A Graph Theoretic Approach to Direct Processing of Sparse Unwarped Panoramic Images

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

3 Citations (Scopus)

Abstract

The use of omnidirectional cameras has had a significant impact on the success of vision systems for video surveillance and autonomous robot navigation. Typically images obtained from such cameras are transformed to sparse panoramic images that are interpolated prior to low level image processing. We present a graph theoretic approach that enables image processing techniques, principally feature extraction, to be performed directly on sparse panoramic images, avoiding the need for image interpolation. We thus aim to reduce the computational overheads of processing images arising from omnidirectional cameras, whilst retaining accuracy sufficient for application to real-time robot vision.
LanguageEnglish
Title of host publicationUnknown Host Publication
Pages1557-1560
Number of pages4
DOIs
Publication statusPublished - Oct 2006
EventIEEE International Conference on Image Processing (ICIP 2006) - Atlanta
Duration: 1 Oct 2006 → …

Conference

ConferenceIEEE International Conference on Image Processing (ICIP 2006)
Period1/10/06 → …

Fingerprint

Image processing
Cameras
Processing
Computer vision
Feature extraction
Interpolation
Navigation
Robots

Keywords

  • feature extraction
  • sparse images

Cite this

@inproceedings{de08a8a3ed0944258e81ed8ff9dcbd08,
title = "A Graph Theoretic Approach to Direct Processing of Sparse Unwarped Panoramic Images",
abstract = "The use of omnidirectional cameras has had a significant impact on the success of vision systems for video surveillance and autonomous robot navigation. Typically images obtained from such cameras are transformed to sparse panoramic images that are interpolated prior to low level image processing. We present a graph theoretic approach that enables image processing techniques, principally feature extraction, to be performed directly on sparse panoramic images, avoiding the need for image interpolation. We thus aim to reduce the computational overheads of processing images arising from omnidirectional cameras, whilst retaining accuracy sufficient for application to real-time robot vision.",
keywords = "feature extraction, sparse images",
author = "BW Scotney and SA Coleman and D Kerr",
year = "2006",
month = "10",
doi = "10.1109/ICIP.2006.312604",
language = "English",
isbn = "1-4244-0481-9",
pages = "1557--1560",
booktitle = "Unknown Host Publication",

}

Scotney, BW, Coleman, SA & Kerr, D 2006, A Graph Theoretic Approach to Direct Processing of Sparse Unwarped Panoramic Images. in Unknown Host Publication. pp. 1557-1560, IEEE International Conference on Image Processing (ICIP 2006), 1/10/06. https://doi.org/10.1109/ICIP.2006.312604

A Graph Theoretic Approach to Direct Processing of Sparse Unwarped Panoramic Images. / Scotney, BW; Coleman, SA; Kerr, D.

Unknown Host Publication. 2006. p. 1557-1560.

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

TY - GEN

T1 - A Graph Theoretic Approach to Direct Processing of Sparse Unwarped Panoramic Images

AU - Scotney, BW

AU - Coleman, SA

AU - Kerr, D

PY - 2006/10

Y1 - 2006/10

N2 - The use of omnidirectional cameras has had a significant impact on the success of vision systems for video surveillance and autonomous robot navigation. Typically images obtained from such cameras are transformed to sparse panoramic images that are interpolated prior to low level image processing. We present a graph theoretic approach that enables image processing techniques, principally feature extraction, to be performed directly on sparse panoramic images, avoiding the need for image interpolation. We thus aim to reduce the computational overheads of processing images arising from omnidirectional cameras, whilst retaining accuracy sufficient for application to real-time robot vision.

AB - The use of omnidirectional cameras has had a significant impact on the success of vision systems for video surveillance and autonomous robot navigation. Typically images obtained from such cameras are transformed to sparse panoramic images that are interpolated prior to low level image processing. We present a graph theoretic approach that enables image processing techniques, principally feature extraction, to be performed directly on sparse panoramic images, avoiding the need for image interpolation. We thus aim to reduce the computational overheads of processing images arising from omnidirectional cameras, whilst retaining accuracy sufficient for application to real-time robot vision.

KW - feature extraction

KW - sparse images

U2 - 10.1109/ICIP.2006.312604

DO - 10.1109/ICIP.2006.312604

M3 - Conference contribution

SN - 1-4244-0481-9

SP - 1557

EP - 1560

BT - Unknown Host Publication

ER -