Socio-economic vision graph generation and handover in distributed smart camera networks

Lukas Esterle, Peter R. Lewis, Xin Yao, Bernhard Rinner

Research output: Contribution to journalArticle

Abstract

In this article we present an approach to object tracking handover in a network of smart cameras, based on self-interested autonomous agents, which exchange responsibility for tracking objects in a market mechanism, in order to maximise their own utility. A novel ant-colony inspired mechanism is used to learn the vision graph, that is, the camera neighbourhood relations, during runtime, which may then be used to optimise communication between cameras. The key benefits of our completely decentralised approach are on the one hand generating the vision graph online, enabling efficient deployment in unknown scenarios and camera network topologies, and on the other hand relying only on local information, increasing the robustness of the system. Since our market-based approach does not rely on a priori topology information, the need for any multicamera calibration can be avoided. We have evaluated our approach both in a simulation study and in network of real distributed smart cameras.

Original languageEnglish
Article number20
Number of pages24
JournalACM Transactions on Sensor Networks
Volume10
Issue number2
DOIs
Publication statusPublished - Jan 2014

Fingerprint

Cameras
Economics
Topology
Autonomous agents
Calibration
Communication

Keywords

  • ant colony
  • market-based control
  • multicamera tracking
  • smart camera networks
  • topology identification

Cite this

@article{33ae8e202f324e82b275045a3f885690,
title = "Socio-economic vision graph generation and handover in distributed smart camera networks",
abstract = "In this article we present an approach to object tracking handover in a network of smart cameras, based on self-interested autonomous agents, which exchange responsibility for tracking objects in a market mechanism, in order to maximise their own utility. A novel ant-colony inspired mechanism is used to learn the vision graph, that is, the camera neighbourhood relations, during runtime, which may then be used to optimise communication between cameras. The key benefits of our completely decentralised approach are on the one hand generating the vision graph online, enabling efficient deployment in unknown scenarios and camera network topologies, and on the other hand relying only on local information, increasing the robustness of the system. Since our market-based approach does not rely on a priori topology information, the need for any multicamera calibration can be avoided. We have evaluated our approach both in a simulation study and in network of real distributed smart cameras.",
keywords = "ant colony, market-based control, multicamera tracking, smart camera networks, topology identification",
author = "Lukas Esterle and Lewis, {Peter R.} and Xin Yao and Bernhard Rinner",
year = "2014",
month = "1",
doi = "10.1145/2530001",
language = "English",
volume = "10",
journal = "ACM Transactions on Sensor Networks",
issn = "1550-4859",
publisher = "ACM",
number = "2",

}

Socio-economic vision graph generation and handover in distributed smart camera networks. / Esterle, Lukas; Lewis, Peter R.; Yao, Xin; Rinner, Bernhard.

In: ACM Transactions on Sensor Networks, Vol. 10, No. 2, 20, 01.2014.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Socio-economic vision graph generation and handover in distributed smart camera networks

AU - Esterle, Lukas

AU - Lewis, Peter R.

AU - Yao, Xin

AU - Rinner, Bernhard

PY - 2014/1

Y1 - 2014/1

N2 - In this article we present an approach to object tracking handover in a network of smart cameras, based on self-interested autonomous agents, which exchange responsibility for tracking objects in a market mechanism, in order to maximise their own utility. A novel ant-colony inspired mechanism is used to learn the vision graph, that is, the camera neighbourhood relations, during runtime, which may then be used to optimise communication between cameras. The key benefits of our completely decentralised approach are on the one hand generating the vision graph online, enabling efficient deployment in unknown scenarios and camera network topologies, and on the other hand relying only on local information, increasing the robustness of the system. Since our market-based approach does not rely on a priori topology information, the need for any multicamera calibration can be avoided. We have evaluated our approach both in a simulation study and in network of real distributed smart cameras.

AB - In this article we present an approach to object tracking handover in a network of smart cameras, based on self-interested autonomous agents, which exchange responsibility for tracking objects in a market mechanism, in order to maximise their own utility. A novel ant-colony inspired mechanism is used to learn the vision graph, that is, the camera neighbourhood relations, during runtime, which may then be used to optimise communication between cameras. The key benefits of our completely decentralised approach are on the one hand generating the vision graph online, enabling efficient deployment in unknown scenarios and camera network topologies, and on the other hand relying only on local information, increasing the robustness of the system. Since our market-based approach does not rely on a priori topology information, the need for any multicamera calibration can be avoided. We have evaluated our approach both in a simulation study and in network of real distributed smart cameras.

KW - ant colony

KW - market-based control

KW - multicamera tracking

KW - smart camera networks

KW - topology identification

UR - http://www.scopus.com/inward/record.url?scp=84893391595&partnerID=8YFLogxK

U2 - 10.1145/2530001

DO - 10.1145/2530001

M3 - Article

VL - 10

JO - ACM Transactions on Sensor Networks

JF - ACM Transactions on Sensor Networks

SN - 1550-4859

IS - 2

M1 - 20

ER -