Processing Sparse Panoramic Images via Space Variant Operators

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

The use of omni-directional cameras has become increasingly popular in vision systems for video surveillance and autonomous robot navigation. However, to date most of the research relating to omni-directional cameras has focussed on the design of the camera or the way in which to project the omni-directional image to a panoramic view rather than the processing of such images after capture. Typically images obtained from omni-directional cameras are transformed to sparse panoramic images that are interpolated to obtain a complete panoramic view prior to low level image processing. This interpolation presents a significant computational overhead with respect to real-time vision. We present an efficient design procedure for space variant feature extraction operators that can be applied to a sparse panoramic image and directly processes this sparse image. This paper highlights the reduction of the computational overheads of directly processing images arising from omni-directional cameras through efficient coding and storage, whilst retaining accuracy sufficient for application to real-time robot vision.
LanguageEnglish
Pages349-361
JournalJournal of Mathematical Imaging and Vision
Volume32
Issue number2
DOIs
Publication statusPublished - Nov 2008

Fingerprint

Cameras
Processing
Image processing
Computer vision
Feature extraction
Interpolation
Navigation
Robots

Keywords

  • Sparse images
  • Space variant operators
  • Omni-directional images

Cite this

@article{2c2eaf9f70df47009633721e41560a7c,
title = "Processing Sparse Panoramic Images via Space Variant Operators",
abstract = "The use of omni-directional cameras has become increasingly popular in vision systems for video surveillance and autonomous robot navigation. However, to date most of the research relating to omni-directional cameras has focussed on the design of the camera or the way in which to project the omni-directional image to a panoramic view rather than the processing of such images after capture. Typically images obtained from omni-directional cameras are transformed to sparse panoramic images that are interpolated to obtain a complete panoramic view prior to low level image processing. This interpolation presents a significant computational overhead with respect to real-time vision. We present an efficient design procedure for space variant feature extraction operators that can be applied to a sparse panoramic image and directly processes this sparse image. This paper highlights the reduction of the computational overheads of directly processing images arising from omni-directional cameras through efficient coding and storage, whilst retaining accuracy sufficient for application to real-time robot vision.",
keywords = "Sparse images, Space variant operators, Omni-directional images",
author = "SA Coleman and BW Scotney and D Kerr",
year = "2008",
month = "11",
doi = "10.1007/s10851-008-0107-0",
language = "English",
volume = "32",
pages = "349--361",
journal = "Journal of Mathematical Imaging and Vision",
issn = "0924-9907",
number = "2",

}

Processing Sparse Panoramic Images via Space Variant Operators. / Coleman, SA; Scotney, BW; Kerr, D.

In: Journal of Mathematical Imaging and Vision, Vol. 32, No. 2, 11.2008, p. 349-361.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Processing Sparse Panoramic Images via Space Variant Operators

AU - Coleman, SA

AU - Scotney, BW

AU - Kerr, D

PY - 2008/11

Y1 - 2008/11

N2 - The use of omni-directional cameras has become increasingly popular in vision systems for video surveillance and autonomous robot navigation. However, to date most of the research relating to omni-directional cameras has focussed on the design of the camera or the way in which to project the omni-directional image to a panoramic view rather than the processing of such images after capture. Typically images obtained from omni-directional cameras are transformed to sparse panoramic images that are interpolated to obtain a complete panoramic view prior to low level image processing. This interpolation presents a significant computational overhead with respect to real-time vision. We present an efficient design procedure for space variant feature extraction operators that can be applied to a sparse panoramic image and directly processes this sparse image. This paper highlights the reduction of the computational overheads of directly processing images arising from omni-directional cameras through efficient coding and storage, whilst retaining accuracy sufficient for application to real-time robot vision.

AB - The use of omni-directional cameras has become increasingly popular in vision systems for video surveillance and autonomous robot navigation. However, to date most of the research relating to omni-directional cameras has focussed on the design of the camera or the way in which to project the omni-directional image to a panoramic view rather than the processing of such images after capture. Typically images obtained from omni-directional cameras are transformed to sparse panoramic images that are interpolated to obtain a complete panoramic view prior to low level image processing. This interpolation presents a significant computational overhead with respect to real-time vision. We present an efficient design procedure for space variant feature extraction operators that can be applied to a sparse panoramic image and directly processes this sparse image. This paper highlights the reduction of the computational overheads of directly processing images arising from omni-directional cameras through efficient coding and storage, whilst retaining accuracy sufficient for application to real-time robot vision.

KW - Sparse images

KW - Space variant operators

KW - Omni-directional images

U2 - 10.1007/s10851-008-0107-0

DO - 10.1007/s10851-008-0107-0

M3 - Article

VL - 32

SP - 349

EP - 361

JO - Journal of Mathematical Imaging and Vision

T2 - Journal of Mathematical Imaging and Vision

JF - Journal of Mathematical Imaging and Vision

SN - 0924-9907

IS - 2

ER -