Multi Camera Visual Saliency Using Image Stitching

Christopher Wing Hong Ngau, Li-Minn Ang, Kah Phooi Seng

Research output: Book chapter/Published conference paperConference paper

3 Downloads (Pure)

Abstract

This paper presents and investigates two models for a multi camera configuration with visual saliency capability. Applications in various imaging fields each have a different set of detection parameters and requirements which would result in the necessity of software changes. The visual saliency capability offered by this multi camera model allows generic detection of conspicuous objects be it human or nonhuman based on simple low level features. As multiple cameras are used, an image stitching technique is employed to allow combination of Field-of-View (FoV) from different camera captures to provide apanoramic detection field. The stitching technique is also used to complement the visual saliency model in this work. In the first model, image stitching is applied to individual captures to provide a wider FoV, whereby the visual saliency algorithm would able to operate on a wide area. For the second model, visual saliency is applied to individual captures. Then, the maps are recombined based on a set of stitching parameters to reinforced salient features present in objects at the FoV overlap regions. Simulations of the two models are conducted and demonstrated for performance evaluation.
Original languageEnglish
Title of host publicationComputer communication and management
Subtitle of host publicationSelected, peer reviewed papers from the 2011 International Conference on Computer Communication and Management (ICCCM 2011)
EditorsZhang Ting
Place of PublicationSingapore
PublisherIACSIT Press
Pages93-98
Number of pages6
Volume5
ISBN (Electronic)2010-460X
ISBN (Print)9789810886363
Publication statusPublished - 2011
Event2011 International Conference on Computer Communication and Management: ICCCM 2011 - Rydges Bankstown, Sydney, Australia
Duration: 13 May 201114 May 2011
https://web.archive.org/web/20110824063735/http://www.icccm.org/

Publication series

NameInternational Proceedings of Computer Science and Information Technology

Conference

Conference2011 International Conference on Computer Communication and Management
CountryAustralia
CitySydney
Period13/05/1114/05/11
Internet address

Cite this

Ngau, C. W. H., Ang, L-M., & Seng, K. P. (2011). Multi Camera Visual Saliency Using Image Stitching. In Z. Ting (Ed.), Computer communication and management: Selected, peer reviewed papers from the 2011 International Conference on Computer Communication and Management (ICCCM 2011) (Vol. 5, pp. 93-98). (International Proceedings of Computer Science and Information Technology). Singapore: IACSIT Press.
Ngau, Christopher Wing Hong ; Ang, Li-Minn ; Seng, Kah Phooi. / Multi Camera Visual Saliency Using Image Stitching. Computer communication and management: Selected, peer reviewed papers from the 2011 International Conference on Computer Communication and Management (ICCCM 2011). editor / Zhang Ting. Vol. 5 Singapore : IACSIT Press, 2011. pp. 93-98 (International Proceedings of Computer Science and Information Technology).
@inproceedings{2569601864604945b60f69abe5b87299,
title = "Multi Camera Visual Saliency Using Image Stitching",
abstract = "This paper presents and investigates two models for a multi camera configuration with visual saliency capability. Applications in various imaging fields each have a different set of detection parameters and requirements which would result in the necessity of software changes. The visual saliency capability offered by this multi camera model allows generic detection of conspicuous objects be it human or nonhuman based on simple low level features. As multiple cameras are used, an image stitching technique is employed to allow combination of Field-of-View (FoV) from different camera captures to provide apanoramic detection field. The stitching technique is also used to complement the visual saliency model in this work. In the first model, image stitching is applied to individual captures to provide a wider FoV, whereby the visual saliency algorithm would able to operate on a wide area. For the second model, visual saliency is applied to individual captures. Then, the maps are recombined based on a set of stitching parameters to reinforced salient features present in objects at the FoV overlap regions. Simulations of the two models are conducted and demonstrated for performance evaluation.",
keywords = "image stitching, multiple cameras, panoramic saliency map, visual saliency",
author = "Ngau, {Christopher Wing Hong} and Li-Minn Ang and Seng, {Kah Phooi}",
year = "2011",
language = "English",
isbn = "9789810886363",
volume = "5",
series = "International Proceedings of Computer Science and Information Technology",
publisher = "IACSIT Press",
pages = "93--98",
editor = "Zhang Ting",
booktitle = "Computer communication and management",

