Online Zoom Selection Approaches for Coverage Redundancy in Visual Sensor Networks

Arezoo Vejdanparast, Peter R. Lewis, Lukas Esterle

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

Abstract

When a network of cameras with adjustable zoom lenses is tasked with object coverage, an important question is how to determine the optimal zoom level for each camera. While covering a smaller area allows for higher detection likelihood, overlapping fields of view introduce a redundancy which is vital to fault tolerance and acquisition of multiple perspectives of targets. In this paper, we study the coverage redundancy problem in visual sensor networks formalised as the k-coverage. We propose a resolution-based detection model that enables the exploration of the zoom level impact on the extension of coverage redundancy. Given mobile targets, we investigate the network-wide best k-coverage using global knowledge of the network. We explore the advantages and disadvantages of this approach and propose a realistic zoom adaptation model for cameras under a new zoom level proximity constraint. Further to the global approach, which aim to provide the highest possible k-coverage across the network, we study the performance of several online heuristics and learning approaches which use only local knowledge to approximate the highest k-coverage under our zoom level proximity constraint. Furthermore, we show that in many scenarios the dynamic behaviour resulting from the online learning approaches is not only computationally less expensive but also leads to a significant improvement on the level of coverage redundancy compared with heuristic approaches. This becomes even more apparent when objects follow scripted movement patterns.
Original languageEnglish
Title of host publicationProceedings of the 12th International Conference on Distributed Smart Cameras, ICDSC 2018
PublisherACM
ISBN (Print)978-1-4503-6511-6
DOIs
Publication statusPublished - 3 Sep 2018
Event12th International Conference on Distributed Smart Cameras, ICDSC 2018 - Eindhoven, Netherlands
Duration: 3 Sep 20184 Sep 2018

Conference

Conference12th International Conference on Distributed Smart Cameras, ICDSC 2018
CountryNetherlands
CityEindhoven
Period3/09/184/09/18

Fingerprint

Sensor networks
Redundancy
Cameras
Fault tolerance
Lenses

Keywords

  • Decentralised systems
  • Machine learning approaches
  • Online learning
  • Smart cameras
  • Visual sensor networks

Cite this

Vejdanparast, A., Lewis, P. R., & Esterle, L. (2018). Online Zoom Selection Approaches for Coverage Redundancy in Visual Sensor Networks. In Proceedings of the 12th International Conference on Distributed Smart Cameras, ICDSC 2018 [15] ACM. https://doi.org/10.1145/3243394.3243697
Vejdanparast, Arezoo ; Lewis, Peter R. ; Esterle, Lukas. / Online Zoom Selection Approaches for Coverage Redundancy in Visual Sensor Networks. Proceedings of the 12th International Conference on Distributed Smart Cameras, ICDSC 2018. ACM, 2018.
@inproceedings{88804c644e0f48b294704ca0699059ac,
title = "Online Zoom Selection Approaches for Coverage Redundancy in Visual Sensor Networks",
abstract = "When a network of cameras with adjustable zoom lenses is tasked with object coverage, an important question is how to determine the optimal zoom level for each camera. While covering a smaller area allows for higher detection likelihood, overlapping fields of view introduce a redundancy which is vital to fault tolerance and acquisition of multiple perspectives of targets. In this paper, we study the coverage redundancy problem in visual sensor networks formalised as the k-coverage. We propose a resolution-based detection model that enables the exploration of the zoom level impact on the extension of coverage redundancy. Given mobile targets, we investigate the network-wide best k-coverage using global knowledge of the network. We explore the advantages and disadvantages of this approach and propose a realistic zoom adaptation model for cameras under a new zoom level proximity constraint. Further to the global approach, which aim to provide the highest possible k-coverage across the network, we study the performance of several online heuristics and learning approaches which use only local knowledge to approximate the highest k-coverage under our zoom level proximity constraint. Furthermore, we show that in many scenarios the dynamic behaviour resulting from the online learning approaches is not only computationally less expensive but also leads to a significant improvement on the level of coverage redundancy compared with heuristic approaches. This becomes even more apparent when objects follow scripted movement patterns.",
keywords = "Decentralised systems, Machine learning approaches, Online learning, Smart cameras, Visual sensor networks",
author = "Arezoo Vejdanparast and Lewis, {Peter R.} and Lukas Esterle",
year = "2018",
month = "9",
day = "3",
doi = "10.1145/3243394.3243697",
language = "English",
isbn = "978-1-4503-6511-6",
booktitle = "Proceedings of the 12th International Conference on Distributed Smart Cameras, ICDSC 2018",
publisher = "ACM",
address = "United States",

