",

}

Gradient Operators for Feature Extraction and Characterisation in Range Images. / Coleman, SA; Suganthan, Shanmugalingam; Scotney, BW.

In: Pattern Recognition Letters, Vol. 31, No. 9, 23.04.2010, p. 1028-1040.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Gradient Operators for Feature Extraction and Characterisation in Range Images

AU - Coleman, SA

AU - Suganthan, Shanmugalingam

AU - Scotney, BW

PY - 2010/4/23

Y1 - 2010/4/23

N2 - In recent years range images have become prominent in computer vision applications as they provide an almost 3-D description of an otherwise 2-D scene and are suitable for computer vision tasks such as localisation and navigation. Feature extraction from range images has proven to be a complex problem; developing operators that can characterise features in a range image, such as step, crease, or smooth edges, is challenging, due to both the irregular spatial distribution of range image data and the nature of the features themselves. We present an adaptive design procedure for first order gradient operators that can automatically change shape to accommodate irregular data distribution; through appropriate analysis of the output responses, we show that the operators can also be specialised to characterise particular types of range image features. Hence the method is appropriate for direct use on range image data without re-sampling

AB - In recent years range images have become prominent in computer vision applications as they provide an almost 3-D description of an otherwise 2-D scene and are suitable for computer vision tasks such as localisation and navigation. Feature extraction from range images has proven to be a complex problem; developing operators that can characterise features in a range image, such as step, crease, or smooth edges, is challenging, due to both the irregular spatial distribution of range image data and the nature of the features themselves. We present an adaptive design procedure for first order gradient operators that can automatically change shape to accommodate irregular data distribution; through appropriate analysis of the output responses, we show that the operators can also be specialised to characterise particular types of range image features. Hence the method is appropriate for direct use on range image data without re-sampling

U2 - 10.1016/j.patrec.2009.12.022

DO - 10.1016/j.patrec.2009.12.022

M3 - Article

VL - 31

SP - 1028

EP - 1040

JO - Pattern Recognition Letters

T2 - Pattern Recognition Letters

JF - Pattern Recognition Letters

SN - 0167-8655

IS - 9

ER -