}

Ngau, CWH, Ang, L-M & Seng, KP 2011, Multi Camera Visual Saliency Using Image Stitching. in Z Ting (ed.), Computer communication and management: Selected, peer reviewed papers from the 2011 International Conference on Computer Communication and Management (ICCCM 2011). vol. 5, International Proceedings of Computer Science and Information Technology, IACSIT Press, Singapore, pp. 93-98, 2011 International Conference on Computer Communication and Management, Sydney, Australia, 13/05/11.

Multi Camera Visual Saliency Using Image Stitching. / Ngau, Christopher Wing Hong; Ang, Li-Minn; Seng, Kah Phooi.

Computer communication and management: Selected, peer reviewed papers from the 2011 International Conference on Computer Communication and Management (ICCCM 2011). ed. / Zhang Ting. Vol. 5 Singapore : IACSIT Press, 2011. p. 93-98 (International Proceedings of Computer Science and Information Technology).

Research output: Book chapter/Published conference paperConference paper

TY - GEN

T1 - Multi Camera Visual Saliency Using Image Stitching

AU - Ngau, Christopher Wing Hong

AU - Ang, Li-Minn

AU - Seng, Kah Phooi

PY - 2011

Y1 - 2011

N2 - This paper presents and investigates two models for a multi camera configuration with visual saliency capability. Applications in various imaging fields each have a different set of detection parameters and requirements which would result in the necessity of software changes. The visual saliency capability offered by this multi camera model allows generic detection of conspicuous objects be it human or nonhuman based on simple low level features. As multiple cameras are used, an image stitching technique is employed to allow combination of Field-of-View (FoV) from different camera captures to provide apanoramic detection field. The stitching technique is also used to complement the visual saliency model in this work. In the first model, image stitching is applied to individual captures to provide a wider FoV, whereby the visual saliency algorithm would able to operate on a wide area. For the second model, visual saliency is applied to individual captures. Then, the maps are recombined based on a set of stitching parameters to reinforced salient features present in objects at the FoV overlap regions. Simulations of the two models are conducted and demonstrated for performance evaluation.

AB - This paper presents and investigates two models for a multi camera configuration with visual saliency capability. Applications in various imaging fields each have a different set of detection parameters and requirements which would result in the necessity of software changes. The visual saliency capability offered by this multi camera model allows generic detection of conspicuous objects be it human or nonhuman based on simple low level features. As multiple cameras are used, an image stitching technique is employed to allow combination of Field-of-View (FoV) from different camera captures to provide apanoramic detection field. The stitching technique is also used to complement the visual saliency model in this work. In the first model, image stitching is applied to individual captures to provide a wider FoV, whereby the visual saliency algorithm would able to operate on a wide area. For the second model, visual saliency is applied to individual captures. Then, the maps are recombined based on a set of stitching parameters to reinforced salient features present in objects at the FoV overlap regions. Simulations of the two models are conducted and demonstrated for performance evaluation.

KW - image stitching

KW - multiple cameras

KW - panoramic saliency map

KW - visual saliency

UR - http://www.ipcsit.com/list-26-1.html

UR - http://ipcsit.com/

M3 - Conference paper

SN - 9789810886363

VL - 5

T3 - International Proceedings of Computer Science and Information Technology

SP - 93

EP - 98

BT - Computer communication and management

A2 - Ting, Zhang

PB - IACSIT Press

CY - Singapore

ER -

Ngau CWH, Ang L-M, Seng KP. Multi Camera Visual Saliency Using Image Stitching. In Ting Z, editor, Computer communication and management: Selected, peer reviewed papers from the 2011 International Conference on Computer Communication and Management (ICCCM 2011). Vol. 5. Singapore: IACSIT Press. 2011. p. 93-98. (International Proceedings of Computer Science and Information Technology).