}

Vejdanparast, A, Lewis, PR & Esterle, L 2018, Online Zoom Selection Approaches for Coverage Redundancy in Visual Sensor Networks. in Proceedings of the 12th International Conference on Distributed Smart Cameras, ICDSC 2018., 15, ACM, 12th International Conference on Distributed Smart Cameras, ICDSC 2018, Eindhoven, Netherlands, 3/09/18. https://doi.org/10.1145/3243394.3243697

Online Zoom Selection Approaches for Coverage Redundancy in Visual Sensor Networks. / Vejdanparast, Arezoo; Lewis, Peter R.; Esterle, Lukas.

Proceedings of the 12th International Conference on Distributed Smart Cameras, ICDSC 2018. ACM, 2018. 15.

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

TY - GEN

T1 - Online Zoom Selection Approaches for Coverage Redundancy in Visual Sensor Networks

AU - Vejdanparast, Arezoo

AU - Lewis, Peter R.

AU - Esterle, Lukas

PY - 2018/9/3

Y1 - 2018/9/3

N2 - When a network of cameras with adjustable zoom lenses is tasked with object coverage, an important question is how to determine the optimal zoom level for each camera. While covering a smaller area allows for higher detection likelihood, overlapping fields of view introduce a redundancy which is vital to fault tolerance and acquisition of multiple perspectives of targets. In this paper, we study the coverage redundancy problem in visual sensor networks formalised as the k-coverage. We propose a resolution-based detection model that enables the exploration of the zoom level impact on the extension of coverage redundancy. Given mobile targets, we investigate the network-wide best k-coverage using global knowledge of the network. We explore the advantages and disadvantages of this approach and propose a realistic zoom adaptation model for cameras under a new zoom level proximity constraint. Further to the global approach, which aim to provide the highest possible k-coverage across the network, we study the performance of several online heuristics and learning approaches which use only local knowledge to approximate the highest k-coverage under our zoom level proximity constraint. Furthermore, we show that in many scenarios the dynamic behaviour resulting from the online learning approaches is not only computationally less expensive but also leads to a significant improvement on the level of coverage redundancy compared with heuristic approaches. This becomes even more apparent when objects follow scripted movement patterns.

AB - When a network of cameras with adjustable zoom lenses is tasked with object coverage, an important question is how to determine the optimal zoom level for each camera. While covering a smaller area allows for higher detection likelihood, overlapping fields of view introduce a redundancy which is vital to fault tolerance and acquisition of multiple perspectives of targets. In this paper, we study the coverage redundancy problem in visual sensor networks formalised as the k-coverage. We propose a resolution-based detection model that enables the exploration of the zoom level impact on the extension of coverage redundancy. Given mobile targets, we investigate the network-wide best k-coverage using global knowledge of the network. We explore the advantages and disadvantages of this approach and propose a realistic zoom adaptation model for cameras under a new zoom level proximity constraint. Further to the global approach, which aim to provide the highest possible k-coverage across the network, we study the performance of several online heuristics and learning approaches which use only local knowledge to approximate the highest k-coverage under our zoom level proximity constraint. Furthermore, we show that in many scenarios the dynamic behaviour resulting from the online learning approaches is not only computationally less expensive but also leads to a significant improvement on the level of coverage redundancy compared with heuristic approaches. This becomes even more apparent when objects follow scripted movement patterns.

KW - Decentralised systems

KW - Machine learning approaches

KW - Online learning

KW - Smart cameras

KW - Visual sensor networks

UR - http://www.scopus.com/inward/record.url?scp=85056651324&partnerID=8YFLogxK

UR - https://dl.acm.org/citation.cfm?doid=3243394.3243697

U2 - 10.1145/3243394.3243697

DO - 10.1145/3243394.3243697

M3 - Conference contribution

SN - 978-1-4503-6511-6

BT - Proceedings of the 12th International Conference on Distributed Smart Cameras, ICDSC 2018

PB - ACM

ER -

Vejdanparast A, Lewis PR, Esterle L. Online Zoom Selection Approaches for Coverage Redundancy in Visual Sensor Networks. In Proceedings of the 12th International Conference on Distributed Smart Cameras, ICDSC 2018. ACM. 2018. 15 https://doi.org/10.1145/3243394.3243697